diff options
202 files changed, 2540 insertions, 1696 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index dd10b51b4e65..5405f7aecefc 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -32,8 +32,6 @@ DocBook/ - directory with DocBook templates etc. for kernel documentation. HOWTO - the process and procedures of how to do Linux kernel development. -IO-mapping.txt - - how to access I/O mapped memory from within device drivers. IPMI.txt - info on Linux Intelligent Platform Management Interface (IPMI) Driver. IRQ-affinity.txt @@ -84,6 +82,8 @@ blockdev/ - info on block devices & drivers btmrvl.txt - info on Marvell Bluetooth driver usage. +bus-virt-phys-mapping.txt + - how to access I/O mapped memory from within device drivers. cachetlb.txt - describes the cache/TLB flushing interfaces Linux uses. cdrom/ @@ -168,6 +168,8 @@ initrd.txt - how to use the RAM disk as an initial/temporary root filesystem. input/ - info on Linux input device support. +io-mapping.txt + - description of io_mapping functions in linux/io-mapping.h io_ordering.txt - info on ordering I/O writes to memory-mapped addresses. ioctl/ diff --git a/Documentation/IO-mapping.txt b/Documentation/bus-virt-phys-mapping.txt index 1b5aa10df845..1b5aa10df845 100644 --- a/Documentation/IO-mapping.txt +++ b/Documentation/bus-virt-phys-mapping.txt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82d6aeb5228f..4ddb58df081e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1265,7 +1265,7 @@ and is between 256 and 4096 characters. It is defined in the file If there are multiple matching configurations changing the same attribute, the last one is used. - lmb=debug [KNL] Enable lmb debug messages. + memblock=debug [KNL] Enable memblock debug messages. load_ramdisk= [RAM] List of ramdisks to load from floppy See Documentation/blockdev/ramdisk.txt. diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index a0162fa94564..7e79503ab89b 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -40,12 +40,12 @@ static inline void atomic_add(int i, atomic_t *v) int result; __asm__ __volatile__("@ atomic_add\n" -"1: ldrex %0, [%2]\n" -" add %0, %0, %3\n" -" strex %1, %0, [%2]\n" +"1: ldrex %0, [%3]\n" +" add %0, %0, %4\n" +" strex %1, %0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "Ir" (i) : "cc"); } @@ -58,12 +58,12 @@ static inline int atomic_add_return(int i, atomic_t *v) smp_mb(); __asm__ __volatile__("@ atomic_add_return\n" -"1: ldrex %0, [%2]\n" -" add %0, %0, %3\n" -" strex %1, %0, [%2]\n" +"1: ldrex %0, [%3]\n" +" add %0, %0, %4\n" +" strex %1, %0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "Ir" (i) : "cc"); @@ -78,12 +78,12 @@ static inline void atomic_sub(int i, atomic_t *v) int result; __asm__ __volatile__("@ atomic_sub\n" -"1: ldrex %0, [%2]\n" -" sub %0, %0, %3\n" -" strex %1, %0, [%2]\n" +"1: ldrex %0, [%3]\n" +" sub %0, %0, %4\n" +" strex %1, %0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "Ir" (i) : "cc"); } @@ -96,12 +96,12 @@ static inline int atomic_sub_return(int i, atomic_t *v) smp_mb(); __asm__ __volatile__("@ atomic_sub_return\n" -"1: ldrex %0, [%2]\n" -" sub %0, %0, %3\n" -" strex %1, %0, [%2]\n" +"1: ldrex %0, [%3]\n" +" sub %0, %0, %4\n" +" strex %1, %0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "Ir" (i) : "cc"); @@ -118,11 +118,11 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) do { __asm__ __volatile__("@ atomic_cmpxchg\n" - "ldrex %1, [%2]\n" + "ldrex %1, [%3]\n" "mov %0, #0\n" - "teq %1, %3\n" - "strexeq %0, %4, [%2]\n" - : "=&r" (res), "=&r" (oldval) + "teq %1, %4\n" + "strexeq %0, %5, [%3]\n" + : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter) : "r" (&ptr->counter), "Ir" (old), "r" (new) : "cc"); } while (res); @@ -137,12 +137,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr) unsigned long tmp, tmp2; __asm__ __volatile__("@ atomic_clear_mask\n" -"1: ldrex %0, [%2]\n" -" bic %0, %0, %3\n" -" strex %1, %0, [%2]\n" +"1: ldrex %0, [%3]\n" +" bic %0, %0, %4\n" +" strex %1, %0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (tmp), "=&r" (tmp2) + : "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr) : "r" (addr), "Ir" (mask) : "cc"); } @@ -249,7 +249,7 @@ static inline u64 atomic64_read(atomic64_t *v) __asm__ __volatile__("@ atomic64_read\n" " ldrexd %0, %H0, [%1]" : "=&r" (result) - : "r" (&v->counter) + : "r" (&v->counter), "Qo" (v->counter) ); return result; @@ -260,11 +260,11 @@ static inline void atomic64_set(atomic64_t *v, u64 i) u64 tmp; __asm__ __volatile__("@ atomic64_set\n" -"1: ldrexd %0, %H0, [%1]\n" -" strexd %0, %2, %H2, [%1]\n" +"1: ldrexd %0, %H0, [%2]\n" +" strexd %0, %3, %H3, [%2]\n" " teq %0, #0\n" " bne 1b" - : "=&r" (tmp) + : "=&r" (tmp), "=Qo" (v->counter) : "r" (&v->counter), "r" (i) : "cc"); } @@ -275,13 +275,13 @@ static inline void atomic64_add(u64 i, atomic64_t *v) unsigned long tmp; __asm__ __volatile__("@ atomic64_add\n" -"1: ldrexd %0, %H0, [%2]\n" -" adds %0, %0, %3\n" -" adc %H0, %H0, %H3\n" -" strexd %1, %0, %H0, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" +" adds %0, %0, %4\n" +" adc %H0, %H0, %H4\n" +" strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (i) : "cc"); } @@ -294,13 +294,13 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v) smp_mb(); __asm__ __volatile__("@ atomic64_add_return\n" -"1: ldrexd %0, %H0, [%2]\n" -" adds %0, %0, %3\n" -" adc %H0, %H0, %H3\n" -" strexd %1, %0, %H0, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" +" adds %0, %0, %4\n" +" adc %H0, %H0, %H4\n" +" strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (i) : "cc"); @@ -315,13 +315,13 @@ static inline void atomic64_sub(u64 i, atomic64_t *v) unsigned long tmp; __asm__ __volatile__("@ atomic64_sub\n" -"1: ldrexd %0, %H0, [%2]\n" -" subs %0, %0, %3\n" -" sbc %H0, %H0, %H3\n" -" strexd %1, %0, %H0, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" +" subs %0, %0, %4\n" +" sbc %H0, %H0, %H4\n" +" strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (i) : "cc"); } @@ -334,13 +334,13 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) smp_mb(); __asm__ __volatile__("@ atomic64_sub_return\n" -"1: ldrexd %0, %H0, [%2]\n" -" subs %0, %0, %3\n" -" sbc %H0, %H0, %H3\n" -" strexd %1, %0, %H0, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" +" subs %0, %0, %4\n" +" sbc %H0, %H0, %H4\n" +" strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (i) : "cc"); @@ -358,12 +358,12 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new) do { __asm__ __volatile__("@ atomic64_cmpxchg\n" - "ldrexd %1, %H1, [%2]\n" + "ldrexd %1, %H1, [%3]\n" "mov %0, #0\n" - "teq %1, %3\n" - "teqeq %H1, %H3\n" - "strexdeq %0, %4, %H4, [%2]" - : "=&r" (res), "=&r" (oldval) + "teq %1, %4\n" + "teqeq %H1, %H4\n" + "strexdeq %0, %5, %H5, [%3]" + : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter) : "r" (&ptr->counter), "r" (old), "r" (new) : "cc"); } while (res); @@ -381,11 +381,11 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new) smp_mb(); __asm__ __volatile__("@ atomic64_xchg\n" -"1: ldrexd %0, %H0, [%2]\n" -" strexd %1, %3, %H3, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" +" strexd %1, %4, %H4, [%3]\n" " teq %1, #0\n" " bne 1b" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (ptr->counter) : "r" (&ptr->counter), "r" (new) : "cc"); @@ -402,16 +402,16 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v) smp_mb(); __asm__ __volatile__("@ atomic64_dec_if_positive\n" -"1: ldrexd %0, %H0, [%2]\n" +"1: ldrexd %0, %H0, [%3]\n" " subs %0, %0, #1\n" " sbc %H0, %H0, #0\n" " teq %H0, #0\n" " bmi 2f\n" -" strexd %1, %0, %H0, [%2]\n" +" strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b\n" "2:" - : "=&r" (result), "=&r" (tmp) + : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter) : "cc"); @@ -429,18 +429,18 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) smp_mb(); __asm__ __volatile__("@ atomic64_add_unless\n" -"1: ldrexd %0, %H0, [%3]\n" -" teq %0, %4\n" -" teqeq %H0, %H4\n" +"1: ldrexd %0, %H0, [%4]\n" +" teq %0, %5\n" +" teqeq %H0, %H5\n" " moveq %1, #0\n" " beq 2f\n" -" adds %0, %0, %5\n" -" adc %H0, %H0, %H5\n" -" strexd %2, %0, %H0, [%3]\n" +" adds %0, %0, %6\n" +" adc %H0, %H0, %H6\n" +" strexd %2, %0, %H0, [%4]\n" " teq %2, #0\n" " bne 1b\n" "2:" - : "=&r" (val), "=&r" (ret), "=&r" (tmp) + : "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (u), "r" (a) : "cc"); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 7ee48e7f8f31..3fd7861de4d1 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -162,8 +162,6 @@ ENDPROC(__und_invalid) @ r4 - orig_r0 (see pt_regs definition in ptrace.h) @ stmia r5, {r0 - r4} - - asm_trace_hardirqs_off .endm .align 5 @@ -204,7 +202,7 @@ __dabt_svc: @ @ IRQs off again before pulling preserved data off the stack @ - disable_irq + disable_irq_notrace @ @ restore SPSR and restart the instruction @@ -218,6 +216,9 @@ ENDPROC(__dabt_svc) __irq_svc: svc_entry +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif #ifdef CONFIG_PREEMPT get_thread_info tsk ldr r8, [tsk, #TI_PREEMPT] @ get preempt count @@ -291,7 +292,7 @@ __und_svc: @ @ IRQs off again before pulling preserved data off the stack @ -1: disable_irq +1: disable_irq_notrace @ @ restore SPSR and restart the instruction @@ -327,7 +328,7 @@ __pabt_svc: @ @ IRQs off again before pulling preserved data off the stack @ - disable_irq + disable_irq_notrace @ @ restore SPSR and restart the instruction @@ -393,8 +394,6 @@ ENDPROC(__pabt_svc) @ Clear FP to mark the first stack frame @ zero_fp - - asm_trace_hardirqs_off .endm .macro kuser_cmpxchg_check @@ -465,9 +464,6 @@ __irq_usr: THUMB( movne r0, #0 ) THUMB( strne r0, [r0] ) #endif -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on -#endif mov why, #0 b ret_to_user diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c index da1f94906a4e..8bccbfa693ff 100644 --- a/arch/arm/kernel/kprobes-decode.c +++ b/arch/arm/kernel/kprobes-decode.c @@ -583,13 +583,14 @@ static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs) { insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0]; kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; union reg_pair fnr; int rd = (insn >> 12) & 0xf; int rn = (insn >> 16) & 0xf; int rm = insn & 0xf; long rdv; - long rnv = regs->uregs[rn]; - long rmv = regs->uregs[rm]; /* rm/rmv may be invalid, don't care. */ + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; long cpsr = regs->ARM_cpsr; fnr.dr = insnslot_llret_3arg_rflags(rnv, 0, rmv, cpsr, i_fn); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index acf5e6fdb6dc..a4a9cc88bec7 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -351,17 +351,21 @@ EXPORT_SYMBOL(dump_fpu); /* * Shuffle the argument into the correct register before calling the - * thread function. r1 is the thread argument, r2 is the pointer to - * the thread function, and r3 points to the exit function. + * thread function. r4 is the thread argument, r5 is the pointer to + * the thread function, and r6 points to the exit function. */ extern void kernel_thread_helper(void); asm( ".pushsection .text\n" " .align\n" " .type kernel_thread_helper, #function\n" "kernel_thread_helper:\n" -" mov r0, r1\n" -" mov lr, r3\n" -" mov pc, r2\n" +#ifdef CONFIG_TRACE_IRQFLAGS +" bl trace_hardirqs_on\n" +#endif +" msr cpsr_c, r7\n" +" mov r0, r4\n" +" mov lr, r6\n" +" mov pc, r5\n" " .size kernel_thread_helper, . - kernel_thread_helper\n" " .popsection"); @@ -391,11 +395,12 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) memset(®s, 0, sizeof(regs)); - regs.ARM_r1 = (unsigned long)arg; - regs.ARM_r2 = (unsigned long)fn; - regs.ARM_r3 = (unsigned long)kernel_thread_exit; + regs.ARM_r4 = (unsigned long)arg; + regs.ARM_r5 = (unsigned long)fn; + regs.ARM_r6 = (unsigned long)kernel_thread_exit; + regs.ARM_r7 = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE; regs.ARM_pc = (unsigned long)kernel_thread_helper; - regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE; + regs.ARM_cpsr = regs.ARM_r7 | PSR_I_BIT; return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); } diff --git a/arch/arm/mach-ux500/clock.c b/arch/arm/mach-ux500/clock.c index fe84b9021c7a..0a1318fc8e2b 100644 --- a/arch/arm/mach-ux500/clock.c +++ b/arch/arm/mach-ux500/clock.c @@ -131,7 +131,7 @@ EXPORT_SYMBOL(clk_disable); */ static unsigned long clk_mtu_get_rate(struct clk *clk) { - void __iomem *addr = __io_address(U8500_PRCMU_BASE) + void __iomem *addr = __io_address(UX500_PRCMU_BASE) + PRCM_TCR; u32 tcr = readl(addr); int mtu = (int) clk->data; diff --git a/arch/arm/mach-ux500/cpu-db5500.c b/arch/arm/mach-ux500/cpu-db5500.c index 6a3ac4539f16..e9278f6d67aa 100644 --- a/arch/arm/mach-ux500/cpu-db5500.c +++ b/arch/arm/mach-ux500/cpu-db5500.c @@ -21,6 +21,7 @@ static struct map_desc u5500_io_desc[] __initdata = { __IO_DEV_DESC(U5500_GPIO2_BASE, SZ_4K), __IO_DEV_DESC(U5500_GPIO3_BASE, SZ_4K), __IO_DEV_DESC(U5500_GPIO4_BASE, SZ_4K), + __IO_DEV_DESC(U5500_PRCMU_BASE, SZ_4K), }; static struct platform_device *u5500_platform_devs[] __initdata = { diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 9819869d2bc9..df4955885b21 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -218,6 +218,9 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) cache_id = readl(l2x0_base + L2X0_CACHE_ID); aux = readl(l2x0_base + L2X0_AUX_CTRL); + aux &= aux_mask; + aux |= aux_val; + /* Determine the number of ways */ switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: @@ -248,8 +251,6 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) if (!(readl(l2x0_base + L2X0_CTRL) & 1)) { /* l2x0 controller is disabled */ - aux &= aux_mask; - aux |= aux_val; writel(aux, l2x0_base + L2X0_AUX_CTRL); l2x0_inv_all(); diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 8f10d24ae625..48cbdcb6bbd4 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Sat May 1 10:36:42 2010 +# Last update: Mon Jul 12 21:10:14 2010 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -1994,7 +1994,7 @@ spark MACH_SPARK SPARK 2002 benzina MACH_BENZINA BENZINA 2003 blaze MACH_BLAZE BLAZE 2004 linkstation_ls_hgl MACH_LINKSTATION_LS_HGL LINKSTATION_LS_HGL 2005 -htckovsky MACH_HTCVENUS HTCVENUS 2006 +htckovsky MACH_HTCKOVSKY HTCKOVSKY 2006 sony_prs505 MACH_SONY_PRS505 SONY_PRS505 2007 hanlin_v3 MACH_HANLIN_V3 HANLIN_V3 2008 sapphira MACH_SAPPHIRA SAPPHIRA 2009 @@ -2609,7 +2609,7 @@ fujitsu_tvstbsoc1 MACH_FUJITSU_TVSTBSOC1 FUJITSU_TVSTBSOC1 2621 lexikon MACH_LEXIKON LEXIKON 2622 mini2440v2 MACH_MINI2440V2 MINI2440V2 2623 icontrol MACH_ICONTROL ICONTROL 2624 -sheevad MACH_SHEEVAD SHEEVAD 2625 +gplugd MACH_SHEEVAD SHEEVAD 2625 qsd8x50a_st1_1 MACH_QSD8X50A_ST1_1 QSD8X50A_ST1_1 2626 qsd8x50a_st1_5 MACH_QSD8X50A_ST1_5 QSD8X50A_ST1_5 2627 bee MACH_BEE BEE 2628 @@ -2804,3 +2804,149 @@ teton_bga MACH_TETON_BGA TETON_BGA 2816 snapper9g45 MACH_SNAPPER9G45 SNAPPER9G45 2817 tam3517 MACH_TAM3517 TAM3517 2818 pdc100 MACH_PDC100 PDC100 2819 +eukrea_cpuimx25sd MACH_EUKREA_CPUIMX25 EUKREA_CPUIMX25 2820 +eukrea_cpuimx35sd MACH_EUKREA_CPUIMX35 EUKREA_CPUIMX35 2821 +eukrea_cpuimx51sd MACH_EUKREA_CPUIMX51SD EUKREA_CPUIMX51SD 2822 +eukrea_cpuimx51 MACH_EUKREA_CPUIMX51 EUKREA_CPUIMX51 2823 +p565 MACH_P565 P565 2824 +acer_a4 MACH_ACER_A4 ACER_A4 2825 +davinci_dm368_bip MACH_DAVINCI_DM368_BIP DAVINCI_DM368_BIP 2826 +eshare MACH_ESHARE ESHARE 2827 +hw_omapl138_europa MACH_HW_OMAPL138_EUROPA HW_OMAPL138_EUROPA 2828 +wlbargn MACH_WLBARGN WLBARGN 2829 +bm170 MACH_BM170 BM170 2830 +netspace_mini_v2 MACH_NETSPACE_MINI_V2 NETSPACE_MINI_V2 2831 +netspace_plug_v2 MACH_NETSPACE_PLUG_V2 NETSPACE_PLUG_V2 2832 +siemens_l1 MACH_SIEMENS_L1 SIEMENS_L1 2833 +elv_lcu1 MACH_ELV_LCU1 ELV_LCU1 2834 +mcu1 MACH_MCU1 MCU1 2835 +omap3_tao3530 MACH_OMAP3_TAO3530 OMAP3_TAO3530 2836 +omap3_pcutouch MACH_OMAP3_PCUTOUCH OMAP3_PCUTOUCH 2837 +smdkc210 MACH_SMDKC210 SMDKC210 2838 +omap3_braillo MACH_OMAP3_BRAILLO OMAP3_BRAILLO 2839 +spyplug MACH_SPYPLUG SPYPLUG 2840 +ginger MACH_GINGER GINGER 2841 +tny_t3530 MACH_TNY_T3530 TNY_T3530 2842 +pca102 MACH_PCA102 PCA102 2843 +spade MACH_SPADE SPADE 2844 +mxc25_topaz MACH_MXC25_TOPAZ MXC25_TOPAZ 2845 +t5325 MACH_T5325 T5325 2846 +gw2361 MACH_GW2361 GW2361 2847 +elog MACH_ELOG ELOG 2848 +income MACH_INCOME INCOME 2849 +bcm589x MACH_BCM589X BCM589X 2850 +etna MACH_ETNA ETNA 2851 +hawks MACH_HAWKS HAWKS 2852 +meson MACH_MESON MESON 2853 +xsbase255 MACH_XSBASE255 XSBASE255 2854 +pvm2030 MACH_PVM2030 PVM2030 2855 +mioa502 MACH_MIOA502 MIOA502 2856 +vvbox_sdorig2 MACH_VVBOX_SDORIG2 VVBOX_SDORIG2 2857 +vvbox_sdlite2 MACH_VVBOX_SDLITE2 VVBOX_SDLITE2 2858 +vvbox_sdpro4 MACH_VVBOX_SDPRO4 VVBOX_SDPRO4 2859 +htc_spv_m700 MACH_HTC_SPV_M700 HTC_SPV_M700 2860 +mx257sx MACH_MX257SX MX257SX 2861 +goni MACH_GONI GONI 2862 +msm8x55_svlte_ffa MACH_MSM8X55_SVLTE_FFA MSM8X55_SVLTE_FFA 2863 +msm8x55_svlte_surf MACH_MSM8X55_SVLTE_SURF MSM8X55_SVLTE_SURF 2864 +quickstep MACH_QUICKSTEP QUICKSTEP 2865 +dmw96 MACH_DMW96 DMW96 2866 +hammerhead MACH_HAMMERHEAD HAMMERHEAD 2867 +trident MACH_TRIDENT TRIDENT 2868 +lightning MACH_LIGHTNING LIGHTNING 2869 +iconnect MACH_ICONNECT ICONNECT 2870 +autobot MACH_AUTOBOT AUTOBOT 2871 +coconut MACH_COCONUT COCONUT 2872 +durian MACH_DURIAN DURIAN 2873 +cayenne MACH_CAYENNE CAYENNE 2874 +fuji MACH_FUJI FUJI 2875 +synology_6282 MACH_SYNOLOGY_6282 SYNOLOGY_6282 2876 +em1sy MACH_EM1SY EM1SY 2877 +m502 MACH_M502 M502 2878 +matrix518 MACH_MATRIX518 MATRIX518 2879 +tiny_gurnard MACH_TINY_GURNARD TINY_GURNARD 2880 +spear1310 MACH_SPEAR1310 SPEAR1310 2881 +bv07 MACH_BV07 BV07 2882 +mxt_td61 MACH_MXT_TD61 MXT_TD61 2883 +openrd_ultimate MACH_OPENRD_ULTIMATE OPENRD_ULTIMATE 2884 +devixp MACH_DEVIXP DEVIXP 2885 +miccpt MACH_MICCPT MICCPT 2886 +mic256 MACH_MIC256 MIC256 2887 +as1167 MACH_AS1167 AS1167 2888 +omap3_ibiza MACH_OMAP3_IBIZA OMAP3_IBIZA 2889 +u5500 MACH_U5500 U5500 2890 +davinci_picto MACH_DAVINCI_PICTO DAVINCI_PICTO 2891 +mecha MACH_MECHA MECHA 2892 +bubba3 MACH_BUBBA3 BUBBA3 2893 +pupitre MACH_PUPITRE PUPITRE 2894 +tegra_harmony MACH_TEGRA_HARMONY TEGRA_HARMONY 2895 +tegra_vogue MACH_TEGRA_VOGUE TEGRA_VOGUE 2896 +tegra_e1165 MACH_TEGRA_E1165 TEGRA_E1165 2897 +simplenet MACH_SIMPLENET SIMPLENET 2898 +ec4350tbm MACH_EC4350TBM EC4350TBM 2899 +pec_tc MACH_PEC_TC PEC_TC 2900 +pec_hc2 MACH_PEC_HC2 PEC_HC2 2901 +esl_mobilis_a MACH_ESL_MOBILIS_A ESL_MOBILIS_A 2902 +esl_mobilis_b MACH_ESL_MOBILIS_B ESL_MOBILIS_B 2903 +esl_wave_a MACH_ESL_WAVE_A ESL_WAVE_A 2904 +esl_wave_b MACH_ESL_WAVE_B ESL_WAVE_B 2905 +unisense_mmm MACH_UNISENSE_MMM UNISENSE_MMM 2906 +blueshark MACH_BLUESHARK BLUESHARK 2907 +e10 MACH_E10 E10 2908 +app3k_robin MACH_APP3K_ROBIN APP3K_ROBIN 2909 +pov15hd MACH_POV15HD POV15HD 2910 +stella MACH_STELLA STELLA 2911 +linkstation_lschl MACH_LINKSTATION_LSCHL LINKSTATION_LSCHL 2913 +netwalker MACH_NETWALKER NETWALKER 2914 +acsx106 MACH_ACSX106 ACSX106 2915 +atlas5_c1 MACH_ATLAS5_C1 ATLAS5_C1 2916 +nsb3ast MACH_NSB3AST NSB3AST 2917 +gnet_slc MACH_GNET_SLC GNET_SLC 2918 +af4000 MACH_AF4000 AF4000 2919 +ark9431 MACH_ARK9431 ARK9431 2920 +fs_s5pc100 MACH_FS_S5PC100 FS_S5PC100 2921 +omap3505nova8 MACH_OMAP3505NOVA8 OMAP3505NOVA8 2922 +omap3621_edp1 MACH_OMAP3621_EDP1 OMAP3621_EDP1 2923 +oratisaes MACH_ORATISAES ORATISAES 2924 +smdkv310 MACH_SMDKV310 SMDKV310 2925 +siemens_l0 MACH_SIEMENS_L0 SIEMENS_L0 2926 +ventana MACH_VENTANA VENTANA 2927 +wm8505_7in_netbook MACH_WM8505_7IN_NETBOOK WM8505_7IN_NETBOOK 2928 +ec4350sdb MACH_EC4350SDB EC4350SDB 2929 +mimas MACH_MIMAS MIMAS 2930 +titan MACH_TITAN TITAN 2931 +craneboard MACH_CRANEBOARD CRANEBOARD 2932 +es2440 MACH_ES2440 ES2440 2933 +najay_a9263 MACH_NAJAY_A9263 NAJAY_A9263 2934 +htctornado MACH_HTCTORNADO HTCTORNADO 2935 +dimm_mx257 MACH_DIMM_MX257 DIMM_MX257 2936 +jigen301 MACH_JIGEN JIGEN 2937 +smdk6450 MACH_SMDK6450 SMDK6450 2938 +meno_qng MACH_MENO_QNG MENO_QNG 2939 +ns2416 MACH_NS2416 NS2416 2940 +rpc353 MACH_RPC353 RPC353 2941 +tq6410 MACH_TQ6410 TQ6410 2942 +sky6410 MACH_SKY6410 SKY6410 2943 +dynasty MACH_DYNASTY DYNASTY 2944 +vivo MACH_VIVO VIVO 2945 +bury_bl7582 MACH_BURY_BL7582 BURY_BL7582 2946 +bury_bps5270 MACH_BURY_BPS5270 BURY_BPS5270 2947 +basi MACH_BASI BASI 2948 +tn200 MACH_TN200 TN200 2949 +c2mmi MACH_C2MMI C2MMI 2950 +meson_6236m MACH_MESON_6236M MESON_6236M 2951 +meson_8626m MACH_MESON_8626M MESON_8626M 2952 +tube MACH_TUBE TUBE 2953 +messina MACH_MESSINA MESSINA 2954 +mx50_arm2 MACH_MX50_ARM2 MX50_ARM2 2955 +cetus9263 MACH_CETUS9263 CETUS9263 2956 +brownstone MACH_BROWNSTONE BROWNSTONE 2957 +vmx25 MACH_VMX25 VMX25 2958 +vmx51 MACH_VMX51 VMX51 2959 +abacus MACH_ABACUS ABACUS 2960 +cm4745 MACH_CM4745 CM4745 2961 +oratislink MACH_ORATISLINK ORATISLINK 2962 +davinci_dm365_dvr MACH_DAVINCI_DM365_DVR DAVINCI_DM365_DVR 2963 +netviz MACH_NETVIZ NETVIZ 2964 +flexibity MACH_FLEXIBITY FLEXIBITY 2965 +wlan_computer MACH_WLAN_COMPUTER WLAN_COMPUTER 2966 diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 76818f926539..505a08592423 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -5,7 +5,7 @@ mainmenu "Linux/Microblaze Kernel Configuration" config MICROBLAZE def_bool y - select HAVE_LMB + select HAVE_MEMBLOCK select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/microblaze/include/asm/lmb.h b/arch/microblaze/include/asm/memblock.h index a0a0a929c293..f9c2fa331d2a 100644 --- a/arch/microblaze/include/asm/lmb.h +++ b/arch/microblaze/include/asm/memblock.h @@ -6,12 +6,12 @@ * for more details. */ -#ifndef _ASM_MICROBLAZE_LMB_H -#define _ASM_MICROBLAZE_LMB_H +#ifndef _ASM_MICROBLAZE_MEMBLOCK_H +#define _ASM_MICROBLAZE_MEMBLOCK_H -/* LMB limit is OFF */ -#define LMB_REAL_LIMIT 0xFFFFFFFF +/* MEMBLOCK limit is OFF */ +#define MEMBLOCK_REAL_LIMIT 0xFFFFFFFF -#endif /* _ASM_MICROBLAZE_LMB_H */ +#endif /* _ASM_MICROBLAZE_MEMBLOCK_H */ diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c index a15ef6d67ca9..427b13b4740f 100644 --- a/arch/microblaze/kernel/prom.c +++ b/arch/microblaze/kernel/prom.c @@ -29,7 +29,7 @@ #include <linux/kexec.h> #include <linux/debugfs.h> #include <linux/irq.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/prom.h> #include <asm/page.h> @@ -49,12 +49,12 @@ void __init early_init_dt_scan_chosen_arch(unsigned long node) void __init early_init_dt_add_memory_arch(u64 base, u64 size) { - lmb_add(base, size); + memblock_add(base, size); } u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - return lmb_alloc(size, align); + return memblock_alloc(size, align); } #ifdef CONFIG_EARLY_PRINTK @@ -104,8 +104,8 @@ void __init early_init_devtree(void *params) */ of_scan_flat_dt(early_init_dt_scan_chosen, NULL); - /* Scan memory nodes and rebuild LMBs */ - lmb_init(); + /* Scan memory nodes and rebuild MEMBLOCKs */ + memblock_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory, NULL); @@ -113,9 +113,9 @@ void __init early_init_devtree(void *params) strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); parse_early_param(); - lmb_analyze(); + memblock_analyze(); - pr_debug("Phys. mem: %lx\n", (unsigned long) lmb_phys_mem_size()); + pr_debug("Phys. mem: %lx\n", (unsigned long) memblock_phys_mem_size()); pr_debug(" <- early_init_devtree()\n"); } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index cca3579d4268..db5934989926 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -10,7 +10,7 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/mm.h> /* mem_init */ #include <linux/initrd.h> #include <linux/pagemap.h> @@ -76,10 +76,10 @@ void __init setup_memory(void) u32 kernel_align_start, kernel_align_size; /* Find main memory where is the kernel */ - for (i = 0; i < lmb.memory.cnt; i++) { - memory_start = (u32) lmb.memory.region[i].base; - memory_end = (u32) lmb.memory.region[i].base - + (u32) lmb.memory.region[i].size; + for (i = 0; i < memblock.memory.cnt; i++) { + memory_start = (u32) memblock.memory.region[i].base; + memory_end = (u32) memblock.memory.region[i].base + + (u32) memblock.memory.region[i].size; if ((memory_start <= (u32)_text) && ((u32)_text <= memory_end)) { memory_size = memory_end - memory_start; @@ -100,7 +100,7 @@ void __init setup_memory(void) kernel_align_start = PAGE_DOWN((u32)_text); /* ALIGN can be remove because _end in vmlinux.lds.S is align */ kernel_align_size = PAGE_UP((u32)klimit) - kernel_align_start; - lmb_reserve(kernel_align_start, kernel_align_size); + memblock_reserve(kernel_align_start, kernel_align_size); printk(KERN_INFO "%s: kernel addr=0x%08x-0x%08x size=0x%08x\n", __func__, kernel_align_start, kernel_align_start + kernel_align_size, kernel_align_size); @@ -141,18 +141,18 @@ void __init setup_memory(void) map_size = init_bootmem_node(&contig_page_data, PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn); #endif - lmb_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size); + memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size); /* free bootmem is whole main memory */ free_bootmem(memory_start, memory_size); /* reserve allocate blocks */ - for (i = 0; i < lmb.reserved.cnt; i++) { + for (i = 0; i < memblock.reserved.cnt; i++) { pr_debug("reserved %d - 0x%08x-0x%08x\n", i, - (u32) lmb.reserved.region[i].base, - (u32) lmb_size_bytes(&lmb.reserved, i)); - reserve_bootmem(lmb.reserved.region[i].base, - lmb_size_bytes(&lmb.reserved, i) - 1, BOOTMEM_DEFAULT); + (u32) memblock.reserved.region[i].base, + (u32) memblock_size_bytes(&memblock.reserved, i)); + reserve_bootmem(memblock.reserved.region[i].base, + memblock_size_bytes(&memblock.reserved, i) - 1, BOOTMEM_DEFAULT); } #ifdef CONFIG_MMU init_bootmem_done = 1; @@ -235,7 +235,7 @@ static void mm_cmdline_setup(void) if (maxmem && memory_size > maxmem) { memory_size = maxmem; memory_end = memory_start + memory_size; - lmb.memory.region[0].size = memory_size; + memblock.memory.region[0].size = memory_size; } } } @@ -273,19 +273,19 @@ asmlinkage void __init mmu_init(void) { unsigned int kstart, ksize; - if (!lmb.reserved.cnt) { + if (!memblock.reserved.cnt) { printk(KERN_EMERG "Error memory count\n"); machine_restart(NULL); } - if ((u32) lmb.memory.region[0].size < 0x1000000) { + if ((u32) memblock.memory.region[0].size < 0x1000000) { printk(KERN_EMERG "Memory must be greater than 16MB\n"); machine_restart(NULL); } /* Find main memory where the kernel is */ - memory_start = (u32) lmb.memory.region[0].base; - memory_end = (u32) lmb.memory.region[0].base + - (u32) lmb.memory.region[0].size; + memory_start = (u32) memblock.memory.region[0].base; + memory_end = (u32) memblock.memory.region[0].base + + (u32) memblock.memory.region[0].size; memory_size = memory_end - memory_start; mm_cmdline_setup(); /* FIXME parse args from command line - not used */ @@ -297,7 +297,7 @@ asmlinkage void __init mmu_init(void) kstart = __pa(CONFIG_KERNEL_START); /* kernel start */ /* kernel size */ ksize = PAGE_ALIGN(((u32)_end - (u32)CONFIG_KERNEL_START)); - lmb_reserve(kstart, ksize); + memblock_reserve(kstart, ksize); #if defined(CONFIG_BLK_DEV_INITRD) /* Remove the init RAM disk from the available memory. */ @@ -335,7 +335,7 @@ void __init *early_get_page(void) * Mem start + 32MB -> here is limit * because of mem mapping from head.S */ - p = __va(lmb_alloc_base(PAGE_SIZE, PAGE_SIZE, + p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, memory_start + 0x2000000)); } return p; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6506bf4fbff1..2031a2846865 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -132,7 +132,7 @@ config PPC select HAVE_ARCH_KGDB select HAVE_KRETPROBES select HAVE_ARCH_TRACEHOOK - select HAVE_LMB + select HAVE_MEMBLOCK select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select USE_GENERIC_SMP_HELPERS if SMP diff --git a/arch/powerpc/include/asm/abs_addr.h b/arch/powerpc/include/asm/abs_addr.h index 98324c5a8286..9a846efe6382 100644 --- a/arch/powerpc/include/asm/abs_addr.h +++ b/arch/powerpc/include/asm/abs_addr.h @@ -12,7 +12,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/types.h> #include <asm/page.h> diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h index 0835eb977ba9..e50323fe941f 100644 --- a/arch/powerpc/include/asm/cpm.h +++ b/arch/powerpc/include/asm/cpm.h @@ -7,6 +7,30 @@ #include <linux/of.h> /* + * SPI Parameter RAM common to QE and CPM. + */ +struct spi_pram { + __be16 rbase; /* Rx Buffer descriptor base address */ + __be16 tbase; /* Tx Buffer descriptor base address */ + u8 rfcr; /* Rx function code */ + u8 tfcr; /* Tx function code */ + __be16 mrblr; /* Max receive buffer length */ + __be32 rstate; /* Internal */ + __be32 rdp; /* Internal */ + __be16 rbptr; /* Internal */ + __be16 rbc; /* Internal */ + __be32 rxtmp; /* Internal */ + __be32 tstate; /* Internal */ + __be32 tdp; /* Internal */ + __be16 tbptr; /* Internal */ + __be16 tbc; /* Internal */ + __be32 txtmp; /* Internal */ + __be32 res; /* Tx temp. */ + __be16 rpbase; /* Relocation pointer (CPM1 only) */ + __be16 res1; /* Reserved */ +}; + +/* * USB Controller pram common to QE and CPM. */ struct usb_ctlr { diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index 81b01192f440..bd07650dca56 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -17,6 +17,7 @@ #ifndef __CPM1__ #define __CPM1__ +#include <linux/init.h> #include <asm/8xx_immap.h> #include <asm/ptrace.h> #include <asm/cpm.h> @@ -54,7 +55,7 @@ extern cpm8xx_t __iomem *cpmp; /* Pointer to comm processor */ extern void cpm_setbrg(uint brg, uint rate); -extern void cpm_load_patch(cpm8xx_t *cp); +extern void __init cpm_load_patch(cpm8xx_t *cp); extern void cpm_reset(void); diff --git a/arch/powerpc/include/asm/lmb.h b/arch/powerpc/include/asm/lmb.h deleted file mode 100644 index 6f5fdf0a19ae..000000000000 --- a/arch/powerpc/include/asm/lmb.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _ASM_POWERPC_LMB_H -#define _ASM_POWERPC_LMB_H - -#include <asm/udbg.h> - -#define LMB_DBG(fmt...) udbg_printf(fmt) - -#ifdef CONFIG_PPC32 -extern phys_addr_t lowmem_end_addr; -#define LMB_REAL_LIMIT lowmem_end_addr -#else -#define LMB_REAL_LIMIT 0 -#endif - -#endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/memblock.h b/arch/powerpc/include/asm/memblock.h new file mode 100644 index 000000000000..3c29728b56b1 --- /dev/null +++ b/arch/powerpc/include/asm/memblock.h @@ -0,0 +1,15 @@ +#ifndef _ASM_POWERPC_MEMBLOCK_H +#define _ASM_POWERPC_MEMBLOCK_H + +#include <asm/udbg.h> + +#define MEMBLOCK_DBG(fmt...) udbg_printf(fmt) + +#ifdef CONFIG_PPC32 +extern phys_addr_t lowmem_end_addr; +#define MEMBLOCK_REAL_LIMIT lowmem_end_addr +#else +#define MEMBLOCK_REAL_LIMIT 0 +#endif + +#endif /* _ASM_POWERPC_MEMBLOCK_H */ diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 26e58630ed7b..625942ae5585 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -7,7 +7,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/sections.h> #include <asm/prom.h> diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 29df48f2b61a..417f7b05a9ce 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -24,7 +24,7 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/types.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 5fb667a60894..40f524643ba6 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -13,7 +13,7 @@ #include <linux/crash_dump.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/code-patching.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -33,7 +33,7 @@ unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; #ifndef CONFIG_RELOCATABLE void __init reserve_kdump_trampoline(void) { - lmb_reserve(0, KDUMP_RESERVE_LIMIT); + memblock_reserve(0, KDUMP_RESERVE_LIMIT); } static void __init create_trampoline(unsigned long addr) diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index e7fe218b8697..02f724f36753 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -71,7 +71,7 @@ static int ppc_swiotlb_bus_notify(struct notifier_block *nb, sd->max_direct_dma_addr = 0; /* May need to bounce if the device can't address all of DRAM */ - if ((dma_get_mask(dev) + 1) < lmb_end_of_DRAM()) + if ((dma_get_mask(dev) + 1) < memblock_end_of_DRAM()) set_dma_ops(dev, &swiotlb_dma_ops); return NOTIFY_DONE; diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 8d1de6f31d5a..84d6367ec003 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -9,7 +9,7 @@ #include <linux/dma-mapping.h> #include <linux/dma-debug.h> #include <linux/gfp.