diff options
124 files changed, 1481 insertions, 1129 deletions
diff --git a/Documentation/fujitsu/frv/kernel-ABI.txt b/Documentation/fujitsu/frv/kernel-ABI.txt new file mode 100644 index 00000000000..0ed9b0a779b --- /dev/null +++ b/Documentation/fujitsu/frv/kernel-ABI.txt @@ -0,0 +1,234 @@ + ================================= + INTERNAL KERNEL ABI FOR FR-V ARCH + ================================= + +The internal FRV kernel ABI is not quite the same as the userspace ABI. A number of the registers +are used for special purposed, and the ABI is not consistent between modules vs core, and MMU vs +no-MMU. + +This partly stems from the fact that FRV CPUs do not have a separate supervisor stack pointer, and +most of them do not have any scratch registers, thus requiring at least one general purpose +register to be clobbered in such an event. Also, within the kernel core, it is possible to simply +jump or call directly between functions using a relative offset. This cannot be extended to modules +for the displacement is likely to be too far. Thus in modules the address of a function to call +must be calculated in a register and then used, requiring two extra instructions. + +This document has the following sections: + + (*) System call register ABI + (*) CPU operating modes + (*) Internal kernel-mode register ABI + (*) Internal debug-mode register ABI + (*) Virtual interrupt handling + + +======================== +SYSTEM CALL REGISTER ABI +======================== + +When a system call is made, the following registers are effective: + + REGISTERS CALL RETURN + =============== ======================= ======================= + GR7 System call number Preserved + GR8 Syscall arg #1 Return value + GR9-GR13 Syscall arg #2-6 Preserved + + +=================== +CPU OPERATING MODES +=================== + +The FR-V CPU has three basic operating modes. In order of increasing capability: + + (1) User mode. + + Basic userspace running mode. + + (2) Kernel mode. + + Normal kernel mode. There are many additional control registers available that may be + accessed in this mode, in addition to all the stuff available to user mode. This has two + submodes: + + (a) Exceptions enabled (PSR.T == 1). + + Exceptions will invoke the appropriate normal kernel mode handler. On entry to the + handler, the PSR.T bit will be cleared. + + (b) Exceptions disabled (PSR.T == 0). + + No exceptions or interrupts may happen. Any mandatory exceptions will cause the CPU to + halt unless the CPU is told to jump into debug mode instead. + + (3) Debug mode. + + No exceptions may happen in this mode. Memory protection and management exceptions will be + flagged for later consideration, but the exception handler won't be invoked. Debugging traps + such as hardware breakpoints and watchpoints will be ignored. This mode is entered only by + debugging events obtained from the other two modes. + + All kernel mode registers may be accessed, plus a few extra debugging specific registers. + + +================================= +INTERNAL KERNEL-MODE REGISTER ABI +================================= + +There are a number of permanent register assignments that are set up by entry.S in the exception +prologue. Note that there is a complete set of exception prologues for each of user->kernel +transition and kernel->kernel transition. There are also user->debug and kernel->debug mode +transition prologues. + + + REGISTER FLAVOUR USE + =============== ======= ==================================================== + GR1 Supervisor stack pointer + GR15 Current thread info pointer + GR16 GP-Rel base register for small data + GR28 Current exception frame pointer (__frame) + GR29 Current task pointer (current) + GR30 Destroyed by kernel mode entry + GR31 NOMMU Destroyed by debug mode entry + GR31 MMU Destroyed by TLB miss kernel mode entry + CCR.ICC2 Virtual interrupt disablement tracking + CCCR.CC3 Cleared by exception prologue (atomic op emulation) + SCR0 MMU See mmu-layout.txt. + SCR1 MMU See mmu-layout.txt. + SCR2 MMU Save for EAR0 (destroyed by icache insns in debug mode) + SCR3 MMU Save for GR31 during debug exceptions + DAMR/IAMR NOMMU Fixed memory protection layout. + DAMR/IAMR MMU See mmu-layout.txt. + + +Certain registers are also used or modified across function calls: + + REGISTER CALL RETURN + =============== =============================== =============================== + GR0 Fixed Zero - + GR2 Function call frame pointer + GR3 Special Preserved + GR3-GR7 - Clobbered + GR8 Function call arg #1 Return value (or clobbered) + GR9 Function call arg #2 Return value MSW (or clobbered) + GR10-GR13 Function call arg #3-#6 Clobbered + GR14 - Clobbered + GR15-GR16 Special Preserved + GR17-GR27 - Preserved + GR28-GR31 Special Only accessed explicitly + LR Return address after CALL Clobbered + CCR/CCCR - Mostly Clobbered + + +================================ +INTERNAL DEBUG-MODE REGISTER ABI +================================ + +This is the same as the kernel-mode register ABI for functions calls. The difference is that in +debug-mode there's a different stack and a different exception frame. Almost all the global +registers from kernel-mode (including the stack pointer) may be changed. + + REGISTER FLAVOUR USE + =============== ======= ==================================================== + GR1 Debug stack pointer + GR16 GP-Rel base register for small data + GR31 Current debug exception frame pointer (__debug_frame) + SCR3 MMU Saved value of GR31 + + +Note that debug mode is able to interfere with the kernel's emulated atomic ops, so it must be +exceedingly careful not to do any that would interact with the main kernel in this regard. Hence +the debug mode code (gdbstub) is almost completely self-contained. The only external code used is +the sprintf family of functions. + +Futhermore, break.S is so complicated because single-step mode does not switch off on entry to an +exception. That means unless manually disabled, single-stepping will blithely go on stepping into +things like interrupts. See gdbstub.txt for more information. + + +========================== +VIRTUAL INTERRUPT HANDLING +========================== + +Because accesses to the PSR is so slow, and to disable interrupts we have to access it twice (once +to read and once to write), we don't actually disable interrupts at all if we don't have to. What +we do instead is use the ICC2 condition code flags to note virtual disablement, such that if we +then do take an interrupt, we note the flag, really disable interrupts, set another flag and resume +execution at the point the interrupt happened. Setting condition flags as a side effect of an +arithmetic or logical instruction is really fast. This use of the ICC2 only occurs within the +kernel - it does not affect userspace. + +The flags we use are: + + (*) CCR.ICC2.Z [Zero flag] + + Set to virtually disable interrupts, clear when interrupts are virtually enabled. Can be + modified by logical instructions without affecting the Carry flag. + + (*) CCR.ICC2.C [Carry flag] + + Clear to indicate hardware interrupts are really disabled, set otherwise. + + +What happens is this: + + (1) Normal kernel-mode operation. + + ICC2.Z is 0, ICC2.C is 1. + + (2) An interrupt occurs. The exception prologue examines ICC2.Z and determines that nothing needs + doing. This is done simply with an unlikely BEQ instruction. + + (3) The interrupts are disabled (local_irq_disable) + + ICC2.Z is set to 1. + + (4) If interrupts were then re-enabled (local_irq_enable): + + ICC2.Z would be set to 0. + + A TIHI #2 instruction (trap #2 if condition HI - Z==0 && C==0) would be used to trap if + interrupts were now virtually enabled, but physically disabled - which they're not, so the + trap isn't taken. The kernel would then be back to state (1). + + (5) An interrupt occurs. The exception prologue examines ICC2.Z and determines that the interrupt + shouldn't actually have happened. It jumps aside, and there disabled interrupts by setting + PSR.PIL to 14 and then it clears ICC2.C. + + (6) If interrupts were then saved and disabled again (local_irq_save): + + ICC2.Z would be shifted into the save variable and masked off (giving a 1). + + ICC2.Z would then be set to 1 (thus unchanged), and ICC2.C would be unaffected (ie: 0). + + (7) If interrupts were then restored from state (6) (local_irq_restore): + + ICC2.Z would be set to indicate the result of XOR'ing the saved value (ie: 1) with 1, which + gives a result of 0 - thus leaving ICC2.Z set. + + ICC2.C would remain unaffected (ie: 0). + + A TIHI #2 instruction would be used to again assay the current state, but this would do + nothing as Z==1. + + (8) If interrupts were then enabled (local_irq_enable): + + ICC2.Z would be cleared. ICC2.C would be left unaffected. Both flags would now be 0. + + A TIHI #2 instruction again issued to assay the current state would then trap as both Z==0 + [interrupts virtually enabled] and C==0 [interrupts really disabled] would then be true. + + (9) The trap #2 handler would simply enable hardware interrupts (set PSR.PIL to 0), set ICC2.C to + 1 and return. + +(10) Immediately upon returning, the pending interrupt would be taken. + +(11) The interrupt handler would take the path of actually processing the interrupt (ICC2.Z is + clear, BEQ fails as per step (2)). + +(12) The interrupt handler would then set ICC2.C to 1 since hardware interrupts are definitely + enabled - or else the kernel wouldn't be here. + +(13) On return from the interrupt handler, things would be back to state (1). + +This trap (#2) is only available in kernel mode. In user mode it will result in SIGILL. diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 0ea5a0c6e82..2c3b1eae428 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -136,17 +136,20 @@ Kprobes, jprobes, and return probes are implemented on the following architectures: - i386 -- x86_64 (AMD-64, E64MT) +- x86_64 (AMD-64, EM64T) - ppc64 -- ia64 (Support for probes on certain instruction types is still in progress.) +- ia64 (Does not support probes on instruction slot1.) - sparc64 (Return probes not yet implemented.) 3. Configuring Kprobes When configuring the kernel using make menuconfig/xconfig/oldconfig, -ensure that CONFIG_KPROBES is set to "y". Under "Kernel hacking", -look for "Kprobes". You may have to enable "Kernel debugging" -(CONFIG_DEBUG_KERNEL) before you can enable Kprobes. +ensure that CONFIG_KPROBES is set to "y". Under "Instrumentation +Support", look for "Kprobes". + +So that you can load and unload Kprobes-based instrumentation modules, +make sure "Loadable module support" (CONFIG_MODULES) and "Module +unloading" (CONFIG_MODULE_UNLOAD) are set to "y". You may also want to ensure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL are set to "y", since kallsyms_lookup_name() @@ -262,18 +265,18 @@ at any time after the probe has been registered. 5. Kprobes Features and Limitations -As of Linux v2.6.12, Kprobes allows multiple probes at the same -address. Currently, however, there cannot be multiple jprobes on -the same function at the same time. +Kprobes allows multiple probes at the same address. Currently, +however, there cannot be multiple jprobes on the same function at +the same time. In general, you can install a probe anywhere in the kernel. In particular, you can probe interrupt handlers. Known exceptions are discussed in this section. -For obvious reasons, it's a bad idea to install a probe in -the code that implements Kprobes (mostly kernel/kprobes.c and -arch/*/kernel/kprobes.c). A patch in the v2.6.13 timeframe instructs -Kprobes to reject such requests. +The register_*probe functions will return -EINVAL if you attempt +to install a probe in the code that implements Kprobes (mostly +kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such +as do_page_fault and notifier_call_chain). If you install a probe in an inline-able function, Kprobes makes no attempt to chase down all inline instances of the function and @@ -290,18 +293,14 @@ from the accidental ones. Don't drink and probe. Kprobes makes no attempt to prevent probe handlers from stepping on each other -- e.g., probing printk() and then calling printk() from a -probe handler. As of Linux v2.6.12, if a probe handler hits a probe, -that second probe's handlers won't be run in that instance. - -In Linux v2.6.12 and previous versions, Kprobes' data structures are -protected by a single lock that is held during probe registration and -unregistration and while handlers are run. Thus, no two handlers -can run simultaneously. To improve scalability on SMP systems, -this restriction will probably be removed soon, in which case -multiple handlers (or multiple instances of the same handler) may -run concurrently on different CPUs. Code your handlers accordingly. - -Kprobes does not use semaphores or allocate memory except during +probe handler. If a probe handler hits a probe, that second probe's +handlers won't be run in that instance, and the kprobe.nmissed member +of the second probe will be incremented. + +As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of +the same handler) may run concurrently on different CPUs. + +Kprobes does not use mutexes or allocate memory except during registration and unregistration. Probe handlers are run with preemption disabled. Depending on the @@ -316,11 +315,18 @@ address instead of the real return address for kretprobed functions. (As far as we can tell, __builtin_return_address() is used only for instrumentation and error reporting.) -If the number of times a function is called does not match the -number of times it returns, registering a return probe on that -function may produce undesirable results. We have the do_exit() -and do_execve() cases covered. do_fork() is not an issue. We're -unaware of other specific cases where this could be a problem. +If the number of times a function is called does not match the number +of times it returns, registering a return probe on that function may +produce undesirable results. We have the do_exit() case covered. +do_execve() and do_fork() are not an issue. We're unaware of other +specific cases where this could be a problem. + +If, upon entry to or exit from a function, the CPU is running on +a stack other than that of the current task, registering a return +probe on that function may produce undesirable results. For this +reason, Kprobes doesn't support return probes (or kprobes or jprobes) +on the x86_64 version of __switch_to(); the registration functions +return -EINVAL. 6. Probe Overhead @@ -347,14 +353,12 @@ k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99 7. TODO -a. SystemTap (http://sourceware.org/systemtap): Work in progress -to provide a simplified programming interface for probe-based -instrumentation. -b. Improved SMP scalability: Currently, work is in progress to handle -multiple kprobes in parallel. -c. Kernel return probes for sparc64. -d. Support for other architectures. -e. User-space probes. +a. SystemTap (http://sourceware.org/systemtap): Provides a simplified +programming interface for probe-based instrumentation. Try it out. +b. Kernel return probes for sparc64. +c. Support for other architectures. +d. User-space probes. +e. Watchpoint probes (which fire on data references). 8. Kprobes Example @@ -411,8 +415,7 @@ int init_module(void) printk("Couldn't find %s to plant kprobe\n", "do_fork"); return -1; } - ret = register_kprobe(&kp); - if (ret < 0) { + if ((ret = register_kprobe(&kp) < 0)) { printk("register_kprobe failed, returned %d\n", ret); return -1; } diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README index a7e4c4ea356..afb31c141d9 100644 --- a/Documentation/mips/AU1xxx_IDE.README +++ b/Documentation/mips/AU1xxx_IDE.README @@ -95,11 +95,13 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y CONFIG_IDEDMA_PCI_AUTO=y CONFIG_BLK_DEV_IDE_AU1XXX=y CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y -CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON=y CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128 CONFIG_BLK_DEV_IDEDMA=y CONFIG_IDEDMA_AUTO=y +Also define 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to enable +the burst support on DBDMA controller. + If the used system need the USB support enable the following kernel configs for high IDE to USB throughput. @@ -115,6 +117,8 @@ CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128 CONFIG_BLK_DEV_IDEDMA=y CONFIG_IDEDMA_AUTO=y +Also undefine 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to +disable the burst support on DBDMA controller. ADD NEW HARD DISC TO WHITE OR BLACK LIST ---------------------------------------- diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index 60a617aff8b..e0838371237 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -25,6 +25,10 @@ config GENERIC_HARDIRQS bool default n +config TIME_LOW_RES + bool + default y + mainmenu "Fujitsu FR-V Kernel Configuration" source "init/Kconfig" diff --git a/arch/frv/Makefile b/arch/frv/Makefile index 90c0fb8d9dc..d163747d17c 100644 --- a/arch/frv/Makefile +++ b/arch/frv/Makefile @@ -81,7 +81,7 @@ endif # - reserve CC3 for use with atomic ops # - all the extra registers are dealt with only at context switch time CFLAGS += -mno-fdpic -mgpr-32 -msoft-float -mno-media -CFLAGS += -ffixed-fcc3 -ffixed-cc3 -ffixed-gr15 +CFLAGS += -ffixed-fcc3 -ffixed-cc3 -ffixed-gr15 -ffixed-icc2 AFLAGS += -mno-fdpic ASFLAGS += -mno-fdpic diff --git a/arch/frv/kernel/break.S b/arch/frv/kernel/break.S index 33233dc23e2..687c48d62dd 100644 --- a/arch/frv/kernel/break.S +++ b/arch/frv/kernel/break.S @@ -200,12 +200,20 @@ __break_step: movsg bpcsr,gr2 sethi.p %hi(__entry_kernel_external_interrupt),gr3 setlo %lo(__entry_kernel_external_interrupt),gr3 - subcc gr2,gr3,gr0,icc0 + subcc.p gr2,gr3,gr0,icc0 + sethi %hi(__entry_uspace_external_interrupt),gr3 + setlo.p %lo(__entry_uspace_external_interrupt),gr3 beq icc0,#2,__break_step_kernel_external_interrupt - sethi.p %hi(__entry_uspace_external_interrupt),gr3 - setlo %lo(__entry_uspace_external_interrupt),gr3 - subcc gr2,gr3,gr0,icc0 + subcc.p gr2,gr3,gr0,icc0 + sethi %hi(__entry_kernel_external_interrupt_virtually_disabled),gr3 + setlo.p %lo(__entry_kernel_external_interrupt_virtually_disabled),gr3 beq icc0,#2,__break_step_uspace_external_interrupt + subcc.p gr2,gr3,gr0,icc0 + sethi %hi(__entry_kernel_external_interrupt_virtual_reenable),gr3 + setlo.p %lo(__entry_kernel_external_interrupt_virtual_reenable),gr3 + beq icc0,#2,__break_step_kernel_external_interrupt_virtually_disabled + subcc gr2,gr3,gr0,icc0 + beq icc0,#2,__break_step_kernel_external_interrupt_virtual_reenable LEDS 0x2007,gr2 @@ -254,6 +262,9 @@ __break_step_kernel_softprog_interrupt: # step through an external interrupt from kernel mode .globl __break_step_kernel_external_interrupt __break_step_kernel_external_interrupt: + # deal with virtual interrupt disablement + beq icc2,#0,__break_step_kernel_external_interrupt_virtually_disabled + sethi.p %hi(__entry_kernel_external_interrupt_reentry),gr3 setlo %lo(__entry_kernel_external_interrupt_reentry),gr3 @@ -294,6 +305,64 @@ __break_return_as_kernel_prologue: #endif rett #1 +# we single-stepped into an interrupt handler whilst interrupts were merely virtually disabled +# need to really disable interrupts, set flag, fix up and return +__break_step_kernel_external_interrupt_virtually_disabled: + movsg psr,gr2 + andi gr2,#~PSR_PIL,gr2 + ori gr2,#PSR_PIL_14,gr2 /* debugging interrupts only */ + movgs gr2,psr + + ldi @(gr31,#REG_CCR),gr3 + movgs gr3,ccr + subcc.p gr0,gr0,gr0,icc2 /* leave Z set, clear C */ + + # exceptions must've been enabled and we