linux/arch/sparc/kernel/process_64.c

788 lines
19 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/* arch/sparc64/kernel/process.c
*
* Copyright (C) 1995, 1996, 2008 David S. Miller (davem@davemloft.net)
* Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
* Copyright (C) 1997, 1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <stdarg.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
#include <linux/mm.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-30 06:36:13 +08:00
#include <linux/fs.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/delay.h>
#include <linux/compat.h>
#include <linux/tick.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/perf_event.h>
#include <linux/elfcore.h>
#include <linux/sysrq.h>
#include <linux/nmi.h>
#include <linux/context_tracking.h>
#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/pstate.h>
#include <asm/elf.h>
#include <asm/fpumacro.h>
#include <asm/head.h>
#include <asm/cpudata.h>
#include <asm/mmu_context.h>
#include <asm/unistd.h>
#include <asm/hypervisor.h>
#include <asm/syscalls.h>
#include <asm/irq_regs.h>
#include <asm/smp.h>
#include <asm/pcr.h>
#include "kstack.h"
/* Idle loop support on sparc64. */
void arch_cpu_idle(void)
{
if (tlb_type != hypervisor) {
touch_nmi_watchdog();
local_irq_enable();
} else {
unsigned long pstate;
local_irq_enable();
/* The sun4v sleeping code requires that we have PSTATE.IE cleared over
* the cpu sleep hypervisor call.
*/
__asm__ __volatile__(
"rdpr %%pstate, %0\n\t"
"andn %0, %1, %0\n\t"
"wrpr %0, %%g0, %%pstate"
: "=&r" (pstate)
: "i" (PSTATE_IE));
if (!need_resched() && !cpu_is_offline(smp_processor_id())) {
sun4v_cpu_yield();
/* If resumed by cpu_poke then we need to explicitly
* call scheduler_ipi().
*/
scheduler_poke();
}
/* Re-enable interrupts. */
__asm__ __volatile__(
"rdpr %%pstate, %0\n\t"
"or %0, %1, %0\n\t"
"wrpr %0, %%g0, %%pstate"
: "=&r" (pstate)
: "i" (PSTATE_IE));
}
}
#ifdef CONFIG_HOTPLUG_CPU
void arch_cpu_idle_dead(void)
{
sched_preempt_enable_no_resched();
cpu_play_dead();
}
#endif
#ifdef CONFIG_COMPAT
static void show_regwindow32(struct pt_regs *regs)
{
struct reg_window32 __user *rw;
struct reg_window32 r_w;
mm_segment_t old_fs;
__asm__ __volatile__ ("flushw");
rw = compat_ptr((unsigned int)regs->u_regs[14]);
old_fs = get_fs();
set_fs (USER_DS);
if (copy_from_user (&r_w, rw, sizeof(r_w))) {
set_fs (old_fs);
return;
}
set_fs (old_fs);
printk("l0: %08x l1: %08x l2: %08x l3: %08x "
"l4: %08x l5: %08x l6: %08x l7: %08x\n",
r_w.locals[0], r_w.locals[1], r_w.locals[2], r_w.locals[3],
r_w.locals[4], r_w.locals[5], r_w.locals[6], r_w.locals[7]);
printk("i0: %08x i1: %08x i2: %08x i3: %08x "
"i4: %08x i5: %08x i6: %08x i7: %08x\n",
r_w.ins[0], r_w.ins[1], r_w.ins[2], r_w.ins[3],
r_w.ins[4], r_w.ins[5], r_w.ins[6], r_w.ins[7]);
}
#else
#define show_regwindow32(regs) do { } while (0)
#endif
static void show_regwindow(struct pt_regs *regs)
{
struct reg_window __user *rw;
struct reg_window *rwk;