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/bug.h> #include <asm/abs_addr.h> @@ -89,7 +89,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) /* Could be improved so platforms can set the limit in case * they have limited DMA windows */ - return mask >= (lmb_end_of_DRAM() - 1); + return mask >= (memblock_end_of_DRAM() - 1); #else return 1; #endif diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S index beb4d78a2304..a92c79be2728 100644 --- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S +++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S @@ -205,8 +205,7 @@ next_tlb_setup: bdnz+ next_tlb_setup /* 7. Jump to our 1:1 mapping */ - li r6, 0 - + mr r6, r25 #else #error You need to specify the mapping or not use this at all. #endif @@ -217,7 +216,6 @@ next_tlb_setup: 1: mflr r9 rlwimi r6,r9,0,20,31 addi r6,r6,(2f - 1b) - add r6, r6, r25 mtspr SPRN_SRR0,r6 mtspr SPRN_SRR1,r7 rfi /* start execution out of TLB1[0] entry */ diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index bb3d893a8353..89f005116aac 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -12,7 +12,7 @@ #include <linux/kexec.h> #include <linux/reboot.h> #include <linux/threads.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/of.h> #include <asm/machdep.h> #include <asm/prom.h> @@ -66,11 +66,11 @@ void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - /* this is necessary because of lmb_phys_mem_size() */ - lmb_analyze(); + /* this is necessary because of memblock_phys_mem_size() */ + memblock_analyze(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, lmb_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -133,9 +133,9 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(lmb_phys_mem_size() >> 20)); + (unsigned long)(memblock_phys_mem_size() >> 20)); - lmb_reserve(crashk_res.start, crash_size); + memblock_reserve(crashk_res.start, crash_size); } int overlaps_crashkernel(unsigned long start, unsigned long size) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index f88acf0218db..139a773853f4 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -9,7 +9,7 @@ #include <linux/threads.h> #include <linux/module.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/firmware.h> #include <asm/lppaca.h> @@ -117,7 +117,7 @@ void __init allocate_pacas(void) * the first segment. On iSeries they must be within the area mapped * by the HV, which is HvPagesToMap * HVPAGESIZE bytes. */ - limit = min(0x10000000ULL, lmb.rmo_size); + limit = min(0x10000000ULL, memblock.rmo_size); if (firmware_has_feature(FW_FEATURE_ISERIES)) limit = min(limit, HvPagesToMap * HVPAGESIZE); @@ -128,7 +128,7 @@ void __init allocate_pacas(void) paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); - paca = __va(lmb_alloc_base(paca_size, PAGE_SIZE, limit)); + paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); memset(paca, 0, paca_size); printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", @@ -148,7 +148,7 @@ void __init free_unused_pacas(void) if (new_size >= paca_size) return; - lmb_free(__pa(paca) + new_size, paca_size - new_size); + memblock_free(__pa(paca) + new_size, paca_size - new_size); printk(KERN_DEBUG "Freed %u bytes for unused pacas\n", paca_size - new_size); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 05131d634e73..9d3953983fb7 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -31,7 +31,7 @@ #include <linux/kexec.h> #include <linux/debugfs.h> #include <linux/irq.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -98,7 +98,7 @@ static void __init move_device_tree(void) if ((memory_limit && (start + size) > memory_limit) || overlaps_crashkernel(start, size)) { - p = __va(lmb_alloc_base(size, PAGE_SIZE, lmb.rmo_size)); + p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size)); memcpy(p, initial_boot_params, size); initial_boot_params = (struct boot_param_header *)p; DBG("Moved device tree to 0x%p\n", p); @@ -411,13 +411,13 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) { __be32 *dm, *ls, *usm; unsigned long l, n, flags; - u64 base, size, lmb_size; + u64 base, size, memblock_size; unsigned int is_kexec_kdump = 0, rngs; - ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l); + ls = of_get_flat_dt_prop(node, "ibm,memblock-size", &l); if (ls == NULL || l < dt_root_size_cells * sizeof(__be32)) return 0; - lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls); + memblock_size = dt_mem_next_cell(dt_root_size_cells, &ls); dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l); if (dm == NULL || l < sizeof(__be32)) @@ -442,11 +442,11 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) or if the block is not assigned to this partition (0x8) */ if ((flags & 0x80) || !(flags & 0x8)) continue; - size = lmb_size; + size = memblock_size; rngs = 1; if (is_kexec_kdump) { /* - * For each lmb in ibm,dynamic-memory, a corresponding + * For each memblock in ibm,dynamic-memory, a corresponding * entry in linux,drconf-usable-memory property contains * a counter 'p' followed by 'p' (base, size) duple. * Now read the counter from @@ -469,10 +469,10 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) if ((base + size) > 0x80000000ul) size = 0x80000000ul - base; } - lmb_add(base, size); + memblock_add(base, size); } while (--rngs); } - lmb_dump_all(); + memblock_dump_all(); return 0; } #else @@ -501,14 +501,14 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) } #endif - lmb_add(base, size); + memblock_add(base, size); memstart_addr = min((u64)memstart_addr, base); } u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - return lmb_alloc(size, align); + return memblock_alloc(size, align); } #ifdef CONFIG_BLK_DEV_INITRD @@ -534,12 +534,12 @@ static void __init early_reserve_mem(void) /* before we do anything, lets reserve the dt blob */ self_base = __pa((unsigned long)initial_boot_params); self_size = initial_boot_params->totalsize; - lmb_reserve(self_base, self_size); + memblock_reserve(self_base, self_size); #ifdef CONFIG_BLK_DEV_INITRD /* then reserve the initrd, if any */ if (initrd_start && (initrd_end > initrd_start)) - lmb_reserve(__pa(initrd_start), initrd_end - initrd_start); + memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); #endif /* CONFIG_BLK_DEV_INITRD */ #ifdef CONFIG_PPC32 @@ -560,7 +560,7 @@ static void __init early_reserve_mem(void) if (base_32 == self_base && size_32 == self_size) continue; DBG("reserving: %x -> %x\n", base_32, size_32); - lmb_reserve(base_32, size_32); + memblock_reserve(base_32, size_32); } return; } @@ -571,7 +571,7 @@ static void __init early_reserve_mem(void) if (size == 0) break; DBG("reserving: %llx -> %llx\n", base, size); - lmb_reserve(base, size); + memblock_reserve(base, size); } } @@ -594,7 +594,7 @@ static inline unsigned long phyp_dump_calculate_reserve_size(void) return phyp_dump_info->reserve_bootvar; /* divide by 20 to get 5% of value */ - tmp = lmb_end_of_DRAM(); + tmp = memblock_end_of_DRAM(); do_div(tmp, 20); /* round it down in multiples of 256 */ @@ -633,11 +633,11 @@ static void __init phyp_dump_reserve_mem(void) if (phyp_dump_info->phyp_dump_is_active) { /* Reserve *everything* above RMR.Area freed by userland tools*/ base = variable_reserve_size; - size = lmb_end_of_DRAM() - base; + size = memblock_end_of_DRAM() - base; /* XXX crashed_ram_end is wrong, since it may be beyond * the memory_limit, it will need to be adjusted. */ - lmb_reserve(base, size); + memblock_reserve(base, size); phyp_dump_info->init_reserve_start = base; phyp_dump_info->init_reserve_size = size; @@ -645,8 +645,8 @@ static void __init phyp_dump_reserve_mem(void) size = phyp_dump_info->cpu_state_size + phyp_dump_info->hpte_region_size + variable_reserve_size; - base = lmb_end_of_DRAM() - size; - lmb_reserve(base, size); + base = memblock_end_of_DRAM() - size; + memblock_reserve(base, size); phyp_dump_info->init_reserve_start = base; phyp_dump_info->init_reserve_size = size; } @@ -681,8 +681,8 @@ void __init early_init_devtree(void *params) */ of_scan_flat_dt(early_init_dt_scan_chosen, NULL); - /* Scan memory nodes and rebuild LMBs */ - lmb_init(); + /* Scan memory nodes and rebuild MEMBLOCKs */ + memblock_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); @@ -690,11 +690,11 @@ void __init early_init_devtree(void *params) strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); parse_early_param(); - /* Reserve LMB regions used by kernel, initrd, dt, etc... */ - lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); + /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ + memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); /* If relocatable, reserve first 32k for interrupt vectors etc. */ if (PHYSICAL_START > MEMORY_START) - lmb_reserve(MEMORY_START, 0x8000); + memblock_reserve(MEMORY_START, 0x8000); reserve_kdump_trampoline(); reserve_crashkernel(); early_reserve_mem(); @@ -706,17 +706,17 @@ void __init early_init_devtree(void *params) /* Ensure that total memory size is page-aligned, because * otherwise mark_bootmem() gets upset. */ - lmb_analyze(); - memsize = lmb_phys_mem_size(); + memblock_analyze(); + memsize = memblock_phys_mem_size(); if ((memsize & PAGE_MASK) != memsize) limit = memsize & PAGE_MASK; } - lmb_enforce_memory_limit(limit); + memblock_enforce_memory_limit(limit); - lmb_analyze(); - lmb_dump_all(); + memblock_analyze(); + memblock_dump_all(); - DBG("Phys. mem: %llx\n", lmb_phys_mem_size()); + DBG("Phys. mem: %llx\n", memblock_phys_mem_size()); /* We may need to relocate the flat tree, do it now. * FIXME .. and the initrd too? */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 0e1ec6f746f6..d0516dbee762 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -22,7 +22,7 @@ #include <linux/smp.h> #include <linux/completion.h> #include <linux/cpumask.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <asm/prom.h> @@ -934,11 +934,11 @@ void __init rtas_initialize(void) */ #ifdef CONFIG_PPC64 if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) { - rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX); + rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX); ibm_suspend_me_token = rtas_token("ibm,suspend-me"); } #endif - rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); + rtas_rmo_buf = memblock_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 5e4d852f640c..b7e6c7e193ae 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -33,7 +33,7 @@ #include <linux/serial_8250.h> #include <linux/debugfs.h> #include <linux/percpu.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/of_platform.h> #include <asm/io.h> #include <asm/paca.h> diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 7d84b210f168..a10ffc85ada7 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -16,7 +16,7 @@ #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/console.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/io.h> #include <asm/prom.h> @@ -246,12 +246,12 @@ static void __init irqstack_early_init(void) unsigned int i; /* interrupt stacks must be in lowmem, we get that for free on ppc32 - * as the lmb is limited to lowmem by LMB_REAL_LIMIT */ + * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); hardirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); } } @@ -261,15 +261,15 @@ static void __init exc_lvl_early_init(void) unsigned int i; /* interrupt stacks must be in lowmem, we get that for free on ppc32 - * as the lmb is limited to lowmem by LMB_REAL_LIMIT */ + * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { critirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE dbgirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); mcheckirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #endif } } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 643dcac40fcb..d135f93cb0f6 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -34,7 +34,7 @@ #include <linux/bootmem.h> #include <linux/pci.h> #include <linux/lockdep.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/io.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -158,7 +158,7 @@ static void __init setup_paca(struct paca_struct *new_paca) * the CPU that ignores the top 2 bits of the address in real * mode so we can access kernel globals normally provided we * only toy with things in the RMO region. From here, we do - * some early parsing of the device-tree to setup out LMB + * some early parsing of the device-tree to setup out MEMBLOCK * data structures, and allocate & initialize the hash table * and segment tables so we can start running with translation * enabled. @@ -404,7 +404,7 @@ void __init setup_system(void) printk("-----------------------------------------------------\n"); printk("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); - printk("physicalMemorySize = 0x%llx\n", lmb_phys_mem_size()); + printk("physicalMemorySize = 0x%llx\n", memblock_phys_mem_size()); if (ppc64_caches.dline_size != 0x80) printk("ppc64_caches.dcache_line_size = 0x%x\n", ppc64_caches.dline_size); @@ -443,10 +443,10 @@ static void __init irqstack_early_init(void) */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc_base(THREAD_SIZE, + __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); hardirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc_base(THREAD_SIZE, + __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); } } @@ -458,11 +458,11 @@ static void __init exc_lvl_early_init(void) for_each_possible_cpu(i) { critirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); dbgirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); mcheckirq_ctx[i] = (struct thread_info *) - __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); } } #else @@ -487,11 +487,11 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(slb0_limit(), lmb.rmo_size); + limit = min(slb0_limit(), memblock.rmo_size); for_each_possible_cpu(i) { unsigned long sp; - sp = lmb_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); sp += THREAD_SIZE; paca[i].emergency_sp = __va(sp); } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index d84d19224a95..13002fe206e7 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,7 +22,7 @@ #include <linux/elf.h> #include <linux/security.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -734,7 +734,7 @@ static int __init vdso_init(void) vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100; if (firmware_has_feature(FW_FEATURE_LPAR)) vdso_data->platform |= 1; - vdso_data->physicalMemorySize = lmb_phys_mem_size(); + vdso_data->physicalMemorySize = memblock_phys_mem_size(); vdso_data->dcache_size = ppc64_caches.dsize; vdso_data->dcache_line_size = ppc64_caches.dline_size; vdso_data->icache_size = ppc64_caches.isize; diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c index 65abfcfaaa9e..1dc2fa5ce1bd 100644 --- a/arch/powerpc/mm/40x_mmu.c +++ b/arch/powerpc/mm/40x_mmu.c @@ -135,7 +135,7 @@ unsigned long __init mmu_mapin_ram(unsigned long top) /* If the size of RAM is not an exact power of two, we may not * have covered RAM in its entirety with 16 and 4 MiB * pages. Consequently, restrict the top end of RAM currently - * allocable so that calls to the LMB to allocate PTEs for "tail" + * allocable so that calls to the MEMBLOCK to allocate PTEs for "tail" * coverage with normal-sized pages (or other reasons) do not * attempt to allocate outside the allowed range. */ diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 3ecdcec0a39e..98f262de5585 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -31,7 +31,7 @@ #include <linux/cache.h> #include <linux/init.h> #include <linux/signal.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/pgtable.h> @@ -384,8 +384,8 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, printk(KERN_INFO "Huge page(16GB) memory: " "addr = 0x%lX size = 0x%lX pages = %d\n", phys_addr, block_size, expected_pages); - if (phys_addr + (16 * GB) <= lmb_end_of_DRAM()) { - lmb_reserve(phys_addr, block_size * expected_pages); + if (phys_addr + (16 * GB) <= memblock_end_of_DRAM()) { + memblock_reserve(phys_addr, block_size * expected_pages); add_gpage(phys_addr, block_size, expected_pages); } return 0; @@ -458,7 +458,7 @@ static void __init htab_init_page_sizes(void) * and we have at least 1G of RAM at boot */ if (mmu_psize_defs[MMU_PAGE_16M].shift && - lmb_phys_mem_size() >= 0x40000000) + memblock_phys_mem_size() >= 0x40000000) mmu_vmemmap_psize = MMU_PAGE_16M; else if (mmu_psize_defs[MMU_PAGE_64K].shift) mmu_vmemmap_psize = MMU_PAGE_64K; @@ -520,7 +520,7 @@ static unsigned long __init htab_get_table_size(void) return 1UL << ppc64_pft_size; /* round mem_size up to next power of 2 */ - mem_size = lmb_phys_mem_size(); + mem_size = memblock_phys_mem_size(); rnd_mem_size = 1UL << __ilog2(mem_size); if (rnd_mem_size < mem_size) rnd_mem_size <<= 1; @@ -627,7 +627,7 @@ static void __init htab_initialize(void) else limit = 0; - table = lmb_alloc_base(htab_size_bytes, htab_size_bytes, limit); + table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit); DBG("Hash table allocated at %lx, size: %lx\n", table, htab_size_bytes); @@ -647,9 +647,9 @@ static void __init htab_initialize(void) prot = pgprot_val(PAGE_KERNEL); #ifdef CONFIG_DEBUG_PAGEALLOC - linear_map_hash_count = lmb_end_of_DRAM() >> PAGE_SHIFT; - linear_map_hash_slots = __va(lmb_alloc_base(linear_map_hash_count, - 1, lmb.rmo_size)); + linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT; + linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count, + 1, memblock.rmo_size)); memset(linear_map_hash_slots, 0, linear_map_hash_count); #endif /* CONFIG_DEBUG_PAGEALLOC */ @@ -659,16 +659,16 @@ static void __init htab_initialize(void) */ /* create bolted the linear mapping in the hash table */ - for (i=0; i < lmb.memory.cnt; i++) { - base = (unsigned long)__va(lmb.memory.region[i].base); - size = lmb.memory.region[i].size; + for (i=0; i < memblock.memory.cnt; i++) { + base = (unsigned long)__va(memblock.memory.region[i].base); + size = memblock.memory.region[i].size; DBG("creating mapping for region: %lx..%lx (prot: %lx)\n", base, size, prot); #ifdef CONFIG_U3_DART /* Do not map the DART space. Fortunately, it will be aligned - * in such a way that it will not cross two lmb regions and + * in such a way that it will not cross two memblock regions and * will fit within a single 16Mb page. * The DART space is assumed to be a full 16Mb region even if * we only use 2Mb of that space. We will use more of it later diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 767333005eb4..6a6975dc2654 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -30,7 +30,7 @@ #include <linux/highmem.h> #include <linux/initrd.h> #include <linux/pagemap.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <asm/pgalloc.h> @@ -136,17 +136,17 @@ void __init MMU_init(void) /* parse args from command line */ MMU_setup(); - if (lmb.memory.cnt > 1) { + if (memblock.memory.cnt > 1) { #ifndef CONFIG_WII - lmb.memory.cnt = 1; - lmb_analyze(); + memblock.memory.cnt = 1; + memblock_analyze(); printk(KERN_WARNING "Only using first contiguous memory region"); #else wii_memory_fixups(); #endif } - total_lowmem = total_memory = lmb_end_of_DRAM() - memstart_addr; + total_lowmem = total_memory = memblock_end_of_DRAM() - memstart_addr; lowmem_end_addr = memstart_addr + total_lowmem; #ifdef CONFIG_FSL_BOOKE @@ -161,8 +161,8 @@ void __init MMU_init(void) lowmem_end_addr = memstart_addr + total_lowmem; #ifndef CONFIG_HIGHMEM total_memory = total_lowmem; - lmb_enforce_memory_limit(lowmem_end_addr); - lmb_analyze(); + memblock_enforce_memory_limit(lowmem_end_addr); + memblock_analyze(); #endif /* CONFIG_HIGHMEM */ } @@ -200,7 +200,7 @@ void __init *early_get_page(void) if (init_bootmem_done) { p = alloc_bootmem_pages(PAGE_SIZE); } else { - p = __va(lmb_alloc_base(PAGE_SIZE, PAGE_SIZE, + p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, __initial_memory_limit_addr)); } return p; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index e267f223fdff..71f1415e2472 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -40,7 +40,7 @@ #include <linux/nodemask.h> #include <linux/module.h> #include <linux/poison.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/hugetlb.h> #include <linux/slab.h> diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 0f594d774bf7..1a84a8d00005 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -32,7 +32,7 @@ #include <linux/initrd.h> #include <linux/pagemap.h> #include <linux/suspend.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> @@ -83,13 +83,13 @@ int page_is_ram(unsigned long pfn) #else unsigned long paddr = (pfn << PAGE_SHIFT); int i; - for (i=0; i < lmb.memory.cnt; i++) { + for (i=0; i < memblock.memory.cnt; i++) { unsigned long base; - base = lmb.memory.region[i].base; + base = memblock.memory.region[i].base; if ((paddr >= base) && - (paddr < (base + lmb.memory.region[i].size))) { + (paddr < (base + memblock.memory.region[i].size))) { return 1; } } @@ -142,14 +142,14 @@ int arch_add_memory(int nid, u64 start, u64 size) /* * walk_memory_resource() needs to make sure there is no holes in a given * memory range. PPC64 does not maintain the memory layout in /proc/iomem. - * Instead it maintains it in lmb.memory structures. Walk through the + * Instead it maintains it in memblock.memory structures. Walk through the * memory regions, find holes and callback for contiguous regions. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) { - struct lmb_property res; + struct memblock_property res; unsigned long pfn, len; u64 end; int ret = -1; @@ -158,7 +158,7 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, res.size = (u64) nr_pages << PAGE_SHIFT; end = res.base + res.size - 1; - while ((res.base < end) && (lmb_find(&res) >= 0)) { + while ((res.base < end) && (memblock_find(&res) >= 0)) { pfn = (unsigned long)(res.base >> PAGE_SHIFT); len = (unsigned long)(res.size >> PAGE_SHIFT); ret = (*func)(pfn, len, arg); @@ -184,8 +184,8 @@ void __init do_init_bootmem(void) unsigned long total_pages; int boot_mapsize; - max_low_pfn = max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; - total_pages = (lmb_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT; + max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; + total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT; #ifdef CONFIG_HIGHMEM total_pages = total_lowmem >> PAGE_SHIFT; max_low_pfn = lowmem_end_addr >> PAGE_SHIFT; @@ -198,16 +198,16 @@ void __init do_init_bootmem(void) */ bootmap_pages = bootmem_bootmap_pages(total_pages); - start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE); + start = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE); min_low_pfn = MEMORY_START >> PAGE_SHIFT; boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn); /* Add active regions with valid PFNs */ - for (i = 0; i < lmb.memory.cnt; i++) { + for (i = 0; i < memblock.memory.cnt; i++) { unsigned long start_pfn, end_pfn; - start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; - end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i); add_active_range(0, start_pfn, end_pfn); } @@ -218,17 +218,17 @@ void __init do_init_bootmem(void) free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT); /* reserve the sections we're already using */ - for (i = 0; i < lmb.reserved.cnt; i++) { - unsigned long addr = lmb.reserved.region[i].base + - lmb_size_bytes(&lmb.reserved, i) - 1; + for (i = 0; i < memblock.reserved.cnt; i++) { + unsigned long addr = memblock.reserved.region[i].base + + memblock_size_bytes(&memblock.reserved, i) - 1; if (addr < lowmem_end_addr) - reserve_bootmem(lmb.reserved.region[i].base, - lmb_size_bytes(&lmb.reserved, i), + reserve_bootmem(memblock.reserved.region[i].base, + memblock_size_bytes(&memblock.reserved, i), BOOTMEM_DEFAULT); - else if (lmb.reserved.region[i].base < lowmem_end_addr) { + else if (memblock.reserved.region[i].base < lowmem_end_addr) { unsigned long adjusted_size = lowmem_end_addr - - lmb.reserved.region[i].base; - reserve_bootmem(lmb.reserved.region[i].base, + memblock.reserved.region[i].base; + reserve_bootmem(memblock.reserved.region[i].base, adjusted_size, BOOTMEM_DEFAULT); } } @@ -236,9 +236,9 @@ void __init do_init_bootmem(void) free_bootmem_with_active_regions(0, max_pfn); /* reserve the sections we're already using */ - for (i = 0; i < lmb.reserved.cnt; i++) - reserve_bootmem(lmb.reserved.region[i].base, - lmb_size_bytes(&lmb.reserved, i), + for (i = 0; i < memblock.reserved.cnt; i++) + reserve_bootmem(memblock.reserved.region[i].base, + memblock_size_bytes(&memblock.reserved, i), BOOTMEM_DEFAULT); #endif @@ -251,20 +251,20 @@ void __init do_init_bootmem(void) /* mark pages that don't exist as nosave */ static int __init mark_nonram_nosave(void) { - unsigned long lmb_next_region_start_pfn, - lmb_region_max_pfn; + unsigned long memblock_next_region_start_pfn, + memblock_region_max_pfn; int i; - for (i = 0; i < lmb.memory.cnt - 1; i++) { - lmb_region_max_pfn = - (lmb.memory.region[i].base >> PAGE_SHIFT) + - (lmb.memory.region[i].size >> PAGE_SHIFT); - lmb_next_region_start_pfn = - lmb.memory.region[i+1].base >> PAGE_SHIFT; + for (i = 0; i < memblock.memory.cnt - 1; i++) { + memblock_region_max_pfn = + (memblock.memory.region[i].base >> PAGE_SHIFT) + + (memblock.memory.region[i].size >> PAGE_SHIFT); + memblock_next_region_start_pfn = + memblock.memory.region[i+1].base >> PAGE_SHIFT; - if (lmb_region_max_pfn < lmb_next_region_start_pfn) - register_nosave_region(lmb_region_max_pfn, - lmb_next_region_start_pfn); + if (memblock_region_max_pfn < memblock_next_region_start_pfn) + register_nosave_region(memblock_region_max_pfn, + memblock_next_region_start_pfn); } return 0; @@ -275,8 +275,8 @@ static int __init mark_nonram_nosave(void) */ void __init paging_init(void) { - unsigned long total_ram = lmb_phys_mem_size(); - phys_addr_t top_of_ram = lmb_end_of_DRAM(); + unsigned long total_ram = memblock_phys_mem_size(); + phys_addr_t top_of_ram = memblock_end_of_DRAM(); unsigned long max_zone_pfns[MAX_NR_ZONES]; #ifdef CONFIG_PPC32 @@ -327,7 +327,7 @@ void __init mem_init(void) swiotlb_init(1); #endif - num_physpages = lmb.memory.size >> PAGE_SHIFT; + num_physpages = memblock.memory.size >> PAGE_SHIFT; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -364,7 +364,7 @@ void __init mem_init(void) highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT; for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) { struct page *page = pfn_to_page(pfn); - if (lmb_is_reserved(pfn << PAGE_SHIFT)) + if (memblock_is_reserved(pfn << PAGE_SHIFT)) continue; ClearPageReserved(page); init_page_count(page); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 80d110635d24..f47364585ecd 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -17,7 +17,7 @@ #include <linux/nodemask.h> #include <linux/cpu.h> #include <linux/notifier.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/of.h> #include <linux/pfn.h> #include <asm/sparsemem.h> @@ -351,7 +351,7 @@ struct of_drconf_cell { #define DRCONF_MEM_RESERVED 0x00000080 /* - * Read the next lmb list entry from the ibm,dynamic-memory property + * Read the next memblock list entry from the ibm,dynamic-memory property * and return the information in the provided of_drconf_cell structure. */ static void read_drconf_cell(struct of_drconf_cell *drmem, const u32 **cellp) @@ -372,8 +372,8 @@ static void read_drconf_cell(struct of_drconf_cell *drmem, const u32 **cellp) /* * Retreive and validate the ibm,dynamic-memory property of the device tree. * - * The layout of the ibm,dynamic-memory property is a number N of lmb - * list entries followed by N lmb list entries. Each lmb list entry + * The layout of the ibm,dynamic-memory property is a number N of memblock + * list entries followed by N memblock list entries. Each memblock list entry * contains information as layed out in the of_drconf_cell struct above. */ static int of_get_drconf_memory(struct device_node *memory, const u32 **dm) @@ -398,15 +398,15 @@ static int of_get_drconf_memory(struct device_node *memory, const u32 **dm) } /* - * Retreive and validate the ibm,lmb-size property for drconf memory + * Retreive and validate the ibm,memblock-size property for drconf memory * from the device tree. */ -static u64 of_get_lmb_size(struct device_node *memory) +static u64 of_get_memblock_size(struct device_node *memory) { const u32 *prop; u32 len; - prop = of_get_property(memory, "ibm,lmb-size", &len); + prop = of_get_property(memory, "ibm,memblock-size", &len); if (!prop || len < sizeof(unsigned int)) return 0; @@ -540,19 +540,19 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start, unsigned long size) { /* - * We use lmb_end_of_DRAM() in here instead of memory_limit because + * We use memblock_end_of_DRAM() in here instead of memory_limit because * we've already adjusted it for the limit and it takes care of * having memory holes below the limit. Also, in the case of * iommu_is_off, memory_limit is not set but is implicitly enforced. */ - if (start + size <= lmb_end_of_DRAM()) + if (start + size <= memblock_end_of_DRAM()) return size; - if (start >= lmb_end_of_DRAM()) + if (start >= memblock_end_of_DRAM()) return 0; - return lmb_end_of_DRAM() - start; + return memblock_end_of_DRAM() - start; } /* @@ -562,7 +562,7 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start, static inline int __init read_usm_ranges(const u32 **usm) { /* - * For each lmb in ibm,dynamic-memory a corresponding + * For each memblock in ibm,dynamic-memory a corresponding * entry in linux,drconf-usable-memory property contains * a counter followed by that many (base, size) duple. * read the counter from linux,drconf-usable-memory @@ -578,7 +578,7 @@ static void __init parse_drconf_memory(struct device_node *memory) { const u32 *dm, *usm; unsigned int n, rc, ranges, is_kexec_kdump = 0; - unsigned long lmb_size, base, size, sz; + unsigned long memblock_size, base, size, sz; int nid; struct assoc_arrays aa; @@ -586,8 +586,8 @@ static void __init parse_drconf_memory(struct device_node *memory) if (!n) return; - lmb_size = of_get_lmb_size(memory); - if (!lmb_size) + memblock_size = of_get_memblock_size(memory); + if (!memblock_size) return; rc = of_get_assoc_arrays(memory, &aa); @@ -611,7 +611,7 @@ static void __init parse_drconf_memory(struct device_node *memory) continue; base = drmem.base_addr; - size = lmb_size; + size = memblock_size; ranges = 1; if (is_kexec_kdump) { @@ -731,7 +731,7 @@ new_range: } /* - * Now do the same thing for each LMB listed in the ibm,dynamic-memory + * Now do the same thing for each MEMBLOCK listed in the ibm,dynamic-memory * property in the ibm,dynamic-reconfiguration-memory node. */ memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -743,8 +743,8 @@ new_range: static void __init setup_nonnuma(void) { - unsigned long top_of_ram = lmb_end_of_DRAM(); - unsigned long total_ram = lmb_phys_mem_size(); + unsigned long top_of_ram = memblock_end_of_DRAM(); + unsigned long total_ram = memblock_phys_mem_size(); unsigned long start_pfn, end_pfn; unsigned int i, nid = 0; @@ -753,9 +753,9 @@ static void __init setup_nonnuma(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20); - for (i = 0; i < lmb.memory.cnt; ++i) { - start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; - end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + for (i = 0; i < memblock.memory.cnt; ++i) { + start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i); fake_numa_create_new_node(end_pfn, &nid); add_active_range(nid, start_pfn, end_pfn); @@ -813,7 +813,7 @@ static void __init dump_numa_memory_topology(void) count = 0; - for (i = 0; i < lmb_end_of_DRAM(); + for (i = 0; i < memblock_end_of_DRAM(); i += (1 << SECTION_SIZE_BITS)) { if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) { if (count == 0) @@ -833,7 +833,7 @@ static void __init dump_numa_memory_topology(void) } /* - * Allocate some memory, satisfying the lmb or bootmem allocator where + * Allocate some memory, satisfying the memblock or bootmem allocator where * required. nid is the preferred node and end is the physical address of * the highest address in the node. * @@ -847,11 +847,11 @@ static void __init *careful_zallocation(int nid, unsigned long size, int new_nid; unsigned long ret_paddr; - ret_paddr = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT); + ret_paddr = __memblock_alloc_base(size, align, end_pfn << PAGE_SHIFT); /* retry over all memory */ if (!ret_paddr) - ret_paddr = __lmb_alloc_base(size, align, lmb_end_of_DRAM()); + ret_paddr = __memblock_alloc_base(size, align, memblock_end_of_DRAM()); if (!ret_paddr) panic("numa.c: cannot allocate %lu bytes for node %d", @@ -861,14 +861,14 @@ static void __init *careful_zallocation(int nid, unsigned long size, /* * We initialize the nodes in numeric order: 0, 1, 2... - * and hand over control from the LMB allocator to the + * and hand over control from the MEMBLOCK allocator to the * bootmem allocator. If this function is called for * node 5, then we know that all nodes <5 are using the - * bootmem allocator instead of the LMB allocator. + * bootmem allocator instead of the MEMBLOCK allocator. * * So, check the nid from which this allocation came * and double check to see if we need to use bootmem - * instead of the LMB. We don't free the LMB memory + * instead of the MEMBLOCK. We don't free the MEMBLOCK memory * since it would be useless. */ new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT); @@ -893,9 +893,9 @@ static void mark_reserved_regions_for_nid(int nid) struct pglist_data *node = NODE_DATA(nid); int i; - for (i = 0; i < lmb.reserved.cnt; i++) { - unsigned long physbase = lmb.reserved.region[i].base; - unsigned long size = lmb.reserved.region[i].size; + for (i = 0; i < memblock.reserved.cnt; i++) { + unsigned long physbase = memblock.reserved.region[i].base; + unsigned long size = memblock.reserved.region[i].size; unsigned long start_pfn = physbase >> PAGE_SHIFT; unsigned long end_pfn = PFN_UP(physbase + size); struct node_active_region node_ar; @@ -903,7 +903,7 @@ static void mark_reserved_regions_for_nid(int nid) node->node_spanned_pages; /* - * Check to make sure that this lmb.reserved area is + * Check to make sure that this memblock.reserved area is * within the bounds of the node that we care about. * Checking the nid of the start and end points is not * sufficient because the reserved area could span the @@ -961,7 +961,7 @@ void __init do_init_bootmem(void) int nid; min_low_pfn = 0; - max_low_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; + max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; max_pfn = max_low_pfn; if (parse_numa_properties()) @@ -1038,7 +1038,7 @@ void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); - max_zone_pfns[ZONE_DMA] = lmb_end_of_DRAM() >> PAGE_SHIFT; + max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT; free_area_init_nodes(max_zone_pfns); } @@ -1072,7 +1072,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory, { const u32 *dm; unsigned int drconf_cell_cnt, rc; - unsigned long lmb_size; + unsigned long memblock_size; struct assoc_arrays aa; int nid = -1; @@ -1080,8 +1080,8 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory, if (!drconf_cell_cnt) return -1; - lmb_size = of_get_lmb_size(memory); - if (!lmb_size) + memblock_size = of_get_memblock_size(memory); + if (!memblock_size) return -1; rc = of_get_assoc_arrays(memory, &aa); @@ -1100,7 +1100,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory, continue; if ((scn_addr < drmem.base_addr) - || (scn_addr >= (drmem.base_addr + lmb_size))) + || (scn_addr >= (drmem.base_addr + memblock_size))) continue; nid = of_drconf_to_nid_single(&drmem, &aa); @@ -1113,7 +1113,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory, /* * Find the node associated with a hot added memory section for memory * represented in the device tree as a node (i.e. memory@XXXX) for - * each lmb. + * each memblock. */ int hot_add_node_scn_to_nid(unsigned long scn_addr) { @@ -1154,8 +1154,8 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr) /* * Find the node associated with a hot added memory section. Section - * corresponds to a SPARSEMEM section, not an LMB. It is assumed that - * sections are fully contained within a single LMB. + * corresponds to a SPARSEMEM section, not an MEMBLOCK. It is assumed that + * sections are fully contained within a single MEMBLOCK. */ int hot_add_scn_to_nid(unsigned long scn_addr) { diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 34347b2e7e31..a87ead0138b4 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -26,7 +26,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/highmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <asm/pgtable.h> @@ -198,7 +198,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, * mem_init() sets high_memory so only do the check after that. */ if (mem_init_done && (p < virt_to_phys(high_memory)) && - !