must've been in supervisor mode + setlos BPSR_BET|BPSR_BS,gr3 + movgs gr3,bpsr + + # return to where the interrupt happened + movsg pcsr,gr2 + movgs gr2,bpcsr + + lddi.p @(gr31,#REG_GR(2)),gr2 + + xor gr31,gr31,gr31 + movgs gr0,brr +#ifdef CONFIG_MMU + movsg scr3,gr31 +#endif + rett #1 + +# we stepped through into the virtual interrupt reenablement trap +# +# we also want to single step anyway, but after fixing up so that we get an event on the +# instruction after the broken-into exception returns + .globl __break_step_kernel_external_interrupt_virtual_reenable +__break_step_kernel_external_interrupt_virtual_reenable: + movsg psr,gr2 + andi gr2,#~PSR_PIL,gr2 + movgs gr2,psr + + ldi @(gr31,#REG_CCR),gr3 + movgs gr3,ccr + subicc gr0,#1,gr0,icc2 /* clear Z, set C */ + + # save the adjusted ICC2 + movsg ccr,gr3 + sti gr3,@(gr31,#REG_CCR) + + # exceptions must've been enabled and we must've been in supervisor mode + setlos BPSR_BET|BPSR_BS,gr3 + movgs gr3,bpsr + + # return to where the trap happened + movsg pcsr,gr2 + movgs gr2,bpcsr + + # and then process the single step + bra __break_continue + # step through an internal exception from uspace mode .globl __break_step_uspace_softprog_interrupt __break_step_uspace_softprog_interrupt: diff --git a/arch/frv/kernel/entry-table.S b/arch/frv/kernel/entry-table.S index 9b9243e2103..81568acea9c 100644 --- a/arch/frv/kernel/entry-table.S +++ b/arch/frv/kernel/entry-table.S @@ -116,6 +116,8 @@ __break_kerneltrap_fixup_table: .long __break_step_uspace_external_interrupt .section .trap.kernel .org \tbr_tt + # deal with virtual interrupt disablement + beq icc2,#0,__entry_kernel_external_interrupt_virtually_disabled bra __entry_kernel_external_interrupt .section .trap.fixup.kernel .org \tbr_tt >> 2 @@ -259,25 +261,52 @@ __trap_fixup_kernel_data_tlb_miss: .org TBR_TT_TRAP0 .rept 127 bra __entry_uspace_softprog_interrupt - bra __break_step_uspace_softprog_interrupt - .long 0,0 + .long 0,0,0 .endr .org TBR_TT_BREAK bra __entry_break .long 0,0,0 + .section .trap.fixup.user + .org TBR_TT_TRAP0 >> 2 + .rept 127 + .long __break_step_uspace_softprog_interrupt + .endr + .org TBR_TT_BREAK >> 2 + .long 0 + # miscellaneous kernel mode entry points .section .trap.kernel .org TBR_TT_TRAP0 - .rept 127 bra __entry_kernel_softprog_interrupt - bra __break_step_kernel_softprog_interrupt - .long 0,0 + .org TBR_TT_TRAP1 + bra __entry_kernel_softprog_interrupt + + # trap #2 in kernel - reenable interrupts + .org TBR_TT_TRAP2 + bra __entry_kernel_external_interrupt_virtual_reenable + + # miscellaneous kernel traps + .org TBR_TT_TRAP3 + .rept 124 + bra __entry_kernel_softprog_interrupt + .long 0,0,0 .endr .org TBR_TT_BREAK bra __entry_break .long 0,0,0 + .section .trap.fixup.kernel + .org TBR_TT_TRAP0 >> 2 + .long __break_step_kernel_softprog_interrupt + .long __break_step_kernel_softprog_interrupt + .long __break_step_kernel_external_interrupt_virtual_reenable + .rept 124 + .long __break_step_kernel_softprog_interrupt + .endr + .org TBR_TT_BREAK >> 2 + .long 0 + # miscellaneous debug mode entry points .section .trap.break .org TBR_TT_BREAK diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 5f6548388b7..1d21c8d34d8 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -141,7 +141,10 @@ __entry_uspace_external_interrupt_reentry: movsg gner0,gr4 movsg gner1,gr5 - stdi gr4,@(gr28,#REG_GNER0) + stdi.p gr4,@(gr28,#REG_GNER0) + + # interrupts start off fully disabled in the interrupt handler + subcc gr0,gr0,gr0,icc2 /* set Z and clear C */ # set up kernel global registers sethi.p %hi(__kernel_current_task),gr5 @@ -193,9 +196,8 @@ __entry_uspace_external_interrupt_reentry: .type __entry_kernel_external_interrupt,@function __entry_kernel_external_interrupt: LEDS 0x6210 - - sub sp,gr15,gr31 - LEDS32 +// sub sp,gr15,gr31 +// LEDS32 # set up the stack pointer or.p sp,gr0,gr30 @@ -231,7 +233,10 @@ __entry_kernel_external_interrupt_reentry: stdi gr24,@(gr28,#REG_GR(24)) stdi gr26,@(gr28,#REG_GR(26)) sti gr29,@(gr28,#REG_GR(29)) - stdi gr30,@(gr28,#REG_GR(30)) + stdi.p gr30,@(gr28,#REG_GR(30)) + + # note virtual interrupts will be fully enabled upon return + subicc gr0,#1,gr0,icc2 /* clear Z, set C */ movsg tbr ,gr20 movsg psr ,gr22 @@ -267,7 +272,10 @@ __entry_kernel_external_interrupt_reentry: movsg gner0,gr4 movsg gner1,gr5 - stdi gr4,@(gr28,#REG_GNER0) + stdi.p gr4,@(gr28,#REG_GNER0) + + # interrupts start off fully disabled in the interrupt handler + subcc gr0,gr0,gr0,icc2 /* set Z and clear C */ # set the return address sethi.p %hi(__entry_return_from_kernel_interrupt),gr4 @@ -291,6 +299,45 @@ __entry_kernel_external_interrupt_reentry: .size __entry_kernel_external_interrupt,.-__entry_kernel_external_interrupt +############################################################################### +# +# deal with interrupts that were actually virtually disabled +# - we need to really disable them, flag the fact and return immediately +# - if you change this, you must alter break.S also +# +############################################################################### + .balign L1_CACHE_BYTES + .globl __entry_kernel_external_interrupt_virtually_disabled + .type __entry_kernel_external_interrupt_virtually_disabled,@function +__entry_kernel_external_interrupt_virtually_disabled: + movsg psr,gr30 + andi gr30,#~PSR_PIL,gr30 + ori gr30,#PSR_PIL_14,gr30 ; debugging interrupts only + movgs gr30,psr + subcc gr0,gr0,gr0,icc2 ; leave Z set, clear C + rett #0 + + .size __entry_kernel_external_interrupt_virtually_disabled,.-__entry_kernel_external_interrupt_virtually_disabled + +############################################################################### +# +# deal with re-enablement of interrupts that were pending when virtually re-enabled +# - set ICC2.C, re-enable the real interrupts and return +# - we can clear ICC2.Z because we shouldn't be here if it's not 0 [due to TIHI] +# - if you change this, you must alter break.S also +# +############################################################################### + .balign L1_CACHE_BYTES + .globl __entry_kernel_external_interrupt_virtual_reenable + .type __entry_kernel_external_interrupt_virtual_reenable,@function +__entry_kernel_external_interrupt_virtual_reenable: + movsg psr,gr30 + andi gr30,#~PSR_PIL,gr30 ; re-enable interrupts + movgs gr30,psr + subicc gr0,#1,gr0,icc2 ; clear Z, set C + rett #0 + + .size __entry_kernel_external_interrupt_virtual_reenable,.-__entry_kernel_external_interrupt_virtual_reenable ############################################################################### # @@ -335,6 +382,7 @@ __entry_uspace_softprog_interrupt_reentry: sethi.p %hi(__entry_return_from_user_exception),gr23 setlo %lo(__entry_return_from_user_exception),gr23 + bra __entry_common .size __entry_uspace_softprog_interrupt,.-__entry_uspace_softprog_interrupt @@ -495,7 +543,10 @@ __entry_common: movsg gner0,gr4 movsg gner1,gr5 - stdi gr4,@(gr28,#REG_GNER0) + stdi.p gr4,@(gr28,#REG_GNER0) + + # set up virtual interrupt disablement + subicc gr0,#1,gr0,icc2 /* clear Z flag, set C flag */ # set up kernel global registers sethi.p %hi(__kernel_current_task),gr5 @@ -1418,11 +1469,27 @@ sys_call_table: .long sys_add_key .long sys_request_key .long sys_keyctl - .long sys_ni_syscall // sys_vperfctr_open - .long sys_ni_syscall // sys_vperfctr_control /* 290 */ - .long sys_ni_syscall // sys_vperfctr_unlink - .long sys_ni_syscall // sys_vperfctr_iresume - .long sys_ni_syscall // sys_vperfctr_read + .long sys_ioprio_set + .long sys_ioprio_get /* 290 */ + .long sys_inotify_init + .long sys_inotify_add_watch + .long sys_inotify_rm_watch + .long sys_migrate_pages + .long sys_openat /* 295 */ + .long sys_mkdirat + .long sys_mknodat + .long sys_fchownat + .long sys_futimesat + .long sys_newfstatat /* 300 */ + .long sys_unlinkat + .long sys_renameat + .long sys_linkat + .long sys_symlinkat + .long sys_readlinkat /* 305 */ + .long sys_fchmodat + .long sys_faccessat + .long sys_pselect6 + .long sys_ppoll syscall_table_size = (. - sys_call_table) diff --git a/arch/frv/kernel/head.S b/arch/frv/kernel/head.S index c73b4fe9f6c..29a5265489b 100644 --- a/arch/frv/kernel/head.S +++ b/arch/frv/kernel/head.S @@ -513,6 +513,9 @@ __head_mmu_enabled: movgs gr0,ccr movgs gr0,cccr + # initialise the virtual interrupt handling + subcc gr0,gr0,gr0,icc2 /* set Z, clear C */ + #ifdef CONFIG_MMU movgs gr3,scr2 movgs gr3,scr3 diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c index 59580c59c62..27ab4c30aac 100644 --- a/arch/frv/kernel/irq.c +++ b/arch/frv/kernel/irq.c @@ -287,18 +287,11 @@ asmlinkage void do_IRQ(void) struct irq_source *source; int level, cpu; + irq_enter(); + level = (__frame->tbr >> 4) & 0xf; cpu = smp_processor_id(); -#if 0 - { - static u32 irqcount; - *(volatile u32 *) 0xe1200004 = ~((irqcount++ << 8) | level); - *(volatile u16 *) 0xffc00100 = (u16) ~0x9999; - mb(); - } -#endif - if ((unsigned long) __frame - (unsigned long) (current + 1) < 512) BUG(); @@ -308,40 +301,12 @@ asmlinkage void do_IRQ(void) kstat_this_cpu.irqs[level]++; - irq_enter(); - for (source = frv_irq_levels[level].sources; source; source = source->next) source->doirq(source); - irq_exit(); - __clr_MASK(level); - /* only process softirqs if we didn't interrupt another interrupt handler */ - if ((__frame->psr & PSR_PIL) == PSR_PIL_0) - if (local_softirq_pending()) - do_softirq(); - -#ifdef CONFIG_PREEMPT - local_irq_disable(); - while (--current->preempt_count == 0) { - if (!(__frame->psr & PSR_S) || - current->need_resched == 0 || - in_interrupt()) - break; - current->preempt_count++; - local_irq_enable(); - preempt_schedule(); - local_irq_disable(); - } -#endif - -#if 0 - { - *(volatile u16 *) 0xffc00100 = (u16) ~0x6666; - mb(); - } -#endif + irq_exit(); } /* end do_IRQ() */ diff --git a/arch/frv/mm/kmap.c b/arch/frv/mm/kmap.c index 539f45e6d15..c54f18e65ea 100644 --- a/arch/frv/mm/kmap.c +++ b/arch/frv/mm/kmap.c @@ -44,15 +44,6 @@ void iounmap(void *addr) } /* - * __iounmap unmaps nearly everything, so be careful - * it doesn't free currently pointer/page tables anymore but it - * wans't used anyway and might be added later. - */ -void __iounmap(void *addr, unsigned long size) -{ -} - -/* * Set new cache mode for some kernel address space. * The caller must push data for that range itself, if such data may already * be in the cache. diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 80940d712ac..98308b018a3 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -33,6 +33,10 @@ config GENERIC_CALIBRATE_DELAY bool default y +config TIME_LOW_RES + bool + default y + config ISA bool default y diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu index a380167a13c..582797db960 100644 --- a/arch/h8300/Kconfig.cpu +++ b/arch/h8300/Kconfig.cpu @@ -169,7 +169,7 @@ endif config CPU_H8300H bool - depends on (H8002 || H83007 || H83048 || H83068) + depends on (H83002 || H83007 || H83048 || H83068) default y config CPU_H8S diff --git a/arch/i386/boot/.gitignore b/arch/i386/boot/.gitignore new file mode 100644 index 00000000000..495f20c085d --- /dev/null +++ b/arch/i386/boot/.gitignore @@ -0,0 +1,3 @@ +bootsect +bzImage +setup diff --git a/arch/i386/boot/tools/.gitignore b/arch/i386/boot/tools/.gitignore new file mode 100644 index 00000000000..378eac25d31 --- /dev/null +++ b/arch/i386/boot/tools/.gitignore @@ -0,0 +1 @@ +build diff --git a/arch/i386/kernel/.gitignore b/arch/i386/kernel/.gitignore new file mode 100644 index 00000000000..40836ad9079 --- /dev/null +++ b/arch/i386/kernel/.gitignore @@ -0,0 +1 @@ +vsyscall.lds diff --git a/arch/i386/kernel/vsyscall-sysenter.S b/arch/i386/kernel/vsyscall-sysenter.S index 4daefb2ec1b..76b72815940 100644 --- a/arch/i386/kernel/vsyscall-sysenter.S +++ b/arch/i386/kernel/vsyscall-sysenter.S @@ -7,6 +7,21 @@ * for details. */ +/* + * The caller puts arg2 in %ecx, which gets pushed. The kernel will use + * %ecx itself for arg2. The pushing is because the sysexit instruction + * (found in entry.S) requires that we clobber %ecx with the desired %esp. + * User code might expect that %ecx is unclobbered though, as it would be + * for returning via the iret instruction, so we must push and pop. + * + * The caller puts arg3 in %edx, which the sysexit instruction requires + * for %eip. Thus, exactly as for arg2, we must push and pop. + * + * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter + * instruction clobbers %esp, the user's %esp won't even survive entry + * into the kernel. We store %esp in %ebp. Code in entry.S must fetch + * arg6 from the stack. + */ .text .globl __kernel_vsyscall .type __kernel_vsyscall,@function diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index e72de580ebb..bbcfd08378a 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -10,23 +10,8 @@ #include <linux/string.h> EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(memchr); -EXPORT_SYMBOL(memcmp); EXPORT_SYMBOL(memcpy); -EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(memscan); -EXPORT_SYMBOL(strcat); -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strcmp); -EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strncat); -EXPORT_SYMBOL(strncmp); -EXPORT_SYMBOL(strncpy); -EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strrchr); -EXPORT_SYMBOL(strstr); -EXPORT_SYMBOL(strpbrk); #include <asm/checksum.h> EXPORT_SYMBOL(ip_fast_csum); /* hand-coded assembly */ diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index a094ec49ccf..307d01e15b2 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -250,32 +250,27 @@ time_init (void) set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); } -#define SMALLUSECS 100 - -void -udelay (unsigned long usecs) +/* + * Generic udelay assumes that if preemption is allowed and the thread + * migrates to another CPU, that the ITC values are synchronized across + * all CPUs. + */ +static void +ia64_itc_udelay (unsigned long usecs) { - unsigned long start; - unsigned long cycles; - unsigned long smallusecs; + unsigned long start = ia64_get_itc(); + unsigned long end = start + usecs*local_cpu_data->cyc_per_usec; - /* - * Execute the non-preemptible delay loop (because the ITC might - * not be synchronized between CPUS) in relatively short time - * chunks, allowing preemption between the chunks. - */ - while (usecs > 0) { - smallusecs = (usecs > SMALLUSECS) ? SMALLUSECS : usecs; - preempt_disable(); - cycles = smallusecs*local_cpu_data->cyc_per_usec; - start = ia64_get_itc(); + while (time_before(ia64_get_itc(), end)) + cpu_relax(); +} - while (ia64_get_itc() - start < cycles) - cpu_relax(); +void (*ia64_udelay)(unsigned long usecs) = &ia64_itc_udelay; - preempt_enable(); - usecs -= smallusecs; - } +void +udelay (unsigned long usecs) +{ + (*ia64_udelay)(usecs); } EXPORT_SYMBOL(udelay); diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index 55391901b01..dabd6c32641 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -16,6 +16,7 @@ #include <linux/module.h> /* for EXPORT_SYMBOL */ #include <linux/hardirq.h> #include <linux/kprobes.h> +#include <linux/delay.h> /* for ssleep() */ #include <asm/fpswa.h> #include <asm/ia32.h> @@ -116,6 +117,13 @@ die (const char *str, struct pt_regs *regs, long err) bust_spinlocks(0); die.lock_owner = -1; spin_unlock_irq(&die.lock); + + if (panic_on_oops) { + printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); + ssleep(5); + panic("Fatal exception"); + } + do_exit(SIGSEGV); } diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 3437c239042..3edef0d32f8 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -23,6 +23,10 @@ #include "xtalk/hubdev.h" #include "xtalk/xwidgetdev.h" + +extern void sn_init_cpei_timer(void); +extern void register_sn_procfs(void); + static struct list_head sn_sysdata_list; /* sysdata list struct */ @@ -40,12 +44,12 @@ struct brick { struct slab_info slab_info[MAX_SLABS + 1]; }; -int sn_ioif_inited = 0; /* SN I/O infrastructure initialized? */ +int sn_ioif_inited; /* SN I/O infrastructure initialized? */ struct sn_pcibus_provider *sn_pci_provider[PCIIO_ASIC_MAX_TYPES]; /* indexed by asic type */ -static int max_segment_number = 0; /* Default highest segment number */ -static int max_pcibus_number = 255; /* Default highest pci bus number */ +static int max_segment_number; /* Default highest segment number */ +static int max_pcibus_number = 255; /* Default highest pci bus number */ /* * Hooks and struct for unsupported pci providers @@ -84,7 +88,6 @@ static inline u64 sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num, u64 address) { - struct ia64_sal_retval ret_stuff; ret_stuff.status = 0; ret_stuff.v0 = 0; @@ -94,7 +97,6 @@ sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num, (u64) nasid, (u64) widget_num, (u64) device_num, (u64) address, 0, 0, 0); return ret_stuff.status; - } /* @@ -102,7 +104,6 @@ sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num, */ static inline u64 sal_get_hubdev_info(u64 handle, u64 address) { - struct ia64_sal_retval ret_stuff; ret_stuff.status = 0; ret_stuff.v0 = 0; @@ -118,7 +119,6 @@ static inline u64 sal_get_hubdev_info(u64 handle, u64 address) */ static inline u64 sal_get_pcibus_info(u64 segment, u64 busnum, u64 address) { - struct ia64_sal_retval ret_stuff; ret_stuff.status = 0; ret_stuff.v0 = 0; @@ -215,7 +215,7 @@ static void __init sn_fixup_ionodes(void) struct hubdev_info *hubdev; u64 status; u64 nasid; - int i, widget, device; + int i, widget, device, size; /* * Get SGI Specific HUB chipset information. @@ -251,48 +251,37 @@ static void __init sn_fixup_ionodes(void) if (!hubdev->hdi_flush_nasid_list.widget_p) continue; + size = (HUB_WIDGET_ID_MAX + 1) * + sizeof(struct sn_flush_device_kernel *); hubdev->hdi_flush_nasid_list.widget_p = - kmalloc((HUB_WIDGET_ID_MAX + 1) * - sizeof(struct sn_flush_device_kernel *), - GFP_KERNEL); - memset(hubdev->hdi_flush_nasid_list.widget_p, 0x0, - (HUB_WIDGET_ID_MAX + 1) * - sizeof(struct sn_flush_device_kernel *)); + kzalloc(size, GFP_KERNEL); + if (!hubdev->hdi_flush_nasid_list.widget_p) + BUG(); for (widget = 0; widget <= HUB_WIDGET_ID_MAX; widget++) { - sn_flush_device_kernel = kmalloc(DEV_PER_WIDGET * - sizeof(struct - sn_flush_device_kernel), - GFP_KERNEL); + size = DEV_PER_WIDGET * + sizeof(struct sn_flush_device_kernel); + sn_flush_device_kernel = kzalloc(size, GFP_KERNEL); if (!sn_flush_device_kernel) BUG(); - memset(sn_flush_device_kernel, 0x0, - DEV_PER_WIDGET * - sizeof(struct sn_flush_device_kernel)); dev_entry = sn_flush_device_kernel; for (device = 0; device < DEV_PER_WIDGET; device++,dev_entry++) { - dev_entry->common = kmalloc(sizeof(struct - sn_flush_device_common), - GFP_KERNEL); + size = sizeof(struct sn_flush_device_common); + dev_entry->common = kzalloc(size, GFP_KERNEL); if (!dev_entry->common) BUG(); - memset(dev_entry->common, 0x0, sizeof(struct - sn_flush_device_common)); if (sn_prom_feature_available( PRF_DEVICE_FLUSH_LIST)) status = sal_get_device_dmaflush_list( - nasid, - widget, - device, - (u64)(dev_entry->common)); + nasid, widget, device, + (u64)(dev_entry->common)); else status = sn_device_fixup_war(nasid, - widget, - device, - dev_entry->common); + widget, device, + dev_entry->common); if (status != SALRET_OK) panic("SAL call failed: %s\n", ia64_sal_strerror(status)); @@ -383,13 +372,12 @@ void sn_pci_fixup_slot(struct pci_dev *dev) pci_dev_get(dev); /* for the sysdata pointer */ pcidev_info = kzalloc(sizeof(struct pcidev_info), GFP_KERNEL); - if (pcidev_info <= 0) + if (!pcidev_info) BUG(); /* Cannot afford to run out of memory */ - sn_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_KERNEL); - if (sn_irq_info <= 0) + sn_irq_info = kzalloc(sizeof(struct sn_irq_info), GFP_KERNEL); + if (!sn_irq_info) BUG(); /* Cannot