struct reg_window r_w;
mm_segment_t old_fs;
if ((regs->tstate & TSTATE_PRIV) || !(test_thread_flag(TIF_32BIT))) {
__asm__ __volatile__ ("flushw");
rw = (struct reg_window __user *)
(regs->u_regs[14] + STACK_BIAS);
rwk = (struct reg_window *)
(regs->u_regs[14] + STACK_BIAS);
if (!(regs->tstate & TSTATE_PRIV)) {
old_fs = get_fs();
set_fs (USER_DS);
if (copy_from_user (&r_w, rw, sizeof(r_w))) {
set_fs (old_fs);
return;
}
rwk = &r_w;
set_fs (old_fs);
}
} else {
show_regwindow32(regs);
return;
}
printk("l0: %016lx l1: %016lx l2: %016lx l3: %016lx\n",
rwk->locals[0], rwk->locals[1], rwk->locals[2], rwk->locals[3]);
printk("l4: %016lx l5: %016lx l6: %016lx l7: %016lx\n",
rwk->locals[4], rwk->locals[5], rwk->locals[6], rwk->locals[7]);
printk("i0: %016lx i1: %016lx i2: %016lx i3: %016lx\n",
rwk->ins[0], rwk->ins[1], rwk->ins[2], rwk->ins[3]);
printk("i4: %016lx i5: %016lx i6: %016lx i7: %016lx\n",
rwk->ins[4], rwk->ins[5], rwk->ins[6], rwk->ins[7]);
if (regs->tstate & TSTATE_PRIV)
printk("I7: <%pS>\n", (void *) rwk->ins[7]);
}
void show_regs(struct pt_regs *regs)
{
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
show_regs_print_info(KERN_DEFAULT);
printk("TSTATE: %016lx TPC: %016lx TNPC: %016lx Y: %08x %s\n", regs->tstate,
regs->tpc, regs->tnpc, regs->y, print_tainted());
printk("TPC: <%pS>\n", (void *) regs->tpc);
printk("g0: %016lx g1: %016lx g2: %016lx g3: %016lx\n",
regs->u_regs[0], regs->u_regs[1], regs->u_regs[2],
regs->u_regs[3]);
printk("g4: %016lx g5: %016lx g6: %016lx g7: %016lx\n",
regs->u_regs[4], regs->u_regs[5], regs->u_regs[6],
regs->u_regs[7]);
printk("o0: %016lx o1: %016lx o2: %016lx o3: %016lx\n",
regs->u_regs[8], regs->u_regs[9], regs->u_regs[10],
regs->u_regs[11]);
printk("o4: %016lx o5: %016lx sp: %016lx ret_pc: %016lx\n",
regs->u_regs[12], regs->u_regs[13], regs->u_regs[14],
regs->u_regs[15]);
printk("RPC: <%pS>\n", (void *) regs->u_regs[15]);
show_regwindow(regs);
show_stack(current, (unsigned long *) regs->u_regs[UREG_FP]);
}
union global_cpu_snapshot global_cpu_snapshot[NR_CPUS];
static DEFINE_SPINLOCK(global_cpu_snapshot_lock);
static void __global_reg_self(struct thread_info *tp, struct pt_regs *regs,
int this_cpu)
{
struct global_reg_snapshot *rp;
flushw_all();
rp = &global_cpu_snapshot[this_cpu].reg;
rp->tstate = regs->tstate;
rp->tpc = regs->tpc;
rp->tnpc = regs->tnpc;
rp->o7 = regs->u_regs[UREG_I7];
if (regs->tstate & TSTATE_PRIV) {
struct reg_window *rw;
rw = (struct reg_window *)
(regs->u_regs[UREG_FP] + STACK_BIAS);
if (kstack_valid(tp, (unsigned long) rw)) {
rp->i7 = rw->ins[7];
rw = (struct reg_window *)
(rw->ins[6] + STACK_BIAS);
if (kstack_valid(tp, (unsigned long) rw))
rp->rpc = rw->ins[7];
}
} else {
rp->i7 = 0;
rp->rpc = 0;
}
rp->thread = tp;
}
/* In order to avoid hangs we do not try to synchronize with the
* global register dump client cpus. The last store they make is to
* the thread pointer, so do a short poll waiting for that to become
* non-NULL.
