diff options
80 files changed, 2731 insertions, 1654 deletions
diff --git a/Documentation/ia64/README b/Documentation/ia64/README index 7163ae745151..aa17f2154cba 100644 --- a/Documentation/ia64/README +++ b/Documentation/ia64/README @@ -4,40 +4,40 @@ platform. This document provides information specific to IA-64 ONLY, to get additional information about the Linux kernel also read the original Linux README provided with the kernel. - + INSTALLING the kernel: - IA-64 kernel installation is the same as the other platforms, see original README for details. - - + + SOFTWARE REQUIREMENTS Compiling and running this kernel requires an IA-64 compliant GCC compiler. And various software packages also compiled with an IA-64 compliant GCC compiler. - + CONFIGURING the kernel: Configuration is the same, see original README for details. - - + + COMPILING the kernel: - Compiling this kernel doesn't differ from other platform so read the original README for details BUT make sure you have an IA-64 compliant GCC compiler. - + IA-64 SPECIFICS - General issues: - + o Hardly any performance tuning has been done. Obvious targets include the library routines (IP checksum, etc.). Less obvious targets include making sure we don't flush the TLB needlessly, etc. - + o SMP locks cleanup/optimization - + o IA32 support. Currently experimental. It mostly works. diff --git a/Documentation/ia64/fsys.txt b/Documentation/ia64/fsys.txt new file mode 100644 index 000000000000..e258efdbea0b --- /dev/null +++ b/Documentation/ia64/fsys.txt @@ -0,0 +1,231 @@ +-*-Mode: outline-*- + + Light-weight System Calls for IA-64 + ----------------------------------- + + Started: 13-Jan-2003 + Last update: 24-Jan-2003 + + David Mosberger-Tang + <davidm@hpl.hp.com> + +Using the "epc" instruction effectively introduces a new mode of +execution to the ia64 linux kernel. We call this mode the +"fsys-mode". To recap, the normal states of execution are: + + - kernel mode: + Both the register stack and the memory stack have been + switched over to kernel memory. The user-level state is saved + in a pt-regs structure at the top of the kernel memory stack. + + - user mode: + Both the register stack and the kernel stack are in + user memory. The user-level state is contained in the + CPU registers. + + - bank 0 interruption-handling mode: + This is the non-interruptible state which all + interruption-handlers start execution in. The user-level + state remains in the CPU registers and some kernel state may + be stored in bank 0 of registers r16-r31. + +In contrast, fsys-mode has the following special properties: + + - execution is at privilege level 0 (most-privileged) + + - CPU registers may contain a mixture of user-level and kernel-level + state (it is the responsibility of the kernel to ensure that no + security-sensitive kernel-level state is leaked back to + user-level) + + - execution is interruptible and preemptible (an fsys-mode handler + can disable interrupts and avoid all other interruption-sources + to avoid preemption) + + - neither the memory nor the register stack can be trusted while + in fsys-mode (they point to the user-level stacks, which may + be invalid) + +In summary, fsys-mode is much more similar to running in user-mode +than it is to running in kernel-mode. Of course, given that the +privilege level is at level 0, this means that fsys-mode requires some +care (see below). + + +* How to tell fsys-mode + +Linux operates in fsys-mode when (a) the privilege level is 0 (most +privileged) and (b) the stacks have NOT been switched to kernel memory +yet. For convenience, the header file <asm-ia64/ptrace.h> provides +three macros: + + user_mode(regs) + user_stack(task,regs) + fsys_mode(task,regs) + +The "regs" argument is a pointer to a pt_regs structure. The "task" +argument is a pointer to the task structure to which the "regs" +pointer belongs to. user_mode() returns TRUE if the CPU state pointed +to by "regs" was executing in user mode (privilege level 3). +user_stack() returns TRUE if the state pointed to by "regs" was +executing on the user-level stack(s). Finally, fsys_mode() returns +TRUE if the CPU state pointed to by "regs" was executing in fsys-mode. +The fsys_mode() macro is equivalent to the expression: + + !user_mode(regs) && user_stack(task,regs) + +* How to write an fsyscall handler + +The file arch/ia64/kernel/fsys.S contains a table of fsyscall-handlers +(fsyscall_table). This table contains one entry for each system call. +By default, a system call is handled by fsys_fallback_syscall(). This +routine takes care of entering (full) kernel mode and calling the +normal Linux system call handler. For performance-critical system +calls, it is possible to write a hand-tuned fsyscall_handler. For +example, fsys.S contains fsys_getpid(), which is a hand-tuned version +of the getpid() system call. + +The entry and exit-state of an fsyscall handler is as follows: + +** Machine state on entry to fsyscall handler: + + - r10 = 0 + - r11 = saved ar.pfs (a user-level value) + - r15 = system call number + - r16 = "current" task pointer (in normal kernel-mode, this is in r13) + - r32-r39 = system call arguments + - b6 = return address (a user-level value) + - ar.pfs = previous frame-state (a user-level value) + - PSR.be = cleared to zero (i.e., little-endian byte order is in effect) + - all other registers may contain values passed in from user-mode + +** Required machine state on exit to fsyscall handler: + + - r11 = saved ar.pfs (as passed into the fsyscall handler) + - r15 = system call number (as passed into the fsyscall handler) + - r32-r39 = system call arguments (as passed into the fsyscall handler) + - b6 = return address (as passed into the fsyscall handler) + - ar.pfs = previous frame-state (as passed into the fsyscall handler) + +Fsyscall handlers can execute with very little overhead, but with that +speed comes a set of restrictions: + + o Fsyscall-handlers MUST check for any pending work in the flags + member of the thread-info structure and if any of the + TIF_ALLWORK_MASK flags are set, the handler needs to fall back on + doing a full system call (by calling fsys_fallback_syscall). + + o Fsyscall-handlers MUST preserve incoming arguments (r32-r39, r11, + r15, b6, and ar.pfs) because they will be needed in case of a + system call restart. Of course, all "preserved" registers also + must be preserved, in accordance to the normal calling conventions. + + o Fsyscall-handlers MUST check argument registers for containing a + NaT value before using them in any way that could trigger a + NaT-consumption fault. If a system call argument is found to + contain a NaT value, an fsyscall-handler may return immediately + with r8=EINVAL, r10=-1. + + o Fsyscall-handlers MUST NOT use the "alloc" instruction or perform + any other operation that would trigger mandatory RSE + (register-stack engine) traffic. + + o Fsyscall-handlers MUST NOT write to any stacked registers because + it is not safe to assume that user-level called a handler with the + proper number of arguments. + + o Fsyscall-handlers need to be careful when accessing per-CPU variables: + unless proper safe-guards are taken (e.g., interruptions are avoided), + execution may be pre-empted and resumed on another CPU at any given + time. + + o Fsyscall-handlers must be careful not to leak sensitive kernel' + information back to user-level. In particular, before returning to + user-level, care needs to be taken to clear any scratch registers + that could contain sensitive information (note that the current + task pointer is not considered sensitive: it's already exposed + through ar.k6). + +The above restrictions may seem draconian, but remember that it's +possible to trade off some of the restrictions by paying a slightly +higher overhead. For example, if an fsyscall-handler could benefit +from the shadow register bank, it could temporarily disable PSR.i and +PSR.ic, switch to bank 0 (bsw.0) and then use the shadow registers as +needed. In other words, following the above rules yields extremely +fast system call execution (while fully preserving system call +semantics), but there is also a lot of flexibility in handling more +complicated cases. + +* Signal handling + +The delivery of (asynchronous) signals must be delayed until fsys-mode +is exited. This is acomplished with the help of the lower-privilege +transfer trap: arch/ia64/kernel/process.c:do_notify_resume_user() +checks whether the interrupted task was in fsys-mode and, if so, sets +PSR.lp and returns immediately. When fsys-mode is exited via the +"br.ret" instruction that lowers the privilege level, a trap will +occur. The trap handler clears PSR.lp again and returns immediately. +The kernel exit path then checks for and delivers any pending signals. + +* PSR Handling + +The "epc" instruction doesn't change the contents of PSR at all. This +is in contrast to a regular interruption, which clears almost all +bits. Because of that, some care needs to be taken to ensure things +work as expected. The following discussion describes how each PSR bit +is handled. + +PSR.be Cleared when entering fsys-mode. A srlz.d instruction is used + to ensure the CPU is in little-endian mode before the first + load/store instruction is executed. PSR.be is normally NOT + restored upon return from an fsys-mode handler. In other + words, user-level code must not rely on PSR.be being preserved + across a system call. +PSR.up Unchanged. +PSR.ac Unchanged. +PSR.mfl Unchanged. Note: fsys-mode handlers must not write-registers! +PSR.mfh Unchanged. Note: fsys-mode handlers must not write-registers! +PSR.ic Unchanged. Note: fsys-mode handlers can clear the bit, if needed. +PSR.i Unchanged. Note: fsys-mode handlers can clear the bit, if needed. +PSR.pk Unchanged. +PSR.dt Unchanged. +PSR.dfl Unchanged. Note: fsys-mode handlers must not write-registers! +PSR.dfh Unchanged. Note: fsys-mode handlers must not write-registers! +PSR.sp Unchanged. +PSR.pp Unchanged. +PSR.di Unchanged. +PSR.si Unchanged. +PSR.db Unchanged. The kernel prevents user-level from setting a hardware + breakpoint that triggers at any privilege level other than 3 (user-mode). +PSR.lp Unchanged. +PSR.tb Lazy redirect. If a taken-branch trap occurs while in + fsys-mode, the trap-handler modifies the saved machine state + such that execution resumes in the gate page at + syscall_via_break(), with privilege level 3. Note: the + taken branch would occur on the branch invoking the + fsyscall-handler, at which point, by definition, a syscall + restart is still safe. If the system call number is invalid, + the fsys-mode handler will return directly to user-level. This + return will trigger a taken-branch trap, but since the trap is + taken _after_ restoring the privilege level, the CPU has already + left fsys-mode, so no special treatment is needed. +PSR.rt Unchanged. +PSR.cpl Cleared to 0. +PSR.is Unchanged (guaranteed to be 0 on entry to the gate page). +PSR.mc Unchanged. +PSR.it Unchanged (guaranteed to be 1). +PSR.id Unchanged. Note: the ia64 linux kernel never sets this bit. +PSR.da Unchanged. Note: the ia64 linux kernel never sets this bit. +PSR.dd Unchanged. Note: the ia64 linux kernel never sets this bit. +PSR.ss Lazy redirect. If set, "epc" will cause a Single Step Trap to + be taken. The trap handler then modifies the saved machine + state such that execution resumes in the gate page at + syscall_via_break(), with privilege level 3. +PSR.ri Unchanged. +PSR.ed Unchanged. Note: This bit could only have an effect if an fsys-mode + handler performed a speculative load that gets NaTted. If so, this + would be the normal & expected behavior, so no special treatment is + needed. +PSR.bn Unchanged. Note: fsys-mode handlers may clear the bit, if needed. + Doing so requires clearing PSR.i and PSR.ic as well. +PSR.ia Unchanged. Note: the ia64 linux kernel never sets this bit. diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 615fa7ea5764..6f67a0c83e64 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -768,6 +768,9 @@ source "arch/ia64/hp/sim/Kconfig" menu "Kernel hacking" +config FSYS + bool "Light-weight system-call support (via epc)" + choice prompt "Physical memory granularity" default IA64_GRANULE_64MB diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 91ac89227f03..01edd2602ff4 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -5,7 +5,7 @@ # License. See the file "COPYING" in the main directory of this archive # for more details. # -# Copyright (C) 1998-2002 by David Mosberger-Tang <davidm@hpl.hp.com> +# Copyright (C) 1998-2003 by David Mosberger-Tang <davidm@hpl.hp.com> # NM := $(CROSS_COMPILE)nm -B @@ -23,6 +23,16 @@ CFLAGS_KERNEL := -mconstant-gp GCC_VERSION=$(shell $(CC) -v 2>&1 | fgrep 'gcc version' | cut -f3 -d' ' | cut -f1 -d'.') +GAS_STATUS=$(shell arch/ia64/scripts/check-gas $(CC)) + +ifeq ($(GAS_STATUS),buggy) +$(error Sorry, you need a newer version of the assember, one that is built from \ + a source-tree that post-dates 18-Dec-2002. You can find a pre-compiled \ + static binary of such an assembler at: \ + \ + ftp://ftp.hpl.hp.com/pub/linux-ia64/gas-030124.tar.gz) +endif + ifneq ($(GCC_VERSION),2) cflags-y += -frename-registers --param max-inline-insns=5000 endif @@ -48,25 +58,36 @@ drivers-$(CONFIG_IA64_HP_SIM) += arch/ia64/hp/sim/ drivers-$(CONFIG_IA64_HP_ZX1) += arch/ia64/hp/common/ arch/ia64/hp/zx1/ drivers-$(CONFIG_IA64_SGI_SN) += arch/ia64/sn/fakeprom/ -makeboot =$(Q)$(MAKE) -f scripts/Makefile.build obj=arch/ia64/boot $(1) -maketool =$(Q)$(MAKE) -f scripts/Makefile.build obj=arch/ia64/tools $(1) +boot := arch/ia64/boot +tools := arch/ia64/tools .PHONY: boot compressed include/asm-ia64/offsets.h -all compressed: vmlinux.gz +all: vmlinux + +compressed: vmlinux.gz vmlinux.gz: vmlinux - $(call makeboot,vmlinux.gz) + $(Q)$(MAKE) $(build)=$(boot) vmlinux.gz + +check: vmlinux + arch/ia64/scripts/unwcheck.sh vmlinux archclean: - $(Q)$(MAKE) -f scripts/Makefile.clean obj=arch/ia64/boot + $(Q)$(MAKE) $(clean)=$(boot) + $(Q)$(MAKE) $(clean)=$(tools) CLEAN_FILES += include/asm-ia64/offsets.h vmlinux.gz bootloader prepare: include/asm-ia64/offsets.h boot: lib/lib.a vmlinux - $(call makeboot,$@) + $(Q)$(MAKE) $(build)=$(boot) $@ include/asm-ia64/offsets.h: include/asm include/linux/version.h include/config/MARKER - $(call maketool,$@) + $(Q)$(MAKE) $(build)=$(tools) $@ + +define archhelp + echo ' compressed - Build compressed kernel image' + echo ' boot - Build vmlinux and bootloader for Ski simulator' +endef diff --git a/arch/ia64/dig/setup.c b/arch/ia64/dig/setup.c index 66455679daf4..d58003f1ad02 100644 --- a/arch/ia64/dig/setup.c +++ b/arch/ia64/dig/setup.c @@ -3,7 +3,7 @@ * * Copyright (C) 1999 Intel Corp. * Copyright (C) 1999, 2001 Hewlett-Packard Co - * Copyright (C) 1999, 2001 David Mosberger-Tang <davidm@hpl.hp.com> + * Copyright (C) 1999, 2001, 2003 David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> * Copyright (C) 1999 Vijay Chander <vijay@engr.sgi.com> @@ -56,7 +56,7 @@ dig_setup (char **cmdline_p) if (!ia64_boot_param->console_info.num_rows || !ia64_boot_param->console_info.num_cols) { - printk("dig_setup: warning: invalid screen-info, guessing 80x25\n"); + printk(KERN_WARNING "dig_setup: warning: invalid screen-info, guessing 80x25\n"); orig_x = 0; orig_y = 0; num_cols = 80; diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index eea0618b1e7a..7b1af476ded8 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -288,20 +288,19 @@ sba_dump_pdir_entry(struct ioc *ioc, char *msg, uint pide) unsigned long *rptr = (unsigned long *) &(ioc->res_map[(pide >>3) & ~(sizeof(unsigned long) - 1)]); uint rcnt; - /* printk(KERN_DEBUG "SBA: %s rp %p bit %d rval 0x%lx\n", */ - printk("SBA: %s rp %p bit %d rval 0x%lx\n", + printk(KERN_DEBUG "SBA: %s rp %p bit %d rval 0x%lx\n", msg, rptr, pide & (BITS_PER_LONG - 1), *rptr); rcnt = 0; while (rcnt < BITS_PER_LONG) { - printk("%s %2d %p %016Lx\n", - (rcnt == (pide & (BITS_PER_LONG - 1))) - ? " -->" : " ", - rcnt, ptr, *ptr ); + printk(KERN_DEBUG "%s %2d %p %016Lx\n", + (rcnt == (pide & (BITS_PER_LONG - 1))) + ? " -->" : " ", + rcnt, ptr, *ptr ); rcnt++; ptr++; } - printk("%s", msg); + printk(KERN_DEBUG "%s", msg); } @@ -363,11 +362,9 @@ static void sba_dump_sg(struct ioc *ioc, struct scatterlist *startsg, int nents) { while (nents-- > 0) { - printk(" %d : DMA %08lx/%05x CPU %p\n", - nents, - (unsigned long) sba_sg_iova(startsg), - sba_sg_iova_len(startsg), - sba_sg_address(startsg)); + printk(KERN_DEBUG " %d : DMA %08lx/%05x CPU %p\n", nents, + (unsigned long) sba_sg_iova(startsg), sba_sg_iova_len(startsg), + sba_sg_address(startsg)); startsg++; } } @@ -1451,9 +1448,10 @@ sba_common_init(struct sba_device *sba_dev) sba_dev->ioc[i].res_map; } else { u64 reserved_iov; - + /* Yet another 1.x hack */ - printk("zx1 1.x: Starting resource hint offset into IOV space to avoid initial zero value IOVA\n"); + printk(KERN_DEBUG "zx1 1.x: Starting resource hint offset into " + "IOV space to avoid initial zero value IOVA\n"); sba_dev->ioc[i].res_hint = (unsigned long *) &(sba_dev->ioc[i].res_map[L1_CACHE_BYTES]); @@ -1632,7 +1630,7 @@ void __init sba_init(void) device->slot_name, hpa); if ((hw_rev & 0xFF) < 0x20) { - printk("%s: SBA rev less than 2.0 not supported", DRIVER_NAME); + printk(KERN_INFO "%s: SBA rev less than 2.0 not supported", DRIVER_NAME); return; } diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c index b03af9dca130..d54ad634096b 100644 --- a/arch/ia64/hp/sim/simeth.c +++ b/arch/ia64/hp/sim/simeth.c @@ -1,7 +1,7 @@ /* * Simulated Ethernet Driver * - * Copyright (C) 1999-2001 Hewlett-Packard Co + * Copyright (C) 1999-2001, 2003 Hewlett-Packard Co * Stephane Eranian <eranian@hpl.hp.com> */ #include <linux/config.h> @@ -116,7 +116,7 @@ simeth_probe (void) { int r; - printk("simeth: v%s\n", simeth_version); + printk(KERN_INFO "simeth: v%s\n", simeth_version); r = simeth_probe1(); @@ -235,7 +235,8 @@ simeth_probe1(void) /* Fill in the fields of the device structure with ethernet-generic values. */ ether_setup(dev); - printk("%s: hosteth=%s simfd=%d, HwAddr", dev->name, simeth_device, local->simfd); + printk(KERN_INFO "%s: hosteth=%s simfd=%d, HwAddr", + dev->name, simeth_device, local->simfd); for(i = 0; i < ETH_ALEN; i++) { printk(" %2.2x", dev->dev_addr[i]); } @@ -251,7 +252,7 @@ static int simeth_open(struct net_device *dev) { if (request_irq(dev->irq, simeth_interrupt, 0, "simeth", dev)) { - printk ("simeth: unable to get IRQ %d.\n", dev->irq); + printk(KERN_WARNING "simeth: unable to get IRQ %d.\n", dev->irq); return -EAGAIN; } @@ -312,11 +313,12 @@ simeth_device_event(struct notifier_block *this,unsigned long event, void *ptr) if (strcmp(dev->name, ifa->ifa_label) == 0) break; } if ( ifa == NULL ) { - printk("simeth_open: can't find device %s's ifa\n", dev->name); + printk(KERN_ERR "simeth_open: can't find device %s's ifa\n", dev->name); return NOTIFY_DONE; } - printk("simeth_device_event: %s ipaddr=0x%x\n", dev->name, htonl(ifa->ifa_local)); + printk(KERN_INFO "simeth_device_event: %s ipaddr=0x%x\n", + dev->name, htonl(ifa->ifa_local)); /* * XXX Fix me @@ -330,7 +332,8 @@ simeth_device_event(struct notifier_block *this,unsigned long event, void *ptr) netdev_attach(local->simfd, dev->irq, htonl(ifa->ifa_local)): netdev_detach(local->simfd); - printk("simeth: netdev_attach/detach: event=%s ->%d\n", event == NETDEV_UP ? "attach":"detach", r); + printk(KERN_INFO "simeth: netdev_attach/detach: event=%s ->%d\n", + event == NETDEV_UP ? "attach":"detach", r); return NOTIFY_DONE; } @@ -460,7 +463,8 @@ simeth_rx(struct net_device *dev) */ len = netdev_read(local->simfd, skb->data, SIMETH_FRAME_SIZE); if ( len == 0 ) { - if ( simeth_debug > 0 ) printk(KERN_WARNING "%s: count=%d netdev_read=0\n", dev->name, SIMETH_RECV_MAX-rcv_count); + if ( simeth_debug > 0 ) printk(KERN_WARNING "%s: count=%d netdev_read=0\n", + dev->name, SIMETH_RECV_MAX-rcv_count); break; } #if 0 diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c index 8ca6c3fec006..c85bd586d2ab 100644 --- a/arch/ia64/hp/sim/simscsi.c +++ b/arch/ia64/hp/sim/simscsi.c @@ -1,7 +1,7 @@ /* * Simulated SCSI driver. * - * Copyright (C) 1999, 2001-2002 Hewlett-Packard Co + * Copyright (C) 1999, 2001-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * @@ -87,7 +87,8 @@ simscsi_setup (char *s) { /* XXX Fix me we may need to strcpy() ? */ if (strlen(s) > MAX_ROOT_LEN) { - printk("simscsi_setup: prefix too long---using default %s\n", simscsi_root); + printk(KERN_ERR "simscsi_setup: prefix too long---using default %s\n", + simscsi_root); } simscsi_root = s; return 1; @@ -354,7 +355,7 @@ simscsi_queuecommand (Scsi_Cmnd *sc, void (*done)(Scsi_Cmnd *)) break; case START_STOP: - printk("START_STOP\n"); + printk(KERN_ERR "START_STOP\n"); break; default: @@ -380,7 +381,7 @@ simscsi_queuecommand (Scsi_Cmnd *sc, void (*done)(Scsi_Cmnd *)) int simscsi_host_reset (Scsi_Cmnd *sc) { - printk ("simscsi_host_reset: not implemented\n"); + printk(KERN_ERR "simscsi_host_reset: not implemented\n"); return 0; } diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index 184fa96bad1d..2ca3be2678a8 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -7,7 +7,7 @@ * case means sys_sim.c console (goes via the simulator). The code hereafter * is completely leveraged from the serial.c driver. * - * Copyright (C) 1999-2000, 2002 Hewlett-Packard Co + * Copyright (C) 1999-2000, 2002-2003 Hewlett-Packard Co * Stephane Eranian <eranian@hpl.hp.com> * David Mosberger-Tang <davidm@hpl.hp.com> * @@ -195,7 +195,7 @@ static void rs_interrupt_single(int irq, void *dev_id, struct pt_regs * regs) */ info = IRQ_ports[irq]; if (!info || !info->tty) { - printk("simrs_interrupt_single: info|tty=0 info=%p problem\n", info); + printk(KERN_INFO "simrs_interrupt_single: info|tty=0 info=%p problem\n", info); return; } /* @@ -219,13 +219,13 @@ static DECLARE_TASK_QUEUE(tq_serial); /* used to be at the top of the file */ static void do_serial_bh(void) { run_task_queue(&tq_serial); - printk("do_serial_bh: called\n"); + printk(KERN_ERR "do_serial_bh: called\n"); } #endif static void do_softint(void *private_) { - printk("simserial: do_softint called\n"); + printk(KERN_ERR "simserial: do_softint called\n"); } static void rs_put_char(struct tty_struct *tty, unsigned char ch) @@ -439,7 +439,7 @@ static void rs_throttle(struct tty_struct * tty) { if (I_IXOFF(tty)) rs_send_xchar(tty, STOP_CHAR(tty)); - printk("simrs_throttle called\n"); + printk(KERN_INFO "simrs_throttle called\n"); } static void rs_unthrottle(struct tty_struct * tty) @@ -452,7 +452,7 @@ static void rs_unthrottle(struct tty_struct * tty) else rs_send_xchar(tty, START_CHAR(tty)); } - printk("simrs_unthrottle called\n"); + printk(KERN_INFO "simrs_unthrottle called\n"); } /* @@ -474,29 +474,29 @@ static int rs_ioctl(struct tty_struct *tty, struct file * file, switch (cmd) { case TIOCMGET: - printk("rs_ioctl: TIOCMGET called\n"); + printk(KERN_INFO "rs_ioctl: TIOCMGET called\n"); return -EINVAL; case TIOCMBIS: case TIOCMBIC: case TIOCMSET: - printk("rs_ioctl: TIOCMBIS/BIC/SET called\n"); + printk(KERN_INFO "rs_ioctl: TIOCMBIS/BIC/SET called\n"); return -EINVAL; case TIOCGSERIAL: - printk("simrs_ioctl TIOCGSERIAL called\n"); + printk(KERN_INFO "simrs_ioctl TIOCGSERIAL called\n"); return 0; case TIOCSSERIAL: - printk("simrs_ioctl TIOCSSERIAL called\n"); + printk(KERN_INFO "simrs_ioctl TIOCSSERIAL called\n"); return 0; case TIOCSERCONFIG: - printk("rs_ioctl: TIOCSERCONFIG called\n"); + printk(KERN_INFO "rs_ioctl: TIOCSERCONFIG called\n"); return -EINVAL; case TIOCSERGETLSR: /* Get line status register */ - printk("rs_ioctl: TIOCSERGETLSR called\n"); + printk(KERN_INFO "rs_ioctl: TIOCSERGETLSR called\n"); return -EINVAL; case TIOCSERGSTRUCT: - printk("rs_ioctl: TIOCSERGSTRUCT called\n"); + printk(KERN_INFO "rs_ioctl: TIOCSERGSTRUCT called\n"); #if 0 if (copy_to_user((struct async_struct *) arg, info, sizeof(struct async_struct))) @@ -511,7 +511,7 @@ static int rs_ioctl(struct tty_struct *tty, struct file * file, * Caller should use TIOCGICOUNT to see which one it was */ case TIOCMIWAIT: - printk("rs_ioctl: TIOCMIWAIT: called\n"); + printk(KERN_INFO "rs_ioctl: TIOCMIWAIT: called\n"); return 0; /* * Get counter of input serial line interrupts (DCD,RI,DSR,CTS) @@ -520,13 +520,13 @@ static int rs_ioctl(struct tty_struct *tty, struct file * file, * RI where only 0->1 is counted. */ case TIOCGICOUNT: - printk("rs_ioctl: TIOCGICOUNT called\n"); + printk(KERN_INFO "rs_ioctl: TIOCGICOUNT called\n"); return 0; case TIOCSERGWILD: case TIOCSERSWILD: /* "setserial -W" is called in Debian boot */ - printk ("TIOCSER?WILD ioctl obsolete, ignored.\n"); + printk (KERN_INFO "TIOCSER?WILD ioctl obsolete, ignored.\n"); return 0; default: @@ -596,7 +596,7 @@ static void shutdown(struct async_struct * info) IRQ_T(info), "serial", NULL); if (retval) - printk("serial shutdown: request_irq: error %d" + printk(KERN_ERR "serial shutdown: request_irq: error %d" " Couldn't reacquire IRQ.\n", retval); } else free_irq(state->irq, NULL); @@ -654,12 +654,12 @@ static void rs_close(struct tty_struct *tty, struct file * filp) * one, we've got real problems, since it means the * serial port won't be shutdown. */ - printk("rs_close: bad serial port count; tty->count is 1, " + printk(KERN_ERR "rs_close: bad serial port count; tty->count is 1, " "state->count is %d\n", state->count); state->count = 1; } if (--state->count < 0) { - printk("rs_close: bad serial port count for ttys%d: %d\n", + printk(KERN_ERR "rs_close: bad serial port count for ttys%d: %d\n", info->line, state->count); state->count = 0; } @@ -1013,7 +1013,7 @@ done: static inline void show_serial_version(void) { printk(KERN_INFO "%s version %s with", serial_name, serial_version); - printk(" no serial options enabled\n"); + printk(KERN_INFO " no serial options enabled\n"); } /* diff --git a/arch/ia64/hp/zx1/hpzx1_misc.c b/arch/ia64/hp/zx1/hpzx1_misc.c index a1c0e2585469..bf6faa991038 100644 --- a/arch/ia64/hp/zx1/hpzx1_misc.c +++ b/arch/ia64/hp/zx1/hpzx1_misc.c @@ -1,9 +1,9 @@ /* * Misc. support for HP zx1 chipset support * - * Copyright (C) 2002 Hewlett-Packard Co - * Copyright (C) 2002 Alex Williamson <alex_williamson@hp.com> - * Copyright (C) 2002 Bjorn Helgaas <bjorn_helgaas@hp.com> + * Copyright (C) 2002-2003 Hewlett-Packard Co + * Alex Williamson <alex_williamson@hp.com> + * Bjorn Helgaas <bjorn_helgaas@hp.com> */ @@ -17,7 +17,7 @@ #include <asm/dma.h> #include <asm/iosapic.h> -extern acpi_status acpi_evaluate_integer (acpi_handle, acpi_string, acpi_object_list *, +extern acpi_status acpi_evaluate_integer (acpi_handle, acpi_string, struct acpi_object_list *, unsigned long *); #define PFX "hpzx1: " @@ -190,31 +190,31 @@ hpzx1_fake_pci_dev(char *name, unsigned int busnum, unsigned long addr, unsigned hpzx1_devices++; } -typedef struct { +struct acpi_hp_vendor_long { u8 guid_id; u8 guid[16]; u8 csr_base[8]; u8 csr_length[8]; -} acpi_hp_vendor_long; +}; #define HP_CCSR_LENGTH 0x21 #define HP_CCSR_TYPE 0x2 #define HP_CCSR_GUID EFI_GUID(0x69e9adf9, 0x924f, 0xab5f, \ 0xf6, 0x4a, 0x24, 0xd2, 0x01, 0x37, 0x0e, 0xad) -extern acpi_status acpi_get_crs(acpi_handle, acpi_buffer *); -extern acpi_resource *acpi_get_crs_next(acpi_buffer *, int *); -extern acpi_resource_data *acpi_get_crs_type(acpi_buffer *, int *, int); -extern void acpi_dispose_crs(acpi_buffer *); +extern acpi_status acpi_get_crs(acpi_handle, struct acpi_buffer *); +extern struct acpi_resource *acpi_get_crs_next(struct acpi_buffer *, int *); +extern union acpi_resource_data *acpi_get_crs_type(struct acpi_buffer *, int *, int); +extern void acpi_dispose_crs(struct acpi_buffer *); static acpi_status hp_csr_space(acpi_handle obj, u64 *csr_base, u64 *csr_length) { int i, offset = 0; acpi_status status; - acpi_buffer buf; - acpi_resource_vendor *res; - acpi_hp_vendor_long *hp_res; + struct acpi_buffer buf; + struct acpi_resource_vendor *res; + struct acpi_hp_vendor_long *hp_res; efi_guid_t vendor_guid; *csr_base = 0; @@ -226,14 +226,14 @@ hp_csr_space(acpi_handle obj, u64 *csr_base, u64 *csr_length) return status; } - res = (acpi_resource_vendor *)acpi_get_crs_type(&buf, &offset, ACPI_RSTYPE_VENDOR); + res = (struct acpi_resource_vendor *)acpi_get_crs_type(&buf, &offset, ACPI_RSTYPE_VENDOR); if (!res) { printk(KERN_ERR PFX "Failed to find config space for device\n"); acpi_dispose_crs(&buf); return AE_NOT_FOUND; } - hp_res = (acpi_hp_vendor_long *)(res->reserved); + hp_res = (struct acpi_hp_vendor_long *)(res->reserved); if (res->length != HP_CCSR_LENGTH || hp_res->guid_id != HP_CCSR_TYPE) { printk(KERN_ERR PFX "Unknown Vendor data\n"); @@ -288,7 +288,7 @@ hpzx1_lba_probe(acpi_handle obj, u32 depth, void *context, void **ret) { u64 csr_base = 0, csr_length = 0; acpi_status status; - NATIVE_UINT busnum; + acpi_native_uint busnum; char *name = context; char fullname[32]; diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c index fbcbe4a2c74a..790682a0e88c 100644 --- a/arch/ia64/ia32/binfmt_elf32.c +++ b/arch/ia64/ia32/binfmt_elf32.c @@ -44,7 +44,6 @@ extern void put_dirty_page (struct task_struct * tsk, struct page *page, unsigne static void elf32_set_personality (void); -#define ELF_PLAT_INIT(_r) ia64_elf32_init(_r) #define setup_arg_pages(bprm) ia32_setup_arg_pages(bprm) #define elf_map elf32_map diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index 8a3445be6962..87ff1d57bcd2 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -95,12 +95,19 @@ END(sys32_sigsuspend) GLOBAL_ENTRY(ia32_ret_from_clone) PT_REGS_UNWIND_INFO(0) #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) +{ /* + * Some versions of gas generate bad unwind info if the first instruction of a + * procedure doesn't go into the first slot of a bundle. This is a workaround. + */ + nop.m 0 + nop.i 0 /* * We need to call schedule_tail() to complete the scheduling process. * Called by ia64_switch_to after do_fork()->copy_thread(). r8 contains the * address of the previously executing task. */ br.call.sptk.many rp=ia64_invoke_schedule_tail +} .ret1: #endif adds r2=TI_FLAGS+IA64_TASK_SIZE,r13 @@ -264,7 +271,7 @@ ia32_syscall_table: data8 sys_setreuid /* 16-bit version */ /* 70 */ data8 sys_setregid /* 16-bit version */ data8 sys32_sigsuspend - data8 sys32_sigpending + data8 compat_sys_sigpending data8 sys_sethostname data8 sys32_setrlimit /* 75 */ data8 sys32_old_getrlimit @@ -290,8 +297,8 @@ ia32_syscall_table: data8 sys_getpriority data8 sys_setpriority data8 sys32_ni_syscall /* old profil syscall holder */ - data8 sys32_statfs - data8 sys32_fstatfs /* 100 */ + data8 compat_sys_statfs + data8 compat_sys_fstatfs /* 100 */ data8 sys32_ioperm data8 sys32_socketcall data8 sys_syslog @@ -317,7 +324,7 @@ ia32_syscall_table: data8 sys32_modify_ldt data8 sys32_ni_syscall /* adjtimex */ data8 sys32_mprotect /* 125 */ - data8 sys32_sigprocmask + data8 compat_sys_sigprocmask data8 sys32_ni_syscall /* create_module */ data8 sys32_ni_syscall /* init_module */ data8 sys32_ni_syscall /* delete_module */ diff --git a/arch/ia64/ia32/ia32_ioctl.c b/arch/ia64/ia32/ia32_ioctl.c index f525f2453950..b25d9c5c6f88 100644 --- a/arch/ia64/ia32/ia32_ioctl.c +++ b/arch/ia64/ia32/ia32_ioctl.c @@ -510,6 +510,6 @@ sys32_ioctl (unsigned int fd, unsigned int cmd, unsigned int arg) return(sg_ioctl_trans(fd, cmd, arg)); } - printk("%x:unimplemented IA32 ioctl system call\n", cmd); + printk(KERN_ERR "%x:unimplemented IA32 ioctl system call\n", cmd); return -EINVAL; } diff --git a/arch/ia64/ia32/ia32_signal.c b/arch/ia64/ia32/ia32_signal.c index d85b58933635..f2d006240df2 100644 --- a/arch/ia64/ia32/ia32_signal.c +++ b/arch/ia64/ia32/ia32_signal.c @@ -56,7 +56,7 @@ struct sigframe_ia32 int sig; struct sigcontext_ia32 sc; struct _fpstate_ia32 fpstate; - unsigned int extramask[_IA32_NSIG_WORDS-1]; + unsigned int extramask[_COMPAT_NSIG_WORDS-1]; char retcode[8]; }; @@ -463,7 +463,7 @@ sigact_set_handler (struct k_sigaction *sa, unsigned int handler, unsigned int r } asmlinkage long -ia32_rt_sigsuspend (sigset32_t *uset, unsigned int sigsetsize, struct sigscratch *scr) +ia32_rt_sigsuspend (compat_sigset_t *uset, unsigned int sigsetsize, struct sigscratch *scr) { extern long ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall); sigset_t oldset, set; @@ -504,7 +504,7 @@ ia32_rt_sigsuspend (sigset32_t *uset, unsigned int sigsetsize, struct sigscratch asmlinkage long ia32_sigsuspend (unsigned int mask, struct sigscratch *scr) { - return ia32_rt_sigsuspend((sigset32_t *)&mask, sizeof(mask), scr); + return ia32_rt_sigsuspend((compat_sigset_t *)&mask, sizeof(mask), scr); } asmlinkage long @@ -530,14 +530,14 @@ sys32_rt_sigaction (int sig, struct sigaction32 *act, int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset32_t)) + if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (act) { ret = get_user(handler, &act->sa_handler); ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); ret |= get_user(restorer, &act->sa_restorer); - ret |= copy_from_user(&new_ka.sa.sa_mask, &act->sa_mask, sizeof(sigset32_t)); + ret |= copy_from_user(&new_ka.sa.sa_mask, &act->sa_mask, sizeof(compat_sigset_t)); if (ret) return -EFAULT; @@ -550,7 +550,7 @@ sys32_rt_sigaction (int sig, struct sigaction32 *act, ret = put_user(IA32_SA_HANDLER(&old_ka), &oact->sa_handler); ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags); ret |= put_user(IA32_SA_RESTORER(&old_ka), &oact->sa_restorer); - ret |= copy_to_user(&oact->sa_mask, &old_ka.sa.sa_mask, sizeof(sigset32_t)); + ret |= copy_to_user(&oact->sa_mask, &old_ka.sa.sa_mask, sizeof(compat_sigset_t)); } return ret; } @@ -560,7 +560,7 @@ extern asmlinkage long sys_rt_sigprocmask (int how, sigset_t *set, sigset_t *ose size_t sigsetsize); asmlinkage long -sys32_rt_sigprocmask (int how, sigset32_t *set, sigset32_t *oset, unsigned