afford to run out of memory */ - memset(sn_irq_info, 0, sizeof(struct sn_irq_info)); /* Call to retrieve pci device information needed by kernel. */ status = sal_get_pcidev_info((u64) segment, (u64) dev->bus->number, @@ -482,13 +470,13 @@ void sn_pci_fixup_slot(struct pci_dev *dev) */ void sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus) { - int status = 0; + int status; int nasid, cnode; struct pci_controller *controller; struct sn_pci_controller *sn_controller; struct pcibus_bussoft *prom_bussoft_ptr; struct hubdev_info *hubdev_info; - void *provider_soft = NULL; + void *provider_soft; struct sn_pcibus_provider *provider; status = sal_get_pcibus_info((u64) segment, (u64) busnum, @@ -535,6 +523,8 @@ void sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus) bus->sysdata = controller; if (provider->bus_fixup) provider_soft = (*provider->bus_fixup) (prom_bussoft_ptr, controller); + else + provider_soft = NULL; if (provider_soft == NULL) { /* fixup failed or not applicable */ @@ -638,13 +628,8 @@ void sn_bus_free_sysdata(void) static int __init sn_pci_init(void) { - int i = 0; - int j = 0; + int i, j; struct pci_dev *pci_dev = NULL; - extern void sn_init_cpei_timer(void); -#ifdef CONFIG_PROC_FS - extern void register_sn_procfs(void); -#endif if (!ia64_platform_is("sn2") || IS_RUNNING_ON_FAKE_PROM()) return 0; @@ -700,32 +685,29 @@ static int __init sn_pci_init(void) */ void hubdev_init_node(nodepda_t * npda, cnodeid_t node) { - struct hubdev_info *hubdev_info; + int size; + pg_data_t *pg; + + size = sizeof(struct hubdev_info); if (node >= num_online_nodes()) /* Headless/memless IO nodes */ - hubdev_info = - (struct hubdev_info *)alloc_bootmem_node(NODE_DATA(0), - sizeof(struct - hubdev_info)); + pg = NODE_DATA(0); else - hubdev_info = - (struct hubdev_info *)alloc_bootmem_node(NODE_DATA(node), - sizeof(struct - hubdev_info)); - npda->pdinfo = (void *)hubdev_info; + pg = NODE_DATA(node); + hubdev_info = (struct hubdev_info *)alloc_bootmem_node(pg, size); + + npda->pdinfo = (void *)hubdev_info; } geoid_t cnodeid_get_geoid(cnodeid_t cnode) { - struct hubdev_info *hubdev; hubdev = (struct hubdev_info *)(NODEPDA(cnode)->pdinfo); return hubdev->hdi_geoid; - } subsys_initcall(sn_pci_init); @@ -734,3 +716,4 @@ EXPORT_SYMBOL(sn_pci_unfixup_slot); EXPORT_SYMBOL(sn_pci_controller_fixup); EXPORT_SYMBOL(sn_bus_store_sysdata); EXPORT_SYMBOL(sn_bus_free_sysdata); +EXPORT_SYMBOL(sn_pcidev_info_get); diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index 48645ac120f..5b84836c217 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -75,7 +75,7 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second); DEFINE_PER_CPU(struct sn_hub_info_s, __sn_hub_info); EXPORT_PER_CPU_SYMBOL(__sn_hub_info); -DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_NUMNODES]); +DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]); EXPORT_PER_CPU_SYMBOL(__sn_cnodeid_to_nasid); DEFINE_PER_CPU(struct nodepda_s *, __sn_nodepda); @@ -317,6 +317,7 @@ struct pcdp_vga_device { #define PCDP_PCI_TRANS_IOPORT 0x02 #define PCDP_PCI_TRANS_MMIO 0x01 +#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE) static void sn_scan_pcdp(void) { @@ -358,6 +359,7 @@ sn_scan_pcdp(void) break; /* once we find the primary, we're done */ } } +#endif static unsigned long sn2_rtc_initial; diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c index 81c63b2f8ae..6ae276d5d50 100644 --- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c +++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 1999,2001-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (C) 1999,2001-2004, 2006 Silicon Graphics, Inc. All Rights Reserved. * * Module to export the system's Firmware Interface Tables, including * PROM revision numbers and banners, in /proc @@ -190,7 +190,7 @@ static int read_version_entry(char *page, char **start, off_t off, int count, int *eof, void *data) { - int len = 0; + int len; /* data holds the NASID of the node */ len = dump_version(page, (unsigned long)data); @@ -202,7 +202,7 @@ static int read_fit_entry(char *page, char **start, off_t off, int count, int *eof, void *data) { - int len = 0; + int len; /* data holds the NASID of the node */ len = dump_fit(page, (unsigned long)data); @@ -229,13 +229,16 @@ int __init prominfo_init(void) struct proc_dir_entry *p; cnodeid_t cnodeid; unsigned long nasid; + int size; char name[NODE_NAME_LEN]; if (!ia64_platform_is("sn2")) return 0; - proc_entries = kmalloc(num_online_nodes() * sizeof(struct proc_dir_entry *), - GFP_KERNEL); + size = num_online_nodes() * sizeof(struct proc_dir_entry *); + proc_entries = kzalloc(size, GFP_KERNEL); + if (!proc_entries) + return -ENOMEM; sgi_prominfo_entry = proc_mkdir("sgi_prominfo", NULL); @@ -244,14 +247,12 @@ int __init prominfo_init(void) sprintf(name, "node%d", cnodeid); *entp = proc_mkdir(name, sgi_prominfo_entry); nasid = cnodeid_to_nasid(cnodeid); - p = create_proc_read_entry( - "fit", 0, *entp, read_fit_entry, - (void *)nasid); + p = create_proc_read_entry("fit", 0, *entp, read_fit_entry, + (void *)nasid); if (p) p->owner = THIS_MODULE; - p = create_proc_read_entry( - "version", 0, *entp, read_version_entry, - (void *)nasid); + p = create_proc_read_entry("version", 0, *entp, + read_version_entry, (void *)nasid); if (p) p->owner = THIS_MODULE; entp++; @@ -263,7 +264,7 @@ int __init prominfo_init(void) void __exit prominfo_exit(void) { struct proc_dir_entry **entp; - unsigned cnodeid; + unsigned int cnodeid; char name[NODE_NAME_LEN]; entp = proc_entries; diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c index f153a4c35c7..24eefb2fc55 100644 --- a/arch/ia64/sn/kernel/sn2/sn2_smp.c +++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c @@ -46,8 +46,14 @@ DECLARE_PER_CPU(struct ptc_stats, ptcstats); static __cacheline_aligned DEFINE_SPINLOCK(sn2_global_ptc_lock); -void sn2_ptc_deadlock_recovery(short *, short, short, int, volatile unsigned long *, unsigned long, - volatile unsigned long *, unsigned long); +extern unsigned long +sn2_ptc_deadlock_recovery_core(volatile unsigned long *, unsigned long, + volatile unsigned long *, unsigned long, + volatile unsigned long *, unsigned long); +void +sn2_ptc_deadlock_recovery(short *, short, short, int, + volatile unsigned long *, unsigned long, + volatile unsigned long *, unsigned long); /* * Note: some is the following is captured here to make degugging easier @@ -59,16 +65,6 @@ void sn2_ptc_deadlock_recovery(short *, short, short, int, volatile unsigned lon #define reset_max_active_on_deadlock() 1 #define PTC_LOCK(sh1) ((sh1) ? &sn2_global_ptc_lock : &sn_nodepda->ptc_lock) -static inline void ptc_lock(int sh1, unsigned long *flagp) -{ - spin_lock_irqsave(PTC_LOCK(sh1), *flagp); -} - -static inline void ptc_unlock(int sh1, unsigned long flags) -{ - spin_unlock_irqrestore(PTC_LOCK(sh1), flags); -} - struct ptc_stats { unsigned long ptc_l; unsigned long change_rid; @@ -82,6 +78,8 @@ struct ptc_stats { unsigned long shub_ptc_flushes_not_my_mm; }; +#define sn2_ptctest 0 + static inline unsigned long wait_piowc(void) { volatile unsigned long *piows; @@ -200,7 +198,7 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, max_active = max_active_pio(shub1); itc = ia64_get_itc(); - ptc_lock(shub1, &flags); + spin_lock_irqsave(PTC_LOCK(shub1), flags); itc2 = ia64_get_itc(); __get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc; @@ -258,7 +256,7 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, ia64_srlz_d(); } - ptc_unlock(shub1, flags); + spin_unlock_irqrestore(PTC_LOCK(shub1), flags); preempt_enable(); } @@ -270,11 +268,12 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, * TLB flush transaction. The recovery sequence is somewhat tricky & is * coded in assembly language. */ -void sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid, volatile unsigned long *ptc0, unsigned long data0, - volatile unsigned long *ptc1, unsigned long data1) + +void +sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid, + volatile unsigned long *ptc0, unsigned long data0, + volatile unsigned long *ptc1, unsigned long data1) { - extern unsigned long sn2_ptc_deadlock_recovery_core(volatile unsigned long *, unsigned long, - volatile unsigned long *, unsigned long, volatile unsigned long *, unsigned long); short nasid, i; unsigned long *piows, zeroval, n; diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c index a06719d752a..c686d9c12f7 100644 --- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c +++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c @@ -6,11 +6,11 @@ * Copyright (C) 2000-2005 Silicon Graphics, Inc. All rights reserved. */ #include <linux/config.h> -#include <asm/uaccess.h> #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <asm/uaccess.h> #include <asm/sn/sn_sal.h> static int partition_id_show(struct seq_file *s, void *p) @@ -90,10 +90,10 @@ static int coherence_id_open(struct inode *inode, struct file *file) return single_open(file, coherence_id_show, NULL); } -static struct proc_dir_entry *sn_procfs_create_entry( - const char *name, struct proc_dir_entry *parent, - int (*openfunc)(struct inode *, struct file *), - int (*releasefunc)(struct inode *, struct file *)) +static struct proc_dir_entry +*sn_procfs_create_entry(const char *name, struct proc_dir_entry *parent, + int (*openfunc)(struct inode *, struct file *), + int (*releasefunc)(struct inode *, struct file *)) { struct proc_dir_entry *e = create_proc_entry(name, 0444, parent); @@ -126,24 +126,24 @@ void register_sn_procfs(void) return; sn_procfs_create_entry("partition_id", sgi_proc_dir, - partition_id_open, single_release); + partition_id_open, single_release); sn_procfs_create_entry("system_serial_number", sgi_proc_dir, - system_serial_number_open, single_release); + system_serial_number_open, single_release); sn_procfs_create_entry("licenseID", sgi_proc_dir, - licenseID_open, single_release); + licenseID_open, single_release); e = sn_procfs_create_entry("sn_force_interrupt", sgi_proc_dir, - sn_force_interrupt_open, single_release); + sn_force_interrupt_open, single_release); if (e) e->proc_fops->write = sn_force_interrupt_write_proc; sn_procfs_create_entry("coherence_id", sgi_proc_dir, - coherence_id_open, single_release); + coherence_id_open, single_release); sn_procfs_create_entry("sn_topology", sgi_proc_dir, - sn_topology_open, sn_topology_release); + sn_topology_open, sn_topology_release); } #endif /* CONFIG_PROC_FS */ diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c index deb9baf4d47..56a88b6df4b 100644 --- a/arch/ia64/sn/kernel/sn2/timer.c +++ b/arch/ia64/sn/kernel/sn2/timer.c @@ -14,6 +14,7 @@ #include <asm/hw_irq.h> #include <asm/system.h> +#include <asm/timex.h> #include <asm/sn/leds.h> #include <asm/sn/shub_mmr.h> @@ -28,9 +29,27 @@ static struct time_interpolator sn2_interpolator = { .source = TIME_SOURCE_MMIO64 }; +/* + * sn udelay uses the RTC instead of the ITC because the ITC is not + * synchronized across all CPUs, and the thread may migrate to another CPU + * if preemption is enabled. + */ +static void +ia64_sn_udelay (unsigned long usecs) +{ + unsigned long start = rtc_time(); + unsigned long end = start + + usecs * sn_rtc_cycles_per_second / 1000000; + + while (time_before((unsigned long)rtc_time(), end)) + cpu_relax(); +} + void __init sn_timer_init(void) { sn2_interpolator.frequency = sn_rtc_cycles_per_second; sn2_interpolator.addr = RTC_COUNTER_ADDR; register_time_interpolator(&sn2_interpolator); + + ia64_udelay = &ia64_sn_udelay; } diff --git a/arch/ia64/sn/kernel/sn2/timer_interrupt.c b/arch/ia64/sn/kernel/sn2/timer_interrupt.c index adf5db2e2af..fa7f6994591 100644 --- a/arch/ia64/sn/kernel/sn2/timer_interrupt.c +++ b/arch/ia64/sn/kernel/sn2/timer_interrupt.c @@ -1,7 +1,7 @@ /* * * - * Copyright (c) 2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2005, 2006 Silicon Graphics, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -22,11 +22,6 @@ * License along with this program; if not, write the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. * - * Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, - * Mountain View, CA 94043, or: - * - * http://www.sgi.com - * * For further information regarding this notice, see: * * http://oss.sgi.com/projects/GenInfo/NoticeExplan diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c index d263d3e8fbb..8a56f8b5ffa 100644 --- a/arch/ia64/sn/kernel/tiocx.c +++ b/arch/ia64/sn/kernel/tiocx.c @@ -284,12 +284,10 @@ struct sn_irq_info *tiocx_irq_alloc(nasid_t nasid, int widget, int irq, if ((nasid & 1) == 0) return NULL; - sn_irq_info = kmalloc(sn_irq_size, GFP_KERNEL); + sn_irq_info = kzalloc(sn_irq_size, GFP_KERNEL); if (sn_irq_info == NULL) return NULL; - memset(sn_irq_info, 0x0, sn_irq_size); - status = tiocx_intr_alloc(nasid, widget, __pa(sn_irq_info), irq, req_nasid, slice); if (status) { diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c index 36e5437a0fb..cdf6856ce08 100644 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ b/arch/ia64/sn/kernel/xpc_channel.c @@ -738,7 +738,9 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) /* make sure all activity has settled down first */ - if (atomic_read(&ch->references) > 0) { + if (atomic_read(&ch->references) > 0 || + ((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) && + !(ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE))) { return; } DBUG_ON(atomic_read(&ch->kthreads_assigned) != 0); @@ -775,7 +777,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) /* both sides are disconnected now */ - if (ch->flags & XPC_C_CONNECTCALLOUT) { + if (ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE) { spin_unlock_irqrestore(&ch->lock, *irq_flags); xpc_disconnect_callout(ch, xpcDisconnected); spin_lock_irqsave(&ch->lock, *irq_flags); @@ -1300,7 +1302,7 @@ xpc_process_msg_IPI(struct xpc_partition *part, int ch_number) "delivered=%d, partid=%d, channel=%d\n", nmsgs_sent, ch->partid, ch->number); - if (ch->flags & XPC_C_CONNECTCALLOUT) { + if (ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) { xpc_activate_kthreads(ch, nmsgs_sent); } } diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c index 9cd460dfe27..8cbf1643257 100644 --- a/arch/ia64/sn/kernel/xpc_main.c +++ b/arch/ia64/sn/kernel/xpc_main.c @@ -750,12 +750,16 @@ xpc_daemonize_kthread(void *args) /* let registerer know that connection has been established */ spin_lock_irqsave(&ch->lock, irq_flags); - if (!(ch->flags & XPC_C_CONNECTCALLOUT)) { - ch->flags |= XPC_C_CONNECTCALLOUT; + if (!(ch->flags & XPC_C_CONNECTEDCALLOUT)) { + ch->flags |= XPC_C_CONNECTEDCALLOUT; spin_unlock_irqrestore(&ch->lock, irq_flags); xpc_connected_callout(ch); + spin_lock_irqsave(&ch->lock, irq_flags); + ch->flags |= XPC_C_CONNECTEDCALLOUT_MADE; + spin_unlock_irqrestore(&ch->lock, irq_flags); + /* * It is possible that while the callout was being * made that the remote partition sent some messages. @@ -777,15 +781,17 @@ xpc_daemonize_kthread(void *args) if (atomic_dec_return(&ch->kthreads_assigned) == 0) { spin_lock_irqsave(&ch->lock, irq_flags); - if ((ch->flags & XPC_C_CONNECTCALLOUT) && - !(ch->flags & XPC_C_DISCONNECTCALLOUT)) { - ch->flags |= XPC_C_DISCONNECTCALLOUT; + if ((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) && + !(ch->flags & XPC_C_DISCONNECTINGCALLOUT)) { + ch->flags |= XPC_C_DISCONNECTINGCALLOUT; spin_unlock_irqrestore(&ch->lock, irq_flags); xpc_disconnect_callout(ch, xpcDisconnecting); - } else { - spin_unlock_irqrestore(&ch->lock, irq_flags); + + spin_lock_irqsave(&ch->lock, irq_flags); + ch->flags |= XPC_C_DISCONNECTINGCALLOUT_MADE; } + spin_unlock_irqrestore(&ch->lock, irq_flags); if (atomic_dec_return(&part->nchannels_engaged) == 0) { xpc_mark_partition_disengaged(part); xpc_IPI_send_disengage(part); diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index 5a36292388e..b4b84c26921 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -335,10 +335,10 @@ int sn_pci_legacy_read(struct pci_bus *bus, u16 port, u32 *val, u8 size) */ SAL_CALL(isrv, SN_SAL_IOIF_PCI_SAFE, - pci_domain_nr(bus), bus->number, - 0, /* io */ - 0, /* read */ - port, size, __pa(val)); + pci_domain_nr(bus), bus->number, + 0, /* io */ + 0, /* read */ + port, size, __pa(val)); if (isrv.status == 0) return size; @@ -381,10 +381,10 @@ int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size) */ SAL_CALL(isrv, SN_SAL_IOIF_PCI_SAFE, - pci_domain_nr(bus), bus->number, - 0, /* io */ - 1, /* write */ - port, size, __pa(&val)); + pci_domain_nr(bus), bus->number, + 0, /* io */ + 1, /* write */ + port, size, __pa(&val)); if (isrv.status == 0) return size; diff --git a/arch/ia64/sn/pci/pcibr/pcibr_ate.c b/arch/ia64/sn/pci/pcibr/pcibr_ate.c index aa3fa5152a3..1f0253bfe0a 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_ate.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_ate.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2001-2004 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2001-2006 Silicon Graphics, Inc. All rights reserved. */ #include <linux/types.h> @@ -12,7 +12,7 @@ #include <asm/sn/pcibus_provider_defs.h> #include <asm/sn/pcidev.h> -int pcibr_invalidate_ate = 0; /* by default don't invalidate ATE on free */ +int pcibr_invalidate_ate; /* by default don't invalidate ATE on free */ /* * mark_ate: Mark the ate as either free or inuse. @@ -20,14 +20,12 @@ int pcibr_invalidate_ate = 0; /* by default don't invalidate ATE on free */ static void mark_ate(struct ate_resource *ate_resource, int start, int number, u64 value) { - u64 *ate = ate_resource->ate; int index; int length = 0; for (index = start; length < number; index++, length++) ate[index] = value; - } /* @@ -37,7 +35,6 @@ static void mark_ate(struct ate_resource *ate_resource, int start, int number, static int find_free_ate(struct ate_resource *ate_resource, int start, int count) { - u64 *ate = ate_resource->ate; int index; int start_free; @@ -70,12 +67,10 @@ static int find_free_ate(struct ate_resource *ate_resource, int start, static inline void free_ate_resource(struct ate_resource *ate_resource, int start) { - mark_ate(ate_resource, start, ate_resource->ate[start], 0); if ((ate_resource->lowest_free_index > start) || (ate_resource->lowest_free_index < 0)) ate_resource->lowest_free_index = start; - } /* @@ -84,7 +79,6 @@ static inline void free_ate_resource(struct ate_resource *ate_resource, static inline int alloc_ate_resource(struct ate_resource *ate_resource, int ate_needed) { - int start_index; /* @@ -118,19 +112,12 @@ static inline int alloc_ate_resource(struct ate_resource *ate_resource, */ int pcibr_ate_alloc(struct pcibus_info *pcibus_info, int count) { - int status = 0; - u64 flag; + int status; + unsigned long flags; - flag = pcibr_lock(pcibus_info); + spin_lock_irqsave(&pcibus_info->pbi_lock, flags); status = alloc_ate_resource(&pcibus_info->pbi_int_ate_resource, count); - - if (status < 0) { - /* Failed to allocate */ - pcibr_unlock(pcibus_info, flag); - return -1; - } - - pcibr_unlock(pcibus_info, flag); + spin_unlock_irqrestore(&pcibus_info->pbi_lock, flags); return status; } @@ -182,7 +169,7 @@ void pcibr_ate_free(struct pcibus_info *pcibus_info, int index) ate_write(pcibus_info, index, count, (ate & ~PCI32_ATE_V)); } - flags = pcibr_lock(pcibus_info); + spin_lock_irqsave(&pcibus_info->pbi_lock, flags); free_ate_resource(&pcibus_info->pbi_int_ate_resource, index); - pcibr_unlock(pcibus_info, flags); + spin_unlock_irqrestore(&pcibus_info->pbi_lock, flags); } diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index 54ce5b7ceed..9f86bb6519a 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -137,14 +137,12 @@ pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, pci_addr |= PCI64_ATTR_VIRTUAL; return pci_addr; - } static dma_addr_t pcibr_dmatrans_direct32(struct pcidev_info * info, u64 paddr, size_t req_size, u64 flags) { - struct pcidev_info *pcidev_info = info->pdi_host_pcidev_info; struct pcibus_info *pcibus_info = (struct pcibus_info *)pcidev_info-> pdi_pcibus_info; @@ -171,7 +169,6 @@ pcibr_dmatrans_direct32(struct pcidev_info * info, } return PCI32_DIRECT_BASE | offset; - } /* @@ -218,9 +215,8 @@ void sn_dma_flush(u64 addr) u64 flags; u64 itte; struct hubdev_info *hubinfo; - volatile struct sn_flush_device_kernel *p; - volatile struct sn_flush_device_common *common; - + struct sn_flush_device_kernel *p; + struct sn_flush_device_common *common; struct sn_flush_nasid_entry *flush_nasid_list; if (!sn_ioif_inited) @@ -310,8 +306,7 @@ void sn_dma_flush(u64 addr) (common->sfdl_slot - 1)); } } else { - spin_lock_irqsave((spinlock_t *)&p->sfdl_flush_lock, - flags); + spin_lock_irqsave(&p->sfdl_flush_lock, flags); *common->sfdl_flush_addr = 0; /* force an interrupt. */ @@ -322,8 +317,7 @@ void sn_dma_flush(u64 addr) cpu_relax(); /* okay, everything is synched up. */ - spin_unlock_irqrestore((spinlock_t *)&p->sfdl_flush_lock, - flags); + spin_unlock_irqrestore(&p->sfdl_flush_lock, flags); } return; } diff --git a/arch/ia64/sn/pci/pcibr/pcibr_provider.c b/arch/ia64/sn/pci/pcibr/pcibr_provider.c index 2fac27049bf..98f716bd92f 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_provider.