(__allow_ioremap_reserved && lmb_is_region_reserved(p, size))) { + !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) { printk("__ioremap(): phys addr 0x%llx is RAM lr %p\n", (unsigned long long)p, __builtin_return_address(0)); return NULL; @@ -331,7 +331,7 @@ void __init mapin_ram(void) s = mmu_mapin_ram(top); __mapin_ram_chunk(s, top); - top = lmb_end_of_DRAM(); + top = memblock_end_of_DRAM(); s = wii_mmu_mapin_mem2(top); __mapin_ram_chunk(s, top); } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index d050fc8d9714..21d6dfab7942 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -34,7 +34,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <asm/pgalloc.h> @@ -67,7 +67,7 @@ static void *early_alloc_pgtable(unsigned long size) if (init_bootmem_done) pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS)); else - pt = __va(lmb_alloc_base(size, size, + pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); memset(pt, 0, size); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index f11c2cdcb0fe..f8a01829d64f 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -26,7 +26,7 @@ #include <linux/mm.h> #include <linux/init.h> #include <linux/highmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/prom.h> #include <asm/mmu.h> @@ -223,7 +223,7 @@ void __init MMU_init_hw(void) * Find some memory for the hash table. */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); - Hash = __va(lmb_alloc_base(Hash_size, Hash_size, + Hash = __va(memblock_alloc_base(Hash_size, Hash_size, __initial_memory_limit_addr)); cacheable_memzero(Hash, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c index 687fddaa24c5..446a01842a73 100644 --- a/arch/powerpc/mm/stab.c +++ b/arch/powerpc/mm/stab.c @@ -12,7 +12,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/pgtable.h> #include <asm/mmu.h> @@ -252,7 +252,7 @@ void __init stabs_alloc(void) if (cpu == 0) continue; /* stab for CPU 0 is statically allocated */ - newstab = lmb_alloc_base(HW_PAGE_SIZE, HW_PAGE_SIZE, + newstab = memblock_alloc_base(HW_PAGE_SIZE, HW_PAGE_SIZE, 1<<SID_SHIFT); newstab = (unsigned long)__va(newstab); diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index e81d5d67f834..d8695b02a968 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -34,7 +34,7 @@ #include <linux/pagemap.h> #include <linux/preempt.h> #include <linux/spinlock.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/tlbflush.h> #include <asm/tlb.h> @@ -426,7 +426,7 @@ static void __early_init_mmu(int boot_cpu) /* Set the global containing the top of the linear mapping * for use by the TLB miss code */ - linear_map_top = lmb_end_of_DRAM(); + linear_map_top = memblock_end_of_DRAM(); /* A sync won't hurt us after mucking around with * the MMU configuration diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c index 534c2ecc89d9..2ab338c9ac37 100644 --- a/arch/powerpc/platforms/85xx/corenet_ds.c +++ b/arch/powerpc/platforms/85xx/corenet_ds.c @@ -16,7 +16,7 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/interrupt.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/system.h> #include <asm/time.h> @@ -100,7 +100,7 @@ void __init corenet_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 004b7d36cdb7..f79f2f102141 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -17,7 +17,7 @@ #include <linux/seq_file.h> #include <linux/interrupt.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/system.h> #include <asm/time.h> @@ -94,7 +94,7 @@ static void __init mpc8536_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 544011a562fb..8190bc25bf27 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -20,7 +20,7 @@ #include <linux/seq_file.h> #include <linux/interrupt.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/system.h> #include <asm/time.h> @@ -190,7 +190,7 @@ static void __init mpc85xx_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 8fe87fc61485..494513682d70 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -33,7 +33,7 @@ #include <linux/of_platform.h> #include <linux/of_device.h> #include <linux/phy.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/system.h> #include <asm/atomic.h> @@ -325,7 +325,7 @@ static void __init mpc85xx_mds_setup_arch(void) #endif /* CONFIG_QUICC_ENGINE */ #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 2aa69a69bcc8..b11c3535f350 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -19,7 +19,7 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/system.h> #include <asm/time.h> @@ -103,7 +103,7 @@ mpc86xx_hpcn_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 4326b737d913..3712900471ba 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -29,7 +29,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/slab.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/prom.h> #include <asm/iommu.h> @@ -845,10 +845,10 @@ static int __init cell_iommu_init_disabled(void) /* If we found a DMA window, we check if it's big enough to enclose * all of physical memory. If not, we force enable IOMMU */ - if (np && size < lmb_end_of_DRAM()) { + if (np && size < memblock_end_of_DRAM()) { printk(KERN_WARNING "iommu: force-enabled, dma window" " (%ldMB) smaller than total memory (%lldMB)\n", - size >> 20, lmb_end_of_DRAM() >> 20); + size >> 20, memblock_end_of_DRAM() >> 20); return -ENODEV; } @@ -1064,7 +1064,7 @@ static int __init cell_iommu_fixed_mapping_init(void) } fbase = _ALIGN_UP(fbase, 1 << IO_SEGMENT_SHIFT); - fsize = lmb_phys_mem_size(); + fsize = memblock_phys_mem_size(); if ((fbase + fsize) <= 0x800000000ul) hbase = 0; /* use the device tree window */ @@ -1169,7 +1169,7 @@ static int __init cell_iommu_init(void) * Note: should we make sure we have the IOMMU actually disabled ? */ if (iommu_is_off || - (!iommu_force_on && lmb_end_of_DRAM() <= 0x80000000ull)) + (!iommu_force_on && memblock_end_of_DRAM() <= 0x80000000ull)) if (cell_iommu_init_disabled() == 0) goto bail; diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 174a04ac4806..5cdcc7c8d973 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -20,7 +20,7 @@ #include <linux/seq_file.h> #include <linux/kexec.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <mm/mmu_decl.h> #include <asm/io.h> @@ -65,7 +65,7 @@ static int __init page_aligned(unsigned long x) void __init wii_memory_fixups(void) { - struct lmb_property *p = lmb.memory.region; + struct memblock_property *p = memblock.memory.region; /* * This is part of a workaround to allow the use of two @@ -77,7 +77,7 @@ void __init wii_memory_fixups(void) * between both ranges. */ - BUG_ON(lmb.memory.cnt != 2); + BUG_ON(memblock.memory.cnt != 2); BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base)); p[0].size = _ALIGN_DOWN(p[0].size, PAGE_SIZE); @@ -92,11 +92,11 @@ void __init wii_memory_fixups(void) p[0].size += wii_hole_size + p[1].size; - lmb.memory.cnt = 1; - lmb_analyze(); + memblock.memory.cnt = 1; + memblock_analyze(); /* reserve the hole */ - lmb_reserve(wii_hole_start, wii_hole_size); + memblock_reserve(wii_hole_start, wii_hole_size); /* allow ioremapping the address space in the hole */ __allow_ioremap_reserved = 1; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 39df70529d29..3fff8d979b41 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -41,7 +41,7 @@ #include <linux/smp.h> #include <linux/bitops.h> #include <linux/of_device.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/sections.h> diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 7b1d608ea3c8..1f9fb2c57761 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -204,7 +204,7 @@ int __init iob_init(struct device_node *dn) pr_debug(" -> %s\n", __func__); /* Allocate a spare page to map all invalid IOTLB pages. */ - tmp = lmb_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); + tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); if (!tmp) panic("IOBMAP: Cannot allocate spare page!"); /* Empty l1 is marked invalid */ @@ -275,7 +275,7 @@ void __init alloc_iobmap_l2(void) return; #endif /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */ - iob_l2_base = (u32 *)abs_to_virt(lmb_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); + iob_l2_base = (u32 *)abs_to_virt(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base); } diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index f1d0132ebcc7..9deb274841f1 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -51,7 +51,7 @@ #include <linux/suspend.h> #include <linux/of_device.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/reg.h> #include <asm/sections.h> @@ -619,7 +619,7 @@ static int __init pmac_probe(void) * driver needs that. We have to allocate it now. We allocate 4k * (1 small page) for now. */ - smu_cmdbuf_abs = lmb_alloc_base(4096, 4096, 0x80000000UL); + smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL); #endif /* CONFIG_PMAC_SMU */ return 1; diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c index 1e8a1e39dfe8..2c0ed87f2024 100644 --- a/arch/powerpc/platforms/ps3/htab.c +++ b/arch/powerpc/platforms/ps3/htab.c @@ -19,7 +19,7 @@ */ #include <linux/kernel.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/machdep.h> #include <asm/prom.h> diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 7925751e464a..c2045880e674 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -21,7 +21,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/memory_hotplug.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <asm/cell-regs.h> @@ -318,8 +318,8 @@ static int __init ps3_mm_add_memory(void) return result; } - lmb_add(start_addr, map.r1.size); - lmb_analyze(); + memblock_add(start_addr, map.r1.size); + memblock_analyze(); result = online_pages(start_pfn, nr_pages); diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index dd521a181f23..5b759b669598 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -24,7 +24,7 @@ #include <linux/fs.h> #include <linux/syscalls.h> #include <linux/ctype.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/of.h> #include <linux/slab.h> @@ -723,7 +723,7 @@ static void os_area_queue_work(void) * flash to a high address in the boot memory region and then puts that RAM * address and the byte count into the repository for retrieval by the guest. * We copy the data we want into a static variable and allow the memory setup - * by the HV to be claimed by the lmb manager. + * by the HV to be claimed by the memblock manager. * * The os area mirror will not be available to a second stage kernel, and * the header verify will fail. In this case, the saved_params values will diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 01e7b5bb3c1d..deab5f946090 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -10,14 +10,14 @@ */ #include <linux/of.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/vmalloc.h> #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> #include <asm/sparsemem.h> -static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size) +static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long start, start_pfn; struct zone *zone; @@ -26,7 +26,7 @@ static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size) start_pfn = base >> PAGE_SHIFT; if (!pfn_valid(start_pfn)) { - lmb_remove(base, lmb_size); + memblock_remove(base, memblock_size); return 0; } @@ -41,20 +41,20 @@ static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size) * to sysfs "state" file and we can't remove sysfs entries * while writing to it. So we have to defer it to here. */ - ret = __remove_pages(zone, start_pfn, lmb_size >> PAGE_SHIFT); + ret = __remove_pages(zone, start_pfn, memblock_size >> PAGE_SHIFT); if (ret) return ret; /* * Update memory regions for memory remove */ - lmb_remove(base, lmb_size); + memblock_remove(base, memblock_size); /* * Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(base); - ret = remove_section_mapping(start, start + lmb_size); + ret = remove_section_mapping(start, start + memblock_size); /* Ensure all vmalloc mappings are flushed in case they also * hit that section of memory @@ -69,7 +69,7 @@ static int pseries_remove_memory(struct device_node *np) const char *type; const unsigned int *regs; unsigned long base; - unsigned int lmb_size; + unsigned int memblock_size; int ret = -EINVAL; /* @@ -80,16 +80,16 @@ static int pseries_remove_memory(struct device_node *np) return 0; /* - * Find the bae address and size of the lmb + * Find the bae address and size of the memblock */ regs = of_get_property(np, "reg", NULL); if (!regs) return ret; base = *(unsigned long *)regs; - lmb_size = regs[3]; + memblock_size = regs[3]; - ret = pseries_remove_lmb(base, lmb_size); + ret = pseries_remove_memblock(base, memblock_size); return ret; } @@ -98,7 +98,7 @@ static int pseries_add_memory(struct device_node *np) const char *type; const unsigned int *regs; unsigned long base; - unsigned int lmb_size; + unsigned int memblock_size; int ret = -EINVAL; /* @@ -109,43 +109,43 @@ static int pseries_add_memory(struct device_node *np) return 0; /* - * Find the base and size of the lmb + * Find the base and size of the memblock */ regs = of_get_property(np, "reg", NULL); if (!regs) return ret; base = *(unsigned long *)regs; - lmb_size = regs[3]; + memblock_size = regs[3]; /* * Update memory region to represent the memory add */ - ret = lmb_add(base, lmb_size); + ret = memblock_add(base, memblock_size); return (ret < 0) ? -EINVAL : 0; } static int pseries_drconf_memory(unsigned long *base, unsigned int action) { struct device_node *np; - const unsigned long *lmb_size; + const unsigned long *memblock_size; int rc; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (!np) return -EINVAL; - lmb_size = of_get_property(np, "ibm,lmb-size", NULL); - if (!lmb_size) { + memblock_size = of_get_property(np, "ibm,memblock-size", NULL); + if (!memblock_size) { of_node_put(np); return -EINVAL; } if (action == PSERIES_DRCONF_MEM_ADD) { - rc = lmb_add(*base, *lmb_size); + rc = memblock_add(*base, *memblock_size); rc = (rc < 0) ? -EINVAL : 0; } else if (action == PSERIES_DRCONF_MEM_REMOVE) { - rc = pseries_remove_lmb(*base, *lmb_size); + rc = pseries_remove_memblock(*base, *memblock_size); } else { rc = -EINVAL; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index d26182d42cbf..395848e30c52 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -66,7 +66,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, tcep = ((u64 *)tbl->it_base) + index; while (npages--) { - /* can't move this out since we might cross LMB boundary */ + /* can't move this out since we might cross MEMBLOCK boundary */ rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c index 7ebd9e88d369..6e7742da0072 100644 --- a/arch/powerpc/platforms/pseries/phyp_dump.c +++ b/arch/powerpc/platforms/pseries/phyp_dump.c @@ -255,12 +255,12 @@ void invalidate_last_dump(struct phyp_dump_header *ph, unsigned long addr) /* ------------------------------------------------- */ /** - * release_memory_range -- release memory previously lmb_reserved + * release_memory_range -- release memory previously memblock_reserved * @start_pfn: starting physical frame number * @nr_pages: number of pages to free. * * This routine will release memory that had been previously - * lmb_reserved in early boot. The released memory becomes + * memblock_reserved in early boot. The released memory becomes * available for genreal use. */ static void release_memory_range(unsigned long start_pfn, diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index c8b96ed7c015..559db2b846a9 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -36,7 +36,7 @@ #include <linux/dma-mapping.h> #include <linux/vmalloc.h> #include <linux/suspend.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <asm/io.h> #include <asm/prom.h> @@ -232,7 +232,7 @@ static int __init dart_init(struct device_node *dart_node) * that to work around what looks like a problem with the HT bridge * prefetching into invalid pages and corrupting data */ - tmp = lmb_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); + tmp = memblock_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) & DARTMAP_RPNMASK); @@ -407,7 +407,7 @@ void __init alloc_dart_table(void) if (iommu_is_off) return; - if (!iommu_force_on && lmb_end_of_DRAM() <= 0x40000000ull) + if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull) return; /* 512 pages (2MB) is max DART tablesize. */ @@ -416,7 +416,7 @@ void __init alloc_dart_table(void) * will blow up an entire large page anyway in the kernel mapping */ dart_tablebase = (unsigned long) - abs_to_virt(lmb_alloc_base(1UL<<24, 1UL<<24, 0x80000000L)); + abs_to_virt(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L)); printk(KERN_INFO "DART table allocated at: %lx\n", dart_tablebase); } diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index a14760fe513a..356c6a0e1b23 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -23,7 +23,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/log2.h> #include <linux/slab.h> @@ -190,7 +190,7 @@ static void __init setup_pci_atmu(struct pci_controller *hose, pr_info("%s: PCICSRBAR @ 0x%x\n", name, pcicsrbar); /* Setup inbound mem window */ - mem = lmb_end_of_DRAM(); + mem = memblock_end_of_DRAM(); sz = min(mem, paddr_lo); mem_log = __ilog2_u64(sz); diff --git a/arch/powerpc/sysdev/micropatch.c b/arch/powerpc/sysdev/micropatch.c index d8d602840757..c0bb76ef7242 100644 --- a/arch/powerpc/sysdev/micropatch.c +++ b/arch/powerpc/sysdev/micropatch.c @@ -4,6 +4,7 @@ * also relocates SMC2, but this would require additional changes * to uart.c, so I am holding off on that for a moment. */ +#include <linux/init.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -16,6 +17,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/8xx_immap.h> +#include <asm/cpm.h> #include <asm/cpm1.h> /* @@ -24,7 +26,7 @@ #ifdef CONFIG_I2C_SPI_UCODE_PATCH -uint patch_2000[] = { +static uint patch_2000[] __initdata = { 0x7FFFEFD9, 0x3FFD0000, 0x7FFB49F7, @@ -143,7 +145,7 @@ uint patch_2000[] = { 0x5F8247F8 }; -uint patch_2f00[] = { +static uint patch_2f00[] __initdata = { 0x3E303430, 0x34343737, 0xABF7BF9B, @@ -182,7 +184,7 @@ uint patch_2f00[] = { #ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH -uint patch_2000[] = { +static uint patch_2000[] __initdata = { 0x3fff0000, 0x3ffd0000, 0x3ffb0000, @@ -505,7 +507,7 @@ uint patch_2000[] = { 0x6079e2bb }; -uint patch_2f00[] = { +static uint patch_2f00[] __initdata = { 0x30303030, 0x3e3e3434, 0xabbf9b99, @@ -572,7 +574,7 @@ uint patch_2f00[] = { 0xf22f3f23 }; -uint patch_2e00[] = { +static uint patch_2e00[] __initdata = { 0x27eeeeee, 0xeeeeeeee, 0xeeeeeeee, @@ -598,7 +600,7 @@ uint patch_2e00[] = { #ifdef CONFIG_USB_SOF_UCODE_PATCH -uint patch_2000[] = { +static uint patch_2000[] __initdata = { 0x7fff0000, 0x7ffd0000, 0x7ffb0000, @@ -613,21 +615,25 @@ uint patch_2000[] = { 0x60750000 }; -uint patch_2f00[] = { +static uint patch_2f00[] __initdata = { 0x3030304c, 0xcab9e441, 0xa1aaf220 }; #endif -void -cpm_load_patch(cpm8xx_t *cp) +void __init cpm_load_patch(cpm8xx_t *cp) { volatile uint *dp; /* Dual-ported RAM. */ volatile cpm8xx_t *commproc; +#if defined(CONFIG_I2C_SPI_UCODE_PATCH) || \ + defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH) volatile iic_t *iip; - volatile spi_t *spp; + volatile struct spi_pram *spp; +#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH volatile smc_uart_t *smp; +#endif +#endif int i; commproc = cp; @@ -668,8 +674,8 @@ cpm_load_patch(cpm8xx_t *cp) /* Put SPI above the IIC, also 32-byte aligned. */ i = (RPBASE + sizeof(iic_t) + 31) & ~31; - spp = (spi_t *)&commproc->cp_dparam[PROFF_SPI]; - spp->spi_rpbase = i; + spp = (struct spi_pram *)&commproc->cp_dparam[PROFF_SPI]; + spp->rpbase = i; # if defined(CONFIG_I2C_SPI_UCODE_PATCH) commproc->cp_cpmcr1 = 0x802a; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 573fca1fbd9b..82868fee21fd 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -10,7 +10,7 @@ config SUPERH select EMBEDDED select HAVE_CLK select HAVE_IDE if HAS_IOPORT - select HAVE_LMB + select HAVE_MEMBLOCK select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT select HAVE_ARCH_TRACEHOOK diff --git a/arch/sh/include/asm/lmb.h b/arch/sh/include/asm/lmb.h deleted file mode 100644 index 9b437f657ffa..000000000000 --- a/arch/sh/include/asm/lmb.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_SH_LMB_H -#define __ASM_SH_LMB_H - -#define LMB_REAL_LIMIT 0 - -#endif /* __ASM_SH_LMB_H */ diff --git a/arch/sh/include/asm/memblock.h b/arch/sh/include/asm/memblock.h new file mode 100644 index 000000000000..dfe683b88075 --- /dev/null +++ b/arch/sh/include/asm/memblock.h @@ -0,0 +1,6 @@ +#ifndef __ASM_SH_MEMBLOCK_H +#define __ASM_SH_MEMBLOCK_H + +#define MEMBLOCK_REAL_LIMIT 0 + +#endif /* __ASM_SH_MEMBLOCK_H */ diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c index 5a559e666eb3..e2a3af31ff99 100644 --- a/arch/sh/kernel/machine_kexec.c +++ b/arch/sh/kernel/machine_kexec.c @@ -15,7 +15,7 @@ #include <linux/numa.h> #include <linux/ftrace.h> #include <linux/suspend.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/mmu_context.h> @@ -157,10 +157,10 @@ void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - /* this is necessary because of lmb_phys_mem_size() */ - lmb_analyze(); + /* this is necessary because of memblock_phys_mem_size() */ + memblock_analyze(); - ret = parse_crashkernel(boot_command_line, lmb_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -172,14 +172,14 @@ void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crashk_res.end - crashk_res.start + 1); if (!crashk_res.start) { - unsigned long max = lmb_end_of_DRAM() - memory_limit; - crashk_res.start = __lmb_alloc_base(crash_size, PAGE_SIZE, max); + unsigned long max = memblock_end_of_DRAM() - memory_limit; + crashk_res.start = __memblock_alloc_base(crash_size, PAGE_SIZE, max); if (!crashk_res.start) { pr_err("crashkernel allocation failed\n"); goto disable; } } else { - ret = lmb_reserve(crashk_res.start, crash_size); + ret = memblock_reserve(crashk_res.start, crash_size); if (unlikely(ret < 0)) { pr_err("crashkernel reservation failed - " "memory is in use\n"); @@ -192,7 +192,7 @@ void __init reserve_crashkernel(void) /* * Crash kernel trumps memory limit */ - if ((lmb_end_of_DRAM() - memory_limit) <= crashk_res.end) { + if ((memblock_end_of_DRAM() - memory_limit) <= crashk_res.end) { memory_limit = 0; pr_info("Disabled memory limit for crashkernel\n"); } @@ -201,7 +201,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start), - (unsigned long)(lmb_phys_mem_size() >> 20)); + (unsigned long)(memblock_phys_mem_size() >> 20)); return; diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 272734681d29..e769401a78ba 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -30,7 +30,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/platform_device.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/page.h> @@ -141,10 +141,10 @@ void __init check_for_initrd(void) goto disable; } - if (unlikely(end > lmb_end_of_DRAM())) { + if (unlikely(end > memblock_end_of_DRAM())) { pr_err("initrd extends beyond end of memory " "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - end, (unsigned long)lmb_end_of_DRAM()); + end, (unsigned long)memblock_end_of_DRAM()); goto disable; } @@ -161,7 +161,7 @@ void __init check_for_initrd(void) initrd_start = (unsigned long)__va(__pa(start)); initrd_end = initrd_start + INITRD_SIZE; - lmb_reserve(__pa(initrd_start), INITRD_SIZE); + memblock_reserve(__pa(initrd_start), INITRD_SIZE); return; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 46f84de62469..d0e249100e98 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -16,7 +16,7 @@ #include <linux/pagemap.h> #include <linux/percpu.h> #include <linux/io.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/dma-mapping.h> #include <asm/mmu_context.h> #include <asm/mmzone.h> @@ -33,7 +33,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD]; void __init generic_mem_init(void) { - lmb_add(__MEMORY_START, __MEMORY_SIZE); + memblock_add(__MEMORY_START, __MEMORY_SIZE); } void __init __weak plat_mem_setup(void) @@ -176,12 +176,12 @@ void __init allocate_pgdat(unsigned int nid) get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #ifdef CONFIG_NEED_MULTIPLE_NODES - phys = __lmb_alloc_base(sizeof(struct pglist_data), + phys = __memblock_alloc_base(sizeof(struct pglist_data), SMP_CACHE_BYTES, end_pfn << PAGE_SHIFT); /* Retry with all of system memory */ if (!phys) - phys = __lmb_alloc_base(sizeof(struct pglist_data), - SMP_CACHE_BYTES, lmb_end_of_DRAM()); + phys = __memblock_alloc_base(sizeof(struct pglist_data), + SMP_CACHE_BYTES, memblock_end_of_DRAM()); if (!phys) panic("Can't allocate pgdat for node %d\n", nid); @@ -212,7 +212,7 @@ static void __init bootmem_init_one_node(unsigned int nid) total_pages = bootmem_bootmap_pages(p->node_spanned_pages); - paddr = lmb_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE); + paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE); if (!paddr) panic("Can't allocate bootmap for nid[%d]\n", nid); @@ -227,9 +227,9 @@ static void __init bootmem_init_one_node(unsigned int nid) */ if (nid == 0) { /* Reserve the sections we're already using. */ - for (i = 0; i < lmb.reserved.cnt; i++) - reserve_bootmem(lmb.reserved.region[i].base, - lmb_size_bytes(&lmb.reserved, i), + for (i = 0; i < memblock.reserved.cnt; i++) + reserve_bootmem(memblock.reserved.region[i].base, + memblock_size_bytes(&memblock.reserved, i), BOOTMEM_DEFAULT); } @@ -241,10 +241,10 @@ static void __init do_init_bootmem(void) int i; /* Add active regions with valid PFNs. */ - for (i = 0; i < lmb.memory.cnt; i++) { + for (i = 0; i < memblock.memory.cnt; i++) { unsigned long start_pfn, end_pfn; - start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; - end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i); __add_active_range(0, start_pfn, end_pfn); } @@ -276,7 +276,7 @@ static void __init early_reserve_mem(void) * this catches the (definitely buggy) case of us accidentally * initializing the bootmem allocator with an invalid RAM area. */ - lmb_reserve(__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET, + memblock_reserve(__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET, (PFN_PHYS(start_pfn) + PAGE_SIZE - 1) - (__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET)); @@ -284,7 +284,7 @@ static void __init early_reserve_mem(void) * Reserve physical pages below CONFIG_ZERO_PAGE_OFFSET. */ if (CONFIG_ZERO_PAGE_OFFSET != 0) - lmb_reserve(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET); + memblock_reserve(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET); /* * Handle additional early reservations @@ -299,27 +299,27 @@ void __init paging_init(void) unsigned long vaddr, end; int nid; - lmb_init(); + memblock_init(); sh_mv.mv_mem_init(); early_reserve_mem(); - lmb_enforce_memory_limit(memory_limit); - lmb_analyze(); + memblock_enforce_memory_limit(memory_limit); + memblock_analyze(); - lmb_dump_all(); + memblock_dump_all(); /* * Determine low and high memory ranges: */ - max_low_pfn = max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; + max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; min_low_pfn = __MEMORY_START >> PAGE_SHIFT; nodes_clear(node_online_map); memory_start = (unsigned long)__va(__MEMORY_START); - memory_end = memory_start + (memory_limit ?: lmb_phys_mem_size()); + memory_end = memory_start + (memory_limit ?: memblock_phys_mem_size()); uncached_init(); pmb_init(); diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c index a2e645f64a37..3d85225b9e95 100644 --- a/arch/sh/mm/numa.c +++ b/arch/sh/mm/numa.c @@ -9,7 +9,7 @@ */ #include <linux/module.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/numa.h> #include <linux/pfn.h> @@ -39,12 +39,12 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end) pmb_bolt_mapping((unsigned long)__va(start), start, end - start, PAGE_KERNEL); - lmb_add(start, end - start); + memblock_add(start, end - start); __add_active_range(nid, start_pfn, end_pfn); /* Node-local pgdat */ - NODE_DATA(nid) = __va(lmb_alloc_base(sizeof(struct pglist_data), + NODE_DATA(nid) = __va(memblock_alloc_base(sizeof(struct pglist_data), SMP_CACHE_BYTES, end)); memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); @@ -54,7 +54,7 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end) /* Node-local bootmap */ bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); - bootmem_paddr = lmb_alloc_base(bootmap_pages << PAGE_SHIFT, + bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT, PAGE_SIZE, end); init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT, start_pfn, end_pfn); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6f1470baa314..c0015db247ba 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -42,7 +42,7 @@ config SPARC64 select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES - select HAVE_LMB + select HAVE_MEMBLOCK select HAVE_SYSCALL_WRAPPERS select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/sparc/include/asm/lmb.h b/arch/sparc/include/asm/lmb.h deleted file mode 100644 index 6a352cbcf520..000000000000 --- a/arch/sparc/include/asm/lmb.