int sigsetsize) +sys32_rt_sigprocmask (int how, compat_sigset_t *set, compat_sigset_t *oset, unsigned int sigsetsize) { mm_segment_t old_fs = get_fs(); sigset_t s; @@ -587,13 +587,7 @@ sys32_rt_sigprocmask (int how, sigset32_t *set, sigset32_t *oset, unsigned int s } asmlinkage long -sys32_sigprocmask (int how, unsigned int *set, unsigned int *oset) -{ - return sys32_rt_sigprocmask(how, (sigset32_t *) set, (sigset32_t *) oset, sizeof(*set)); -} - -asmlinkage long -sys32_rt_sigtimedwait (sigset32_t *uthese, siginfo_t32 *uinfo, +sys32_rt_sigtimedwait (compat_sigset_t *uthese, siginfo_t32 *uinfo, struct compat_timespec *uts, unsigned int sigsetsize) { extern asmlinkage long sys_rt_sigtimedwait (const sigset_t *, siginfo_t *, @@ -605,16 +599,13 @@ sys32_rt_sigtimedwait (sigset32_t *uthese, siginfo_t32 *uinfo, sigset_t s; int ret; - if (copy_from_user(&s.sig, uthese, sizeof(sigset32_t))) + if (copy_from_user(&s.sig, uthese, sizeof(compat_sigset_t))) + return -EFAULT; + if (uts && get_compat_timespec(&t, uts)) return -EFAULT; - if (uts) { - ret = get_user(t.tv_sec, &uts->tv_sec); - ret |= get_user(t.tv_nsec, &uts->tv_nsec); - if (ret) - return -EFAULT; - } set_fs(KERNEL_DS); - ret = sys_rt_sigtimedwait(&s, &info, &t, sigsetsize); + ret = sys_rt_sigtimedwait(&s, uinfo ? &info : NULL, uts ? &t : NULL, + sigsetsize); set_fs(old_fs); if (ret >= 0 && uinfo) { if (copy_siginfo_to_user32(uinfo, &info)) @@ -648,7 +639,7 @@ sys32_sigaction (int sig, struct old_sigaction32 *act, struct old_sigaction32 *o int ret; if (act) { - old_sigset32_t mask; + compat_old_sigset_t mask; ret = get_user(handler, &act->sa_handler); ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); @@ -866,7 +857,7 @@ setup_frame_ia32 (int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs err |= setup_sigcontext_ia32(&frame->sc, &frame->fpstate, regs, set->sig[0]); - if (_IA32_NSIG_WORDS > 1) + if (_COMPAT_NSIG_WORDS > 1) err |= __copy_to_user(frame->extramask, (char *) &set->sig + 4, sizeof(frame->extramask)); @@ -1011,7 +1002,7 @@ sys32_sigreturn (int arg0, int arg1, int arg2, int arg3, int arg4, int arg5, int goto badframe; if (__get_user(set.sig[0], &frame->sc.oldmask) - || (_IA32_NSIG_WORDS > 1 && __copy_from_user((char *) &set.sig + 4, &frame->extramask, + || (_COMPAT_NSIG_WORDS > 1 && __copy_from_user((char *) &set.sig + 4, &frame->extramask, sizeof(frame->extramask)))) goto badframe; diff --git a/arch/ia64/ia32/ia32_support.c b/arch/ia64/ia32/ia32_support.c index 9d0d71ef57d9..1280c806e43b 100644 --- a/arch/ia64/ia32/ia32_support.c +++ b/arch/ia64/ia32/ia32_support.c @@ -95,8 +95,6 @@ ia32_load_state (struct task_struct *t) struct pt_regs *regs = ia64_task_regs(t); int nr = smp_processor_id(); /* LDT and TSS depend on CPU number: */ - nr = smp_processor_id(); - eflag = t->thread.eflag; fsr = t->thread.fsr; fcr = t->thread.fcr; diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index cc2a8a7e4ba3..c51bcbb5084c 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -6,7 +6,7 @@ * Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com> * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 2000-2002 Hewlett-Packard Co + * Copyright (C) 2000-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * These routines maintain argument size conversion between 32bit and 64bit @@ -609,61 +609,6 @@ sys32_pipe (int *fd) return retval; } -static inline int -put_statfs (struct statfs32 *ubuf, struct statfs *kbuf) -{ - int err; - - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf))) - return -EFAULT; - - err = __put_user(kbuf->f_type, &ubuf->f_type); - err |= __put_user(kbuf->f_bsize, &ubuf->f_bsize); - err |= __put_user(kbuf->f_blocks, &ubuf->f_blocks); - err |= __put_user(kbuf->f_bfree, &ubuf->f_bfree); - err |= __put_user(kbuf->f_bavail, &ubuf->f_bavail); - err |= __put_user(kbuf->f_files, &ubuf->f_files); - err |= __put_user(kbuf->f_ffree, &ubuf->f_ffree); - err |= __put_user(kbuf->f_namelen, &ubuf->f_namelen); - err |= __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]); - err |= __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]); - return err; -} - -extern asmlinkage long sys_statfs(const char * path, struct statfs * buf); - -asmlinkage long -sys32_statfs (const char *path, struct statfs32 *buf) -{ - int ret; - struct statfs s; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret = sys_statfs(path, &s); - set_fs(old_fs); - if (put_statfs(buf, &s)) - return -EFAULT; - return ret; -} - -extern asmlinkage long sys_fstatfs(unsigned int fd, struct statfs * buf); - -asmlinkage long -sys32_fstatfs (unsigned int fd, struct statfs32 *buf) -{ - int ret; - struct statfs s; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret = sys_fstatfs(fd, &s); - set_fs(old_fs); - if (put_statfs(buf, &s)) - return -EFAULT; - return ret; -} - static inline long get_tv32 (struct timeval *o, struct compat_timeval *i) { @@ -1849,10 +1794,10 @@ struct ipc_perm32 { struct ipc64_perm32 { key_t key; - __kernel_uid32_t32 uid; - __kernel_gid32_t32 gid; - __kernel_uid32_t32 cuid; - __kernel_gid32_t32 cgid; + compat_uid32_t uid; + compat_gid32_t gid; + compat_uid32_t cuid; + compat_gid32_t cgid; compat_mode_t mode; unsigned short __pad1; unsigned short seq; @@ -1895,8 +1840,8 @@ struct msqid_ds32 { unsigned short msg_cbytes; unsigned short msg_qnum; unsigned short msg_qbytes; - __kernel_ipc_pid_t32 msg_lspid; - __kernel_ipc_pid_t32 msg_lrpid; + compat_ipc_pid_t msg_lspid; + compat_ipc_pid_t msg_lrpid; }; struct msqid64_ds32 { @@ -1922,8 +1867,8 @@ struct shmid_ds32 { compat_time_t shm_atime; compat_time_t shm_dtime; compat_time_t shm_ctime; - __kernel_ipc_pid_t32 shm_cpid; - __kernel_ipc_pid_t32 shm_lpid; + compat_ipc_pid_t shm_cpid; + compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; }; @@ -2011,6 +1956,10 @@ semctl32 (int first, int second, int third, void *uptr) else fourth.__pad = (void *)A(pad); switch (third) { + default: + err = -EINVAL; + break; + case IPC_INFO: case IPC_RMID: case IPC_SET: @@ -2399,7 +2348,7 @@ shmctl32 (int first, int second, void *uptr) static long semtimedop32(int semid, struct sembuf *tsems, int nsems, - const struct timespec32 *timeout32) + const struct compat_timespec *timeout32) { struct timespec t; if (get_user (t.tv_sec, &timeout32->tv_sec) || @@ -2422,7 +2371,7 @@ sys32_ipc (u32 call, int first, int second, int third, u32 ptr, u32 fifth) return sys_semtimedop(first, (struct sembuf *)AA(ptr), second, NULL); case SEMTIMEDOP: return semtimedop32(first, (struct sembuf *)AA(ptr), second, - (const struct timespec32 *)AA(fifth)); + (const struct compat_timespec *)AA(fifth)); case SEMGET: return sys_semget(first, second, third); case SEMCTL: @@ -3475,12 +3424,6 @@ sys32_fstat64 (unsigned int fd, struct stat64 *statbuf) return ret; } -asmlinkage long -sys32_sigpending (unsigned int *set) -{ - return do_sigpending(set, sizeof(*set)); -} - struct sysinfo32 { s32 uptime; u32 loads[3]; @@ -3536,7 +3479,7 @@ sys32_sched_rr_get_interval (pid_t pid, struct compat_timespec *interval) set_fs(KERNEL_DS); ret = sys_sched_rr_get_interval(pid, &t); set_fs(old_fs); - if (put_user (t.tv_sec, &interval->tv_sec) || put_user (t.tv_nsec, &interval->tv_nsec)) + if (put_compat_timespec(&t, interval)) return -EFAULT; return ret; } diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 7d466721ecca..e37fa087ffe5 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -10,6 +10,7 @@ obj-y := acpi.o entry.o gate.o efi.o efi_stub.o ia64_ksyms.o \ semaphore.o setup.o \ signal.o sys_ia64.o traps.o time.o unaligned.o unwind.o +obj-$(CONFIG_FSYS) += fsys.o obj-$(CONFIG_IOSAPIC) += iosapic.o obj-$(CONFIG_IA64_PALINFO) += palinfo.o obj-$(CONFIG_EFI_VARS) += efivars.o diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index fa757e40fa2f..b73b8e12161c 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -3,7 +3,7 @@ * * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999,2000 Walt Drummond <drummond@valinux.com> - * Copyright (C) 2000, 2002 Hewlett-Packard Co. + * Copyright (C) 2000, 2002-2003 Hewlett-Packard Co. * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 2000 Intel Corp. * Copyright (C) 2000,2001 J.I. Lee <jung-ik.lee@intel.com> @@ -75,20 +75,20 @@ acpi_get_sysname (void) rsdp_phys = acpi_find_rsdp(); if (!rsdp_phys) { - printk("ACPI 2.0 RSDP not found, default to \"dig\"\n"); + printk(KERN_ERR "ACPI 2.0 RSDP not found, default to \"dig\"\n"); return "dig"; } rsdp = (struct acpi20_table_rsdp *) __va(rsdp_phys); if (strncmp(rsdp->signature, RSDP_SIG, sizeof(RSDP_SIG) - 1)) { - printk("ACPI 2.0 RSDP signature incorrect, default to \"dig\"\n"); + printk(KERN_ERR "ACPI 2.0 RSDP signature incorrect, default to \"dig\"\n"); return "dig"; } xsdt = (struct acpi_table_xsdt *) __va(rsdp->xsdt_address); hdr = &xsdt->header; if (strncmp(hdr->signature, XSDT_SIG, sizeof(XSDT_SIG) - 1)) { - printk("ACPI 2.0 XSDT signature incorrect, default to \"dig\"\n"); + printk(KERN_ERR "ACPI 2.0 XSDT signature incorrect, default to \"dig\"\n"); return "dig"; } @@ -128,7 +128,7 @@ acpi_get_sysname (void) * with a list of acpi_resource structures. */ acpi_status -acpi_get_crs (acpi_handle obj, acpi_buffer *buf) +acpi_get_crs (acpi_handle obj, struct acpi_buffer *buf) { acpi_status result; buf->length = 0; @@ -144,10 +144,10 @@ acpi_get_crs (acpi_handle obj, acpi_buffer *buf) return acpi_get_current_resources(obj, buf); } -acpi_resource * -acpi_get_crs_next (acpi_buffer *buf, int *offset) +struct acpi_resource * +acpi_get_crs_next (struct acpi_buffer *buf, int *offset) { - acpi_resource *res; + struct acpi_resource *res; if (*offset >= buf->length) return NULL; @@ -157,11 +157,11 @@ acpi_get_crs_next (acpi_buffer *buf, int *offset) return res; } -acpi_resource_data * -acpi_get_crs_type (acpi_buffer *buf, int *offset, int type) +union acpi_resource_data * +acpi_get_crs_type (struct acpi_buffer *buf, int *offset, int type) { for (;;) { - acpi_resource *res = acpi_get_crs_next(buf, offset); + struct acpi_resource *res = acpi_get_crs_next(buf, offset); if (!res) return NULL; if (res->id == type) @@ -170,7 +170,7 @@ acpi_get_crs_type (acpi_buffer *buf, int *offset, int type) } void -acpi_dispose_crs (acpi_buffer *buf) +acpi_dispose_crs (struct acpi_buffer *buf) { kfree(buf->pointer); } @@ -199,7 +199,7 @@ acpi_request_vector (u32 int_type) /* correctable platform error interrupt */ vector = platform_intr_list[int_type]; } else - printk("acpi_request_vector(): invalid interrupt type\n"); + printk(KERN_ERR "acpi_request_vector(): invalid interrupt type\n"); return vector; } @@ -249,7 +249,7 @@ acpi_parse_lsapic (acpi_table_entry_header *header) acpi_table_print_madt_entry(header); - printk("CPU %d (0x%04x)", total_cpus, (lsapic->id << 8) | lsapic->eid); + printk(KERN_INFO "CPU %d (0x%04x)", total_cpus, (lsapic->id << 8) | lsapic->eid); if (lsapic->flags.enabled) { available_cpus++; @@ -478,8 +478,8 @@ acpi_numa_slit_init (struct acpi_table_slit *slit) len = sizeof(struct acpi_table_header) + 8 + slit->localities * slit->localities; if (slit->header.length != len) { - printk("ACPI 2.0 SLIT: size mismatch: %d expected, %d actual\n", - len, slit->header.length); + printk(KERN_ERR "ACPI 2.0 SLIT: size mismatch: %d expected, %d actual\n", + len, slit->header.length); memset(numa_slit, 10, sizeof(numa_slit)); return; } @@ -514,8 +514,8 @@ acpi_numa_memory_affinity_init (struct acpi_table_memory_affinity *ma) size = (size << 32) | ma->length_lo; if (num_memblks >= NR_MEMBLKS) { - printk("Too many mem chunks in SRAT. Ignoring %ld MBytes at %lx\n", - size/(1024*1024), paddr); + printk(KERN_ERR "Too many mem chunks in SRAT. Ignoring %ld MBytes at %lx\n", + size/(1024*1024), paddr); return; } @@ -545,8 +545,8 @@ acpi_numa_memory_affinity_init (struct acpi_table_memory_affinity *ma) if (min_hole_size) { if (min_hole_size > size) { - printk("Too huge memory hole. Ignoring %ld MBytes at %lx\n", - size/(1024*1024), paddr); + printk(KERN_ERR "Too huge memory hole. Ignoring %ld MBytes at %lx\n", + size/(1024*1024), paddr); return; } } @@ -605,8 +605,8 @@ acpi_numa_arch_fixup(void) for (i = 0; i < srat_num_cpus; i++) node_cpuid[i].nid = pxm_to_nid_map[node_cpuid[i].nid]; - printk("Number of logical nodes in system = %d\n", numnodes); - printk("Number of memory chunks in system = %d\n", num_memblks); + printk(KERN_INFO "Number of logical nodes in system = %d\n", numnodes); + printk(KERN_INFO "Number of memory chunks in system = %d\n", num_memblks); if (!slit_table) return; memset(numa_slit, -1, sizeof(numa_slit)); @@ -638,7 +638,7 @@ static int __init acpi_parse_fadt (unsigned long phys_addr, unsigned long size) { struct acpi_table_header *fadt_header; - fadt_descriptor_rev2 *fadt; + struct fadt_descriptor_rev2 *fadt; u32 sci_irq, gsi_base; char *iosapic_address; @@ -649,7 +649,7 @@ acpi_parse_fadt (unsigned long phys_addr, unsigned long size) if (fadt_header->revision != 3) return -ENODEV; /* Only deal with ACPI 2.0 FADT */ - fadt = (fadt_descriptor_rev2 *) fadt_header; + fadt = (struct fadt_descriptor_rev2 *) fadt_header; if (!(fadt->iapc_boot_arch & BAF_8042_KEYBOARD_CONTROLLER)) acpi_kbd_controller_present = 0; @@ -806,7 +806,7 @@ acpi_boot_init (char *cmdline) #ifdef CONFIG_SMP if (available_cpus == 0) { - printk("ACPI: Found 0 CPUS; assuming 1\n"); + printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n"); available_cpus = 1; /* We've got at least one of these, no? */ } smp_boot_data.cpu_count = total_cpus; @@ -817,7 +817,7 @@ acpi_boot_init (char *cmdline) #endif #endif /* Make boot-up look pretty */ - printk("%d CPUs available, %d CPUs total\n", available_cpus, total_cpus); + printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus, total_cpus); return 0; } @@ -888,4 +888,26 @@ acpi_irq_to_vector (u32 irq) return gsi_to_vector(irq); } +int __init +acpi_register_irq (u32 gsi, u32 polarity, u32 trigger) +{ + int vector = 0; + u32 irq_base; + char *iosapic_address; + + if (acpi_madt->flags.pcat_compat && (gsi < 16)) + return isa_irq_to_vector(gsi); + + if (!iosapic_register_intr) + return 0; + + /* Find the IOSAPIC */ + if (!acpi_find_iosapic(gsi, &irq_base, &iosapic_address)) { + /* Turn it on */ + vector = iosapic_register_intr (gsi, polarity, trigger, + irq_base, iosapic_address); + } + return vector; +} + #endif /* CONFIG_ACPI_BOOT */ diff --git a/arch/ia64/kernel/brl_emu.c b/arch/ia64/kernel/brl_emu.c index 6101686da2a9..541addcbe50c 100644 --- a/arch/ia64/kernel/brl_emu.c +++ b/arch/ia64/kernel/brl_emu.c @@ -195,7 +195,7 @@ ia64_emulate_brl (struct pt_regs *regs, unsigned long ar_ec) /* * The target address contains unimplemented bits. */ - printk("Woah! Unimplemented Instruction Address Trap!\n"); + printk(KERN_DEBUG "Woah! Unimplemented Instruction Address Trap!\n"); siginfo.si_signo = SIGILL; siginfo.si_errno = 0; siginfo.si_flags = 0; diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index bd74d72cb924..78c8c05096c8 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -5,7 +5,7 @@ * * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> - * Copyright (C) 1999-2002 Hewlett-Packard Co. + * Copyright (C) 1999-2003 Hewlett-Packard Co. * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * @@ -33,15 +33,6 @@ #define EFI_DEBUG 0 -#ifdef CONFIG_HUGETLB_PAGE - -/* By default at total of 512MB is reserved huge pages. */ -#define HTLBZONE_SIZE_DEFAULT 0x20000000 - -unsigned long htlbzone_pages = (HTLBZONE_SIZE_DEFAULT >> HPAGE_SHIFT); - -#endif - extern efi_status_t efi_call_phys (void *, ...); struct efi efi; @@ -374,7 +365,7 @@ efi_memmap_walk (efi_freemem_callback_t callback, void *arg) prev_valid = 1; } else { if (curr.start < prev.start) - printk("Oops: EFI memory table not ordered!\n"); + printk(KERN_ERR "Oops: EFI memory table not ordered!\n"); if (prev.end == curr.start) { /* merge two consecutive memory ranges */ @@ -446,7 +437,8 @@ efi_map_pal_code (void) * dedicated ITR for the PAL code. */ if ((vaddr & mask) == (KERNEL_START & mask)) { - printk("%s: no need to install ITR for PAL code\n", __FUNCTION__); + printk(KERN_INFO "%s: no need to install ITR for PAL code\n", + __FUNCTION__); continue; } @@ -454,7 +446,7 @@ efi_map_pal_code (void) panic("Woah! PAL code size bigger than a granule!"); mask = ~((1 << IA64_GRANULE_SHIFT) - 1); - printk("CPU %d: mapping PAL code [0x%lx-0x%lx) into [0x%lx-0x%lx)\n", + printk(KERN_INFO "CPU %d: mapping PAL code [0x%lx-0x%lx) into [0x%lx-0x%lx)\n", smp_processor_id(), md->phys_addr, md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT), vaddr & mask, (vaddr & mask) + IA64_GRANULE_SIZE); @@ -497,27 +489,8 @@ efi_init (void) ++cp; } } -#ifdef CONFIG_HUGETLB_PAGE - /* Just duplicating the above algo for lpzone start */ - for (cp = saved_command_line; *cp; ) { - if (memcmp(cp, "lpmem=", 6) == 0) { - cp += 6; - htlbzone_pages = memparse(cp, &end); - htlbzone_pages = (htlbzone_pages >> HPAGE_SHIFT); - if (end != cp) - break; - cp = end; - } else { - while (*cp != ' ' && *cp) - ++cp; - while (*cp == ' ') - ++cp; - } - } - printk("Total HugeTLB_Page memory pages requested 0x%lx \n", htlbzone_pages); -#endif if (mem_limit != ~0UL) - printk("Ignoring memory above %luMB\n", mem_limit >> 20); + printk(KERN_INFO "Ignoring memory above %luMB\n", mem_limit >> 20); efi.systab = __va(ia64_boot_param->efi_systab); @@ -529,7 +502,7 @@ efi_init (void) if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) panic("Woah! EFI system table signature incorrect\n"); if ((efi.systab->hdr.revision ^ EFI_SYSTEM_TABLE_REVISION) >> 16 != 0) - printk("Warning: EFI system table major version mismatch: " + printk(KERN_WARNING "Warning: EFI system table major version mismatch: " "got %d.%02d, expected %d.%02d\n", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, EFI_SYSTEM_TABLE_REVISION >> 16, EFI_SYSTEM_TABLE_REVISION & 0xffff); @@ -544,7 +517,7 @@ efi_init (void) vendor[i] = '\0'; } - printk("EFI v%u.%.02u by %s:", + printk(KERN_INFO "EFI v%u.%.02u by %s:", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); for (i = 0; i < efi.systab->nr_tables; i++) { @@ -636,7 +609,7 @@ efi_enter_virtual_mode (void) | _PAGE_PL_0 | _PAGE_AR_RW)); #else - printk("EFI_MEMORY_WC mapping\n"); + printk(KERN_INFO "EFI_MEMORY_WC mapping\n"); md->virt_addr = (u64) ioremap(md->phys_addr, 0); #endif } else if (md->attribute & EFI_MEMORY_WT) { @@ -646,7 +619,7 @@ efi_enter_virtual_mode (void) | _PAGE_PL_0 | _PAGE_AR_RW)); #else - printk("EFI_MEMORY_WT mapping\n"); + printk(KERN_INFO "EFI_MEMORY_WT mapping\n"); md->virt_addr = (u64) ioremap(md->phys_addr, 0); #endif } @@ -658,7 +631,8 @@ efi_enter_virtual_mode (void) efi_desc_size, ia64_boot_param->efi_memdesc_version, ia64_boot_param->efi_memmap); if (status != EFI_SUCCESS) { - printk("Warning: unable to switch EFI into virtual mode (status=%lu)\n", status); + printk(KERN_WARNING "warning: unable to switch EFI into virtual mode " + "(status=%lu)\n", status); return; } diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 5907111d2a67..5ed695e62d4d 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -3,7 +3,7 @@ * * Kernel entry points. * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> @@ -22,8 +22,8 @@ /* * Global (preserved) predicate usage on syscall entry/exit path: * - * pKern: See entry.h. - * pUser: See entry.h. + * pKStk: See entry.h. + * pUStk: See entry.h. * pSys: See entry.h. * pNonSys: !pSys */ @@ -63,7 +63,7 @@ ENTRY(ia64_execve) sxt4 r8=r8 // return 64-bit result ;; stf.spill [sp]=f0 -(p6) cmp.ne pKern,pUser=r0,r0 // a successful execve() lands us in user-mode... +(p6) cmp.ne pKStk,pUStk=r0,r0 // a successful execve() lands us in user-mode... mov rp=loc0 (p6) mov ar.pfs=r0 // clear ar.pfs on success (p7) br.ret.sptk.many rp @@ -193,7 +193,7 @@ GLOBAL_ENTRY(ia64_switch_to) ;; (p6) srlz.d ld8 sp=[r21] // load kernel stack pointer of new task - mov IA64_KR(CURRENT)=r20 // update "current" application register + mov IA64_KR(CURRENT)=in0 // update "current" application register mov r8=r13 // return pointer to previously running task mov r13=in0 // set "current" pointer ;; @@ -507,7 +507,14 @@ END(invoke_syscall_trace) GLOBAL_ENTRY(ia64_trace_syscall) PT_REGS_UNWIND_INFO(0) +{ /* + * Some versions of gas generate bad unwind info if the first instruction of a + * procedure doesn't go into the first slot of a bundle. This is a workaround. + */ + nop.m 0 + nop.i 0 br.call.sptk.many rp=invoke_syscall_trace // give parent a chance to catch syscall args +} .ret6: br.call.sptk.many rp=b6 // do the syscall strace_check_retval: cmp.lt p6,p0=r8,r0 // syscall failed? @@ -537,12 +544,19 @@ END(ia64_trace_syscall) GLOBAL_ENTRY(ia64_ret_from_clone) PT_REGS_UNWIND_INFO(0) +{ /* + * Some versions of gas generate bad unwind info if the first instruction of a + * procedure doesn't go into the first slot of a bundle. This is a workaround. + */ + nop.m 0 + nop.i 0 /* * We need to call schedule_tail() to complete the scheduling process. * Called by ia64_switch_to() after do_fork()->copy_thread(). r8 contains the * address of the previously executing task. */ br.call.sptk.many rp=ia64_invoke_schedule_tail +} .ret8: adds r2=TI_FLAGS+IA64_TASK_SIZE,r13 ;; @@ -569,11 +583,12 @@ END(ia64_ret_from_syscall) // fall through GLOBAL_ENTRY(ia64_leave_kernel) PT_REGS_UNWIND_INFO(0) - // work.need_resched etc. mustn't get changed by this CPU before it returns to userspace: -(pUser) cmp.eq.unc p6,p0=r0,r0 // p6 <- pUser -(pUser) rsm psr.i + // work.need_resched etc. mustn't get changed by this CPU before it returns to + // user- or fsys-mode: +(pUStk) cmp.eq.unc p6,p0=r0,r0 // p6 <- pUStk +(pUStk) rsm psr.i ;; -(pUser) adds r17=TI_FLAGS+IA64_TASK_SIZE,r13 +(pUStk) adds r17=TI_FLAGS+IA64_TASK_SIZE,r13 ;; .work_processed: (p6) ld4 r18=[r17] // load current_thread_info()->flags @@ -635,9 +650,9 @@ GLOBAL_ENTRY(ia64_leave_kernel) ;; srlz.i // ensure interruption collection is off mov b7=r15 + bsw.0 // switch back to bank 0 (no stop bit required beforehand...) ;; - bsw.0 // switch back to bank 0 - ;; +(pUStk) mov r18=IA64_KR(CURRENT) // Itanium 2: 12 cycle read latency adds r16=16,r12 adds r17=24,r12 ;; @@ -665,16 +680,21 @@ GLOBAL_ENTRY(ia64_leave_kernel) ;; ld8.fill r12=[r16],16 ld8.fill r13=[r17],16 +(pUStk) adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18 ;; ld8.fill r14=[r16] ld8.fill r15=[r17] +(pUStk) mov r17=1 + ;; +(pUStk) st1 [r18]=r17 // restore current->thread.on_ustack shr.u r18=r19,16 // get byte size of existing "dirty" partition ;; mov r16=ar.bsp // get existing backing store pointer movl r17=THIS_CPU(ia64_phys_stacked_size_p8) ;; ld4 r17=[r17] // r17 = cpu_data->phys_stacked_size_p8 -(pKern) br.cond.dpnt skip_rbs_switch +(pKStk) br.cond.dpnt skip_rbs_switch + /* * Restore user backing store. * @@ -710,21 +730,9 @@ dont_preserve_current_frame: shr.u loc1=r18,9 // RNaTslots <= dirtySize / (64*8) + 1 sub r17=r17,r18 // r17 = (physStackedSize + 8) - dirtySize ;; -#if 1 - .align 32 // see comment below about gas bug... -#endif mov ar.rsc=r19 // load ar.rsc to be used for "loadrs" shladd in0=loc1,3,r17 mov in1=0 -#if 0 - // gas-2.12.90 is unable to generate a stop bit after .align, which is bad, - // because alloc must be at the beginning of an insn-group. - .align 32 -#else - nop 0 - nop 0 - nop 0 -#endif ;; rse_clear_invalid: #ifdef CONFIG_ITANIUM @@ -788,12 +796,12 @@ rse_clear_invalid: skip_rbs_switch: mov b6=rB6 mov ar.pfs=rARPFS -(pUser) mov ar.bspstore=rARBSPSTORE +(pUStk) mov ar.bspstore=rARBSPSTORE (p9) mov cr.ifs=rCRIFS mov cr.ipsr=rCRIPSR mov cr.iip=rCRIIP ;; -(pUser) mov ar.rnat=rARRNAT // must happen with RSE in lazy mode +(pUStk) mov ar.rnat=rARRNAT // must happen with RSE in lazy mode mov ar.rsc=rARRSC mov ar.unat=rARUNAT mov pr=rARPR,-1 @@ -963,17 +971,16 @@ ENTRY(sys_rt_sigreturn) END(sys_rt_sigreturn) GLOBAL_ENTRY(ia64_prepare_handle_unaligned) - // - // r16 = fake ar.pfs, we simply need to make sure - // privilege is still 0 - // - mov r16=r0 .prologue + /* + * r16 = fake ar.pfs, we simply need to make sure privilege is still 0 + */ + mov r16=r0 DO_SAVE_SWITCH_STACK - br.call.sptk.many rp=ia64_handle_unaligned // stack frame setup in ivt + br.call.sptk.many rp=ia64_handle_unaligned // stack frame setup in ivt .ret21: .body DO_LOAD_SWITCH_STACK - br.cond.sptk.many rp // goes to ia64_leave_kernel + br.cond.sptk.many rp // goes to ia64_leave_kernel END(ia64_prepare_handle_unaligned) // @@ -1235,8 +1242,8 @@ sys_call_table: data8 sys_sched_setaffinity data8 sys_sched_getaffinity data8 sys_set_tid_address - data8 ia64_ni_syscall // available. (was sys_alloc_hugepages) - data8 ia64_ni_syscall // available (was sys_free_hugepages) + data8 ia64_ni_syscall + data8 ia64_ni_syscall // 1235 data8 sys_exit_group data8 sys_lookup_dcookie data8 sys_io_setup diff --git a/arch/ia64/kernel/entry.h b/arch/ia64/kernel/entry.h index fb80a0461569..b7db22533114 100644 --- a/arch/ia64/kernel/entry.h +++ b/arch/ia64/kernel/entry.h @@ -4,8 +4,8 @@ * Preserved registers that are shared between code in ivt.S and entry.S. Be * careful not to step on these! */ -#define pKern p2 /* will leave_kernel return to kernel-mode? */ -#define pUser p3 /* will leave_kernel return to user-mode? */ +#define pKStk p2 /* will leave_kernel return to kernel-stacks? */ +#define pUStk p3 /* will leave_kernel return to user-stacks? */ #define pSys p4 /* are we processing a (synchronous) system call? */ #define pNonSys p5 /* complement of pSys */ diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S new file mode 100644 index 000000000000..200d66891b1c --- /dev/null +++ b/arch/ia64/kernel/fsys.S @@ -0,0 +1,384 @@ +/* + * This file contains the light-weight system call handlers (fsyscall-handlers). + * + * Copyright (C) 2003 Hewlett-Packard Co + * David Mosberger-Tang <davidm@hpl.hp.com> + */ + +#include <asm/asmmacro.h> +#include <asm/errno.h> +#include <asm/offsets.h> +#include <asm/thread_info.h> + +/* + * See Documentation/ia64/fsys.txt for details on fsyscalls. + * + * On entry to an fsyscall handler: + * r10 = 0 (i.e., defaults to "successful syscall return") + * r11 = saved ar.pfs (a user-level value) + * r15 = system call number + * r16 = "current" task pointer (in normal kernel-mode, this is in r13) + * r32-r39 = system call arguments + * b6 = return address (a user-level value) + * ar.pfs = previous frame-state (a user-level value) + * PSR.be = cleared to zero (i.e., little-endian byte order is in effect) + * all other registers may contain values passed in from user-mode + * + * On return from an fsyscall handler: + * r11 = saved ar.pfs (as passed into the fsyscall handler) + * r15 = system call number (as passed into the fsyscall handler) + * r32-r39 = system call arguments (as passed into the fsyscall handler) + * b6 = return address (as passed into the fsyscall handler) + * ar.pfs = previous frame-state (as passed into the fsyscall handler) + */ + +ENTRY(fsys_ni_syscall) + mov r8=ENOSYS + mov r10=-1 + MCKINLEY_E9_WORKAROUND + br.ret.sptk.many b6 +END(fsys_ni_syscall) + +ENTRY(fsys_getpid) + add r9=TI_FLAGS+IA64_TASK_SIZE,r16 + ;; + ld4 r9=[r9] + add r8=IA64_TASK_TGID_OFFSET,r16 + ;; + and r9=TIF_ALLWORK_MASK,r9 + ld4 r8=[r8] // r8 = current->tgid + ;; + cmp.ne p8,p0=0,r9 +(p8) br.spnt.many fsys_fallback_syscall + MCKINLEY_E9_WORKAROUND + br.ret.sptk.many b6 +END(fsys_getpid) + +ENTRY(fsys_getppid) + add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16 + ;; + ld8 r17=[r17] // r17 = current->group_leader + add r9=TI_FLAGS+IA64_TASK_SIZE,r16 + ;; + + ld4 r9=[r9] + add r17=IA64_TASK_REAL_PARENT_OFFSET,r17 // r17 = ¤t->group_leader->real_parent + ;; + and r9=TIF_ALLWORK_MASK,r9 + +1: ld8 r18=[r17] // r18 = current->group_leader->real_parent + ;; + cmp.ne p8,p0=0,r9 + add r8=IA64_TASK_TGID_OFFSET,r18 // r8 = ¤t->group_leader->real_parent->tgid + ;; + + /* + * The .acq is needed to ensure that the read of tgid has returned its data before + * we re-check "real_parent". + */ + ld4.acq r8=[r8] // r8 = current->group_leader->real_parent->tgid +#ifdef CONFIG_SMP + /* + * Re-read current->group_leader->real_parent. + */ + ld8 r19=[r17] // r19 = current->group_leader->real_parent +(p8) br.spnt.many fsys_fallback_syscall + ;; + cmp.ne p6,p0=r18,r19 // did real_parent change? + mov r19=0 // i must not leak kernel bits... +(p6) br.cond.spnt.few 1b // yes -> redo the read of tgid and the check + ;; + mov r17=0 // i must not leak kernel bits... + mov r18=0 // i must not leak kernel bits... +#else + mov r17=0 // i must not leak kernel bits... + mov r18=0 // i must not leak kernel bits... + mov r19=0 // i must not leak kernel bits... +#endif + MCKINLEY_E9_WORKAROUND + br.ret.sptk.many b6 +END(fsys_getppid) + +ENTRY(fsys_set_tid_address) + add r9=TI_FLAGS+IA64_TASK_SIZE,r16 + ;; + ld4 r9=[r9] + tnat.z p6,p7=r32 // check argument register for being NaT + ;; + and r9=TIF_ALLWORK_MASK,r9 + add r8=IA64_TASK_PID_OFFSET,r16 + add r18=IA64_TASK_CLEAR_CHILD_TID_OFFSET,r16 + ;; + ld4 r8=[r8] + cmp.ne p8,p0=0,r9 + mov r17=-1 + ;; +(p6) st8 [r18]=r32 +(p7) st8 [r18]=r17 +(p8) br.spnt.many fsys_fallback_syscall + ;; + mov r17=0 // i must not leak kernel bits... + mov r18=0 // i must not leak kernel bits... + MCKINLEY_E9_WORKAROUND + br.ret.sptk.many b6 +END(fsys_set_tid_address) + + .rodata + .align 8 + .globl fsyscall_table +fsyscall_table: + data8 fsys_ni_syscall + data8 fsys_fallback_syscall // exit // 1025 + data8 fsys_fallback_syscall // read + data8 fsys_fallback_syscall // write + data8 fsys_fallback_syscall // open + data8 fsys_fallback_syscall // close + data8 fsys_fallback_syscall // creat // 1030 + data8 fsys_fallback_syscall // link + data8 fsys_fallback_syscall // unlink + data8 fsys_fallback_syscall // execve + data8 fsys_fallback_syscall // chdir + data8 fsys_fallback_syscall // fchdir // 1035 + data8 fsys_fallback_syscall // utimes + data8 fsys_fallback_syscall // mknod + data8 fsys_fallback_syscall // chmod + data8 fsys_fallback_syscall // chown + data8 fsys_fallback_syscall // lseek // 1040 + data8 fsys_getpid + data8 fsys_getppid // getppid + data8 fsys_fallback_syscall // mount + data8 fsys_fallback_syscall // umount + data8 fsys_fallback_syscall // setuid // 1045 + data8 fsys_fallback_syscall // getuid + data8 fsys_fallback_syscall // geteuid + data8 fsys_fallback_syscall // ptrace + data8 fsys_fallback_syscall // access + data8 fsys_fallback_syscall // sync // 1050 + data8 fsys_fallback_syscall // fsync + data8 fsys_fallback_syscall // fdatasync + data8 fsys_fallback_syscall // kill + data8 fsys_fallback_syscall // rename + data8 fsys_fallback_syscall // mkdir // 1055 + data8 fsys_fallback_syscall // rmdir + data8 fsys_fallback_syscall // dup + data8 fsys_fallback_syscall // pipe + data8 fsys_fallback_syscall // times + data8 fsys_fallback_syscall // brk // 1060 + data8 fsys_fallback_syscall // setgid + data8 fsys_fallback_syscall // getgid + data8 fsys_fallback_syscall // getegid + data8 fsys_fallback_syscall // acct + data8 fsys_fallback_syscall // ioctl // 1065 + data8 fsys_fallback_syscall // fcntl + data8 fsys_fallback_syscall // umask + data8 fsys_fallback_syscall // chroot + data8 fsys_fallback_syscall // ustat + data8 fsys_fallback_syscall // dup2 // 1070 + data8 fsys_fallback_syscall // setreuid + data8 fsys_fallback_syscall // setregid + data8 fsys_fallback_syscall // getresuid + data8 fsys_fallback_syscall // setresuid + data8 fsys_fallback_syscall // getresgid // 1075 + data8 fsys_fallback_syscall // setresgid + data8 fsys_fallback_syscall // getgroups + data8 fsys_fallback_syscall // setgroups + data8 fsys_fallback_syscall // getpgid + data8 fsys_fallback_syscall // setpgid // 1080 + data8 fsys_fallback_syscall // setsid + data8 fsys_fallback_syscall // getsid + data8 fsys_fallback_syscall // sethostname + data8 fsys_fallback_syscall // setrlimit + data8 fsys_fallback_syscall // getrlimit // 1085 + data8 fsys_fallback_syscall // getrusage + data8 fsys_fallback_syscall // gettimeofday + data8 fsys_fallback_syscall // settimeofday + data8 fsys_fallback_syscall // select + data8 fsys_fallback_syscall // poll // 1090 + data8 fsys_fallback_syscall // symlink + data8 fsys_fallback_syscall // readlink + data8 fsys_fallback_syscall // uselib + data8 fsys_fallback_syscall // swapon + data8 fsys_fallback_syscall // swapoff // 1095 + data8 fsys_fallback_syscall // reboot + data8 fsys_fallback_syscall // truncate + data8 fsys_fallback_syscall // ftruncate + data8 fsys_fallback_syscall // fchmod + data8 fsys_fallback_syscall // fchown // 1100 + data8 fsys_fallback_syscall // getpriority + data8 fsys_fallback_syscall // setpriority + data8 fsys_fallback_syscall // statfs + data8 fsys_fallback_syscall // fstatfs + data8 fsys_fallback_syscall // gettid // 1105 + data8 fsys_fallback_syscall // semget + data8 fsys_fallback_syscall // semop + data8 fsys_fallback_syscall // semctl + data8 fsys_fallback_syscall // msgget + data8 fsys_fallback_syscall // msgsnd // 1110 + data8 fsys_fallback_syscall // msgrcv + data8 fsys_fallback_syscall // msgctl + data8 fsys_fallback_syscall // shmget + data8 fsys_fallback_syscall // shmat + data8 fsys_fallback_syscall // shmdt // 1115 + data8 fsys_fallback_syscall // shmctl + data8 fsys_fallback_syscall // syslog + data8 fsys_fallback_syscall // setitimer + data8 fsys_fallback_syscall // getitimer + data8 fsys_fallback_syscall // 1120 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // vhangup + data8 fsys_fallback_syscall // lchown + data8 fsys_fallback_syscall // remap_file_pages // 1125 + data8 fsys_fallback_syscall // wait4 + data8 fsys_fallback_syscall // sysinfo + data8 fsys_fallback_syscall // clone + data8 fsys_fallback_syscall // setdomainname + data8 fsys_fallback_syscall // newuname // 1130 + data8 fsys_fallback_syscall // adjtimex + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // init_module + data8 fsys_fallback_syscall // delete_module + data8 fsys_fallback_syscall // 1135 