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_provider.c @@ -163,9 +163,12 @@ pcibr_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont /* Setup the PMU ATE map */ soft->pbi_int_ate_resource.lowest_free_index = 0; soft->pbi_int_ate_resource.ate = - kmalloc(soft->pbi_int_ate_size * sizeof(u64), GFP_KERNEL); - memset(soft->pbi_int_ate_resource.ate, 0, - (soft->pbi_int_ate_size * sizeof(u64))); + kzalloc(soft->pbi_int_ate_size * sizeof(u64), GFP_KERNEL); + + if (!soft->pbi_int_ate_resource.ate) { + kfree(soft); + return NULL; + } if (prom_bussoft->bs_asic_type == PCIIO_ASIC_TYPE_TIOCP) { /* TIO PCI Bridge: find nearest node with CPUs */ diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 96b91982805..8849439e88d 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -21,6 +21,10 @@ config GENERIC_CALIBRATE_DELAY bool default y +config TIME_LOW_RES + bool + default y + config ARCH_MAY_HAVE_PC_FDC bool depends on Q40 || (BROKEN && SUN3X) diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig index e2a6e864896..e50858dbc23 100644 --- a/arch/m68knommu/Kconfig +++ b/arch/m68knommu/Kconfig @@ -29,6 +29,10 @@ config GENERIC_CALIBRATE_DELAY bool default y +config TIME_LOW_RES + bool + default y + source "init/Kconfig" menu "Processor type and features" diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 6a57407df1b..38c0f3360d5 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -94,7 +94,6 @@ endif # machines may also. Since BFD is incredibly buggy with respect to # crossformat linking we rely on the elf2ecoff tool for format conversion. # -cflags-y += -I $(TOPDIR)/include/asm/gcc cflags-y += -G 0 -mno-abicalls -fno-pic -pipe LDFLAGS_vmlinux += -G 0 -static -n -nostdlib MODFLAGS += -mlong-calls diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 5232fc75293..092679c2dca 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/a.out.h> #include <linux/init.h> #include <linux/completion.h> +#include <linux/kallsyms.h> #include <asm/abi.h> #include <asm/bootinfo.h> @@ -272,46 +273,19 @@ long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) static struct mips_frame_info { void *func; - int omit_fp; /* compiled without fno-omit-frame-pointer */ - int frame_offset; + unsigned long func_size; + int frame_size; int pc_offset; -} schedule_frame, mfinfo[] = { - { schedule, 0 }, /* must be first */ - /* arch/mips/kernel/semaphore.c */ - { __down, 1 }, - { __down_interruptible, 1 }, - /* kernel/sched.c */ -#ifdef CONFIG_PREEMPT - { preempt_schedule, 0 }, -#endif - { wait_for_completion, 0 }, - { interruptible_sleep_on, 0 }, - { interruptible_sleep_on_timeout, 0 }, - { sleep_on, 0 }, - { sleep_on_timeout, 0 }, - { yield, 0 }, - { io_schedule, 0 }, - { io_schedule_timeout, 0 }, -#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT) - { __preempt_spin_lock, 0 }, - { __preempt_write_lock, 0 }, -#endif - /* kernel/timer.c */ - { schedule_timeout, 1 }, -/* { nanosleep_restart, 1 }, */ - /* lib/rwsem-spinlock.c */ - { __down_read, 1 }, - { __down_write, 1 }, -}; +} *schedule_frame, mfinfo[64]; +static int mfinfo_num; -static int mips_frame_info_initialized; static int __init get_frame_info(struct mips_frame_info *info) { int i; void *func = info->func; union mips_instruction *ip = (union mips_instruction *)func; info->pc_offset = -1; - info->frame_offset = info->omit_fp ? 0 : -1; + info->frame_size = 0; for (i = 0; i < 128; i++, ip++) { /* if jal, jalr, jr, stop. */ if (ip->j_format.opcode == jal_op || @@ -320,6 +294,23 @@ static int __init get_frame_info(struct mips_frame_info *info) ip->r_format.func == jr_op))) break; + if (info->func_size && i >= info->func_size / 4) + break; + if ( +#ifdef CONFIG_32BIT + ip->i_format.opcode == addiu_op && +#endif +#ifdef CONFIG_64BIT + ip->i_format.opcode == daddiu_op && +#endif + ip->i_format.rs == 29 && + ip->i_format.rt == 29) { + /* addiu/daddiu sp,sp,-imm */ + if (info->frame_size) + continue; + info->frame_size = - ip->i_format.simmediate; + } + if ( #ifdef CONFIG_32BIT ip->i_format.opcode == sw_op && @@ -327,31 +318,20 @@ static int __init get_frame_info(struct mips_frame_info *info) #ifdef CONFIG_64BIT ip->i_format.opcode == sd_op && #endif - ip->i_format.rs == 29) - { + ip->i_format.rs == 29 && + ip->i_format.rt == 31) { /* sw / sd $ra, offset($sp) */ - if (ip->i_format.rt == 31) { - if (info->pc_offset != -1) - continue; - info->pc_offset = - ip->i_format.simmediate / sizeof(long); - } - /* sw / sd $s8, offset($sp) */ - if (ip->i_format.rt == 30) { -//#if 0 /* gcc 3.4 does aggressive optimization... */ - if (info->frame_offset != -1) - continue; -//#endif - info->frame_offset = - ip->i_format.simmediate / sizeof(long); - } + if (info->pc_offset != -1) + continue; + info->pc_offset = + ip->i_format.simmediate / sizeof(long); } } - if (info->pc_offset == -1 || info->frame_offset == -1) { - printk("Can't analyze prologue code at %p\n", func); + if (info->pc_offset == -1 || info->frame_size == 0) { + if (func == schedule) + printk("Can't analyze prologue code at %p\n", func); info->pc_offset = -1; - info->frame_offset = -1; - return -1; + info->frame_size = 0; } return 0; @@ -359,25 +339,36 @@ static int __init get_frame_info(struct mips_frame_info *info) static int __init frame_info_init(void) { - int i, found; - for (i = 0; i < ARRAY_SIZE(mfinfo); i++) - if (get_frame_info(&mfinfo[i])) - return -1; - schedule_frame = mfinfo[0]; - /* bubble sort */ - do { - struct mips_frame_info tmp; - found = 0; - for (i = 1; i < ARRAY_SIZE(mfinfo); i++) { - if (mfinfo[i-1].func > mfinfo[i].func) { - tmp = mfinfo[i]; - mfinfo[i] = mfinfo[i-1]; - mfinfo[i-1] = tmp; - found = 1; - } - } - } while (found); - mips_frame_info_initialized = 1; + int i; +#ifdef CONFIG_KALLSYMS + char *modname; + char namebuf[KSYM_NAME_LEN + 1]; + unsigned long start, size, ofs; + extern char __sched_text_start[], __sched_text_end[]; + extern char __lock_text_start[], __lock_text_end[]; + + start = (unsigned long)__sched_text_start; + for (i = 0; i < ARRAY_SIZE(mfinfo); i++) { + if (start == (unsigned long)schedule) + schedule_frame = &mfinfo[i]; + if (!kallsyms_lookup(start, &size, &ofs, &modname, namebuf)) + break; + mfinfo[i].func = (void *)(start + ofs); + mfinfo[i].func_size = size; + start += size - ofs; + if (start >= (unsigned long)__lock_text_end) + break; + if (start == (unsigned long)__sched_text_end) + start = (unsigned long)__lock_text_start; + } +#else + mfinfo[0].func = schedule; + schedule_frame = &mfinfo[0]; +#endif + for (i = 0; i < ARRAY_SIZE(mfinfo) && mfinfo[i].func; i++) + get_frame_info(&mfinfo[i]); + + mfinfo_num = i; return 0; } @@ -394,47 +385,52 @@ unsigned long thread_saved_pc(struct task_struct *tsk) if (t->reg31 == (unsigned long) ret_from_fork) return t->reg31; - if (schedule_frame.pc_offset < 0) + if (!schedule_frame || schedule_frame->pc_offset < 0) return 0; - return ((unsigned long *)t->reg29)[schedule_frame.pc_offset]; + return ((unsigned long *)t->reg29)[schedule_frame->pc_offset]; } /* get_wchan - a maintenance nightmare^W^Wpain in the ass ... */ unsigned long get_wchan(struct task_struct *p) { unsigned long stack_page; - unsigned long frame, pc; + unsigned long pc; +#ifdef CONFIG_KALLSYMS + unsigned long frame; +#endif if (!p || p == current || p->state == TASK_RUNNING) return 0; stack_page = (unsigned long)task_stack_page(p); - if (!stack_page || !mips_frame_info_initialized) + if (!stack_page || !mfinfo_num) return 0; pc = thread_saved_pc(p); +#ifdef CONFIG_KALLSYMS if (!in_sched_functions(pc)) return pc; - frame = ((unsigned long *)p->thread.reg30)[schedule_frame.frame_offset]; + frame = p->thread.reg29 + schedule_frame->frame_size; do { int i; if (frame < stack_page || frame > stack_page + THREAD_SIZE - 32) return 0; - for (i = ARRAY_SIZE(mfinfo) - 1; i >= 0; i--) { + for (i = mfinfo_num - 1; i >= 0; i--) { if (pc >= (unsigned long) mfinfo[i].func) break; } if (i < 0) break; - if (mfinfo[i].omit_fp) - break; pc = ((unsigned long *)frame)[mfinfo[i].pc_offset]; - frame = ((unsigned long *)frame)[mfinfo[i].frame_offset]; + if (!mfinfo[i].frame_size) + break; + frame += mfinfo[i].frame_size; } while (in_sched_functions(pc)); +#endif return pc; } diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h index 0fbc492d24b..36bfc2588aa 100644 --- a/arch/mips/kernel/signal-common.h +++ b/arch/mips/kernel/signal-common.h @@ -176,7 +176,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size) if ((ka->sa.sa_flags & SA_ONSTACK) && (sas_ss_flags (sp) == 0)) sp = current->sas_ss_sp + current->sas_ss_size; - return (void __user *)((sp - frame_size) & (ICACHE_REFILLS_WORKAROUND_WAR ? 32 : ALMASK)); + return (void __user *)((sp - frame_size) & (ICACHE_REFILLS_WORKAROUND_WAR ? ~(cpu_icache_line_size()-1) : ALMASK)); } static inline int install_sigtramp(unsigned int __user *tramp, diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index da3271e1fda..8a8b8dd9041 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -537,7 +537,7 @@ _sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) /* The ucontext contains a stack32_t, so we must convert! */ if (__get_user(sp, &frame->rs_uc.uc_stack.ss_sp)) goto badframe; - st.ss_size = (long) sp; + st.ss_sp = (void *)(long) sp; if (__get_user(st.ss_size, &frame->rs_uc.uc_stack.ss_size)) goto badframe; if (__get_user(st.ss_flags, &frame->rs_uc.uc_stack.ss_flags)) diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c index 384fc4a639a..5a3776096f0 100644 --- a/arch/mips/kernel/signal_n32.c +++ b/arch/mips/kernel/signal_n32.c @@ -108,7 +108,7 @@ _sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) /* The ucontext contains a stack32_t, so we must convert! */ if (__get_user(sp, &frame->rs_uc.uc_stack.ss_sp)) goto badframe; - st.ss_size = (long) sp; + st.ss_sp = (void *)(long) sp; if (__get_user(st.ss_size, &frame->rs_uc.uc_stack.ss_size)) goto badframe; if (__get_user(st.ss_flags, &frame->rs_uc.uc_stack.ss_flags)) diff --git a/arch/mips/kernel/smp_mt.c b/arch/mips/kernel/smp_mt.c index 794a1c3de2a..c930364830d 100644 --- a/arch/mips/kernel/smp_mt.c +++ b/arch/mips/kernel/smp_mt.c @@ -68,6 +68,8 @@ void __init sanitize_tlb_entries(void) set_c0_mvpcontrol(MVPCONTROL_VPC); + back_to_back_c0_hazard(); + /* Disable TLB sharing */ clear_c0_mvpcontrol(MVPCONTROL_STLB); @@ -102,35 +104,6 @@ void __init sanitize_tlb_entries(void) clear_c0_mvpcontrol(MVPCONTROL_VPC); } -#if 0 -/* - * Use c0_MVPConf0 to find out how many CPUs are available, setting up - * phys_cpu_present_map and the logical/physical mappings. - */ -void __init prom_build_cpu_map(void) -{ - int i, num, ncpus; - - cpus_clear(phys_cpu_present_map); - - /* assume we boot on cpu 0.... */ - cpu_set(0, phys_cpu_present_map); - __cpu_number_map[0] = 0; - __cpu_logical_map[0] = 0; - - if (cpu_has_mipsmt) { - ncpus = ((read_c0_mvpconf0() & (MVPCONF0_PVPE)) >> MVPCONF0_PVPE_SHIFT) + 1; - for (i=1, num=0; i< NR_CPUS && i<ncpus; i++) { - cpu_set(i, phys_cpu_present_map); - __cpu_number_map[i] = ++num; - __cpu_logical_map[num] = i; - } - - printk(KERN_INFO "%i available secondary CPU(s)\n", num); - } -} -#endif - static void ipi_resched_dispatch (struct pt_regs *regs) { do_IRQ(MIPS_CPU_IPI_RESCHED_IRQ, regs); @@ -222,6 +195,9 @@ void prom_prepare_cpus(unsigned int max_cpus) /* set config to be the same as vpe0, particularly kseg0 coherency alg */ write_vpe_c0_config( read_c0_config()); + + /* Propagate Config7 */ + write_vpe_c0_config7(read_c0_config7()); } } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index e51c38cef88..1b71d91e826 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -471,61 +471,29 @@ struct flush_icache_range_args { static inline void local_r4k_flush_icache_range(void *args) { struct flush_icache_range_args *fir_args = args; - unsigned long dc_lsize = cpu_dcache_line_size(); - unsigned long ic_lsize = cpu_icache_line_size(); - unsigned long sc_lsize = cpu_scache_line_size(); unsigned long start = fir_args->start; unsigned long end = fir_args->end; - unsigned long addr, aend; if (!cpu_has_ic_fills_f_dc) { if (end - start > dcache_size) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; - addr = start & ~(dc_lsize - 1); - aend = (end - 1) & ~(dc_lsize - 1); - - while (1) { - /* Hit_Writeback_Inv_D */ - protected_writeback_dcache_line(addr); - if (addr == aend) - break; - addr += dc_lsize; - } + protected_blast_dcache_range(start, end); } if (!cpu_icache_snoops_remote_store) { - if (end - start > scache_size) { + if (end - start > scache_size) r4k_blast_scache(); - } else { - addr = start & ~(sc_lsize - 1); - aend = (end - 1) & ~(sc_lsize - 1); - - while (1) { - /* Hit_Writeback_Inv_SD */ - protected_writeback_scache_line(addr); - if (addr == aend) - break; - addr += sc_lsize; - } - } + else + protected_blast_scache_range(start, end); } } if (end - start > icache_size) r4k_blast_icache(); - else { - addr = start & ~(ic_lsize - 1); - aend = (end - 1) & ~(ic_lsize - 1); - while (1) { - /* Hit_Invalidate_I */ - protected_flush_icache_line(addr); - if (addr == aend) - break; - addr += ic_lsize; - } - } + else + protected_blast_icache_range(start, end); } static void r4k_flush_icache_range(unsigned long start, unsigned long end) @@ -619,27 +587,14 @@ static void r4k_flush_icache_page(struct vm_area_struct *vma, static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) { - unsigned long end, a; - /* Catch bad driver code */ BUG_ON(size == 0); if (cpu_has_subset_pcaches) { - unsigned long sc_lsize = cpu_scache_line_size(); - - if (size >= scache_size) { + if (size >= scache_size) r4k_blast_scache(); - return; - } - - a = addr & ~(sc_lsize - 1); - end = (addr + size - 1) & ~(sc_lsize - 1); - while (1) { - flush_scache_line(a); /* Hit_Writeback_Inv_SD */ - if (a == end) - break; - a += sc_lsize; - } + else + blast_scache_range(addr, addr + size); return; } @@ -651,17 +606,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) if (size >= dcache_size) { r4k_blast_dcache(); } else { - unsigned long dc_lsize = cpu_dcache_line_size(); - R4600_HIT_CACHEOP_WAR_IMPL; - a = addr & ~(dc_lsize - 1); - end = (addr + size - 1) & ~(dc_lsize - 1); - while (1) { - flush_dcache_line(a); /* Hit_Writeback_Inv_D */ - if (a == end) - break; - a += dc_lsize; - } + blast_dcache_range(addr, addr + size); } bc_wback_inv(addr, size); @@ -669,44 +615,22 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) { - unsigned long end, a; - /* Catch bad driver code */ BUG_ON(size == 0); if (cpu_has_subset_pcaches) { - unsigned long sc_lsize = cpu_scache_line_size(); - - if (size >= scache_size) { + if (size >= scache_size) r4k_blast_scache(); - return; - } - - a = addr & ~(sc_lsize - 1); - end = (addr + size - 1) & ~(sc_lsize - 1); - while (1) { - flush_scache_line(a); /* Hit_Writeback_Inv_SD */ - if (a == end) - break; - a += sc_lsize; - } + else + blast_scache_range(addr, addr + size); return; } if (size >= dcache_size) { r4k_blast_dcache(); } else { - unsigned long dc_lsize = cpu_dcache_line_size(); - R4600_HIT_CACHEOP_WAR_IMPL; - a = addr & ~(dc_lsize - 1); - end = (addr + size - 1) & ~(dc_lsize - 1); - while (1) { - flush_dcache_line(a); /* Hit_Writeback_Inv_D */ - if (a == end) - break; - a += dc_lsize; - } + blast_dcache_range(addr, addr + size); } bc_inv(addr, size); diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index 0a97a9434eb..7c572bea4a9 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -44,8 +44,6 @@ __asm__ __volatile__( \ /* TX39H-style cache flush routines. */ static void tx39h_flush_icache_all(void) { - unsigned long start = KSEG0; - unsigned long end = (start + icache_size); unsigned long flags, config; /* disable icache (set ICE#) */ @@ -53,33 +51,18 @@ static void tx39h_flush_icache_all(void) config = read_c0_conf(); write_c0_conf(config & ~TX39_CONF_ICE); TX39_STOP_STREAMING(); - - /* invalidate icache */ - while (start < end) { - cache16_unroll32(start, Index_Invalidate_I); - start += 0x200; - } - + blast_icache16(); write_c0_conf(config); local_irq_restore(flags); } static void tx39h_dma_cache_wback_inv(unsigned long addr, unsigned long size) { - unsigned long end, a; - unsigned long dc_lsize = current_cpu_data.dcache.linesz; - /* Catch bad driver code */ BUG_ON(size == 0); iob(); - a = addr & ~(dc_lsize - 1); - end = (addr + size - 1) & ~(dc_lsize - 1); - while (1) { - invalidate_dcache_line(a); /* Hit_Invalidate_D */ - if (a == end) break; - a += dc_lsize; - } + blast_inv_dcache_range(addr, addr + size); } @@ -241,42 +224,21 @@ static void tx39_flush_data_cache_page(unsigned long addr) static void tx39_flush_icache_range(unsigned long start, unsigned long end) { - unsigned long dc_lsize = current_cpu_data.dcache.linesz; - unsigned long addr, aend; - if (end - start > dcache_size) tx39_blast_dcache(); - else { - addr = start & ~(dc_lsize - 1); - aend = (end - 1) & ~(dc_lsize - 1); - - while (1) { - /* Hit_Writeback_Inv_D */ - protected_writeback_dcache_line(addr); - if (addr == aend) - break; - addr += dc_lsize; - } - } + else + protected_blast_dcache_range(start, end); if (end - start > icache_size) tx39_blast_icache(); else { unsigned long flags, config; - addr = start & ~(dc_lsize - 1); - aend = (end - 1) & ~(dc_lsize - 1); /* disable icache (set ICE#) */ local_irq_save(flags); config = read_c0_conf(); write_c0_conf(config & ~TX39_CONF_ICE); TX39_STOP_STREAMING(); - while (1) { - /* Hit_Invalidate_I */ - protected_flush_icache_line(addr); - if (addr == aend) - break; - addr += dc_lsize; - } + protected_blast_icache_range(start, end); write_c0_conf(config); local_irq_restore(flags); } @@ -311,7 +273,7 @@ static void tx39_flush_icache_page(struct vm_area_struct *vma, struct page *page static void tx39_dma_cache_wback_inv(unsigned long addr, unsigned long size) { - unsigned long end, a; + unsigned long end; if (((size | addr) & (PAGE_SIZE - 1)) == 0) { end = addr + size; @@ -322,20 +284,13 @@ static void tx39_dma_cache_wback_inv(unsigned long addr, unsigned long size) } else if (size > dcache_size) { tx39_blast_dcache(); } else { - unsigned long dc_lsize = current_cpu_data.dcache.linesz; - a = addr & ~(dc_lsize - 1); - end = (addr + size - 1) & ~(dc_lsize - 1); - while (1) { - flush_dcache_line(a); /* Hit_Writeback_Inv_D */ - if (a == end) break; - a += dc_lsize; - } + blast_dcache_range(addr, addr + size); } } static void tx39_dma_cache_inv(unsigned long addr, unsigned long size) { - unsigned long end, a; + unsigned long end; if (((size | addr) & (PAGE_SIZE - 1)) == 0) { end = addr + size; @@ -346,14 +301,7 @@ static void tx39_dma_cache_inv(unsigned long addr, unsigned long size) } else if (size > dcache_size) { tx39_blast_dcache(); } else { - unsigned long dc_lsize = current_cpu_data.dcache.linesz; - a = addr & ~(dc_lsize - 1); - end = (addr + size - 1) & ~(dc_lsize - 1); - while (1) { - invalidate_dcache_line(a); /* Hit_Invalidate_D */ - if (a == end) break; - a += dc_lsize; - } + blast_inv_dcache_range(addr, addr + size); } } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7c914a4c67c..eca33cfa8a4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -29,6 +29,11 @@ config GENERIC_CALIBRATE_DELAY bool default y +config TIME_LOW_RES + bool + depends on SMP + default y + config GENERIC_ISA_DMA bool diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index e96c35bddac..71f0a2fb307 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -30,7 +30,7 @@ void __delay(unsigned long loops) */ __asm__ __volatile__( "0: brct %0,0b" - : /* no outputs */ : "r" (loops/2) ); + : /* no outputs */ : "r" ((loops/2) + 1)); } /* diff --git a/arch/v850/Kconfig b/arch/v850/Kconfig index 04494638b96..e7fc3e50034 100644 --- a/arch/v850/Kconfig +++ b/arch/v850/Kconfig @@ -28,6 +28,10 @@ config GENERIC_IRQ_PROBE bool default y +config TIME_LOW_RES + bool + default y + # Turn off some random 386 crap that can affect device config config ISA bool diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 4e7dbcc425f..93e44d0292a 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -645,7 +645,7 @@ static void pkt_copy_bio_data(struct bio *src_bio, int seg, int offs, struct pag * b) The data can be used as cache to avoid read requests if we receive a * new write request for the same zone. */ -static void pkt_make_local_copy(struct packet_data *pkt, struct page **pages, int *offsets) +static void pkt_make_local_copy(struct packet_data *pkt, struct bio_vec *bvec) { int f, p, offs; @@ -653,15 +653,15 @@ static void pkt_make_local_copy(struct packet_data *pkt, struct page **pages, in p = 0; offs = 0; for (f = 0; f < pkt->frames; f++) { - if (pages[f] != pkt->pages[p]) { - void *vfrom = kmap_atomic(pages[f], KM_USER0) + offsets[f]; + if (bvec[f].bv_page != pkt->pages[p]) { + void *vfrom = kmap_atomic(bvec[f].bv_page, KM_USER0) + bvec[f].bv_offset; void *vto = page_address(pkt->pages[p]) + offs; memcpy(vto, vfrom, CD_FRAMESIZE); kunmap_atomic(vfrom, KM_USER0); - pages[f] = pkt->pages[p]; - offsets[f] = offs; + bvec[f].bv_page = pkt->pages[p]; + bvec[f].bv_offset = offs; } else { - BUG_ON(offsets[f] != offs); + BUG_ON(bvec[f].bv_offset != offs); } offs += CD_FRAMESIZE; if (offs >= PAGE_SIZE) { @@ -991,18 +991,17 @@ try_next_bio: static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { struct bio *bio; - struct page *pages[PACKET_MAX_SIZE]; - int offsets[PACKET_MAX_SIZE]; int f; int frames_write; + struct bio_vec *bvec = pkt->w_bio->bi_io_vec; for (f = 0; f < pkt->frames; f++) { - pages[f] = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE]; - offsets[f] = (f * CD_FRAMESIZE) % PAGE_SIZE; + bvec[f].bv_page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE]; + bvec[f].bv_offset = (f * CD_FRAMESIZE) % PAGE_SIZE; } /* - * Fill-in pages[] and offsets[] with data from orig_bios. + * Fill-in bvec with data from orig_bios. */ frames_write = 0; spin_lock(&pkt->lock); @@ -1024,11 +1023,11 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) } if (src_bvl->bv_len - src_offs >= CD_FRAMESIZE) { - pages[f] = src_bvl->bv_page; - offsets[f] = src_bvl->bv_offset + src_offs; + bvec[f].bv_page = src_bvl->bv_page; + bvec[f].bv_offset = src_bvl->bv_offset + src_offs; } else { pkt_copy_bio_data(bio, segment, src_offs, - pages[f], offsets[f]); + bvec[f].bv_page, bvec[f].bv_offset); } src_offs += CD_FRAMESIZE; frames_write++; @@ -1042,7 +1041,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) BUG_ON(frames_write != pkt->write_size); if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) { - pkt_make_local_copy(pkt, pages, offsets); + pkt_make_local_copy(pkt, bvec); pkt->cache_valid = 1; } else { pkt->cache_valid = 0; @@ -1055,17 +1054,9 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) pkt->w_bio->bi_bdev = pd->bdev; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; - for (f = 0; f < pkt->frames; f++) { - if ((f + 1 < pkt->frames) && (pages[f + 1] == pages[f]) && - (offsets[f + 1] = offsets[f] + CD_FRAMESIZE)) { - if (!bio_add_page(pkt->w_bio, pages[f], CD_FRAMESIZE * 2, offsets[f])) - BUG(); - f++; - } else { - if (!bio_add_page(pkt->w_bio, pages[f], CD_FRAMESIZE, offsets[f])) - BUG(); - } - } + for (f = 0; f < pkt->frames; f++) + if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset)) + BUG(); VPRINTK("pktcdvd: vcnt=%d\n", pkt->w_bio->bi_vcnt); atomic_set(&pkt->io_wait, 1); @@ -1548,7 +1539,7 @@ static int pkt_good_disc(struct pktcdvd_device *pd, disc_information *di) case 0x12: /* DVD-RAM */ return 0; default: - printk("pktcdvd: Wrong disc profile (%x)\n", pd->mmc3_profile); + VPRINTK("pktcdvd: Wrong disc profile (%x)\n", pd->mmc3_profile); return 1; } @@ -1894,8 +1885,8 @@ static int pkt_open_write(struct pktcdvd_device *pd) unsigned int write_speed, media_write_speed, read_speed; if ((ret = pkt_probe_settings(pd))) { - DPRINTK("pktcdvd: %s failed probe\n", pd->name); - return -EIO; + VPRINTK("pktcdvd: %s failed probe\n", pd->name); + return -EROFS; } if ((ret = pkt_set_write_settings(pd))) { @@ -2053,10 +2044,9 @@ static int pkt_open(struct inode *inode, struct file *file) goto out_dec; } } else { - if (pkt_open_dev(pd, file->f_mode & FMODE_WRITE)) { - ret = -EIO; + ret = pkt_open_dev(pd, file->f_mode & FMODE_WRITE); + if (ret) goto out_dec; - } /* * needed here as well, since ext2 (among others) may change * the blocksize at mount time @@ -2436,11 +2426,12 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u * The door gets locked when the device is opened, so we * have to unlock it or else the eject command fails. */ - pkt_lock_door(pd, 0); + if (pd->refcnt == 1) + pkt_lock_door(pd, 0); return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg); default: - printk("pktcdvd: Unknown ioctl for %s (%x)\n", pd->name, cmd); + VPRINTK("pktcdvd: Unknown ioctl for %s (%x)\n", pd->name, cmd); return -ENOTTY; } diff --git a/drivers/char/esp.c b/drivers/char/esp.c index 57539d8f9f7..09dc4b01232 100644 --- a/drivers/char/esp.c +++ b/drivers/char/esp.c @@ -150,17 +150,6 @@ static void rs_wait_until_sent(struct tty_struct *, int); /* Standard COM flags (except for COM4, because of the 8514 problem) */ #define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST) -/* - * tmp_buf is used as a temporary buffer by serial_write. We need to - * lock it in case the memcpy_fromfs blocks while swapping in a page, - * and some other program tries to do a serial write at the same time. - * Since the lock will only come under contention when the system is - * swapping and available memory is low, it makes sense to share one - * buffer across all the serial ports, since it significantly saves - * memory if large numbers of serial ports are open. - */ -static unsigned char *tmp_buf; - static inline int serial_paranoia_check(struct esp_struct *info, char *name, const char *routine) { @@ -1267,7 +1256,7 @@ static int rs_write(struct tty_struct * tty, if (serial_paranoia_check(info, tty->name, "rs_write")) return 0; - if (!tty || !info->xmit_buf || !tmp_buf) + if (!tty || !info->xmit_buf) return 0; while (1) { @@ -2291,11 +2280,7 @@ static int esp_open(struct tty_struct *tty, struct file * filp) tty->driver_data = info; info->tty = tty; - if (!tmp_buf) { - tmp_buf = (unsigned char *) get_zeroed_page(GFP_KERNEL); - if (!tmp_buf) - return -ENOMEM; - } + spin_unlock_irqrestore(&info->lock, flags); /* * Start up serial port @@ -2602,9 +2587,6 @@ static void __exit espserial_exit(void) free_pages((unsigned long)dma_buffer, get_order(DMA_BUFFER_SZ)); - if (tmp_buf) - free_page((unsigned long)tmp_buf); - while (free_pio_buf) { pio_buf = free_pio_buf->next; kfree(free_pio_buf); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 66a2fee06eb..ef140ebde11 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -956,22 +956,18 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data) } } else if (res->type == ACPI_RESOURCE_TYPE_EXTENDED_IRQ) { struct acpi_resource_extended_irq *irqp; - int i; + int i, irq; irqp = &res->data.extended_irq; - if (irqp->interrupt_count > 0) { - hdp->hd_nirqs = irqp->interrupt_count; - - for (i = 0; i < hdp->hd_nirqs; i++) { - int rc = - acpi_register_gsi(irqp->interrupts[i], - irqp->triggering, - irqp->polarity); - if (rc < 0) - return AE_ERROR; - hdp->hd_irq[i] = rc; - } + for (i = 0; i < irqp->interrupt_count; i++) { + irq = acpi_register_gsi(irqp->interrupts[i], + irqp->triggering, irqp->polarity); + if (irq < 0) + return AE_ERROR; + + hdp->hd_irq[hdp->hd_nirqs] = irq; + hdp->hd_nirqs++; } } diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index a23816d3e9a..e9bba94fc89 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -1841,7 +1841,6 @@ static void release_dev(struct file * filp) tty_closing = tty->count <= 1; o_tty_closing = o_tty && (o_tty->count <= (pty_master ? 1 : 0)); - up(&tty_sem); do_sleep = 0; if (tty_closing) { @@ -1869,6 +1868,7 @@ static void release_dev(struct file * filp) printk(KERN_WARNING "release_dev: %s: read/write wait queue " "active!\n", tty_name(tty, buf)); + up(&tty_sem); schedule(); } @@ -1877,8 +1877,6 @@ static void release_dev(struct file * filp) * both sides, and we've completed the last operation that could * block, so it's safe to proceed with closing. */ - - down(&tty_sem); if (pty_master) { if (--o_tty->count < 0) { printk(KERN_WARNING "release_dev: bad pty slave count " @@ -1892,7 +1890,6 @@ static void release_dev(struct file * filp) tty->count, tty_name(tty, buf)); tty->count = 0; } - up(&tty_sem); /* * We've decremented tty->count, so we need to remove this file @@ -1937,6 +1934,8 @@ static void release_dev(struct file * filp) read_unlock(&tasklist_lock); } + up(&tty_sem); + /* check whether both sides are closing ... */ if (!tty_closing || (o_tty && !o_tty_closing)) return; diff --git a/drivers/ide/pci/sgiioc4.c b/drivers/ide/pci/sgiioc4.c index 2b286e86516..43b96e29836 100644 --- a/drivers/ide/pci/sgiioc4.c +++ b/drivers/ide/pci/sgiioc4.c @@ -13,11 +13,6 @@ * License along with this program; if not, write the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. * - * Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, - * Mountain View, CA 94043, or: - * - * http://www.sgi.com - * * For further information regarding this notice, see: * * http://oss.sgi.com/projects/GenInfo/NoticeExplan diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index d393b504bf2..c82f47a66e4 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -665,7 +665,15 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv, struct ib_wc mad_wc; struct ib_send_wr *send_wr = &mad_send_wr->send_wr; - if (!smi_handle_dr_smp_send(smp, device->node_type, port_num)) { + /* + * Directed route handling starts if the initial LID routed part of + * a request or the ending LID routed part of a response is empty. + * If we are at the start of the LID routed part, don't update the + * hop_ptr or hop_cnt. See section 14.2.2, Vol 1 IB spec. + */ + if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) == + IB_LID_PERMISSIVE && + !smi_handle_dr_smp_send(smp, device->node_type, port_num)) { ret = -EINVAL; printk(KERN_ERR PFX "Invalid directed route\n"); goto out; diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index f9b9b93dc50..2825615ce81 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -1029,25 +1029,6 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev, MTHCA_GET(size, outbox, QUERY_DEV_LIM_UAR_ENTRY_SZ_OFFSET); dev_lim->uar_scratch_entry_sz = size; - mthca_dbg(dev, "Max QPs: %d, reserved QPs: %d, entry size: %d\n", - dev_lim->max_qps, dev_lim->reserved_qps, dev_lim->qpc_entry_sz); - mthca_dbg(dev, "Max SRQs: %d, reserved SRQs: %d, entry size: %d\n", - dev_lim->max_srqs, dev_lim->reserved_srqs, dev_lim->srq_entry_sz); - mthca_dbg(dev, "Max CQs: %d, reserved CQs: %d, entry size: %d\n", - dev_lim->max_cqs, dev_lim->reserved_cqs, dev_lim->cqc_entry_sz); - mthca_dbg(dev, "Max EQs: %d, reserved EQs: %d, entry size: %d\n", - dev_lim->max_eqs, dev_lim->reserved_eqs, dev_lim->eqc_entry_sz); - mthca_dbg(dev, "reserved MPTs: %d, reserved MTTs: %d\n", - dev_lim->reserved_mrws, dev_lim->reserved_mtts); - mthca_dbg(dev, "Max PDs: %d, reserved PDs: %d, reserved UARs: %d\n", - dev_lim->max_pds, dev_lim->reserved_pds, dev_lim->reserved_uars); - mthca_dbg(dev, "Max QP/MCG: %d, reserved MGMs: %d\n", - dev_lim->max_pds, dev_lim->reserved_mgms); - mthca_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n", - dev_lim->max_cq_sz, dev_lim->max_qp_sz, dev_lim->max_srq_sz); - - mthca_dbg(dev, "Flags: %08x\n", dev_lim->flags); - if (mthca_is_memfree(dev)) { MTHCA_GET(field, outbox, QUERY_DEV_LIM_MAX_SRQ_SZ_OFFSET); dev_lim->max_srq_sz = 1 << field; @@ -1093,6 +1074,25 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev, dev_lim->mpt_entry_sz = MTHCA_MPT_ENTRY_SIZE; } + mthca_dbg(dev, "Max QPs: %d, reserved QPs: %d, entry size: %d\n", + dev_lim->max_qps, dev_lim->reserved_qps, dev_lim->qpc_entry_sz); + mthca_dbg(dev, "Max SRQs: %d, reserved SRQs: %d, entry size: %d\n", + dev_lim->max_srqs, dev_lim->reserved_srqs, dev_lim->srq_entry_sz); + mthca_dbg(dev, "Max CQs: %d, reserved CQs: %d, entry size: %d\n", + dev_lim->max_cqs, dev_lim->reserved_cqs, dev_lim->cqc_entry_sz); + mthca_dbg(dev, "Max EQs: %d, reserved EQs: %d, entry size: %d\n", + dev_lim->max_eqs, dev_lim->reserved_eqs, dev_lim->eqc_entry_sz); + mthca_dbg(dev, "reserved MPTs: %d, reserved MTTs: %d\n", + dev_lim->reserved_mrws, dev_lim->reserved_mtts); + mthca_dbg(dev, "Max PDs: %d, reserved PDs: %d, reserved UARs: %d\n", + dev_lim->max_pds, dev_lim->reserved_pds, dev_lim->reserved_uars); + mthca_dbg(dev, "Max QP/MCG: %d, reserved MGMs: %d\n", + dev_lim->max_pds, dev_lim->reserved_mgms); + mthca_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n", + dev_lim->max_cq_sz, dev_lim->max_qp_sz, dev_lim->max_srq_sz); + + mthca_dbg(dev, "Flags: %08x\n", dev_lim->flags); + out: mthca_free_mailbox(dev, mailbox); return err; diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h index 2a165fd06e5..e481037288d 100644 --- a/drivers/infiniband/hw/mthca/mthca_dev.h +++ b/drivers/infiniband/hw/mthca/mthca_dev.h @@ -53,8 +53,8 @@ #define DRV_NAME "ib_mthca" #define PFX DRV_NAME ": " -#define DRV_VERSION "0.06" -#define DRV_RELDATE "June 23, 2005" +#define DRV_VERSION "0.07" +#define DRV_RELDATE "February 13, 2006" enum { MTHCA_FLAG_DDR_HIDDEN = 1 << 1, diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index e0a5412b7e6..2f85a9a831b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -78,6 +78,7 @@ enum { IPOIB_FLAG_SUBINTERFACE = 4, IPOIB_MCAST_RUN = 5, IPOIB_STOP_REAPER = 6, + IPOIB_MCAST_STARTED = 7, IPOIB_MAX_BACKOFF_SECONDS = 16, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index ccaa0c38707..a2408d7ec59 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -533,8 +533,10 @@ void ipoib_mcast_join_task(void *dev_ptr) } if (!priv->broadcast) { - priv->broadcast = ipoib_mcast_alloc(dev, 1); - if (!priv->broadcast) { + struct ipoib_mcast *broadcast; + + broadcast = ipoib_mcast_alloc(dev, 1); + if (!broadcast) { ipoib_warn(priv, "failed to allocate broadcast group\n"); mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) @@ -544,10 +546,11 @@ void ipoib_mcast_join_task(void *dev_ptr) return; } - memcpy(priv->broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4, + spin_lock_irq(&priv->lock); + memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4, sizeof (union ib_gid)); + priv->broadcast = broadcast; - spin_lock_irq(&priv->lock); __ipoib_mcast_add(dev, priv->broadcast); spin_unlock_irq(&priv->lock); } @@ -601,6 +604,10 @@ int ipoib_mcast_start_thread(struct net_device *dev) queue_work(ipoib_workqueue, &priv->mcast_task); mutex_unlock(&mcast_mutex); + spin_lock_irq(&priv->lock); + set_bit(IPOIB_MCAST_STARTED, &priv->flags); + spin_unlock_irq(&priv->lock); + return 0; } @@ -611,6 +618,10 @@ int ipoib_mcast_stop_thread(struct net_device *dev, int flush) ipoib_dbg_mcast(priv, "stopping multicast thread\n"); + spin_lock_irq(&priv->lock); + clear_bit(IPOIB_MCAST_STARTED, &priv->flags); + spin_unlock_irq(&priv->lock); + mutex_lock(&mcast_mutex); clear_bit(IPOIB_MCAST_RUN, &priv->flags); cancel_delayed_work(&priv->mcast_task); @@ -693,6 +704,14 @@ void ipoib_mcast_send(struct net_device *dev, union ib_gid *mgid, */ spin_lock(&priv->lock); + if (!test_bit(IPOIB_MCAST_STARTED, &priv->flags) || + !priv->broadcast || + !