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _SPARC64_LMB_H -#define _SPARC64_LMB_H - -#include <asm/oplib.h> - -#define LMB_DBG(fmt...) prom_printf(fmt) - -#define LMB_REAL_LIMIT 0 - -#endif /* !(_SPARC64_LMB_H) */ diff --git a/arch/sparc/include/asm/memblock.h b/arch/sparc/include/asm/memblock.h new file mode 100644 index 000000000000..f12af880649b --- /dev/null +++ b/arch/sparc/include/asm/memblock.h @@ -0,0 +1,10 @@ +#ifndef _SPARC64_MEMBLOCK_H +#define _SPARC64_MEMBLOCK_H + +#include <asm/oplib.h> + +#define MEMBLOCK_DBG(fmt...) prom_printf(fmt) + +#define MEMBLOCK_REAL_LIMIT 0 + +#endif /* !(_SPARC64_MEMBLOCK_H) */ diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index cdc91d919e93..83e85c2e802a 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -4,7 +4,7 @@ */ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/log2.h> #include <linux/list.h> #include <linux/slab.h> @@ -86,7 +86,7 @@ static void mdesc_handle_init(struct mdesc_handle *hp, hp->handle_size = handle_size; } -static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size) +static struct mdesc_handle * __init mdesc_memblock_alloc(unsigned int mdesc_size) { unsigned int handle_size, alloc_size; struct mdesc_handle *hp; @@ -97,7 +97,7 @@ static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size) mdesc_size); alloc_size = PAGE_ALIGN(handle_size); - paddr = lmb_alloc(alloc_size, PAGE_SIZE); + paddr = memblock_alloc(alloc_size, PAGE_SIZE); hp = NULL; if (paddr) { @@ -107,7 +107,7 @@ static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size) return hp; } -static void mdesc_lmb_free(struct mdesc_handle *hp) +static void mdesc_memblock_free(struct mdesc_handle *hp) { unsigned int alloc_size; unsigned long start; @@ -120,9 +120,9 @@ static void mdesc_lmb_free(struct mdesc_handle *hp) free_bootmem_late(start, alloc_size); } -static struct mdesc_mem_ops lmb_mdesc_ops = { - .alloc = mdesc_lmb_alloc, - .free = mdesc_lmb_free, +static struct mdesc_mem_ops memblock_mdesc_ops = { + .alloc = mdesc_memblock_alloc, + .free = mdesc_memblock_free, }; static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) @@ -914,7 +914,7 @@ void __init sun4v_mdesc_init(void) printk("MDESC: Size is %lu bytes.\n", len); - hp = mdesc_alloc(len, &lmb_mdesc_ops); + hp = mdesc_alloc(len, &memblock_mdesc_ops); if (hp == NULL) { prom_printf("MDESC: alloc of %lu bytes failed.\n", len); prom_halt(); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index fb06ac2bd38f..466a32763ea8 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -20,7 +20,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/module.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/of_device.h> #include <asm/prom.h> @@ -34,7 +34,7 @@ void * __init prom_early_alloc(unsigned long size) { - unsigned long paddr = lmb_alloc(size, SMP_CACHE_BYTES); + unsigned long paddr = memblock_alloc(size, SMP_CACHE_BYTES); void *ret; if (!paddr) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index b2831dc3c121..f0434513df15 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -23,7 +23,7 @@ #include <linux/cache.h> #include <linux/sort.h> #include <linux/percpu.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/gfp.h> @@ -726,7 +726,7 @@ static void __init find_ramdisk(unsigned long phys_base) initrd_start = ramdisk_image; initrd_end = ramdisk_image + sparc_ramdisk_size; - lmb_reserve(initrd_start, sparc_ramdisk_size); + memblock_reserve(initrd_start, sparc_ramdisk_size); initrd_start += PAGE_OFFSET; initrd_end += PAGE_OFFSET; @@ -822,7 +822,7 @@ static void __init allocate_node_data(int nid) struct pglist_data *p; #ifdef CONFIG_NEED_MULTIPLE_NODES - paddr = lmb_alloc_nid(sizeof(struct pglist_data), + paddr = memblock_alloc_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid, nid_range); if (!paddr) { prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); @@ -843,7 +843,7 @@ static void __init allocate_node_data(int nid) if (p->node_spanned_pages) { num_pages = bootmem_bootmap_pages(p->node_spanned_pages); - paddr = lmb_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid, + paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid, nid_range); if (!paddr) { prom_printf("Cannot allocate bootmap for nid[%d]\n", @@ -974,11 +974,11 @@ static void __init add_node_ranges(void) { int i; - for (i = 0; i < lmb.memory.cnt; i++) { - unsigned long size = lmb_size_bytes(&lmb.memory, i); + for (i = 0; i < memblock.memory.cnt; i++) { + unsigned long size = memblock_size_bytes(&memblock.memory, i); unsigned long start, end; - start = lmb.memory.region[i].base; + start = memblock.memory.region[i].base; end = start + size; while (start < end) { unsigned long this_end; @@ -1010,7 +1010,7 @@ static int __init grab_mlgroups(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = lmb_alloc(count * sizeof(struct mdesc_mlgroup), + paddr = memblock_alloc(count * sizeof(struct mdesc_mlgroup), SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; @@ -1051,7 +1051,7 @@ static int __init grab_mblocks(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = lmb_alloc(count * sizeof(struct mdesc_mblock), + paddr = memblock_alloc(count * sizeof(struct mdesc_mblock), SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; @@ -1279,8 +1279,8 @@ static int bootmem_init_numa(void) static void __init bootmem_init_nonnuma(void) { - unsigned long top_of_ram = lmb_end_of_DRAM(); - unsigned long total_ram = lmb_phys_mem_size(); + unsigned long top_of_ram = memblock_end_of_DRAM(); + unsigned long total_ram = memblock_phys_mem_size(); unsigned int i; numadbg("bootmem_init_nonnuma()\n"); @@ -1292,15 +1292,15 @@ static void __init bootmem_init_nonnuma(void) init_node_masks_nonnuma(); - for (i = 0; i < lmb.memory.cnt; i++) { - unsigned long size = lmb_size_bytes(&lmb.memory, i); + for (i = 0; i < memblock.memory.cnt; i++) { + unsigned long size = memblock_size_bytes(&memblock.memory, i); unsigned long start_pfn, end_pfn; if (!size) continue; - start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; - end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i); add_active_range(0, start_pfn, end_pfn); } @@ -1338,9 +1338,9 @@ static void __init trim_reserved_in_node(int nid) numadbg(" trim_reserved_in_node(%d)\n", nid); - for (i = 0; i < lmb.reserved.cnt; i++) { - unsigned long start = lmb.reserved.region[i].base; - unsigned long size = lmb_size_bytes(&lmb.reserved, i); + for (i = 0; i < memblock.reserved.cnt; i++) { + unsigned long start = memblock.reserved.region[i].base; + unsigned long size = memblock_size_bytes(&memblock.reserved, i); unsigned long end = start + size; reserve_range_in_node(nid, start, end); @@ -1384,7 +1384,7 @@ static unsigned long __init bootmem_init(unsigned long phys_base) unsigned long end_pfn; int nid; - end_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; + end_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; max_pfn = max_low_pfn = end_pfn; min_low_pfn = (phys_base >> PAGE_SHIFT); @@ -1734,7 +1734,7 @@ void __init paging_init(void) sun4v_ktsb_init(); } - lmb_init(); + memblock_init(); /* Find available physical memory... * @@ -1752,17 +1752,17 @@ void __init paging_init(void) phys_base = 0xffffffffffffffffUL; for (i = 0; i < pavail_ents; i++) { phys_base = min(phys_base, pavail[i].phys_addr); - lmb_add(pavail[i].phys_addr, pavail[i].reg_size); + memblock_add(pavail[i].phys_addr, pavail[i].reg_size); } - lmb_reserve(kern_base, kern_size); + memblock_reserve(kern_base, kern_size); find_ramdisk(phys_base); - lmb_enforce_memory_limit(cmdline_memory_size); + memblock_enforce_memory_limit(cmdline_memory_size); - lmb_analyze(); - lmb_dump_all(); + memblock_analyze(); + memblock_dump_all(); set_bit(0, mmu_context_bmap); @@ -1816,8 +1816,8 @@ void __init paging_init(void) */ for_each_possible_cpu(i) { /* XXX Use node local allocations... XXX */ - softirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); - hardirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + softirq_stack[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + hardirq_stack[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); } /* Setup bootmem... */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 519b54327d75..baa579c8e038 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -142,6 +142,7 @@ struct x86_cpuinit_ops { * @set_wallclock: set time back to HW clock * @is_untracked_pat_range exclude from PAT logic * @nmi_init enable NMI on cpus + * @i8042_detect pre-detect if i8042 controller exists */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); @@ -150,6 +151,7 @@ struct x86_platform_ops { void (*iommu_shutdown)(void); bool (*is_untracked_pat_range)(u64 start, u64 end); void (*nmi_init)(void); + int (*i8042_detect)(void); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c02cc692985c..a96489ee6cab 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -921,7 +921,7 @@ void disable_local_APIC(void) unsigned int value; /* APIC hasn't been mapped yet */ - if (!apic_phys) + if (!x2apic_mode && !apic_phys) return; clear_local_APIC(); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index ebdb85cf2686..e5cc7e82e60d 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -18,6 +18,7 @@ #include <asm/apic.h> #include <asm/iommu.h> #include <asm/gart.h> +#include <asm/hpet.h> static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -191,6 +192,21 @@ static void __init ati_bugs_contd(int num, int slot, int func) } #endif +/* + * Force the read back of the CMP register in hpet_next_event() + * to work around the problem that the CMP register write seems to be + * delayed. See hpet_next_event() for details. + * + * We do this on all SMBUS incarnations for now until we have more + * information about the affected chipsets. + */ +static void __init ati_hpet_bugs(int num, int slot, int func) +{ +#ifdef CONFIG_HPET_TIMER + hpet_readback_cmp = 1; +#endif +} + #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -220,6 +236,8 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs }, { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, + { PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs }, {} }; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 345a4b1fe144..675879b65ce6 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -640,8 +640,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) /* Skip cs, ip, orig_ax and gs. */ \ " subl $16, %esp\n" \ " pushl %fs\n" \ - " pushl %ds\n" \ " pushl %es\n" \ + " pushl %ds\n" \ " pushl %eax\n" \ " pushl %ebp\n" \ " pushl %edi\n" \ diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index e796448f0eb5..5915e0b33303 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -216,6 +216,12 @@ static void __init mrst_setup_boot_clock(void) setup_boot_APIC_clock(); }; +/* MID systems don't have i8042 controller */ +static int mrst_i8042_detect(void) +{ + return 0; +} + /* * Moorestown specific x86_init function overrides and early setup * calls. @@ -233,6 +239,7 @@ void __init x86_mrst_early_setup(void) x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; + x86_platform.i8042_detect = mrst_i8042_detect; x86_init.pci.init = pci_mrst_init; x86_init.pci.fixup_irqs = x86_init_noop; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index e72d3fc6547d..939b9e98245f 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -498,15 +498,10 @@ void force_hpet_resume(void) * See erratum #27 (Misinterpreted MSI Requests May Result in * Corrupted LPC DMA Data) in AMD Publication #46837, * "SB700 Family Product Errata", Rev. 1.0, March 2010. - * - * Also force the read back of the CMP register in hpet_next_event() - * to work around the problem that the CMP register write seems to be - * delayed. See hpet_next_event() for details. */ static void force_disable_hpet_msi(struct pci_dev *unused) { hpet_msi_disable = 1; - hpet_readback_cmp = 1; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index de3b63ae3da2..690c2c09faf3 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -238,6 +238,15 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_NUMA per_cpu(x86_cpu_to_node_map, cpu) = early_per_cpu_map(x86_cpu_to_node_map, cpu); + /* + * Ensure taht the boot cpu numa_node is correct when the boot + * cpu is on a node that doesn't have memory installed. + * Also cpu_up() will call cpu_to_node() for APs when + * MEMORY_HOTPLUG is defined, before per_cpu(numa_node) is set + * up later with c_init aka intel_init/amd_init. + * So set them all (boot cpu and all APs). + */ + set_cpu_numa_node(cpu, early_cpu_to_node(cpu)); #endif #endif /* @@ -257,14 +266,6 @@ void __init setup_per_cpu_areas(void) early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA) - /* - * make sure boot cpu numa_node is right, when boot cpu is on the - * node that doesn't have mem installed - */ - set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id)); -#endif - /* Setup node to cpumask map */ setup_node_to_cpumask_map(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 61a1e8c7e19f..cd6da6bf3eca 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -5,6 +5,7 @@ */ #include <linux/init.h> #include <linux/ioport.h> +#include <linux/module.h> #include <asm/bios_ebda.h> #include <asm/paravirt.h> @@ -85,6 +86,7 @@ struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { }; static void default_nmi_init(void) { }; +static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, @@ -92,5 +94,8 @@ struct x86_platform_ops x86_platform = { .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, - .nmi_init = default_nmi_init + .nmi_init = default_nmi_init, + .i8042_detect = default_i8042_detect }; + +EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a6f695d76928..b1ed0a1a5913 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1879,6 +1879,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*sptep), pfn); rmap_remove(vcpu->kvm, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } else was_rmapped = 1; } @@ -2924,7 +2926,7 @@ static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm) return kvm_mmu_zap_page(kvm, page) + 1; } -static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) +static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { struct kvm *kvm; struct kvm *kvm_freed = NULL; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 859a01a07dbf..ee03679efe78 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1744,18 +1744,15 @@ static void enter_lmode(struct kvm_vcpu *vcpu) (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); } - vcpu->arch.efer |= EFER_LMA; - vmx_set_efer(vcpu, vcpu->arch.efer); + vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } static void exit_lmode(struct kvm_vcpu *vcpu) { - vcpu->arch.efer &= ~EFER_LMA; - vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) & ~VM_ENTRY_IA32E_MODE); - vmx_set_efer(vcpu, vcpu->arch.efer); + vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } #endif diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 6fdb3ec30c31..55253095be84 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -184,6 +184,7 @@ static void __init pcibios_allocate_resources(int pass) idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { /* We'll assign a new address later */ + dev->fw_addr[idx] = r->start; r->end -= r->start; r->start = 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 7ef3a2735df3..cb29191cee58 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -66,8 +66,9 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn) devfn, pos, 4, &pcie_cap)) return 0; - if (pcie_cap == 0xffffffff) - return 0; + if (PCI_EXT_CAP_ID(pcie_cap) == 0x0000 || + PCI_EXT_CAP_ID(pcie_cap) == 0xffff) + break; if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) { raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number, @@ -76,7 +77,7 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn) return pos; } - pos = pcie_cap >> 20; + pos = PCI_EXT_CAP_NEXT(pcie_cap); } return 0; diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c index 98a66103f4f2..a854df2a5a4b 100644 --- a/crypto/ablkcipher.c +++ b/crypto/ablkcipher.c @@ -165,7 +165,7 @@ static inline int ablkcipher_next_slow(struct ablkcipher_request *req, p = kmalloc(n, GFP_ATOMIC); if (!p) - ablkcipher_walk_done(req, walk, -ENOMEM); + return ablkcipher_walk_done(req, walk, -ENOMEM); base = p + 1; diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c index d7be69f13154..b7dab32ce63c 100644 --- a/drivers/clocksource/cs5535-clockevt.c +++ b/drivers/clocksource/cs5535-clockevt.c @@ -194,6 +194,6 @@ err_timer: module_init(cs5535_mfgpt_init); -MODULE_AUTHOR("Andres Salomon <dilinger@collabora.co.uk>"); +MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>"); MODULE_DESCRIPTION("CS5535/CS5536 MFGPT clock event driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index aedef7941b22..0d2f9dbb47e4 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -209,7 +209,7 @@ config EDAC_I5100 config EDAC_MPC85XX tristate "Freescale MPC83xx / MPC85xx" - depends on EDAC_MM_EDAC && FSL_SOC && (PPC_83xx || MPC85xx) + depends on EDAC_MM_EDAC && FSL_SOC && (PPC_83xx || PPC_85xx) help Support for error detection and correction on the Freescale MPC8349, MPC8560, MPC8540, MPC8548 diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 52ca09bf4726..f39b00a46eda 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -1120,6 +1120,7 @@ static struct of_device_id mpc85xx_mc_err_of_match[] = { { .compatible = "fsl,mpc8555-memory-controller", }, { .compatible = "fsl,mpc8560-memory-controller", }, { .compatible = "fsl,mpc8568-memory-controller", }, + { .compatible = "fsl,mpc8569-memory-controller", }, { .compatible = "fsl,mpc8572-memory-controller", }, { .compatible = "fsl,mpc8349-memory-controller", }, { .compatible = "fsl,p2020-memory-controller", }, diff --git a/drivers/gpio/cs5535-gpio.c b/drivers/gpio/cs5535-gpio.c index f73a1555e49d..e23c06893d19 100644 --- a/drivers/gpio/cs5535-gpio.c +++ b/drivers/gpio/cs5535-gpio.c @@ -352,6 +352,6 @@ static void __exit cs5535_gpio_exit(void) module_init(cs5535_gpio_init); module_exit(cs5535_gpio_exit); -MODULE_AUTHOR("Andres Salomon <dilinger@collabora.co.uk>"); +MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>"); MODULE_DESCRIPTION("AMD CS5535/CS5536 GPIO driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 43ce3809ef64..51bd301cf10d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2241,6 +2241,7 @@ i915_gem_object_get_pages(struct drm_gem_object *obj, page = read_cache_page_gfp(mapping, i, GFP_HIGHUSER | __GFP_COLD | + __GFP_RECLAIMABLE | gfpmask); if (IS_ERR(page)) goto err_pages; @@ -4987,7 +4988,7 @@ i915_gpu_is_active(struct drm_device *dev) } static int -i915_gem_shrink(int nr_to_scan, gfp_t gfp_mask) +i915_gem_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { drm_i915_private_t *dev_priv, *next_dev; struct drm_i915_gem_object *obj_priv, *next_obj; diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 0f9a4785d798..3525f533e186 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -69,11 +69,11 @@ config KEYBOARD_ATARI module will be called atakbd. config KEYBOARD_ATKBD - tristate "AT keyboard" if EMBEDDED || !X86 || X86_MRST + tristate "AT keyboard" if EMBEDDED || !X86 default y select SERIO select SERIO_LIBPS2 - select SERIO_I8042 if X86 && !X86_MRST + select SERIO_I8042 if X86 select SERIO_GSCPS2 if GSC help Say Y here if you want to use a standard AT or PS/2 keyboard. Usually diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig index eeb58c1cac16..c714ca2407f8 100644 --- a/drivers/input/mouse/Kconfig +++ b/drivers/input/mouse/Kconfig @@ -17,7 +17,7 @@ config MOUSE_PS2 default y select SERIO select SERIO_LIBPS2 - select SERIO_I8042 if X86 && !X86_MRST + select SERIO_I8042 if X86 select SERIO_GSCPS2 if GSC help Say Y here if you have a PS/2 mouse connected to your system. This diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 40cea334ad13..9ba9c4a17e15 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -206,6 +206,7 @@ static int synaptics_resolution(struct psmouse *psmouse) unsigned char max[3]; if (SYN_ID_MAJOR(priv->identity) < 4) + return 0; if (synaptics_send_cmd(psmouse, SYN_QUE_RESOLUTION, res) == 0) { if (res[0] != 0 && (res[1] & 0x80) && res[2] != 0) { diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig index 256b9e9394dc..3bfe8fafc6ad 100644 --- a/drivers/input/serio/Kconfig +++ b/drivers/input/serio/Kconfig @@ -22,7 +22,7 @@ config SERIO_I8042 tristate "i8042 PC Keyboard controller" if EMBEDDED || !X86 default y depends on !PARISC && (!ARM || ARCH_SHARK || FOOTBRIDGE_HOST) && \ - (!SUPERH || SH_CAYMAN) && !M68K && !BLACKFIN && !X86_MRST + (!SUPERH || SH_CAYMAN) && !M68K && !BLACKFIN help i8042 is the chip over which the standard AT keyboard and PS/2 mouse are connected to the computer. If you use these devices, diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 6168469ad1a6..81003c4739f4 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -7,6 +7,10 @@ * the Free Software Foundation. */ +#ifdef CONFIG_X86 +#include <asm/x86_init.h> +#endif + /* * Names. */ @@ -840,6 +844,12 @@ static int __init i8042_platform_init(void) { int retval; +#ifdef CONFIG_X86 + /* Just return if pre-detection shows no i8042 controller exist */ + if (!x86_platform.i8042_detect()) + return -ENODEV; +#endif + /* * On ix86 platforms touching the i8042 data register region can do really * bad things. Because of this the region is always reserved on ix86 boxes. diff --git a/drivers/input/touchscreen/w90p910_ts.c b/drivers/input/touchscreen/w90p910_ts.c index cc18265be1a8..7a45d68c3516 100644 --- a/drivers/input/touchscreen/w90p910_ts.c +++ b/drivers/input/touchscreen/w90p910_ts.c @@ -233,7 +233,7 @@ static int __devinit w90x900ts_probe(struct platform_device *pdev) w90p910_ts->state = TS_IDLE; spin_lock_init(&w90p910_ts->lock); setup_timer(&w90p910_ts->timer, w90p910_check_pen_up, - (unsigned long)&w90p910_ts); + (unsigned long)w90p910_ts); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { diff --git a/drivers/misc/cs5535-mfgpt.c b/drivers/misc/cs5535-mfgpt.c index 9bec24db4d41..2d44b3300104 100644 --- a/drivers/misc/cs5535-mfgpt.c +++ b/drivers/misc/cs5535-mfgpt.c @@ -366,6 +366,6 @@ static int __init cs5535_mfgpt_init(void) module_init(cs5535_mfgpt_init); -MODULE_AUTHOR("Andres Salomon <dilinger@collabora.co.uk>"); +MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>"); MODULE_DESCRIPTION("CS5535/CS5536 MFGPT timer driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index af217924a76e..ad30f074ee15 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -365,6 +365,26 @@ static int __devinit sdhci_s3c_probe(struct platform_device *pdev) static int __devexit sdhci_s3c_remove(struct platform_device *pdev) { + struct sdhci_host *host = platform_get_drvdata(pdev); + struct sdhci_s3c *sc = sdhci_priv(host); + int ptr; + + sdhci_remove_host(host, 1); + + for (ptr = 0; ptr < 3; ptr++) { + clk_disable(sc->clk_bus[ptr]); + clk_put(sc->clk_bus[ptr]); + } + clk_disable(sc->clk_io); + clk_put(sc->clk_io); + + iounmap(host->ioaddr); + release_resource(sc->ioarea); + kfree(sc->ioarea); + + sdhci_free_host(host); + platform_set_drvdata(pdev, NULL); + return 0; } diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 7acb3edc47ef..2602852cc55a 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -677,7 +677,7 @@ static int ibmveth_close(struct net_device *netdev) if (!adapter->pool_config) netif_stop_queue(netdev); - free_irq(netdev->irq, netdev); + h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE); do { lpar_rc = h_free_logical_lan(adapter->vdev->unit_address); @@ -689,6 +689,8 @@ static int ibmveth_close(struct net_device *netdev) lpar_rc); } + free_irq(netdev->irq, netdev); + adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8); ibmveth_cleanup(adapter); diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c index 5b3dfb4ab279..33525bf2a3d3 100644 --- a/drivers/net/pcmcia/axnet_cs.c +++ b/drivers/net/pcmcia/axnet_cs.c @@ -1168,6 +1168,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) int interrupts, nr_serviced = 0, i; struct ei_device *ei_local; int handled = 0; + unsigned long flags; e8390_base = dev->base_addr; ei_local = netdev_priv(dev); @@ -1176,7 +1177,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) * Protect the irq test too. */ - spin_lock(&ei_local->page_lock); + spin_lock_irqsave(&ei_local->page_lock, flags); if (ei_local->irqlock) { @@ -1188,7 +1189,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) dev->name, inb_p(e8390_base + EN0_ISR), inb_p(e8390_base + EN0_IMR)); #endif - spin_unlock(&ei_local->page_lock); + spin_unlock_irqrestore(&ei_local->page_lock, flags); return IRQ_NONE; } @@ -1261,7 +1262,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) ei_local->irqlock = 0; outb_p(ENISR_ALL, e8390_base + EN0_IMR); - spin_unlock(&ei_local->page_lock); + spin_unlock_irqrestore(&ei_local->page_lock, flags); return IRQ_RETVAL(handled); } diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 96b6cfbf0a3a..cdc6a5c2e70d 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -1316,7 +1316,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, { 0x7c800000, 0x28000000, RTL_GIGA_MAC_VER_26 }, /* 8168C family. */ - { 0x7cf00000, 0x3ca00000, RTL_GIGA_MAC_VER_24 }, + { 0x7cf00000, 0x3cb00000, RTL_GIGA_MAC_VER_24 }, { 0x7cf00000, 0x3c900000, RTL_GIGA_MAC_VER_23 }, { 0x7cf00000, 0x3c800000, RTL_GIGA_MAC_VER_18 }, { 0x7c800000, 0x3c800000, RTL_GIGA_MAC_VER_24 }, diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 77b359162d6c..23c15aa9fbd5 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -730,13 +730,17 @@ static int ath9k_hif_usb_alloc_urbs(struct hif_device_usb *hif_dev) /* RX */ if (ath9k_hif_usb_alloc_rx_urbs(hif_dev) < 0) - goto err; + goto err_rx; /* Register Read */ if (ath9k_hif_usb_alloc_reg_in_urb(hif_dev) < 0) - goto err; + goto err_reg; return 0; +err_reg: + ath9k_hif_usb_dealloc_rx_urbs(hif_dev); +err_rx: + ath9k_hif_usb_dealloc_tx_urbs(hif_dev); err: return -ENOMEM; } diff --git a/drivers/net/wireless/hostap/hostap_pci.c b/drivers/net/wireless/hostap/hostap_pci.c index d24dc7dc0723..972a9c3af39e 100644 --- a/drivers/net/wireless/hostap/hostap_pci.c +++ b/drivers/net/wireless/hostap/hostap_pci.c @@ -330,6 +330,7 @@ static int prism2_pci_probe(struct pci_dev *pdev, dev->irq = pdev->irq; hw_priv->mem_start = mem; + dev->base_addr = (unsigned long) mem; prism2_pci_cor_sreset(local); diff --git a/drivers/net/wireless/iwlwifi/iwl-sta.h b/drivers/net/wireless/iwlwifi/iwl-sta.h index c2a453a1a991..dc43ebd1f1fd 100644 --- a/drivers/net/wireless/iwlwifi/iwl-sta.h +++ b/drivers/net/wireless/iwlwifi/iwl-sta.h @@ -97,6 +97,17 @@ static inline void iwl_clear_driver_stations(struct iwl_priv *priv) spin_lock_irqsave(&priv->sta_lock, flags); memset(priv->stations, 0, sizeof(priv->stations)); priv->num_stations = 0; + + /* + * Remove all key information that is not stored as part of station + * information since mac80211 may not have had a + * chance to remove all the keys. When device is reconfigured by + * mac80211 after an error all keys will be reconfigured. + */ + priv->ucode_key_table = 0; + priv->key_mapping_key = 0; + memset(priv->wep_keys, 0, sizeof(priv->wep_keys)); + spin_unlock_irqrestore(&priv->sta_lock, flags); } diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 3ae468c4d760..f20d3eeeea7f 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -854,6 +854,11 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) BIT(NL80211_IFTYPE_WDS); /* + * Initialize configuration work. + */ + INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled); + + /* * Let the driver probe the device to detect the capabilities. */ retval = rt2x00dev->ops->lib->probe_hw(rt2x00dev); @@ -863,11 +868,6 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) } /* - * Initialize configuration work. - */ - INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled); - - /* * Allocate queue array. */ retval = rt2x00queue_allocate(rt2x00dev); diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 92379e2d37e7..2aaa13150de3 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -156,6 +156,38 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, pcibios_align_resource, dev); } + if (ret < 0 && dev->fw_addr[resno]) { + struct resource *root, *conflict; + resource_size_t start, end; + + /* + * If we failed to assign anything, let's try the address + * where firmware left it. That at least has a chance of + * working, which is better than just leaving it disabled. + */ + + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + else + root = &iomem_resource; + + start = res->start; + end = res->end; + res->start = dev->fw_addr[resno]; + res->end = res->start + size - 1; + dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n", + resno, res); + conflict = request_resource_conflict(root, res); + if (conflict) { + dev_info(&dev->dev, + "BAR %d: %pR conflicts with %s %pR\n", resno, + res, conflict->name, conflict); + res->start = start; + res->end = end; + } else + ret = 0; + } + if (!ret) { res->flags &= ~IORESOURCE_STARTALIGN; dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res); diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 40658e3385b4..bb2f1fba637b 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -489,7 +489,7 @@ int intel_scu_ipc_simple_command(int cmd, int sub) mutex_unlock(&ipclock); return -ENODEV; } - ipc_command(cmd << 12 | sub); + ipc_command(sub << 12 | cmd); err = busy_loop(); mutex_unlock(&ipclock); return err; @@ -501,9 +501,9 @@ EXPORT_SYMBOL(intel_scu_ipc_simple_command); * @cmd: command * @sub: sub type * @in: input data - * @inlen: input length + * @inlen: input length in dwords * @out: output data - * @outlein: output length + * @outlein: output length in dwords * * Issue a command to the SCU which involves data transfers. Do the * data copies under the lock but leave it for the caller to interpret @@ -524,7 +524,7 @@ int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, for (i = 0; i < inlen; i++) ipc_data_writel(*in++, 4 * i); - ipc_command((cmd << 12) | sub | (inlen << 18)); + ipc_command((sub << 12) | cmd | (inlen << 18)); err = busy_loop(); for (i = 0; i < outlen; i++) @@ -556,6 +556,10 @@ int intel_scu_ipc_i2c_cntrl(u32 addr, u32 *data) u32 cmd = 0; mutex_lock(&ipclock); + if (ipcdev.pdev == NULL) { + mutex_unlock(&ipclock); + return -ENODEV; + } cmd = (addr >> 24) & 0xFF; if (cmd == IPC_I2C_READ) { writel(addr, ipcdev.i2c_base + IPC_I2C_CNTRL_ADDR); diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c index d762a0cbc6af..2afbeec8b791 100644 --- a/drivers/power/ds2782_battery.c +++ b/drivers/power/ds2782_battery.c @@ -163,7 +163,7 @@ static int ds2782_get_capacity(struct ds278x_info *info, int *capacity) if (err) return err; *capacity = raw; - return raw; + return 0; } static int ds2786_get_current(struct ds278x_info *info, int *current_uA) diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 34d51dd4c539..bed7b4634ccd 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -948,8 +948,10 @@ static ssize_t dasd_alias_show(struct device *dev, if (device->discipline && device->discipline->get_uid && !device->discipline->get_uid(device, &uid)) { if (uid.type == UA_BASE_PAV_ALIAS || - uid.type == UA_HYPER_PAV_ALIAS) + uid.type == UA_HYPER_PAV_ALIAS) { + dasd_put_device(device); return sprintf(buf, "1\n"); + } } dasd_put_device(device); diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index ce7cb87479fe..407d0e9adfaf 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -713,7 +713,7 @@ int chsc_determine_base_channel_path_desc(struct chp_id chpid, ret = chsc_determine_channel_path_desc(chpid, 0, 0, 0, 0, chsc_resp); if (ret) goto out_free; - memcpy(desc, &chsc_resp->data, chsc_resp->length); + memcpy(desc, &chsc_resp->data, sizeof(*desc)); out_free: kfree(chsc_resp); return ret; diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c index ffa111a7e9d4..97ab0a81338a 100644 --- a/drivers/spi/spi_mpc8xxx.c +++ b/drivers/spi/spi_mpc8xxx.c @@ -66,28 +66,6 @@ struct mpc8xxx_spi_reg { __be32 receive; }; -/* SPI Parameter RAM */ -struct spi_pram { - __be16 rbase; /* Rx Buffer descriptor base address */ - __be16 tbase; /* Tx Buffer descriptor base address */ - u8 rfcr; /* Rx function code */ - u8 tfcr; /* Tx function code */ - __be16 mrblr; /* Max receive buffer length */ - __be32 rstate; /* Internal */ - __be32 rdp; /* Internal */ - __be16 rbptr; /* Internal */ - __be16 rbc; /* Internal */ - __be32 rxtmp; /* Internal */ - __be32 tstate; /* Internal */ - __be32 tdp; /* Internal */ - __be16 tbptr; /* Internal */ - __be16 tbc; /* Internal */ - __be32 txtmp; /* Internal */ - __be32 res; /* Tx temp. */ - __be16 rpbase; /* Relocation pointer (CPM1 only) */ - __be16 res1; /* Reserved */ -}; - /* SPI Controller mode register definitions */ #define SPMODE_LOOP (1 << 30) #define SPMODE_CI_INACTIVEHIGH (1 << 29) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 57a593c58cf4..d219070fed3d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -177,8 +177,8 @@ static void handle_tx(struct vhost_net *net) break; } if (err != len) - pr_err("Truncated TX packet: " - " len %d != %zd\n", err, len); + pr_debug("Truncated TX packet: " + " len %d != %zd\n", err, len); vhost_add_used_and_signal(&net->dev, vq, head, 0); total_len += len; if (unlikely(total_len >= VHOST_NET_WEIGHT)) { @@ -275,8 +275,8 @@ static void handle_rx(struct vhost_net *net) } /* TODO: Should check and handle checksum. */ if (err > len) { - pr_err("Discarded truncated rx packet: " - " len %d > %zd\n", err, len); + pr_debug("Discarded truncated rx packet: " + " len %d > %zd\n", err, len); vhost_discard_vq_desc(vq); continue; } @@ -534,11 +534,16 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) rcu_assign_pointer(vq->private_data, sock); vhost_net_enable_vq(n, vq); done: + mutex_unlock(&vq->mutex); + if (oldsock) { vhost_net_flush_vq(n, index); fput(oldsock->file); } + mutex_unlock(&n->dev.mutex); + return 0; + err_vq: mutex_unlock(&vq->mutex); err: diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 0d1d966b0fe4..c3df14ce2cc2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2304,12 +2304,17 @@ noinline int btrfs_leaf_free_space(struct btrfs_root *root, return ret; } +/* + * min slot controls the lowest index we're willing to push to the + * right. We'll push up to and including min_slot, but no lower + */ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *right, - int free_space, u32 left_nritems) + int free_space, u32 left_nritems, + u32 min_slot) { struct extent_buffer *left = path->nodes[0]; struct extent_buffer *upper = path->nodes[1]; @@ -2327,7 +2332,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, if (empty) nr = 0; else - nr = 1; + nr = max_t(u32, 1, min_slot); if (path->slots[0] >= left_nritems) push_space += data_size; @@ -2469,10 +2474,14 @@ out_unlock: * * returns 1 if the push failed because the other node didn't have enough * room, 0 if everything worked out and < 0 if there were major errors. + * + * this will push starting from min_slot to the end of the leaf. It won't + * push any slot lower than min_slot */ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_path *path, int data_size, - int empty) + *root, struct btrfs_path *path, + int min_data_size, int data_size, + int empty, u32 min_slot) { struct extent_buffer *left = path->nodes[0]; struct extent_buffer *right; @@ -2514,8 +2523,8 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (left_nritems == 0) goto out_unlock; - return __push_leaf_right(trans, root, path, data_size, empty, - right, free_space, left_nritems); + return __push_leaf_right(trans, root, path, min_data_size, empty, + right, free_space, left_nritems, min_slot); out_unlock: btrfs_tree_unlock(right); free_extent_buffer(right); @@ -2525,12 +2534,17 @@ out_unlock: /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise + * + * max_slot can put a limit on how far into the leaf we'll push items. The + * item at 'max_slot' won't be touched. Use (u32)-1 to make us do all the + * items */ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *left, - int free_space, int right_nritems) + int free_space, u32 right_nritems, + u32 max_slot) { struct btrfs_disk_key disk_key; struct extent_buffer *right = path->nodes[0]; @@ -2549,9 +2563,9 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, slot = path->slots[1]; if (empty) - nr = right_nritems; + nr = min(right_nritems, max_slot); else - nr = right_nritems - 1; + nr = min(right_nritems - 1, max_slot); for (i = 0; i < nr; i++) { item = btrfs_item_nr(right, i); @@ -2712,10 +2726,14 @@ out: /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise + * + * max_slot can put a limit on how far into the leaf we'll push items. The + * item at 'max_slot' won't be touched. Use (u32)-1 to make us push all the + * items */ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_path *path, int data_size, - int empty) + *root, struct btrfs_path *path, int min_data_size, + int data_size, int empty, u32 max_slot) { struct extent_buffer *right = path->nodes[0]; struct extent_buffer *left; @@ -2761,8 +2779,9 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root goto out; } - return __push_leaf_left(trans, root, path, data_size, - empty, left, free_space, right_nritems); + return __push_leaf_left(trans, root, path, min_data_size, + empty, left, free_space, right_nritems, + max_slot); out: btrfs_tree_unlock(left); free_extent_buffer(left); @@ -2855,6 +2874,64 @@ static noinline int copy_for_split(struct btrfs_trans_handle *trans, } /* + * double splits happen when we need to insert a big item in the middle + * of a leaf. A double split can leave us with 3 mostly empty leaves: + * leaf: [ slots 0 - N] [ our target ] [ N + 1 - total in leaf ] + * A B C + * + * We avoid this by trying to push the items on either side of our target + * into the adjacent leaves. If all goes well we can avoid the double split + * completely. + */ +static noinline int push_for_double_split(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + int data_size) +{ + int ret; + int progress = 0; + int slot; + u32 nritems; + + slot = path->slots[0]; + + /* + * try to push all the items after our slot into the + * right leaf + */ + ret = push_leaf_right(trans, root, path, 1, data_size, 0, slot); + if (ret < 0) + return ret; + + if (ret == 0) + progress++; + + nritems = btrfs_header_nritems(path->nodes[0]); + /* + * our goal is to get our slot at the start or end of a leaf. If + * we've done so we're done + */ + if (path->slots[0] == 0 || path->slots[0] == nritems) + return 0; + + if (btrfs_leaf_free_space(root, path->nodes[0]) >= data_size) + return 0; + + /* try to push all the items before our slot into the next leaf */ + slot = path->slots[0]; + ret = push_leaf_left(trans, root, path, 1, data_size, 0, slot); + if (ret < 0) + return ret; + + if (ret == 0) + progress++; + + if (progress) + return 0; + return 1; +} + +/* * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. * @@ -2876,6 +2953,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, int wret; int split; int num_doubles = 0; + int tried_avoid_double = 0; l = path->nodes[0]; slot = path->slots[0]; @@ -2884,12 +2962,14 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, return -EOVERFLOW; /* first try to make some room by pushing left and right */ - if (data_size && ins_key->type != BTRFS_DIR_ITEM_KEY) { - wret = push_leaf_right(trans, root, path, data_size, 0); + if (data_size) { + wret = push_leaf_right(trans, root, path, data_size, + data_size, 0, 0); if (wret < 0) return wret; if (wret) { - wret = push_leaf_left(trans, root, path, data_size, 0); + wret = push_leaf_left(trans, root, path, data_size, + data_size, 0, (u32)-1); if (wret < 0) return wret; } @@ -2923,6 +3003,8 @@ again: if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(root)) { + if (data_size && !tried_avoid_double) + goto push_for_double; split = 2; } } @@ -2939,6 +3021,8 @@ again: if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(root)) { + if (data_size && !tried_avoid_double) + goto push_for_double; split = 2 ; } } @@ -3019,6 +3103,13 @@ again: } return ret; + +push_for_double: + push_for_double_split(trans, root, path, data_size); + tried_avoid_double = 1; + if (btrfs_leaf_free_space(root, path->nodes[0]) >= data_size) + return 0; + goto again; } static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, @@ -3915,13 +4006,15 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, extent_buffer_get(leaf); btrfs_set_path_blocking(path); - wret = push_leaf_left(trans, root, path, 1, 1); + wret = push_leaf_left(trans, root, path, 1, 1, + 1, (u32)-1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (path->nodes[0] == leaf && btrfs_header_nritems(leaf)) { - wret = push_leaf_right(trans, root, path, 1, 1); + wret = push_leaf_right(trans, root, path, 1, + 1, 1, 0); if (wret < 0 && wret != -ENOSPC) ret = wret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4dbaf89b1337..9254b3d58dbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1458,7 +1458,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, */ /* the destination must be opened for writing */ - if (!(file->f_mode & FMODE_WRITE)) + if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) return -EINVAL; ret = mnt_want_write(file->f_path.mnt); @@ -1511,7 +1511,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, /* determine range to clone */ ret = -EINVAL; - if (off >= src->i_size || off + len > src->i_size) + if (off + len > src->i_size || off + len < off) goto out_unlock; if (len == 0) olen = len = src->i_size - off; @@ -1578,6 +1578,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, u64 disko = 0, diskl = 0; u64 datao = 0, datal = 0; u8 comp; + u64 endoff; size = btrfs_item_size_nr(leaf, slot); read_extent_buffer(leaf, buf, @@ -1712,9 +1713,18 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, btrfs_release_path(root, path); inode->i_mtime = inode->i_ctime = CURRENT_TIME; - if (new_key.offset + datal > inode->i_size) - btrfs_i_size_write(inode, - new_key.offset + datal); + + /* + * we round up to the block size at eof when + * determining which extents to clone above, + * but shouldn't round up the file size + */ + endoff = new_key.offset + datal; + if (endoff > off+olen) + endoff = off+olen; + if (endoff > inode->i_size) + btrfs_i_size_write(inode, endoff); + BTRFS_I(inode)->flags = BTRFS_I(src)->flags; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); diff --git a/fs/ceph/auth_x.c b/fs/ceph/auth_x.c index 3fe49042d8ad..6d44053ecff1 100644 --- a/fs/ceph/auth_x.c +++ b/fs/ceph/auth_x.c @@ -613,6 +613,9 @@ static void ceph_x_destroy(struct ceph_auth_client *ac) remove_ticket_handler(ac, th); } + if (xi->auth_authorizer.buf) + ceph_buffer_put(xi->auth_authorizer.buf); + kfree(ac->private); ac->private = NULL; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3ab79f6c4ce8..416c08d315db 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1514,6 +1514,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ceph_encode_filepath(&p, end, ino1, path1); ceph_encode_filepath(&p, end, ino2, path2); + /* make note of release offset, in case we need to replay */ + req->r_request_release_offset = p - msg->front.iov_base; + /* cap releases */ releases = 0; if (req->r_inode_drop) @@ -1580,6 +1583,32 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc, dout("prepare_send_request %p tid %lld %s (attempt %d)\n", req, req->r_tid, ceph_mds_op_name(req->r_op), req->r_attempts); + if (req->r_got_unsafe) { + /* + * Replay. Do not regenerate message (and rebuild + * paths, etc.); just use the original message. + * Rebuilding paths will break for renames because + * d_move mangles the src name. + */ + msg = req->r_request; + rhead = msg->front.iov_base; + + flags = le32_to_cpu(rhead->flags); + flags |= CEPH_MDS_FLAG_REPLAY; + rhead->flags = cpu_to_le32(flags); + + if (req->r_target_inode) + rhead->ino = cpu_to_le64(ceph_ino(req->r_target_inode)); + + rhead->num_retry = req->r_attempts - 1; + + /* remove cap/dentry releases from message */ + rhead->num_releases = 0; + msg->hdr.front_len = cpu_to_le32(req->r_request_release_offset); + msg->front.iov_len = req->r_request_release_offset; + return 0; + } + if (req->r_request) { ceph_msg_put(req->r_request); req->r_request = NULL; @@ -1601,13 +1630,9 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc, rhead->flags = cpu_to_le32(flags); rhead->num_fwd = req->r_num_fwd; rhead->num_retry = req->r_attempts - 1; + rhead->ino = 0; dout(" r_locked_dir = %p\n", req->r_locked_dir); - - if (req->r_target_inode && req->r_got_unsafe) - rhead->ino = cpu_to_le64(ceph_ino(req->r_target_inode)); - else - rhead->ino = 0; return 0; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index b292fa42a66d..952410c60d09 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -188,6 +188,7 @@ struct ceph_mds_request { int r_old_inode_drop, r_old_inode_unless; struct ceph_msg *r_request; /* original request */ + int r_request_release_offset; struct ceph_msg *r_reply; struct ceph_mds_reply_info_parsed r_reply_info; int r_err; diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c index 9ad43a310a41..15167b2daa55 100644 --- a/fs/ceph/messenger.c +++ b/fs/ceph/messenger.c @@ -43,7 +43,8 @@ static void ceph_fault(struct ceph_connection *con); * nicely render a sockaddr as a string. */ #define MAX_ADDR_STR 20 -static char addr_str[MAX_ADDR_STR][40]; +#define MAX_ADDR_STR_LEN 60 +static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN]; static DEFINE_SPINLOCK(addr_str_lock); static int last_addr_str; @@ -52,7 +53,6 @@ const char *pr_addr(const struct sockaddr_storage *ss) int i; char *s; struct sockaddr_in *in4 = (void *)ss; - unsigned char *quad = (void *)&in4->sin_addr.s_addr; struct sockaddr_in6 *in6 = (void *)ss; spin_lock(&addr_str_lock); @@ -64,25 +64,13 @@ const char *pr_addr(const struct sockaddr_storage *ss) switch (ss->ss_family) { case AF_INET: - sprintf(s, "%u.%u.%u.%u:%u", - (unsigned int)quad[0], - (unsigned int)quad[1], - (unsigned int)quad[2], - (unsigned int)quad[3], - (unsigned int)ntohs(in4->sin_port)); + snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr, + (unsigned int)ntohs(in4->sin_port)); break; case AF_INET6: - sprintf(s, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%u", - in6->sin6_addr.s6_addr16[0], - in6->sin6_addr.s6_addr16[1], - in6->sin6_addr.s6_addr16[2], - in6->sin6_addr.s6_addr16[3], - in6->sin6_addr.s6_addr16[4], - in6->sin6_addr.s6_addr16[5], - in6->sin6_addr.s6_addr16[6], - in6->sin6_addr.s6_addr16[7], - (unsigned int)ntohs(in6->sin6_port)); + snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr, + (unsigned int)ntohs(in6->sin6_port)); break; default: @@ -215,12 +203,13 @@ static void set_sock_callbacks(struct socket *sock, */ static struct socket *ceph_tcp_connect(struct ceph_connection *con) { - struct sockaddr *paddr = (struct sockaddr *)&con->peer_addr.in_addr; + struct sockaddr_storage *paddr = &con->peer_addr.in_addr; struct socket *sock; int ret; BUG_ON(con->sock); - ret = sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM, + IPPROTO_TCP, &sock); if (ret) return ERR_PTR(ret); con->sock = sock; @@ -234,7 +223,8 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) dout("connect %s\n", pr_addr(&con->peer_addr.in_addr)); - ret = sock->ops->connect(sock, paddr, sizeof(*paddr), O_NONBLOCK); + ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr), + O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", pr_addr(&con->peer_addr.in_addr), @@ -1009,19 +999,32 @@ int ceph_parse_ips(const char *c, const char *end, struct sockaddr_in *in4 = (void *)ss; struct sockaddr_in6 *in6 = (void *)ss; int port; + char delim = ','; + + if (*p == '[') { + delim = ']'; + p++; + } memset(ss, 0, sizeof(*ss)); if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr, - ',', &ipend)) { + delim, &ipend)) ss->ss_family = AF_INET; - } else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr, - ',', &ipend)) { + else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr, + delim, &ipend)) ss->ss_family = AF_INET6; - } else { + else goto bad; - } p = ipend; + if (delim == ']') { + if (*p != ']') { + dout("missing matching ']'\n"); + goto bad; + } + p++; + } + /* port? */ if (p < end && *p == ':') { port = 0; @@ -1055,7 +1058,7 @@ int ceph_parse_ips(const char *c, const char *end, return 0; bad: - pr_err("parse_ips bad ip '%s'\n", c); + pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); return -EINVAL; } @@ -2015,20 +2018,20 @@ void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) { mutex_lock(&con->mutex); if (!list_empty(&msg->list_head)) { - dout("con_revoke %p msg %p\n", con, msg); + dout("con_revoke %p msg %p - was on queue\n", con, msg); list_del_init(&msg->list_head); ceph_msg_put(msg); msg->hdr.seq = 0; - if (con->out_msg == msg) { - ceph_msg_put(con->out_msg); - con->out_msg = NULL; - } + } + if (con->out_msg == msg) { + dout("con_revoke %p msg %p - was sending\n", con, msg); + con->out_msg = NULL; if (con->out_kvec_is_msg) { con->out_skip = con->out_kvec_bytes; con->out_kvec_is_msg = false; } - } else { - dout("con_revoke %p msg %p - not queued (sent?)\n", con, msg); + ceph_msg_put(msg); + msg->hdr.seq = 0; } mutex_unlock(&con->mutex); } diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c index 50ce64ebd330..277f8b339577 100644 --- a/fs/ceph/osdmap.c +++ b/fs/ceph/osdmap.c @@ -568,6 +568,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) if (ev > CEPH_PG_POOL_VERSION) { pr_warning("got unknown v %d > %d of ceph_pg_pool\n", ev, CEPH_PG_POOL_VERSION); + kfree(pi); goto bad; } __decode_pool(p, pi); diff --git a/fs/dcache.c b/fs/dcache.c index c8c78ba07827..86d4db15473e 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -896,7 +896,7 @@ EXPORT_SYMBOL(shrink_dcache_parent); * * In this case we return -1 to tell the caller that we baled. */ -static int shrink_dcache_memory(int nr, gfp_t gfp_mask) +static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { if (nr) { if (!(gfp_mask & __GFP_FS)) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 4a48c0f4b402..84da64b551b2 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1041,6 +1041,7 @@ static int trunc_start(struct gfs2_inode *ip, u64 size) if (gfs2_is_stuffed(ip)) { u64 dsize = size + sizeof(struct gfs2_inode); + ip->i_disksize = size; ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 8295c5b5d4a9..26ca3361a8bc 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -392,7 +392,7 @@ static int gfs2_dirent_find_space(const struct gfs2_dirent *dent, unsigned totlen = be16_to_cpu(dent->de_rec_len); if (gfs2_dirent_sentinel(dent)) - actual = GFS2_DIRENT_SIZE(0); + actual = 0; if (totlen - actual >= required) return 1; return 0; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ddcdbf493536..0898f3ec8212 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -706,8 +706,18 @@ static void glock_work_func(struct work_struct *work) { unsigned long delay = 0; struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); + struct gfs2_holder *gh; int drop_ref = 0; + if (unlikely(test_bit(GLF_FROZEN, &gl->gl_flags))) { + spin_lock(&gl->gl_spin); + gh = find_first_waiter(gl); + if (gh && (gh->gh_flags & LM_FLAG_NOEXP) && + test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) + set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + spin_unlock(&gl->gl_spin); + } + if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { finish_xmote(gl, gl->gl_reply); drop_ref = 1; @@ -1348,7 +1358,7 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) } -static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask) +static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { struct gfs2_glock *gl; int may_demote; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index b5612cbb62a5..f03afd9c44bc 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -169,7 +169,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, { struct inode *inode; struct gfs2_inode *ip; - struct gfs2_glock *io_gl; + struct gfs2_glock *io_gl = NULL; int error; inode = gfs2_iget(sb, no_addr); @@ -198,6 +198,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, ip->i_iopen_gh.gh_gl->gl_object = ip; gfs2_glock_put(io_gl); + io_gl = NULL; if ((type == DT_UNKNOWN) && (no_formal_ino == 0)) goto gfs2_nfsbypass; @@ -228,7 +229,8 @@ gfs2_nfsbypass: fail_glock: gfs2_glock_dq(&ip->i_iopen_gh); fail_iopen: - gfs2_glock_put(io_gl); + if (io_gl) + gfs2_glock_put(io_gl); fail_put: if (inode->i_state & I_NEW) ip->i_gl->gl_object = NULL; @@ -256,7 +258,7 @@ void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr) { struct gfs2_sbd *sdp; struct gfs2_inode *ip; - struct gfs2_glock *io_gl; + struct gfs2_glock *io_gl = NULL; int error; struct gfs2_holder gh; struct inode *inode; @@ -293,6 +295,7 @@ void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr) ip->i_iopen_gh.gh_gl->gl_object = ip; gfs2_glock_put(io_gl); + io_gl = NULL; inode->i_mode = DT2IF(DT_UNKNOWN); @@ -319,7 +322,8 @@ void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr) fail_glock: gfs2_glock_dq(&ip->i_iopen_gh); fail_iopen: - gfs2_glock_put(io_gl); + if (io_gl) + gfs2_glock_put(io_gl); fail_put: ip->i_gl->gl_object = NULL; gfs2_glock_put(ip->i_gl); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 49667d68769e..8f02d3db8f42 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -77,7 +77,7 @@ static LIST_HEAD(qd_lru_list); static atomic_t qd_lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(qd_lru_lock); -int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask) +int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { struct gfs2_quota_data *qd; struct gfs2_sbd *sdp; @@ -694,10 +694,8 @@ get_a_page: if (!buffer_mapped(bh)) goto unlock_out; /* If it's a newly allocated disk block for quota, zero it */ - if (buffer_new(bh)) { - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - } + if (buffer_new(bh)) + zero_user(page, pos - blocksize, bh->b_size); } if (PageUptodate(page)) @@ -723,7 +721,7 @@ get_a_page: /* If quota straddles page boundary, we need to update the rest of the * quota at the beginning of the next page */ - if (offset != 0) { /* first page, offset is closer to PAGE_CACHE_SIZE */ + if ((offset + sizeof(struct gfs2_quota)) > PAGE_CACHE_SIZE) { ptr = ptr + nbytes; nbytes = sizeof(struct gfs2_quota) - nbytes; offset = 0; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 195f60c8bd14..e7d236ca48bd 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -51,7 +51,7 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; } -extern int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask); +extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask); extern const struct quotactl_ops gfs2_quotactl_ops; #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/inode.c b/fs/inode.c index 2bee20ae3d65..722860b323a9 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -512,7 +512,7 @@ static void prune_icache(int nr_to_scan) * This function is passed the number of inodes to scan, and it returns the * total number of remaining possibly-reclaimable inodes. */ -static int shrink_icache_memory(int nr, gfp_t gfp_mask) +static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { if (nr) { /* diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index bc2ff5932769..036880895bfc 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -297,7 +297,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct page *new_page; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); - struct jbd2_buffer_trigger_type *triggers; journal_t *journal = transaction->t_journal; /* @@ -328,21 +327,21 @@ repeat: done_copy_out = 1; new_page = virt_to_page(jh_in->b_frozen_data); new_offset = offset_in_page(jh_in->b_frozen_data); - triggers = jh_in->b_frozen_triggers; } else { new_page = jh2bh(jh_in)->b_page; new_offset = offset_in_page(jh2bh(jh_in)->b_data); - triggers = jh_in->b_triggers; } mapped_data = kmap_atomic(new_page, KM_USER0); /* - * Fire any commit trigger. Do this before checking for escaping, - * as the trigger may modify the magic offset. If a copy-out - * happens afterwards, it will have the correct data in the buffer. + * Fire data frozen trigger if data already wasn't frozen. Do this + * before checking for escaping, as the trigger may modify the magic + * offset. If a copy-out happens afterwards, it will have the correct + * data in the buffer. */ - jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset, - triggers); + if (!done_copy_out) + jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset, + jh_in->b_triggers); /* * Check for escaping diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e214d68620ac..b8e0806681bb 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -725,6 +725,9 @@ done: page = jh2bh(jh)->b_page; offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK; source = kmap_atomic(page, KM_USER0); + /* Fire data frozen trigger just before we copy the data */ + jbd2_buffer_frozen_trigger(jh, source + offset, + jh->b_triggers); memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size); kunmap_atomic(source, KM_USER0); @@ -963,15 +966,15 @@ void jbd2_journal_set_triggers(struct buffer_head *bh, jh->b_triggers = type; } -void jbd2_buffer_commit_trigger(struct journal_head *jh, void *mapped_data, +void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers) { struct buffer_head *bh = jh2bh(jh); - if (!triggers || !triggers->t_commit) + if (!triggers || !triggers->t_frozen) return; - triggers->t_commit(triggers, bh, mapped_data, bh->b_size); + triggers->t_frozen(triggers, bh, mapped_data, bh->b_size); } void jbd2_buffer_abort_trigger(struct journal_head *jh, diff --git a/fs/mbcache.c b/fs/mbcache.c index ec88ff3d04a9..e28f21b95344 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -115,7 +115,7 @@ mb_cache_indexes(struct mb_cache *cache) * What the mbcache registers as to get shrunk dynamically. */ -static int mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask); +static int mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask); static struct shrinker mb_cache_shrinker = { .shrink = mb_cache_shrink_fn, @@ -191,13 +191,14 @@ forget: * This function is called by the kernel memory management when memory * gets low. * + * @shrink: (ignored) * @nr_to_scan: Number of objects to scan * @gfp_mask: (ignored) * * Returns the number of objects which are present in the cache. */ static int -mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask) +mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { LIST_HEAD(free_list); struct list_head *l, *ltmp; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 782b431ef91c..e60416d3f818 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1710,7 +1710,7 @@ static void nfs_access_free_list(struct list_head *head) } } -int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask) +int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { LIST_HEAD(head); struct nfs_inode *nfsi; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d8bd619e386c..e70f44b9b3f4 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -205,7 +205,8 @@ extern struct rpc_procinfo nfs4_procedures[]; void nfs_close_context(struct nfs_open_context *ctx, int is_sync); /* dir.c */ -extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask); +extern int nfs_access_cache_shrinker(struct shrinker *shrink, + int nr_to_scan, gfp_t gfp_mask); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 3623ca20cc18..356e976772bf 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -196,15 +196,14 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock, dump_stack(); goto bail; } - - past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); - mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino, - (unsigned long long)past_eof); - - if (create && (iblock >= past_eof)) - set_buffer_new(bh_result); } + past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); + mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino, + (unsigned long long)past_eof); + if (create && (iblock >= past_eof)) + set_buffer_new(bh_result); + bail: if (err < 0) err = -EIO; @@ -459,36 +458,6 @@ int walk_page_buffers( handle_t *handle, return ret; } -handle_t *ocfs2_start_walk_page_trans(struct inode *inode, - struct page *page, - unsigned from, - unsigned to) -{ - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - handle_t *handle; - int ret = 0; - - handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); - if (IS_ERR(handle)) { - ret = -ENOMEM; - mlog_errno(ret); - goto out; - } - - if (ocfs2_should_order_data(inode)) { - ret = ocfs2_jbd2_file_inode(handle, inode); - if (ret < 0) - mlog_errno(ret); - } -out: - if (ret) { - if (!IS_ERR(handle)) - ocfs2_commit_trans(osb, handle); - handle = ERR_PTR(ret); - } - return handle; -} - static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) { sector_t status; @@ -1131,23 +1100,37 @@ out: */ static int ocfs2_grab_pages_for_write(struct address_space *mapping, struct ocfs2_write_ctxt *wc, - u32 cpos, loff_t user_pos, int new, + u32 cpos, loff_t user_pos, + unsigned user_len, int new, struct page *mmap_page) { int ret = 0, i; - unsigned long start, target_index, index; + unsigned long start, target_index, end_index, index; struct inode *inode = mapping->host; + loff_t last_byte; target_index = user_pos >> PAGE_CACHE_SHIFT; /* * Figure out how many pages we'll be manipulating here. For * non allocating write, we just change the one - * page. Otherwise, we'll need a whole clusters worth. + * page. Otherwise, we'll need a whole clusters worth. If we're + * writing past i_size, we only need enough pages to cover the + * last page of the write. */ if (new) { wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb); start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos); + /* + * We need the index *past* the last page we could possibly + * touch. This is the page past the end of the write or + * i_size, whichever is greater. + */ + last_byte = max(user_pos + user_len, i_size_read(inode)); + BUG_ON(last_byte < 1); + end_index = ((last_byte - 1) >> PAGE_CACHE_SHIFT) + 1; + if ((start + wc->w_num_pages) > end_index) + wc->w_num_pages = end_index - start; } else { wc->w_num_pages = 1; start = target_index; @@ -1620,21 +1603,20 @@ out: * write path can treat it as an non-allocating write, which has no * special case code for sparse/nonsparse files. */ -static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos, - unsigned len, +static int ocfs2_expand_nonsparse_inode(struct inode *inode, + struct buffer_head *di_bh, + loff_t pos, unsigned len, struct ocfs2_write_ctxt *wc) { int ret; - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); loff_t newsize = pos + len; - if (ocfs2_sparse_alloc(osb)) - return 0; + BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); if (newsize <= i_size_read(inode)) return 0; - ret = ocfs2_extend_no_holes(inode, newsize, pos); + ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos); if (ret) mlog_errno(ret); @@ -1644,6 +1626,18 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos, return ret; } +static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, + loff_t pos) +{ + int ret = 0; + + BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); + if (pos > i_size_read(inode)) + ret = ocfs2_zero_extend(inode, di_bh, pos); + + return ret; +} + int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, @@ -1679,7 +1673,11 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, } } - ret = ocfs2_expand_nonsparse_inode(inode, pos, len, wc); + if (ocfs2_sparse_alloc(osb)) + ret = ocfs2_zero_tail(inode, di_bh, pos); + else + ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len, + wc); if (ret) { mlog_errno(ret); goto out; @@ -1789,7 +1787,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, * that we can zero and flush if we error after adding the * extent. */ - ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, + ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len, cluster_of_pages, mmap_page); if (ret) { mlog_errno(ret); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 6b5a492e1749..153abb5abef0 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1671,7 +1671,7 @@ struct dlm_ctxt * dlm_register_domain(const char *domain, struct dlm_ctxt *dlm = NULL; struct dlm_ctxt *new_ctxt = NULL; - if (strlen(domain) > O2NM_MAX_NAME_LEN) { + if (strlen(domain) >= O2NM_MAX_NAME_LEN) { ret = -ENAMETOOLONG; mlog(ML_ERROR, "domain name length too long\n"); goto leave; @@ -1709,6 +1709,7 @@ retry: } if (dlm_protocol_compare(&dlm->fs_locking_proto, fs_proto)) { + spin_unlock(&dlm_domain_lock); mlog(ML_ERROR, "Requested locking protocol version is not " "compatible with already registered domain " diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 4a7506a4e314..94b97fc6a88e 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2808,14 +2808,8 @@ again: mlog(0, "trying again...