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // quotactl + data8 fsys_fallback_syscall // bdflush + data8 fsys_fallback_syscall // sysfs + data8 fsys_fallback_syscall // personality // 1140 + data8 fsys_fallback_syscall // afs_syscall + data8 fsys_fallback_syscall // setfsuid + data8 fsys_fallback_syscall // setfsgid + data8 fsys_fallback_syscall // getdents + data8 fsys_fallback_syscall // flock // 1145 + data8 fsys_fallback_syscall // readv + data8 fsys_fallback_syscall // writev + data8 fsys_fallback_syscall // pread64 + data8 fsys_fallback_syscall // pwrite64 + data8 fsys_fallback_syscall // sysctl // 1150 + data8 fsys_fallback_syscall // mmap + data8 fsys_fallback_syscall // munmap + data8 fsys_fallback_syscall // mlock + data8 fsys_fallback_syscall // mlockall + data8 fsys_fallback_syscall // mprotect // 1155 + data8 fsys_fallback_syscall // mremap + data8 fsys_fallback_syscall // msync + data8 fsys_fallback_syscall // munlock + data8 fsys_fallback_syscall // munlockall + data8 fsys_fallback_syscall // sched_getparam // 1160 + data8 fsys_fallback_syscall // sched_setparam + data8 fsys_fallback_syscall // sched_getscheduler + data8 fsys_fallback_syscall // sched_setscheduler + data8 fsys_fallback_syscall // sched_yield + data8 fsys_fallback_syscall // sched_get_priority_max // 1165 + data8 fsys_fallback_syscall // sched_get_priority_min + data8 fsys_fallback_syscall // sched_rr_get_interval + data8 fsys_fallback_syscall // nanosleep + data8 fsys_fallback_syscall // nfsservctl + data8 fsys_fallback_syscall // prctl // 1170 + data8 fsys_fallback_syscall // getpagesize + data8 fsys_fallback_syscall // mmap2 + data8 fsys_fallback_syscall // pciconfig_read + data8 fsys_fallback_syscall // pciconfig_write + data8 fsys_fallback_syscall // perfmonctl // 1175 + data8 fsys_fallback_syscall // sigaltstack + data8 fsys_fallback_syscall // rt_sigaction + data8 fsys_fallback_syscall // rt_sigpending + data8 fsys_fallback_syscall // rt_sigprocmask + data8 fsys_fallback_syscall // rt_sigqueueinfo // 1180 + data8 fsys_fallback_syscall // rt_sigreturn + data8 fsys_fallback_syscall // rt_sigsuspend + data8 fsys_fallback_syscall // rt_sigtimedwait + data8 fsys_fallback_syscall // getcwd + data8 fsys_fallback_syscall // capget // 1185 + data8 fsys_fallback_syscall // capset + data8 fsys_fallback_syscall // sendfile + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // socket // 1190 + data8 fsys_fallback_syscall // bind + data8 fsys_fallback_syscall // connect + data8 fsys_fallback_syscall // listen + data8 fsys_fallback_syscall // accept + data8 fsys_fallback_syscall // getsockname // 1195 + data8 fsys_fallback_syscall // getpeername + data8 fsys_fallback_syscall // socketpair + data8 fsys_fallback_syscall // send + data8 fsys_fallback_syscall // sendto + data8 fsys_fallback_syscall // recv // 1200 + data8 fsys_fallback_syscall // recvfrom + data8 fsys_fallback_syscall // shutdown + data8 fsys_fallback_syscall // setsockopt + data8 fsys_fallback_syscall // getsockopt + data8 fsys_fallback_syscall // sendmsg // 1205 + data8 fsys_fallback_syscall // recvmsg + data8 fsys_fallback_syscall // pivot_root + data8 fsys_fallback_syscall // mincore + data8 fsys_fallback_syscall // madvise + data8 fsys_fallback_syscall // newstat // 1210 + data8 fsys_fallback_syscall // newlstat + data8 fsys_fallback_syscall // newfstat + data8 fsys_fallback_syscall // clone2 + data8 fsys_fallback_syscall // getdents64 + data8 fsys_fallback_syscall // getunwind // 1215 + data8 fsys_fallback_syscall // readahead + data8 fsys_fallback_syscall // setxattr + data8 fsys_fallback_syscall // lsetxattr + data8 fsys_fallback_syscall // fsetxattr + data8 fsys_fallback_syscall // getxattr // 1220 + data8 fsys_fallback_syscall // lgetxattr + data8 fsys_fallback_syscall // fgetxattr + data8 fsys_fallback_syscall // listxattr + data8 fsys_fallback_syscall // llistxattr + data8 fsys_fallback_syscall // flistxattr // 1225 + data8 fsys_fallback_syscall // removexattr + data8 fsys_fallback_syscall // lremovexattr + data8 fsys_fallback_syscall // fremovexattr + data8 fsys_fallback_syscall // tkill + data8 fsys_fallback_syscall // futex // 1230 + data8 fsys_fallback_syscall // sched_setaffinity + data8 fsys_fallback_syscall // sched_getaffinity + data8 fsys_set_tid_address // set_tid_address + data8 fsys_fallback_syscall // unused + data8 fsys_fallback_syscall // unused // 1235 + data8 fsys_fallback_syscall // exit_group + data8 fsys_fallback_syscall // lookup_dcookie + data8 fsys_fallback_syscall // io_setup + data8 fsys_fallback_syscall // io_destroy + data8 fsys_fallback_syscall // io_getevents // 1240 + data8 fsys_fallback_syscall // io_submit + data8 fsys_fallback_syscall // io_cancel + data8 fsys_fallback_syscall // epoll_create + data8 fsys_fallback_syscall // epoll_ctl + data8 fsys_fallback_syscall // epoll_wait // 1245 + data8 fsys_fallback_syscall // restart_syscall + data8 fsys_fallback_syscall // semtimedop + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1250 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1255 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1260 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1265 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1270 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall // 1275 + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall + data8 fsys_fallback_syscall diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S index 1e34ad720b3e..302fc06fb04b 100644 --- a/arch/ia64/kernel/gate.S +++ b/arch/ia64/kernel/gate.S @@ -2,7 +2,7 @@ * This file contains the code that gets mapped at the upper end of each task's text * region. For now, it contains the signal trampoline code only. * - * Copyright (C) 1999-2002 Hewlett-Packard Co + * Copyright (C) 1999-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ @@ -14,6 +14,87 @@ #include <asm/page.h> .section .text.gate, "ax" +.start_gate: + + +#if CONFIG_FSYS + +#include <asm/errno.h> + +/* + * On entry: + * r11 = saved ar.pfs + * r15 = system call # + * b0 = saved return address + * b6 = return address + * On exit: + * r11 = saved ar.pfs + * r15 = system call # + * b0 = saved return address + * all other "scratch" registers: undefined + * all "preserved" registers: same as on entry + */ +GLOBAL_ENTRY(syscall_via_epc) + .prologue + .altrp b6 + .body +{ + /* + * Note: the kernel cannot assume that the first two instructions in this + * bundle get executed. The remaining code must be safe even if + * they do not get executed. + */ + adds r17=-1024,r15 + mov r10=0 // default to successful syscall execution + epc +} + ;; + rsm psr.be + movl r18=fsyscall_table + + mov r16=IA64_KR(CURRENT) + mov r19=255 + ;; + shladd r18=r17,3,r18 + cmp.geu p6,p0=r19,r17 // (syscall > 0 && syscall <= 1024+255)? + ;; + srlz.d // ensure little-endian byteorder is in effect +(p6) ld8 r18=[r18] + ;; +(p6) mov b7=r18 +(p6) br.sptk.many b7 + + mov r10=-1 + mov r8=ENOSYS + MCKINLEY_E9_WORKAROUND + br.ret.sptk.many b6 +END(syscall_via_epc) + +GLOBAL_ENTRY(syscall_via_break) + .prologue + .altrp b6 + .body + break 0x100000 + br.ret.sptk.many b6 +END(syscall_via_break) + +GLOBAL_ENTRY(fsys_fallback_syscall) + /* + * It would be better/fsyser to do the SAVE_MIN magic directly here, but for now + * we simply fall back on doing a system-call via break. Good enough + * to get started. (Note: we have to do this through the gate page again, since + * the br.ret will switch us back to user-level privilege.) + * + * XXX Move this back to fsys.S after changing it over to avoid break 0x100000. + */ + movl r2=(syscall_via_break - .start_gate) + GATE_ADDR + ;; + MCKINLEY_E9_WORKAROUND + mov b7=r2 + br.ret.sptk.many b7 +END(fsys_fallback_syscall) + +#endif /* CONFIG_FSYS */ # define ARG0_OFF (16 + IA64_SIGFRAME_ARG0_OFFSET) # define ARG1_OFF (16 + IA64_SIGFRAME_ARG1_OFFSET) @@ -63,15 +144,18 @@ * call stack. */ +#define SIGTRAMP_SAVES \ + .unwabi @svr4, 's' // mark this as a sigtramp handler (saves scratch regs) \ + .savesp ar.unat, UNAT_OFF+SIGCONTEXT_OFF \ + .savesp ar.fpsr, FPSR_OFF+SIGCONTEXT_OFF \ + .savesp pr, PR_OFF+SIGCONTEXT_OFF \ + .savesp rp, RP_OFF+SIGCONTEXT_OFF \ + .vframesp SP_OFF+SIGCONTEXT_OFF + GLOBAL_ENTRY(ia64_sigtramp) // describe the state that is active when we get here: .prologue - .unwabi @svr4, 's' // mark this as a sigtramp handler (saves scratch regs) - .savesp ar.unat, UNAT_OFF+SIGCONTEXT_OFF - .savesp ar.fpsr, FPSR_OFF+SIGCONTEXT_OFF - .savesp pr, PR_OFF+SIGCONTEXT_OFF - .savesp rp, RP_OFF+SIGCONTEXT_OFF - .vframesp SP_OFF+SIGCONTEXT_OFF + SIGTRAMP_SAVES .body .label_state 1 @@ -156,10 +240,11 @@ back_from_restore_rbs: ldf.fill f14=[base0],32 ldf.fill f15=[base1],32 mov r15=__NR_rt_sigreturn + .restore sp // pop .prologue break __BREAK_SYSCALL - .body - .copy_state 1 + .prologue + SIGTRAMP_SAVES setup_rbs: mov ar.rsc=0 // put RSE into enforced lazy mode ;; @@ -171,6 +256,7 @@ setup_rbs: ;; .spillsp ar.rnat, RNAT_OFF+SIGCONTEXT_OFF st8 [r14]=r16 // save sc_ar_rnat + .body adds r14=(LOADRS_OFF+SIGCONTEXT_OFF),sp mov.m r16=ar.bsp // sc_loadrs <- (new bsp - new bspstore) << 16 @@ -182,10 +268,11 @@ setup_rbs: ;; st8 [r14]=r15 // save sc_loadrs mov ar.rsc=0xf // set RSE into eager mode, pl 3 + .restore sp // pop .prologue br.cond.sptk back_from_setup_rbs .prologue - .copy_state 1 + SIGTRAMP_SAVES .spillsp ar.rnat, RNAT_OFF+SIGCONTEXT_OFF .body restore_rbs: diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index 55917acf140e..28dd4e66f7c1 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -5,7 +5,7 @@ * to set up the kernel's global pointer and jump to the kernel * entry point. * - * Copyright (C) 1998-2001 Hewlett-Packard Co + * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * Copyright (C) 1999 VA Linux Systems @@ -143,17 +143,14 @@ start_ap: movl r2=init_thread_union cmp.eq isBP,isAP=r0,r0 #endif - ;; - extr r3=r2,0,61 // r3 == phys addr of task struct mov r16=KERNEL_TR_PAGE_NUM ;; // load the "current" pointer (r13) and ar.k6 with the current task - mov r13=r2 - mov IA64_KR(CURRENT)=r3 // Physical address - + mov IA64_KR(CURRENT)=r2 // virtual address // initialize k4 to a safe value (64-128MB is mapped by TR_KERNEL) mov IA64_KR(CURRENT_STACK)=r16 + mov r13=r2 /* * Reserve space at the top of the stack for "struct pt_regs". Kernel threads * don't store interesting values in that structure, but the space still needs diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index a240db18945e..029ab1f72fdc 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -142,4 +142,8 @@ EXPORT_SYMBOL(efi_dir); EXPORT_SYMBOL(ia64_mv); #endif EXPORT_SYMBOL(machvec_noop); - +#ifdef CONFIG_PERFMON +#include <asm/perfmon.h> +EXPORT_SYMBOL(pfm_install_alternate_syswide_subsystem); +EXPORT_SYMBOL(pfm_remove_alternate_syswide_subsystem); +#endif diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index d8ffef34209f..6e38d3909e7a 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -4,7 +4,7 @@ * Copyright (C) 1999 Intel Corp. * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com> * Copyright (C) 2000-2002 J.I. Lee <jung-ik.lee@intel.com> - * Copyright (C) 1999-2000, 2002 Hewlett-Packard Co. + * Copyright (C) 1999-2000, 2002-2003 Hewlett-Packard Co. * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999,2000 Walt Drummond <drummond@valinux.com> @@ -433,7 +433,7 @@ iosapic_reassign_vector (int vector) || iosapic_intr_info[vector].polarity || iosapic_intr_info[vector].trigger) { new_vector = ia64_alloc_vector(); - printk("Reassigning vector %d to %d\n", vector, new_vector); + printk(KERN_INFO "Reassigning vector %d to %d\n", vector, new_vector); memcpy(&iosapic_intr_info[new_vector], &iosapic_intr_info[vector], sizeof(struct iosapic_intr_info)); memset(&iosapic_intr_info[vector], 0, sizeof(struct iosapic_intr_info)); @@ -468,17 +468,17 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery, #else if (iosapic_address) { if (iosapic_intr_info[vector].addr && (iosapic_intr_info[vector].addr != iosapic_address)) - printk("WARN: register_intr: diff IOSAPIC ADDRESS for GSI 0x%x, vector %d\n", - gsi, vector); + printk(KERN_WARNING "warning: register_intr: diff IOSAPIC ADDRESS for " + "GSI 0x%x, vector %d\n", gsi, vector); iosapic_intr_info[vector].addr = iosapic_address; if (iosapic_intr_info[vector].gsi_base && (iosapic_intr_info[vector].gsi_base != gsi_base)) { - printk("WARN: register_intr: diff GSI base 0x%x for GSI 0x%x, vector %d\n", - gsi_base, gsi, vector); + printk(KERN_WARNING "warning: register_intr: diff GSI base 0x%x for " + "GSI 0x%x, vector %d\n", gsi_base, gsi, vector); } iosapic_intr_info[vector].gsi_base = gsi_base; } else if (!iosapic_intr_info[vector].addr) - printk("WARN: register_intr: invalid override for GSI 0x%x, vector %d\n", - gsi, vector); + printk(KERN_WARNING "warning: register_intr: invalid override for GSI 0x%x, " + "vector %d\n", gsi, vector); #endif if (edge_triggered) { iosapic_intr_info[vector].trigger = IOSAPIC_EDGE; @@ -491,9 +491,8 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery, idesc = irq_desc(vector); if (idesc->handler != irq_type) { if (idesc->handler != &no_irq_type) - printk("%s: changing vector %d from %s to %s\n", - __FUNCTION__, vector, idesc->handler->typename, - irq_type->typename); + printk(KERN_WARNING "%s: changing vector %d from %s to %s\n", + __FUNCTION__, vector, idesc->handler->typename, irq_type->typename); idesc->handler = irq_type; } } @@ -518,7 +517,7 @@ iosapic_register_intr (unsigned int gsi, register_intr(gsi, vector, IOSAPIC_LOWEST_PRIORITY, polarity, edge_triggered, gsi_base, iosapic_address); - printk("GSI 0x%x(%s,%s) -> CPU 0x%04x vector %d\n", + printk(KERN_INFO "GSI 0x%x(%s,%s) -> CPU 0x%04x vector %d\n", gsi, (polarity ? "high" : "low"), (edge_triggered ? "edge" : "level"), dest, vector); @@ -560,14 +559,14 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi, delivery = IOSAPIC_LOWEST_PRIORITY; break; default: - printk("iosapic_register_platform_irq(): invalid int type\n"); + printk(KERN_ERR "iosapic_register_platform_irq(): invalid int type\n"); return -1; } register_intr(gsi, vector, delivery, polarity, edge_triggered, gsi_base, iosapic_address); - printk("PLATFORM int 0x%x: GSI 0x%x(%s,%s) -> CPU 0x%04x vector %d\n", + printk(KERN_INFO "PLATFORM int 0x%x: GSI 0x%x(%s,%s) -> CPU 0x%04x vector %d\n", int_type, gsi, (polarity ? "high" : "low"), (edge_triggered ? "edge" : "level"), dest, vector); @@ -594,7 +593,7 @@ iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi, index = find_iosapic(gsi); if (index < 0) { - printk("ISA: No corresponding IOSAPIC found : ISA IRQ %u -> GSI 0x%x\n", + printk(KERN_ERR "ISA: No corresponding IOSAPIC found : ISA IRQ %u -> GSI 0x%x\n", isa_irq, gsi); return; } @@ -634,7 +633,7 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base, int pcat_compat) * Disable the compatibility mode interrupts (8259 style), needs IN/OUT support * enabled. */ - printk("%s: Disabling PC-AT compatible 8259 interrupts\n", __FUNCTION__); + printk(KERN_INFO "%s: Disabling PC-AT compatible 8259 interrupts\n", __FUNCTION__); outb(0xff, 0xA1); outb(0xff, 0x21); } @@ -655,7 +654,7 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base, int pcat_compat) iosapic_lists[num_iosapic].num_rte = num_rte; num_iosapic++; - printk(KERN_INFO" IOSAPIC v%x.%x, address 0x%lx, GSIs 0x%x-0x%x\n", + printk(KERN_INFO " IOSAPIC v%x.%x, address 0x%lx, GSIs 0x%x-0x%x\n", (ver & 0xf0) >> 4, (ver & 0x0f), phys_addr, gsi_base, gsi_base + num_rte - 1); if ((gsi_base == 0) && pcat_compat) { @@ -692,7 +691,7 @@ fixup_vector (int vector, unsigned int gsi, const char *pci_id) idesc = irq_desc(vector); if (idesc->handler != irq_type) { if (idesc->handler != &no_irq_type) - printk("IOSAPIC: changing vector %d from %s to %s\n", + printk(KERN_INFO "IOSAPIC: changing vector %d from %s to %s\n", vector, idesc->handler->typename, irq_type->typename); idesc->handler = irq_type; } @@ -723,7 +722,8 @@ fixup_vector (int vector, unsigned int gsi, const char *pci_id) #endif set_rte(vector, dest); - printk("IOSAPIC: %s -> GSI 0x%x -> CPU 0x%04x vector %d\n", pci_id, gsi, dest, vector); + printk(KERN_INFO "IOSAPIC: %s -> GSI 0x%x -> CPU 0x%04x vector %d\n", + pci_id, gsi, dest, vector); } void __init @@ -751,8 +751,8 @@ iosapic_parse_prt (void) index = find_iosapic(gsi); if (index < 0) { - printk(KERN_WARNING"IOSAPIC: GSI 0x%x has no IOSAPIC!\n", gsi); - return; + printk(KERN_WARNING "IOSAPIC: GSI 0x%x has no IOSAPIC!\n", gsi); + continue; } addr = iosapic_lists[index].addr; gsi_base = iosapic_lists[index].gsi_base; diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index a1fcd948efad..91ac80986823 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -108,7 +108,7 @@ static void ack_none(unsigned int irq) * a generic callback i think. */ #if CONFIG_X86 - printk("unexpected IRQ trap at vector %02x\n", irq); + printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq); #ifdef CONFIG_X86_LOCAL_APIC /* * Currently unexpected vectors happen only on SMP and APIC. @@ -122,7 +122,7 @@ static void ack_none(unsigned int irq) #endif #endif #if CONFIG_IA64 - printk("Unexpected irq vector 0x%x on CPU %u!\n", irq, smp_processor_id()); + printk(KERN_ERR "Unexpected irq vector 0x%x on CPU %u!\n", irq, smp_processor_id()); #endif } @@ -317,7 +317,7 @@ void enable_irq(unsigned int irq) desc->depth--; break; case 0: - printk("enable_irq(%u) unbalanced from %p\n", + printk(KERN_ERR "enable_irq(%u) unbalanced from %p\n", irq, (void *) __builtin_return_address(0)); } spin_unlock_irqrestore(&desc->lock, flags); @@ -466,7 +466,7 @@ int request_irq(unsigned int irq, */ if (irqflags & SA_SHIRQ) { if (!dev_id) - printk("Bad boy: %s called us without a dev_id!\n", devname); + printk(KERN_ERR "Bad boy: %s called us without a dev_id!\n", devname); } #endif @@ -547,7 +547,7 @@ void free_irq(unsigned int irq, void *dev_id) kfree(action); return; } - printk("Trying to free free IRQ%d\n",irq); + printk(KERN_ERR "Trying to free free IRQ%d\n",irq); spin_unlock_irqrestore(&desc->lock,flags); return; } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 0462d4080e33..d158a7cf8aa5 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -178,7 +178,7 @@ init_IRQ (void) register_percpu_irq(IA64_IPI_VECTOR, &ipi_irqaction); #endif #ifdef CONFIG_PERFMON - perfmon_init_percpu(); + pfm_init_percpu(); #endif platform_irq_init(); } diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S index 5dc8e49c345b..8a0f5d87df44 100644 --- a/arch/ia64/kernel/ivt.S +++ b/arch/ia64/kernel/ivt.S @@ -192,7 +192,7 @@ ENTRY(vhpt_miss) rfi END(vhpt_miss) - .align 1024 + .org ia64_ivt+0x400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x0400 Entry 1 (size 64 bundles) ITLB (21) ENTRY(itlb_miss) @@ -206,7 +206,7 @@ ENTRY(itlb_miss) mov r16=cr.ifa // get virtual address mov r29=b0 // save b0 mov r31=pr // save predicates -itlb_fault: +.itlb_fault: mov r17=cr.iha // get virtual address of L3 PTE movl r30=1f // load nested fault continuation point ;; @@ -230,7 +230,7 @@ itlb_fault: rfi END(itlb_miss) - .align 1024 + .org ia64_ivt+0x0800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x0800 Entry 2 (size 64 bundles) DTLB (9,48) ENTRY(dtlb_miss) @@ -268,7 +268,7 @@ dtlb_fault: rfi END(dtlb_miss) - .align 1024 + .org ia64_ivt+0x0c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x0c00 Entry 3 (size 64 bundles) Alt ITLB (19) ENTRY(alt_itlb_miss) @@ -288,7 +288,7 @@ ENTRY(alt_itlb_miss) ;; (p8) mov cr.iha=r17 (p8) mov r29=b0 // save b0 -(p8) br.cond.dptk itlb_fault +(p8) br.cond.dptk .itlb_fault #endif extr.u r23=r21,IA64_PSR_CPL0_BIT,2 // extract psr.cpl and r19=r19,r16 // clear ed, reserved bits, and PTE control bits @@ -306,7 +306,7 @@ ENTRY(alt_itlb_miss) rfi END(alt_itlb_miss) - .align 1024 + .org ia64_ivt+0x1000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x1000 Entry 4 (size 64 bundles) Alt DTLB (7,46) ENTRY(alt_dtlb_miss) @@ -379,7 +379,7 @@ ENTRY(page_fault) br.call.sptk.many b6=ia64_do_page_fault // ignore return address END(page_fault) - .align 1024 + .org ia64_ivt+0x1400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x1400 Entry 5 (size 64 bundles) Data nested TLB (6,45) ENTRY(nested_dtlb_miss) @@ -440,7 +440,7 @@ ENTRY(nested_dtlb_miss) br.sptk.many b0 // return to continuation point END(nested_dtlb_miss) - .align 1024 + .org ia64_ivt+0x1800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x1800 Entry 6 (size 64 bundles) Instruction Key Miss (24) ENTRY(ikey_miss) @@ -448,7 +448,7 @@ ENTRY(ikey_miss) FAULT(6) END(ikey_miss) - .align 1024 + .org ia64_ivt+0x1c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x1c00 Entry 7 (size 64 bundles) Data Key Miss (12,51) ENTRY(dkey_miss) @@ -456,7 +456,7 @@ ENTRY(dkey_miss) FAULT(7) END(dkey_miss) - .align 1024 + .org ia64_ivt+0x2000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x2000 Entry 8 (size 64 bundles) Dirty-bit (54) ENTRY(dirty_bit) @@ -512,7 +512,7 @@ ENTRY(dirty_bit) rfi END(idirty_bit) - .align 1024 + .org ia64_ivt+0x2400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x2400 Entry 9 (size 64 bundles) Instruction Access-bit (27) ENTRY(iaccess_bit) @@ -571,7 +571,7 @@ ENTRY(iaccess_bit) rfi END(iaccess_bit) - .align 1024 + .org ia64_ivt+0x2800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x2800 Entry 10 (size 64 bundles) Data Access-bit (15,55) ENTRY(daccess_bit) @@ -618,7 +618,7 @@ ENTRY(daccess_bit) rfi END(daccess_bit) - .align 1024 + .org ia64_ivt+0x2c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x2c00 Entry 11 (size 64 bundles) Break instruction (33) ENTRY(break_fault) @@ -690,7 +690,7 @@ ENTRY(break_fault) // NOT REACHED END(break_fault) -ENTRY(demine_args) +ENTRY_MIN_ALIGN(demine_args) alloc r2=ar.pfs,8,0,0,0 tnat.nz p8,p0=in0 tnat.nz p9,p0=in1 @@ -719,7 +719,7 @@ ENTRY(demine_args) br.ret.sptk.many rp END(demine_args) - .align 1024 + .org ia64_ivt+0x3000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x3000 Entry 12 (size 64 bundles) External Interrupt (4) ENTRY(interrupt) @@ -746,19 +746,19 @@ ENTRY(interrupt) br.call.sptk.many b6=ia64_handle_irq END(interrupt) - .align 1024 + .org ia64_ivt+0x3400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x3400 Entry 13 (size 64 bundles) Reserved DBG_FAULT(13) FAULT(13) - .align 1024 + .org ia64_ivt+0x3800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x3800 Entry 14 (size 64 bundles) Reserved DBG_FAULT(14) FAULT(14) - .align 1024 + .org ia64_ivt+0x3c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x3c00 Entry 15 (size 64 bundles) Reserved DBG_FAULT(15) @@ -803,7 +803,7 @@ ENTRY(dispatch_illegal_op_fault) br.sptk.many ia64_leave_kernel END(dispatch_illegal_op_fault) - .align 1024 + .org ia64_ivt+0x4000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x4000 Entry 16 (size 64 bundles) Reserved DBG_FAULT(16) @@ -893,7 +893,7 @@ END(dispatch_to_ia32_handler) #endif /* CONFIG_IA32_SUPPORT */ - .align 1024 + .org ia64_ivt+0x4400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x4400 Entry 17 (size 64 bundles) Reserved DBG_FAULT(17) @@ -925,7 +925,7 @@ ENTRY(non_syscall) br.call.sptk.many b6=ia64_bad_break // avoid WAW on CFM and ignore return addr END(non_syscall) - .align 1024 + .org ia64_ivt+0x4800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x4800 Entry 18 (size 64 bundles) Reserved DBG_FAULT(18) @@ -959,7 +959,7 @@ ENTRY(dispatch_unaligned_handler) br.sptk.many ia64_prepare_handle_unaligned END(dispatch_unaligned_handler) - .align 1024 + .org ia64_ivt+0x4c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x4c00 Entry 19 (size 64 bundles) Reserved DBG_FAULT(19) @@ -1005,7 +1005,7 @@ END(dispatch_to_fault_handler) // --- End of long entries, Beginning of short entries // - .align 1024 + .org ia64_ivt+0x5000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5000 Entry 20 (size 16 bundles) Page Not Present (10,22,49) ENTRY(page_not_present) @@ -1025,7 +1025,7 @@ ENTRY(page_not_present) br.sptk.many page_fault END(page_not_present) - .align 256 + .org ia64_ivt+0x5100 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5100 Entry 21 (size 16 bundles) Key Permission (13,25,52) ENTRY(key_permission) @@ -1038,7 +1038,7 @@ ENTRY(key_permission) br.sptk.many page_fault END(key_permission) - .align 256 + .org ia64_ivt+0x5200 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5200 Entry 22 (size 16 bundles) Instruction Access Rights (26) ENTRY(iaccess_rights) @@ -1051,7 +1051,7 @@ ENTRY(iaccess_rights) br.sptk.many page_fault END(iaccess_rights) - .align 256 + .org ia64_ivt+0x5300 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53) ENTRY(daccess_rights) @@ -1064,7 +1064,7 @@ ENTRY(daccess_rights) br.sptk.many page_fault END(daccess_rights) - .align 256 + .org ia64_ivt+0x5400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5400 Entry 24 (size 16 bundles) General Exception (5,32,34,36,38,39) ENTRY(general_exception) @@ -1079,7 +1079,7 @@ ENTRY(general_exception) br.sptk.many dispatch_to_fault_handler END(general_exception) - .align 256 + .org ia64_ivt+0x5500 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5500 Entry 25 (size 16 bundles) Disabled FP-Register (35) ENTRY(disabled_fp_reg) @@ -1092,7 +1092,7 @@ ENTRY(disabled_fp_reg) br.sptk.many dispatch_to_fault_handler END(disabled_fp_reg) - .align 256 + .org ia64_ivt+0x5600 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5600 Entry 26 (size 16 bundles) Nat Consumption (11,23,37,50) ENTRY(nat_consumption) @@ -1100,7 +1100,7 @@ ENTRY(nat_consumption) FAULT(26) END(nat_consumption) - .align 256 + .org ia64_ivt+0x5700 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5700 Entry 27 (size 16 bundles) Speculation (40) ENTRY(speculation_vector) @@ -1137,13 +1137,13 @@ ENTRY(speculation_vector) rfi // and go back END(speculation_vector) - .align 256 + .org ia64_ivt+0x5800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5800 Entry 28 (size 16 bundles) Reserved DBG_FAULT(28) FAULT(28) - .align 256 + .org ia64_ivt+0x5900 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5900 Entry 29 (size 16 bundles) Debug (16,28,56) ENTRY(debug_vector) @@ -1151,7 +1151,7 @@ ENTRY(debug_vector) FAULT(29) END(debug_vector) - .align 256 + .org ia64_ivt+0x5a00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5a00 Entry 30 (size 16 bundles) Unaligned Reference (57) ENTRY(unaligned_access) @@ -1162,91 +1162,103 @@ ENTRY(unaligned_access) br.sptk.many dispatch_unaligned_handler END(unaligned_access) - .align 256 + .org ia64_ivt+0x5b00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5b00 Entry 31 (size 16 bundles) Unsupported Data Reference (57) +ENTRY(unsupported_data_reference) DBG_FAULT(31) FAULT(31) +END(unsupported_data_reference) - .align 256 + .org ia64_ivt+0x5c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5c00 Entry 32 (size 16 bundles) Floating-Point Fault (64) +ENTRY(floating_point_fault) DBG_FAULT(32) FAULT(32) +END(floating_point_fault) - .align 256 + .org ia64_ivt+0x5d00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5d00 Entry 33 (size 16 bundles) Floating Point Trap (66) +ENTRY(floating_point_trap) DBG_FAULT(33) FAULT(33) +END(floating_point_trap) - .align 256 + .org ia64_ivt+0x5e00 ///////////////////////////////////////////////////////////////////////////////////////// -// 0x5e00 Entry 34 (size 16 bundles) Lower Privilege Tranfer Trap (66) +// 0x5e00 Entry 34 (size 16 bundles) Lower Privilege Transfer Trap (66) +ENTRY(lower_privilege_trap) DBG_FAULT(34) FAULT(34) +END(lower_privilege_trap) - .align 256 + .org ia64_ivt+0x5f00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x5f00 Entry 35 (size 16 bundles) Taken Branch Trap (68) +ENTRY(taken_branch_trap) DBG_FAULT(35) FAULT(35) +END(taken_branch_trap) - .align 256 + .org ia64_ivt+0x6000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6000 Entry 36 (size 16 bundles) Single Step Trap (69) +ENTRY(single_step_trap) DBG_FAULT(36) FAULT(36) +END(single_step_trap) - .align 256 + .org ia64_ivt+0x6100 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6100 Entry 37 (size 16 bundles) Reserved DBG_FAULT(37) FAULT(37) - .align 256 + .org ia64_ivt+0x6200 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6200 Entry 38 (size 16 bundles) Reserved DBG_FAULT(38) FAULT(38) - .align 256 + .org ia64_ivt+0x6300 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6300 Entry 39 (size 16 bundles) Reserved DBG_FAULT(39) FAULT(39) - .align 256 + .org ia64_ivt+0x6400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6400 Entry 40 (size 16 bundles) Reserved DBG_FAULT(40) FAULT(40) - .align 256 + .org ia64_ivt+0x6500 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6500 Entry 41 (size 16 bundles) Reserved DBG_FAULT(41) FAULT(41) - .align 256 + .org ia64_ivt+0x6600 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6600 Entry 42 (size 16 bundles) Reserved DBG_FAULT(42) FAULT(42) - .align 256 + .org ia64_ivt+0x6700 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6700 Entry 43 (size 16 bundles) Reserved DBG_FAULT(43) FAULT(43) - .align 256 + .org ia64_ivt+0x6800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6800 Entry 44 (size 16 bundles) Reserved DBG_FAULT(44) FAULT(44) - .align 256 + .org ia64_ivt+0x6900 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6900 Entry 45 (size 16 bundles) IA-32 Exeception (17,18,29,41,42,43,44,58,60,61,62,72,73,75,76,77) ENTRY(ia32_exception) @@ -1254,7 +1266,7 @@ ENTRY(ia32_exception) FAULT(45) END(ia32_exception) - .align 256 + .org ia64_ivt+0x6a00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6a00 Entry 46 (size 16 bundles) IA-32 Intercept (30,31,59,70,71) ENTRY(ia32_intercept) @@ -1284,7 +1296,7 @@ ENTRY(ia32_intercept) FAULT(46) END(ia32_intercept) - .align 256 + .org ia64_ivt+0x6b00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6b00 Entry 47 (size 16 bundles) IA-32 Interrupt (74) ENTRY(ia32_interrupt) @@ -1297,121 +1309,121 @@ ENTRY(ia32_interrupt) #endif END(ia32_interrupt) - .align 256 + .org ia64_ivt+0x6c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6c00 Entry 48 (size 16 bundles) Reserved DBG_FAULT(48) FAULT(48) - .align 256 + .org ia64_ivt+0x6d00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6d00 Entry 49 (size 16 bundles) Reserved DBG_FAULT(49) FAULT(49) - .align 256 + .org ia64_ivt+0x6e00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6e00 Entry 50 (size 16 bundles) Reserved DBG_FAULT(50) FAULT(50) - .align 256 + .org ia64_ivt+0x6f00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x6f00 Entry 51 (size 16 bundles) Reserved DBG_FAULT(51) FAULT(51) - .align 256 + .org ia64_ivt+0x7000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7000 Entry 52 (size 16 bundles) Reserved DBG_FAULT(52) FAULT(52) - .align 256 + .org ia64_ivt+0x7100 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7100 Entry 53 (size 16 bundles) Reserved DBG_FAULT(53) FAULT(53) - .align 256 + .org ia64_ivt+0x7200 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7200 Entry 54 (size 16 bundles) Reserved DBG_FAULT(54) FAULT(54) - .align 256 + .org ia64_ivt+0x7300 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7300 Entry 55 (size 16 bundles) Reserved DBG_FAULT(55) FAULT(55) - .align 256 + .org ia64_ivt+0x7400 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7400 Entry 56 (size 16 bundles) Reserved DBG_FAULT(56) FAULT(56) - .align 256 + .org ia64_ivt+0x7500 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7500 Entry 57 (size 16 bundles) Reserved DBG_FAULT(57) FAULT(57) - .align 256 + .org ia64_ivt+0x7600 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7600 Entry 58 (size 16 bundles) Reserved DBG_FAULT(58) FAULT(58) - .align 256 + .org ia64_ivt+0x7700 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7700 Entry 59 (size 16 bundles) Reserved DBG_FAULT(59) FAULT(59) - .align 256 + .org ia64_ivt+0x7800 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7800 Entry 60 (size 16 bundles) Reserved DBG_FAULT(60) FAULT(60) - .align 256 + .org ia64_ivt+0x7900 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7900 Entry 61 (size 16 bundles) Reserved DBG_FAULT(61) FAULT(61) - .align 256 + .org ia64_ivt+0x7a00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7a00 Entry 62 (size 16 bundles) Reserved DBG_FAULT(62) FAULT(62) - .align 256 + .org ia64_ivt+0x7b00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7b00 Entry 63 (size 16 bundles) Reserved DBG_FAULT(63) FAULT(63) - .align 256 + .org ia64_ivt+0x7c00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7c00 Entry 64 (size 16 bundles) Reserved DBG_FAULT(64) FAULT(64) - .align 256 + .org ia64_ivt+0x7d00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7d00 Entry 65 (size 16 bundles) Reserved DBG_FAULT(65) FAULT(65) - .align 256 + .org ia64_ivt+0x7e00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7e00 Entry 66 (size 16 bundles) Reserved DBG_FAULT(66) FAULT(66) - .align 256 + .org ia64_ivt+0x7f00 ///////////////////////////////////////////////////////////////////////////////////////// // 0x7f00 Entry 67 (size 16 bundles) Reserved DBG_FAULT(67) diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c index f1be3eb676d4..def11142fa5a 100644 --- a/arch/ia64/kernel/machvec.c +++ b/arch/ia64/kernel/machvec.c @@ -47,7 +47,7 @@ machvec_init (const char *name) panic("generic kernel failed to find machine vector for platform %s!", name); } ia64_mv = *mv; - printk("booting generic kernel on platform %s\n", name); + printk(KERN_INFO "booting generic kernel on platform %s\n", name); } #endif /* CONFIG_IA64_GENERIC */ diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 129239fa3d3d..d45e4cc9d0c9 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -231,7 +231,7 @@ ia64_mca_register_cpev (int cpev) { /* Register the CPE interrupt vector with SAL */ if (ia64_sal_mc_set_params(SAL_MC_PARAM_CPE_INT, SAL_MC_PARAM_MECHANISM_INT, cpev, 0, 0)) { - printk("ia64_mca_platform_init: failed to register Corrected " + printk(KERN_ERR "ia64_mca_platform_init: failed to register Corrected " "Platform Error interrupt vector with SAL.