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) { + ++priv->stats.tx_dropped; + dev_kfree_skb_any(skb); + goto unlock; + } + mcast = __ipoib_mcast_find(dev, mgid); if (!mcast) { /* Let's create a new send only group now */ @@ -754,6 +773,7 @@ out: ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN); } +unlock: spin_unlock(&priv->lock); } diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c index f190a99604f..393633681f4 100644 --- a/drivers/isdn/i4l/isdn_tty.c +++ b/drivers/isdn/i4l/isdn_tty.c @@ -2359,8 +2359,8 @@ isdn_tty_at_cout(char *msg, modem_info * info) /* use queue instead of direct, if online and */ /* data is in queue or buffer is full */ - if ((info->online && tty_buffer_request_room(tty, l) < l) || - (!skb_queue_empty(&dev->drv[info->isdn_driver]->rpqueue[info->isdn_channel]))) { + if (info->online && ((tty_buffer_request_room(tty, l) < l) || + !skb_queue_empty(&dev->drv[info->isdn_driver]->rpqueue[info->isdn_channel]))) { skb = alloc_skb(l, GFP_ATOMIC); if (!skb) { spin_unlock_irqrestore(&info->readlock, flags); diff --git a/drivers/video/neofb.c b/drivers/video/neofb.c index 747602aa561..b85e2b180a4 100644 --- a/drivers/video/neofb.c +++ b/drivers/video/neofb.c @@ -1334,6 +1334,12 @@ static int neofb_blank(int blank_mode, struct fb_info *info) struct neofb_par *par = info->par; int seqflags, lcdflags, dpmsflags, reg; + /* + * Reload the value stored in the register, might have been changed via + * FN keystroke + */ + par->PanelDispCntlReg1 = vga_rgfx(NULL, 0x20) & 0x03; + switch (blank_mode) { case FB_BLANK_POWERDOWN: /* powerdown - both sync lines down */ seqflags = VGA_SR01_SCREEN_OFF; /* Disable sequencer */ @@ -1366,7 +1372,7 @@ static int neofb_blank(int blank_mode, struct fb_info *info) case FB_BLANK_NORMAL: /* just blank screen (backlight stays on) */ seqflags = VGA_SR01_SCREEN_OFF; /* Disable sequencer */ lcdflags = par->PanelDispCntlReg1 & 0x02; /* LCD normal */ - dpmsflags = 0; /* no hsync/vsync suppression */ + dpmsflags = 0x00; /* no hsync/vsync suppression */ break; case FB_BLANK_UNBLANK: /* unblank */ seqflags = 0; /* Enable sequencer */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index d17c97d07c8..675bd256829 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1442,13 +1442,15 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data, &bytes_read, &smb_read_data, &buf_type); pSMBr = (struct smb_com_read_rsp *)smb_read_data; - if (copy_to_user(current_offset, - smb_read_data + 4 /* RFC1001 hdr */ - + le16_to_cpu(pSMBr->DataOffset), - bytes_read)) { - rc = -EFAULT; - } if (smb_read_data) { + if (copy_to_user(current_offset, + smb_read_data + + 4 /* RFC1001 length field */ + + le16_to_cpu(pSMBr->DataOffset), + bytes_read)) { + rc = -EFAULT; + } + if(buf_type == CIFS_SMALL_BUFFER) cifs_small_buf_release(smb_read_data); else if(buf_type == CIFS_LARGE_BUFFER) diff --git a/fs/exec.c b/fs/exec.c index 055378d2513..0e1c95074d4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1403,7 +1403,7 @@ static void zap_threads (struct mm_struct *mm) do_each_thread(g,p) { if (mm == p->mm && p != tsk && p->ptrace && p->parent->mm == mm) { - __ptrace_unlink(p); + __ptrace_detach(p, 0); } } while_each_thread(g,p); write_unlock_irq(&tasklist_lock); diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index e6265a0b56b..543ed543d1e 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -24,75 +24,29 @@ #include <linux/slab.h> /* - * Unlink a buffer from a transaction checkpoint list. + * Unlink a buffer from a transaction. * * Called with j_list_lock held. */ -static void __buffer_unlink_first(struct journal_head *jh) +static inline void __buffer_unlink(struct journal_head *jh) { transaction_t *transaction; transaction = jh->b_cp_transaction; + jh->b_cp_transaction = NULL; jh->b_cpnext->b_cpprev = jh->b_cpprev; jh->b_cpprev->b_cpnext = jh->b_cpnext; - if (transaction->t_checkpoint_list == jh) { + if (transaction->t_checkpoint_list == jh) transaction->t_checkpoint_list = jh->b_cpnext; - if (transaction->t_checkpoint_list == jh) - transaction->t_checkpoint_list = NULL; - } -} - -/* - * Unlink a buffer from a transaction checkpoint(io) list. - * - * Called with j_list_lock held. - */ - -static inline void __buffer_unlink(struct journal_head *jh) -{ - transaction_t *transaction; - - transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - if (transaction->t_checkpoint_io_list == jh) { - transaction->t_checkpoint_io_list = jh->b_cpnext; - if (transaction->t_checkpoint_io_list == jh) - transaction->t_checkpoint_io_list = NULL; - } -} - -/* - * Move a buffer from the checkpoint list to the checkpoint io list - * - * Called with j_list_lock held - */ - -static inline void __buffer_relink_io(struct journal_head *jh) -{ - transaction_t *transaction; - - transaction = jh->b_cp_transaction; - __buffer_unlink_first(jh); - - if (!transaction->t_checkpoint_io_list) { - jh->b_cpnext = jh->b_cpprev = jh; - } else { - jh->b_cpnext = transaction->t_checkpoint_io_list; - jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev; - jh->b_cpprev->b_cpnext = jh; - jh->b_cpnext->b_cpprev = jh; - } - transaction->t_checkpoint_io_list = jh; + if (transaction->t_checkpoint_list == jh) + transaction->t_checkpoint_list = NULL; } /* * Try to release a checkpointed buffer from its transaction. - * Returns 1 if we released it and 2 if we also released the - * whole transaction. - * + * Returns 1 if we released it. * Requires j_list_lock * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it */ @@ -103,11 +57,12 @@ static int __try_to_free_cp_buf(struct journal_head *jh) if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) { JBUFFER_TRACE(jh, "remove from checkpoint list"); - ret = __journal_remove_checkpoint(jh) + 1; + __journal_remove_checkpoint(jh); jbd_unlock_bh_state(bh); journal_remove_journal_head(bh); BUFFER_TRACE(bh, "release"); __brelse(bh); + ret = 1; } else { jbd_unlock_bh_state(bh); } @@ -162,53 +117,83 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh) } /* - * Clean up transaction's list of buffers submitted for io. - * We wait for any pending IO to complete and remove any clean - * buffers. Note that we take the buffers in the opposite ordering - * from the one in which they were submitted for IO. + * Clean up a transaction's checkpoint list. + * + * We wait for any pending IO to complete and make sure any clean + * buffers are removed from the transaction. + * + * Return 1 if we performed any actions which might have destroyed the + * checkpoint. (journal_remove_checkpoint() deletes the transaction when + * the last checkpoint buffer is cleansed) * * Called with j_list_lock held. */ - -static void __wait_cp_io(journal_t *journal, transaction_t *transaction) +static int __cleanup_transaction(journal_t *journal, transaction_t *transaction) { - struct journal_head *jh; + struct journal_head *jh, *next_jh, *last_jh; struct buffer_head *bh; - tid_t this_tid; - int released = 0; - - this_tid = transaction->t_tid; -restart: - /* Didn't somebody clean up the transaction in the meanwhile */ - if (journal->j_checkpoint_transactions != transaction || - transaction->t_tid != this_tid) - return; - while (!released && transaction->t_checkpoint_io_list) { - jh = transaction->t_checkpoint_io_list; + int ret = 0; + + assert_spin_locked(&journal->j_list_lock); + jh = transaction->t_checkpoint_list; + if (!jh) + return 0; + + last_jh = jh->b_cpprev; + next_jh = jh; + do { + jh = next_jh; bh = jh2bh(jh); - if (!jbd_trylock_bh_state(bh)) { - jbd_sync_bh(journal, bh); - spin_lock(&journal->j_list_lock); - goto restart; - } if (buffer_locked(bh)) { atomic_inc(&bh->b_count); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); __brelse(bh); - spin_lock(&journal->j_list_lock); - goto restart; + goto out_return_1; } + /* - * Now in whatever state the buffer currently is, we know that - * it has been written out and so we can drop it from the list + * This is foul */ - released = __journal_remove_checkpoint(jh); - jbd_unlock_bh_state(bh); - } + if (!jbd_trylock_bh_state(bh)) { + jbd_sync_bh(journal, bh); + goto out_return_1; + } + + if (jh->b_transaction != NULL) { + transaction_t *t = jh->b_transaction; + tid_t tid = t->t_tid; + + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + log_start_commit(journal, tid); + log_wait_commit(journal, tid); + goto out_return_1; + } + + /* + * AKPM: I think the buffer_jbddirty test is redundant - it + * shouldn't have NULL b_transaction? + */ + next_jh = jh->b_cpnext; + if (!buffer_dirty(bh) && !buffer_jbddirty(bh)) { + BUFFER_TRACE(bh, "remove from checkpoint"); + __journal_remove_checkpoint(jh); + jbd_unlock_bh_state(bh); + journal_remove_journal_head(bh); + __brelse(bh); + ret = 1; + } else { + jbd_unlock_bh_state(bh); + } + } while (jh != last_jh); + + return ret; +out_return_1: + spin_lock(&journal->j_list_lock); + return 1; } #define NR_BATCH 64 @@ -218,7 +203,9 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) { int i; + spin_unlock(&journal->j_list_lock); ll_rw_block(SWRITE, *batch_count, bhs); + spin_lock(&journal->j_list_lock); for (i = 0; i < *batch_count; i++) { struct buffer_head *bh = bhs[i]; clear_buffer_jwrite(bh); @@ -234,46 +221,19 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) * Return 1 if something happened which requires us to abort the current * scan of the checkpoint list. * - * Called with j_list_lock held and drops it if 1 is returned + * Called with j_list_lock held. * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it */ -static int __process_buffer(journal_t *journal, struct journal_head *jh, - struct buffer_head **bhs, int *batch_count) +static int __flush_buffer(journal_t *journal, struct journal_head *jh, + struct buffer_head **bhs, int *batch_count, + int *drop_count) { struct buffer_head *bh = jh2bh(jh); int ret = 0; - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - put_bh(bh); - ret = 1; - } - else if (jh->b_transaction != NULL) { - transaction_t *t = jh->b_transaction; - tid_t tid = t->t_tid; + if (buffer_dirty(bh) && !buffer_locked(bh) && jh->b_jlist == BJ_None) { + J_ASSERT_JH(jh, jh->b_transaction == NULL); - spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - log_start_commit(journal, tid); - log_wait_commit(journal, tid); - ret = 1; - } - else if (!buffer_dirty(bh)) { - J_ASSERT_JH(jh, !buffer_jbddirty(bh)); - BUFFER_TRACE(bh, "remove from checkpoint"); - __journal_remove_checkpoint(jh); - spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - journal_remove_journal_head(bh); - put_bh(bh); - ret = 1; - } - else { /* * Important: we are about to write the buffer, and * possibly block, while still holding the journal lock. @@ -286,30 +246,45 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, J_ASSERT_BH(bh, !buffer_jwrite(bh)); set_buffer_jwrite(bh); bhs[*batch_count] = bh; - __buffer_relink_io(jh); jbd_unlock_bh_state(bh); (*batch_count)++; if (*batch_count == NR_BATCH) { - spin_unlock(&journal->j_list_lock); __flush_batch(journal, bhs, batch_count); ret = 1; } + } else { + int last_buffer = 0; + if (jh->b_cpnext == jh) { + /* We may be about to drop the transaction. Tell the + * caller that the lists have changed. + */ + last_buffer = 1; + } + if (__try_to_free_cp_buf(jh)) { + (*drop_count)++; + ret = last_buffer; + } } return ret; } /* - * Perform an actual checkpoint. We take the first transaction on the - * list of transactions to be checkpointed and send all its buffers - * to disk. We submit larger chunks of data at once. + * Perform an actual checkpoint. We don't write out only enough to + * satisfy the current blocked requests: rather we submit a reasonably + * sized chunk of the outstanding data to disk at once for + * efficiency. __log_wait_for_space() will retry if we didn't free enough. * + * However, we _do_ take into account the amount requested so that once + * the IO has been queued, we can return as soon as enough of it has + * completed to disk. + * * The journal should be locked before calling this function. */ int log_do_checkpoint(journal_t *journal) { - transaction_t *transaction; - tid_t this_tid; int result; + int batch_count = 0; + struct buffer_head *bhs[NR_BATCH]; jbd_debug(1, "Start checkpoint\n"); @@ -324,70 +299,79 @@ int log_do_checkpoint(journal_t *journal) return result; /* - * OK, we need to start writing disk blocks. Take one transaction - * and write it. + * OK, we need to start writing disk blocks. Try to free up a + * quarter of the log in a single checkpoint if we can. */ - spin_lock(&journal->j_list_lock); - if (!journal->j_checkpoint_transactions) - goto out; - transaction = journal->j_checkpoint_transactions; - this_tid = transaction->t_tid; -restart: /* - * If someone cleaned up this transaction while we slept, we're - * done (maybe it's a new transaction, but it fell at the same - * address). + * AKPM: check this code. I had a feeling a while back that it + * degenerates into a busy loop at unmount time. */ - if (journal->j_checkpoint_transactions == transaction && - transaction->t_tid == this_tid) { - int batch_count = 0; - struct buffer_head *bhs[NR_BATCH]; - struct journal_head *jh; - int retry = 0; - - while (!retry && transaction->t_checkpoint_list) { + spin_lock(&journal->j_list_lock); + while (journal->j_checkpoint_transactions) { + transaction_t *transaction; + struct journal_head *jh, *last_jh, *next_jh; + int drop_count = 0; + int cleanup_ret, retry = 0; + tid_t this_tid; + + transaction = journal->j_checkpoint_transactions; + this_tid = transaction->t_tid; + jh = transaction->t_checkpoint_list; + last_jh = jh->b_cpprev; + next_jh = jh; + do { struct buffer_head *bh; - jh = transaction->t_checkpoint_list; + jh = next_jh; + next_jh = jh->b_cpnext; bh = jh2bh(jh); if (!jbd_trylock_bh_state(bh)) { jbd_sync_bh(journal, bh); + spin_lock(&journal->j_list_lock); retry = 1; break; } - retry = __process_buffer(journal, jh, bhs, - &batch_count); - if (!retry && - lock_need_resched(&journal->j_list_lock)) { - spin_unlock(&journal->j_list_lock); + retry = __flush_buffer(journal, jh, bhs, &batch_count, &drop_count); + if (cond_resched_lock(&journal->j_list_lock)) { retry = 1; break; } - } + } while (jh != last_jh && !retry); if (batch_count) { - if (!retry) { - spin_unlock(&journal->j_list_lock); - retry = 1; - } __flush_batch(journal, bhs, &batch_count); + retry = 1; } - if (retry) { - spin_lock(&journal->j_list_lock); - goto restart; - } /* - * Now we have cleaned up the first transaction's checkpoint - * list. Let's clean up the second one. + * If someone cleaned up this transaction while we slept, we're + * done + */ + if (journal->j_checkpoint_transactions != transaction) + break; + if (retry) + continue; + /* + * Maybe it's a new transaction, but it fell at the same + * address */ - __wait_cp_io(journal, transaction); + if (transaction->t_tid != this_tid) + continue; + /* + * We have walked the whole transaction list without + * finding anything to write to disk. We had better be + * able to make some progress or we are in trouble. + */ + cleanup_ret = __cleanup_transaction(journal, transaction); + J_ASSERT(drop_count != 0 || cleanup_ret != 0); + if (journal->j_checkpoint_transactions != transaction) + break; } -out: spin_unlock(&journal->j_list_lock); result = cleanup_journal_tail(journal); if (result < 0) return result; + return 0; } @@ -472,91 +456,52 @@ int cleanup_journal_tail(journal_t *journal) /* Checkpoint list management */ /* - * journal_clean_one_cp_list - * - * Find all the written-back checkpoint buffers in the given list and release them. - * - * Called with the journal locked. - * Called with j_list_lock held. - * Returns number of bufers reaped (for debug) - */ - -static int journal_clean_one_cp_list(struct journal_head *jh, int *released) -{ - struct journal_head *last_jh; - struct journal_head *next_jh = jh; - int ret, freed = 0; - - *released = 0; - if (!jh) - return 0; - - last_jh = jh->b_cpprev; - do { - jh = next_jh; - next_jh = jh->b_cpnext; - /* Use trylock because of the ranking */ - if (jbd_trylock_bh_state(jh2bh(jh))) { - ret = __try_to_free_cp_buf(jh); - if (ret) { - freed++; - if (ret == 2) { - *released = 1; - return freed; - } - } - } - /* - * This function only frees up some memory if possible so we - * dont have an obligation to finish processing. Bail out if - * preemption requested: - */ - if (need_resched()) - return freed; - } while (jh != last_jh); - - return freed; -} - -/* * journal_clean_checkpoint_list * * Find all the written-back checkpoint buffers in the journal and release them. * * Called with the journal locked. * Called with j_list_lock held. - * Returns number of buffers reaped (for debug) + * Returns number of bufers reaped (for debug) */ int __journal_clean_checkpoint_list(journal_t *journal) { transaction_t *transaction, *last_transaction, *next_transaction; - int ret = 0, released; + int ret = 0; transaction = journal->j_checkpoint_transactions; - if (!transaction) + if (transaction == 0) goto out; last_transaction = transaction->t_cpprev; next_transaction = transaction; do { + struct journal_head *jh; + transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret += journal_clean_one_cp_list(transaction-> - t_checkpoint_list, &released); - if (need_resched()) - goto out; - if (released) - continue; - /* - * It is essential that we are as careful as in the case of - * t_checkpoint_list with removing the buffer from the list as - * we can possibly see not yet submitted buffers on io_list - */ - ret += journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list, &released); - if (need_resched()) - goto out; + jh = transaction->t_checkpoint_list; + if (jh) { + struct journal_head *last_jh = jh->b_cpprev; + struct journal_head *next_jh = jh; + + do { + jh = next_jh; + next_jh = jh->b_cpnext; + /* Use trylock because of the ranknig */ + if (jbd_trylock_bh_state(jh2bh(jh))) + ret += __try_to_free_cp_buf(jh); + /* + * This function only frees up some memory + * if possible so we dont have an obligation + * to finish processing. Bail out if preemption + * requested: + */ + if (need_resched()) + goto out; + } while (jh != last_jh); + } } while (transaction != last_transaction); out: return ret; @@ -571,22 +516,18 @@ out: * buffer updates committed in that transaction have safely been stored * elsewhere on disk. To achieve this, all of the buffers in a * transaction need to be maintained on the transaction's checkpoint - * lists until they have been rewritten, at which point this function is + * list until they have been rewritten, at which point this function is * called to remove the buffer from the existing transaction's - * checkpoint lists. - * - * The function returns 1 if it frees the transaction, 0 otherwise. + * checkpoint list. * * This function is called with the journal locked. * This function is called with j_list_lock held. - * This function is called with jbd_lock_bh_state(jh2bh(jh)) */ -int __journal_remove_checkpoint(struct journal_head *jh) +void __journal_remove_checkpoint(struct journal_head *jh) { transaction_t *transaction; journal_t *journal; - int ret = 0; JBUFFER_TRACE(jh, "entry"); @@ -597,10 +538,8 @@ int __journal_remove_checkpoint(struct journal_head *jh) journal = transaction->t_journal; __buffer_unlink(jh); - jh->b_cp_transaction = NULL; - if (transaction->t_checkpoint_list != NULL || - transaction->t_checkpoint_io_list != NULL) + if (transaction->t_checkpoint_list != NULL) goto out; JBUFFER_TRACE(jh, "transaction has no more buffers"); @@ -626,10 +565,8 @@ int __journal_remove_checkpoint(struct journal_head *jh) /* Just in case anybody was waiting for more transactions to be checkpointed... */ wake_up(&journal->j_wait_logspace); - ret = 1; out: JBUFFER_TRACE(jh, "exit"); - return ret; } /* @@ -691,7 +628,6 @@ void __journal_drop_transaction(journal_t *journal, transaction_t *transaction) J_ASSERT(transaction->t_shadow_list == NULL); J_ASSERT(transaction->t_log_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); - J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(transaction->t_updates == 0); J_ASSERT(journal->j_committing_transaction != transaction); J_ASSERT(journal->j_running_transaction != transaction); diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 29e62d98bae..002ad2bbc76 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -829,8 +829,7 @@ restart_loop: journal->j_committing_transaction = NULL; spin_unlock(&journal->j_state_lock); - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { + if (commit_transaction->t_checkpoint_list == NULL) { __journal_drop_transaction(journal, commit_transaction); } else { if (journal->j_checkpoint_transactions == NULL) { diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 3eaf6e70108..da6354baa0b 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -111,9 +111,10 @@ long nlmclnt_block(struct nlm_rqst *req, long timeout) /* * The server lockd has called us back to tell us the lock was granted */ -u32 -nlmclnt_grant(struct nlm_lock *lock) +u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock) { + const struct file_lock *fl = &lock->fl; + const struct nfs_fh *fh = &lock->fh; struct nlm_wait *block; u32 res = nlm_lck_denied; @@ -122,14 +123,20 @@ nlmclnt_grant(struct nlm_lock *lock) * Warning: must not use cookie to match it! */ list_for_each_entry(block, &nlm_blocked, b_list) { - if (nlm_compare_locks(block->b_lock, &lock->fl)) { - /* Alright, we found a lock. Set the return status - * and wake up the caller - */ - block->b_status = NLM_LCK_GRANTED; - wake_up(&block->b_wait); - res = nlm_granted; - } + struct file_lock *fl_blocked = block->b_lock; + + if (!nlm_compare_locks(fl_blocked, fl)) + continue; + if (!nlm_cmp_addr(&block->b_host->h_addr, addr)) + continue; + if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_dentry->d_inode) ,fh) != 0) + continue; + /* Alright, we found a lock. Set the return status + * and wake up the caller + */ + block->b_status = NLM_LCK_GRANTED; + wake_up(&block->b_wait); + res = nlm_granted; } return res; } diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 4063095d849..b10f913aa06 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -228,7 +228,7 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); - resp->status = nlmclnt_grant(&argp->lock); + resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock); dprintk("lockd: GRANTED status %d\n", ntohl(resp->status)); return