\n"); goto again; } - /* now that we are sure the MIGRATING state is there, drop - * the unneded state which blocked threads trying to DIRTY */ - spin_lock(&res->spinlock); - BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY)); - BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING)); - res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY; - spin_unlock(&res->spinlock); + ret = 0; /* did the target go down or die? */ spin_lock(&dlm->spinlock); if (!test_bit(target, dlm->domain_map)) { @@ -2826,9 +2820,21 @@ again: spin_unlock(&dlm->spinlock); /* + * if target is down, we need to clear DLM_LOCK_RES_BLOCK_DIRTY for + * another try; otherwise, we are sure the MIGRATING state is there, + * drop the unneded state which blocked threads trying to DIRTY + */ + spin_lock(&res->spinlock); + BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY)); + res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY; + if (!ret) + BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING)); + spin_unlock(&res->spinlock); + + /* * at this point: * - * o the DLM_LOCK_RES_MIGRATING flag is set + * o the DLM_LOCK_RES_MIGRATING flag is set if target not down * o there are no pending asts on this lockres * o all processes trying to reserve an ast on this * lockres must wait for the MIGRATING flag to clear diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index f8b75ce4be70..9dfaac73b36d 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -463,7 +463,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) { int bit; - bit = find_next_bit (dlm->recovery_map, O2NM_MAX_NODES+1, 0); + bit = find_next_bit (dlm->recovery_map, O2NM_MAX_NODES, 0); if (bit >= O2NM_MAX_NODES || bit < 0) dlm_set_reco_dead_node(dlm, O2NM_INVALID_NODE_NUM); else diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 6a13ea64c447..2b10b36d1577 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -724,28 +724,55 @@ leave: return status; } +/* + * While a write will already be ordering the data, a truncate will not. + * Thus, we need to explicitly order the zeroed pages. + */ +static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + handle_t *handle = NULL; + int ret = 0; + + if (!ocfs2_should_order_data(inode)) + goto out; + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + ret = ocfs2_jbd2_file_inode(handle, inode); + if (ret < 0) + mlog_errno(ret); + +out: + if (ret) { + if (!IS_ERR(handle)) + ocfs2_commit_trans(osb, handle); + handle = ERR_PTR(ret); + } + return handle; +} + /* Some parts of this taken from generic_cont_expand, which turned out * to be too fragile to do exactly what we need without us having to * worry about recursive locking in ->write_begin() and ->write_end(). */ -static int ocfs2_write_zero_page(struct inode *inode, - u64 size) +static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, + u64 abs_to) { struct address_space *mapping = inode->i_mapping; struct page *page; - unsigned long index; - unsigned int offset; + unsigned long index = abs_from >> PAGE_CACHE_SHIFT; handle_t *handle = NULL; - int ret; + int ret = 0; + unsigned zero_from, zero_to, block_start, block_end; - offset = (size & (PAGE_CACHE_SIZE-1)); /* Within page */ - /* ugh. in prepare/commit_write, if from==to==start of block, we - ** skip the prepare. make sure we never send an offset for the start - ** of a block - */ - if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) { - offset++; - } - index = size >> PAGE_CACHE_SHIFT; + BUG_ON(abs_from >= abs_to); + BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT)); + BUG_ON(abs_from & (inode->i_blkbits - 1)); page = grab_cache_page(mapping, index); if (!page) { @@ -754,31 +781,56 @@ static int ocfs2_write_zero_page(struct inode *inode, goto out; } - ret = ocfs2_prepare_write_nolock(inode, page, offset, offset); - if (ret < 0) { - mlog_errno(ret); - goto out_unlock; - } + /* Get the offsets within the page that we want to zero */ + zero_from = abs_from & (PAGE_CACHE_SIZE - 1); + zero_to = abs_to & (PAGE_CACHE_SIZE - 1); + if (!zero_to) + zero_to = PAGE_CACHE_SIZE; - if (ocfs2_should_order_data(inode)) { - handle = ocfs2_start_walk_page_trans(inode, page, offset, - offset); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - handle = NULL; + mlog(0, + "abs_from = %llu, abs_to = %llu, index = %lu, zero_from = %u, zero_to = %u\n", + (unsigned long long)abs_from, (unsigned long long)abs_to, + index, zero_from, zero_to); + + /* We know that zero_from is block aligned */ + for (block_start = zero_from; block_start < zero_to; + block_start = block_end) { + block_end = block_start + (1 << inode->i_blkbits); + + /* + * block_start is block-aligned. Bump it by one to + * force ocfs2_{prepare,commit}_write() to zero the + * whole block. + */ + ret = ocfs2_prepare_write_nolock(inode, page, + block_start + 1, + block_start + 1); + if (ret < 0) { + mlog_errno(ret); goto out_unlock; } - } - /* must not update i_size! */ - ret = block_commit_write(page, offset, offset); - if (ret < 0) - mlog_errno(ret); - else - ret = 0; + if (!handle) { + handle = ocfs2_zero_start_ordered_transaction(inode); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + handle = NULL; + break; + } + } + + /* must not update i_size! */ + ret = block_commit_write(page, block_start + 1, + block_start + 1); + if (ret < 0) + mlog_errno(ret); + else + ret = 0; + } if (handle) ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); + out_unlock: unlock_page(page); page_cache_release(page); @@ -786,22 +838,114 @@ out: return ret; } -static int ocfs2_zero_extend(struct inode *inode, - u64 zero_to_size) +/* + * Find the next range to zero. We do this in terms of bytes because + * that's what ocfs2_zero_extend() wants, and it is dealing with the + * pagecache. We may return multiple extents. + * + * zero_start and zero_end are ocfs2_zero_extend()s current idea of what + * needs to be zeroed. range_start and range_end return the next zeroing + * range. A subsequent call should pass the previous range_end as its + * zero_start. If range_end is 0, there's nothing to do. + * + * Unwritten extents are skipped over. Refcounted extents are CoWd. + */ +static int ocfs2_zero_extend_get_range(struct inode *inode, + struct buffer_head *di_bh, + u64 zero_start, u64 zero_end, + u64 *range_start, u64 *range_end) { - int ret = 0; - u64 start_off; - struct super_block *sb = inode->i_sb; + int rc = 0, needs_cow = 0; + u32 p_cpos, zero_clusters = 0; + u32 zero_cpos = + zero_start >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; + u32 last_cpos = ocfs2_clusters_for_bytes(inode->i_sb, zero_end); + unsigned int num_clusters = 0; + unsigned int ext_flags = 0; - start_off = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode)); - while (start_off < zero_to_size) { - ret = ocfs2_write_zero_page(inode, start_off); - if (ret < 0) { - mlog_errno(ret); + while (zero_cpos < last_cpos) { + rc = ocfs2_get_clusters(inode, zero_cpos, &p_cpos, + &num_clusters, &ext_flags); + if (rc) { + mlog_errno(rc); + goto out; + } + + if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { + zero_clusters = num_clusters; + if (ext_flags & OCFS2_EXT_REFCOUNTED) + needs_cow = 1; + break; + } + + zero_cpos += num_clusters; + } + if (!zero_clusters) { + *range_end = 0; + goto out; + } + + while ((zero_cpos + zero_clusters) < last_cpos) { + rc = ocfs2_get_clusters(inode, zero_cpos + zero_clusters, + &p_cpos, &num_clusters, + &ext_flags); + if (rc) { + mlog_errno(rc); goto out; } - start_off += sb->s_blocksize; + if (!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN)) + break; + if (ext_flags & OCFS2_EXT_REFCOUNTED) + needs_cow = 1; + zero_clusters += num_clusters; + } + if ((zero_cpos + zero_clusters) > last_cpos) + zero_clusters = last_cpos - zero_cpos; + + if (needs_cow) { + rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos, zero_clusters, + UINT_MAX); + if (rc) { + mlog_errno(rc); + goto out; + } + } + + *range_start = ocfs2_clusters_to_bytes(inode->i_sb, zero_cpos); + *range_end = ocfs2_clusters_to_bytes(inode->i_sb, + zero_cpos + zero_clusters); + +out: + return rc; +} + +/* + * Zero one range returned from ocfs2_zero_extend_get_range(). The caller + * has made sure that the entire range needs zeroing. + */ +static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, + u64 range_end) +{ + int rc = 0; + u64 next_pos; + u64 zero_pos = range_start; + + mlog(0, "range_start = %llu, range_end = %llu\n", + (unsigned long long)range_start, + (unsigned long long)range_end); + BUG_ON(range_start >= range_end); + + while (zero_pos < range_end) { + next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE; + if (next_pos > range_end) + next_pos = range_end; + rc = ocfs2_write_zero_page(inode, zero_pos, next_pos); + if (rc < 0) { + mlog_errno(rc); + break; + } + zero_pos = next_pos; /* * Very large extends have the potential to lock up @@ -810,16 +954,63 @@ static int ocfs2_zero_extend(struct inode *inode, cond_resched(); } -out: + return rc; +} + +int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, + loff_t zero_to_size) +{ + int ret = 0; + u64 zero_start, range_start = 0, range_end = 0; + struct super_block *sb = inode->i_sb; + + zero_start = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode)); + mlog(0, "zero_start %llu for i_size %llu\n", + (unsigned long long)zero_start, + (unsigned long long)i_size_read(inode)); + while (zero_start < zero_to_size) { + ret = ocfs2_zero_extend_get_range(inode, di_bh, zero_start, + zero_to_size, + &range_start, + &range_end); + if (ret) { + mlog_errno(ret); + break; + } + if (!range_end) + break; + /* Trim the ends */ + if (range_start < zero_start) + range_start = zero_start; + if (range_end > zero_to_size) + range_end = zero_to_size; + + ret = ocfs2_zero_extend_range(inode, range_start, + range_end); + if (ret) { + mlog_errno(ret); + break; + } + zero_start = range_end; + } + return ret; } -int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to) +int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, + u64 new_i_size, u64 zero_to) { int ret; u32 clusters_to_add; struct ocfs2_inode_info *oi = OCFS2_I(inode); + /* + * Only quota files call this without a bh, and they can't be + * refcounted. + */ + BUG_ON(!di_bh && (oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!di_bh && !(oi->ip_flags & OCFS2_INODE_SYSTEM_FILE)); + clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size); if (clusters_to_add < oi->ip_clusters) clusters_to_add = 0; @@ -840,7 +1031,7 @@ int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to) * still need to zero the area between the old i_size and the * new i_size. */ - ret = ocfs2_zero_extend(inode, zero_to); + ret = ocfs2_zero_extend(inode, di_bh, zero_to); if (ret < 0) mlog_errno(ret); @@ -862,27 +1053,15 @@ static int ocfs2_extend_file(struct inode *inode, goto out; if (i_size_read(inode) == new_i_size) - goto out; + goto out; BUG_ON(new_i_size < i_size_read(inode)); /* - * Fall through for converting inline data, even if the fs - * supports sparse files. - * - * The check for inline data here is legal - nobody can add - * the feature since we have i_mutex. We must check it again - * after acquiring ip_alloc_sem though, as paths like mmap - * might have raced us to converting the inode to extents. - */ - if (!(oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) - && ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) - goto out_update_size; - - /* * The alloc sem blocks people in read/write from reading our * allocation until we're done changing it. We depend on * i_mutex to block other extend/truncate calls while we're - * here. + * here. We even have to hold it for sparse files because there + * might be some tail zeroing. */ down_write(&oi->ip_alloc_sem); @@ -899,14 +1078,16 @@ static int ocfs2_extend_file(struct inode *inode, ret = ocfs2_convert_inline_data_to_extents(inode, di_bh); if (ret) { up_write(&oi->ip_alloc_sem); - mlog_errno(ret); goto out; } } - if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) - ret = ocfs2_extend_no_holes(inode, new_i_size, new_i_size); + if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + ret = ocfs2_zero_extend(inode, di_bh, new_i_size); + else + ret = ocfs2_extend_no_holes(inode, di_bh, new_i_size, + new_i_size); up_write(&oi->ip_alloc_sem); diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index d66cf4f7c70e..97bf761c9e7c 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -54,8 +54,10 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb, int ocfs2_simple_size_update(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size); -int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, - u64 zero_to); +int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, + u64 new_i_size, u64 zero_to); +int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, + loff_t zero_to); int ocfs2_setattr(struct dentry *dentry, struct iattr *attr); int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 47878cf16418..625de9d7088c 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -472,7 +472,7 @@ static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger return container_of(triggers, struct ocfs2_triggers, ot_triggers); } -static void ocfs2_commit_trigger(struct jbd2_buffer_trigger_type *triggers, +static void ocfs2_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { @@ -491,7 +491,7 @@ static void ocfs2_commit_trigger(struct jbd2_buffer_trigger_type *triggers, * Quota blocks have their own trigger because the struct ocfs2_block_check * offset depends on the blocksize. */ -static void ocfs2_dq_commit_trigger(struct jbd2_buffer_trigger_type *triggers, +static void ocfs2_dq_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { @@ -511,7 +511,7 @@ static void ocfs2_dq_commit_trigger(struct jbd2_buffer_trigger_type *triggers, * Directory blocks also have their own trigger because the * struct ocfs2_block_check offset depends on the blocksize. */ -static void ocfs2_db_commit_trigger(struct jbd2_buffer_trigger_type *triggers, +static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { @@ -544,7 +544,7 @@ static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, static struct ocfs2_triggers di_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_dinode, i_check), @@ -552,7 +552,7 @@ static struct ocfs2_triggers di_triggers = { static struct ocfs2_triggers eb_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_extent_block, h_check), @@ -560,7 +560,7 @@ static struct ocfs2_triggers eb_triggers = { static struct ocfs2_triggers rb_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_refcount_block, rf_check), @@ -568,7 +568,7 @@ static struct ocfs2_triggers rb_triggers = { static struct ocfs2_triggers gd_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_group_desc, bg_check), @@ -576,14 +576,14 @@ static struct ocfs2_triggers gd_triggers = { static struct ocfs2_triggers db_triggers = { .ot_triggers = { - .t_commit = ocfs2_db_commit_trigger, + .t_frozen = ocfs2_db_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, }; static struct ocfs2_triggers xb_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_xattr_block, xb_check), @@ -591,14 +591,14 @@ static struct ocfs2_triggers xb_triggers = { static struct ocfs2_triggers dq_triggers = { .ot_triggers = { - .t_commit = ocfs2_dq_commit_trigger, + .t_frozen = ocfs2_dq_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, }; static struct ocfs2_triggers dr_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check), @@ -606,7 +606,7 @@ static struct ocfs2_triggers dr_triggers = { static struct ocfs2_triggers dl_triggers = { .ot_triggers = { - .t_commit = ocfs2_commit_trigger, + .t_frozen = ocfs2_frozen_trigger, .t_abort = ocfs2_abort_trigger, }, .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check), @@ -1936,7 +1936,7 @@ void ocfs2_orphan_scan_work(struct work_struct *work) mutex_lock(&os->os_lock); ocfs2_queue_orphan_scan(osb); if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) - schedule_delayed_work(&os->os_orphan_scan_work, + queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work, ocfs2_orphan_scan_timeout()); mutex_unlock(&os->os_lock); } @@ -1976,8 +1976,8 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb) atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); else { atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE); - schedule_delayed_work(&os->os_orphan_scan_work, - ocfs2_orphan_scan_timeout()); + queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work, + ocfs2_orphan_scan_timeout()); } } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 3d7419682dc0..ec6adbf8f551 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -118,6 +118,7 @@ unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb) { unsigned int la_mb; unsigned int gd_mb; + unsigned int la_max_mb; unsigned int megs_per_slot; struct super_block *sb = osb->sb; @@ -182,6 +183,12 @@ unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb) if (megs_per_slot < la_mb) la_mb = megs_per_slot; + /* We can't store more bits than we can in a block. */ + la_max_mb = ocfs2_clusters_to_megabytes(osb->sb, + ocfs2_local_alloc_size(sb) * 8); + if (la_mb > la_max_mb) + la_mb = la_max_mb; + return la_mb; } diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2bb35fe00511..4607923eb24c 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -775,7 +775,7 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) * locking allocators ranks above a transaction start */ WARN_ON(journal_current_handle()); - status = ocfs2_extend_no_holes(gqinode, + status = ocfs2_extend_no_holes(gqinode, NULL, gqinode->i_size + (need_alloc << sb->s_blocksize_bits), gqinode->i_size); if (status < 0) diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 8bd70d4d184d..dc78764ccc4c 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -971,7 +971,7 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( u64 p_blkno; /* We are protected by dqio_sem so no locking needed */ - status = ocfs2_extend_no_holes(lqinode, + status = ocfs2_extend_no_holes(lqinode, NULL, lqinode->i_size + 2 * sb->s_blocksize, lqinode->i_size); if (status < 0) { @@ -1114,7 +1114,7 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( return ocfs2_local_quota_add_chunk(sb, type, offset); /* We are protected by dqio_sem so no locking needed */ - status = ocfs2_extend_no_holes(lqinode, + status = ocfs2_extend_no_holes(lqinode, NULL, lqinode->i_size + sb->s_blocksize, lqinode->i_size); if (status < 0) { diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 4793f36f6518..3ac5aa733e9c 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2931,6 +2931,12 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle, offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits; end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits); + /* + * We only duplicate pages until we reach the page contains i_size - 1. + * So trim 'end' to i_size. + */ + if (end > i_size_read(context->inode)) + end = i_size_read(context->inode); while (offset < end) { page_index = offset >> PAGE_CACHE_SHIFT; @@ -4166,6 +4172,12 @@ static int __ocfs2_reflink(struct dentry *old_dentry, struct inode *inode = old_dentry->d_inode; struct buffer_head *new_bh = NULL; + if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) { + ret = -EINVAL; + mlog_errno(ret); + goto out; + } + ret = filemap_fdatawrite(inode->i_mapping); if (ret) { mlog_errno(ret); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index f4c2a9eb8c4d..a8e6a95a353f 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -741,7 +741,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, le16_to_cpu(bg->bg_free_bits_count)); le32_add_cpu(&cl->cl_recs[alloc_rec].c_total, le16_to_cpu(bg->bg_bits)); - cl->cl_recs[alloc_rec].c_blkno = cpu_to_le64(bg->bg_blkno); + cl->cl_recs[alloc_rec].c_blkno = bg->bg_blkno; if (le16_to_cpu(cl->cl_next_free_rec) < le16_to_cpu(cl->cl_count)) le16_add_cpu(&cl->cl_next_free_rec, 1); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index e97b34842cfe..d03469f61801 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -709,7 +709,7 @@ static int ocfs2_xattr_extend_allocation(struct inode *inode, struct ocfs2_xattr_value_buf *vb, struct ocfs2_xattr_set_ctxt *ctxt) { - int status = 0; + int status = 0, credits; handle_t *handle = ctxt->handle; enum ocfs2_alloc_restarted why; u32 prev_clusters, logical_start = le32_to_cpu(vb->vb_xv->xr_clusters); @@ -719,38 +719,54 @@ static int ocfs2_xattr_extend_allocation(struct inode *inode, ocfs2_init_xattr_value_extent_tree(&et, INODE_CACHE(inode), vb); - status = vb->vb_access(handle, INODE_CACHE(inode), vb->vb_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto leave; - } + while (clusters_to_add) { + status = vb->vb_access(handle, INODE_CACHE(inode), vb->vb_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (status < 0) { + mlog_errno(status); + break; + } - prev_clusters = le32_to_cpu(vb->vb_xv->xr_clusters); - status = ocfs2_add_clusters_in_btree(handle, - &et, - &logical_start, - clusters_to_add, - 0, - ctxt->data_ac, - ctxt->meta_ac, - &why); - if (status < 0) { - mlog_errno(status); - goto leave; - } + prev_clusters = le32_to_cpu(vb->vb_xv->xr_clusters); + status = ocfs2_add_clusters_in_btree(handle, + &et, + &logical_start, + clusters_to_add, + 0, + ctxt->data_ac, + ctxt->meta_ac, + &why); + if ((status < 0) && (status != -EAGAIN)) { + if (status != -ENOSPC) + mlog_errno(status); + break; + } - ocfs2_journal_dirty(handle, vb->vb_bh); + ocfs2_journal_dirty(handle, vb->vb_bh); - clusters_to_add -= le32_to_cpu(vb->vb_xv->xr_clusters) - prev_clusters; + clusters_to_add -= le32_to_cpu(vb->vb_xv->xr_clusters) - + prev_clusters; - /* - * We should have already allocated enough space before the transaction, - * so no need to restart. - */ - BUG_ON(why != RESTART_NONE || clusters_to_add); - -leave: + if (why != RESTART_NONE && clusters_to_add) { + /* + * We can only fail in case the alloc file doesn't give + * up enough clusters. + */ + BUG_ON(why == RESTART_META); + + mlog(0, "restarting xattr value extension for %u" + " clusters,.\n", clusters_to_add); + credits = ocfs2_calc_extend_credits(inode->i_sb, + &vb->vb_xv->xr_list, + clusters_to_add); + status = ocfs2_extend_trans(handle, credits); + if (status < 0) { + status = -ENOMEM; + mlog_errno(status); + break; + } + } + } return status; } @@ -6788,16 +6804,15 @@ out: return ret; } -static int ocfs2_reflink_xattr_buckets(handle_t *handle, +static int ocfs2_reflink_xattr_bucket(handle_t *handle, u64 blkno, u64 new_blkno, u32 clusters, + u32 *cpos, int num_buckets, struct ocfs2_alloc_context *meta_ac, struct ocfs2_alloc_context *data_ac, struct ocfs2_reflink_xattr_tree_args *args) { int i, j, ret = 0; struct super_block *sb = args->reflink->old_inode->i_sb; - u32 bpc = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(sb)); - u32 num_buckets = clusters * bpc; int bpb = args->old_bucket->bu_blocks; struct ocfs2_xattr_value_buf vb = { .vb_access = ocfs2_journal_access, @@ -6816,14 +6831,6 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle, break; } - /* - * The real bucket num in this series of blocks is stored - * in the 1st bucket. - */ - if (i == 0) - num_buckets = le16_to_cpu( - bucket_xh(args->old_bucket)->xh_num_buckets); - ret = ocfs2_xattr_bucket_journal_access(handle, args->new_bucket, OCFS2_JOURNAL_ACCESS_CREATE); @@ -6837,6 +6844,18 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle, bucket_block(args->old_bucket, j), sb->s_blocksize); + /* + * Record the start cpos so that we can use it to initialize + * our xattr tree we also set the xh_num_bucket for the new + * bucket. + */ + if (i == 0) { + *cpos = le32_to_cpu(bucket_xh(args->new_bucket)-> + xh_entries[0].xe_name_hash); + bucket_xh(args->new_bucket)->xh_num_buckets = + cpu_to_le16(num_buckets); + } + ocfs2_xattr_bucket_journal_dirty(handle, args->new_bucket); ret = ocfs2_reflink_xattr_header(handle, args->reflink, @@ -6866,6 +6885,7 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle, } ocfs2_xattr_bucket_journal_dirty(handle, args->new_bucket); + ocfs2_xattr_bucket_relse(args->old_bucket); ocfs2_xattr_bucket_relse(args->new_bucket); } @@ -6874,6 +6894,75 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle, ocfs2_xattr_bucket_relse(args->new_bucket); return ret; } + +static int ocfs2_reflink_xattr_buckets(handle_t *handle, + struct inode *inode, + struct ocfs2_reflink_xattr_tree_args *args, + struct ocfs2_extent_tree *et, + struct ocfs2_alloc_context *meta_ac, + struct ocfs2_alloc_context *data_ac, + u64 blkno, u32 cpos, u32 len) +{ + int ret, first_inserted = 0; + u32 p_cluster, num_clusters, reflink_cpos = 0; + u64 new_blkno; + unsigned int num_buckets, reflink_buckets; + unsigned int bpc = + ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb)); + + ret = ocfs2_read_xattr_bucket(args->old_bucket, blkno); + if (ret) { + mlog_errno(ret); + goto out; + } + num_buckets = le16_to_cpu(bucket_xh(args->old_bucket)->xh_num_buckets); + ocfs2_xattr_bucket_relse(args->old_bucket); + + while (len && num_buckets) { + ret = ocfs2_claim_clusters(handle, data_ac, + 1, &p_cluster, &num_clusters); + if (ret) { + mlog_errno(ret); + goto out; + } + + new_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster); + reflink_buckets = min(num_buckets, bpc * num_clusters); + + ret = ocfs2_reflink_xattr_bucket(handle, blkno, + new_blkno, num_clusters, + &reflink_cpos, reflink_buckets, + meta_ac, data_ac, args); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * For the 1st allocated cluster, we make it use the same cpos + * so that the xattr tree looks the same as the original one + * in the most case. + */ + if (!first_inserted) { + reflink_cpos = cpos; + first_inserted = 1; + } + ret = ocfs2_insert_extent(handle, et, reflink_cpos, new_blkno, + num_clusters, 0, meta_ac); + if (ret) + mlog_errno(ret); + + mlog(0, "insert new xattr extent rec start %llu len %u to %u\n", + (unsigned long long)new_blkno, num_clusters, reflink_cpos); + + len -= num_clusters; + blkno += ocfs2_clusters_to_blocks(inode->i_sb, num_clusters); + num_buckets -= reflink_buckets; + } +out: + return ret; +} + /* * Create the same xattr extent record in the new inode's xattr tree. */ @@ -6885,8 +6974,6 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode, void *para) { int ret, credits = 0; - u32 p_cluster, num_clusters; - u64 new_blkno; handle_t *handle; struct ocfs2_reflink_xattr_tree_args *args = (struct ocfs2_reflink_xattr_tree_args *)para; @@ -6895,6 +6982,9 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode, struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_extent_tree et; + mlog(0, "reflink xattr buckets %llu len %u\n", + (unsigned long long)blkno, len); + ocfs2_init_xattr_tree_extent_tree(&et, INODE_CACHE(args->reflink->new_inode), args->new_blk_bh); @@ -6914,32 +7004,12 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode, goto out; } - ret = ocfs2_claim_clusters(handle, data_ac, - len, &p_cluster, &num_clusters); - if (ret) { - mlog_errno(ret); - goto out_commit; - } - - new_blkno = ocfs2_clusters_to_blocks(osb->sb, p_cluster); - - mlog(0, "reflink xattr buckets %llu to %llu, len %u\n", - (unsigned long long)blkno, (unsigned long long)new_blkno, len); - ret = ocfs2_reflink_xattr_buckets(handle, blkno, new_blkno, len, - meta_ac, data_ac, args); - if (ret) { - mlog_errno(ret); - goto out_commit; - } - - mlog(0, "insert new xattr extent rec start %llu len %u to %u\n", - (unsigned long long)new_blkno, len, cpos); - ret = ocfs2_insert_extent(handle, &et, cpos, new_blkno, - len, 0, meta_ac); + ret = ocfs2_reflink_xattr_buckets(handle, inode, args, &et, + meta_ac, data_ac, + blkno, cpos, len); if (ret) mlog_errno(ret); -out_commit: ocfs2_commit_trans(osb, handle); out: diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c index 3e73de5967ff..fc8497643fd0 100644 --- a/fs/partitions/ibm.c +++ b/fs/partitions/ibm.c @@ -74,6 +74,7 @@ int ibm_partition(struct parsed_partitions *state) } *label; unsigned char *data; Sector sect; + sector_t labelsect; res = 0; blocksize = bdev_logical_block_size(bdev); @@ -98,10 +99,19 @@ int ibm_partition(struct parsed_partitions *state) goto out_freeall; /* + * Special case for FBA disks: label sector does not depend on + * blocksize. + */ + if ((info->cu_type == 0x6310 && info->dev_type == 0x9336) || + (info->cu_type == 0x3880 && info->dev_type == 0x3370)) + labelsect = info->label_block; + else + labelsect = info->label_block * (blocksize >> 9); + + /* * Get volume label, extract name and type. */ - data = read_part_sector(state, info->label_block*(blocksize/512), - §); + data = read_part_sector(state, labelsect, §); if (data == NULL) goto out_readerr; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 12c233da1b6b..437d2ca2de97 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -676,7 +676,7 @@ static void prune_dqcache(int count) * This is called from kswapd when we think we need some * more memory */ -static int shrink_dqcache_memory(int nr, gfp_t gfp_mask) +static int shrink_dqcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { if (nr) { spin_lock(&dq_list_lock); diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index 02feb59cefca..0b201114a5ad 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -277,7 +277,7 @@ static int kick_a_thread(void) return 0; } -int ubifs_shrinker(int nr, gfp_t gfp_mask) +int ubifs_shrinker(struct shrinker *shrink, int nr, gfp_t gfp_mask) { int freed, contention = 0; long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 2eef553d50c8..04310878f449 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1575,7 +1575,7 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot); int ubifs_tnc_end_commit(struct ubifs_info *c); /* shrinker.c */ -int ubifs_shrinker(int nr_to_scan, gfp_t gfp_mask); +int ubifs_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask); /* commit.c */ int ubifs_bg_thread(void *info); diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 649ade8ef598..2ee3f7a60163 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -45,7 +45,7 @@ static kmem_zone_t *xfs_buf_zone; STATIC int xfsbufd(void *); -STATIC int xfsbufd_wakeup(int, gfp_t); +STATIC int xfsbufd_wakeup(struct shrinker *, int, gfp_t); STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int); static struct shrinker xfs_buf_shake = { .shrink = xfsbufd_wakeup, @@ -340,7 +340,7 @@ _xfs_buf_lookup_pages( __func__, gfp_mask); XFS_STATS_INC(xb_page_retries); - xfsbufd_wakeup(0, gfp_mask); + xfsbufd_wakeup(NULL, 0, gfp_mask); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } @@ -1762,6 +1762,7 @@ xfs_buf_runall_queues( STATIC int xfsbufd_wakeup( + struct shrinker *shrink, int priority, gfp_t mask) { diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index f2d1718c9165..80938c736c27 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1883,7 +1883,6 @@ init_xfs_fs(void) goto out_cleanup_procfs; vfs_initquota(); - xfs_inode_shrinker_init(); error = register_filesystem(&xfs_fs_type); if (error) @@ -1911,7 +1910,6 @@ exit_xfs_fs(void) { vfs_exitquota(); unregister_filesystem(&xfs_fs_type); - xfs_inode_shrinker_destroy(); xfs_sysctl_unregister(); xfs_cleanup_procfs(); xfs_buf_terminate(); diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index ef7f0218bccb..a51a07c3a70c 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -144,6 +144,41 @@ restart: return last_error; } +/* + * Select the next per-ag structure to iterate during the walk. The reclaim + * walk is optimised only to walk AGs with reclaimable inodes in them. + */ +static struct xfs_perag * +xfs_inode_ag_iter_next_pag( + struct xfs_mount *mp, + xfs_agnumber_t *first, + int tag) +{ + struct xfs_perag *pag = NULL; + + if (tag == XFS_ICI_RECLAIM_TAG) { + int found; + int ref; + + spin_lock(&mp->m_perag_lock); + found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, + (void **)&pag, *first, 1, tag); + if (found <= 0) { + spin_unlock(&mp->m_perag_lock); + return NULL; + } + *first = pag->pag_agno + 1; + /* open coded pag reference increment */ + ref = atomic_inc_return(&pag->pag_ref); + spin_unlock(&mp->m_perag_lock); + trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_); + } else { + pag = xfs_perag_get(mp, *first); + (*first)++; + } + return pag; +} + int xfs_inode_ag_iterator( struct xfs_mount *mp, @@ -154,16 +189,15 @@ xfs_inode_ag_iterator( int exclusive, int *nr_to_scan) { + struct xfs_perag *pag; int error = 0; int last_error = 0; xfs_agnumber_t ag; int nr; nr = nr_to_scan ? *nr_to_scan : INT_MAX; - for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) { - struct xfs_perag *pag; - - pag = xfs_perag_get(mp, ag); + ag = 0; + while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, tag))) { error = xfs_inode_ag_walk(mp, pag, execute, flags, tag, exclusive, &nr); xfs_perag_put(pag); @@ -640,6 +674,17 @@ __xfs_inode_set_reclaim_tag( radix_tree_tag_set(&pag->pag_ici_root, XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), XFS_ICI_RECLAIM_TAG); + + if (!pag->pag_ici_reclaimable) { + /* propagate the reclaim tag up into the perag radix tree */ + spin_lock(&ip->i_mount->m_perag_lock); + radix_tree_tag_set(&ip->i_mount->m_perag_tree, + XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), + XFS_ICI_RECLAIM_TAG); + spin_unlock(&ip->i_mount->m_perag_lock); + trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno, + -1, _RET_IP_); + } pag->pag_ici_reclaimable++; } @@ -674,6 +719,16 @@ __xfs_inode_clear_reclaim_tag( radix_tree_tag_clear(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); pag->pag_ici_reclaimable--; + if (!pag->pag_ici_reclaimable) { + /* clear the reclaim tag from the perag radix tree */ + spin_lock(&ip->i_mount->m_perag_lock); + radix_tree_tag_clear(&ip->i_mount->m_perag_tree, + XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), + XFS_ICI_RECLAIM_TAG); + spin_unlock(&ip->i_mount->m_perag_lock); + trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno, + -1, _RET_IP_); + } } /* @@ -828,83 +883,52 @@ xfs_reclaim_inodes( /* * Shrinker infrastructure. - * - * This is all far more complex than it needs to be. It adds a global list of - * mounts because the shrinkers can only call a global context. We need to make - * the shrinkers pass a context to avoid the need for global state. */ -static LIST_HEAD(xfs_mount_list); -static struct rw_semaphore xfs_mount_list_lock; - static int xfs_reclaim_inode_shrink( + struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { struct xfs_mount *mp; struct xfs_perag *pag; xfs_agnumber_t ag; - int reclaimable = 0; + int reclaimable; + mp = container_of(shrink, struct xfs_mount, m_inode_shrink); if (nr_to_scan) { if (!