\n"); return; } @@ -398,7 +398,7 @@ ia64_mca_init(void) IA64_MCA_RENDEZ_TIMEOUT, 0))) { - printk("ia64_mca_init: Failed to register rendezvous interrupt " + printk(KERN_ERR "ia64_mca_init: Failed to register rendezvous interrupt " "with SAL. rc = %ld\n", rc); return; } @@ -409,8 +409,8 @@ ia64_mca_init(void) IA64_MCA_WAKEUP_VECTOR, 0, 0))) { - printk("ia64_mca_init: Failed to register wakeup interrupt with SAL. rc = %ld\n", - rc); + printk(KERN_ERR "ia64_mca_init: Failed to register wakeup interrupt with SAL. " + "rc = %ld\n", rc); return; } @@ -430,8 +430,8 @@ ia64_mca_init(void) ia64_mc_info.imi_mca_handler_size, 0, 0, 0))) { - printk("ia64_mca_init: Failed to register os mca handler with SAL. rc = %ld\n", - rc); + printk(KERN_ERR "ia64_mca_init: Failed to register os mca handler with SAL. " + "rc = %ld\n", rc); return; } @@ -459,8 +459,8 @@ ia64_mca_init(void) __pa(ia64_get_gp()), ia64_mc_info.imi_slave_init_handler_size))) { - printk("ia64_mca_init: Failed to register m/s init handlers with SAL. rc = %ld\n", - rc); + printk(KERN_ERR "ia64_mca_init: Failed to register m/s init handlers with SAL. " + "rc = %ld\n", rc); return; } @@ -495,7 +495,8 @@ ia64_mca_init(void) } ia64_mca_register_cpev(cpev); } else - printk("ia64_mca_init: Failed to get routed CPEI vector from ACPI.\n"); + printk(KERN_ERR + "ia64_mca_init: Failed to get routed CPEI vector from ACPI.\n"); } /* Initialize the areas set aside by the OS to buffer the @@ -511,7 +512,7 @@ ia64_mca_init(void) mca_test(); #endif /* #if defined(MCA_TEST) */ - printk("Mca related initialization done\n"); + printk(KERN_INFO "Mca related initialization done\n"); /* commented out because this is done elsewhere */ #if 0 @@ -807,7 +808,7 @@ ia64_init_handler (struct pt_regs *regs) sal_log_processor_info_t *proc_ptr; ia64_err_rec_t *plog_ptr; - printk("Entered OS INIT handler\n"); + printk(KERN_INFO "Entered OS INIT handler\n"); /* Get the INIT processor log */ if (!ia64_log_get(SAL_INFO_TYPE_INIT, (prfunc_t)printk)) @@ -1736,8 +1737,7 @@ ia64_log_processor_info_print(sal_log_record_header_t *lh, prfunc_t prfunc) /* * Now process processor device error record section */ - ia64_log_proc_dev_err_info_print((sal_log_processor_info_t *)slsh, - printk); + ia64_log_proc_dev_err_info_print((sal_log_processor_info_t *)slsh, printk); } IA64_MCA_DEBUG("ia64_mca_log_print: " diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h index 81aebc4a2924..ed1d91daafac 100644 --- a/arch/ia64/kernel/minstate.h +++ b/arch/ia64/kernel/minstate.h @@ -30,25 +30,23 @@ * on interrupts. */ #define MINSTATE_START_SAVE_MIN_VIRT \ -(pUser) mov ar.rsc=0; /* set enforced lazy mode, pl 0, little-endian, loadrs=0 */ \ - dep r1=-1,r1,61,3; /* r1 = current (virtual) */ \ +(pUStk) mov ar.rsc=0; /* set enforced lazy mode, pl 0, little-endian, loadrs=0 */ \ ;; \ -(pUser) mov.m rARRNAT=ar.rnat; \ -(pUser) addl rKRBS=IA64_RBS_OFFSET,r1; /* compute base of RBS */ \ -(pKern) mov r1=sp; /* get sp */ \ +(pUStk) mov.m rARRNAT=ar.rnat; \ +(pUStk) addl rKRBS=IA64_RBS_OFFSET,r1; /* compute base of RBS */ \ +(pKStk) mov r1=sp; /* get sp */ \ ;; \ -(pUser) lfetch.fault.excl.nt1 [rKRBS]; \ -(pUser) mov rARBSPSTORE=ar.bspstore; /* save ar.bspstore */ \ -(pUser) addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1; /* compute base of memory stack */ \ +(pUStk) lfetch.fault.excl.nt1 [rKRBS]; \ +(pUStk) addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1; /* compute base of memory stack */ \ +(pUStk) mov rARBSPSTORE=ar.bspstore; /* save ar.bspstore */ \ ;; \ -(pUser) mov ar.bspstore=rKRBS; /* switch to kernel RBS */ \ -(pKern) addl r1=-IA64_PT_REGS_SIZE,r1; /* if in kernel mode, use sp (r12) */ \ +(pUStk) mov ar.bspstore=rKRBS; /* switch to kernel RBS */ \ +(pKStk) addl r1=-IA64_PT_REGS_SIZE,r1; /* if in kernel mode, use sp (r12) */ \ ;; \ -(pUser) mov r18=ar.bsp; \ -(pUser) mov ar.rsc=0x3; /* set eager mode, pl 0, little-endian, loadrs=0 */ \ +(pUStk) mov r18=ar.bsp; \ +(pUStk) mov ar.rsc=0x3; /* set eager mode, pl 0, little-endian, loadrs=0 */ \ #define MINSTATE_END_SAVE_MIN_VIRT \ - or r13=r13,r14; /* make `current' a kernel virtual address */ \ bsw.1; /* switch back to bank 1 (must be last in insn group) */ \ ;; @@ -57,21 +55,21 @@ * go virtual and dont want to destroy the iip or ipsr. */ #define MINSTATE_START_SAVE_MIN_PHYS \ -(pKern) movl sp=ia64_init_stack+IA64_STK_OFFSET-IA64_PT_REGS_SIZE; \ -(pUser) mov ar.rsc=0; /* set enforced lazy mode, pl 0, little-endian, loadrs=0 */ \ -(pUser) addl rKRBS=IA64_RBS_OFFSET,r1; /* compute base of register backing store */ \ +(pKStk) movl sp=ia64_init_stack+IA64_STK_OFFSET-IA64_PT_REGS_SIZE; \ +(pUStk) mov ar.rsc=0; /* set enforced lazy mode, pl 0, little-endian, loadrs=0 */ \ +(pUStk) addl rKRBS=IA64_RBS_OFFSET,r1; /* compute base of register backing store */ \ ;; \ -(pUser) mov rARRNAT=ar.rnat; \ -(pKern) dep r1=0,sp,61,3; /* compute physical addr of sp */ \ -(pUser) addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1; /* compute base of memory stack */ \ -(pUser) mov rARBSPSTORE=ar.bspstore; /* save ar.bspstore */ \ -(pUser) dep rKRBS=-1,rKRBS,61,3; /* compute kernel virtual addr of RBS */\ +(pUStk) mov rARRNAT=ar.rnat; \ +(pKStk) dep r1=0,sp,61,3; /* compute physical addr of sp */ \ +(pUStk) addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1; /* compute base of memory stack */ \ +(pUStk) mov rARBSPSTORE=ar.bspstore; /* save ar.bspstore */ \ +(pUStk) dep rKRBS=-1,rKRBS,61,3; /* compute kernel virtual addr of RBS */\ ;; \ -(pKern) addl r1=-IA64_PT_REGS_SIZE,r1; /* if in kernel mode, use sp (r12) */ \ -(pUser) mov ar.bspstore=rKRBS; /* switch to kernel RBS */ \ +(pKStk) addl r1=-IA64_PT_REGS_SIZE,r1; /* if in kernel mode, use sp (r12) */ \ +(pUStk) mov ar.bspstore=rKRBS; /* switch to kernel RBS */ \ ;; \ -(pUser) mov r18=ar.bsp; \ -(pUser) mov ar.rsc=0x3; /* set eager mode, pl 0, little-endian, loadrs=0 */ \ +(pUStk) mov r18=ar.bsp; \ +(pUStk) mov ar.rsc=0x3; /* set eager mode, pl 0, little-endian, loadrs=0 */ \ #define MINSTATE_END_SAVE_MIN_PHYS \ or r12=r12,r14; /* make sp a kernel virtual address */ \ @@ -79,11 +77,13 @@ ;; #ifdef MINSTATE_VIRT +# define MINSTATE_GET_CURRENT(reg) mov reg=IA64_KR(CURRENT) # define MINSTATE_START_SAVE_MIN MINSTATE_START_SAVE_MIN_VIRT # define MINSTATE_END_SAVE_MIN MINSTATE_END_SAVE_MIN_VIRT #endif #ifdef MINSTATE_PHYS +# define MINSTATE_GET_CURRENT(reg) mov reg=IA64_KR(CURRENT);; dep reg=0,reg,61,3 # define MINSTATE_START_SAVE_MIN MINSTATE_START_SAVE_MIN_PHYS # define MINSTATE_END_SAVE_MIN MINSTATE_END_SAVE_MIN_PHYS #endif @@ -110,23 +110,26 @@ * we can pass interruption state as arguments to a handler. */ #define DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA) \ - mov rARRSC=ar.rsc; \ - mov rARPFS=ar.pfs; \ - mov rR1=r1; \ - mov rARUNAT=ar.unat; \ - mov rCRIPSR=cr.ipsr; \ - mov rB6=b6; /* rB6 = branch reg 6 */ \ - mov rCRIIP=cr.iip; \ - mov r1=IA64_KR(CURRENT); /* r1 = current (physical) */ \ - COVER; \ - ;; \ - invala; \ - extr.u r16=rCRIPSR,32,2; /* extract psr.cpl */ \ - ;; \ - cmp.eq pKern,pUser=r0,r16; /* are we in kernel mode already? (psr.cpl==0) */ \ + mov rARRSC=ar.rsc; /* M */ \ + mov rARUNAT=ar.unat; /* M */ \ + mov rR1=r1; /* A */ \ + MINSTATE_GET_CURRENT(r1); /* M (or M;;I) */ \ + mov rCRIPSR=cr.ipsr; /* M */ \ + mov rARPFS=ar.pfs; /* I */ \ + mov rCRIIP=cr.iip; /* M */ \ + mov rB6=b6; /* I */ /* rB6 = branch reg 6 */ \ + COVER; /* B;; (or nothing) */ \ + ;; \ + adds r16=IA64_TASK_THREAD_ON_USTACK_OFFSET,r1; \ + ;; \ + ld1 r17=[r16]; /* load current->thread.on_ustack flag */ \ + st1 [r16]=r0; /* clear current->thread.on_ustack flag */ \ /* switch from user to kernel RBS: */ \ ;; \ + invala; /* M */ \ SAVE_IFS; \ + cmp.eq pKStk,pUStk=r0,r17; /* are we in kernel mode already? (psr.cpl==0) */ \ + ;; \ MINSTATE_START_SAVE_MIN \ add r17=L1_CACHE_BYTES,r1 /* really: biggest cache-line size */ \ ;; \ @@ -138,23 +141,23 @@ ;; \ lfetch.fault.excl.nt1 [r17]; \ adds r17=8,r1; /* initialize second base pointer */ \ -(pKern) mov r18=r0; /* make sure r18 isn't NaT */ \ +(pKStk) mov r18=r0; /* make sure r18 isn't NaT */ \ ;; \ st8 [r17]=rCRIIP,16; /* save cr.iip */ \ st8 [r16]=rCRIFS,16; /* save cr.ifs */ \ -(pUser) sub r18=r18,rKRBS; /* r18=RSE.ndirty*8 */ \ +(pUStk) sub r18=r18,rKRBS; /* r18=RSE.ndirty*8 */ \ ;; \ st8 [r17]=rARUNAT,16; /* save ar.unat */ \ st8 [r16]=rARPFS,16; /* save ar.pfs */ \ shl r18=r18,16; /* compute ar.rsc to be used for "loadrs" */ \ ;; \ st8 [r17]=rARRSC,16; /* save ar.rsc */ \ -(pUser) st8 [r16]=rARRNAT,16; /* save ar.rnat */ \ -(pKern) adds r16=16,r16; /* skip over ar_rnat field */ \ +(pUStk) st8 [r16]=rARRNAT,16; /* save ar.rnat */ \ +(pKStk) adds r16=16,r16; /* skip over ar_rnat field */ \ ;; /* avoid RAW on r16 & r17 */ \ -(pUser) st8 [r17]=rARBSPSTORE,16; /* save ar.bspstore */ \ +(pUStk) st8 [r17]=rARBSPSTORE,16; /* save ar.bspstore */ \ st8 [r16]=rARPR,16; /* save predicates */ \ -(pKern) adds r17=16,r17; /* skip over ar_bspstore field */ \ +(pKStk) adds r17=16,r17; /* skip over ar_bspstore field */ \ ;; \ st8 [r17]=rB6,16; /* save b6 */ \ st8 [r16]=r18,16; /* save ar.rsc value for "loadrs" */ \ diff --git a/arch/ia64/kernel/pal.S b/arch/ia64/kernel/pal.S index ae0a0305d86e..d44041380e87 100644 --- a/arch/ia64/kernel/pal.S +++ b/arch/ia64/kernel/pal.S @@ -4,7 +4,7 @@ * * Copyright (C) 1999 Don Dugger <don.dugger@intel.com> * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> - * Copyright (C) 1999-2001 Hewlett-Packard Co + * Copyright (C) 1999-2001, 2003 Hewlett-Packard Co * David Mosberger <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * @@ -114,7 +114,7 @@ GLOBAL_ENTRY(ia64_pal_call_stacked) ;; rsm psr.i mov b7 = loc2 - ;; + ;; br.call.sptk.many rp=b7 // now make the call .ret0: mov psr.l = loc3 mov ar.pfs = loc1 @@ -131,15 +131,15 @@ END(ia64_pal_call_stacked) * in0 Index of PAL service * in2 - in3 Remaning PAL arguments * - * PSR_DB, PSR_LP, PSR_TB, PSR_ID, PSR_DA are never set by the kernel. + * PSR_LP, PSR_TB, PSR_ID, PSR_DA are never set by the kernel. * So we don't need to clear them. */ -#define PAL_PSR_BITS_TO_CLEAR \ - (IA64_PSR_I | IA64_PSR_IT | IA64_PSR_DT | IA64_PSR_RT | \ - IA64_PSR_DD | IA64_PSR_SS | IA64_PSR_RI | IA64_PSR_ED | \ +#define PAL_PSR_BITS_TO_CLEAR \ + (IA64_PSR_I | IA64_PSR_IT | IA64_PSR_DT | IA64_PSR_DB | IA64_PSR_RT | \ + IA64_PSR_DD | IA64_PSR_SS | IA64_PSR_RI | IA64_PSR_ED | \ IA64_PSR_DFL | IA64_PSR_DFH) -#define PAL_PSR_BITS_TO_SET \ +#define PAL_PSR_BITS_TO_SET \ (IA64_PSR_BN) @@ -161,7 +161,7 @@ GLOBAL_ENTRY(ia64_pal_call_phys_static) ;; mov loc3 = psr // save psr adds r8 = 1f-1b,r8 // calculate return address for call - ;; + ;; mov loc4=ar.rsc // save RSE configuration dep.z loc2=loc2,0,61 // convert pal entry point to physical dep.z r8=r8,0,61 // convert rp to physical @@ -275,7 +275,6 @@ END(ia64_save_scratch_fpregs) * Inputs: * in0 Address of stack storage for fp regs */ - GLOBAL_ENTRY(ia64_load_scratch_fpregs) alloc r3=ar.pfs,1,0,0,0 add r2=16,in0 diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index a0d6a97ca2e6..19b44cf837b8 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -6,7 +6,7 @@ * Intel IA-64 Architecture Software Developer's Manual v1.0. * * - * Copyright (C) 2000-2001 Hewlett-Packard Co + * Copyright (C) 2000-2001, 2003 Hewlett-Packard Co * Stephane Eranian <eranian@hpl.hp.com> * * 05/26/2000 S.Eranian initial release @@ -225,15 +225,12 @@ cache_info(char *page) int i,j, k; s64 status; - if ((status=ia64_pal_cache_summary(&levels, &unique_caches)) != 0) { - printk("ia64_pal_cache_summary=%ld\n", status); - return 0; + if ((status = ia64_pal_cache_summary(&levels, &unique_caches)) != 0) { + printk(KERN_ERR "ia64_pal_cache_summary=%ld\n", status); + return 0; } - p += sprintf(p, "Cache levels : %ld\n" \ - "Unique caches : %ld\n\n", - levels, - unique_caches); + p += sprintf(p, "Cache levels : %ld\nUnique caches : %ld\n\n", levels, unique_caches); for (i=0; i < levels; i++) { @@ -308,8 +305,8 @@ vm_info(char *page) int i, j; s64 status; - if ((status=ia64_pal_vm_summary(&vm_info_1, &vm_info_2)) !=0) { - printk("ia64_pal_vm_summary=%ld\n", status); + if ((status = ia64_pal_vm_summary(&vm_info_1, &vm_info_2)) !=0) { + printk(KERN_ERR "ia64_pal_vm_summary=%ld\n", status); return 0; } @@ -339,8 +336,8 @@ vm_info(char *page) } p += sprintf(p, "\n"); - if ((status=ia64_pal_vm_page_size(&tr_pages, &vw_pages)) !=0) { - printk("ia64_pal_vm_page_size=%ld\n", status); + if ((status = ia64_pal_vm_page_size(&tr_pages, &vw_pages)) !=0) { + printk(KERN_ERR "ia64_pal_vm_page_size=%ld\n", status); return 0; } @@ -360,7 +357,7 @@ vm_info(char *page) p = bitvector_process(p, vw_pages); if ((status=ia64_get_ptce(&ptce)) != 0) { - printk("ia64_get_ptce=%ld\n",status); + printk(KERN_ERR "ia64_get_ptce=%ld\n", status); return 0; } @@ -710,8 +707,8 @@ tr_info(char *page) u64 rv2:32; } *rid_reg; - if ((status=ia64_pal_vm_summary(&vm_info_1, &vm_info_2)) !=0) { - printk("ia64_pal_vm_summary=%ld\n", status); + if ((status = ia64_pal_vm_summary(&vm_info_1, &vm_info_2)) !=0) { + printk(KERN_ERR "ia64_pal_vm_summary=%ld\n", status); return 0; } max[0] = vm_info_1.pal_vm_info_1_s.max_itr_entry+1; @@ -722,7 +719,8 @@ tr_info(char *page) status = ia64_pal_tr_read(j, i, tr_buffer, &tr_valid); if (status != 0) { - printk("palinfo: pal call failed on tr[%d:%d]=%ld\n", i, j, status); + printk(KERN_ERR "palinfo: pal call failed on tr[%d:%d]=%ld\n", + i, j, status); continue; } @@ -841,7 +839,7 @@ palinfo_smp_call(void *info) { palinfo_smp_data_t *data = (palinfo_smp_data_t *)info; if (data == NULL) { - printk("%s palinfo: data pointer is NULL\n", KERN_ERR); + printk(KERN_ERR "palinfo: data pointer is NULL\n"); data->ret = 0; /* no output */ return; } @@ -868,7 +866,8 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) /* will send IPI to other CPU and wait for completion of remote call */ if ((ret=smp_call_function_single(f->req_cpu, palinfo_smp_call, &ptr, 0, 1))) { - printk("palinfo: remote CPU call from %d to %d on function %d: error %d\n", smp_processor_id(), f->req_cpu, f->func_id, ret); + printk(KERN_ERR "palinfo: remote CPU call from %d to %d on function %d: " + "error %d\n", smp_processor_id(), f->req_cpu, f->func_id, ret); return 0; } return ptr.ret; @@ -877,7 +876,7 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) static int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page) { - printk("palinfo: should not be called with non SMP kernel\n"); + printk(KERN_ERR "palinfo: should not be called with non SMP kernel\n"); return 0; } #endif /* CONFIG_SMP */ diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 7ec39ed57d52..4a63c27ac26d 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -28,7 +28,6 @@ #include <asm/bitops.h> #include <asm/errno.h> #include <asm/page.h> -#include <asm/pal.h> #include <asm/perfmon.h> #include <asm/processor.h> #include <asm/signal.h> @@ -56,8 +55,8 @@ /* * Reset register flags */ -#define PFM_RELOAD_LONG_RESET 1 -#define PFM_RELOAD_SHORT_RESET 2 +#define PFM_PMD_LONG_RESET 1 +#define PFM_PMD_SHORT_RESET 2 /* * Misc macros and definitions @@ -83,8 +82,10 @@ #define PFM_REG_CONFIG (0x4<<4|PFM_REG_IMPL) /* refine configuration */ #define PFM_REG_BUFFER (0x5<<4|PFM_REG_IMPL) /* PMD used as buffer */ +#define PMC_IS_LAST(i) (pmu_conf.pmc_desc[i].type & PFM_REG_END) +#define PMD_IS_LAST(i) (pmu_conf.pmd_desc[i].type & PFM_REG_END) -#define PFM_IS_DISABLED() pmu_conf.pfm_is_disabled +#define PFM_IS_DISABLED() pmu_conf.disabled #define PMC_OVFL_NOTIFY(ctx, i) ((ctx)->ctx_soft_pmds[i].flags & PFM_REGFL_OVFL_NOTIFY) #define PFM_FL_INHERIT_MASK (PFM_FL_INHERIT_NONE|PFM_FL_INHERIT_ONCE|PFM_FL_INHERIT_ALL) @@ -102,7 +103,6 @@ #define PMD_PMD_DEP(i) pmu_conf.pmd_desc[i].dep_pmd[0] #define PMC_PMD_DEP(i) pmu_conf.pmc_desc[i].dep_pmd[0] - /* k assume unsigned */ #define IBR_IS_IMPL(k) (k<pmu_conf.num_ibrs) #define DBR_IS_IMPL(k) (k<pmu_conf.num_dbrs) @@ -131,6 +131,9 @@ #define PFM_REG_RETFLAG_SET(flags, val) do { flags &= ~PFM_REG_RETFL_MASK; flags |= (val); } while(0) +#define PFM_CPUINFO_CLEAR(v) __get_cpu_var(pfm_syst_info) &= ~(v) +#define PFM_CPUINFO_SET(v) __get_cpu_var(pfm_syst_info) |= (v) + #ifdef CONFIG_SMP #define cpu_is_online(i) (cpu_online_map & (1UL << i)) #else @@ -211,7 +214,7 @@ typedef struct { u64 reset_pmds[4]; /* which other pmds to reset when this counter overflows */ u64 seed; /* seed for random-number generator */ u64 mask; /* mask for random-number generator */ - int flags; /* notify/do not notify */ + unsigned int flags; /* notify/do not notify */ } pfm_counter_t; /* @@ -226,7 +229,8 @@ typedef struct { unsigned int frozen:1; /* pmu must be kept frozen on ctxsw in */ unsigned int protected:1; /* allow access to creator of context only */ unsigned int using_dbreg:1; /* using range restrictions (debug registers) */ - unsigned int reserved:24; + unsigned int excl_idle:1; /* exclude idle task in system wide session */ + unsigned int reserved:23; } pfm_context_flags_t; /* @@ -261,10 +265,8 @@ typedef struct pfm_context { u64 ctx_saved_psr; /* copy of psr used for lazy ctxsw */ unsigned long ctx_saved_cpus_allowed; /* copy of the task cpus_allowed (system wide) */ - unsigned long ctx_cpu; /* cpu to which perfmon is applied (system wide) */ + unsigned int ctx_cpu; /* CPU used by system wide session */ - atomic_t ctx_saving_in_progress; /* flag indicating actual save in progress */ - atomic_t ctx_is_busy; /* context accessed by overflow handler */ atomic_t ctx_last_cpu; /* CPU id of current or last CPU used */ } pfm_context_t; @@ -274,6 +276,7 @@ typedef struct pfm_context { #define ctx_fl_frozen ctx_flags.frozen #define ctx_fl_protected ctx_flags.protected #define ctx_fl_using_dbreg ctx_flags.using_dbreg +#define ctx_fl_excl_idle ctx_flags.excl_idle /* * global information about all sessions @@ -282,10 +285,10 @@ typedef struct pfm_context { typedef struct { spinlock_t pfs_lock; /* lock the structure */ - unsigned long pfs_task_sessions; /* number of per task sessions */ - unsigned long pfs_sys_sessions; /* number of per system wide sessions */ - unsigned long pfs_sys_use_dbregs; /* incremented when a system wide session uses debug regs */ - unsigned long pfs_ptrace_use_dbregs; /* incremented when a process uses debug regs */ + unsigned int pfs_task_sessions; /* number of per task sessions */ + unsigned int pfs_sys_sessions; /* number of per system wide sessions */ + unsigned int pfs_sys_use_dbregs; /* incremented when a system wide session uses debug regs */ + unsigned int pfs_ptrace_use_dbregs; /* incremented when a process uses debug regs */ struct task_struct *pfs_sys_session[NR_CPUS]; /* point to task owning a system-wide session */ } pfm_session_t; @@ -313,23 +316,22 @@ typedef struct { /* * This structure is initialized at boot time and contains - * a description of the PMU main characteristic as indicated - * by PAL along with a list of inter-registers dependencies and configurations. + * a description of the PMU main characteristics. */ typedef struct { - unsigned long pfm_is_disabled; /* indicates if perfmon is working properly */ - unsigned long perf_ovfl_val; /* overflow value for generic counters */ - unsigned long max_counters; /* upper limit on counter pair (PMC/PMD) */ - unsigned long num_pmcs ; /* highest PMC implemented (may have holes) */ - unsigned long num_pmds; /* highest PMD implemented (may have holes) */ - unsigned long impl_regs[16]; /* buffer used to hold implememted PMC/PMD mask */ - unsigned long num_ibrs; /* number of instruction debug registers */ - unsigned long num_dbrs; /* number of data debug registers */ - pfm_reg_desc_t *pmc_desc; /* detailed PMC register descriptions */ - pfm_reg_desc_t *pmd_desc; /* detailed PMD register descriptions */ + unsigned int disabled; /* indicates if perfmon is working properly */ + unsigned long ovfl_val; /* overflow value for generic counters */ + unsigned long impl_pmcs[4]; /* bitmask of implemented PMCS */ + unsigned long impl_pmds[4]; /* bitmask of implemented PMDS */ + unsigned int num_pmcs; /* number of implemented PMCS */ + unsigned int num_pmds; /* number of implemented PMDS */ + unsigned int num_ibrs; /* number of implemented IBRS */ + unsigned int num_dbrs; /* number of implemented DBRS */ + unsigned int num_counters; /* number of PMD/PMC counters */ + pfm_reg_desc_t *pmc_desc; /* detailed PMC register dependencies descriptions */ + pfm_reg_desc_t *pmd_desc; /* detailed PMD register dependencies descriptions */ } pmu_config_t; - /* * structure used to pass argument to/from remote CPU * using IPI to check and possibly save the PMU context on SMP systems. @@ -389,13 +391,12 @@ typedef struct { /* * perfmon internal variables */ -static pmu_config_t pmu_conf; /* PMU configuration */ static pfm_session_t pfm_sessions; /* global sessions information */ static struct proc_dir_entry *perfmon_dir; /* for debug only */ static pfm_stats_t pfm_stats[NR_CPUS]; +static pfm_intr_handler_desc_t *pfm_alternate_intr_handler; -DEFINE_PER_CPU(int, pfm_syst_wide); -static DEFINE_PER_CPU(int, pfm_dcr_pp); +DEFINE_PER_CPU(unsigned long, pfm_syst_info); /* sysctl() controls */ static pfm_sysctl_t pfm_sysctl; @@ -436,9 +437,6 @@ static struct { * forward declarations */ static void pfm_reset_pmu(struct task_struct *); -#ifdef CONFIG_SMP -static void pfm_fetch_regs(int cpu, struct task_struct *task, pfm_context_t *ctx); -#endif static void pfm_lazy_save_regs (struct task_struct *ta); #if defined(CONFIG_ITANIUM) @@ -449,43 +447,76 @@ static void pfm_lazy_save_regs (struct task_struct *ta); #include "perfmon_generic.h" #endif +static inline void +pfm_clear_psr_pp(void) +{ + __asm__ __volatile__ ("rsm psr.pp;; srlz.i;;"::: "memory"); +} + +static inline void +pfm_set_psr_pp(void) +{ + __asm__ __volatile__ ("ssm psr.pp;; srlz.i;;"::: "memory"); +} + +static inline void +pfm_clear_psr_up(void) +{ + __asm__ __volatile__ ("rum psr.up;; srlz.i;;"::: "memory"); +} + +static inline void +pfm_set_psr_up(void) +{ + __asm__ __volatile__ ("sum psr.up;; srlz.i;;"::: "memory"); +} + +static inline unsigned long +pfm_get_psr(void) +{ + unsigned long tmp; + __asm__ __volatile__ ("mov %0=psr;;": "=r"(tmp) :: "memory"); + return tmp; +} + +static inline void +pfm_set_psr_l(unsigned long val) +{ + __asm__ __volatile__ ("mov psr.l=%0;; srlz.i;;"::"r"(val): "memory"); +} + +static inline void +pfm_freeze_pmu(void) +{ + ia64_set_pmc(0,1UL); + ia64_srlz_d(); +} + +static inline void +pfm_unfreeze_pmu(void) +{ + ia64_set_pmc(0,0UL); + ia64_srlz_d(); +} + static inline unsigned long pfm_read_soft_counter(pfm_context_t *ctx, int i) { - return ctx->ctx_soft_pmds[i].val + (ia64_get_pmd(i) & pmu_conf.perf_ovfl_val); + return ctx->ctx_soft_pmds[i].val + (ia64_get_pmd(i) & pmu_conf.ovfl_val); } static inline void pfm_write_soft_counter(pfm_context_t *ctx, int i, unsigned long val) { - ctx->ctx_soft_pmds[i].val = val & ~pmu_conf.perf_ovfl_val; + ctx->ctx_soft_pmds[i].val = val & ~pmu_conf.ovfl_val; /* * writing to unimplemented part is ignore, so we do not need to * mask off top part */ - ia64_set_pmd(i, val & pmu_conf.perf_ovfl_val); + ia64_set_pmd(i, val & pmu_conf.ovfl_val); } /* - * finds the number of PM(C|D) registers given - * the bitvector returned by PAL - */ -static unsigned long __init -find_num_pm_regs(long *buffer) -{ - int i=3; /* 4 words/per bitvector */ - - /* start from the most significant word */ - while (i>=0 && buffer[i] == 0 ) i--; - if (i< 0) { - printk(KERN_ERR "perfmon: No bit set in pm_buffer\n"); - return 0; - } - return 1+ ia64_fls(buffer[i]) + 64 * i; -} - - -/* * Generates a unique (per CPU) timestamp */ static inline unsigned long @@ -562,7 +593,7 @@ pfm_vm_close(struct vm_area_struct *vma) pfm_smpl_buffer_desc_t *psb = (pfm_smpl_buffer_desc_t *)vma->vm_private_data; if (psb == NULL) { - printk("perfmon: psb is null in [%d]\n", current->pid); + printk(KERN_DEBUG "perfmon: psb is null in [%d]\n", current->pid); return; } /* @@ -627,7 +658,7 @@ pfm_remove_smpl_mapping(struct task_struct *task) * some sanity checks first */ if (ctx == NULL || task->mm == NULL || ctx->ctx_smpl_vaddr == 0 || ctx->ctx_psb == NULL) { - printk("perfmon: invalid context mm=%p\n", task->mm); + printk(KERN_DEBUG "perfmon: invalid context mm=%p\n", task->mm); return -1; } psb = ctx->ctx_psb; @@ -638,11 +669,11 @@ pfm_remove_smpl_mapping(struct task_struct *task) up_write(&task->mm->mmap_sem); if (r !=0) { - printk("perfmon: pid %d unable to unmap sampling buffer @0x%lx size=%ld\n", - task->pid, ctx->ctx_smpl_vaddr, psb->psb_size); + printk(KERN_DEBUG "perfmon: pid %d unable to unmap sampling buffer " + "@0x%lx size=%ld\n", task->pid, ctx->ctx_smpl_vaddr, psb->psb_size); } - DBprintk(("[%d] do_unmap(0x%lx, %ld)=%d refcnt=%lu psb_flags=0x%x\n", + DBprintk(("[%d] do_unmap(0x%lx, %ld)=%d refcnt=%lu psb_flags=0x%x\n", task->pid, ctx->ctx_smpl_vaddr, psb->psb_size, r, psb->psb_refcnt, psb->psb_flags)); return 0; @@ -677,7 +708,7 @@ pfm_remap_buffer(struct vm_area_struct *vma, unsigned long buf, unsigned long ad page = pfm_kvirt_to_pa(buf); if (remap_page_range(vma, addr, page, PAGE_SIZE, PAGE_READONLY)) return -ENOMEM; - + addr += PAGE_SIZE; buf += PAGE_SIZE; size -= PAGE_SIZE; @@ -834,7 +865,7 @@ pfm_smpl_buffer_alloc(pfm_context_t *ctx, unsigned long *which_pmds, unsigned lo vma->vm_end = vma->vm_start + size; DBprintk(("entries=%ld aligned size=%ld, unmapped @0x%lx\n", entries, size, vma->vm_start)); - + /* can only be applied to current, need to have the mm semaphore held when called */ if (pfm_remap_buffer(vma, (unsigned long)smpl_buf, vma->vm_start, size)) { DBprintk(("Can't remap buffer\n")); @@ -875,6 +906,121 @@ error_kmalloc: return -ENOMEM; } +static int +pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned long cpu_mask) +{ + unsigned long m, undo_mask; + unsigned int n, i; + + /* + * validy checks on cpu_mask have been done upstream + */ + LOCK_PFS(); + + if (is_syswide) { + /* + * cannot mix system wide and per-task sessions + */ + if (pfm_sessions.pfs_task_sessions > 0UL) { + DBprintk(("system wide not possible, %u conflicting task_sessions\n", + pfm_sessions.pfs_task_sessions)); + goto abort; + } + + m = cpu_mask; undo_mask = 0UL; n = 0; + DBprintk(("cpu_mask=0x%lx\n", cpu_mask)); + for(i=0; m; i++, m>>=1) { + + if ((m & 0x1) == 0UL) continue; + + if (pfm_sessions.pfs_sys_session[i]) goto undo; + + DBprintk(("reserving CPU%d currently on CPU%d\n", i, smp_processor_id())); + + pfm_sessions.pfs_sys_session[i] = task; + undo_mask |= 1UL << i; + n++; + } + pfm_sessions.pfs_sys_sessions += n; + } else { + if (pfm_sessions.pfs_sys_sessions) goto abort; + pfm_sessions.pfs_task_sessions++; + } + DBprintk(("task_sessions=%u sys_session[%d]=%d", + pfm_sessions.pfs_task_sessions, + smp_processor_id(), pfm_sessions.pfs_sys_session[smp_processor_id()] ? 1 : 0)); + UNLOCK_PFS(); + return 0; +undo: + DBprintk(("system wide not possible, conflicting session [%d] on CPU%d\n", + pfm_sessions.pfs_sys_session[i]->pid, i)); + + for(i=0; undo_mask; i++, undo_mask >>=1) { + pfm_sessions.pfs_sys_session[i] = NULL; + } +abort: + UNLOCK_PFS(); + + return -EBUSY; + +} + +static int +pfm_unreserve_session(struct task_struct *task, int is_syswide, unsigned long cpu_mask) +{ + pfm_context_t *ctx; + unsigned long m; + unsigned int n, i; + + ctx = task ? task->thread.pfm_context : NULL; + + /* + * validy checks on cpu_mask have been done upstream + */ + LOCK_PFS(); + + DBprintk(("[%d] sys_sessions=%u task_sessions=%u dbregs=%u syswide=%d cpu_mask=0x%lx\n", + task->pid, + pfm_sessions.pfs_sys_sessions, + pfm_sessions.pfs_task_sessions, + pfm_sessions.pfs_sys_use_dbregs, + is_syswide, + cpu_mask)); + + + if (is_syswide) { + m = cpu_mask; n = 0; + for(i=0; m; i++, m>>=1) { + if ((m & 0x1) == 0UL) continue; + pfm_sessions.pfs_sys_session[i] = NULL; + n++; + } + /* + * would not work with perfmon+more than one bit in cpu_mask + */ + if (ctx && ctx->ctx_fl_using_dbreg) { + if (pfm_sessions.pfs_sys_use_dbregs == 0) { + printk(KERN_DEBUG "perfmon: invalid release for [%d] " + "sys_use_dbregs=0\n", task->pid); + } else { + pfm_sessions.pfs_sys_use_dbregs--; + } + } + pfm_sessions.pfs_sys_sessions -= n; + + DBprintk(("CPU%d sys_sessions=%u\n", + smp_processor_id(), pfm_sessions.pfs_sys_sessions)); + } else { + pfm_sessions.pfs_task_sessions--; + DBprintk(("[%d] task_sessions=%u\n", + task->pid, pfm_sessions.pfs_task_sessions)); + } + + UNLOCK_PFS(); + + return 0; +} + /* * XXX: do something better here */ @@ -891,6 +1037,7 @@ pfm_bad_permissions(struct task_struct *task) static int pfx_is_sane(struct task_struct *task, pfarg_context_t *pfx) { + unsigned long smpl_pmds = pfx->ctx_smpl_regs[0]; int ctx_flags; int cpu; @@ -957,6 +1104,11 @@ pfx_is_sane(struct task_struct *task, pfarg_context_t *pfx) } #endif } + /* verify validity of smpl_regs */ + if ((smpl_pmds & pmu_conf.impl_pmds[0]) != smpl_pmds) { + DBprintk(("invalid smpl_regs 0x%lx\n", smpl_pmds)); + return -EINVAL; + } /* probably more to add here */ return 0; @@ -968,7 +1120,7 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int { pfarg_context_t tmp; void *uaddr = NULL; - int ret, cpu = 0; + int ret; int ctx_flags; pid_t notify_pid; @@ -987,40 +1139,8 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int ctx_flags = tmp.ctx_flags; - ret = -EBUSY; - - LOCK_PFS(); - - if (ctx_flags & PFM_FL_SYSTEM_WIDE) { - - /* at this point, we know there is at least one bit set */ - cpu = ffz(~tmp.ctx_cpu_mask); - - DBprintk(("requesting CPU%d currently on CPU%d\n",cpu, smp_processor_id())); - - if (pfm_sessions.pfs_task_sessions > 0) { - DBprintk(("system wide not possible, task_sessions=%ld\n", pfm_sessions.pfs_task_sessions)); - goto abort; - } - - if (pfm_sessions.pfs_sys_session[cpu]) { - DBprintk(("system wide not possible, conflicting session [%d] on CPU%d\n",pfm_sessions.pfs_sys_session[cpu]->pid, cpu)); - goto abort; - } - pfm_sessions.pfs_sys_session[cpu] = task; - /* - * count the number of system wide sessions - */ - pfm_sessions.pfs_sys_sessions++; - - } else if (pfm_sessions.pfs_sys_sessions == 0) { - pfm_sessions.pfs_task_sessions++; - } else { - /* no per-process monitoring while there is a system wide session */ - goto abort; - } - - UNLOCK_PFS(); + ret = pfm_reserve_session(task, ctx_flags & PFM_FL_SYSTEM_WIDE, tmp.ctx_cpu_mask); + if (ret) goto abort; ret = -ENOMEM; @@ -1103,6 +1223,7 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int ctx->ctx_fl_inherit = ctx_flags & PFM_FL_INHERIT_MASK; ctx->ctx_fl_block = (ctx_flags & PFM_FL_NOTIFY_BLOCK) ? 1 : 0; ctx->ctx_fl_system = (ctx_flags & PFM_FL_SYSTEM_WIDE) ? 1: 0; + ctx->ctx_fl_excl_idle = (ctx_flags & PFM_FL_EXCL_IDLE) ? 