rpc_success; } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 3bc437e0cf5..35681d9cf1f 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -256,7 +256,7 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); - resp->status = nlmclnt_grant(&argp->lock); + resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock); dprintk("lockd: GRANTED status %d\n", ntohl(resp->status)); return rpc_success; } diff --git a/include/asm-alpha/mman.h b/include/asm-alpha/mman.h index f6439532a26..a21515c16a4 100644 --- a/include/asm-alpha/mman.h +++ b/include/asm-alpha/mman.h @@ -43,6 +43,8 @@ #define MADV_SPACEAVAIL 5 /* ensure resources are available */ #define MADV_DONTNEED 6 /* don't need these pages */ #define MADV_REMOVE 7 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-arm/mman.h b/include/asm-arm/mman.h index f0bebca2ac2..693ed859e63 100644 --- a/include/asm-arm/mman.h +++ b/include/asm-arm/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-arm26/mman.h b/include/asm-arm26/mman.h index 0ed7780541f..2096c50df88 100644 --- a/include/asm-arm26/mman.h +++ b/include/asm-arm26/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-cris/mman.h b/include/asm-cris/mman.h index 5a382b8bf3f..deddfb239ff 100644 --- a/include/asm-cris/mman.h +++ b/include/asm-cris/mman.h @@ -38,6 +38,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-frv/atomic.h b/include/asm-frv/atomic.h index a59f684b4f3..5d9f84bfdca 100644 --- a/include/asm-frv/atomic.h +++ b/include/asm-frv/atomic.h @@ -220,9 +220,9 @@ extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsig switch (sizeof(__xg_orig)) { \ case 4: \ asm volatile( \ - "swap%I0 %2,%M0" \ - : "+m"(*__xg_ptr), "=&r"(__xg_orig) \ - : "r"(x) \ + "swap%I0 %M0,%1" \ + : "+m"(*__xg_ptr), "=r"(__xg_orig) \ + : "1"(x) \ : "memory" \ ); \ break; \ diff --git a/include/asm-frv/cacheflush.h b/include/asm-frv/cacheflush.h index 3007deccb49..eaa5826bc1c 100644 --- a/include/asm-frv/cacheflush.h +++ b/include/asm-frv/cacheflush.h @@ -87,5 +87,17 @@ static inline void flush_icache_page(struct vm_area_struct *vma, struct page *pa flush_icache_user_range(vma, page, page_to_phys(page), PAGE_SIZE); } +/* + * permit ptrace to access another process's address space through the icache + * and the dcache + */ +#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ +do { \ + memcpy((dst), (src), (len)); \ + flush_icache_user_range((vma), (page), (vaddr), (len)); \ +} while(0) + +#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ + memcpy((dst), (src), (len)) #endif /* _ASM_CACHEFLUSH_H */ diff --git a/include/asm-frv/io.h b/include/asm-frv/io.h index 075369b1a34..01247cb2bc3 100644 --- a/include/asm-frv/io.h +++ b/include/asm-frv/io.h @@ -251,7 +251,6 @@ static inline void writel(uint32_t datum, volatile void __iomem *addr) #define IOMAP_WRITETHROUGH 3 extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag); -extern void __iounmap(void __iomem *addr, unsigned long size); static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size) { diff --git a/include/asm-frv/mman.h b/include/asm-frv/mman.h index 8af4a41c255..d3bca306da8 100644 --- a/include/asm-frv/mman.h +++ b/include/asm-frv/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-frv/spr-regs.h b/include/asm-frv/spr-regs.h index ef472f058d9..c2a541ef828 100644 --- a/include/asm-frv/spr-regs.h +++ b/include/asm-frv/spr-regs.h @@ -98,6 +98,7 @@ #define TBR_TT_TRAP0 (0x80 << 4) #define TBR_TT_TRAP1 (0x81 << 4) #define TBR_TT_TRAP2 (0x82 << 4) +#define TBR_TT_TRAP3 (0x83 << 4) #define TBR_TT_TRAP126 (0xfe << 4) #define TBR_TT_BREAK (0xff << 4) diff --git a/include/asm-frv/system.h b/include/asm-frv/system.h index d2aea70a5f6..f72ff0c4dc0 100644 --- a/include/asm-frv/system.h +++ b/include/asm-frv/system.h @@ -40,8 +40,84 @@ do { \ /* * interrupt flag manipulation + * - use virtual interrupt management since touching the PSR is slow + * - ICC2.Z: T if interrupts virtually disabled + * - ICC2.C: F if interrupts really disabled + * - if Z==1 upon interrupt: + * - C is set to 0 + * - interrupts are really disabled + * - entry.S returns immediately + * - uses TIHI (TRAP if Z==0 && C==0) #2 to really reenable interrupts + * - if taken, the trap: + * - sets ICC2.C + * - enables interrupts */ -#define local_irq_disable() \ +#define local_irq_disable() \ +do { \ + /* set Z flag, but don't change the C flag */ \ + asm volatile(" andcc gr0,gr0,gr0,icc2 \n" \ + : \ + : \ + : "memory", "icc2" \ + ); \ +} while(0) + +#define local_irq_enable() \ +do { \ + /* clear Z flag and then test the C flag */ \ + asm volatile(" oricc gr0,#1,gr0,icc2 \n" \ + " tihi icc2,gr0,#2 \n" \ + : \ + : \ + : "memory", "icc2" \ + ); \ +} while(0) + +#define local_save_flags(flags) \ +do { \ + typecheck(unsigned long, flags); \ + asm volatile("movsg ccr,%0" \ + : "=r"(flags) \ + : \ + : "memory"); \ + \ + /* shift ICC2.Z to bit 0 */ \ + flags >>= 26; \ + \ + /* make flags 1 if interrupts disabled, 0 otherwise */ \ + flags &= 1UL; \ +} while(0) + +#define irqs_disabled() \ + ({unsigned long flags; local_save_flags(flags); flags; }) + +#define local_irq_save(flags) \ +do { \ + typecheck(unsigned long, flags); \ + local_save_flags(flags); \ + local_irq_disable(); \ +} while(0) + +#define local_irq_restore(flags) \ +do { \ + typecheck(unsigned long, flags); \ + \ + /* load the Z flag by turning 1 if disabled into 0 if disabled \ + * and thus setting the Z flag but not the C flag */ \ + asm volatile(" xoricc %0,#1,gr0,icc2 \n" \ + /* then test Z=0 and C=0 */ \ + " tihi icc2,gr0,#2 \n" \ + : \ + : "r"(flags) \ + : "memory", "icc2" \ + ); \ + \ +} while(0) + +/* + * real interrupt flag manipulation + */ +#define __local_irq_disable() \ do { \ unsigned long psr; \ asm volatile(" movsg psr,%0 \n" \ @@ -53,7 +129,7 @@ do { \ : "memory"); \ } while(0) -#define local_irq_enable() \ +#define __local_irq_enable() \ do { \ unsigned long psr; \ asm volatile(" movsg psr,%0 \n" \ @@ -64,7 +140,7 @@ do { \ : "memory"); \ } while(0) -#define local_save_flags(flags) \ +#define __local_save_flags(flags) \ do { \ typecheck(unsigned long, flags); \ asm("movsg psr,%0" \ @@ -73,7 +149,7 @@ do { \ : "memory"); \ } while(0) -#define local_irq_save(flags) \ +#define __local_irq_save(flags) \ do { \ unsigned long npsr; \ typecheck(unsigned long, flags); \ @@ -86,7 +162,7 @@ do { \ : "memory"); \ } while(0) -#define local_irq_restore(flags) \ +#define __local_irq_restore(flags) \ do { \ typecheck(unsigned long, flags); \ asm volatile(" movgs %0,psr \n" \ @@ -95,7 +171,7 @@ do { \ : "memory"); \ } while(0) -#define irqs_disabled() \ +#define __irqs_disabled() \ ((__get_PSR() & PSR_PIL) >= PSR_PIL_14) /* diff --git a/include/asm-frv/uaccess.h b/include/asm-frv/uaccess.h index b6bcbe01f6e..a1d14043886 100644 --- a/include/asm-frv/uaccess.h +++ b/include/asm-frv/uaccess.h @@ -306,7 +306,4 @@ extern long strnlen_user(const char *src, long count); extern unsigned long search_exception_table(unsigned long addr); -#define copy_to_user_page(vma, page, vaddr, dst, src, len) memcpy(dst, src, len) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) memcpy(dst, src, len) - #endif /* _ASM_UACCESS_H */ diff --git a/include/asm-frv/unistd.h b/include/asm-frv/unistd.h index 4d994d2e99e..322531caa48 100644 --- a/include/asm-frv/unistd.h +++ b/include/asm-frv/unistd.h @@ -295,13 +295,29 @@ #define __NR_add_key 286 #define __NR_request_key 287 #define __NR_keyctl 288 -#define __NR_vperfctr_open 289 -#define __NR_vperfctr_control (__NR_perfctr_info+1) -#define __NR_vperfctr_unlink (__NR_perfctr_info+2) -#define __NR_vperfctr_iresume (__NR_perfctr_info+3) -#define __NR_vperfctr_read (__NR_perfctr_info+4) +#define __NR_ioprio_set 289 +#define __NR_ioprio_get 290 +#define __NR_inotify_init 291 +#define __NR_inotify_add_watch 292 +#define __NR_inotify_rm_watch 293 +#define __NR_migrate_pages 294 +#define __NR_openat 295 +#define __NR_mkdirat 296 +#define __NR_mknodat 297 +#define __NR_fchownat 298 +#define __NR_futimesat 299 +#define __NR_newfstatat 300 +#define __NR_unlinkat 301 +#define __NR_renameat 302 +#define __NR_linkat 303 +#define __NR_symlinkat 304 +#define __NR_readlinkat 305 +#define __NR_fchmodat 306 +#define __NR_faccessat 307 +#define __NR_pselect6 308 +#define __NR_ppoll 309 -#define NR_syscalls 294 +#define NR_syscalls 310 /* * process the return value of a syscall, consigning it to one of two possible fates diff --git a/include/asm-h8300/mman.h b/include/asm-h8300/mman.h index 744a8fb485c..ac0346f7d11 100644 --- a/include/asm-h8300/mman.h +++ b/include/asm-h8300/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-i386/mman.h b/include/asm-i386/mman.h index ba4941e6f64..ab2339a1d80 100644 --- a/include/asm-i386/mman.h +++ b/include/asm-i386/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-i386/topology.h b/include/asm-i386/topology.h index af503a122b2..aa958c6ee83 100644 --- a/include/asm-i386/topology.h +++ b/include/asm-i386/topology.h @@ -27,7 +27,7 @@ #ifndef _ASM_I386_TOPOLOGY_H #define _ASM_I386_TOPOLOGY_H -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_HT #define topology_physical_package_id(cpu) \ (phys_proc_id[cpu] == BAD_APICID ? -1 : phys_proc_id[cpu]) #define topology_core_id(cpu) \ diff --git a/include/asm-ia64/machvec_sn2.h b/include/asm-ia64/machvec_sn2.h index e1b6cd63f49..03d00faf03b 100644 --- a/include/asm-ia64/machvec_sn2.h +++ b/include/asm-ia64/machvec_sn2.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2002-2003 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2002-2003, 2006 Silicon Graphics, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -20,11 +20,6 @@ * License along with this program; if not, write the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. * - * Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, - * Mountain View, CA 94043, or: - * - * http://www.sgi.com - * * For further information regarding this notice, see: * * http://oss.sgi.com/projects/GenInfo/NoticeExplan diff --git a/include/asm-ia64/mman.h b/include/asm-ia64/mman.h index 828beb24a20..357ebb780cc 100644 --- a/include/asm-ia64/mman.h +++ b/include/asm-ia64/mman.h @@ -44,6 +44,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-ia64/sn/arch.h b/include/asm-ia64/sn/arch.h index 1a3831c04af..91c31be87b1 100644 --- a/include/asm-ia64/sn/arch.h +++ b/include/asm-ia64/sn/arch.h @@ -70,7 +70,7 @@ DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info); * Compact node ID to nasid mappings kept in the per-cpu data areas of each * cpu. */ -DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_NUMNODES]); +DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]); #define sn_cnodeid_to_nasid (&__get_cpu_var(__sn_cnodeid_to_nasid[0])) diff --git a/include/asm-ia64/sn/bte.h b/include/asm-ia64/sn/bte.h index 01e5b410323..5335d87ca5f 100644 --- a/include/asm-ia64/sn/bte.h +++ b/include/asm-ia64/sn/bte.h @@ -46,7 +46,7 @@ #define BTES_PER_NODE (is_shub2() ? 4 : 2) #define MAX_BTES_PER_NODE 4 -#define BTE2OFF_CTRL (0) +#define BTE2OFF_CTRL 0 #define BTE2OFF_SRC (SH2_BT_ENG_SRC_ADDR_0 - SH2_BT_ENG_CSR_0) #define BTE2OFF_DEST (SH2_BT_ENG_DEST_ADDR_0 - SH2_BT_ENG_CSR_0) #define BTE2OFF_NOTIFY (SH2_BT_ENG_NOTIF_ADDR_0 - SH2_BT_ENG_CSR_0) @@ -75,11 +75,11 @@ : base + (BTEOFF_NOTIFY/8)) /* Define hardware modes */ -#define BTE_NOTIFY (IBCT_NOTIFY) +#define BTE_NOTIFY IBCT_NOTIFY #define BTE_NORMAL BTE_NOTIFY #define BTE_ZERO_FILL (BTE_NOTIFY | IBCT_ZFIL_MODE) /* Use a reserved bit to let the caller specify a wait for any BTE */ -#define BTE_WACQUIRE (0x4000) +#define BTE_WACQUIRE 0x4000 /* Use the BTE on the node with the destination memory */ #define BTE_USE_DEST (BTE_WACQUIRE << 1) /* Use any available BTE interface on any node for the transfer */ diff --git a/include/asm-ia64/sn/pcibr_provider.h b/include/asm-ia64/sn/pcibr_provider.h index 9334078b089..a601d3af39b 100644 --- a/include/asm-ia64/sn/pcibr_provider.h +++ b/include/asm-ia64/sn/pcibr_provider.h @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 1992-1997,2000-2004 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 1992-1997,2000-2006 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_IA64_SN_PCI_PCIBR_PROVIDER_H #define _ASM_IA64_SN_PCI_PCIBR_PROVIDER_H @@ -115,18 +115,6 @@ struct pcibus_info { spinlock_t pbi_lock; }; -/* - * pcibus_info structure locking macros - */ -inline static unsigned long -pcibr_lock(struct pcibus_info *pcibus_info) -{ - unsigned long flag; - spin_lock_irqsave(&pcibus_info->pbi_lock, flag); - return(flag); -} -#define pcibr_unlock(pcibus_info, flag) spin_unlock_irqrestore(&pcibus_info->pbi_lock, flag) - extern int pcibr_init_provider(void); extern void *pcibr_bus_fixup(struct pcibus_bussoft *, struct pci_controller *); extern dma_addr_t pcibr_dma_map(struct pci_dev *, unsigned long, size_t); diff --git a/include/asm-ia64/sn/sn_feature_sets.h b/include/asm-ia64/sn/sn_feature_sets.h index 9ca642cad33..ff33e3bd3f8 100644 --- a/include/asm-ia64/sn/sn_feature_sets.h +++ b/include/asm-ia64/sn/sn_feature_sets.h @@ -12,9 +12,6 @@ */ -#include <asm/types.h> -#include <asm/bitops.h> - /* --------------------- PROM Features -----------------------------*/ extern int sn_prom_feature_available(int id); diff --git a/include/asm-ia64/sn/xpc.h b/include/asm-ia64/sn/xpc.h index 0c36928ffd8..df7f5f4f3cd 100644 --- a/include/asm-ia64/sn/xpc.h +++ b/include/asm-ia64/sn/xpc.h @@ -508,19 +508,24 @@ struct xpc_channel { #define XPC_C_OPENREQUEST 0x00000010 /* local open channel request */ #define XPC_C_SETUP 0x00000020 /* channel's msgqueues are alloc'd */ -#define XPC_C_CONNECTCALLOUT 0x00000040 /* channel connected callout made */ -#define XPC_C_CONNECTED 0x00000080 /* local channel is connected */ -#define XPC_C_CONNECTING 0x00000100 /* channel is being connected */ - -#define XPC_C_RCLOSEREPLY 0x00000200 /* remote close channel reply */ -#define XPC_C_CLOSEREPLY 0x00000400 /* local close channel reply */ -#define XPC_C_RCLOSEREQUEST 0x00000800 /* remote close channel request */ -#define XPC_C_CLOSEREQUEST 0x00001000 /* local close channel request */ - -#define XPC_C_DISCONNECTED 0x00002000 /* channel is disconnected */ -#define XPC_C_DISCONNECTING 0x00004000 /* channel is being disconnected */ -#define XPC_C_DISCONNECTCALLOUT 0x00008000 /* chan disconnected callout made */ -#define XPC_C_WDISCONNECT 0x00010000 /* waiting for channel disconnect */ +#define XPC_C_CONNECTEDCALLOUT 0x00000040 /* connected callout initiated */ +#define XPC_C_CONNECTEDCALLOUT_MADE \ + 0x00000080 /* connected callout completed */ +#define XPC_C_CONNECTED 0x00000100 /* local channel is connected */ +#define XPC_C_CONNECTING 0x00000200 /* channel is being connected */ + +#define XPC_C_RCLOSEREPLY 0x00000400 /* remote close channel reply */ +#define XPC_C_CLOSEREPLY 0x00000800 /* local close channel reply */ +#define XPC_C_RCLOSEREQUEST 0x00001000 /* remote close channel request */ +#define XPC_C_CLOSEREQUEST 0x00002000 /* local close channel request */ + +#define XPC_C_DISCONNECTED 0x00004000 /* channel is disconnected */ +#define XPC_C_DISCONNECTING 0x00008000 /* channel is being disconnected */ +#define XPC_C_DISCONNECTINGCALLOUT \ + 0x00010000 /* disconnecting callout initiated */ +#define XPC_C_DISCONNECTINGCALLOUT_MADE \ + 0x00020000 /* disconnecting callout completed */ +#define XPC_C_WDISCONNECT 0x00040000 /* waiting for channel disconnect */ diff --git a/include/asm-ia64/timex.h b/include/asm-ia64/timex.h index 414aae06044..05a6baf8a47 100644 --- a/include/asm-ia64/timex.h +++ b/include/asm-ia64/timex.h @@ -15,6 +15,8 @@ typedef unsigned long cycles_t; +extern void (*ia64_udelay)(unsigned long usecs); + /* * For performance reasons, we don't want to define CLOCK_TICK_TRATE as * local_cpu_data->itc_rate. Fortunately, we don't have to, either: according to George diff --git a/include/asm-m32r/mman.h b/include/asm-m32r/mman.h index 12e29747bc8..6b02fe3fcff 100644 --- a/include/asm-m32r/mman.h +++ b/include/asm-m32r/mman.h @@ -38,6 +38,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-m68k/mman.h b/include/asm-m68k/mman.h index ea262ab88b3..efd12bc4ccb 100644 --- a/include/asm-m68k/mman.h +++ b/include/asm-m68k/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-mips/cpu.h b/include/asm-mips/cpu.h index 934e063e79f..818b9a97e21 100644 --- a/include/asm-mips/cpu.h +++ b/include/asm-mips/cpu.h @@ -204,9 +204,9 @@ */ #define MIPS_CPU_ISA_I 0x00000001 #define MIPS_CPU_ISA_II 0x00000002 -#define MIPS_CPU_ISA_III 0x00000003 -#define MIPS_CPU_ISA_IV 0x00000004 -#define MIPS_CPU_ISA_V 0x00000005 +#define MIPS_CPU_ISA_III 0x00000004 +#define MIPS_CPU_ISA_IV 0x00000008 +#define MIPS_CPU_ISA_V 0x00000010 #define MIPS_CPU_ISA_M32R1 0x00000020 #define MIPS_CPU_ISA_M32R2 0x00000040 #define MIPS_CPU_ISA_M64R1 0x00000080 diff --git a/include/asm-mips/gcc/sgidefs.h b/include/asm-mips/gcc/sgidefs.h deleted file mode 100644 index 05994371a2a..00000000000 --- a/include/asm-mips/gcc/sgidefs.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * include/sgidefs.