(gfp_mask & __GFP_FS)) return -1; - down_read(&xfs_mount_list_lock); - list_for_each_entry(mp, &xfs_mount_list, m_mplist) { - xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0, + xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0, XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan); - if (nr_to_scan <= 0) - break; - } - up_read(&xfs_mount_list_lock); - } + /* if we don't exhaust the scan, don't bother coming back */ + if (nr_to_scan > 0) + return -1; + } - down_read(&xfs_mount_list_lock); - list_for_each_entry(mp, &xfs_mount_list, m_mplist) { - for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) { - pag = xfs_perag_get(mp, ag); - reclaimable += pag->pag_ici_reclaimable; - xfs_perag_put(pag); - } + reclaimable = 0; + ag = 0; + while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, + XFS_ICI_RECLAIM_TAG))) { + reclaimable += pag->pag_ici_reclaimable; + xfs_perag_put(pag); } - up_read(&xfs_mount_list_lock); return reclaimable; } -static struct shrinker xfs_inode_shrinker = { - .shrink = xfs_reclaim_inode_shrink, - .seeks = DEFAULT_SEEKS, -}; - -void __init -xfs_inode_shrinker_init(void) -{ - init_rwsem(&xfs_mount_list_lock); - register_shrinker(&xfs_inode_shrinker); -} - -void -xfs_inode_shrinker_destroy(void) -{ - ASSERT(list_empty(&xfs_mount_list)); - unregister_shrinker(&xfs_inode_shrinker); -} - void xfs_inode_shrinker_register( struct xfs_mount *mp) { - down_write(&xfs_mount_list_lock); - list_add_tail(&mp->m_mplist, &xfs_mount_list); - up_write(&xfs_mount_list_lock); + mp->m_inode_shrink.shrink = xfs_reclaim_inode_shrink; + mp->m_inode_shrink.seeks = DEFAULT_SEEKS; + register_shrinker(&mp->m_inode_shrink); } void xfs_inode_shrinker_unregister( struct xfs_mount *mp) { - down_write(&xfs_mount_list_lock); - list_del(&mp->m_mplist); - up_write(&xfs_mount_list_lock); + unregister_shrinker(&mp->m_inode_shrink); } diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index cdcbaaca9880..e28139aaa4aa 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -55,8 +55,6 @@ int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), int flags, int tag, int write_lock, int *nr_to_scan); -void xfs_inode_shrinker_init(void); -void xfs_inode_shrinker_destroy(void); void xfs_inode_shrinker_register(struct xfs_mount *mp); void xfs_inode_shrinker_unregister(struct xfs_mount *mp); diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h index 73d5aa117384..302820690904 100644 --- a/fs/xfs/linux-2.6/xfs_trace.h +++ b/fs/xfs/linux-2.6/xfs_trace.h @@ -124,7 +124,10 @@ DEFINE_EVENT(xfs_perag_class, name, \ unsigned long caller_ip), \ TP_ARGS(mp, agno, refcount, caller_ip)) DEFINE_PERAG_REF_EVENT(xfs_perag_get); +DEFINE_PERAG_REF_EVENT(xfs_perag_get_reclaim); DEFINE_PERAG_REF_EVENT(xfs_perag_put); +DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim); +DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim); TRACE_EVENT(xfs_attr_list_node_descend, TP_PROTO(struct xfs_attr_list_context *ctx, diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 8c117ff2e3ab..67c018392d62 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -69,7 +69,7 @@ STATIC void xfs_qm_list_destroy(xfs_dqlist_t *); STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); -STATIC int xfs_qm_shake(int, gfp_t); +STATIC int xfs_qm_shake(struct shrinker *, int, gfp_t); static struct shrinker xfs_qm_shaker = { .shrink = xfs_qm_shake, @@ -2117,7 +2117,10 @@ xfs_qm_shake_freelist( */ /* ARGSUSED */ STATIC int -xfs_qm_shake(int nr_to_scan, gfp_t gfp_mask) +xfs_qm_shake( + struct shrinker *shrink, + int nr_to_scan, + gfp_t gfp_mask) { int ndqused, nfree, n; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 1d2c7eed4eda..5761087ee8ea 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -259,7 +259,7 @@ typedef struct xfs_mount { wait_queue_head_t m_wait_single_sync_task; __int64_t m_update_flags; /* sb flags we need to update on the next remount,rw */ - struct list_head m_mplist; /* inode shrinker mount list */ + struct shrinker m_inode_shrink; /* inode reclaim shrinker */ } xfs_mount_t; /* diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 013dc529e95f..d147461bc271 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -61,7 +61,8 @@ struct files_struct { (rcu_dereference_check((fdtfd), \ rcu_read_lock_held() || \ lockdep_is_held(&(files)->file_lock) || \ - atomic_read(&(files)->count) == 1)) + atomic_read(&(files)->count) == 1 || \ + rcu_my_thread_group_empty())) #define files_fdtable(files) \ (rcu_dereference_check_fdtable((files), (files)->fdt)) diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 9bf6870ee5f4..a986ff588944 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -46,31 +46,31 @@ int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, #else -void i8042_lock_chip(void) +static inline void i8042_lock_chip(void) { } -void i8042_unlock_chip(void) +static inline void i8042_unlock_chip(void) { } -int i8042_command(unsigned char *param, int command) +static inline int i8042_command(unsigned char *param, int command) { return -ENODEV; } -bool i8042_check_port_owner(const struct serio *serio) +static inline bool i8042_check_port_owner(const struct serio *serio) { return false; } -int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, +static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)) { return -ENODEV; } -int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, +static inline int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)) { return -ENODEV; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a4d2e9f7088a..adf832dec3f3 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1026,11 +1026,12 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); struct jbd2_buffer_trigger_type { /* - * Fired just before a buffer is written to the journal. - * mapped_data is a mapped buffer that is the frozen data for - * commit. + * Fired a the moment data to write to the journal are known to be + * stable - so either at the moment b_frozen_data is created or just + * before a buffer is written to the journal. mapped_data is a mapped + * buffer that is the frozen data for commit. */ - void (*t_commit)(struct jbd2_buffer_trigger_type *type, + void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); @@ -1042,7 +1043,7 @@ struct jbd2_buffer_trigger_type { struct buffer_head *bh); }; -extern void jbd2_buffer_commit_trigger(struct journal_head *jh, +extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, diff --git a/include/linux/lmb.h b/include/linux/lmb.h deleted file mode 100644 index f3d14333ebed..000000000000 --- a/include/linux/lmb.h +++ /dev/null @@ -1,89 +0,0 @@ -#ifndef _LINUX_LMB_H -#define _LINUX_LMB_H -#ifdef __KERNEL__ - -/* - * Logical memory blocks. - * - * Copyright (C) 2001 Peter Bergner, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/init.h> -#include <linux/mm.h> - -#define MAX_LMB_REGIONS 128 - -struct lmb_property { - u64 base; - u64 size; -}; - -struct lmb_region { - unsigned long cnt; - u64 size; - struct lmb_property region[MAX_LMB_REGIONS+1]; -}; - -struct lmb { - unsigned long debug; - u64 rmo_size; - struct lmb_region memory; - struct lmb_region reserved; -}; - -extern struct lmb lmb; - -extern void __init lmb_init(void); -extern void __init lmb_analyze(void); -extern long lmb_add(u64 base, u64 size); -extern long lmb_remove(u64 base, u64 size); -extern long __init lmb_free(u64 base, u64 size); -extern long __init lmb_reserve(u64 base, u64 size); -extern u64 __init lmb_alloc_nid(u64 size, u64 align, int nid, - u64 (*nid_range)(u64, u64, int *)); -extern u64 __init lmb_alloc(u64 size, u64 align); -extern u64 __init lmb_alloc_base(u64 size, - u64, u64 max_addr); -extern u64 __init __lmb_alloc_base(u64 size, - u64 align, u64 max_addr); -extern u64 __init lmb_phys_mem_size(void); -extern u64 lmb_end_of_DRAM(void); -extern void __init lmb_enforce_memory_limit(u64 memory_limit); -extern int __init lmb_is_reserved(u64 addr); -extern int lmb_is_region_reserved(u64 base, u64 size); -extern int lmb_find(struct lmb_property *res); - -extern void lmb_dump_all(void); - -static inline u64 -lmb_size_bytes(struct lmb_region *type, unsigned long region_nr) -{ - return type->region[region_nr].size; -} -static inline u64 -lmb_size_pages(struct lmb_region *type, unsigned long region_nr) -{ - return lmb_size_bytes(type, region_nr) >> PAGE_SHIFT; -} -static inline u64 -lmb_start_pfn(struct lmb_region *type, unsigned long region_nr) -{ - return type->region[region_nr].base >> PAGE_SHIFT; -} -static inline u64 -lmb_end_pfn(struct lmb_region *type, unsigned long region_nr) -{ - return lmb_start_pfn(type, region_nr) + - lmb_size_pages(type, region_nr); -} - -#include <asm/lmb.h> - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_LMB_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h new file mode 100644 index 000000000000..a59faf2b5edd --- /dev/null +++ b/include/linux/memblock.h @@ -0,0 +1,89 @@ +#ifndef _LINUX_MEMBLOCK_H +#define _LINUX_MEMBLOCK_H +#ifdef __KERNEL__ + +/* + * Logical memory blocks. + * + * Copyright (C) 2001 Peter Bergner, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mm.h> + +#define MAX_MEMBLOCK_REGIONS 128 + +struct memblock_property { + u64 base; + u64 size; +}; + +struct memblock_region { + unsigned long cnt; + u64 size; + struct memblock_property region[MAX_MEMBLOCK_REGIONS+1]; +}; + +struct memblock { + unsigned long debug; + u64 rmo_size; + struct memblock_region memory; + struct memblock_region reserved; +}; + +extern struct memblock memblock; + +extern void __init memblock_init(void); +extern void __init memblock_analyze(void); +extern long memblock_add(u64 base, u64 size); +extern long memblock_remove(u64 base, u64 size); +extern long __init memblock_free(u64 base, u64 size); +extern long __init memblock_reserve(u64 base, u64 size); +extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid, + u64 (*nid_range)(u64, u64, int *)); +extern u64 __init memblock_alloc(u64 size, u64 align); +extern u64 __init memblock_alloc_base(u64 size, + u64, u64 max_addr); +extern u64 __init __memblock_alloc_base(u64 size, + u64 align, u64 max_addr); +extern u64 __init memblock_phys_mem_size(void); +extern u64 memblock_end_of_DRAM(void); +extern void __init memblock_enforce_memory_limit(u64 memory_limit); +extern int __init memblock_is_reserved(u64 addr); +extern int memblock_is_region_reserved(u64 base, u64 size); +extern int memblock_find(struct memblock_property *res); + +extern void memblock_dump_all(void); + +static inline u64 +memblock_size_bytes(struct memblock_region *type, unsigned long region_nr) +{ + return type->region[region_nr].size; +} +static inline u64 +memblock_size_pages(struct memblock_region *type, unsigned long region_nr) +{ + return memblock_size_bytes(type, region_nr) >> PAGE_SHIFT; +} +static inline u64 +memblock_start_pfn(struct memblock_region *type, unsigned long region_nr) +{ + return type->region[region_nr].base >> PAGE_SHIFT; +} +static inline u64 +memblock_end_pfn(struct memblock_region *type, unsigned long region_nr) +{ + return memblock_start_pfn(type, region_nr) + + memblock_size_pages(type, region_nr); +} + +#include <asm/memblock.h> + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_MEMBLOCK_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b969efb03787..a2b48041b910 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -999,7 +999,7 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) * querying the cache size, so a fastpath for that case is appropriate. */ struct shrinker { - int (*shrink)(int nr_to_scan, gfp_t gfp_mask); + int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask); int seeks; /* seeks to recreate an obj */ /* These are for internal use */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 7cb00845f150..f26fda76b87f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -288,6 +288,7 @@ struct pci_dev { */ unsigned int irq; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ + resource_size_t fw_addr[DEVICE_COUNT_RESOURCE]; /* FW-assigned addr */ /* These fields are used by common fixups */ unsigned int transparent:1; /* Transparent PCI bridge */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7f614ce274a9..13ebb5413a79 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -124,7 +124,8 @@ extern struct trace_event_functions enter_syscall_print_funcs; extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ - static struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata \ + __attribute__((__aligned__(4))) __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_enter_##sname; \ static struct ftrace_event_call __used \ @@ -138,7 +139,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ - static struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata \ + __attribute__((__aligned__(4))) __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_exit_##sname; \ static struct ftrace_event_call __used \ diff --git a/include/net/sock.h b/include/net/sock.h index 731150d52799..0a691ea7654a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1224,12 +1224,7 @@ static inline void sk_tx_queue_clear(struct sock *sk) static inline int sk_tx_queue_get(const struct sock *sk) { - return sk->sk_tx_queue_mapping; -} - -static inline bool sk_tx_queue_recorded(const struct sock *sk) -{ - return (sk && sk->sk_tx_queue_mapping >= 0); + return sk ? sk->sk_tx_queue_mapping : -1; } static inline void sk_set_socket(struct sock *sk, struct socket *sock) diff --git a/ipc/sem.c b/ipc/sem.c index 506c8491a8d1..40a8f462a822 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1256,6 +1256,33 @@ out: return un; } + +/** + * get_queue_result - Retrieve the result code from sem_queue + * @q: Pointer to queue structure + * + * Retrieve the return code from the pending queue. If IN_WAKEUP is found in + * q->status, then we must loop until the value is replaced with the final + * value: This may happen if a task is woken up by an unrelated event (e.g. + * signal) and in parallel the task is woken up by another task because it got + * the requested semaphores. + * + * The function can be called with or without holding the semaphore spinlock. + */ +static int get_queue_result(struct sem_queue *q) +{ + int error; + + error = q->status; + while (unlikely(error == IN_WAKEUP)) { + cpu_relax(); + error = q->status; + } + + return error; +} + + SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, unsigned, nsops, const struct timespec __user *, timeout) { @@ -1409,15 +1436,18 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, else schedule(); - error = queue.status; - while(unlikely(error == IN_WAKEUP)) { - cpu_relax(); - error = queue.status; - } + error = get_queue_result(&queue); if (error != -EINTR) { /* fast path: update_queue already obtained all requested - * resources */ + * resources. + * Perform a smp_mb(): User space could assume that semop() + * is a memory barrier: Without the mb(), the cpu could + * speculatively read in user space stale data that was + * overwritten by the previous owner of the semaphore. + */ + smp_mb(); + goto out_free; } @@ -1427,10 +1457,12 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, goto out_free; } + error = get_queue_result(&queue); + /* * If queue.status != -EINTR we are woken up by another process */ - error = queue.status; + if (error != -EINTR) { goto out_unlock_free; } diff --git a/kernel/early_res.c b/kernel/early_res.c index 31aa9332ef3f..7bfae887f211 100644 --- a/kernel/early_res.c +++ b/kernel/early_res.c @@ -7,6 +7,8 @@ #include <linux/bootmem.h> #include <linux/mm.h> #include <linux/early_res.h> +#include <linux/slab.h> +#include <linux/kmemleak.h> /* * Early reserved memory areas. @@ -319,6 +321,8 @@ void __init free_early(u64 start, u64 end) struct early_res *r; int i; + kmemleak_free_part(__va(start), end - start); + i = find_overlapped_early(start, end); r = &early_res[i]; if (i >= max_early_res || r->end != end || r->start != start) @@ -333,6 +337,8 @@ void __init free_early_partial(u64 start, u64 end) struct early_res *r; int i; + kmemleak_free_part(__va(start), end - start); + if (start == end) return; diff --git a/lib/Kconfig b/lib/Kconfig index 170d8ca901d8..5b916bc0fbae 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -181,9 +181,6 @@ config HAS_DMA config CHECK_SIGNATURE bool -config HAVE_LMB - boolean - config CPUMASK_OFFSTACK bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS help diff --git a/lib/Makefile b/lib/Makefile index 3f1062cbbff4..0bfabba1bb32 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -89,8 +89,6 @@ obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o lib-$(CONFIG_GENERIC_BUG) += bug.o -obj-$(CONFIG_HAVE_LMB) += lmb.o - obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o diff --git a/lib/lmb.c b/lib/lmb.c deleted file mode 100644 index b1fc52606524..000000000000 --- a/lib/lmb.c +++ /dev/null @@ -1,541 +0,0 @@ -/* - * Procedures for maintaining information about logical memory blocks. - * - * Peter Bergner, IBM Corp. June 2001. - * Copyright (C) 2001 Peter Bergner. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/bitops.h> -#include <linux/lmb.h> - -#define LMB_ALLOC_ANYWHERE 0 - -struct lmb lmb; - -static int lmb_debug; - -static int __init early_lmb(char *p) -{ - if (p && strstr(p, "debug")) - lmb_debug = 1; - return 0; -} -early_param("lmb", early_lmb); - -static void lmb_dump(struct lmb_region *region, char *name) -{ - unsigned long long base, size; - int i; - - pr_info(" %s.cnt = 0x%lx\n", name, region->cnt); - - for (i = 0; i < region->cnt; i++) { - base = region->region[i].base; - size = region->region[i].size; - - pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n", - name, i, base, base + size - 1, size); - } -} - -void lmb_dump_all(void) -{ - if (!lmb_debug) - return; - - pr_info("LMB configuration:\n"); - pr_info(" rmo_size = 0x%llx\n", (unsigned long long)lmb.rmo_size); - pr_info(" memory.size = 0x%llx\n", (unsigned long long)lmb.memory.size); - - lmb_dump(&lmb.memory, "memory"); - lmb_dump(&lmb.reserved, "reserved"); -} - -static unsigned long lmb_addrs_overlap(u64 base1, u64 size1, u64 base2, - u64 size2) -{ - return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); -} - -static long lmb_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2) -{ - if (base2 == base1 + size1) - return 1; - else if (base1 == base2 + size2) - return -1; - - return 0; -} - -static long lmb_regions_adjacent(struct lmb_region *rgn, - unsigned long r1, unsigned long r2) -{ - u64 base1 = rgn->region[r1].base; - u64 size1 = rgn->region[r1].size; - u64 base2 = rgn->region[r2].base; - u64 size2 = rgn->region[r2].size; - - return lmb_addrs_adjacent(base1, size1, base2, size2); -} - -static void lmb_remove_region(struct lmb_region *rgn, unsigned long r) -{ - unsigned long i; - - for (i = r; i < rgn->cnt - 1; i++) { - rgn->region[i].base = rgn->region[i + 1].base; - rgn->region[i].size = rgn->region[i + 1].size; - } - rgn->cnt--; -} - -/* Assumption: base addr of region 1 < base addr of region 2 */ -static void lmb_coalesce_regions(struct lmb_region *rgn, - unsigned long r1, unsigned long r2) -{ - rgn->region[r1].size += rgn->region[r2].size; - lmb_remove_region(rgn, r2); -} - -void __init lmb_init(void) -{ - /* Create a dummy zero size LMB which will get coalesced away later. - * This simplifies the lmb_add() code below... - */ - lmb.memory.region[0].base = 0; - lmb.memory.region[0].size = 0; - lmb.memory.cnt = 1; - - /* Ditto. */ - lmb.reserved.region[0].base = 0; - lmb.reserved.region[0].size = 0; - lmb.reserved.cnt = 1; -} - -void __init lmb_analyze(void) -{ - int i; - - lmb.memory.size = 0; - - for (i = 0; i < lmb.memory.cnt; i++) - lmb.memory.size += lmb.memory.region[i].size; -} - -static long lmb_add_region(struct lmb_region *rgn, u64 base, u64 size) -{ - unsigned long coalesced = 0; - long adjacent, i; - - if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) { - rgn->region[0].base = base; - rgn->region[0].size = size; - return 0; - } - - /* First try and coalesce this LMB with another. */ - for (i = 0; i < rgn->cnt; i++) { - u64 rgnbase = rgn->region[i].base; - u64 rgnsize = rgn->region[i].size; - - if ((rgnbase == base) && (rgnsize == size)) - /* Already have this region, so we're done */ - return 0; - - adjacent = lmb_addrs_adjacent(base, size, rgnbase, rgnsize); - if (adjacent > 0) { - rgn->region[i].base -= size; - rgn->region[i].size += size; - coalesced++; - break; - } else if (adjacent < 0) { - rgn->region[i].size += size; - coalesced++; - break; - } - } - - if ((i < rgn->cnt - 1) && lmb_regions_adjacent(rgn, i, i+1)) { - lmb_coalesce_regions(rgn, i, i+1); - coalesced++; - } - - if (coalesced) - return coalesced; - if (rgn->cnt >= MAX_LMB_REGIONS) - return -1; - - /* Couldn't coalesce the LMB, so add it to the sorted table. */ - for (i = rgn->cnt - 1; i >= 0; i--) { - if (base < rgn->region[i].base) { - rgn->region[i+1].base = rgn->region[i].base; - rgn->region[i+1].size = rgn->region[i].size; - } else { - rgn->region[i+1].base = base; - rgn->region[i+1].size = size; - break; - } - } - - if (base < rgn->region[0].base) { - rgn->region[0].base = base; - rgn->region[0].size = size; - } - rgn->cnt++; - - return 0; -} - -long lmb_add(u64 base, u64 size) -{ - struct lmb_region *_rgn = &lmb.memory; - - /* On pSeries LPAR systems, the first LMB is our RMO region. */ - if (base == 0) - lmb.rmo_size = size; - - return lmb_add_region(_rgn, base, size); - -} - -static long __lmb_remove(struct lmb_region *rgn, u64 base, u64 size) -{ - u64 rgnbegin, rgnend; - u64 end = base + size; - int i; - - rgnbegin = rgnend = 0; /* supress gcc warnings */ - - /* Find the region where (base, size) belongs to */ - for (i=0; i < rgn->cnt; i++) { - rgnbegin = rgn->region[i].base; - rgnend = rgnbegin + rgn->region[i].size; - - if ((rgnbegin <= base) && (end <= rgnend)) - break; - } - - /* Didn't find the region */ - if (i == rgn->cnt) - return -1; - - /* Check to see if we are removing entire region */ - if ((rgnbegin == base) && (rgnend == end)) { - lmb_remove_region(rgn, i); - return 0; - } - - /* Check to see if region is matching at the front */ - if (rgnbegin == base) { - rgn->region[i].base = end; - rgn->region[i].size -= size; - return 0; - } - - /* Check to see if the region is matching at the end */ - if (rgnend == end) { - rgn->region[i].size -= size; - return 0; - } - - /* - * We need to split the entry - adjust the current one to the - * beginging of the hole and add the region after hole. - */ - rgn->region[i].size = base - rgn->region[i].base; - return lmb_add_region(rgn, end, rgnend - end); -} - -long lmb_remove(u64 base, u64 size) -{ - return __lmb_remove(&lmb.memory, base, size); -} - -long __init lmb_free(u64 base, u64 size) -{ - return __lmb_remove(&lmb.reserved, base, size); -} - -long __init lmb_reserve(u64 base, u64 size) -{ - struct lmb_region *_rgn = &lmb.reserved; - - BUG_ON(0 == size); - - return lmb_add_region(_rgn, base, size); -} - -long lmb_overlaps_region(struct lmb_region *rgn, u64 base, u64 size) -{ - unsigned long i; - - for (i = 0; i < rgn->cnt; i++) { - u64 rgnbase = rgn->region[i].base; - u64 rgnsize = rgn->region[i].size; - if (lmb_addrs_overlap(base, size, rgnbase, rgnsize)) - break; - } - - return (i < rgn->cnt) ? i : -1; -} - -static u64 lmb_align_down(u64 addr, u64 size) -{ - return addr & ~(size - 1); -} - -static u64 lmb_align_up(u64 addr, u64 size) -{ - return (addr + (size - 1)) & ~(size - 1); -} - -static u64 __init lmb_alloc_nid_unreserved(u64 start, u64 end, - u64 size, u64 align) -{ - u64 base, res_base; - long j; - - base = lmb_align_down((end - size), align); - while (start <= base) { - j = lmb_overlaps_region(&lmb.reserved, base, size); - if (j < 0) { - /* this area isn't reserved, take it */ - if (lmb_add_region(&lmb.reserved, base, size) < 0) - base = ~(u64)0; - return base; - } - res_base = lmb.reserved.region[j].base; - if (res_base < size) - break; - base = lmb_align_down(res_base - size, align); - } - - return ~(u64)0; -} - -static u64 __init lmb_alloc_nid_region(struct lmb_property *mp, - u64 (*nid_range)(u64, u64, int *), - u64 size, u64 align, int nid) -{ - u64 start, end; - - start = mp->base; - end = start + mp->size; - - start = lmb_align_up(start, align); - while (start < end) { - u64 this_end; - int this_nid; - - this_end = nid_range(start, end, &this_nid); - if (this_nid == nid) { - u64 ret = lmb_alloc_nid_unreserved(start, this_end, - size, align); - if (ret != ~(u64)0) - return ret; - } - start = this_end; - } - - return ~(u64)0; -} - -u64 __init lmb_alloc_nid(u64 size, u64 align, int nid, - u64 (*nid_range)(u64 start, u64 end, int *nid)) -{ - struct lmb_region *mem = &lmb.memory; - int i; - - BUG_ON(0 == size); - - size = lmb_align_up(size, align); - - for (i = 0; i < mem->cnt; i++) { - u64 ret = lmb_alloc_nid_region(&mem->region[i], - nid_range, - size, align, nid); - if (ret != ~(u64)0) - return ret; - } - - return lmb_alloc(size, align); -} - -u64 __init lmb_alloc(u64 size, u64 align) -{ - return lmb_alloc_base(size, align, LMB_ALLOC_ANYWHERE); -} - -u64 __init lmb_alloc_base(u64 size, u64 align, u64 max_addr) -{ - u64 alloc; - - alloc = __lmb_alloc_base(size, align, max_addr); - - if (alloc == 0) - panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", - (unsigned long long) size, (unsigned long long) max_addr); - - return alloc; -} - -u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr) -{ - long i, j; - u64 base = 0; - u64 res_base; - - BUG_ON(0 == size); - - size = lmb_align_up(size, align); - - /* On some platforms, make sure we allocate lowmem */ - /* Note that LMB_REAL_LIMIT may be LMB_ALLOC_ANYWHERE */ - if (max_addr == LMB_ALLOC_ANYWHERE) - max_addr = LMB_REAL_LIMIT; - - for (i = lmb.memory.cnt - 1; i >= 0; i--) { - u64 lmbbase = lmb.memory.region[i].base; - u64 lmbsize = lmb.memory.region[i].size; - - if (lmbsize < size) - continue; - if (max_addr == LMB_ALLOC_ANYWHERE) - base = lmb_align_down(lmbbase + lmbsize - size, align); - else if (lmbbase < max_addr) { - base = min(lmbbase + lmbsize, max_addr); - base = lmb_align_down(base - size, align); - } else - continue; - - while (base && lmbbase <= base) { - j = lmb_overlaps_region(&lmb.reserved, base, size); - if (j < 0) { - /* this area isn't reserved, take it */ - if (lmb_add_region(&lmb.reserved, base, size) < 0) - return 0; - return base; - } - res_base = lmb.reserved.region[j].base; - if (res_base < size) - break; - base = lmb_align_down(res_base - size, align); - } - } - return 0; -} - -/* You must call lmb_analyze() before this. */ -u64 __init lmb_phys_mem_size(void) -{ - return lmb.memory.size; -} - -u64 lmb_end_of_DRAM(void) -{ - int idx = lmb.memory.cnt - 1; - - return (lmb.memory.region[idx].base + lmb.memory.region[idx].size); -} - -/* You must call lmb_analyze() after this. */ -void __init lmb_enforce_memory_limit(u64 memory_limit) -{ - unsigned long i; - u64 limit; - struct lmb_property *p; - - if (!memory_limit) - return; - - /* Truncate the lmb regions to satisfy the memory limit. */ - limit = memory_limit; - for (i = 0; i < lmb.memory.cnt; i++) { - if (limit > lmb.memory.region[i].size) { - limit -= lmb.memory.region[i].size; - continue; - } - - lmb.memory.region[i].size = limit; - lmb.memory.cnt = i + 1; - break; - } - - if (lmb.memory.region[0].size < lmb.rmo_size) - lmb.rmo_size = lmb.memory.region[0].size; - - memory_limit = lmb_end_of_DRAM(); - - /* And truncate any reserves above the limit also. */ - for (i = 0; i < lmb.reserved.cnt; i++) { - p = &lmb.reserved.region[i]; - - if (p->base > memory_limit) - p->size = 0; - else if ((p->base + p->size) > memory_limit) - p->size = memory_limit - p->base; - - if (p->size == 0) { - lmb_remove_region(&lmb.reserved, i); - i--; - } - } -} - -int __init lmb_is_reserved(u64 addr) -{ - int i; - - for (i = 0; i < lmb.reserved.cnt; i++) { - u64 upper = lmb.reserved.region[i].base + - lmb.reserved.region[i].size - 1; - if ((addr >= lmb.reserved.region[i].base) && (addr <= upper)) - return 1; - } - return 0; -} - -int lmb_is_region_reserved(u64 base, u64 size) -{ - return lmb_overlaps_region(&lmb.reserved, base, size); -} - -/* - * Given a <base, len>, find which memory regions belong to this range. - * Adjust the request and return a contiguous chunk. - */ -int lmb_find(struct lmb_property *res) -{ - int i; - u64 rstart, rend; - - rstart = res->base; - rend = rstart + res->size - 1; - - for (i = 0; i < lmb.memory.cnt; i++) { - u64 start = lmb.memory.region[i].base; - u64 end = start + lmb.memory.region[i].size - 1; - - if (start > rend) - return -1; - - if ((end >= rstart) && (start < rend)) { - /* adjust the request */ - if (rstart < start) - rstart = start; - if (rend > end) - rend = end; - res->base = rstart; - res->size = rend - rstart + 1; - return 0; - } - } - return -1; -} diff --git a/mm/Kconfig b/mm/Kconfig index 527136b22384..f4e516e9c37c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -128,6 +128,9 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. +config HAVE_MEMBLOCK + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" diff --git a/mm/Makefile b/mm/Makefile index 8982504bd03b..34b2546a9e37 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -15,6 +15,8 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ $(mmu-y) obj-y += init-mm.o +obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o + obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HAS_DMA) += dmapool.o diff --git a/mm/bootmem.c b/mm/bootmem.c index 58c66cc5056a..142c84a54993 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -833,15 +833,24 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { + void *ptr; + if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); #ifdef CONFIG_NO_BOOTMEM - return __alloc_memory_core_early(pgdat->node_id, size, align, + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, -1ULL); + if (ptr) + return ptr; + + ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, -1ULL); #else - return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); + ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); #endif + + return ptr; } void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, @@ -977,14 +986,21 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { + void *ptr; + if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); #ifdef CONFIG_NO_BOOTMEM - return __alloc_memory_core_early(pgdat->node_id, size, align, + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, ARCH_LOW_ADDRESS_LIMIT); + if (ptr) + return ptr; + ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, ARCH_LOW_ADDRESS_LIMIT); #else - return ___alloc_bootmem_node(pgdat->bdata, size, align, + ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, ARCH_LOW_ADDRESS_LIMIT); #endif + return ptr; } diff --git a/mm/memblock.c b/mm/memblock.c new file mode 100644 index 000000000000..3024eb30fc27 --- /dev/null +++ b/mm/memblock.c @@ -0,0 +1,541 @@ +/* + * Procedures for maintaining information about logical memory blocks. + * + * Peter Bergner, IBM Corp. June 2001. + * Copyright (C) 2001 Peter Bergner. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/memblock.h> + +#define MEMBLOCK_ALLOC_ANYWHERE 0 + +struct memblock memblock; + +static int memblock_debug; + +static int __init early_memblock(char *p) +{ + if (p && strstr(p, "debug")) + memblock_debug = 1; + return 0; +} +early_param("memblock", early_memblock); + +static void memblock_dump(struct memblock_region *region, char *name) +{ + unsigned long long base, size; + int i; + + pr_info(" %s.cnt = 0x%lx\n", name, region->cnt); + + for (i = 0; i < region->cnt; i++) { + base = region->region[i].base; + size = region->region[i].size; + + pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n", + name, i, base, base + size - 1, size); + } +} + +void memblock_dump_all(void) +{ + if (!memblock_debug) + return; + + pr_info("MEMBLOCK configuration:\n"); + pr_info(" rmo_size = 0x%llx\n", (unsigned long long)memblock.rmo_size); + pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size); + + memblock_dump(&memblock.memory, "memory"); + memblock_dump(&memblock.reserved, "reserved"); +} + +static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2, + u64 size2) +{ + return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); +} + +static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2) +{ + if (base2 == base1 + size1) + return 1; + else if (base1 == base2 + size2) + return -1; + + return 0; +} + +static long memblock_regions_adjacent(struct memblock_region *rgn, + unsigned long r1, unsigned long r2) +{ + u64 base1 = rgn->region[r1].base; + u64 size1 = rgn->region[r1].size; + u64 base2 = rgn->region[r2].base; + u64 size2 = rgn->region[r2].size; + + return memblock_addrs_adjacent(base1, size1, base2, size2); +} + +static void memblock_remove_region(struct memblock_region *rgn, unsigned long r) +{ + unsigned long i; + + for (i = r; i < rgn->cnt - 1; i++) { + rgn->region[i].base = rgn->region[i + 1].base; + rgn->region[i].size = rgn->region[i + 1].size; + } + rgn->cnt--; +} + +/* Assumption: base addr of region 1 < base addr of region 2 */ +static void memblock_coalesce_regions(struct memblock_region *rgn, + unsigned long r1, unsigned long r2) +{ + rgn->region[r1].size += rgn->region[r2].size; + memblock_remove_region(rgn, r2); +} + +void __init memblock_init(void) +{ + /* Create a dummy zero size MEMBLOCK which will get coalesced away later. + * This simplifies the memblock_add() code below... + */ + memblock.memory.region[0].base = 0; + memblock.memory.region[0].size = 0; + memblock.memory.cnt = 1; + + /* Ditto. */ + memblock.reserved.region[0].base = 0; + memblock.reserved.region[0].size = 0; + memblock.reserved.cnt = 1; +} + +void __init memblock_analyze(void) +{ + int i; + + memblock.memory.size = 0; + + for (i = 0; i < memblock.memory.cnt; i++) + memblock.memory.size += memblock.memory.region[i].size; +} + +static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size) +{ + unsigned long coalesced = 0; + long adjacent, i; + + if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) { + rgn->region[0].base = base; + rgn->region[0].size = size; + return 0; + } + + /* First try and coalesce this MEMBLOCK with another. */ + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + + if ((rgnbase == base) && (rgnsize == size)) + /* Already have this region, so we're done */ + return 0; + + adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize); + if (adjacent > 0) { + rgn->region[i].base -= size; + rgn->region[i].size += size; + coalesced++; + break; + } else if (adjacent < 0) { + rgn->region[i].size += size; + coalesced++; + break; + } + } + + if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) { + memblock_coalesce_regions(rgn, i, i+1); + coalesced++; + } + + if (coalesced) + return coalesced; + if (rgn->cnt >= MAX_MEMBLOCK_REGIONS) + return -1; + + /* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */ + for (i = rgn->cnt - 1; i >= 0; i--) { + if (base < rgn->region[i].base) { + rgn->region[i+1].base = rgn->region[i].base; + rgn->region[i+1].size = rgn->region[i].size; + } else { + rgn->region[i+1].base = base; + rgn->region[i+1].size = size; + break; + } + } + + if (base < rgn->region[0].base) { + rgn->region[0].base = base; + rgn->region[0].size = size; + } + rgn->cnt++; + + return 0; +} + +long memblock_add(u64 base, u64 size) +{ + struct memblock_region *_rgn = &memblock.memory; + + /* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */ + if (base == 0) + memblock.rmo_size = size; + + return memblock_add_region(_rgn, base, size); + +} + +static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size) +{ + u64 rgnbegin, rgnend; + u64 end = base + size; + int i; + + rgnbegin = rgnend = 0; /* supress gcc warnings */ + + /* Find the region where (base, size) belongs to */ + for (i=0; i < rgn->cnt; i++) { + rgnbegin = rgn->region[i].base; + rgnend = rgnbegin + rgn->region[i].size; + + if ((rgnbegin <= base) && (end <= rgnend)) + break; + } + + /* Didn't find the region */ + if (i == rgn->cnt) + return -1; + + /* Check to see if we are removing entire region */ + if ((rgnbegin == base) && (rgnend == end)) { + memblock_remove_region(rgn, i); + return 0; + } + + /* Check to see if region is matching at the front */ + if (rgnbegin == base) { + rgn->region[i].base = end; + rgn->region[i].size -= size; + return 0; + } + + /* Check to see if the region is matching at the end */ + if (rgnend == end) { + rgn->region[i].size -= size; + return 0; + } + + /* + * We need to split the entry - adjust the current one to the + * beginging of the hole and add the region after hole. + */ + rgn->region[i].size = base - rgn->region[i].base; + return memblock_add_region(rgn, end, rgnend - end); +} + +long memblock_remove(u64 base, u64 size) +{ + return __memblock_remove(&memblock.memory, base, size); +} + +long __init memblock_free(u64 base, u64 size) +{ + return __memblock_remove(&memblock.reserved, base, size); +} + +long __init memblock_reserve(u64 base, u64 size) +{ + struct memblock_region *_rgn = &memblock.reserved; + + BUG_ON(0 == size); + + return memblock_add_region(_rgn, base, size); +} + +long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size) +{ + unsigned long i; + + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + if (memblock_addrs_overlap(base, size, rgnbase, rgnsize)) + break; + } + + return (i < rgn->cnt) ? i : -1; +} + +static u64 memblock_align_down(u64 addr, u64 size) +{ + return addr & ~(size - 1); +} + +static u64 memblock_align_up(u64 addr, u64 size) +{ + return (addr + (size - 1)) & ~(size - 1); +} + +static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end, + u64 size, u64 align) +{ + u64 base, res_base; + long j; + + base = memblock_align_down((end - size), align); + while (start <= base) { + j = memblock_overlaps_region(&memblock.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (memblock_add_region(&memblock.reserved, base, size) < 0) + base = ~(u64)0; + return base; + } + res_base = memblock.reserved.region[j].base; + if (res_base < size) + break; + base = memblock_align_down(res_base - size, align); + } + + return ~(u64)0; +} + +static u64 __init memblock_alloc_nid_region(struct memblock_property *mp, + u64 (*nid_range)(u64, u64, int *), + u64 size, u64 align, int nid) +{ + u64 start, end; + + start = mp->base; + end = start + mp->size; + + start = memblock_align_up(start, align); + while (start < end) { + u64 this_end; + int this_nid; + + this_end = nid_range(start, end, &this_nid); + if (this_nid == nid) { + u64 ret = memblock_alloc_nid_unreserved(start, this_end, + size, align); + if (ret != ~(u64)0) + return ret; + } + start = this_end; + } + + return ~(u64)0; +} + +u64 __init memblock_alloc_nid(u64 size, u64 align, int nid, + u64 (*nid_range)(u64 start, u64 end, int *nid)) +{ + struct memblock_region *mem = &memblock.memory; + int i; + + BUG_ON(0 == size); + + size = memblock_align_up(size, align); + + for (i = 0; i < mem->cnt; i++) { + u64 ret = memblock_alloc_nid_region(&mem->region[i], + nid_range, + size, align, nid); + if (ret != ~(u64)0) + return ret; + } + + return memblock_alloc(size, align); +} + +u64 __init memblock_alloc(u64 size, u64 align) +{ + return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE); +} + +u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr) +{ + u64 alloc; + + alloc = __memblock_alloc_base(size, align, max_addr); + + if (alloc == 0) + panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", + (unsigned long long) size, (unsigned long long) max_addr); + + return alloc; +} + +u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr) +{ + long i, j; + u64 base = 0; + u64 res_base; + + BUG_ON(0 == size); + + size = memblock_align_up(size, align); + + /* On some platforms, make sure we allocate lowmem */ + /* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */ + if (max_addr == MEMBLOCK_ALLOC_ANYWHERE) + max_addr = MEMBLOCK_REAL_LIMIT; + + for (i = memblock.memory.cnt - 1; i >= 0; i--) { + u64 memblockbase = memblock.memory.region[i].base; + u64 memblocksize = memblock.memory.region[i].size; + + if (memblocksize < size) + continue; + if (max_addr == MEMBLOCK_ALLOC_ANYWHERE) + base = memblock_align_down(memblockbase + memblocksize - size, align); + else if (memblockbase < max_addr) { + base = min(memblockbase + memblocksize, max_addr); + base = memblock_align_down(base - size, align); + } else + continue; + + while (base && memblockbase <= base) { + j = memblock_overlaps_region(&memblock.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (memblock_add_region(&memblock.reserved, base, size) < 0) + return 0; + return base; + } + res_base = memblock.reserved.region[j].base; + if (res_base < size) + break; + base = memblock_align_down(res_base - size, align); + } + } + return 0; +} + +/* You must call memblock_analyze() before this. */ +u64 __init memblock_phys_mem_size(void) +{ + return memblock.memory.size; +} + +u64 memblock_end_of_DRAM(void) +{ + int idx = memblock.memory.cnt - 1; + + return (memblock.memory.region[idx].base + memblock.memory.region[idx].size); +} + +/* You must call memblock_analyze() after this. */ +void __init memblock_enforce_memory_limit(u64 memory_limit) +{ + unsigned long i; + u64 limit; + struct memblock_property *p; + + if (!memory_limit) + return; + + /* Truncate the memblock regions to satisfy the memory limit. */ + limit = memory_limit; + for (i = 0; i < memblock.memory.cnt; i++) { + if (limit > memblock.memory.region[i].size) { + limit -= memblock.memory.region[i].size; + continue; + } + + memblock.memory.region[i].size = limit; + memblock.memory.cnt = i + 1; + break; + } + + if (memblock.memory.region[0].size < memblock.rmo_size) + memblock.rmo_size = memblock.memory.region[0].size; + + memory_limit = memblock_end_of_DRAM(); + + /* And truncate any reserves above the limit also. */ + for (i = 0; i < memblock.reserved.cnt; i++) { + p = &memblock.reserved.region[i]; + + if (p->base > memory_limit) + p->size = 0; + else if ((p->base + p->size) > memory_limit) + p->size = memory_limit - p->base; + + if (p->size == 0) { + memblock_remove_region(&memblock.reserved, i); + i--; + } + } +} + +int __init memblock_is_reserved(u64 addr) +{ + int i; + + for (i = 0; i < memblock.reserved.cnt; i++) { + u64 upper = memblock.reserved.region[i].base + + memblock.reserved.region[i].size - 1; + if ((addr >= memblock.reserved.region[i].base) && (addr <= upper)) + return 1; + } + return 0; +} + +int memblock_is_region_reserved(u64 base, u64 size) +{ + return memblock_overlaps_region(&memblock.reserved, base, size); +} + +/* + * Given a <base, len>, find which memory regions belong to this range. + * Adjust the request and return a contiguous chunk. + */ +int memblock_find(struct memblock_property *res) +{ + int i; + u64 rstart, rend; + + rstart = res->base; + rend = rstart + res->size - 1; + + for (i = 0; i < memblock.memory.cnt; i++) { + u64 start = memblock.memory.region[i].base; + u64 end = start + memblock.memory.region[i].size - 1; + + if (start > rend) + return -1; + + if ((end >= rstart) && (start < rend)) { + /* adjust the request */ + if (rstart < start) + rstart = start; + if (rend > end) + rend = end; + res->base = rstart; + res->size = rend - rstart + 1; + return 0; + } + } + return -1; +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 431214b941ac..9bd339eb04c6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3634,6 +3634,9 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, int i; void *ptr; + if (limit > get_max_mapped()) + limit = get_max_mapped(); + /* need to go over early_node_map to find out good range for node */ for_each_active_range_index_in_nid(i, nid) { u64 addr; @@ -3659,6 +3662,11 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, ptr = phys_to_virt(addr); memset(ptr, 0, size); reserve_early_without_check(addr, addr + size, "BOOTMEM"); + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. + */ + kmemleak_alloc(ptr, size, 0, 0); return ptr; } diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 6c0081441a32..5bffada7cde1 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -9,6 +9,7 @@ #include <linux/vmalloc.h> #include <linux/cgroup.h> #include <linux/swapops.h> +#include <linux/kmemleak.h> static void __meminit __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn) @@ -126,6 +127,12 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn) if (!base) base = vmalloc(table_size); } + /* + * The value stored in section->page_cgroup is (base - pfn) + * and it does not point to the memory block allocated above, + * causing kmemleak false positives. + */ + kmemleak_not_leak(base); } else { /* * We don't have to allocate page_cgroup again, but diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c7e57cc63a3..b94fe1b3da43 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -213,8 +213,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, list_for_each_entry(shrinker, &shrinker_list, list) { unsigned long long delta; unsigned long total_scan; - unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask); + unsigned long max_pass; + max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask); delta = (4 * scanned) / shrinker->seeks; delta *= max_pass; do_div(delta, lru_pages + 1); @@ -242,8 +243,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, int shrink_ret; int nr_before; - nr_before = (*shrinker->shrink)(0, gfp_mask); - shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask); + nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask); + shrink_ret = (*shrinker->shrink)(shrinker, this_scan, + gfp_mask); if (shrink_ret == -1) break; if (shrink_ret < nr_before) @@ -296,7 +298,7 @@ static int may_write_to_queue(struct backing_dev_info *bdi) static void handle_write_error(struct address_space *mapping, struct page *page, int error) { - lock_page(page); + lock_page_nosync(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b10e3cdb08f8..800b6b9fbbae 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -358,6 +358,11 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 acl->sec_level = sec_level; acl->auth_type = auth_type; hci_acl_connect(acl); + } else { + if (acl->sec_level < sec_level) + acl->sec_level = sec_level; + if (acl->auth_type < auth_type) + acl->auth_type = auth_type; } if (type == ACL_LINK) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 6c57fc71c7e2..786b5de0bac4 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1049,6 +1049,8 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (conn) { if (!ev->status) conn->link_mode |= HCI_LM_AUTH; + else + conn->sec_level = BT_SECURITY_LOW; clear_bit(HCI_CONN_AUTH_PEND, &conn->pend); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 1b682a5aa061..cf3c4073a8a6 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -401,6 +401,11 @@ static inline void l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) l2cap_send_sframe(pi, control); } +static inline int __l2cap_no_conn_pending(struct sock *sk) +{ + return !(l2cap_pi(sk)->conf_state & L2CAP_CONF_CONNECT_PEND); +} + static void l2cap_do_start(struct sock *sk) { struct l2cap_conn *conn = l2cap_pi(sk)->conn; @@ -409,12 +414,13 @@ static void l2cap_do_start(struct sock *sk) if (!(conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE)) return; - if (l2cap_check_security(sk)) { + if (l2cap_check_security(sk) && __l2cap_no_conn_pending(sk)) { struct l2cap_conn_req req; req.scid = cpu_to_le16(l2cap_pi(sk)->scid); req.psm = l2cap_pi(sk)->psm; l2cap_pi(sk)->ident = l2cap_get_ident(conn); + l2cap_pi(sk)->conf_state |= L2CAP_CONF_CONNECT_PEND; l2cap_send_cmd(conn, l2cap_pi(sk)->ident, L2CAP_CONN_REQ, sizeof(req), &req); @@ -464,12 +470,14 @@ static void l2cap_conn_start(struct l2cap_conn *conn) } if (sk->sk_state == BT_CONNECT) { - if (l2cap_check_security(sk)) { + if (l2cap_check_security(sk) && + __l2cap_no_conn_pending(sk)) { struct l2cap_conn_req req; req.scid = cpu_to_le16(l2cap_pi(sk)->scid); req.psm = l2cap_pi(sk)->psm; l2cap_pi(sk)->ident = l2cap_get_ident(conn); + l2cap_pi(sk)->conf_state |= L2CAP_CONF_CONNECT_PEND; l2cap_send_cmd(conn, l2cap_pi(sk)->ident, L2CAP_CONN_REQ, sizeof(req), &req); @@ -2912,7 +2920,6 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd l2cap_pi(sk)->ident = 0; l2cap_pi(sk)->dcid = dcid; l2cap_pi(sk)->conf_state |= L2CAP_CONF_REQ_SENT; - l2cap_pi(sk)->conf_state &= ~L2CAP_CONF_CONNECT_PEND; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, @@ -4404,6 +4411,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) req.psm = l2cap_pi(sk)->psm; l2cap_pi(sk)->ident = l2cap_get_ident(conn); + l2cap_pi(sk)->conf_state |= L2CAP_CONF_CONNECT_PEND; l2cap_send_cmd(conn, l2cap_pi(sk)->ident, L2CAP_CONN_REQ, sizeof(req), &req); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index eedf2c94820e..753fc4221f3c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -217,14 +217,6 @@ static bool br_devices_support_netpoll(struct net_bridge *br) return count != 0 && ret; } -static void br_poll_controller(struct net_device *br_dev) -{ - struct netpoll *np = br_dev->npinfo->netpoll; - - if (np->real_dev != br_dev) - netpoll_poll_dev(np->real_dev); -} - void br_netpoll_cleanup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -295,7 +287,6 @@ static const struct net_device_ops br_netdev_ops = { .ndo_do_ioctl = br_dev_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_cleanup = br_netpoll_cleanup, - .ndo_poll_controller = br_poll_controller, #endif }; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index a4e72a89e4ff..595da45f9088 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -50,14 +50,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) kfree_skb(skb); else { skb_push(skb, ETH_HLEN); - -#ifdef CONFIG_NET_POLL_CONTROLLER - if (unlikely(skb->dev->priv_flags & IFF_IN_NETPOLL)) { - netpoll_send_skb(skb->dev->npinfo->netpoll, skb); - skb->dev->priv_flags &= ~IFF_IN_NETPOLL; - } else -#endif - dev_queue_xmit(skb); + dev_queue_xmit(skb); } } @@ -73,23 +66,9 @@ int br_forward_finish(struct sk_buff *skb) static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { -#ifdef CONFIG_NET_POLL_CONTROLLER - struct net_bridge *br = to->br; - if (unlikely(br->dev->priv_flags & IFF_IN_NETPOLL)) { - struct netpoll *np; - to->dev->npinfo = skb->dev->npinfo; - np = skb->dev->npinfo->netpoll; - np->real_dev = np->dev = to->dev; - to->dev->priv_flags |= IFF_IN_NETPOLL; - } -#endif skb->dev = to->dev; NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, br_forward_finish); -#ifdef CONFIG_NET_POLL_CONTROLLER - if (skb->dev->npinfo) - skb->dev->npinfo->netpoll->dev = br->dev; -#endif } static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) diff --git a/net/core/dev.c b/net/core/dev.c index 723a34710ad4..0ea10f849be8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1911,8 +1911,16 @@ static int dev_gso_segment(struct sk_buff *skb) */ static inline void skb_orphan_try(struct sk_buff *skb) { - if (!skb_tx(skb)->flags) + struct sock *sk = skb->sk; + + if (sk && !skb_tx(skb)->flags) { + /* skb_tx_hash() wont be able to get sk. + * We copy sk_hash into skb->rxhash + */ + if (!skb->rxhash) + skb->rxhash = sk->sk_hash; skb_orphan(skb); + } } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -1998,8 +2006,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = (__force u16) skb->protocol; - + hash = (__force u16) skb->protocol ^ skb->rxhash; hash = jhash_1word(hash, hashrnd); return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); @@ -2022,12 +2029,11 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { - u16 queue_index; + int queue_index; struct sock *sk = skb->sk; - if (sk_tx_queue_recorded(sk)) { - queue_index = sk_tx_queue_get(sk); - } else { + queue_index = sk_tx_queue_get(sk); + if (queue_index < 0) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6ba1c0eece03..a4e0a7482c2b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -949,7 +949,10 @@ static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) - = neigh->dev->header_ops->cache_update; + = NULL; + + if (neigh->dev->header_ops) + update = neigh->dev->header_ops->cache_update; if (update) { for (hh = neigh->hh; hh; hh = hh->hh_next) { diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index c51b55400dc5..11201784d29a 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -1,7 +1,7 @@ menuconfig NET_DSA bool "Distributed Switch Architecture support" default n - depends on EXPERIMENTAL && !S390 + depends on EXPERIMENTAL && NET_ETHERNET && !S390 select PHYLIB ---help--- This allows you to use hardware switch chips that use diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 757f25eb9b4b..7f6273506eea 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -442,8 +442,10 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) int err; err = ipmr_fib_lookup(net, &fl, &mrt); - if (err < 0) + if (err < 0) { + kfree_skb(skb); return err; + } read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; @@ -1728,8 +1730,10 @@ int ip_mr_input(struct sk_buff *skb) goto dont_forward; err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt); - if (err < 0) + if (err < 0) { + kfree_skb(skb); return err; + } if (!local) { if (IPCB(skb)->opt.router_alert) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6596b4feeddc..65afeaec15b7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -608,6 +608,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ssize_t spliced; int ret; + sock_rps_record_flow(sk); /* * We can't seek on a socket input */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b4ed957f201a..7ed9dc1042d1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2208,6 +2208,9 @@ void tcp_xmit_retransmit_queue(struct sock *sk) int mib_idx; int fwd_rexmitting = 0; + if (!tp->packets_out) + return; + if (!tp->lost_out) tp->retransmit_high = tp->snd_una; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 2794b6002836..d6e9599d0705 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -347,11 +347,12 @@ static const struct xfrm_type mip6_destopt_type = static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) { + struct ipv6hdr *iph = ipv6_hdr(skb); struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data; int err = rt2->rt_hdr.nexthdr; spin_lock(&x->lock); - if (!ipv6_addr_equal(&rt2->addr, (struct in6_addr *)x->coaddr) && + if (!ipv6_addr_equal(&iph->daddr, (struct in6_addr *)x->coaddr) && !ipv6_addr_any((struct in6_addr *)x->coaddr)) err = -ENOENT; spin_unlock(&x->lock); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 94d72e85a475..b2a3ae6cad78 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -698,6 +698,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) newsk = NULL; goto out; } + kfree_skb(oskb); sock_hold(sk); pep_sk(newsk)->listener = sk; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 570949417f38..724553e8ed7b 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -205,7 +205,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a, { struct icmphdr *icmph; - if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph))) + if (!pskb_may_pull(skb, ihl + sizeof(*icmph))) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); @@ -215,6 +215,9 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a, (icmph->type != ICMP_PARAMETERPROB)) break; + if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph))) + goto drop; + iph = (void *)(icmph + 1); if (egress) addr = iph->daddr; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index af1c173be4ad..a7ec5a8a2380 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1594,8 +1594,8 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); - if (err < 0) { - if (err != -EAGAIN) + if (err <= 0) { + if (err != 0 && err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } @@ -1678,6 +1678,13 @@ xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir, goto make_dummy_bundle; dst_hold(&xdst->u.dst); return oldflo; + } else if (new_xdst == NULL) { + num_xfrms = 0; + if (oldflo == NULL) + goto make_dummy_bundle; + xdst->num_xfrms = 0; + dst_hold(&xdst->u.dst); + return oldflo; } /* Kill the previous bundle */ @@ -1760,6 +1767,10 @@ restart: xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); goto dropdst; + } else if (xdst == NULL) { + num_xfrms = 0; + drop_pols = num_pols; + goto no_transform; } spin_lock_bh(&xfrm_policy_sk_bundle_lock); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 359205782964..fd7407c7205c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -107,7 +107,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, goto out_free_syms; err = 0; if (symbol_conf.use_callchain) { - err = append_chain(he->callchain, data->callchain, syms); + err = append_chain(he->callchain, data->callchain, syms, data->period); if (err) goto out_free_syms; } diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 49ece7921914..97d76562a1a0 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -5,17 +5,13 @@ if [ $# -eq 1 ] ; then fi GVF=${OUTPUT}PERF-VERSION-FILE -DEF_VER=v0.0.2.PERF LF=' ' -# First see if there is a version file (included in release tarballs), -# then try git-describe, then default. -if test -f version -then - VN=$(cat version) || VN="$DEF_VER" -elif test -d .git -o -f .git && +# First check if there is a .git to get the version from git describe +# otherwise try to get the version from the kernel makefile +if test -d ../../.git -o -f ../../.git && VN=$(git describe --abbrev=4 HEAD 2>/dev/null) && case "$VN" in *$LF*) (exit 1) ;; @@ -27,7 +23,12 @@ elif test -d .git -o -f .git && then VN=$(echo "$VN" | sed -e 's/-/./g'); else - VN="$DEF_VER" + eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '` + eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '` + eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '` + eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '` + + VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}" fi VN=$(expr "$VN" : v*'\(.*\)') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 62b69ad4aa73..52c777e451ed 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -230,7 +230,7 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) static void add_child(struct callchain_node *parent, struct resolved_chain *chain, - int start) + int start, u64 period) { struct callchain_node *new; @@ -238,7 +238,7 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain, fill_node(new, chain, start); new->children_hit = 0; - new->hit = 1; + new->hit = period; } /* @@ -248,7 +248,8 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain, */ static void split_add_child(struct callchain_node *parent, struct resolved_chain *chain, - struct callchain_list *to_split, int idx_parents, int idx_local) + struct callchain_list *to_split, int idx_parents, int idx_local, + u64 period) { struct callchain_node *new; struct list_head *old_tail; @@ -275,41 +276,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain, /* create a new child for the new branch if any */ if (idx_total < chain->nr) { parent->hit = 0; - add_child(parent, chain, idx_total); - parent->children_hit++; + add_child(parent, chain, idx_total, period); + parent->children_hit += period; } else { - parent->hit = 1; + parent->hit = period; } } static int __append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start); + unsigned int start, u64 period); static void __append_chain_children(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start) + unsigned int start, u64 period) { struct callchain_node *rnode; /* lookup in childrens */ chain_for_each_child(rnode, root) { - unsigned int ret = __append_chain(rnode, chain, start); + unsigned int ret = __append_chain(rnode, chain, start, period); if (!ret) goto inc_children_hit; } /* nothing in children, add to the current node */ - add_child(root, chain, start); + add_child(root, chain, start, period); inc_children_hit: - root->children_hit++; + root->children_hit += period; } static int __append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start) + unsigned int start, u64 period) { struct callchain_list *cnode; unsigned int i = start; @@ -345,18 +346,18 @@ __append_chain(struct callchain_node *root, struct resolved_chain *chain, /* we match only a part of the node. Split it and add the new chain */ if (i - start < root->val_nr) { - split_add_child(root, chain, cnode, start, i - start); + split_add_child(root, chain, cnode, start, i - start, period); return 0; } /* we match 100% of the path, increment the hit */ if (i - start == root->val_nr && i == chain->nr) { - root->hit++; + root->hit += period; return 0; } /* We match the node and still have a part remaining */ - __append_chain_children(root, chain, i); + __append_chain_children(root, chain, i, period); return 0; } @@ -380,7 +381,7 @@ static void filter_context(struct ip_callchain *old, struct resolved_chain *new, int append_chain(struct callchain_node *root, struct ip_callchain *chain, - struct map_symbol *syms) + struct map_symbol *syms, u64 period) { struct resolved_chain *filtered; @@ -397,7 +398,7 @@ int append_chain(struct callchain_node *root, struct ip_callchain *chain, if (!filtered->nr) goto end; - __append_chain_children(root, filtered, 0); + __append_chain_children(root, filtered, 0, period); end: free(filtered); diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 1ca73e4a2723..f2e9ee164bd8 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -49,6 +49,9 @@ static inline void callchain_init(struct callchain_node *node) INIT_LIST_HEAD(&node->brothers); INIT_LIST_HEAD(&node->children); INIT_LIST_HEAD(&node->val); + + node->parent = NULL; + node->hit = 0; } static inline u64 cumul_hits(struct callchain_node *node) @@ -58,7 +61,7 @@ static inline u64 cumul_hits(struct callchain_node *node) int register_callchain_param(struct callchain_param *param); int append_chain(struct callchain_node *root, struct ip_callchain *chain, - struct map_symbol *syms); + struct map_symbol *syms, u64 period); bool ip_callchain__valid(struct ip_callchain *chain, event_t *event); #endif /* __PERF_CALLCHAIN_H */ |