1: 0; ctx->ctx_fl_frozen = 0; /* * setting this flag to 0 here means, that the creator or the task that the @@ -1113,14 +1234,10 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int ctx->ctx_fl_protected = 0; /* for system wide mode only (only 1 bit set) */ - ctx->ctx_cpu = cpu; + ctx->ctx_cpu = ffz(~tmp.ctx_cpu_mask); atomic_set(&ctx->ctx_last_cpu,-1); /* SMP only, means no CPU */ - /* may be redudant with memset() but at least it's easier to remember */ - atomic_set(&ctx->ctx_saving_in_progress, 0); - atomic_set(&ctx->ctx_is_busy, 0); - sema_init(&ctx->ctx_restart_sem, 0); /* init this semaphore to locked */ if (__copy_to_user(req, &tmp, sizeof(tmp))) { @@ -1131,9 +1248,9 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int DBprintk(("context=%p, pid=%d notify_task=%p\n", (void *)ctx, task->pid, ctx->ctx_notify_task)); - DBprintk(("context=%p, pid=%d flags=0x%x inherit=%d block=%d system=%d\n", + DBprintk(("context=%p, pid=%d flags=0x%x inherit=%d block=%d system=%d excl_idle=%d\n", (void *)ctx, task->pid, ctx_flags, ctx->ctx_fl_inherit, - ctx->ctx_fl_block, ctx->ctx_fl_system)); + ctx->ctx_fl_block, ctx->ctx_fl_system, ctx->ctx_fl_excl_idle)); /* * when no notification is required, we can make this visible at the last moment @@ -1146,8 +1263,8 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int */ if (ctx->ctx_fl_system) { ctx->ctx_saved_cpus_allowed = task->cpus_allowed; - set_cpus_allowed(task, 1UL << cpu); - DBprintk(("[%d] rescheduled allowed=0x%lx\n", task->pid,task->cpus_allowed)); + set_cpus_allowed(task, tmp.ctx_cpu_mask); + DBprintk(("[%d] rescheduled allowed=0x%lx\n", task->pid, task->cpus_allowed)); } return 0; @@ -1155,20 +1272,8 @@ pfm_context_create(struct task_struct *task, pfm_context_t *ctx, void *req, int buffer_error: pfm_context_free(ctx); error: - /* - * undo session reservation - */ - LOCK_PFS(); - - if (ctx_flags & PFM_FL_SYSTEM_WIDE) { - pfm_sessions.pfs_sys_session[cpu] = NULL; - pfm_sessions.pfs_sys_sessions--; - } else { - pfm_sessions.pfs_task_sessions--; - } + pfm_unreserve_session(task, ctx_flags & PFM_FL_SYSTEM_WIDE , tmp.ctx_cpu_mask); abort: - UNLOCK_PFS(); - /* make sure we don't leave anything behind */ task->thread.pfm_context = NULL; @@ -1200,9 +1305,7 @@ pfm_reset_regs(pfm_context_t *ctx, unsigned long *ovfl_regs, int flag) unsigned long mask = ovfl_regs[0]; unsigned long reset_others = 0UL; unsigned long val; - int i, is_long_reset = (flag & PFM_RELOAD_LONG_RESET); - - DBprintk(("masks=0x%lx\n", mask)); + int i, is_long_reset = (flag == PFM_PMD_LONG_RESET); /* * now restore reset value on sampling overflowed counters @@ -1213,7 +1316,7 @@ pfm_reset_regs(pfm_context_t *ctx, unsigned long *ovfl_regs, int flag) val = pfm_new_counter_value(ctx->ctx_soft_pmds + i, is_long_reset); reset_others |= ctx->ctx_soft_pmds[i].reset_pmds[0]; - DBprintk(("[%d] %s reset soft_pmd[%d]=%lx\n", current->pid, + DBprintk_ovfl(("[%d] %s reset soft_pmd[%d]=%lx\n", current->pid, is_long_reset ? "long" : "short", i, val)); /* upper part is ignored on rval */ @@ -1235,7 +1338,7 @@ pfm_reset_regs(pfm_context_t *ctx, unsigned long *ovfl_regs, int flag) } else { ia64_set_pmd(i, val); } - DBprintk(("[%d] %s reset_others pmd[%d]=%lx\n", current->pid, + DBprintk_ovfl(("[%d] %s reset_others pmd[%d]=%lx\n", current->pid, is_long_reset ? "long" : "short", i, val)); } ia64_srlz_d(); @@ -1246,7 +1349,7 @@ pfm_write_pmcs(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun { struct thread_struct *th = &task->thread; pfarg_reg_t tmp, *req = (pfarg_reg_t *)arg; - unsigned long value; + unsigned long value, reset_pmds; unsigned int cnum, reg_flags, flags; int i; int ret = -EINVAL; @@ -1262,10 +1365,11 @@ pfm_write_pmcs(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun if (__copy_from_user(&tmp, req, sizeof(tmp))) return -EFAULT; - cnum = tmp.reg_num; - reg_flags = tmp.reg_flags; - value = tmp.reg_value; - flags = 0; + cnum = tmp.reg_num; + reg_flags = tmp.reg_flags; + value = tmp.reg_value; + reset_pmds = tmp.reg_reset_pmds[0]; + flags = 0; /* * we reject all non implemented PMC as well @@ -1283,6 +1387,8 @@ pfm_write_pmcs(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun * any other configuration is rejected. */ if (PMC_IS_MONITOR(cnum) || PMC_IS_COUNTING(cnum)) { + DBprintk(("pmc[%u].pm=%ld\n", cnum, PMC_PM(cnum, value))); + if (ctx->ctx_fl_system ^ PMC_PM(cnum, value)) { DBprintk(("pmc_pm=%ld fl_system=%d\n", PMC_PM(cnum, value), ctx->ctx_fl_system)); goto error; @@ -1310,6 +1416,11 @@ pfm_write_pmcs(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun if (reg_flags & PFM_REGFL_RANDOM) flags |= PFM_REGFL_RANDOM; + /* verify validity of reset_pmds */ + if ((reset_pmds & pmu_conf.impl_pmds[0]) != reset_pmds) { + DBprintk(("invalid reset_pmds 0x%lx for pmc%u\n", reset_pmds, cnum)); + goto error; + } } else if (reg_flags & (PFM_REGFL_OVFL_NOTIFY|PFM_REGFL_RANDOM)) { DBprintk(("cannot set ovfl_notify or random on pmc%u\n", cnum)); goto error; @@ -1348,13 +1459,10 @@ pfm_write_pmcs(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun ctx->ctx_soft_pmds[cnum].flags = flags; if (PMC_IS_COUNTING(cnum)) { - /* - * copy reset vector - */ - ctx->ctx_soft_pmds[cnum].reset_pmds[0] = tmp.reg_reset_pmds[0]; - ctx->ctx_soft_pmds[cnum].reset_pmds[1] = tmp.reg_reset_pmds[1]; - ctx->ctx_soft_pmds[cnum].reset_pmds[2] = tmp.reg_reset_pmds[2]; - ctx->ctx_soft_pmds[cnum].reset_pmds[3] = tmp.reg_reset_pmds[3]; + ctx->ctx_soft_pmds[cnum].reset_pmds[0] = reset_pmds; + + /* mark all PMDS to be accessed as used */ + CTX_USED_PMD(ctx, reset_pmds); } /* @@ -1397,7 +1505,7 @@ pfm_write_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun unsigned long value, hw_value; unsigned int cnum; int i; - int ret; + int ret = 0; /* we don't quite support this right now */ if (task != current) return -EINVAL; @@ -1448,9 +1556,9 @@ pfm_write_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun /* update virtualized (64bits) counter */ if (PMD_IS_COUNTING(cnum)) { ctx->ctx_soft_pmds[cnum].lval = value; - ctx->ctx_soft_pmds[cnum].val = value & ~pmu_conf.perf_ovfl_val; + ctx->ctx_soft_pmds[cnum].val = value & ~pmu_conf.ovfl_val; - hw_value = value & pmu_conf.perf_ovfl_val; + hw_value = value & pmu_conf.ovfl_val; ctx->ctx_soft_pmds[cnum].long_reset = tmp.reg_long_reset; ctx->ctx_soft_pmds[cnum].short_reset = tmp.reg_short_reset; @@ -1478,7 +1586,7 @@ pfm_write_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int coun ctx->ctx_soft_pmds[cnum].val, ctx->ctx_soft_pmds[cnum].short_reset, ctx->ctx_soft_pmds[cnum].long_reset, - ia64_get_pmd(cnum) & pmu_conf.perf_ovfl_val, + ia64_get_pmd(cnum) & pmu_conf.ovfl_val, PMC_OVFL_NOTIFY(ctx, cnum) ? 'Y':'N', ctx->ctx_used_pmds[0], ctx->ctx_soft_pmds[cnum].reset_pmds[0])); @@ -1504,15 +1612,18 @@ abort_mission: return ret; } - static int pfm_read_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs) { struct thread_struct *th = &task->thread; - unsigned long val = 0UL; + unsigned long val, lval; pfarg_reg_t *req = (pfarg_reg_t *)arg; unsigned int cnum, reg_flags = 0; - int i, ret = -EINVAL; + int i, ret = 0; + +#if __GNUC__ < 3 + int foo; +#endif if (!CTX_IS_ENABLED(ctx)) return -EINVAL; @@ -1528,9 +1639,16 @@ pfm_read_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int count DBprintk(("ctx_last_cpu=%d for [%d]\n", atomic_read(&ctx->ctx_last_cpu), task->pid)); for (i = 0; i < count; i++, req++) { - +#if __GNUC__ < 3 + foo = __get_user(cnum, &req->reg_num); + if (foo) return -EFAULT; + foo = __get_user(reg_flags, &req->reg_flags); + if (foo) return -EFAULT; +#else if (__get_user(cnum, &req->reg_num)) return -EFAULT; if (__get_user(reg_flags, &req->reg_flags)) return -EFAULT; +#endif + lval = 0UL; if (!PMD_IS_IMPL(cnum)) goto abort_mission; /* @@ -1553,34 +1671,16 @@ pfm_read_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int count val = ia64_get_pmd(cnum); DBprintk(("reading pmd[%u]=0x%lx from hw\n", cnum, val)); } else { -#ifdef CONFIG_SMP - int cpu; - /* - * for SMP system, the context may still be live on another - * CPU so we need to fetch it before proceeding with the read - * This call we only be made once for the whole loop because - * of ctx_last_cpu becoming == -1. - * - * We cannot reuse ctx_last_cpu as it may change before we get to the - * actual IPI call. In this case, we will do the call for nothing but - * there is no way around it. The receiving side will simply do nothing. - */ - cpu = atomic_read(&ctx->ctx_last_cpu); - if (cpu != -1) { - DBprintk(("must fetch on CPU%d for [%d]\n", cpu, task->pid)); - pfm_fetch_regs(cpu, task, ctx); - } -#endif - /* context has been saved */ val = th->pmd[cnum]; } if (PMD_IS_COUNTING(cnum)) { /* * XXX: need to check for overflow */ - - val &= pmu_conf.perf_ovfl_val; + val &= pmu_conf.ovfl_val; val += ctx->ctx_soft_pmds[cnum].val; + + lval = ctx->ctx_soft_pmds[cnum].lval; } /* @@ -1592,10 +1692,11 @@ pfm_read_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int count val = v; } - PFM_REG_RETFLAG_SET(reg_flags, 0); + PFM_REG_RETFLAG_SET(reg_flags, ret); DBprintk(("read pmd[%u] ret=%d value=0x%lx pmc=0x%lx\n", - cnum, ret, val, ia64_get_pmc(cnum))); + cnum, ret, val, ia64_get_pmc(cnum))); + /* * update register return value, abort all if problem during copy. * we only modify the reg_flags field. no check mode is fine because @@ -1604,16 +1705,19 @@ pfm_read_pmds(struct task_struct *task, pfm_context_t *ctx, void *arg, int count if (__put_user(cnum, &req->reg_num)) return -EFAULT; if (__put_user(val, &req->reg_value)) return -EFAULT; if (__put_user(reg_flags, &req->reg_flags)) return -EFAULT; + if (__put_user(lval, &req->reg_last_reset_value)) return -EFAULT; } return 0; abort_mission: PFM_REG_RETFLAG_SET(reg_flags, PFM_REG_RETFL_EINVAL); + /* + * XXX: if this fails, we stick with the original failure, flag not updated! + */ + __put_user(reg_flags, &req->reg_flags); - if (__put_user(reg_flags, &req->reg_flags)) ret = -EFAULT; - - return ret; + return -EINVAL; } #ifdef PFM_PMU_USES_DBR @@ -1655,7 +1759,7 @@ pfm_use_debug_registers(struct task_struct *task) else pfm_sessions.pfs_ptrace_use_dbregs++; - DBprintk(("ptrace_use_dbregs=%lu sys_use_dbregs=%lu by [%d] ret = %d\n", + DBprintk(("ptrace_use_dbregs=%u sys_use_dbregs=%u by [%d] ret = %d\n", pfm_sessions.pfs_ptrace_use_dbregs, pfm_sessions.pfs_sys_use_dbregs, task->pid, ret)); @@ -1673,7 +1777,6 @@ pfm_use_debug_registers(struct task_struct *task) * perfmormance monitoring, so we only decrement the number * of "ptraced" debug register users to keep the count up to date */ - int pfm_release_debug_registers(struct task_struct *task) { @@ -1681,7 +1784,8 @@ pfm_release_debug_registers(struct task_struct *task) LOCK_PFS(); if (pfm_sessions.pfs_ptrace_use_dbregs == 0) { - printk("perfmon: invalid release for [%d] ptrace_use_dbregs=0\n", task->pid); + printk(KERN_DEBUG "perfmon: invalid release for [%d] ptrace_use_dbregs=0\n", + task->pid); ret = -1; } else { pfm_sessions.pfs_ptrace_use_dbregs--; @@ -1702,6 +1806,7 @@ pfm_use_debug_registers(struct task_struct *task) { return 0; } + int pfm_release_debug_registers(struct task_struct *task) { @@ -1721,9 +1826,12 @@ pfm_restart(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, if (!CTX_IS_ENABLED(ctx)) return -EINVAL; if (task == current) { - DBprintk(("restarting self %d frozen=%d \n", current->pid, ctx->ctx_fl_frozen)); + DBprintk(("restarting self %d frozen=%d ovfl_regs=0x%lx\n", + task->pid, + ctx->ctx_fl_frozen, + ctx->ctx_ovfl_regs[0])); - pfm_reset_regs(ctx, ctx->ctx_ovfl_regs, PFM_RELOAD_LONG_RESET); + pfm_reset_regs(ctx, ctx->ctx_ovfl_regs, PFM_PMD_LONG_RESET); ctx->ctx_ovfl_regs[0] = 0UL; @@ -1739,8 +1847,7 @@ pfm_restart(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, } /* simply unfreeze */ - ia64_set_pmc(0, 0); - ia64_srlz_d(); + pfm_unfreeze_pmu(); return 0; } @@ -1806,18 +1913,18 @@ pfm_stop(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, ia64_set_dcr(ia64_get_dcr() & ~IA64_DCR_PP); /* stop monitoring */ - __asm__ __volatile__ ("rsm psr.pp;;"::: "memory"); + pfm_clear_psr_pp(); ia64_srlz_i(); - __get_cpu_var(pfm_dcr_pp) = 0; + PFM_CPUINFO_CLEAR(PFM_CPUINFO_DCR_PP); ia64_psr(regs)->pp = 0; } else { /* stop monitoring */ - __asm__ __volatile__ ("rum psr.up;;"::: "memory"); + pfm_clear_psr_up(); ia64_srlz_i(); @@ -1939,7 +2046,7 @@ pfm_debug(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, pfm_sysctl.debug = mode == 0 ? 0 : 1; - printk("perfmon debugging %s\n", pfm_sysctl.debug ? "on" : "off"); + printk(KERN_INFO "perfmon debugging %s\n", pfm_sysctl.debug ? "on" : "off"); return 0; } @@ -1979,14 +2086,9 @@ pfm_write_ibr_dbr(int mode, struct task_struct *task, void *arg, int count, stru int i, ret = 0; /* - * for range restriction: psr.db must be cleared or the - * the PMU will ignore the debug registers. - * - * XXX: may need more in system wide mode, - * no task can have this bit set? + * we do not need to check for ipsr.db because we do clear ibr.x, dbr.r, and dbr.w + * ensuring that no real breakpoint can be installed via this call. */ - if (ia64_psr(regs)->db == 1) return -EINVAL; - first_time = ctx->ctx_fl_using_dbreg == 0; @@ -2055,7 +2157,6 @@ pfm_write_ibr_dbr(int mode, struct task_struct *task, void *arg, int count, stru * Now install the values into the registers */ for (i = 0; i < count; i++, req++) { - if (__copy_from_user(&tmp, req, sizeof(tmp))) goto abort_mission; @@ -2145,7 +2246,7 @@ abort_mission: * XXX: for now we can only come here on EINVAL */ PFM_REG_RETFLAG_SET(tmp.dbreg_flags, PFM_REG_RETFL_EINVAL); - __put_user(tmp.dbreg_flags, &req->dbreg_flags); + if (__put_user(tmp.dbreg_flags, &req->dbreg_flags)) ret = -EFAULT; } return ret; } @@ -2209,19 +2310,19 @@ pfm_start(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, current)); if (PMU_OWNER() != task) { - printk("perfmon: pfm_start task [%d] not pmu owner\n", task->pid); + printk(KERN_DEBUG "perfmon: pfm_start task [%d] not pmu owner\n", task->pid); return -EINVAL; } if (ctx->ctx_fl_system) { - __get_cpu_var(pfm_dcr_pp) = 1; + PFM_CPUINFO_SET(PFM_CPUINFO_DCR_PP); /* set user level psr.pp */ ia64_psr(regs)->pp = 1; /* start monitoring at kernel level */ - __asm__ __volatile__ ("ssm psr.pp;;"::: "memory"); + pfm_set_psr_pp(); /* enable dcr pp */ ia64_set_dcr(ia64_get_dcr()|IA64_DCR_PP); @@ -2230,14 +2331,15 @@ pfm_start(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, } else { if ((task->thread.flags & IA64_THREAD_PM_VALID) == 0) { - printk("perfmon: pfm_start task flag not set for [%d]\n", task->pid); + printk(KERN_DEBUG "perfmon: pfm_start task flag not set for [%d]\n", + task->pid); return -EINVAL; } /* set user level psr.up */ ia64_psr(regs)->up = 1; /* start monitoring at kernel level */ - __asm__ __volatile__ ("sum psr.up;;"::: "memory"); + pfm_set_psr_up(); ia64_srlz_i(); } @@ -2264,11 +2366,12 @@ pfm_enable(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, ia64_psr(regs)->up = 0; /* just to make sure! */ /* make sure monitoring is stopped */ - __asm__ __volatile__ ("rsm psr.pp;;"::: "memory"); + pfm_clear_psr_pp(); ia64_srlz_i(); - __get_cpu_var(pfm_dcr_pp) = 0; - __get_cpu_var(pfm_syst_wide) = 1; + PFM_CPUINFO_CLEAR(PFM_CPUINFO_DCR_PP); + PFM_CPUINFO_SET(PFM_CPUINFO_SYST_WIDE); + if (ctx->ctx_fl_excl_idle) PFM_CPUINFO_SET(PFM_CPUINFO_EXCL_IDLE); } else { /* * needed in case the task was a passive task during @@ -2279,7 +2382,7 @@ pfm_enable(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, ia64_psr(regs)->up = 0; /* make sure monitoring is stopped */ - __asm__ __volatile__ ("rum psr.up;;"::: "memory"); + pfm_clear_psr_up(); ia64_srlz_i(); DBprintk(("clearing psr.sp for [%d]\n", current->pid)); @@ -2297,8 +2400,7 @@ pfm_enable(struct task_struct *task, pfm_context_t *ctx, void *arg, int count, atomic_set(&ctx->ctx_last_cpu, smp_processor_id()); /* simply unfreeze */ - ia64_set_pmc(0, 0); - ia64_srlz_d(); + pfm_unfreeze_pmu(); return 0; } @@ -2331,6 +2433,7 @@ pfm_get_pmc_reset(struct task_struct *task, pfm_context_t *ctx, void *arg, int c abort_mission: PFM_REG_RETFLAG_SET(tmp.reg_flags, PFM_REG_RETFL_EINVAL); if (__copy_to_user(req, &tmp, sizeof(tmp))) ret = -EFAULT; + return ret; } @@ -2400,7 +2503,7 @@ check_task_state(struct task_struct *task) return ret; } -asmlinkage int +asmlinkage long sys_perfmonctl (pid_t pid, int cmd, void *arg, int count, long arg5, long arg6, long arg7, long arg8, long stack) { @@ -2503,7 +2606,7 @@ pfm_ovfl_block_reset(void) * do some sanity checks first */ if (!ctx) { - printk("perfmon: [%d] has no PFM context\n", current->pid); + printk(KERN_DEBUG "perfmon: [%d] has no PFM context\n", current->pid); return; } @@ -2532,7 +2635,7 @@ non_blocking: * use the local reference */ - pfm_reset_regs(ctx, ctx->ctx_ovfl_regs, PFM_RELOAD_LONG_RESET); + pfm_reset_regs(ctx, ctx->ctx_ovfl_regs, PFM_PMD_LONG_RESET); ctx->ctx_ovfl_regs[0] = 0UL; @@ -2545,8 +2648,7 @@ non_blocking: ctx->ctx_psb->psb_index = 0; } - ia64_set_pmc(0, 0); - ia64_srlz_d(); + pfm_unfreeze_pmu(); /* state restored, can go back to work (user mode) */ } @@ -2591,19 +2693,11 @@ pfm_record_sample(struct task_struct *task, pfm_context_t *ctx, unsigned long ov h->pid = current->pid; h->cpu = smp_processor_id(); h->last_reset_value = ovfl_mask ? ctx->ctx_soft_pmds[ffz(~ovfl_mask)].lval : 0UL; - /* - * where did the fault happen - */ - h->ip = regs ? regs->cr_iip | ((regs->cr_ipsr >> 41) & 0x3): 0x0UL; - - /* - * which registers overflowed - */ - h->regs = ovfl_mask; + h->ip = regs ? regs->cr_iip | ((regs->cr_ipsr >> 41) & 0x3): 0x0UL; + h->regs = ovfl_mask; /* which registers overflowed */ /* guaranteed to monotonically increase on each cpu */ h->stamp = pfm_get_stamp(); - h->period = 0UL; /* not yet used */ /* position for first pmd */ e = (unsigned long *)(h+1); @@ -2683,16 +2777,16 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str * Don't think this could happen given upfront tests */ if ((t->flags & IA64_THREAD_PM_VALID) == 0 && ctx->ctx_fl_system == 0) { - printk("perfmon: Spurious overflow interrupt: process %d not using perfmon\n", - task->pid); + printk(KERN_DEBUG "perfmon: Spurious overflow interrupt: process %d not " + "using perfmon\n", task->pid); return 0x1; } /* * sanity test. Should never happen */ if ((pmc0 & 0x1) == 0) { - printk("perfmon: pid %d pmc0=0x%lx assumption error for freeze bit\n", - task->pid, pmc0); + printk(KERN_DEBUG "perfmon: pid %d pmc0=0x%lx assumption error for freeze bit\n", + task->pid, pmc0); return 0x0; } @@ -2724,7 +2818,7 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str * pfm_read_pmds(). */ old_val = ctx->ctx_soft_pmds[i].val; - ctx->ctx_soft_pmds[i].val += 1 + pmu_conf.perf_ovfl_val; + ctx->ctx_soft_pmds[i].val += 1 + pmu_conf.ovfl_val; /* * check for overflow condition @@ -2739,9 +2833,7 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str } DBprintk_ovfl(("soft_pmd[%d].val=0x%lx old_val=0x%lx pmd=0x%lx ovfl_pmds=0x%lx ovfl_notify=0x%lx\n", i, ctx->ctx_soft_pmds[i].val, old_val, - ia64_get_pmd(i) & pmu_conf.perf_ovfl_val, ovfl_pmds, ovfl_notify)); - - + ia64_get_pmd(i) & pmu_conf.ovfl_val, ovfl_pmds, ovfl_notify)); } /* @@ -2776,7 +2868,7 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str */ if (ovfl_notify == 0UL) { if (ovfl_pmds) - pfm_reset_regs(ctx, &ovfl_pmds, PFM_RELOAD_SHORT_RESET); + pfm_reset_regs(ctx, &ovfl_pmds, PFM_PMD_SHORT_RESET); return 0x0; } @@ -2859,8 +2951,8 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str * this call is safe in an interrupt handler, so does read_lock() on tasklist_lock */ ret = send_sig_info(SIGPROF, &si, ctx->ctx_notify_task); - if (ret != 0) - printk("send_sig_info(process %d, SIGPROF)=%d\n", + if (ret != 0) + printk(KERN_DEBUG "send_sig_info(process %d, SIGPROF)=%d\n", ctx->ctx_notify_task->pid, ret); /* * now undo the protections in order @@ -2924,7 +3016,7 @@ lost_notify: /* XXX: more to do here, to convert to non-blocking (reset values) } static void -perfmon_interrupt (int irq, void *arg, struct pt_regs *regs) +pfm_interrupt_handler(int irq, void *arg, struct pt_regs *regs) { u64 pmc0; struct task_struct *task; @@ -2932,6 +3024,14 @@ perfmon_interrupt (int irq, void *arg, struct pt_regs *regs) pfm_stats[smp_processor_id()].pfm_ovfl_intr_count++; + /* + * if an alternate handler is registered, just bypass the default one + */ + if (pfm_alternate_intr_handler) { + (*pfm_alternate_intr_handler->handler)(irq, arg, regs); + return; + } + /* * srlz.d done before arriving here * @@ -2951,23 +3051,10 @@ perfmon_interrupt (int irq, void *arg, struct pt_regs *regs) /* sanity check */ if (!ctx) { - printk("perfmon: Spurious overflow interrupt: process %d has no PFM context\n", - task->pid); + printk(KERN_DEBUG "perfmon: Spurious overflow interrupt: process %d has " + "no PFM context\n", task->pid); return; } -#ifdef CONFIG_SMP - /* - * Because an IPI has higher priority than the PMU overflow interrupt, it is - * possible that the handler be interrupted by a request from another CPU to fetch - * the PMU state of the currently active context. The task may have just been - * migrated to another CPU which is trying to restore the context. If there was - * a pending overflow interrupt when the task left this CPU, it is possible for - * the handler to get interrupt by the IPI. In which case, we fetch request - * MUST be postponed until the interrupt handler is done. The ctx_is_busy - * flag indicates such a condition. The other CPU must busy wait until it's cleared. - */ - atomic_set(&ctx->ctx_is_busy, 1); -#endif /* * assume PMC[0].fr = 1 at this point @@ -2981,12 +3068,6 @@ perfmon_interrupt (int irq, void *arg, struct pt_regs *regs) ia64_set_pmc(0, pmc0); ia64_srlz_d(); -#ifdef CONFIG_SMP - /* - * announce that we are doing with the context - */ - atomic_set(&ctx->ctx_is_busy, 0); -#endif } else { pfm_stats[smp_processor_id()].pfm_spurious_ovfl_intr_count++; } @@ -2994,14 +3075,13 @@ perfmon_interrupt (int irq, void *arg, struct pt_regs *regs) /* for debug only */ static int -perfmon_proc_info(char *page) +pfm_proc_info(char *page) { char *p = page; int i; - p += sprintf(p, "enabled : %s\n", pmu_conf.pfm_is_disabled ? "No": "Yes"); p += sprintf(p, "fastctxsw : %s\n", pfm_sysctl.fastctxsw > 0 ? "Yes": "No"); - p += sprintf(p, "ovfl_mask : 0x%lx\n", pmu_conf.perf_ovfl_val); + p += sprintf(p, "ovfl_mask : 0x%lx\n", pmu_conf.ovfl_val); for(i=0; i < NR_CPUS; i++) { if (cpu_is_online(i) == 0) continue; @@ -3009,16 +3089,18 @@ perfmon_proc_info(char *page) p += sprintf(p, "CPU%-2d spurious intrs : %lu\n", i, pfm_stats[i].pfm_spurious_ovfl_intr_count); p += sprintf(p, "CPU%-2d recorded samples : %lu\n", i, pfm_stats[i].pfm_recorded_samples_count); p += sprintf(p, "CPU%-2d smpl buffer full : %lu\n", i, pfm_stats[i].pfm_full_smpl_buffer_count); + p += sprintf(p, "CPU%-2d syst_wide : %d\n", i, per_cpu(pfm_syst_info, i) & PFM_CPUINFO_SYST_WIDE ? 1 : 0); + p += sprintf(p, "CPU%-2d dcr_pp : %d\n", i, per_cpu(pfm_syst_info, i) & PFM_CPUINFO_DCR_PP ? 1 : 0); + p += sprintf(p, "CPU%-2d exclude idle : %d\n", i, per_cpu(pfm_syst_info, i) & PFM_CPUINFO_EXCL_IDLE ? 1 : 0); p += sprintf(p, "CPU%-2d owner : %d\n", i, pmu_owners[i].owner ? pmu_owners[i].owner->pid: -1); - p += sprintf(p, "CPU%-2d syst_wide : %d\n", i, per_cpu(pfm_syst_wide, i)); - p += sprintf(p, "CPU%-2d dcr_pp : %d\n", i, per_cpu(pfm_dcr_pp, i)); } LOCK_PFS(); - p += sprintf(p, "proc_sessions : %lu\n" - "sys_sessions : %lu\n" - "sys_use_dbregs : %lu\n" - "ptrace_use_dbregs : %lu\n", + + p += sprintf(p, "proc_sessions : %u\n" + "sys_sessions : %u\n" + "sys_use_dbregs : %u\n" + "ptrace_use_dbregs : %u\n", pfm_sessions.pfs_task_sessions, pfm_sessions.pfs_sys_sessions, pfm_sessions.pfs_sys_use_dbregs, @@ -3033,7 +3115,7 @@ perfmon_proc_info(char *page) static int perfmon_read_entry(char *page, char **start, off_t off, int count, int *eof, void *data) { - int len = perfmon_proc_info(page); + int len = pfm_proc_info(page); if (len <= off+count) *eof = 1; @@ -3046,24 +3128,66 @@ perfmon_read_entry(char *page, char **start, off_t off, int count, int *eof, voi return len; } +/* + * we come here as soon as PFM_CPUINFO_SYST_WIDE is set. This happens + * during pfm_enable() hence before pfm_start(). We cannot assume monitoring + * is active or inactive based on mode. We must rely on the value in + * cpu_data(i)->pfm_syst_info + */ void -pfm_syst_wide_update_task(struct task_struct *task, int mode) +pfm_syst_wide_update_task(struct task_struct *task, unsigned long info, int is_ctxswin) { - struct pt_regs *regs = (struct pt_regs *)((unsigned long) task + IA64_STK_OFFSET); + struct pt_regs *regs; + unsigned long dcr; + unsigned long dcr_pp; - regs--; + dcr_pp = info & PFM_CPUINFO_DCR_PP ? 1 : 0; /* - * propagate the value of the dcr_pp bit to the psr + * pid 0 is guaranteed to be the idle task. There is one such task with pid 0 + * on every CPU, so we can rely on the pid to identify the idle task. */ - ia64_psr(regs)->pp = mode ? __get_cpu_var(pfm_dcr_pp) : 0; + if ((info & PFM_CPUINFO_EXCL_IDLE) == 0 || task->pid) { + regs = (struct pt_regs *)((unsigned long) task + IA64_STK_OFFSET); + regs--; + ia64_psr(regs)->pp = is_ctxswin ? dcr_pp : 0; + return; + } + /* + * if monitoring has started + */ + if (dcr_pp) { + dcr = ia64_get_dcr(); + /* + * context switching in? + */ + if (is_ctxswin) { + /* mask monitoring for the idle task */ + ia64_set_dcr(dcr & ~IA64_DCR_PP); + pfm_clear_psr_pp(); + ia64_srlz_i(); + return; + } + /* + * context switching out + * restore monitoring for next task + * + * Due to inlining this odd if-then-else construction generates + * better code. + */ + ia64_set_dcr(dcr |IA64_DCR_PP); + pfm_set_psr_pp(); + ia64_srlz_i(); + } } void pfm_save_regs (struct task_struct *task) { pfm_context_t *ctx; + unsigned long mask; u64 psr; + int i; ctx = task->thread.pfm_context; @@ -3071,7 +3195,7 @@ pfm_save_regs (struct task_struct *task) /* * save current PSR: needed because we modify it */ - __asm__ __volatile__ ("mov %0=psr;;": "=r"(psr) :: "memory"); + psr = pfm_get_psr(); /* * stop monitoring: @@ -3080,129 +3204,61 @@ pfm_save_regs (struct task_struct *task) * We do not need to set psr.sp because, it is irrelevant in kernel. * It will be restored from ipsr when going back to user level */ - __asm__ __volatile__ ("rum psr.up;;"::: "memory"); + pfm_clear_psr_up(); ia64_srlz_i(); ctx->ctx_saved_psr = psr; - //ctx->ctx_last_cpu = smp_processor_id(); - -} - -static void -pfm_lazy_save_regs (struct task_struct *task) -{ - pfm_context_t *ctx; - struct thread_struct *t; - unsigned long mask; - int i; - - DBprintk(("on [%d] by [%d]\n", task->pid, current->pid)); - - t = &task->thread; - ctx = task->thread.pfm_context; - #ifdef CONFIG_SMP - /* - * announce we are saving this PMU state - * This will cause other CPU, to wait until we're done - * before using the context.h + /* + * We do not use a lazy scheme in SMP because + * of the new scheduler which masks interrupts + * during low-level context switch. So we save + * all the PMD register we use and restore on + * ctxsw in. * - * must be an atomic operation + * release ownership of this PMU. + * must be done before we save the registers. */ - atomic_set(&ctx->ctx_saving_in_progress, 1); - - /* - * if owner is NULL, it means that the other CPU won the race - * and the IPI has caused the context to be saved in pfm_handle_fectch_regs() - * instead of here. We have nothing to do - * - * note that this is safe, because the other CPU NEVER modifies saving_in_progress. - */ - if (PMU_OWNER() == NULL) goto do_nothing; -#endif + SET_PMU_OWNER(NULL); /* - * do not own the PMU + * save PMDs */ - SET_PMU_OWNER(NULL); - ia64_srlz_d(); - /* - * XXX needs further optimization. - * Also must take holes into account - */ mask = ctx->ctx_used_pmds[0]; for (i=0; mask; i++, mask>>=1) { - if (mask & 0x1) t->pmd[i] =ia64_get_pmd(i); + if (mask & 0x1) task->thread.pmd[i] =ia64_get_pmd(i); } - /* save pmc0 */ - t->pmc[0] = ia64_get_pmc(0); + /* + * save pmc0 + */ + task->thread.pmc[0] = ia64_get_pmc(0); - /* not owned by this CPU */ + /* + * force a full reload + */ atomic_set(&ctx->ctx_last_cpu, -1); - -#ifdef CONFIG_SMP -do_nothing: #endif - /* - * declare we are done saving this context - * - * must be an atomic operation - */ - atomic_set(&ctx->ctx_saving_in_progress,0); - } -#ifdef CONFIG_SMP -/* - * Handles request coming from other CPUs - */ -static void -pfm_handle_fetch_regs(void *info) +static void +pfm_lazy_save_regs (struct task_struct *task) { - pfm_smp_ipi_arg_t *arg = info; - struct thread_struct *t; pfm_context_t *ctx; + struct thread_struct *t; unsigned long mask; int i; - ctx = arg->task->thread.pfm_context; - t = &arg->task->thread; - - DBprintk(("task=%d owner=%d saving=%d\n", - arg->task->pid, - PMU_OWNER() ? PMU_OWNER()->pid: -1, - atomic_read(&ctx->ctx_saving_in_progress))); - - /* must wait until not busy before retrying whole request */ - if (atomic_read(&ctx->ctx_is_busy)) { - arg->retval = 2; - return; - } - - /* must wait if saving was interrupted */ - if (atomic_read(&ctx->ctx_saving_in_progress)) { - arg->retval = 1; - return; - } - - /* can proceed, done with context */ - if (PMU_OWNER() != arg->task) { - arg->retval = 0; - return; - } + DBprintk(("on [%d] by [%d]\n", task->pid, current->pid)); - DBprintk(("saving state for [%d] used_pmcs=0x%lx reload_pmcs=0x%lx used_pmds=0x%lx\n", - arg->task->pid, - ctx->ctx_used_pmcs[0], - ctx->ctx_reload_pmcs[0], - ctx->ctx_used_pmds[0])); + t = &task->thread; + ctx = task->thread.pfm_context; /* - * XXX: will be replaced with pure assembly call + * do not own the PMU */ SET_PMU_OWNER(NULL); @@ -3210,10 +3266,11 @@ pfm_handle_fetch_regs(void *info) /* * XXX needs further optimization. + * Also must take holes into account */ mask = ctx->ctx_used_pmds[0]; for (i=0; mask; i++, mask>>=1) { - if (mask & 0x1) t->pmd[i] = ia64_get_pmd(i); + if (mask & 0x1) t->pmd[i] =ia64_get_pmd(i); } /* save pmc0 */ @@ -3221,67 +3278,8 @@ pfm_handle_fetch_regs(void *info) /* not owned by this CPU */ atomic_set(&ctx->ctx_last_cpu, -1); - - /* can proceed */ - arg->retval = 0; } -/* - * Function call to fetch PMU state from another CPU identified by 'cpu'. - * If the context is being saved on the remote CPU, then we busy wait until - * the saving is done and then we return. In this case, non IPI is sent. - * Otherwise, we send an IPI to the remote CPU, potentially interrupting - * pfm_lazy_save_regs() over there. - * - * If the retval==1, then it means that we interrupted remote save and that we must - * wait until the saving is over before proceeding. - * Otherwise, we did the saving on the remote CPU, and it was done by the time we got there. - * in either case, we can proceed. - */ -static void -pfm_fetch_regs(int cpu, struct task_struct *task, pfm_context_t *ctx) -{ - pfm_smp_ipi_arg_t arg; - int ret; - - arg.task = task; - arg.retval = -1; - - if (atomic_read(&ctx->ctx_is_busy)) { -must_wait_busy: - while (atomic_read(&ctx->ctx_is_busy)); - } - - if (atomic_read(&ctx->ctx_saving_in_progress)) { - DBprintk(("no IPI, must wait for [%d] to be saved on [%d]\n", task->pid, cpu)); -must_wait_saving: - /* busy wait */ - while (atomic_read(&ctx->ctx_saving_in_progress)); - DBprintk(("done saving for [%d] on [%d]\n", task->pid, cpu)); - return; - } - DBprintk(("calling CPU %d from CPU %d\n", cpu, smp_processor_id())); - - if (cpu == -1) { - printk("refusing to use -1 for [%d]\n", task->pid); - return; - } - - /* will send IPI to other CPU and wait for completion of remote call */ - if ((ret=smp_call_function_single(cpu, pfm_handle_fetch_regs, &arg, 0, 1))) { - printk("perfmon: remote CPU call from %d to %d error %d\n", smp_processor_id(), cpu, ret); - return; - } - /* - * we must wait until saving is over on the other CPU - * This is the case, where we interrupted the saving which started just at the time we sent the - * IPI. - */ - if (arg.retval == 1) goto must_wait_saving; - if (arg.retval == 2) goto must_wait_busy; -} -#endif /* CONFIG_SMP */ - void pfm_load_regs (struct task_struct *task) { @@ -3291,14 +3289,16 @@ pfm_load_regs (struct task_struct *task) unsigned long mask; u64 psr; int i; -#ifdef CONFIG_SMP - int cpu; -#endif owner = PMU_OWNER(); ctx = task->thread.pfm_context; t = &task->thread; + if (ctx == NULL) { + printk("perfmon: pfm_load_regs: null ctx for [%d]\n", task->pid); + return; + } + /* * we restore ALL the debug registers to avoid picking up * stale state. @@ -3324,6 +3324,7 @@ pfm_load_regs (struct task_struct *task) /* * if we were the last user, then nothing to do except restore psr + * this path cannot be used in SMP */ if (owner == task) { if (atomic_read(&ctx->ctx_last_cpu) != smp_processor_id()) @@ -3331,32 +3332,19 @@ pfm_load_regs (struct task_struct *task) atomic_read(&ctx->ctx_last_cpu), task->pid)); psr = ctx->ctx_saved_psr; - __asm__ __volatile__ ("mov psr.l=%0;; srlz.i;;"::"r"(psr): "memory"); + pfm_set_psr_l(psr); return; } - DBprintk(("load_regs: must reload for [%d] owner=%d\n", - task->pid, owner ? owner->pid : -1 )); + /* * someone else is still using the PMU, first push it out and * then we'll be able to install our stuff ! + * + * not possible in SMP */ if (owner) pfm_lazy_save_regs(owner); -#ifdef CONFIG_SMP - /* - * check if context on another CPU (-1 means saved) - * We MUST use the variable, as last_cpu may change behind our - * back. If it changes to -1 (not on a CPU anymore), then in cpu - * we have the last CPU the context was on. We may be sending the - * IPI for nothing, but we have no way of verifying this. - */ - cpu = atomic_read(&ctx->ctx_last_cpu); - if (cpu != -1) { - pfm_fetch_regs(cpu, task, ctx); - } -#endif - /* * To avoid leaking information to the user level when psr.sp=0, * we must reload ALL implemented pmds (even the ones we don't use). @@ -3369,7 +3357,7 @@ pfm_load_regs (struct task_struct *task) */ mask = pfm_sysctl.fastctxsw || ctx->ctx_fl_protected ? ctx->ctx_used_pmds[0] : ctx->ctx_reload_pmds[0]; for (i=0; mask; i++, mask>>=1) { - if (mask & 0x1) ia64_set_pmd(i, t->pmd[i] & pmu_conf.perf_ovfl_val); + if (mask & 0x1) ia64_set_pmd(i, t->pmd[i] & pmu_conf.ovfl_val); } /* @@ -3393,8 +3381,7 @@ pfm_load_regs (struct task_struct *task) * fl_frozen==1 when we are in blocking mode waiting for restart */ if (ctx->ctx_fl_frozen == 0) { - ia64_set_pmc(0, 0); - ia64_srlz_d(); + pfm_unfreeze_pmu(); } atomic_set(&ctx->ctx_last_cpu, smp_processor_id()); @@ -3404,8 +3391,7 @@ pfm_load_regs (struct task_struct *task) * restore the psr we changed in pfm_save_regs() */ psr = ctx->ctx_saved_psr; - __asm__ __volatile__ ("mov psr.l=%0;; srlz.i;;"::"r"(psr): "memory"); - + pfm_set_psr_l(psr); } /* @@ -3419,15 +3405,16 @@ pfm_reset_pmu(struct task_struct *task) int i; if (task != current) { - printk("perfmon: invalid task in ia64_reset_pmu()\n"); + printk("perfmon: invalid task in pfm_reset_pmu()\n"); return; } /* Let's make sure the PMU is frozen */ - ia64_set_pmc(0,1); + pfm_freeze_pmu(); /* * install reset values for PMC. We skip PMC0 (done above) + * XX: good up to 64 PMCS */ for (i=1; (pmu_conf.pmc_desc[i].type & PFM_REG_END) == 0; i++) { if ((pmu_conf.pmc_desc[i].type & PFM_REG_IMPL) == 0) continue; @@ -3444,7 +3431,7 @@ pfm_reset_pmu(struct task_struct *task) /* * clear reset values for PMD. - * XXX: good up to 64 PMDS. Suppose that zero is a valid value. + * XXX: good up to 64 PMDS. */ for (i=0; (pmu_conf.pmd_desc[i].type & PFM_REG_END) == 0; i++) { if ((pmu_conf.pmd_desc[i].type & PFM_REG_IMPL) == 0) continue; @@ -3477,13 +3464,13 @@ pfm_reset_pmu(struct task_struct *task) * * We never directly restore PMC0 so we do not include it in the mask. */ - ctx->ctx_reload_pmcs[0] = pmu_conf.impl_regs[0] & ~0x1; + ctx->ctx_reload_pmcs[0] = pmu_conf.impl_pmcs[0] & ~0x1; /* * We must include all the PMD in this mask to avoid picking * up stale value and leak information, especially directly * at the user level when psr.sp=0 */ - ctx->ctx_reload_pmds[0] = pmu_conf.impl_regs[4]; + ctx->ctx_reload_pmds[0] = pmu_conf.impl_pmds[0]; /* * Keep track of the pmds we want to sample @@ -3493,7 +3480,7 @@ pfm_reset_pmu(struct task_struct *task) * * We ignore the unimplemented pmds specified by the user */ - ctx->ctx_used_pmds[0] = ctx->ctx_smpl_regs[0] & pmu_conf.impl_regs[4]; + ctx->ctx_used_pmds[0] = ctx->ctx_smpl_regs[0]; ctx->ctx_used_pmcs[0] = 1; /* always save/restore PMC[0] */ /* @@ -3547,16 +3534,17 @@ pfm_flush_regs (struct task_struct *task) ia64_set_dcr(ia64_get_dcr() & ~IA64_DCR_PP); /* stop monitoring */ - __asm__ __volatile__ ("rsm psr.pp;;"::: "memory"); + pfm_clear_psr_pp(); ia64_srlz_i(); - __get_cpu_var(pfm_syst_wide) = 0; - __get_cpu_var(pfm_dcr_pp) = 0; + PFM_CPUINFO_CLEAR(PFM_CPUINFO_SYST_WIDE); + PFM_CPUINFO_CLEAR(PFM_CPUINFO_DCR_PP); + PFM_CPUINFO_CLEAR(PFM_CPUINFO_EXCL_IDLE); } else { /* stop monitoring */ - __asm__ __volatile__ ("rum psr.up;;"::: "memory"); + pfm_clear_psr_up(); ia64_srlz_i(); @@ -3589,8 +3577,7 @@ pfm_flush_regs (struct task_struct *task) * This destroys the overflow information. This is required to make sure * next process does not start with monitoring on if not requested */ - ia64_set_pmc(0, 1); - ia64_srlz_d(); + pfm_freeze_pmu(); /* * We don't need to restore psr, because we are on our way out @@ -3606,8 +3593,9 @@ pfm_flush_regs (struct task_struct *task) * */ - if (atomic_read(&ctx->ctx_last_cpu) != smp_processor_id()) - printk("perfmon: [%d] last_cpu=%d\n", task->pid, atomic_read(&ctx->ctx_last_cpu)); + if (atomic_read(&ctx->ctx_last_cpu) != smp_processor_id()) + printk(KERN_DEBUG "perfmon: [%d] last_cpu=%d\n", + task->pid, atomic_read(&ctx->ctx_last_cpu)); /* * we save all the used pmds @@ -3622,10 +3610,14 @@ pfm_flush_regs (struct task_struct *task) val = ia64_get_pmd(i); if (PMD_IS_COUNTING(i)) { - DBprintk(("[%d] pmd[%d] soft_pmd=0x%lx hw_pmd=0x%lx\n", task->pid, i, ctx->ctx_soft_pmds[i].val, val & pmu_conf.perf_ovfl_val)); + DBprintk(("[%d] pmd[%d] soft_pmd=0x%lx hw_pmd=0x%lx\n", + task->pid, + i, + ctx->ctx_soft_pmds[i].val, + val & pmu_conf.ovfl_val)); /* collect latest results */ - ctx->ctx_soft_pmds[i].val += val & pmu_conf.perf_ovfl_val; + ctx->ctx_soft_pmds[i].val += val & pmu_conf.ovfl_val; /* * now everything is in ctx_soft_pmds[] and we need @@ -3638,7 +3630,7 @@ pfm_flush_regs (struct task_struct *task) * take care of overflow inline */ if (pmc0 & (1UL << i)) { - ctx->ctx_soft_pmds[i].val += 1 + pmu_conf.perf_ovfl_val; + ctx->ctx_soft_pmds[i].val += 1 + pmu_conf.ovfl_val; DBprintk(("[%d] pmd[%d] overflowed soft_pmd=0x%lx\n", task->pid, i, ctx->ctx_soft_pmds[i].val)); } @@ -3771,8 +3763,8 @@ pfm_inherit(struct task_struct *task, struct pt_regs *regs) m = nctx->ctx_used_pmds[0] >> PMU_FIRST_COUNTER; for(i = PMU_FIRST_COUNTER ; m ; m>>=1, i++) { if ((m & 0x1) && pmu_conf.pmd_desc[i].type == PFM_REG_COUNTING) { - nctx->ctx_soft_pmds[i].val = nctx->ctx_soft_pmds[i].lval & ~pmu_conf.perf_ovfl_val; - thread->pmd[i] = nctx->ctx_soft_pmds[i].lval & pmu_conf.perf_ovfl_val; + nctx->ctx_soft_pmds[i].val = nctx->ctx_soft_pmds[i].lval & ~pmu_conf.ovfl_val; + thread->pmd[i] = nctx->ctx_soft_pmds[i].lval & pmu_conf.ovfl_val; } else { thread->pmd[i] = 0UL; /* reset to initial state */ } @@ -3811,6 +3803,16 @@ pfm_inherit(struct task_struct *task, struct pt_regs *regs) sema_init(&nctx->ctx_restart_sem, 0); /* reset this semaphore to locked */ + /* + * propagate kernel psr in new context (used for first ctxsw in + */ + nctx->ctx_saved_psr = pfm_get_psr(); + + /* + * propagate kernel psr in new context (used for first ctxsw in + */ + nctx->ctx_saved_psr = pfm_get_psr(); + /* link with new task */ thread->pfm_context = nctx; @@ -3939,30 +3941,14 @@ pfm_context_exit(struct task_struct *task) UNLOCK_CTX(ctx); - LOCK_PFS(); + pfm_unreserve_session(task, ctx->ctx_fl_system, 1UL << ctx->ctx_cpu); if (ctx->ctx_fl_system) { - - pfm_sessions.pfs_sys_session[ctx->ctx_cpu] = NULL; - pfm_sessions.pfs_sys_sessions--; - DBprintk(("freeing syswide session on CPU%ld\n", ctx->ctx_cpu)); - - /* update perfmon debug register usage counter */ - if (ctx->ctx_fl_using_dbreg) { - if (pfm_sessions.pfs_sys_use_dbregs == 0) { - printk("perfmon: invalid release for [%d] sys_use_dbregs=0\n", task->pid); - } else - pfm_sessions.pfs_sys_use_dbregs--; - } - /* * remove any CPU pinning */ set_cpus_allowed(task, ctx->ctx_saved_cpus_allowed); - } else { - pfm_sessions.pfs_task_sessions--; - } - UNLOCK_PFS(); + } pfm_context_free(ctx); /* @@ -3983,15 +3969,14 @@ pfm_cleanup_smpl_buf(struct task_struct *task) pfm_smpl_buffer_desc_t *tmp, *psb = task->thread.pfm_smpl_buf_list; if (psb == NULL) { - printk("perfmon: psb is null in [%d]\n", current->pid); + printk(KERN_DEBUG "perfmon: psb is null in [%d]\n", current->pid); return -1; } /* * Walk through the list and free the sampling buffer and psb */ while (psb) { - DBprintk(("[%d] freeing smpl @%p size %ld\n", - current->pid, psb->psb_hdr, psb->psb_size)); + DBprintk(("[%d] freeing smpl @%p size %ld\n", current->pid, psb->psb_hdr, psb->psb_size)); pfm_rvfree(psb->psb_hdr, psb->psb_size); tmp = psb->psb_next; @@ -4095,16 +4080,16 @@ pfm_cleanup_notifiers(struct task_struct *task) if (ctx && ctx->ctx_notify_task == task) { DBprintk(("trying for notifier [%d] in [%d]\n", task->pid, p->pid)); /* - * the spinlock is required to take care of a race condition with - * the send_sig_info() call. We must make sure that either the - * send_sig_info() completes using a valid task, or the - * notify_task is cleared before the send_sig_info() can pick up a - * stale value. Note that by the time this function is executed - * the 'task' is already detached from the tasklist. The problem - * is that the notifiers have a direct pointer to it. It is okay - * to send a signal to a task in this stage, it simply will have - * no effect. But it is better than sending to a completely - * destroyed task or worse to a new task using the same + * the spinlock is required to take care of a race condition + * with the send_sig_info() call. We must make sure that + * either the send_sig_info() completes using a valid task, + * or the notify_task is cleared before the send_sig_info() + * can pick up a stale value. Note that by the time this + * function is executed the 'task' is already detached from the + * tasklist. The problem is that the notifiers have a direct + * pointer to it. It is okay to send a signal to a task in this + * stage, it simply will have no effect. But it is better than sending + * to a completely destroyed task or worse to a new task using the same * task_struct address. */ LOCK_CTX(ctx); @@ -4123,87 +4108,130 @@ pfm_cleanup_notifiers(struct task_struct *task) } static struct irqaction perfmon_irqaction = { - .handler = perfmon_interrupt, - .flags = SA_INTERRUPT, - .name = "perfmon" + .handler = pfm_interrupt_handler, + .flags = SA_INTERRUPT, + .name = "perfmon" }; +int +pfm_install_alternate_syswide_subsystem(pfm_intr_handler_desc_t *hdl) +{ + int ret; + + /* some sanity checks */ + if (hdl == NULL || hdl->handler == NULL) return -EINVAL; + + /* do the easy test first */ + if (pfm_alternate_intr_handler) return -EBUSY; + + /* reserve our session */ + ret = pfm_reserve_session(NULL, 1, cpu_online_map); + if (ret) return ret; + + if (pfm_alternate_intr_handler) { + printk(KERN_DEBUG "perfmon: install_alternate, intr_handler not NULL " + "after reserve\n"); + return -EINVAL; + } + + pfm_alternate_intr_handler = hdl; + + return 0; +} + +int +pfm_remove_alternate_syswide_subsystem(pfm_intr_handler_desc_t *hdl) +{ + if (hdl == NULL) return -EINVAL; + + /* cannot remove someone else's handler! */ + if (pfm_alternate_intr_handler != hdl) return -EINVAL; + + pfm_alternate_intr_handler = NULL; + + /* + * XXX: assume cpu_online_map has not changed since reservation + */ + pfm_unreserve_session(NULL, 1, cpu_online_map); + + return 0; +} /* * perfmon initialization routine, called from the initcall() table */ int __init -perfmon_init (void) +pfm_init(void) { - pal_perf_mon_info_u_t pm_info; - s64 status; + unsigned int n, n_counters, i; - pmu_conf.pfm_is_disabled = 1; + pmu_conf.disabled = 1; - printk("perfmon: version %u.%u (sampling format v%u.%u) IRQ %u\n", - PFM_VERSION_MAJ, - PFM_VERSION_MIN, - PFM_SMPL_VERSION_MAJ, - PFM_SMPL_VERSION_MIN, - IA64_PERFMON_VECTOR); - - if ((status=ia64_pal_perf_mon_info(pmu_conf.impl_regs, &pm_info)) != 0) { - printk("perfmon: PAL call failed (%ld), perfmon disabled\n", status); - return -1; - } + printk(KERN_INFO "perfmon: version %u.%u IRQ %u\n", PFM_VERSION_MAJ, PFM_VERSION_MIN, + IA64_PERFMON_VECTOR); - pmu_conf.perf_ovfl_val = (1UL << pm_info.pal_perf_mon_info_s.width) - 1; /* - * XXX: use the pfm_*_desc tables instead and simply verify with PAL + * compute the number of implemented PMD/PMC from the + * description tables */ - pmu_conf.max_counters = pm_info.pal_perf_mon_info_s.generic; - pmu_conf.num_pmcs = find_num_pm_regs(pmu_conf.impl_regs); - pmu_conf.num_pmds = find_num_pm_regs(&pmu_conf.impl_regs[4]); - - printk("perfmon: %u bits counters\n", pm_info.pal_perf_mon_info_s.width); + n = 0; + for (i=0; PMC_IS_LAST(i) == 0; i++) { + if (PMC_IS_IMPL(i) == 0) continue; + pmu_conf.impl_pmcs[i>>6] |= 1UL << (i&63); + n++; + } + pmu_conf.num_pmcs = n; + + n = 0; n_counters = 0; + for (i=0; PMD_IS_LAST(i) == 0; i++) { + if (PMD_IS_IMPL(i) == 0) continue; + pmu_conf.impl_pmds[i>>6] |= 1UL << (i&63); + n++; + if (PMD_IS_COUNTING(i)) n_counters++; + } + pmu_conf.num_pmds = n; + pmu_conf.num_counters = n_counters; - printk("perfmon: %lu PMC/PMD pairs, %lu PMCs, %lu PMDs\n", - pmu_conf.max_counters, pmu_conf.num_pmcs, pmu_conf.num_pmds); + printk(KERN_INFO "perfmon: %u PMCs, %u PMDs, %u counters (%lu bits)\n", + pmu_conf.num_pmcs, + pmu_conf.num_pmds, + pmu_conf.num_counters, + ffz(pmu_conf.ovfl_val)); /* sanity check */ if (pmu_conf.num_pmds >= IA64_NUM_PMD_REGS || pmu_conf.num_pmcs >= IA64_NUM_PMC_REGS) { - printk(KERN_ERR "perfmon: not enough pmc/pmd, perfmon is DISABLED\n"); - return -1; /* no need to continue anyway */ - } - - if (ia64_pal_debug_info(&pmu_conf.num_ibrs, &pmu_conf.num_dbrs)) { - printk(KERN_WARNING "perfmon: unable to get number of debug registers\n"); - pmu_conf.num_ibrs = pmu_conf.num_dbrs = 0; + printk(KERN_ERR "perfmon: not enough pmc/pmd, perfmon disabled\n"); + return -1; } - /* PAL reports the number of pairs */ - pmu_conf.num_ibrs <<=1; - pmu_conf.num_dbrs <<=1; - - /* - * setup the register configuration descriptions for the CPU - */ - pmu_conf.pmc_desc = pfm_pmc_desc; - pmu_conf.pmd_desc = pfm_pmd_desc; - - /* we are all set */ - pmu_conf.pfm_is_disabled = 0; /* * for now here for debug purposes */ perfmon_dir = create_proc_read_entry ("perfmon", 0, 0, perfmon_read_entry, NULL); + if (perfmon_dir == NULL) { + printk(KERN_ERR "perfmon: cannot create /proc entry, perfmon disabled\n"); + return -1; + } + /* + * create /proc/perfmon + */ pfm_sysctl_header = register_sysctl_table(pfm_sysctl_root, 0); + /* + * initialize all our spinlocks + */ spin_lock_init(&pfm_sessions.pfs_lock); + /* we are all set */ + pmu_conf.disabled = 0; + return 0; } - -__initcall(perfmon_init); +__initcall(pfm_init); void -perfmon_init_percpu (void) +pfm_init_percpu(void) { int i; @@ -4222,22 +4250,21 @@ perfmon_init_percpu (void) * * On McKinley, this code is ineffective until PMC4 is initialized. */ - for (i=1; (pfm_pmc_desc[i].type & PFM_REG_END) == 0; i++) { - if ((pfm_pmc_desc[i].type & PFM_REG_IMPL) == 0) continue; - ia64_set_pmc(i, pfm_pmc_desc[i].default_value); + for (i=1; PMC_IS_LAST(i) == 0; i++) { + if (PMC_IS_IMPL(i) == 0) continue; + ia64_set_pmc(i, PMC_DFL_VAL(i)); } - for (i=0; (pfm_pmd_desc[i].type & PFM_REG_END) == 0; i++) { - if ((pfm_pmd_desc[i].type & PFM_REG_IMPL) == 0) continue; + + for (i=0; PMD_IS_LAST(i); i++) { + if (PMD_IS_IMPL(i) == 0) continue; ia64_set_pmd(i, 0UL); } - ia64_set_pmc(0,1UL); - ia64_srlz_d(); - + pfm_freeze_pmu(); } #else /* !CONFIG_PERFMON */ -asmlinkage int +asmlinkage long sys_perfmonctl (int pid, int cmd, void *req, int count, long arg5, long arg6, long arg7, long arg8, long stack) { diff --git a/arch/ia64/kernel/perfmon_generic.h b/arch/ia64/kernel/perfmon_generic.h index 6abd23864073..72fb62692318 100644 --- a/arch/ia64/kernel/perfmon_generic.h +++ b/arch/ia64/kernel/perfmon_generic.h @@ -1,10 +1,17 @@ +/* + * This file contains the architected PMU register description tables + * and pmc checker used by perfmon.c. + * + * Copyright (C) 2002 Hewlett Packard Co + * Stephane Eranian <eranian@hpl.hp.com> + */ #define RDEP(x) (1UL<<(x)) -#if defined(CONFIG_ITANIUM) || defined(CONFIG_MCKINLEY) -#error "This file should only be used when CONFIG_ITANIUM and CONFIG_MCKINLEY are not defined" +#if defined(CONFIG_ITANIUM) || defined (CONFIG_MCKINLEY) +#error "This file should not be used when CONFIG_ITANIUM or CONFIG_MCKINLEY is defined" #endif -static pfm_reg_desc_t pmc_desc[PMU_MAX_PMCS]={ +static pfm_reg_desc_t pmc_gen_desc[PMU_MAX_PMCS]={ /* pmc0 */ { PFM_REG_CONTROL , 0, 0x1UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc1 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc2 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, @@ -13,10 +20,10 @@ static pfm_reg_desc_t pmc_desc[PMU_MAX_PMCS]={ /* pmc5 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(5),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc6 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(6),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc7 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(7),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, - { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ + { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ }; -static pfm_reg_desc_t pmd_desc[PMU_MAX_PMDS]={ +static pfm_reg_desc_t pmd_gen_desc[PMU_MAX_PMDS]={ /* pmd0 */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* pmd1 */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* pmd2 */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, @@ -25,5 +32,17 @@ static pfm_reg_desc_t pmd_desc[PMU_MAX_PMDS]={ /* pmd5 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(5),0UL, 0UL, 0UL}}, /* pmd6 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(6),0UL, 0UL, 0UL}}, /* pmd7 */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(7),0UL, 0UL, 0UL}}, - { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ + { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ +}; + +/* + * impl_pmcs, impl_pmds are computed at runtime to minimize errors! + */ +static pmu_config_t pmu_conf={ + .disabled = 1, + .ovfl_val = (1UL << 32) - 1, + .num_ibrs = 8, + .num_dbrs = 8, + .pmd_desc = pfm_gen_pmd_desc, + .pmc_desc = pfm_gen_pmc_desc }; diff --git a/arch/ia64/kernel/perfmon_itanium.h b/arch/ia64/kernel/perfmon_itanium.h index 88928ebe005c..b0f9a8876961 100644 --- a/arch/ia64/kernel/perfmon_itanium.h +++ b/arch/ia64/kernel/perfmon_itanium.h @@ -15,7 +15,7 @@ static int pfm_ita_pmc_check(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs); static int pfm_write_ibr_dbr(int mode, struct task_struct *task, void *arg, int count, struct pt_regs *regs); -static pfm_reg_desc_t pfm_pmc_desc[PMU_MAX_PMCS]={ +static pfm_reg_desc_t pfm_ita_pmc_desc[PMU_MAX_PMCS]={ /* pmc0 */ { PFM_REG_CONTROL , 0, 0x1UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc1 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc2 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, @@ -33,7 +33,7 @@ static pfm_reg_desc_t pfm_pmc_desc[PMU_MAX_PMCS]={ { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ }; -static pfm_reg_desc_t pfm_pmd_desc[PMU_MAX_PMDS]={ +static pfm_reg_desc_t pfm_ita_pmd_desc[PMU_MAX_PMDS]={ /* pmd0 */ { PFM_REG_BUFFER , 0, 0UL, -1UL, NULL, NULL, {RDEP(1),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}}, /* pmd1 */ { PFM_REG_BUFFER , 0, 0UL, -1UL, NULL, NULL, {RDEP(0),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}}, /* pmd2 */ { PFM_REG_BUFFER , 0, 0UL, -1UL, NULL, NULL, {RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}}, @@ -55,6 +55,19 @@ static pfm_reg_desc_t pfm_pmd_desc[PMU_MAX_PMDS]={ { PFM_REG_END , 0, 0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ }; +/* + * impl_pmcs, impl_pmds are computed at runtime to minimize errors! + */ +static pmu_config_t pmu_conf={ + .disabled = 1, + .ovfl_val = (1UL << 32) - 1, + .num_ibrs = 8, + .num_dbrs = 8, + .pmd_desc = pfm_ita_pmd_desc, + .pmc_desc = pfm_ita_pmc_desc +}; + + static int pfm_ita_pmc_check(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs) { diff --git a/arch/ia64/kernel/perfmon_mckinley.h b/arch/ia64/kernel/perfmon_mckinley.h index 27c4f03291cd..c4e8a12b5c52 100644 --- a/arch/ia64/kernel/perfmon_mckinley.h +++ b/arch/ia64/kernel/perfmon_mckinley.h @@ -16,7 +16,7 @@ static int pfm_mck_reserved(struct task_struct *task, unsigned int cnum, unsigne static int pfm_mck_pmc_check(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs); static int pfm_write_ibr_dbr(int mode, struct task_struct *task, void *arg, int count, struct pt_regs *regs); -static pfm_reg_desc_t pfm_pmc_desc[PMU_MAX_PMCS]={ +static pfm_reg_desc_t pfm_mck_pmc_desc[PMU_MAX_PMCS]={ /* pmc0 */ { PFM_REG_CONTROL , 0, 0x1UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc1 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, /* pmc2 */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}}, @@ -36,7 +36,7 @@ static pfm_reg_desc_t pfm_pmc_desc[PMU_MAX_PMCS]={ { PFM_REG_END , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */ }; -static pfm_reg_desc_t pfm_pmd_desc[PMU_MAX_PMDS]={ +static pfm_reg_desc_t pfm_mck_pmd_desc[PMU_MAX_PMDS]={ /* pmd0 */ { PFM_REG_BUFFER , 0, 0x0UL, -1UL, NULL, NULL, {RDEP(1),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}}, /* pmd1 */ { PFM_REG_BUFFER , 0, 0x0UL, -1UL, NULL, NULL, {RDEP(0),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}}, /* pmd2 */ { PFM_REG_BUFFER , 0, 0x0UL, -1UL, NULL, NULL, {RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}}, @@ -59,6 +59,19 @@ static pfm_reg_desc_t pfm_pmd_desc[PMU_MAX_PMDS]={ }; /* + * impl_pmcs, impl_pmds are computed at runtime to minimize errors! + */ +static pmu_config_t pmu_conf={ + .disabled = 1, + .ovfl_val = (1UL << 47) - 1, + .num_ibrs = 8, + .num_dbrs = 8, + .pmd_desc = pfm_mck_pmd_desc, + .pmc_desc = pfm_mck_pmc_desc +}; + + +/* * PMC reserved fields must have their power-up values preserved */ static int @@ -150,12 +163,12 @@ pfm_mck_pmc_check(struct task_struct *task, unsigned int cnum, unsigned long *va * i-side events in L1D and L2 caches */ if (check_case1) { - ret = ((val13 >> 45) & 0xf) == 0 + ret = ((val13 >> 45) & 0xf) == 0 && ((val8 & 0x1) == 0) && ((((val14>>1) & 0x3) == 0x2 || ((val14>>1) & 0x3) == 0x0) ||(((val14>>4) & 0x3) == 0x2 || ((val14>>4) & 0x3) == 0x0)); - if (ret) printk("perfmon: failure check_case1\n"); + if (ret) printk(KERN_DEBUG "perfmon: failure check_case1\n"); } return ret ? -EINVAL : 0; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index f26b3fe2d28e..ed63bbaa9069 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -1,7 +1,7 @@ /* * Architecture-specific setup. * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ #define __KERNEL_SYSCALLS__ /* see <asm/unistd.h> */ @@ -96,7 +96,7 @@ show_regs (struct pt_regs *regs) { unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri; - printk("\nPid: %d, comm: %20s\n", current->pid, current->comm); + printk("\nPid: %d, CPU %d, comm: %20s\n", current->pid, smp_processor_id(), current->comm); printk("psr : %016lx ifs : %016lx ip : [<%016lx>] %s\n", regs->cr_ipsr, regs->cr_ifs, ip, print_tainted()); print_symbol("ip is at %s\n", ip); @@ -144,6 +144,15 @@ show_regs (struct pt_regs *regs) void do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall) { +#ifdef CONFIG_FSYS + if (fsys_mode(current, &scr->pt)) { + /* defer signal-handling etc. until we return to privilege-level 0. */ + if (!ia64_psr(&scr->pt)->lp) + ia64_psr(&scr->pt)->lp = 1; + return; + } +#endif + #ifdef CONFIG_PERFMON if (current->thread.pfm_ovfl_block_reset) pfm_ovfl_block_reset(); @@ -198,6 +207,10 @@ cpu_idle (void *unused) void ia64_save_extra (struct task_struct *task) { +#ifdef CONFIG_PERFMON + unsigned long info; +#endif + if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0) ia64_save_debug_regs(&task->thread.dbr[0]); @@ -205,8 +218,9 @@ ia64_save_extra (struct task_struct *task) if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0) pfm_save_regs(task); - if (__get_cpu_var(pfm_syst_wide)) - pfm_syst_wide_update_task(task, 0); + info = __get_cpu_var(pfm_syst_info); + if (info & PFM_CPUINFO_SYST_WIDE) + pfm_syst_wide_update_task(task, info, 0); #endif #ifdef CONFIG_IA32_SUPPORT @@ -218,6 +232,10 @@ ia64_save_extra (struct task_struct *task) void ia64_load_extra (struct task_struct *task) { +#ifdef CONFIG_PERFMON + unsigned long info; +#endif + if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0) ia64_load_debug_regs(&task->thread.dbr[0]); @@ -225,8 +243,9 @@ ia64_load_extra (struct task_struct *task) if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0) pfm_load_regs(task); - if (__get_cpu_var(pfm_syst_wide)) - pfm_syst_wide_update_task(task, 1); + info = __get_cpu_var(pfm_syst_info); + if (info & PFM_CPUINFO_SYST_WIDE) + pfm_syst_wide_update_task(task, info, 1); #endif #ifdef CONFIG_IA32_SUPPORT diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 880c22a1e961..b5270c92677d 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -833,21 +833,19 @@ access_uarea (struct task_struct *child, unsigned long addr, unsigned long *data return -1; } #ifdef CONFIG_PERFMON - /* - * Check if debug registers are used - * by perfmon. This test must be done once we know that we can - * do the operation, i.e. the arguments are all valid, but before - * we start modifying the state. + /* + * Check if debug registers are used by perfmon. This test must be done + * once we know that we can do the operation, i.e. the arguments are all + * valid, but before we start modifying the state. * - * Perfmon needs to keep a count of how many processes are - * trying to modify the debug registers for system wide monitoring - * sessions. + * Perfmon needs to keep a count of how many processes are trying to + * modify the debug registers for system wide monitoring sessions. * - * We also include read access here, because they may cause - * the PMU-installed debug register state (dbr[], ibr[]) to - * be reset. The two arrays are also used by perfmon, but - * we do not use IA64_THREAD_DBG_VALID. The registers are restored - * by the PMU context switch code. + * We also include read access here, because they may cause the + * PMU-installed debug register state (dbr[], ibr[]) to be reset. The two + * arrays are also used by perfmon, but we do not use + * IA64_THREAD_DBG_VALID. The registers are restored by the PMU context + * switch code. */ if (pfm_use_debug_registers(child)) return -1; #endif diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c index 462f58836dc8..ffd5e361b46e 100644 --- a/arch/ia64/kernel/sal.c +++ b/arch/ia64/kernel/sal.c @@ -1,7 +1,7 @@ /* * System Abstraction Layer (SAL) interface routines. * - * Copyright (C) 1998, 1999, 2001 Hewlett-Packard Co + * Copyright (C) 1998, 1999, 2001, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> @@ -96,17 +96,17 @@ ia64_sal_init (struct ia64_sal_systab *systab) int i; if (!systab) { - printk("Hmm, no SAL System Table.\n"); + printk(KERN_WARNING "Hmm, no SAL System Table.\n"); return; } if (strncmp(systab->signature, "SST_", 4) != 0) - printk("bad signature in system table!"); + printk(KERN_ERR "bad signature in system table!"); /* * revisions are coded in BCD, so %x does the job for us */ - printk("SAL v%x.%02x: oem=%.32s, product=%.32s\n", + printk(KERN_INFO "SAL v%x.%02x: oem=%.32s, product=%.32s\n", systab->sal_rev_major, systab->sal_rev_minor, systab->oem_id, systab->product_id); @@ -121,7 +121,7 @@ ia64_sal_init (struct ia64_sal_systab *systab) switch (*p) { case SAL_DESC_ENTRY_POINT: ep = (struct ia64_sal_desc_entry_point *) p; - printk("SAL: entry: pal_proc=0x%lx, sal_proc=0x%lx\n", + printk(KERN_INFO "SAL: entry: pal_proc=0x%lx, sal_proc=0x%lx\n", ep->pal_proc, ep->sal_proc); ia64_pal_handler_init(__va(ep->pal_proc)); ia64_sal_handler_init(__va(ep->sal_proc), __va(ep->gp)); @@ -139,12 +139,12 @@ ia64_sal_init (struct ia64_sal_systab *systab) switch (ap->mechanism) { case IA64_SAL_AP_EXTERNAL_INT: ap_wakeup_vector = ap->vector; - printk("SAL: AP wakeup using external interrupt " + printk(KERN_INFO "SAL: AP wakeup using external interrupt " "vector 0x%lx\n", ap_wakeup_vector); break; default: - printk("SAL: AP wakeup mechanism unsupported!\n"); + printk(KERN_ERR "SAL: AP wakeup mechanism unsupported!\n"); break; } break; @@ -154,7 +154,7 @@ ia64_sal_init (struct ia64_sal_systab *systab) { struct ia64_sal_desc_platform_feature *pf = (void *) p; sal_platform_features = pf->feature_mask; - printk("SAL: Platform features "); + printk(KERN_INFO "SAL: Platform features "); if (pf->feature_mask & IA64_SAL_PLATFORM_FEATURE_BUS_LOCK) printk("BusLock "); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 65b0489b2d47..c8a439ca44f7 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1,7 +1,7 @@ /* * Architecture-specific setup. * - * Copyright (C) 1998-2001 Hewlett-Packard Co + * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * Copyright (C) 2000, Rohit Seth <rohit.seth@intel.com> @@ -171,7 +171,7 @@ filter_rsvd_memory (unsigned long start, unsigned long end, void *arg) #if IGNORE_PFN0 if (start == PAGE_OFFSET) { - printk("warning: skipping physical page 0\n"); + printk(KERN_WARNING "warning: skipping physical page 0\n"); start += PAGE_SIZE; if (start >= end) return 0; } @@ -341,7 +341,7 @@ find_memory (void) initrd_start = (unsigned long)__va(ia64_boot_param->initrd_start); initrd_end = initrd_start+ia64_boot_param->initrd_size; - printk("Initial ramdisk at: 0x%lx (%lu bytes)\n", + printk(KERN_INFO "Initial ramdisk at: 0x%lx (%lu bytes)\n", initrd_start, ia64_boot_param->initrd_size); } #endif @@ -409,8 +409,9 @@ setup_arch (char **cmdline_p) ia64_set_kr(IA64_KR_IO_BASE, phys_iobase); else { phys_iobase = ia64_get_kr(IA64_KR_IO_BASE); - printk("No I/O port range found in EFI memory map, falling back to AR.KR0\n"); - printk("I/O port base = 0x%lx\n", phys_iobase); + printk(KERN_INFO "No I/O port range found in EFI memory map, falling back " + "to AR.KR0\n"); + printk(KERN_INFO "I/O port base = 0x%lx\n", phys_iobase); } ia64_iobase = (unsigned long) ioremap(phys_iobase, 0); @@ -615,7 +616,7 @@ identify_cpu (struct cpuinfo_ia64 *c) impl_va_msb = vm2.pal_vm_info_2_s.impl_va_msb; phys_addr_size = vm1.pal_vm_info_1_s.phys_add_size; } - printk("CPU %d: %lu virtual and %lu physical address bits\n", + printk(KERN_INFO "CPU %d: %lu virtual and %lu physical address bits\n", smp_processor_id(), impl_va_msb + 1, phys_addr_size); c->unimpl_va_mask = ~((7L<<61) | ((1L << (impl_va_msb + 1)) - 1)); c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1)); @@ -738,7 +739,7 @@ cpu_init (void) if (ia64_pal_vm_summary(NULL, &vmi) == 0) max_ctx = (1U << (vmi.pal_vm_info_2_s.rid_size - 3)) - 1; else { - printk("cpu_init: PAL VM summary failed, assuming 18 RID bits\n"); + printk(KERN_WARNING "cpu_init: PAL VM summary failed, assuming 18 RID bits\n"); max_ctx = (1U << 15) - 1; /* use architected minimum */ } while (max_ctx < ia64_ctx.max_ctx) { @@ -748,10 +749,39 @@ cpu_init (void) } if (ia64_pal_rse_info(&num_phys_stacked, 0) != 0) { - printk ("cpu_init: PAL RSE info failed, assuming 96 physical stacked regs\n"); + printk(KERN_WARNING "cpu_init: PAL RSE info failed; assuming 96 physical " + "stacked regs\n"); num_phys_stacked = 96; } /* size of physical stacked register partition plus 8 bytes: */ __get_cpu_var(ia64_phys_stacked_size_p8) = num_phys_stacked*8 + 8; platform_cpu_init(); } + +void +check_bugs (void) +{ + extern int __start___mckinley_e9_bundles[]; + extern int __end___mckinley_e9_bundles[]; + u64 *bundle; + int *wp; + + if (local_cpu_data->family == 0x1f && local_cpu_data->model == 0) + printk(KERN_INFO "check_bugs: leaving McKinley Errata 9 workaround enabled\n"); + else { + printk(KERN_INFO "check_bugs: McKinley Errata 9 workaround not needed; " + "disabling it\n"); + for (wp = __start___mckinley_e9_bundles; wp < __end___mckinley_e9_bundles; ++wp) { + bundle = (u64 *) ((char *) wp + *wp); + /* install a bundle of NOPs: */ + bundle[0] = 0x0000000100000000; + bundle[1] = 0x0004000000000200; + ia64_fc(bundle); + } + ia64_insn_group_barrier(); + ia64_sync_i(); + ia64_insn_group_barrier(); + ia64_srlz_i(); + ia64_insn_group_barrier(); + } +} diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 6223825e0beb..15d820d88c64 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -1,7 +1,7 @@ /* * SMP boot-related support * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * 01/05/16 Rohit Seth <rohit.seth@intel.com> Moved SMP booting functions from smp.c to here. @@ -204,7 +204,7 @@ ia64_sync_itc (unsigned int master) go[MASTER] = 1; if (smp_call_function_single(master, sync_master, NULL, 1, 0) < 0) { - printk("sync_itc: failed to get attention of CPU %u!\n", master); + printk(KERN_ERR "sync_itc: failed to get attention of CPU %u!\n", master); return; } @@ -244,8 +244,8 @@ ia64_sync_itc (unsigned int master) t[i].rt, t[i].master, t[i].diff, t[i].lat); #endif - printk("CPU %d: synchronized ITC with CPU %u (last diff %ld cycles, maxerr %lu cycles)\n", - smp_processor_id(), master, delta, rt); + printk(KERN_INFO "CPU %d: synchronized ITC with CPU %u (last diff %ld cycles, " + "maxerr %lu cycles)\n", smp_processor_id(), master, delta, rt); } /* @@ -265,14 +265,15 @@ smp_callin (void) extern void ia64_init_itm(void); #ifdef CONFIG_PERFMON - extern void perfmon_init_percpu(void); + extern void pfm_init_percpu(void); #endif cpuid = smp_processor_id(); phys_id = hard_smp_processor_id(); if (test_and_set_bit(cpuid, &cpu_online_map)) { - printk("huh, phys CPU#0x%x, CPU#0x%x already present??\n", phys_id, cpuid); + printk(KERN_ERR "huh, phys CPU#0x%x, CPU#0x%x already present??\n", + phys_id, cpuid); BUG(); } @@ -300,7 +301,7 @@ smp_callin (void) #endif #ifdef CONFIG_PERFMON - perfmon_init_percpu(); + pfm_init_percpu(); #endif local_irq_enable(); @@ -380,9 +381,7 @@ do_boot_cpu (int sapicid, int cpu) if (test_bit(cpu, &cpu_callin_map)) { /* number CPUs logically, starting from 1 (BSP is 0) */ - printk("CPU%d: ", cpu); - /*print_cpu_info(&cpu_data[cpu]); */ - printk("CPU has booted.\n"); + printk(KERN_INFO "CPU%d: CPU has booted.\n", cpu); } else { printk(KERN_ERR "Processor 0x%x/0x%x is stuck.\n", cpu, sapicid); ia64_cpu_to_sapicid[cpu] = -1; @@ -399,7 +398,7 @@ smp_tune_scheduling (void) { cache_decay_ticks = 10; /* XXX base this on PAL info and cache-bandwidth estimate */ - printk("task migration cache decay timeout: %ld msecs.\n", + printk(KERN_INFO "task migration cache decay timeout: %ld msecs.\n", (cache_decay_ticks + 1) * 1000 / HZ); } @@ -491,7 +490,7 @@ smp_prepare_cpus (unsigned int max_cpus) local_cpu_data->loops_per_jiffy = loops_per_jiffy; ia64_cpu_to_sapicid[0] = boot_cpu_id; - printk("Boot processor id 0x%x/0x%x\n", 0, boot_cpu_id); + printk(KERN_INFO "Boot processor id 0x%x/0x%x\n", 0, boot_cpu_id); current_thread_info()->cpu = 0; smp_tune_scheduling(); @@ -526,7 +525,7 @@ smp_cpus_done (unsigned int dummy) if (cpu_online(cpu)) bogosum += cpu_data(cpu)->loops_per_jiffy; - printk(KERN_INFO"Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + printk(KERN_INFO "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100); } @@ -571,5 +570,6 @@ init_smp_config(void) sal_ret = ia64_sal_set_vectors(SAL_VECTOR_OS_BOOT_RENDEZ, __pa(ap_startup->fp), __pa(ap_startup->gp), 0, 0, 0, 0); if (sal_ret < 0) - printk("SMP: Can't set SAL AP Boot Rendezvous: %s\n", ia64_sal_strerror(sal_ret)); + printk(KERN_ERR "SMP: Can't set SAL AP Boot Rendezvous: %s\n", + ia64_sal_strerror(sal_ret)); } diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index 369fa11df115..66a2e57e50f3 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -16,11 +16,11 @@ #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/highuid.h> +#include <linux/hugetlb.h> #include <asm/shmparam.h> #include <asm/uaccess.h> - unsigned long arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -31,6 +31,20 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len if (len > RGN_MAP_LIMIT) return -ENOMEM; + +#ifdef CONFIG_HUGETLB_PAGE +#define COLOR_HALIGN(addr) ((addr + HPAGE_SIZE - 1) & ~(HPAGE_SIZE - 1)) +#define TASK_HPAGE_BASE ((REGION_HPAGE << REGION_SHIFT) | HPAGE_SIZE) + if (filp && is_file_hugepages(filp)) { + if ((REGION_NUMBER(addr) != REGION_HPAGE) || (addr & (HPAGE_SIZE -1))) + addr = TASK_HPAGE_BASE; + addr = COLOR_HALIGN(addr); + } + else { + if (REGION_NUMBER(addr) == REGION_HPAGE) + addr = 0; + } +#endif if (!addr) addr = TASK_UNMAPPED_BASE; diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 101e53cef7de..b85fe8b701b2 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -1,7 +1,7 @@ /* * linux/arch/ia64/kernel/time.c * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * Stephane Eranian <eranian@hpl.hp.com> * David Mosberger <davidm@hpl.hp.com> * Copyright (C) 1999 Don Dugger <don.dugger@intel.com> @@ -75,10 +75,8 @@ gettimeoffset (void) now = ia64_get_itc(); if ((long) (now - last_tick) < 0) { -# if 1 - printk("CPU %d: now < last_tick (now=0x%lx,last_tick=0x%lx)!\n", + printk(KERN_ERR "CPU %d: now < last_tick (now=0x%lx,last_tick=0x%lx)!\n", smp_processor_id(), now, last_tick); -# endif return last_time_offset; } elapsed_cycles = now - last_tick; @@ -157,7 +155,7 @@ timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) new_itm = local_cpu_data->itm_next; if (!time_after(ia64_get_itc(), new_itm)) - printk("Oops: timer tick before it's due (itc=%lx,itm=%lx)\n", + printk(KERN_ERR "Oops: timer tick before it's due (itc=%lx,itm=%lx)\n", ia64_get_itc(), new_itm); while (1) { @@ -246,21 +244,22 @@ ia64_init_itm (void) */ status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM, &platform_base_freq, &drift); if (status != 0) { - printk("SAL_FREQ_BASE_PLATFORM failed: %s\n", ia64_sal_strerror(status)); + printk(KERN_ERR "SAL_FREQ_BASE_PLATFORM failed: %s\n", ia64_sal_strerror(status)); } else { status = ia64_pal_freq_ratios(&proc_ratio, 0, &itc_ratio); if (status != 0) - printk("PAL_FREQ_RATIOS failed with status=%ld\n", status); + printk(KERN_ERR "PAL_FREQ_RATIOS failed with status=%ld\n", status); } if (status != 0) { /* invent "random" values */ - printk("SAL/PAL failed to obtain frequency info---inventing reasonably values\n"); + printk(KERN_ERR + "SAL/PAL failed to obtain frequency info---inventing reasonably values\n"); platform_base_freq = 100000000; itc_ratio.num = 3; itc_ratio.den = 1; } if (platform_base_freq < 40000000) { - printk("Platform base frequency %lu bogus---resetting to 75MHz!