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1996 by Ralf Baechle - * - * This file is here to satisfy GCC's expectations. - */ -#ifndef __SGIDEFS_H -#define __SGIDEFS_H - -#include <asm/sgidefs.h> - -#endif /* __SGIDEFS_H */ diff --git a/include/asm-mips/mach-generic/timex.h b/include/asm-mips/mach-generic/timex.h index c6a2e5f0574..48b4cfaa0d5 100644 --- a/include/asm-mips/mach-generic/timex.h +++ b/include/asm-mips/mach-generic/timex.h @@ -3,20 +3,11 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2003 by Ralf Baechle + * Copyright (C) 2003, 2005 by Ralf Baechle */ #ifndef __ASM_MACH_GENERIC_TIMEX_H #define __ASM_MACH_GENERIC_TIMEX_H -#include <linux/config.h> - -/* - * Last remaining user of the i8254 PIC, will be converted, too ... - */ -#ifdef CONFIG_SNI_RM200_PCI -#define CLOCK_TICK_RATE 1193182 -#else #define CLOCK_TICK_RATE 500000 -#endif #endif /* __ASM_MACH_GENERIC_TIMEX_H */ diff --git a/include/asm-mips/mach-rm200/timex.h b/include/asm-mips/mach-rm200/timex.h new file mode 100644 index 00000000000..11ff6cb0f21 --- /dev/null +++ b/include/asm-mips/mach-rm200/timex.h @@ -0,0 +1,13 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2003, 2005 by Ralf Baechle + */ +#ifndef __ASM_MACH_RM200_TIMEX_H +#define __ASM_MACH_RM200_TIMEX_H + +#define CLOCK_TICK_RATE 1193182 + +#endif /* __ASM_MACH_RM200_TIMEX_H */ diff --git a/include/asm-mips/mman.h b/include/asm-mips/mman.h index dd17c8bd62a..6d01e26830f 100644 --- a/include/asm-mips/mman.h +++ b/include/asm-mips/mman.h @@ -66,6 +66,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-mips/r4kcache.h b/include/asm-mips/r4kcache.h index cc53196efa4..9632c27dad1 100644 --- a/include/asm-mips/r4kcache.h +++ b/include/asm-mips/r4kcache.h @@ -14,6 +14,7 @@ #include <asm/asm.h> #include <asm/cacheops.h> +#include <asm/cpu-features.h> /* * This macro return a properly sign-extended address suitable as base address @@ -78,22 +79,25 @@ static inline void flush_scache_line(unsigned long addr) cache_op(Hit_Writeback_Inv_SD, addr); } +#define protected_cache_op(op,addr) \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set noreorder \n" \ + " .set mips3 \n" \ + "1: cache %0, (%1) \n" \ + "2: .set pop \n" \ + " .section __ex_table,\"a\" \n" \ + " "STR(PTR)" 1b, 2b \n" \ + " .previous" \ + : \ + : "i" (op), "r" (addr)) + /* * The next two are for badland addresses like signal trampolines. */ static inline void protected_flush_icache_line(unsigned long addr) { - __asm__ __volatile__( - " .set push \n" - " .set noreorder \n" - " .set mips3 \n" - "1: cache %0, (%1) \n" - "2: .set pop \n" - " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 2b \n" - " .previous" - : - : "i" (Hit_Invalidate_I), "r" (addr)); + protected_cache_op(Hit_Invalidate_I, addr); } /* @@ -104,32 +108,12 @@ static inline void protected_flush_icache_line(unsigned long addr) */ static inline void protected_writeback_dcache_line(unsigned long addr) { - __asm__ __volatile__( - " .set push \n" - " .set noreorder \n" - " .set mips3 \n" - "1: cache %0, (%1) \n" - "2: .set pop \n" - " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 2b \n" - " .previous" - : - : "i" (Hit_Writeback_Inv_D), "r" (addr)); + protected_cache_op(Hit_Writeback_Inv_D, addr); } static inline void protected_writeback_scache_line(unsigned long addr) { - __asm__ __volatile__( - " .set push \n" - " .set noreorder \n" - " .set mips3 \n" - "1: cache %0, (%1) \n" - "2: .set pop \n" - " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 2b \n" - " .previous" - : - : "i" (Hit_Writeback_Inv_SD), "r" (addr)); + protected_cache_op(Hit_Writeback_Inv_SD, addr); } /* @@ -295,4 +279,28 @@ __BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64) __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64) __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128) +/* build blast_xxx_range, protected_blast_xxx_range */ +#define __BUILD_BLAST_CACHE_RANGE(pfx, desc, hitop, prot) \ +static inline void prot##blast_##pfx##cache##_range(unsigned long start, \ + unsigned long end) \ +{ \ + unsigned long lsize = cpu_##desc##_line_size(); \ + unsigned long addr = start & ~(lsize - 1); \ + unsigned long aend = (end - 1) & ~(lsize - 1); \ + while (1) { \ + prot##cache_op(hitop, addr); \ + if (addr == aend) \ + break; \ + addr += lsize; \ + } \ +} + +__BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, protected_) +__BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, protected_) +__BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I, protected_) +__BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, ) +__BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, ) +/* blast_inv_dcache_range */ +__BUILD_BLAST_CACHE_RANGE(inv_d, dcache, Hit_Invalidate_D, ) + #endif /* _ASM_R4KCACHE_H */ diff --git a/include/asm-mips/uaccess.h b/include/asm-mips/uaccess.h index 91d813a3782..7a553e9d44d 100644 --- a/include/asm-mips/uaccess.h +++ b/include/asm-mips/uaccess.h @@ -266,6 +266,8 @@ do { \ */ #define __get_user_asm_ll32(val, addr) \ { \ + unsigned long long __gu_tmp; \ + \ __asm__ __volatile__( \ "1: lw %1, (%3) \n" \ "2: lw %D1, 4(%3) \n" \ @@ -280,8 +282,9 @@ do { \ " " __UA_ADDR " 1b, 4b \n" \ " " __UA_ADDR " 2b, 4b \n" \ " .previous \n" \ - : "=r" (__gu_err), "=&r" (val) \ + : "=r" (__gu_err), "=&r" (__gu_tmp) \ : "0" (0), "r" (addr), "i" (-EFAULT)); \ + (val) = __gu_tmp; \ } /* diff --git a/include/asm-mips/unistd.h b/include/asm-mips/unistd.h index e7ff9b18778..769305d2010 100644 --- a/include/asm-mips/unistd.h +++ b/include/asm-mips/unistd.h @@ -1184,10 +1184,8 @@ type name (atype a,btype b,ctype c,dtype d,etype e,ftype f) \ #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -# ifndef __mips64 -# define __ARCH_WANT_STAT64 -# endif # ifdef CONFIG_32BIT +# define __ARCH_WANT_STAT64 # define __ARCH_WANT_SYS_TIME # endif # ifdef CONFIG_MIPS32_O32 diff --git a/include/asm-parisc/mman.h b/include/asm-parisc/mman.h index 736b0abcac0..a381cf5c8f5 100644 --- a/include/asm-parisc/mman.h +++ b/include/asm-parisc/mman.h @@ -49,6 +49,8 @@ #define MADV_4M_PAGES 22 /* Use 4 Megabyte pages */ #define MADV_16M_PAGES 24 /* Use 16 Megabyte pages */ #define MADV_64M_PAGES 26 /* Use 64 Megabyte pages */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-powerpc/mman.h b/include/asm-powerpc/mman.h index a2e34c21b44..fcff25d13f1 100644 --- a/include/asm-powerpc/mman.h +++ b/include/asm-powerpc/mman.h @@ -45,6 +45,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-s390/mman.h b/include/asm-s390/mman.h index c8d5409b5d5..d41ca147701 100644 --- a/include/asm-s390/mman.h +++ b/include/asm-s390/mman.h @@ -44,6 +44,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-sh/mman.h b/include/asm-sh/mman.h index 693bd55a371..0e08d0573ab 100644 --- a/include/asm-sh/mman.h +++ b/include/asm-sh/mman.h @@ -36,6 +36,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-sparc/mman.h b/include/asm-sparc/mman.h index 98435ad8619..4a298b2be85 100644 --- a/include/asm-sparc/mman.h +++ b/include/asm-sparc/mman.h @@ -55,6 +55,8 @@ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_FREE 0x5 /* (Solaris) contents can be freed */ #define MADV_REMOVE 0x6 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-sparc64/mman.h b/include/asm-sparc64/mman.h index cb4b6156194..d705ec92da8 100644 --- a/include/asm-sparc64/mman.h +++ b/include/asm-sparc64/mman.h @@ -55,6 +55,8 @@ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_FREE 0x5 /* (Solaris) contents can be freed */ #define MADV_REMOVE 0x6 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-v850/mman.h b/include/asm-v850/mman.h index edc79965193..7b851c310e4 100644 --- a/include/asm-v850/mman.h +++ b/include/asm-v850/mman.h @@ -33,6 +33,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-x86_64/mman.h b/include/asm-x86_64/mman.h index d0e97b74f73..b699a38c1c3 100644 --- a/include/asm-x86_64/mman.h +++ b/include/asm-x86_64/mman.h @@ -37,6 +37,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/asm-xtensa/mman.h b/include/asm-xtensa/mman.h index 082a7504925..e2d7afb679c 100644 --- a/include/asm-xtensa/mman.h +++ b/include/asm-xtensa/mman.h @@ -73,6 +73,8 @@ #define MADV_WILLNEED 0x3 /* pre-fault pages */ #define MADV_DONTNEED 0x4 /* discard these pages */ #define MADV_REMOVE 0x5 /* remove these pages & resources */ +#define MADV_DONTFORK 0x30 /* dont inherit across fork */ +#define MADV_DOFORK 0x31 /* do inherit across fork */ /* compatibility flags */ #define MAP_ANON MAP_ANONYMOUS diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 0fe4aa891dd..41ee79962bb 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -498,12 +498,6 @@ struct transaction_s struct journal_head *t_checkpoint_list; /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - - /* * Doubly-linked circular list of temporary buffers currently undergoing * IO in the log [j_list_lock] */ @@ -852,7 +846,7 @@ extern void journal_commit_transaction(journal_t *); /* Checkpoint list management */ int __journal_clean_checkpoint_list(journal_t *journal); -int __journal_remove_checkpoint(struct journal_head *); +void __journal_remove_checkpoint(struct journal_head *); void __journal_insert_checkpoint(struct journal_head *, transaction_t *); /* Buffer IO */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 920766cea79..ef21ed29603 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -149,7 +149,7 @@ struct nlm_rqst * nlmclnt_alloc_call(void); int nlmclnt_prepare_block(struct nlm_rqst *req, struct nlm_host *host, struct file_lock *fl); void nlmclnt_finish_block(struct nlm_rqst *req); long nlmclnt_block(struct nlm_rqst *req, long timeout); -u32 nlmclnt_grant(struct nlm_lock *); +u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); void nlmclnt_recovery(struct nlm_host *, u32); int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); int nlmclnt_setgrantargs(struct nlm_rqst *, struct nlm_lock *); @@ -204,7 +204,7 @@ nlmsvc_file_inode(struct nlm_file *file) * Compare two host addresses (needs modifying for ipv6) */ static __inline__ int -nlm_cmp_addr(struct sockaddr_in *sin1, struct sockaddr_in *sin2) +nlm_cmp_addr(const struct sockaddr_in *sin1, const struct sockaddr_in *sin2) { return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; } @@ -214,7 +214,7 @@ nlm_cmp_addr(struct sockaddr_in *sin1, struct sockaddr_in *sin2) * When the second lock is of type F_UNLCK, this acts like a wildcard. */ static __inline__ int -nlm_compare_locks(struct file_lock *fl1, struct file_lock *fl2) +nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { return fl1->fl_pid == fl2->fl_pid && fl1->fl_start == fl2->fl_start diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index fdc4a952734..43c09d790b8 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -79,7 +79,7 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb); - +extern int ip_xfrm_me_harder(struct sk_buff **pskb); #endif /*__KERNEL__*/ #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 9d5cd106b34..0d36750fc0f 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -84,6 +84,7 @@ extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __us extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); extern int ptrace_attach(struct task_struct *tsk); extern int ptrace_detach(struct task_struct *, unsigned int); +extern void __ptrace_detach(struct task_struct *, unsigned int); extern void ptrace_disable(struct task_struct *); extern int ptrace_check_attach(struct task_struct *task, int kill); extern int ptrace_request(struct task_struct *child, long request, long addr, long data); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c1da0269a1..b6f51e3a38e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -697,12 +697,9 @@ struct task_struct { int lock_depth; /* BKL lock depth */ -#if defined(CONFIG_SMP) - int last_waker_cpu; /* CPU that last woke this task up */ -#if defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) int oncpu; #endif -#endif int prio, static_prio; struct list_head run_list; prio_array_t *array; diff --git a/kernel/fork.c b/kernel/fork.c index 8e88b374cee..fbea12d7a94 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1123,8 +1123,8 @@ static task_t *copy_process(unsigned long clone_flags, p->real_parent = current; p->parent = p->real_parent; + spin_lock(¤t->sighand->siglock); if (clone_flags & CLONE_THREAD) { - spin_lock(¤t->sighand->siglock); /* * Important: if an exit-all has been started then * do not create this new thread - the whole thread @@ -1162,8 +1162,6 @@ static task_t *copy_process(unsigned long clone_flags, */ p->it_prof_expires = jiffies_to_cputime(1); } - - spin_unlock(¤t->sighand->siglock); } /* @@ -1175,8 +1173,6 @@ static task_t *copy_process(unsigned long clone_flags, if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); - attach_pid(p, PIDTYPE_PID, p->pid); - attach_pid(p, PIDTYPE_TGID, p->tgid); if (thread_group_leader(p)) { p->signal->tty = current->signal->tty; p->signal->pgrp = process_group(current); @@ -1186,9 +1182,12 @@ static task_t *copy_process(unsigned long clone_flags, if (p->pid) __get_cpu_var(process_counts)++; } + attach_pid(p, PIDTYPE_TGID, p->tgid); + attach_pid(p, PIDTYPE_PID, p->pid); nr_threads++; total_forks++; + spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); return p; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2b6e1757aed..5ae51f1bc7c 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -418,8 +418,19 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) /* Switch the timer base, if necessary: */ new_base = switch_hrtimer_base(timer, base); - if (mode == HRTIMER_REL) + if (mode == HRTIMER_REL) { tim = ktime_add(tim, new_base->get_time()); + /* + * CONFIG_TIME_LOW_RES is a temporary way for architectures + * to signal that they simply return xtime in + * do_gettimeoffset(). In this case we want to round up by + * resolution when starting a relative timer, to avoid short + * timeouts. This will go away with the GTOD framework. + */ +#ifdef CONFIG_TIME_LOW_RES + tim = ktime_add(tim, base->resolution); +#endif + } timer->expires = tim; enqueue_hrtimer(timer, new_base); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 5f33cdb6fff..d95a72c9279 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -72,8 +72,8 @@ void ptrace_untrace(task_t *child) */ void __ptrace_unlink(task_t *child) { - if (!child->ptrace) - BUG(); + BUG_ON(!child->ptrace); + child->ptrace = 0; if (!list_empty(&child->ptrace_list)) { list_del_init(&child->ptrace_list); @@ -184,22 +184,27 @@ bad: return retval; } +void __ptrace_detach(struct task_struct *child, unsigned int data) +{ + child->exit_code = data; + /* .. re-parent .. */ + __ptrace_unlink(child); + /* .. and wake it up. */ + if (child->exit_state != EXIT_ZOMBIE) + wake_up_process(child); +} + int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) - return -EIO; + return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); - /* .. re-parent .. */ - child->exit_code = data; - write_lock_irq(&tasklist_lock); - __ptrace_unlink(child); - /* .. and wake it up. */ - if (child->exit_state != EXIT_ZOMBIE) - wake_up_process(child); + if (child->ptrace) + __ptrace_detach(child, data); write_unlock_irq(&tasklist_lock); return 0; @@ -242,8 +247,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); - if (!PageCompound(page)) - set_page_dirty_lock(page); + set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); diff --git a/kernel/sched.c b/kernel/sched.c index 87d93be336a..66d957227de 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1204,9 +1204,6 @@ static int try_to_wake_up(task_t *p, unsigned int state, int sync) } } - if (p->last_waker_cpu != this_cpu) - goto out_set_cpu; - if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) goto out_set_cpu; @@ -1277,8 +1274,6 @@ out_set_cpu: cpu = task_cpu(p); } - p->last_waker_cpu = this_cpu; - out_activate: #endif /* CONFIG_SMP */ if (old_state == TASK_UNINTERRUPTIBLE) { @@ -1360,12 +1355,9 @@ void fastcall sched_fork(task_t *p, int clone_flags) #ifdef CONFIG_SCHEDSTATS memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) - p->last_waker_cpu = cpu; -#if defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) p->oncpu = 0; #endif -#endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 67f29516662..508707704d2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -85,7 +85,7 @@ void free_huge_page(struct page *page) BUG_ON(page_count(page)); INIT_LIST_HEAD(&page->lru); - page[1].mapping = NULL; + page[1].lru.next = NULL; /* reset dtor */ spin_lock(&hugetlb_lock); enqueue_huge_page(page); @@ -105,7 +105,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr) } spin_unlock(&hugetlb_lock); set_page_count(page, 1); - page[1].mapping = (void *)free_huge_page; + page[1].lru.next = (void *)free_huge_page; /* set dtor */ for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i) clear_user_highpage(&page[i], addr); return page; diff --git a/mm/madvise.c b/mm/madvise.c index ae0ae3ea299..af3d573b014 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -22,16 +22,23 @@ static long madvise_behavior(struct vm_area_struct * vma, struct mm_struct * mm = vma->vm_mm; int error = 0; pgoff_t pgoff; - int new_flags = vma->vm_flags & ~VM_READHINTMASK; + int new_flags = vma->vm_flags; switch (behavior) { + case MADV_NORMAL: + new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; + break; case MADV_SEQUENTIAL: - new_flags |= VM_SEQ_READ; + new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: - new_flags |= VM_RAND_READ; + new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; - default: + case MADV_DONTFORK: + new_flags |= VM_DONTCOPY; + break; + case MADV_DOFORK: + new_flags &= ~VM_DONTCOPY; break; } @@ -177,6 +184,12 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, long error; switch (behavior) { + case MADV_DOFORK: + if (vma->vm_flags & VM_IO) { + error = -EINVAL; + break; + } + case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dde04ff4be3..62c12252858 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -56,6 +56,7 @@ long nr_swap_pages; int percpu_pagelist_fraction; static void fastcall free_hot_cold_page(struct page *page, int cold); +static void __free_pages_ok(struct page *page, unsigned int order); /* * results with 256, 32 in the lowmem_reserve sysctl: @@ -169,20 +170,23 @@ static void bad_page(struct page *page) * All pages have PG_compound set. All pages have their ->private pointing at * the head page (even the head page has this). * - * The first tail page's ->mapping, if non-zero, holds the address of the - * compound page's put_page() function. - * - * The order of the allocation is stored in the first tail page's ->index - * This is only for debug at present. This usage means that zero-order pages - * may not be compound. + * The first tail page's ->lru.next holds the address of the compound page's + * put_page() function. Its ->lru.prev holds the order of allocation. + * This usage means that zero-order pages may not be compound. */ + +static void free_compound_page(struct page *page) +{ + __free_pages_ok(page, (unsigned long)page[1].lru.prev); +} + static void prep_compound_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; - page[1].mapping = NULL; - page[1].index = order; + page[1].lru.next = (void *)free_compound_page; /* set dtor */ + page[1].lru.prev = (void *)order; for (i = 0; i < nr_pages; i++) { struct page *p = page + i; @@ -196,7 +200,7 @@ static void destroy_compound_page(struct page *page, unsigned long order) int i; int nr_pages = 1 << order; - if (unlikely(page[1].index != order)) + if (unlikely((unsigned long)page[1].lru.prev != order)) bad_page(page); for (i = 0; i < nr_pages; i++) { diff --git a/mm/swap.c b/mm/swap.c index 76247424dea..cce3dda59c5 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -40,7 +40,7 @@ static void put_compound_page(struct page *page) if (put_page_testzero(page)) { void (*dtor)(struct page *page); - dtor = (void (*)(struct page *))page[1].mapping; + dtor = (void (*)(struct page *))page[1].lru.next; (*dtor)(page); } } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index cc047f7fb6e..35cf3a07408 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -67,7 +67,7 @@ void br_stp_disable_bridge(struct net_bridge *br) { struct net_bridge_port *p; - spin_lock(&br->lock); + spin_lock_bh(&br->lock); list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED) br_stp_disable_port(p); @@ -76,7 +76,7 @@ void br_stp_disable_bridge(struct net_bridge *br) br->topology_change = 0; br->topology_change_detected = 0; - spin_unlock(&br->lock); + spin_unlock_bh(&br->lock); del_timer_sync(&br->hello_timer); del_timer_sync(&br->topology_change_timer); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 52a3d7c5790..ed42cdc57cd 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -78,6 +78,47 @@ int ip_route_me_harder(struct sk_buff **pskb) } EXPORT_SYMBOL(ip_route_me_harder); +#ifdef CONFIG_XFRM +int ip_xfrm_me_harder(struct sk_buff **pskb) +{ + struct flowi fl; + unsigned int hh_len; + struct dst_entry *dst; + + if (IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED) + return 0; + if (xfrm_decode_session(*pskb, &fl, AF_INET) < 0) + return -1; + + dst = (*pskb)->dst; + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + dst_hold(dst); + + if (xfrm_lookup(&dst, &fl, (*pskb)->sk, 0) < 0) + return -1; + + dst_release((*pskb)->dst); + (*pskb)->dst = dst; + + /* Change in oif may mean change in hh_len. */ + hh_len = (*pskb)->dst->dev->hard_header_len; + if (skb_headroom(*pskb) < hh_len) { + struct sk_buff *nskb; + + nskb = skb_realloc_headroom(*pskb, hh_len); + if (!nskb) + return -1; + if ((*pskb)->sk) + skb_set_owner_w(nskb, (*pskb)->sk); + kfree_skb(*pskb); + *pskb = nskb; + } + return 0; +} +EXPORT_SYMBOL(ip_xfrm_me_harder); +#endif + void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(ip_nat_decode_session); diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 92c54999a19..7c3f7d38024 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -235,19 +235,19 @@ ip_nat_out(unsigned int hooknum, return NF_ACCEPT; ret = ip_nat_fn(hooknum, pskb, in, out, okfn); +#ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.ip != ct->tuplehash[!dir].tuple.dst.ip -#ifdef CONFIG_XFRM || ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all -#endif ) - return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + return ip_xfrm_me_harder(pskb) == 0 ? ret : NF_DROP; } +#endif return ret; } |