\n", + printk(KERN_ERR "Platform base frequency %lu bogus---resetting to 75MHz!\n", platform_base_freq); platform_base_freq = 75000000; } @@ -271,8 +270,8 @@ ia64_init_itm (void) itc_freq = (platform_base_freq*itc_ratio.num)/itc_ratio.den; local_cpu_data->itm_delta = (itc_freq + HZ/2) / HZ; - printk("CPU %d: base freq=%lu.%03luMHz, ITC ratio=%lu/%lu, ITC freq=%lu.%03luMHz\n", - smp_processor_id(), + printk(KERN_INFO "CPU %d: base freq=%lu.%03luMHz, ITC ratio=%lu/%lu, " + "ITC freq=%lu.%03luMHz\n", smp_processor_id(), platform_base_freq / 1000000, (platform_base_freq / 1000) % 1000, itc_ratio.num, itc_ratio.den, itc_freq / 1000000, (itc_freq / 1000) % 1000); diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index f6612529150c..bb8e11fc0a13 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -1,7 +1,7 @@ /* * Architecture-specific trap handling. * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * 05/12/00 grao <goutham.rao@intel.com> : added isr in siginfo for SIGFPE @@ -57,7 +57,8 @@ trap_init (void) major = fpswa_interface->revision >> 16; minor = fpswa_interface->revision & 0xffff; } - printk("fpswa interface at %lx (rev %d.%d)\n", ia64_boot_param->fpswa, major, minor); + printk(KERN_INFO "fpswa interface at %lx (rev %d.%d)\n", + ia64_boot_param->fpswa, major, minor); } /* @@ -142,7 +143,7 @@ ia64_bad_break (unsigned long break_num, struct pt_regs *regs) switch (break_num) { case 0: /* unknown error (used by GCC for __builtin_abort()) */ - die_if_kernel("bad break", regs, break_num); + die_if_kernel("bugcheck!", regs, break_num); sig = SIGILL; code = ILL_ILLOPC; break; @@ -222,7 +223,7 @@ ia64_ni_syscall (unsigned long arg0, unsigned long arg1, unsigned long arg2, uns { struct pt_regs *regs = (struct pt_regs *) &stack; - printk("%s(%d): <sc%ld(%lx,%lx,%lx,%lx)>\n", current->comm, current->pid, + printk(KERN_DEBUG "%s(%d): <sc%ld(%lx,%lx,%lx,%lx)>\n", current->comm, current->pid, regs->r15, arg0, arg1, arg2, arg3); return -ENOSYS; } @@ -346,7 +347,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr) /* emulation was successful */ ia64_increment_ip(regs); } else if (exception == -1) { - printk("handle_fpu_swa: fp_emulate() returned -1\n"); + printk(KERN_ERR "handle_fpu_swa: fp_emulate() returned -1\n"); return -1; } else { /* is next instruction a trap? */ @@ -369,7 +370,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr) } } else { if (exception == -1) { - printk("handle_fpu_swa: fp_emulate() returned -1\n"); + printk(KERN_ERR "handle_fpu_swa: fp_emulate() returned -1\n"); return -1; } else if (exception != 0) { /* raise exception */ @@ -467,7 +468,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, ? " (RSE access)" : " (data access)") : ""); if (code == 8) { # ifdef CONFIG_IA64_PRINT_HAZARDS - printk("%016lx:possible hazard, pr = %016lx\n", regs->cr_iip, regs->pr); + printk("%s[%d]: possible hazard @ ip=%016lx (pr = %016lx)\n", + current->comm, current->pid, regs->cr_iip + ia64_psr(regs)->ri, + regs->pr); # endif return; } @@ -524,6 +527,25 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, case 29: /* Debug */ case 35: /* Taken Branch Trap */ case 36: /* Single Step Trap */ +#ifdef CONFIG_FSYS + if (fsys_mode(current, regs)) { + extern char syscall_via_break[], __start_gate_section[]; + /* + * Got a trap in fsys-mode: Taken Branch Trap and Single Step trap + * need special handling; Debug trap is not supposed to happen. + */ + if (unlikely(vector == 29)) { + die("Got debug trap in fsys-mode---not supposed to happen!", + regs, 0); + return; + } + /* re-do the system call via break 0x100000: */ + regs->cr_iip = GATE_ADDR + (syscall_via_break - __start_gate_section); + ia64_psr(regs)->ri = 0; + ia64_psr(regs)->cpl = 3; + return; + } +#endif switch (vector) { case 29: siginfo.si_code = TRAP_HWBKPT; @@ -563,19 +585,31 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, } return; - case 34: /* Unimplemented Instruction Address Trap */ - if (user_mode(regs)) { - siginfo.si_signo = SIGILL; - siginfo.si_code = ILL_BADIADDR; - siginfo.si_errno = 0; - siginfo.si_flags = 0; - siginfo.si_isr = 0; - siginfo.si_imm = 0; - siginfo.si_addr = (void *) (regs->cr_iip + ia64_psr(regs)->ri); - force_sig_info(SIGILL, &siginfo, current); + case 34: + if (isr & 0x2) { + /* Lower-Privilege Transfer Trap */ + /* + * Just clear PSR.lp and then return immediately: all the + * interesting work (e.g., signal delivery is done in the kernel + * exit path). + */ + ia64_psr(regs)->lp = 0; return; + } else { + /* Unimplemented Instr. Address Trap */ + if (user_mode(regs)) { + siginfo.si_signo = SIGILL; + siginfo.si_code = ILL_BADIADDR; + siginfo.si_errno = 0; + siginfo.si_flags = 0; + siginfo.si_isr = 0; + siginfo.si_imm = 0; + siginfo.si_addr = (void *) (regs->cr_iip + ia64_psr(regs)->ri); + force_sig_info(SIGILL, &siginfo, current); + return; + } + sprintf(buf, "Unimplemented Instruction Address fault"); } - sprintf(buf, "Unimplemented Instruction Address fault"); break; case 45: @@ -583,8 +617,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, if (ia32_exception(regs, isr) == 0) return; #endif - printk("Unexpected IA-32 exception (Trap 45)\n"); - printk(" iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx\n", regs->cr_iip, ifa, isr); + printk(KERN_ERR "Unexpected IA-32 exception (Trap 45)\n"); + printk(KERN_ERR " iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx\n", + regs->cr_iip, ifa, isr); force_sig(SIGSEGV, current); break; @@ -593,8 +628,8 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, if (ia32_intercept(regs, isr) == 0) return; #endif - printk("Unexpected IA-32 intercept trap (Trap 46)\n"); - printk(" iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx, iim - 0x%lx\n", + printk(KERN_ERR "Unexpected IA-32 intercept trap (Trap 46)\n"); + printk(KERN_ERR " iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx, iim - 0x%lx\n", regs->cr_iip, ifa, isr, iim); force_sig(SIGSEGV, current); return; diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index 55719fce87e9..cb366a3bd3a7 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -331,12 +331,8 @@ set_rse_reg (struct pt_regs *regs, unsigned long r1, unsigned long val, int nat) return; } - /* - * Avoid using user_mode() here: with "epc", we cannot use the privilege level to - * infer whether the interrupt task was running on the kernel backing store. - */ - if (regs->r12 >= TASK_SIZE) { - DPRINT("ignoring kernel write to r%lu; register isn't on the RBS!", r1); + if (!user_stack(current, regs)) { + DPRINT("ignoring kernel write to r%lu; register isn't on the kernel RBS!", r1); return; } @@ -406,11 +402,7 @@ get_rse_reg (struct pt_regs *regs, unsigned long r1, unsigned long *val, int *na return; } - /* - * Avoid using user_mode() here: with "epc", we cannot use the privilege level to - * infer whether the interrupt task was running on the kernel backing store. - */ - if (regs->r12 >= TASK_SIZE) { + if (!user_stack(current, regs)) { DPRINT("ignoring kernel read of r%lu; register isn't on the RBS!", r1); goto fail; } @@ -1302,12 +1294,12 @@ within_logging_rate_limit (void) void ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) { - struct exception_fixup fix = { 0 }; struct ia64_psr *ipsr = ia64_psr(regs); mm_segment_t old_fs = get_fs(); unsigned long bundle[2]; unsigned long opcode; struct siginfo si; + const struct exception_table_entry *eh = NULL; union { unsigned long l; load_store_t insn; @@ -1325,10 +1317,9 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) * user-level unaligned accesses. Otherwise, a clever program could trick this * handler into reading an arbitrary kernel addresses... */ - if (!user_mode(regs)) { - fix = SEARCH_EXCEPTION_TABLE(regs); - } - if (user_mode(regs) || fix.cont) { + if (!user_mode(regs)) + eh = SEARCH_EXCEPTION_TABLE(regs); + if (user_mode(regs) || eh) { if ((current->thread.flags & IA64_THREAD_UAC_SIGBUS) != 0) goto force_sigbus; @@ -1494,8 +1485,8 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) failure: /* something went wrong... */ if (!user_mode(regs)) { - if (fix.cont) { - handle_exception(regs, fix); + if (eh) { + handle_exception(regs, eh); goto done; } die_if_kernel("error during unaligned kernel access\n", regs, ret); diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index 5d5f584d4562..e54bf65985a6 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 1999-2002 Hewlett-Packard Co + * Copyright (C) 1999-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ /* @@ -532,7 +532,7 @@ push (struct unw_state_record *sr) rs = alloc_reg_state(); if (!rs) { - printk("unwind: cannot stack reg state!\n"); + printk(KERN_ERR "unwind: cannot stack reg state!\n"); return; } memcpy(rs, &sr->curr, sizeof(*rs)); @@ -545,7 +545,7 @@ pop (struct unw_state_record *sr) struct unw_reg_state *rs = sr->curr.next; if (!rs) { - printk("unwind: stack underflow!\n"); + printk(KERN_ERR "unwind: stack underflow!\n"); return; } memcpy(&sr->curr, rs, sizeof(*rs)); @@ -561,7 +561,7 @@ dup_state_stack (struct unw_reg_state *rs) while (rs) { copy = alloc_reg_state(); if (!copy) { - printk ("unwind.dup_state_stack: out of memory\n"); + printk(KERN_ERR "unwind.dup_state_stack: out of memory\n"); return NULL; } memcpy(copy, rs, sizeof(*copy)); @@ -951,7 +951,7 @@ desc_copy_state (unw_word label, struct unw_state_record *sr) return; } } - printk("unwind: failed to find state labeled 0x%lx\n", label); + printk(KERN_ERR "unwind: failed to find state labeled 0x%lx\n", label); } static inline void @@ -961,7 +961,7 @@ desc_label_state (unw_word label, struct unw_state_record *sr) ls = alloc_labeled_state(); if (!ls) { - printk("unwind.desc_label_state(): out of memory\n"); + printk(KERN_ERR "unwind.desc_label_state(): out of memory\n"); return; } ls->label = label; @@ -1055,7 +1055,8 @@ desc_spill_sprel_p (unsigned char qp, unw_word t, unsigned char abreg, unw_word r->val = 4*spoff; } -#define UNW_DEC_BAD_CODE(code) printk("unwind: unknown code 0x%02x\n", code); +#define UNW_DEC_BAD_CODE(code) printk(KERN_ERR "unwind: unknown code 0x%02x\n", \ + code); /* * region headers: @@ -1997,23 +1998,25 @@ unw_create_gate_table (void) { extern char __start_gate_section[], __stop_gate_section[]; unsigned long *lp, start, end, segbase = unw.kernel_table.segment_base; - const struct unw_table_entry *entry, *first; + const struct unw_table_entry *entry, *first, *unw_table_end; + extern int ia64_unw_end; size_t info_size, size; char *info; start = (unsigned long) __start_gate_section - segbase; end = (unsigned long) __stop_gate_section - segbase; + unw_table_end = (struct unw_table_entry *) &ia64_unw_end; size = 0; first = lookup(&unw.kernel_table, start); - for (entry = first; entry->start_offset < end; ++entry) + for (entry = first; entry < unw_table_end && entry->start_offset < end; ++entry) size += 3*8 + 8 + 8*UNW_LENGTH(*(u64 *) (segbase + entry->info_offset)); size += 8; /* reserve space for "end of table" marker */ unw.gate_table = alloc_bootmem(size); if (!unw.gate_table) { unw.gate_table_size = 0; - printk("unwind: unable to create unwind data for gate page!\n"); + printk(KERN_ERR "unwind: unable to create unwind data for gate page!\n"); return; } unw.gate_table_size = size; @@ -2021,7 +2024,7 @@ unw_create_gate_table (void) lp = unw.gate_table; info = (char *) unw.gate_table + size; - for (entry = first; entry->start_offset < end; ++entry, lp += 3) { + for (entry = first; entry < unw_table_end && entry->start_offset < end; ++entry, lp += 3) { info_size = 8 + 8*UNW_LENGTH(*(u64 *) (segbase + entry->info_offset)); info -= info_size; memcpy(info, (char *) segbase + entry->info_offset, info_size); diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S index 5a1450973bb0..2e7559eeb304 100644 --- a/arch/ia64/lib/memcpy_mck.S +++ b/arch/ia64/lib/memcpy_mck.S @@ -159,7 +159,7 @@ GLOBAL_ENTRY(__copy_user) mov ar.ec=2 (p10) br.dpnt.few .aligned_src_tail ;; - .align 32 +// .align 32 1: EX(.ex_handler, (p16) ld8 r34=[src0],16) EK(.ex_handler, (p16) ld8 r38=[src1],16) @@ -316,7 +316,7 @@ EK(.ex_handler, (p[D]) st8 [dst1] = t15, 4*8) (p7) mov ar.lc = r21 (p8) mov ar.lc = r0 ;; - .align 32 +// .align 32 1: lfetch.fault [src_pre_mem], 128 lfetch.fault.excl [dst_pre_mem], 128 br.cloop.dptk.few 1b @@ -522,7 +522,7 @@ EK(.ex_handler, (p17) st8 [dst1]=r39,8); \ shrp r21=r22,r38,shift; /* speculative work */ \ br.sptk.few .unaligned_src_tail /* branch out of jump table */ \ ;; - .align 32 +// .align 32 .jump_table: COPYU(8) // unaligned cases .jmp1: diff --git a/arch/ia64/lib/memset.S b/arch/ia64/lib/memset.S index 655ff4cb179d..350663bcb9ca 100644 --- a/arch/ia64/lib/memset.S +++ b/arch/ia64/lib/memset.S @@ -125,7 +125,7 @@ GLOBAL_ENTRY(memset) (p_zr) br.cond.dptk.many .l1b // Jump to use stf.spill ;; } - .align 32 // -------------------------- // L1A: store ahead into cache lines; fill later +// .align 32 // -------------------------- // L1A: store ahead into cache lines; fill later { .mmi and tmp = -(LINE_SIZE), cnt // compute end of range mov ptr9 = ptr1 // used for prefetching @@ -194,7 +194,7 @@ GLOBAL_ENTRY(memset) br.cond.dpnt.many .move_bytes_from_alignment // Branch no. 3 ;; } - .align 32 +// .align 32 .l1b: // ------------------------------------ // L1B: store ahead into cache lines; fill later { .mmi and tmp = -(LINE_SIZE), cnt // compute end of range @@ -261,7 +261,7 @@ GLOBAL_ENTRY(memset) and cnt = 0x1f, cnt // compute the remaining cnt mov.i ar.lc = loopcnt ;; } - .align 32 +// .align 32 .l2: // ------------------------------------ // L2A: store 32B in 2 cycles { .mmb stf8 [ptr1] = fvalue, 8 diff --git a/arch/ia64/lib/swiotlb.c b/arch/ia64/lib/swiotlb.c index d06543fafbf8..f390da81d018 100644 --- a/arch/ia64/lib/swiotlb.c +++ b/arch/ia64/lib/swiotlb.c @@ -113,7 +113,7 @@ swiotlb_init (void) io_tlb_index = 0; io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *)); - printk("Placing software IO TLB between 0x%p - 0x%p\n", + printk(KERN_INFO "Placing software IO TLB between 0x%p - 0x%p\n", (void *) io_tlb_start, (void *) io_tlb_end); } diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 3e2e0b879ad8..f855cb69db21 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -215,7 +215,7 @@ discontig_mem_init(void) int node; if (numnodes == 0) { - printk("node info missing!\n"); + printk(KERN_ERR "node info missing!\n"); numnodes = 1; } diff --git a/arch/ia64/mm/extable.c b/arch/ia64/mm/extable.c index 3d11a8ad6451..898824e69a1a 100644 --- a/arch/ia64/mm/extable.c +++ b/arch/ia64/mm/extable.c @@ -10,20 +10,19 @@ #include <asm/uaccess.h> #include <asm/module.h> -extern const struct exception_table_entry __start___ex_table[]; -extern const struct exception_table_entry __stop___ex_table[]; - -static inline const struct exception_table_entry * -search_one_table (const struct exception_table_entry *first, - const struct exception_table_entry *last, - unsigned long ip, unsigned long gp) +const struct exception_table_entry * +search_extable (const struct exception_table_entry *first, + const struct exception_table_entry *last, + unsigned long ip) { - while (first <= last) { - const struct exception_table_entry *mid; - long diff; + const struct exception_table_entry *mid; + unsigned long mid_ip; + long diff; + while (first <= last) { mid = &first[(last - first)/2]; - diff = (mid->addr + gp) - ip; + mid_ip = (u64) &mid->addr + mid->addr; + diff = mid_ip - ip; if (diff == 0) return mid; else if (diff < 0) @@ -34,50 +33,14 @@ search_one_table (const struct exception_table_entry *first, return 0; } -#ifndef CONFIG_MODULES -register unsigned long main_gp __asm__("gp"); -#endif - -struct exception_fixup -search_exception_table (unsigned long addr) -{ - const struct exception_table_entry *entry; - struct exception_fixup fix = { 0 }; - -#ifndef CONFIG_MODULES - /* There is only the kernel to search. */ - entry = search_one_table(__start___ex_table, __stop___ex_table - 1, addr, main_gp); - if (entry) - fix.cont = entry->cont + main_gp; - return fix; -#else - struct archdata *archdata; - struct module *mp; - - /* The kernel is the last "module" -- no need to treat it special. */ - for (mp = module_list; mp; mp = mp->next) { - if (!mp->ex_table_start) - continue; - archdata = (struct archdata *) mp->archdata_start; - if (!archdata) - continue; - entry = search_one_table(mp->ex_table_start, mp->ex_table_end - 1, - addr, (unsigned long) archdata->gp); - if (entry) { - fix.cont = entry->cont + (unsigned long) archdata->gp; - return fix; - } - } -#endif - return fix; -} - void -handle_exception (struct pt_regs *regs, struct exception_fixup fix) +handle_exception (struct pt_regs *regs, const struct exception_table_entry *e) { + long fix = (u64) &e->cont + e->cont; + regs->r8 = -EFAULT; - if (fix.cont & 4) + if (fix & 4) regs->r9 = 0; - regs->cr_iip = (long) fix.cont & ~0xf; - ia64_psr(regs)->ri = fix.cont & 0x3; /* set continuation slot number */ + regs->cr_iip = fix & ~0xf; + ia64_psr(regs)->ri = fix & 0x3; /* set continuation slot number */ } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 45b20d7eb71c..c1e982f74e32 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -196,7 +196,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re yield(); goto survive; } - printk("VM: killing process %s\n", current->comm); + printk(KERN_CRIT "VM: killing process %s\n", current->comm); if (user_mode(regs)) do_exit(SIGKILL); goto no_context; diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 37bcf76e2b63..a08a64c1d39d 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -12,70 +12,41 @@ #include <linux/pagemap.h> #include <linux/smp_lock.h> #include <linux/slab.h> - #include <asm/mman.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -struct list_head htlbpage_freelist; -spinlock_t htlbpage_lock = SPIN_LOCK_UNLOCKED; -extern long htlbpagemem; +#include <linux/sysctl.h> + +static long htlbpagemem; +int htlbpage_max; +static long htlbzone_pages; -static void zap_hugetlb_resources (struct vm_area_struct *); +static LIST_HEAD(htlbpage_freelist); +static spinlock_t htlbpage_lock = SPIN_LOCK_UNLOCKED; -static struct page * -alloc_hugetlb_page (void) +static struct page *alloc_hugetlb_page(void) { - struct list_head *curr, *head; + int i; struct page *page; spin_lock(&htlbpage_lock); - - head = &htlbpage_freelist; - curr = head->next; - - if (curr == head) { + if (list_empty(&htlbpage_freelist)) { spin_unlock(&htlbpage_lock); return NULL; } - page = list_entry(curr, struct page, list); - list_del(curr); + + page = list_entry(htlbpage_freelist.next, struct page, list); + list_del(&page->list); htlbpagemem--; spin_unlock(&htlbpage_lock); set_page_count(page, 1); - memset(page_address(page), 0, HPAGE_SIZE); + for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i) + clear_highpage(&page[i]); return page; } -static void -free_hugetlb_page (struct page *page) -{ - spin_lock(&htlbpage_lock); - if ((page->mapping != NULL) && (page_count(page) == 2)) { - struct inode *inode = page->mapping->host; - int i; - - ClearPageDirty(page); - remove_from_page_cache(page); - set_page_count(page, 1); - if ((inode->i_size -= HPAGE_SIZE) == 0) { - for (i = 0; i < MAX_ID; i++) - if (htlbpagek[i].key == inode->i_ino) { - htlbpagek[i].key = 0; - htlbpagek[i].in = NULL; - break; - } - kfree(inode); - } - } - if (put_page_testzero(page)) { - list_add(&page->list, &htlbpage_freelist); - htlbpagemem++; - } - spin_unlock(&htlbpage_lock); -} - static pte_t * huge_pte_alloc (struct mm_struct *mm, unsigned long addr) { @@ -125,63 +96,8 @@ set_huge_pte (struct mm_struct *mm, struct vm_area_struct *vma, return; } -static int -anon_get_hugetlb_page (struct mm_struct *mm, struct vm_area_struct *vma, - int write_access, pte_t * page_table) -{ - struct page *page; - - page = alloc_hugetlb_page(); - if (page == NULL) - return -1; - set_huge_pte(mm, vma, page, page_table, write_access); - return 1; -} - -static int -make_hugetlb_pages_present (unsigned long addr, unsigned long end, int flags) -{ - int write; - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - pte_t *pte; - - vma = find_vma(mm, addr); - if (!vma) - goto out_error1; - - write = (vma->vm_flags & VM_WRITE) != 0; - if ((vma->vm_end - vma->vm_start) & (HPAGE_SIZE - 1)) - goto out_error1; - spin_lock(&mm->page_table_lock); - do { - pte = huge_pte_alloc(mm, addr); - if ((pte) && (pte_none(*pte))) { - if (anon_get_hugetlb_page(mm, vma, write ? VM_WRITE : VM_READ, pte) == -1) - goto out_error; - } else - goto out_error; - addr += HPAGE_SIZE; - } while (addr < end); - spin_unlock(&mm->page_table_lock); - vma->vm_flags |= (VM_HUGETLB | VM_RESERVED); - if (flags & MAP_PRIVATE) - vma->vm_flags |= VM_DONTCOPY; - vma->vm_ops = &hugetlb_vm_ops; - return 0; -out_error: - if (addr > vma->vm_start) { - vma->vm_end = addr; - zap_hugetlb_resources(vma); - vma->vm_end = end; - } - spin_unlock(&mm->page_table_lock); -out_error1: - return -1; -} - -int -copy_hugetlb_page_range (struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) +int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, + struct vm_area_struct *vma) { pte_t *src_pte, *dst_pte, entry; struct page *ptepage; @@ -201,15 +117,14 @@ copy_hugetlb_page_range (struct mm_struct *dst, struct mm_struct *src, struct vm addr += HPAGE_SIZE; } return 0; - - nomem: +nomem: return -ENOMEM; } int -follow_hugetlb_page (struct mm_struct *mm, struct vm_area_struct *vma, - struct page **pages, struct vm_area_struct **vmas, - unsigned long *st, int *length, int i) +follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, + struct page **pages, struct vm_area_struct **vmas, + unsigned long *st, int *length, int i) { pte_t *ptep, pte; unsigned long start = *st; @@ -234,8 +149,8 @@ back1: i++; len--; start += PAGE_SIZE; - if (((start & HPAGE_MASK) == pstart) && len - && (start < vma->vm_end)) + if (((start & HPAGE_MASK) == pstart) && len && + (start < vma->vm_end)) goto back1; } while (len && start < vma->vm_end); *length = len; @@ -243,51 +158,149 @@ back1: return i; } -static void -zap_hugetlb_resources (struct vm_area_struct *mpnt) +void free_huge_page(struct page *page) +{ + BUG_ON(page_count(page)); + BUG_ON(page->mapping); + + INIT_LIST_HEAD(&page->list); + + spin_lock(&htlbpage_lock); + list_add(&page->list, &htlbpage_freelist); + htlbpagemem++; + spin_unlock(&htlbpage_lock); +} + +void huge_page_release(struct page *page) +{ + if (!put_page_testzero(page)) + return; + + free_huge_page(page); +} + +void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct mm_struct *mm = mpnt->vm_mm; - unsigned long len, addr, end; - pte_t *ptep; + struct mm_struct *mm = vma->vm_mm; + unsigned long address; + pte_t *pte; struct page *page; - addr = mpnt->vm_start; - end = mpnt->vm_end; - len = end - addr; - do { - ptep = huge_pte_offset(mm, addr); - page = pte_page(*ptep); - pte_clear(ptep); - free_hugetlb_page(page); - addr += HPAGE_SIZE; - } while (addr < end); - mm->rss -= (len >> PAGE_SHIFT); - mpnt->vm_ops = NULL; - flush_tlb_range(mpnt, end - len, end); + BUG_ON(start & (HPAGE_SIZE - 1)); + BUG_ON(end & (HPAGE_SIZE - 1)); + + spin_lock(&htlbpage_lock); + spin_unlock(&htlbpage_lock); + for (address = start; address < end; address += HPAGE_SIZE) { + pte = huge_pte_offset(mm, address); + if (pte_none(*pte)) + continue; + page = pte_page(*pte); + huge_page_release(page); + pte_clear(pte); + } + mm->rss -= (end - start) >> PAGE_SHIFT; + flush_tlb_range(vma, start, end); } -static void -unlink_vma (struct vm_area_struct *mpnt) +void zap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long length) +{ + struct mm_struct *mm = vma->vm_mm; + spin_lock(&mm->page_table_lock); + unmap_hugepage_range(vma, start, start + length); + spin_unlock(&mm->page_table_lock); +} + +int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - - vma = mm->mmap; - if (vma == mpnt) { - mm->mmap = vma->vm_next; - } else { - while (vma->vm_next != mpnt) { - vma = vma->vm_next; + unsigned long addr; + int ret = 0; + + BUG_ON(vma->vm_start & ~HPAGE_MASK); + BUG_ON(vma->vm_end & ~HPAGE_MASK); + + spin_lock(&mm->page_table_lock); + for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { + unsigned long idx; + pte_t *pte = huge_pte_alloc(mm, addr); + struct page *page; + + if (!pte) { + ret = -ENOMEM; + goto out; } - vma->vm_next = mpnt->vm_next; + if (!pte_none(*pte)) + continue; + + idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) + + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + page = find_get_page(mapping, idx); + if (!page) { + page = alloc_hugetlb_page(); + if (!page) { + ret = -ENOMEM; + goto out; + } + add_to_page_cache(page, mapping, idx, GFP_ATOMIC); + unlock_page(page); + } + set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE); } - rb_erase(&mpnt->vm_rb, &mm->mm_rb); - mm->mmap_cache = NULL; - mm->map_count--; +out: + spin_unlock(&mm->page_table_lock); + return ret; } -int -set_hugetlb_mem_size (int count) +void update_and_free_page(struct page *page) +{ + int j; + struct page *map; + + map = page; + htlbzone_pages--; + for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) { + map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | + 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved | + 1 << PG_private | 1<< PG_writeback); + set_page_count(map, 0); + map++; + } + set_page_count(page, 1); + __free_pages(page, HUGETLB_PAGE_ORDER); +} + +int try_to_free_low(int count) +{ + struct list_head *p; + struct page *page, *map; + + map = NULL; + spin_lock(&htlbpage_lock); + list_for_each(p, &htlbpage_freelist) { + if (map) { + list_del(&map->list); + update_and_free_page(map); + htlbpagemem--; + map = NULL; + if (++count == 0) + break; + } + page = list_entry(p, struct page, list); + if ((page_zone(page))->name[0] != 'H') // Look for non-Highmem + map = page; + } + if (map) { + list_del(&map->list); + update_and_free_page(map); + htlbpagemem--; + count++; + } + spin_unlock(&htlbpage_lock); + return count; +} + +int set_hugetlb_mem_size(int count) { int j, lcount; struct page *page, *map; @@ -298,7 +311,10 @@ set_hugetlb_mem_size (int count) lcount = count; else lcount = count - htlbzone_pages; - if (lcount > 0) { /*Increase the mem size. */ + + if (lcount == 0) + return (int)htlbzone_pages; + if (lcount > 0) { /* Increase the mem size. */ while (lcount--) { page = alloc_pages(__GFP_HIGHMEM, HUGETLB_PAGE_ORDER); if (page == NULL) @@ -311,35 +327,80 @@ set_hugetlb_mem_size (int count) } return (int) htlbzone_pages; } - /*Shrink the memory size. */ + /* Shrink the memory size. */ + lcount = try_to_free_low(lcount); while (lcount++) { page = alloc_hugetlb_page(); if (page == NULL) break; spin_lock(&htlbpage_lock); - htlbzone_pages--; + update_and_free_page(page); spin_unlock(&htlbpage_lock); - map = page; - for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) { - map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | - 1 << PG_dirty | 1 << PG_active | - 1 << PG_private | 1<< PG_writeback); - map++; - } - set_page_count(page, 1); - __free_pages(page, HUGETLB_PAGE_ORDER); } return (int) htlbzone_pages; } -static struct page * -hugetlb_nopage(struct vm_area_struct *vma, unsigned long address, int unused) +int hugetlb_sysctl_handler(ctl_table *table, int write, struct file *file, void *buffer, size_t *length) +{ + proc_dointvec(table, write, file, buffer, length); + htlbpage_max = set_hugetlb_mem_size(htlbpage_max); + return 0; +} + +static int __init hugetlb_setup(char *s) +{ + if (sscanf(s, "%d", &htlbpage_max) <= 0) + htlbpage_max = 0; + return 1; +} +__setup("hugepages=", hugetlb_setup); + +static int __init hugetlb_init(void) +{ + int i, j; + struct page *page; + + for (i = 0; i < htlbpage_max; ++i) { + page = alloc_pages(__GFP_HIGHMEM, HUGETLB_PAGE_ORDER); + if (!page) + break; + for (j = 0; j < HPAGE_SIZE/PAGE_SIZE; ++j) + SetPageReserved(&page[j]); + spin_lock(&htlbpage_lock); + list_add(&page->list, &htlbpage_freelist); + spin_unlock(&htlbpage_lock); + } + htlbpage_max = htlbpagemem = htlbzone_pages = i; + printk("Total HugeTLB memory allocated, %ld\n", htlbpagemem); + return 0; +} +module_init(hugetlb_init); + +int hugetlb_report_meminfo(char *buf) +{ + return sprintf(buf, + "HugePages_Total: %5lu\n" + "HugePages_Free: %5lu\n" + "Hugepagesize: %5lu kB\n", + htlbzone_pages, + htlbpagemem, + HPAGE_SIZE/1024); +} + +int is_hugepage_mem_enough(size_t size) +{ + if (size > (htlbpagemem << HPAGE_SHIFT)) + return 0; + return 1; +} + +static struct page *hugetlb_nopage(struct vm_area_struct * area, unsigned long address, int unused) { BUG(); return NULL; } -static struct vm_operations_struct hugetlb_vm_ops = { +struct vm_operations_struct hugetlb_vm_ops = { .nopage = hugetlb_nopage, .close = zap_hugetlb_resources, }; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 7980c94fab35..49114de81896 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -234,7 +234,7 @@ put_gate_page (struct page *page, unsigned long address) pte_t *pte; if (!PageReserved(page)) - printk("put_gate_page: gate page at 0x%p not in reserved memory\n", + printk(KERN_ERR "put_gate_page: gate page at 0x%p not in reserved memory\n", page_address(page)); pgd = pgd_offset_k(address); /* note: this is NOT pgd_offset()! */ @@ -342,13 +342,6 @@ ia64_mmu_init (void *my_cpu_data) * Set up the page tables. */ -#ifdef CONFIG_HUGETLB_PAGE -long htlbpagemem; -int htlbpage_max; -extern long htlbzone_pages; -extern struct list_head htlbpage_freelist; -#endif - #ifdef CONFIG_DISCONTIGMEM void paging_init (void) @@ -438,10 +431,10 @@ mem_init (void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - printk("Memory: %luk/%luk available (%luk code, %luk reserved, %luk data, %luk init)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT - 10), - num_physpages << (PAGE_SHIFT - 10), codesize >> 10, reserved_pages << (PAGE_SHIFT - 10), - datasize >> 10, initsize >> 10); + printk(KERN_INFO "Memory: %luk/%luk available (%luk code, %luk reserved, " + "%luk data, %luk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT - 10), + num_physpages << (PAGE_SHIFT - 10), codesize >> 10, + reserved_pages << (PAGE_SHIFT - 10), datasize >> 10, initsize >> 10); /* * Allow for enough (cached) page table pages so that we can map the entire memory @@ -462,29 +455,4 @@ mem_init (void) #ifdef CONFIG_IA32_SUPPORT ia32_gdt_init(); #endif -#ifdef CONFIG_HUGETLB_PAGE - { - long i; - int j; - struct page *page, *map; - - if ((htlbzone_pages << (HPAGE_SHIFT - PAGE_SHIFT)) >= max_low_pfn) - htlbzone_pages = (max_low_pfn >> ((HPAGE_SHIFT - PAGE_SHIFT) + 1)); - INIT_LIST_HEAD(&htlbpage_freelist); - for (i = 0; i < htlbzone_pages; i++) { - page = alloc_pages(__GFP_HIGHMEM, HUGETLB_PAGE_ORDER); - if (!page) - break; - map = page; - for (j = 0; j < (HPAGE_SIZE/PAGE_SIZE); j++) { - SetPageReserved(map); - map++; - } - list_add(&page->list, &htlbpage_freelist); - } - printk("Total Huge_TLB_Page memory pages allocated %ld \n", i); - htlbzone_pages = htlbpagemem = i; - htlbpage_max = (int)i; - } -#endif } diff --git a/arch/ia64/scripts/check-gas b/arch/ia64/scripts/check-gas new file mode 100755 index 000000000000..ef652caf82ae --- /dev/null +++ b/arch/ia64/scripts/check-gas @@ -0,0 +1,11 @@ +#!/bin/sh +dir=$(dirname $0) +CC=$1 +$CC -c $dir/check-gas-asm.S +res=$(objdump -r --section .data check-gas-asm.o | fgrep 00004 | tr -s ' ' |cut -f3 -d' ') +if [ $res != ".text" ]; then + echo buggy +else + echo good +fi +exit 0 diff --git a/arch/ia64/scripts/check-gas-asm.S b/arch/ia64/scripts/check-gas-asm.S new file mode 100644 index 000000000000..010e1d227e5d --- /dev/null +++ b/arch/ia64/scripts/check-gas-asm.S @@ -0,0 +1,2 @@ +[1:] nop 0 + .xdata4 ".data", 0, 1b-. diff --git a/arch/ia64/scripts/unwcheck.sh b/arch/ia64/scripts/unwcheck.sh new file mode 100755 index 000000000000..cf61dd42cba2 --- /dev/null +++ b/arch/ia64/scripts/unwcheck.sh @@ -0,0 +1,109 @@ +#!/bin/sh +# Usage: unwcheck.sh <executable_file_name> +# Pre-requisite: readelf [from Gnu binutils package] +# Purpose: Check the following invariant +# For each code range in the input binary: +# Sum[ lengths of unwind regions] = Number of slots in code range. +# Author : Harish Patil +# First version: January 2002 +# Modified : 2/13/2002 +# Modified : 3/15/2002: duplicate detection +readelf -u $1 | gawk '\ + function todec(hexstr){ + dec = 0; + l = length(hexstr); + for (i = 1; i <= l; i++) + { + c = substr(hexstr, i, 1); + if (c == "A") + dec = dec*16 + 10; + else if (c == "B") + dec = dec*16 + 11; + else if (c == "C") + dec = dec*16 + 12; + else if (c == "D") + dec = dec*16 + 13; + else if (c == "E") + dec = dec*16 + 14; + else if (c == "F") + dec = dec*16 + 15; + else + dec = dec*16 + c; + } + return dec; + } + BEGIN { first = 1; sum_rlen = 0; no_slots = 0; errors=0; no_code_ranges=0; } + { + if (NF==5 && $3=="info") + { + no_code_ranges += 1; + if (first == 0) + { + if (sum_rlen != no_slots) + { + print full_code_range; + print " ", "lo = ", lo, " hi =", hi; + print " ", "sum_rlen = ", sum_rlen, "no_slots = " no_slots; + print " "," ", "*******ERROR ***********"; + print " "," ", "sum_rlen:", sum_rlen, " != no_slots:" no_slots; + errors += 1; + } + sum_rlen = 0; + } + full_code_range = $0; + code_range = $2; + gsub("..$", "", code_range); + gsub("^.", "", code_range); + split(code_range, addr, "-"); + lo = toupper(addr[1]); + + code_range_lo[no_code_ranges] = addr[1]; + occurs[addr[1]] += 1; + full_range[addr[1]] = $0; + + gsub("0X.[0]*", "", lo); + hi = toupper(addr[2]); + gsub("0X.[0]*", "", hi); + no_slots = (todec(hi) - todec(lo))/ 16*3 + first = 0; + } + if (index($0,"rlen") > 0 ) + { + rlen_str = substr($0, index($0,"rlen")); + rlen = rlen_str; + gsub("rlen=", "", rlen); + gsub(")", "", rlen); + sum_rlen = sum_rlen + rlen; + } + } + END { + if (first == 0) + { + if (sum_rlen != no_slots) + { + print "code_range=", code_range; + print " ", "lo = ", lo, " hi =", hi; + print " ", "sum_rlen = ", sum_rlen, "no_slots = " no_slots; + print " "," ", "*******ERROR ***********"; + print " "," ", "sum_rlen:", sum_rlen, " != no_slots:" no_slots; + errors += 1; + } + } + no_duplicates = 0; + for (i=1; i<=no_code_ranges; i++) + { + cr = code_range_lo[i]; + if (reported_cr[cr]==1) continue; + if ( occurs[cr] > 1) + { + reported_cr[cr] = 1; + print "Code range low ", code_range_lo[i], ":", full_range[cr], " occurs: ", occurs[cr], " times."; + print " "; + no_duplicates++; + } + } + print "======================================" + print "Total errors:", errors, "/", no_code_ranges, " duplicates:", no_duplicates; + print "======================================" + } + ' diff --git a/arch/ia64/tools/Makefile b/arch/ia64/tools/Makefile index e8dc9c8f40a3..ce1fe06d9d97 100644 --- a/arch/ia64/tools/Makefile +++ b/arch/ia64/tools/Makefile @@ -4,14 +4,7 @@ TARGET = include/asm-ia64/offsets.h src = $(obj) -all: - -fastdep: - -mrproper: clean - -clean: - rm -f $(obj)/print_offsets.s $(obj)/print_offsets $(obj)/offsets.h +clean-files := print_offsets.s print_offsets offsets.h $(TARGET): $(obj)/offsets.h @if ! cmp -s $(obj)/offsets.h ${TARGET}; then \ diff --git a/arch/ia64/tools/print_offsets.c b/arch/ia64/tools/print_offsets.c index 20fc8ee4f32f..5f52857e3dd0 100644 --- a/arch/ia64/tools/print_offsets.c +++ b/arch/ia64/tools/print_offsets.c @@ -1,7 +1,7 @@ /* * Utility to generate asm-ia64/offsets.h. * - * Copyright (C) 1999-2002 Hewlett-Packard Co + * Copyright (C) 1999-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * Note that this file has dual use: when building the kernel @@ -52,8 +52,13 @@ tab[] = { "SIGFRAME_SIZE", sizeof (struct sigframe) }, { "UNW_FRAME_INFO_SIZE", sizeof (struct unw_frame_info) }, { "", 0 }, /* spacer */ - { "IA64_TASK_THREAD_KSP_OFFSET", offsetof (struct task_struct, thread.ksp) }, + { "IA64_TASK_CLEAR_CHILD_TID_OFFSET",offsetof (struct task_struct, clear_child_tid) }, + { "IA64_TASK_GROUP_LEADER_OFFSET", offsetof (struct task_struct, group_leader) }, { "IA64_TASK_PID_OFFSET", offsetof (struct task_struct, pid) }, + { "IA64_TASK_REAL_PARENT_OFFSET", offsetof (struct task_struct, real_parent) }, + { "IA64_TASK_TGID_OFFSET", offsetof (struct task_struct, tgid) }, + { "IA64_TASK_THREAD_KSP_OFFSET", offsetof (struct task_struct, thread.ksp) }, + { "IA64_TASK_THREAD_ON_USTACK_OFFSET", offsetof (struct task_struct, thread.on_ustack) }, { "IA64_PT_REGS_CR_IPSR_OFFSET", offsetof (struct pt_regs, cr_ipsr) }, { "IA64_PT_REGS_CR_IIP_OFFSET", offsetof (struct pt_regs, cr_iip) }, { "IA64_PT_REGS_CR_IFS_OFFSET", offsetof (struct pt_regs, cr_ifs) }, diff --git a/arch/ia64/vmlinux.lds.S b/arch/ia64/vmlinux.lds.S index 37a65b7fb9ad..1389f87f513c 100644 --- a/arch/ia64/vmlinux.lds.S +++ b/arch/ia64/vmlinux.lds.S @@ -6,7 +6,7 @@ #define LOAD_OFFSET PAGE_OFFSET #include <asm-generic/vmlinux.lds.h> - + OUTPUT_FORMAT("elf64-ia64-little") OUTPUT_ARCH(ia64) ENTRY(phys_start) @@ -29,6 +29,7 @@ SECTIONS _text = .; _stext = .; + .text : AT(ADDR(.text) - PAGE_OFFSET) { *(.text.ivt) @@ -44,33 +45,46 @@ SECTIONS /* Read-only data */ - /* Global data */ - _data = .; - /* Exception table */ . = ALIGN(16); - __start___ex_table = .; __ex_table : AT(ADDR(__ex_table) - PAGE_OFFSET) - { *(__ex_table) } - __stop___ex_table = .; + { + __start___ex_table = .; + *(__ex_table) + __stop___ex_table = .; + } + + __mckinley_e9_bundles : AT(ADDR(__mckinley_e9_bundles) - PAGE_OFFSET) + { + __start___mckinley_e9_bundles = .; + *(__mckinley_e9_bundles) + __end___mckinley_e9_bundles = .; + } + + /* Global data */ + _data = .; #if defined(CONFIG_IA64_GENERIC) /* Machine Vector */ . = ALIGN(16); - machvec_start = .; .machvec : AT(ADDR(.machvec) - PAGE_OFFSET) - { *(.machvec) } - machvec_end = .; + { + machvec_start = .; + *(.machvec) + machvec_end = .; + } #endif /* Unwind info & table: */ . = ALIGN(8); .IA_64.unwind_info : AT(ADDR(.IA_64.unwind_info) - PAGE_OFFSET) { *(.IA_64.unwind_info*) } - ia64_unw_start = .; .IA_64.unwind : AT(ADDR(.IA_64.unwind) - PAGE_OFFSET) - { *(.IA_64.unwind*) } - ia64_unw_end = .; + { + ia64_unw_start = .; + *(.IA_64.unwind*) + ia64_unw_end = .; + } RODATA @@ -87,32 +101,38 @@ SECTIONS .init.data : AT(ADDR(.init.data) - PAGE_OFFSET) { *(.init.data) } - __initramfs_start = .; .init.ramfs : AT(ADDR(.init.ramfs) - PAGE_OFFSET) - { *(.init.ramfs) } - __initramfs_end = .; + { + __initramfs_start = .; + *(.init.ramfs) + __initramfs_end = .; + } . = ALIGN(16); - __setup_start = .; .init.setup : AT(ADDR(.init.setup) - PAGE_OFFSET) - { *(.init.setup) } - __setup_end = .; - __start___param = .; + { + __setup_start = .; + *(.init.setup) + __setup_end = .; + } __param : AT(ADDR(__param) - PAGE_OFFSET) - { *(__param) } - __stop___param = .; - __initcall_start = .; + { + __start___param = .; + *(__param) + __stop___param = .; + } .initcall.init : AT(ADDR(.initcall.init) - PAGE_OFFSET) { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + __initcall_start = .; + *(.initcall1.init) + *(.initcall2.init) + *(.initcall3.init) + *(.initcall4.init) + *(.initcall5.init) + *(.initcall6.init) + *(.initcall7.init) + __initcall_end = .; } - __initcall_end = .; . = ALIGN(PAGE_SIZE); __init_end = .; @@ -131,10 +151,6 @@ SECTIONS .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - PAGE_OFFSET) { *(.data.cacheline_aligned) } - /* Kernel symbol names for modules: */ - .kstrtab : AT(ADDR(.kstrtab) - PAGE_OFFSET) - { *(.kstrtab) } - /* Per-cpu data: */ . = ALIGN(PERCPU_PAGE_SIZE); __phys_per_cpu_start = .; diff --git a/include/asm-ia64/asmmacro.h b/include/asm-ia64/asmmacro.h index 010c6fc11a91..d3c3a0998f47 100644 --- a/include/asm-ia64/asmmacro.h +++ b/include/asm-ia64/asmmacro.h @@ -2,15 +2,22 @@ #define _ASM_IA64_ASMMACRO_H /* - * Copyright (C) 2000-2001 Hewlett-Packard Co + * Copyright (C) 2000-2001, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ +#include <linux/config.h> + #define ENTRY(name) \ .align 32; \ .proc name; \ name: +#define ENTRY_MIN_ALIGN(name) \ + .align 16; \ + .proc name; \ +name: + #define GLOBAL_ENTRY(name) \ .global name; \ ENTRY(name) @@ -37,19 +44,40 @@ name: .previous #if __GNUC__ >= 3 -# define EX(y,x...) \ - .xdata4 "__ex_table", @gprel(99f), @gprel(y); \ +# define EX(y,x...) \ + .xdata4 "__ex_table", 99f-., y-.; \ [99:] x -# define EXCLR(y,x...) \ - .xdata4 "__ex_table", @gprel(99f), @gprel(y)+4; \ +# define EXCLR(y,x...) \ + .xdata4 "__ex_table", 99f-., y-.+4; \ [99:] x #else -# define EX(y,x...) \ - .xdata4 "__ex_table", @gprel(99f), @gprel(y); \ +# define EX(y,x...) \ + .xdata4 "__ex_table", 99f-., y-.; \ 99: x -# define EXCLR(y,x...) \ - .xdata4 "__ex_table", @gprel(99f), @gprel(y)+4; \ +# define EXCLR(y,x...) \ + .xdata4 "__ex_table", 99f-., y-.+4; \ 99: x #endif +/* + * For now, we always put in the McKinley E9 workaround. On CPUs that don't need it, + * we'll patch out the work-around bundles with NOPs, so their impact is minimal. + */ +#define DO_MCKINLEY_E9_WORKAROUND +#ifdef DO_MCKINLEY_E9_WORKAROUND + .section "__mckinley_e9_bundles", "a" + .previous +/* workaround for Itanium 2 Errata 9: */ +# define MCKINLEY_E9_WORKAROUND \ + .xdata4 "__mckinley_e9_bundles", 1f-.; \ +1:{ .mib; \ + nop.m 0; \ + nop.i 0; \ + br.call.sptk.many b7=1f;; \ + }; \ +1: +#else +# define MCKINLEY_E9_WORKAROUND +#endif + #endif /* _ASM_IA64_ASMMACRO_H */ diff --git a/include/asm-ia64/bitops.h b/include/asm-ia64/bitops.h index 325bec339c3b..bec48081bba7 100644 --- a/include/asm-ia64/bitops.h +++ b/include/asm-ia64/bitops.h @@ -2,7 +2,7 @@ #define _ASM_IA64_BITOPS_H /* - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * 02/06/02 find_next_bit() and find_first_bit() added from Erich Focht's ia64 O(1) @@ -320,7 +320,7 @@ __ffs (unsigned long x) static inline unsigned long ia64_fls (unsigned long x) { - double d = x; + long double d = x; long exp; __asm__ ("getf.exp %0=%1" : "=r"(exp) : "f"(d)); diff --git a/include/asm-ia64/bugs.h b/include/asm-ia64/bugs.h index c74d2261ccc3..e94677a3b22f 100644 --- a/include/asm-ia64/bugs.h +++ b/include/asm-ia64/bugs.h @@ -4,16 +4,14 @@ * Needs: * void check_bugs(void); * - * Copyright (C) 1998, 1999 Hewlett-Packard Co - * Copyright (C) 1998, 1999 David Mosberger-Tang <davidm@hpl.hp.com> + * Copyright (C) 1998, 1999, 2003 Hewlett-Packard Co + * David Mosberger-Tang <davidm@hpl.hp.com> */ +#ifndef _ASM_IA64_BUGS_H +#define _ASM_IA64_BUGS_H #include <asm/processor.h> -/* - * I don't know of any ia-64 bugs yet.. - */ -static void -check_bugs (void) -{ -} +extern void check_bugs (void); + +#endif /* _ASM_IA64_BUGS_H */ diff --git a/include/asm-ia64/compat.h b/include/asm-ia64/compat.h index 69bf8481be81..4dbbbf499800 100644 --- a/include/asm-ia64/compat.h +++ b/include/asm-ia64/compat.h @@ -14,11 +14,18 @@ typedef s32 compat_clock_t; typedef s32 compat_pid_t; typedef u16 compat_uid_t; typedef u16 compat_gid_t; +typedef u32 compat_uid32_t; +typedef u32 compat_gid32_t; typedef u16 compat_mode_t; typedef u32 compat_ino_t; typedef u16 compat_dev_t; typedef s32 compat_off_t; +typedef s64 compat_loff_t; typedef u16 compat_nlink_t; +typedef u16 compat_ipc_pid_t; +typedef s32 compat_daddr_t; +typedef u32 compat_caddr_t; +typedef __kernel_fsid_t compat_fsid_t; struct compat_timespec { compat_time_t tv_sec; @@ -54,11 +61,31 @@ struct compat_stat { }; struct compat_flock { - short l_type; - short l_whence; - compat_off_t l_start; - compat_off_t l_len; - compat_pid_t l_pid; + short l_type; + short l_whence; + compat_off_t l_start; + compat_off_t l_len; + compat_pid_t l_pid; }; +struct compat_statfs { + int f_type; + int f_bsize; + int f_blocks; + int f_bfree; + int f_bavail; + int f_files; + int f_ffree; + compat_fsid_t f_fsid; + int f_namelen; /* SunOS ignores this field. */ + int f_spare[6]; +}; + +typedef u32 compat_old_sigset_t; /* at least 32 bits */ + +#define _COMPAT_NSIG 64 +#define _COMPAT_NSIG_BPW 32 + +typedef u32 compat_sigset_word; + #endif /* _ASM_IA64_COMPAT_H */ diff --git a/include/asm-ia64/elf.h b/include/asm-ia64/elf.h index 6cc69c3299f6..8fb191e7712e 100644 --- a/include/asm-ia64/elf.h +++ b/include/asm-ia64/elf.h @@ -4,10 +4,12 @@ /* * ELF-specific definitions. * - * Copyright (C) 1998, 1999, 2002 Hewlett-Packard Co + * Copyright (C) 1998-1999, 2002-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ +#include <linux/config.h> + #include <asm/fpu.h> #include <asm/page.h> @@ -88,6 +90,11 @@ extern void ia64_elf_core_copy_regs (struct pt_regs *src, elf_gregset_t dst); relevant until we have real hardware to play with... */ #define ELF_PLATFORM 0 +/* + * This should go into linux/elf.h... + */ +#define AT_SYSINFO 32 + #ifdef __KERNEL__ struct elf64_hdr; extern void ia64_set_personality (struct elf64_hdr *elf_ex, int ibcs2_interpreter); @@ -99,7 +106,14 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *); #define ELF_CORE_COPY_TASK_REGS(tsk, elf_gregs) dump_task_regs(tsk, elf_gregs) #define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs) - +#ifdef CONFIG_FSYS +#define ARCH_DLINFO \ +do { \ + extern char syscall_via_epc[], __start_gate_section[]; \ + NEW_AUX_ENT(AT_SYSINFO, GATE_ADDR + (syscall_via_epc - __start_gate_section)); \ +} while (0) #endif +#endif /* __KERNEL__ */ + #endif /* _ASM_IA64_ELF_H */ diff --git a/include/asm-ia64/ia32.h b/include/asm-ia64/ia32.h index bb2f802fe3dc..4824df582b8a 100644 --- a/include/asm-ia64/ia32.h +++ b/include/asm-ia64/ia32.h @@ -12,17 +12,6 @@ * 32 bit structures for IA32 support. */ -/* 32bit compatibility types */ -typedef unsigned short __kernel_ipc_pid_t32; -typedef unsigned int __kernel_uid32_t32; -typedef unsigned int __kernel_gid32_t32; -typedef unsigned short __kernel_umode_t32; -typedef short __kernel_nlink_t32; -typedef int __kernel_daddr_t32; -typedef unsigned int __kernel_caddr_t32; -typedef long __kernel_loff_t32; -typedef __kernel_fsid_t __kernel_fsid_t32; - #define IA32_PAGE_SHIFT 12 /* 4KB pages */ #define IA32_PAGE_SIZE (1UL << IA32_PAGE_SHIFT) #define IA32_PAGE_MASK (~(IA32_PAGE_SIZE - 1)) @@ -143,10 +132,6 @@ struct ia32_user_fxsr_struct { }; /* signal.h */ -#define _IA32_NSIG 64 -#define _IA32_NSIG_BPW 32 -#define _IA32_NSIG_WORDS (_IA32_NSIG / _IA32_NSIG_BPW) - #define IA32_SET_SA_HANDLER(ka,handler,restorer) \ ((ka)->sa.sa_handler = (__sighandler_t) \ (((unsigned long)(restorer) << 32) \ @@ -154,23 +139,17 @@ struct ia32_user_fxsr_struct { #define IA32_SA_HANDLER(ka) ((unsigned long) (ka)->sa.sa_handler & 0xffffffff) #define IA32_SA_RESTORER(ka) ((unsigned long) (ka)->sa.sa_handler >> 32) -typedef struct { - unsigned int sig[_IA32_NSIG_WORDS]; -} sigset32_t; - struct sigaction32 { unsigned int sa_handler; /* Really a pointer, but need to deal with 32 bits */ unsigned int sa_flags; unsigned int sa_restorer; /* Another 32 bit pointer */ - sigset32_t sa_mask; /* A 32 bit mask */ + compat_sigset_t sa_mask; /* A 32 bit mask */ }; -typedef unsigned int old_sigset32_t; /* at least 32 bits */ - struct old_sigaction32 { unsigned int sa_handler; /* Really a pointer, but need to deal with 32 bits */ - old_sigset32_t sa_mask; /* A 32 bit mask */ + compat_old_sigset_t sa_mask; /* A 32 bit mask */ unsigned int sa_flags; unsigned int sa_restorer; /* Another 32 bit pointer */ }; @@ -214,19 +193,6 @@ struct stat64 { unsigned int st_ino_hi; }; -struct statfs32 { - int f_type; - int f_bsize; - int f_blocks; - int f_bfree; - int f_bavail; - int f_files; - int f_ffree; - __kernel_fsid_t32 f_fsid; - int f_namelen; /* SunOS ignores this field. */ - int f_spare[6]; -}; - typedef union sigval32 { int sival_int; unsigned int sival_ptr; diff --git a/include/asm-ia64/intrinsics.h b/include/asm-ia64/intrinsics.h index d2977f600f80..b9a3c5e049c9 100644 --- a/include/asm-ia64/intrinsics.h +++ b/include/asm-ia64/intrinsics.h @@ -4,10 +4,12 @@ /* * Compiler-dependent intrinsics. * - * Copyright (C) 2002 Hewlett-Packard Co + * Copyright (C) 2002-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ +#include <linux/config.h> + /* * Force an unresolved reference if someone tries to use * ia64_fetch_and_add() with a bad value. diff --git a/include/asm-ia64/mmu_context.h b/include/asm-ia64/mmu_context.h index 479d63d05ed9..a614a1dbbb61 100644 --- a/include/asm-ia64/mmu_context.h +++ b/include/asm-ia64/mmu_context.h @@ -28,6 +28,36 @@ #include <asm/processor.h> +#define MMU_CONTEXT_DEBUG 0 + +#if MMU_CONTEXT_DEBUG + +#include <ia64intrin.h> + +extern struct mmu_trace_entry { + char op; + u8 cpu; + u32 context; + void *mm; +} mmu_tbuf[1024]; + +extern volatile int mmu_tbuf_index; + +# define MMU_TRACE(_op,_cpu,_mm,_ctx) \ +do { \ + int i = __sync_fetch_and_add(&mmu_tbuf_index, 1) % ARRAY_SIZE(mmu_tbuf); \ + struct mmu_trace_entry e; \ + e.op = (_op); \ + e.cpu = (_cpu); \ + e.mm = (_mm); \ + e.context = (_ctx); \ + mmu_tbuf[i] = e; \ +} while (0) + +#else +# define MMU_TRACE(op,cpu,mm,ctx) do { ; } while (0) +#endif + struct ia64_ctx { spinlock_t lock; unsigned int next; /* next context number to use */ @@ -91,6 +121,7 @@ get_mmu_context (struct mm_struct *mm) static inline int init_new_context (struct task_struct *p, struct mm_struct *mm) { + MMU_TRACE('N', smp_processor_id(), mm, 0); mm->context = 0; return 0; } @@ -99,6 +130,7 @@ static inline void destroy_context (struct mm_struct *mm) { /* Nothing to do. */ + MMU_TRACE('D', smp_processor_id(), mm, mm->context); } static inline void @@ -138,12 +170,17 @@ activate_context (struct mm_struct *mm) do { context = get_mmu_context(mm); + MMU_TRACE('A', smp_processor_id(), mm, context); reload_context(context); + MMU_TRACE('a', smp_processor_id(), mm, context); /* in the unlikely event of a TLB-flush by another thread, redo the load: */ } while (unlikely(context != mm->context)); } -#define deactivate_mm(tsk,mm) do { } while (0) +#define deactivate_mm(tsk,mm) \ +do { \ + MMU_TRACE('d', smp_processor_id(), mm, mm->context); \ +} while (0) /* * Switch from address space PREV to address space NEXT. diff --git a/include/asm-ia64/perfmon.h b/include/asm-ia64/perfmon.h index c95e8d5fd3b7..110d439d45a2 100644 --- a/include/asm-ia64/perfmon.h +++ b/include/asm-ia64/perfmon.h @@ -40,6 +40,7 @@ #define PFM_FL_INHERIT_ALL 0x02 /* always clone pfm_context across fork() */ #define PFM_FL_NOTIFY_BLOCK 0x04 /* block task on user level notifications */ #define PFM_FL_SYSTEM_WIDE 0x08 /* create a system wide context */ +#define PFM_FL_EXCL_IDLE 0x20 /* exclude idle task from system wide session */ /* * PMC flags @@ -86,11 +87,12 @@ typedef struct { unsigned long reg_long_reset; /* reset after sampling buffer overflow (large) */ unsigned long reg_short_reset;/* reset after counter overflow (small) */ - unsigned long reg_reset_pmds[4]; /* which other counters to reset on overflow */ - unsigned long reg_random_seed; /* seed value when randomization is used */ - unsigned long reg_random_mask; /* bitmask used to limit random value */ + unsigned long reg_reset_pmds[4]; /* which other counters to reset on overflow */ + unsigned long reg_random_seed; /* seed value when randomization is used */ + unsigned long reg_random_mask; /* bitmask used to limit random value */ + unsigned long reg_last_reset_value;/* last value used to reset the PMD (PFM_READ_PMDS) */ - unsigned long reserved[14]; /* for future use */ + unsigned long reserved[13]; /* for future use */ } pfarg_reg_t; typedef struct { @@ -123,7 +125,7 @@ typedef struct { * Define the version numbers for both perfmon as a whole and the sampling buffer format. */ #define PFM_VERSION_MAJ 1U -#define PFM_VERSION_MIN 1U +#define PFM_VERSION_MIN 3U #define PFM_VERSION (((PFM_VERSION_MAJ&0xffff)<<16)|(PFM_VERSION_MIN & 0xffff)) #define PFM_SMPL_VERSION_MAJ 1U @@ -156,13 +158,17 @@ typedef struct { unsigned long stamp; /* timestamp */ unsigned long ip; /* where did the overflow interrupt happened */ unsigned long regs; /* bitmask of which registers overflowed */ - unsigned long period; /* unused */ + unsigned long reserved; /* unused */ } perfmon_smpl_entry_t; -extern int perfmonctl(pid_t pid, int cmd, void *arg, int narg); +extern long perfmonctl(pid_t pid, int cmd, void *arg, int narg); #ifdef __KERNEL__ +typedef struct { + void (*handler)(int irq, void *arg, struct pt_regs *regs); +} pfm_intr_handler_desc_t; + extern void pfm_save_regs (struct task_struct *); extern void pfm_load_regs (struct task_struct *); @@ -174,9 +180,24 @@ extern void pfm_cleanup_owners (struct task_struct *); extern int pfm_use_debug_registers(struct task_struct *); extern int pfm_release_debug_registers(struct task_struct *); extern int pfm_cleanup_smpl_buf(struct task_struct *); -extern void pfm_syst_wide_update_task(struct task_struct *, int); +extern void pfm_syst_wide_update_task(struct task_struct *, unsigned long info, int is_ctxswin); extern void pfm_ovfl_block_reset(void); -extern void perfmon_init_percpu(void); +extern void pfm_init_percpu(void); + +/* + * hooks to allow VTune/Prospect to cooperate with perfmon. + * (reserved for system wide monitoring modules only) + */ +extern int pfm_install_alternate_syswide_subsystem(pfm_intr_handler_desc_t *h); +extern int pfm_remove_alternate_syswide_subsystem(pfm_intr_handler_desc_t *h); + +/* + * describe the content of the local_cpu_date->pfm_syst_info field + */ +#define PFM_CPUINFO_SYST_WIDE 0x1 /* if set a system wide session exist */ +#define PFM_CPUINFO_DCR_PP 0x2 /* if set the system wide session has started */ +#define PFM_CPUINFO_EXCL_IDLE 0x4 /* the system wide session excludes the idle task */ + #endif /* __KERNEL__ */ diff --git a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h index b4a59a5173cb..83dbb132e4e5 100644 --- a/include/asm-ia64/processor.h +++ b/include/asm-ia64/processor.h @@ -2,7 +2,7 @@ #define _ASM_IA64_PROCESSOR_H /* - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com> @@ -223,7 +223,10 @@ typedef struct { struct siginfo; struct thread_struct { - __u64 flags; /* various thread flags (see IA64_THREAD_*) */ + __u32 flags; /* various thread flags (see IA64_THREAD_*) */ + /* writing on_ustack is performance-critical, so it's worth spending 8 bits on it... */ + __u8 on_ustack; /* executing on user-stacks? */ + __u8 pad[3]; __u64 ksp; /* kernel stack pointer */ __u64 map_base; /* base address for get_unmapped_area() */ __u64 task_size; /* limit for task size */ @@ -277,6 +280,7 @@ struct thread_struct { #define INIT_THREAD { \ .flags = 0, \ + .on_ustack = 0, \ .ksp = 0, \ .map_base = DEFAULT_MAP_BASE, \ .task_size = DEFAULT_TASK_SIZE, \ diff --git a/include/asm-ia64/ptrace.h b/include/asm-ia64/ptrace.h index eb33ef4579f7..92966a334ce3 100644 --- a/include/asm-ia64/ptrace.h +++ b/include/asm-ia64/ptrace.h @@ -2,7 +2,7 @@ #define _ASM_IA64_PTRACE_H /* - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> * @@ -218,6 +218,13 @@ struct switch_stack { # define ia64_task_regs(t) (((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1) # define ia64_psr(regs) ((struct ia64_psr *) &(regs)->cr_ipsr) # define user_mode(regs) (((struct ia64_psr *) &(regs)->cr_ipsr)->cpl != 0) +# define user_stack(task,regs) ((long) regs - (long) task == IA64_STK_OFFSET - sizeof(*regs)) +# define fsys_mode(task,regs) \ + ({ \ + struct task_struct *_task = (task); \ + struct pt_regs *_regs = (regs); \ + !user_mode(_regs) && user_stack(_task, _regs); \ + }) struct task_struct; /* forward decl */ diff --git a/include/asm-ia64/spinlock.h b/include/asm-ia64/spinlock.h index 297e6b09e30d..46c473d80d44 100644 --- a/include/asm-ia64/spinlock.h +++ b/include/asm-ia64/spinlock.h @@ -74,6 +74,27 @@ typedef struct { #define SPIN_LOCK_UNLOCKED (spinlock_t) { 0 } #define spin_lock_init(x) ((x)->lock = 0) +#define DEBUG_SPIN_LOCK 0 + +#if DEBUG_SPIN_LOCK + +#include <ia64intrin.h> + +#define _raw_spin_lock(x) \ +do { \ + unsigned long _timeout = 1000000000; \ + volatile unsigned int _old = 0, _new = 1, *_ptr = &((x)->lock); \ + do { \ + if (_timeout-- == 0) { \ + extern void dump_stack (void); \ + printk("kernel DEADLOCK at %s:%d?\n", __FILE__, __LINE__); \ + dump_stack(); \ + } \ + } while (__sync_val_compare_and_swap(_ptr, _old, _new) != _old); \ +} while (0) + +#else + /* * Streamlined test_and_set_bit(0, (x)). We use test-and-test-and-set * rather than a simple xchg to avoid writing the cache-line when @@ -95,6 +116,8 @@ typedef struct { ";;\n" \ :: "r"(&(x)->lock) : "ar.ccv", "p7", "r2", "r29", "memory") +#endif /* !DEBUG_SPIN_LOCK */ + #define spin_is_locked(x) ((x)->lock != 0) #define _raw_spin_unlock(x) do { barrier(); ((spinlock_t *) x)->lock = 0; } while (0) #define _raw_spin_trylock(x) (cmpxchg_acq(&(x)->lock, 0, 1) == 0) diff --git a/include/asm-ia64/system.h b/include/asm-ia64/system.h index e621c5c08b94..357758463c87 100644 --- a/include/asm-ia64/system.h +++ b/include/asm-ia64/system.h @@ -7,7 +7,7 @@ * on information published in the Processor Abstraction Layer * and the System Abstraction Layer manual. * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com> * Copyright (C) 1999 Don Dugger <don.dugger@intel.com> @@ -17,6 +17,7 @@ #include <asm/kregs.h> #include <asm/page.h> #include <asm/pal.h> +#include <asm/percpu.h> #define KERNEL_START (PAGE_OFFSET + 68*1024*1024) @@ -26,7 +27,6 @@ #ifndef __ASSEMBLY__ -#include <linux/percpu.h> #include <linux/kernel.h> #include <linux/types.h> @@ -117,62 +117,51 @@ ia64_insn_group_barrier (void) */ /* For spinlocks etc */ +/* clearing psr.i is implicitly serialized (visible by next insn) */ +/* setting psr.i requires data serialization */ +#define __local_irq_save(x) __asm__ __volatile__ ("mov %0=psr;;" \ + "rsm psr.i;;" \ + : "=r" (x) :: "memory") +#define __local_irq_disable() __asm__ __volatile__ (";; rsm psr.i;;" ::: "memory") +#define __local_irq_restore(x) __asm__ __volatile__ ("cmp.ne p6,p7=%0,r0;;" \ + "(p6) ssm psr.i;" \ + "(p7) rsm psr.i;;" \ + "(p6) srlz.d" \ + :: "r" ((x) & IA64_PSR_I) \ + : "p6", "p7", "memory") + #ifdef CONFIG_IA64_DEBUG_IRQ extern unsigned long last_cli_ip; -# define local_irq_save(x) \ -do { \ - unsigned long ip, psr; \ - \ - __asm__ __volatile__ ("mov %0=psr;; rsm psr.i;;" : "=r" (psr) :: "memory"); \ - if (psr & (1UL << 14)) { \ - __asm__ ("mov %0=ip" : "=r"(ip)); \ - last_cli_ip = ip; \ - } \ - (x) = psr; \ -} while (0) +# define __save_ip() __asm__ ("mov %0=ip" : "=r" (last_cli_ip)) -# define local_irq_disable() \ -do { \ - unsigned long ip, psr; \ - \ - __asm__ __volatile__ ("mov %0=psr;; rsm psr.i;;" : "=r" (psr) :: "memory"); \ - if (psr & (1UL << 14)) { \ - __asm__ ("mov %0=ip" : "=r"(ip)); \ - last_cli_ip = ip; \ - } \ +# define local_irq_save(x) \ +do { \ + unsigned long psr; \ + \ + __local_irq_save(psr); \ + if (psr & IA64_PSR_I) \ + __save_ip(); \ + (x) = psr; \ } while (0) -# define local_irq_restore(x) \ -do { \ - unsigned long ip, old_psr, psr = (x); \ - \ - __asm__ __volatile__ ("mov %0=psr;" \ - "cmp.ne p6,p7=%1,r0;;" \ - "(p6) ssm psr.i;" \ - "(p7) rsm psr.i;;" \ - "(p6) srlz.d" \ - : "=r" (old_psr) : "r"((psr) & IA64_PSR_I) \ - : "p6", "p7", "memory"); \ - if ((old_psr & IA64_PSR_I) && !(psr & IA64_PSR_I)) { \ - __asm__ ("mov %0=ip" : "=r"(ip)); \ - last_cli_ip = ip; \ - } \ +# define local_irq_disable() do { unsigned long x; local_irq_save(x); } while (0) + +# define local_irq_restore(x) \ +do { \ + unsigned long old_psr, psr = (x); \ + \ + local_save_flags(old_psr); \ + __local_irq_restore(psr); \ + if ((old_psr & IA64_PSR_I) && !(psr & IA64_PSR_I)) \ + __save_ip(); \ } while (0) #else /* !CONFIG_IA64_DEBUG_IRQ */ - /* clearing of psr.i is implicitly serialized (visible by next insn) */ -# define local_irq_save(x) __asm__ __volatile__ ("mov %0=psr;; rsm psr.i;;" \ - : "=r" (x) :: "memory") -# define local_irq_disable() __asm__ __volatile__ (";; rsm psr.i;;" ::: "memory") -/* (potentially) setting psr.i requires data serialization: */ -# define local_irq_restore(x) __asm__ __volatile__ ("cmp.ne p6,p7=%0,r0;;" \ - "(p6) ssm psr.i;" \ - "(p7) rsm psr.i;;" \ - "srlz.d" \ - :: "r"((x) & IA64_PSR_I) \ - : "p6", "p7", "memory") +# define local_irq_save(x) __local_irq_save(x) +# define local_irq_disable() __local_irq_disable() +# define local_irq_restore(x) __local_irq_restore(x) #endif /* !CONFIG_IA64_DEBUG_IRQ */ #define local_irq_enable() __asm__ __volatile__ (";; ssm psr.i;; srlz.d" ::: "memory") @@ -216,8 +205,8 @@ extern void ia64_save_extra (struct task_struct *task); extern void ia64_load_extra (struct task_struct *task); #ifdef CONFIG_PERFMON - DECLARE_PER_CPU(int, pfm_syst_wide); -# define PERFMON_IS_SYSWIDE() (get_cpu_var(pfm_syst_wide) != 0) + DECLARE_PER_CPU(unsigned long, pfm_syst_info); +# define PERFMON_IS_SYSWIDE() (get_cpu_var(pfm_syst_info) & 0x1) #else # define PERFMON_IS_SYSWIDE() (0) #endif diff --git a/include/asm-ia64/tlb.h b/include/asm-ia64/tlb.h index 9370ac9bc997..2edbcee407e7 100644 --- a/include/asm-ia64/tlb.h +++ b/include/asm-ia64/tlb.h @@ -1,7 +1,7 @@ #ifndef _ASM_IA64_TLB_H #define _ASM_IA64_TLB_H /* - * Copyright (C) 2002 Hewlett-Packard Co + * Copyright (C) 2002-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * This file was derived from asm-generic/tlb.h. @@ -70,8 +70,7 @@ extern struct mmu_gather mmu_gathers[NR_CPUS]; * freed pages that where gathered up to this point. */ static inline void -ia64_tlb_flush_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end) +ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end) { unsigned int nr; @@ -197,8 +196,7 @@ tlb_remove_page (struct mmu_gather *tlb, struct page *page) * PTE, not just those pointing to (normal) physical memory. */ static inline void -__tlb_remove_tlb_entry(struct mmu_gather *tlb, - pte_t *ptep, unsigned long address) +__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { if (tlb->start_addr == ~0UL) tlb->start_addr = address; diff --git a/include/asm-ia64/tlbflush.h b/include/asm-ia64/tlbflush.h index 21ca04115809..dd49222e8f08 100644 --- a/include/asm-ia64/tlbflush.h +++ b/include/asm-ia64/tlbflush.h @@ -47,19 +47,22 @@ local_finish_flush_tlb_mm (struct mm_struct *mm) static inline void flush_tlb_mm (struct mm_struct *mm) { + MMU_TRACE('F', smp_processor_id(), mm, mm->context); if (!mm) - return; + goto out; mm->context = 0; if (atomic_read(&mm->mm_users) == 0) - return; /* happens as a result of exit_mmap() */ + goto out; /* happens as a result of exit_mmap() */ #ifdef CONFIG_SMP smp_flush_tlb_mm(mm); #else local_finish_flush_tlb_mm(mm); #endif + out: + MMU_TRACE('f', smp_processor_id(), mm, mm->context); } extern void flush_tlb_range (struct vm_area_struct *vma, unsigned long start, unsigned long end); diff --git a/include/asm-ia64/uaccess.h b/include/asm-ia64/uaccess.h index afe47af459bc..b4bfc4ca9739 100644 --- a/include/asm-ia64/uaccess.h +++ b/include/asm-ia64/uaccess.h @@ -26,7 +26,7 @@ * associated and, if so, sets r8 to -EFAULT and clears r9 to 0 and * then resumes execution at the continuation point. * - * Copyright (C) 1998, 1999, 2001-2002 Hewlett-Packard Co + * Copyright (C) 1998, 1999, 2001-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ @@ -128,38 +128,28 @@ struct __large_struct { unsigned long buf[100]; }; /* We need to declare the __ex_table section before we can use it in .xdata. */ asm (".section \"__ex_table\", \"a\"\n\t.previous"); -#if __GNUC__ >= 3 -# define GAS_HAS_LOCAL_TAGS /* define if gas supports local tags a la [1:] */ -#endif - -#ifdef GAS_HAS_LOCAL_TAGS -# define _LL "[1:]" -#else -# define _LL "1:" -#endif - #define __get_user_64(addr) \ - asm ("\n"_LL"\tld8 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)+4\n" \ - _LL \ + asm ("\n[1:]\tld8 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.+4\n" \ + "[1:]" \ : "=r"(__gu_val), "=r"(__gu_err) : "m"(__m(addr)), "1"(__gu_err)); #define __get_user_32(addr) \ - asm ("\n"_LL"\tld4 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)+4\n" \ - _LL \ + asm ("\n[1:]\tld4 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.+4\n" \ + "[1:]" \ : "=r"(__gu_val), "=r"(__gu_err) : "m"(__m(addr)), "1"(__gu_err)); #define __get_user_16(addr) \ - asm ("\n"_LL"\tld2 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)+4\n" \ - _LL \ + asm ("\n[1:]\tld2 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.+4\n" \ + "[1:]" \ : "=r"(__gu_val), "=r"(__gu_err) : "m"(__m(addr)), "1"(__gu_err)); #define __get_user_8(addr) \ - asm ("\n"_LL"\tld1 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)+4\n" \ - _LL \ + asm ("\n[1:]\tld1 %0=%2%P2\t// %0 and %1 get overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.+4\n" \ + "[1:]" \ : "=r"(__gu_val), "=r"(__gu_err) : "m"(__m(addr)), "1"(__gu_err)); extern void __put_user_unknown (void); @@ -201,30 +191,30 @@ extern void __put_user_unknown (void); */ #define __put_user_64(x,addr) \ asm volatile ( \ - "\n"_LL"\tst8 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)\n" \ - _LL \ + "\n[1:]\tst8 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.\n" \ + "[1:]" \ : "=r"(__pu_err) : "m"(__m(addr)), "rO"(x), "0"(__pu_err)) #define __put_user_32(x,addr) \ asm volatile ( \ - "\n"_LL"\tst4 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)\n" \ - _LL \ + "\n[1:]\tst4 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.\n" \ + "[1:]" \ : "=r"(__pu_err) : "m"(__m(addr)), "rO"(x), "0"(__pu_err)) #define __put_user_16(x,addr) \ asm volatile ( \ - "\n"_LL"\tst2 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)\n" \ - _LL \ + "\n[1:]\tst2 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.\n" \ + "[1:]" \ : "=r"(__pu_err) : "m"(__m(addr)), "rO"(x), "0"(__pu_err)) #define __put_user_8(x,addr) \ asm volatile ( \ - "\n"_LL"\tst1 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ - "\t.xdata4 \"__ex_table\", @gprel(1b), @gprel(1f)\n" \ - _LL \ + "\n[1:]\tst1 %1=%r2%P1\t// %0 gets overwritten by exception handler\n" \ + "\t.xdata4 \"__ex_table\", 1b-., 1f-.\n" \ + "[1:]" \ : "=r"(__pu_err) : "m"(__m(addr)), "rO"(x), "0"(__pu_err)) /* @@ -314,26 +304,22 @@ struct exception_table_entry { int cont; /* gp-relative continuation address; if bit 2 is set, r9 is set to 0 */ }; -struct exception_fixup { - unsigned long cont; /* continuation point (bit 2: clear r9 if set) */ -}; - -extern struct exception_fixup search_exception_table (unsigned long addr); -extern void handle_exception (struct pt_regs *regs, struct exception_fixup fixup); +extern void handle_exception (struct pt_regs *regs, const struct exception_table_entry *e); +extern const struct exception_table_entry *search_exception_tables (unsigned long addr); #ifdef GAS_HAS_LOCAL_TAGS -#define SEARCH_EXCEPTION_TABLE(regs) search_exception_table(regs->cr_iip + ia64_psr(regs)->ri); +# define SEARCH_EXCEPTION_TABLE(regs) search_exception_tables(regs->cr_iip + ia64_psr(regs)->ri) #else -#define SEARCH_EXCEPTION_TABLE(regs) search_exception_table(regs->cr_iip); +# define SEARCH_EXCEPTION_TABLE(regs) search_exception_tables(regs->cr_iip) #endif static inline int done_with_exception (struct pt_regs *regs) { - struct exception_fixup fix; - fix = SEARCH_EXCEPTION_TABLE(regs); - if (fix.cont) { - handle_exception(regs, fix); + const struct exception_table_entry *e; + e = SEARCH_EXCEPTION_TABLE(regs); + if (e) { + handle_exception(regs, e); return 1; } return 0; diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h index 579b4f0d22d2..5517083e6b67 100644 --- a/include/asm-ia64/unistd.h +++ b/include/asm-ia64/unistd.h @@ -4,7 +4,7 @@ /* * IA-64 Linux syscall numbers and inline-functions. * - * Copyright (C) 1998-2002 Hewlett-Packard Co + * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ @@ -223,8 +223,8 @@ #define __NR_sched_setaffinity 1231 #define __NR_sched_getaffinity 1232 #define __NR_set_tid_address 1233 -/* #define __NR_alloc_hugepages 1234 reusable */ -/* #define __NR_free_hugepages 1235 reusable */ +/* 1234 available for reuse */ +/* 1235 available for reuse */ #define __NR_exit_group 1236 #define __NR_lookup_dcookie 1237 #define __NR_io_setup 1238 |