*/
static void __global_reg_poll(struct global_reg_snapshot *gp)
{
int limit = 0;
while (!gp->thread && ++limit < 100) {
barrier();
udelay(1);
}
}
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{
struct thread_info *tp = current_thread_info();
struct pt_regs *regs = get_irq_regs();
unsigned long flags;
int this_cpu, cpu;
if (!regs)
regs = tp->kregs;
spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
this_cpu = raw_smp_processor_id();
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
__global_reg_self(tp, regs, this_cpu);
smp_fetch_global_regs();
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
for_each_cpu(cpu, mask) {
struct global_reg_snapshot *gp;
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
if (exclude_self && cpu == this_cpu)
continue;
gp = &global_cpu_snapshot[cpu].reg;
__global_reg_poll(gp);
tp = gp->thread;
printk("%c CPU[%3d]: TSTATE[%016lx] TPC[%016lx] TNPC[%016lx] TASK[%s:%d]\n",
(cpu == this_cpu ? '*' : ' '), cpu,
gp->tstate, gp->tpc, gp->tnpc,
((tp && tp->task) ? tp->task->comm : "NULL"),
((tp && tp->task) ? tp->task->pid : -1));
if (gp->tstate & TSTATE_PRIV) {
printk(" TPC[%pS] O7[%pS] I7[%pS] RPC[%pS]\n",
(void *) gp->tpc,
(void *) gp->o7,
(void *) gp->i7,
(void *) gp->rpc);
} else {
printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
gp->tpc, gp->o7, gp->i7, gp->rpc);
}
touch_nmi_watchdog();
}
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
spin_unlock_irqrestore(&global_cpu_snapshot_lock, flags);
}
#ifdef CONFIG_MAGIC_SYSRQ
static void sysrq_handle_globreg(int key)
{
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
trigger_all_cpu_backtrace();
}
static struct sysrq_key_op sparc_globalreg_op = {
.handler = sysrq_handle_globreg,
.help_msg = "global-regs(y)",
.action_msg = "Show Global CPU Regs",
};
static void __global_pmu_self(int this_cpu)
{
struct global_pmu_snapshot *pp;
int i, num;
if (!pcr_ops)
return;
pp = &global_cpu_snapshot[this_cpu].pmu;
num = 1;
if (tlb_type == hypervisor &&
sun4v_chip_type >= SUN4V_CHIP_NIAGARA4)
num = 4;
for (i = 0; i < num; i++) {
pp->pcr[i] = pcr_ops->read_pcr(i);
pp->pic[i] = pcr_ops->read_pic(i);
}
}
static void __global_pmu_poll(struct global_pmu_snapshot *pp)
{
int limit = 0;
while (!pp->pcr[0] && ++limit < 100) {
barrier();
udelay(1);
}
}
static void pmu_snapshot_all_cpus(void)
{
unsigned long flags;
int this_cpu, cpu;
spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
this_cpu = raw_smp_processor_id();
__global_pmu_self(this_cpu);
smp_fetch_global_pmu();
for_each_online_cpu(cpu) {
struct global_pmu_snapshot *pp = &global_cpu_snapshot[cpu].pmu;
__global_pmu_poll(pp);
printk("%c CPU[%3d]: PCR[%08lx:%08lx:%08lx:%08lx] PIC[%08lx:%08lx:%08lx:%08lx]\n",
(cpu == this_cpu ? '*' : ' '), cpu,
pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
touch_nmi_watchdog();
}
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
spin_unlock_irqrestore(&global_cpu_snapshot_lock, flags);
}
static void sysrq_handle_globpmu(int key)
{
pmu_snapshot_all_cpus();
}
static struct sysrq_key_op sparc_globalpmu_op = {
.handler = sysrq_handle_globpmu,
.help_msg = "global-pmu(x)",
.action_msg = "Show Global PMU Regs",
};
static int __init sparc_sysrq_init(void)
{
int ret = register_sysrq_key('y', &sparc_globalreg_op);
if (!ret)
ret = register_sysrq_key('x', &sparc_globalpmu_op);
return ret;
}
core_initcall(sparc_sysrq_init);
#endif
/* Free current thread data structures etc.. */
exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Jonas Bonn <jonas@southpole.se> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:20 +08:00
void exit_thread(struct task_struct *tsk)
{
exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Jonas Bonn <jonas@southpole.se> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:20 +08:00
struct thread_info *t = task_thread_info(tsk);
if (t->utraps) {
if (t->utraps[0] < 2)
kfree (t->utraps);
else
t->utraps[0]--;
}
}
void flush_thread(void)
{
struct thread_info *t = current_thread_info();
struct mm_struct *mm;
mm = t->task->mm;
if (mm)
tsb_context_switch(mm);
set_thread_wsaved(0);
/* Clear FPU register state. */
t->fpsaved[0] = 0;
}
/* It's a bit more tricky when 64-bit tasks are involved... */
static unsigned long clone_stackframe(unsigned long csp, unsigned long psp)
{
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
bool stack_64bit = test_thread_64bit_stack(psp);
unsigned long fp, distance, rval;
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
if (stack_64bit) {
csp += STACK_BIAS;
psp += STACK_BIAS;
__get_user(fp, &(((struct reg_window __user *)psp)->ins[6]));
fp += STACK_BIAS;
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
if (test_thread_flag(TIF_32BIT))
fp &= 0xffffffff;
} else
__get_user(fp, &(((struct reg_window32 __user *)psp)->ins[6]));
/* Now align the stack as this is mandatory in the Sparc ABI
* due to how register windows work. This hides the
* restriction from thread libraries etc.
*/
csp &= ~15UL;
distance = fp - psp;
rval = (csp - distance);
if (copy_in_user((void __user *) rval, (void __user *) psp, distance))
rval = 0;
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
else if (!stack_64bit) {
if (put_user(((u32)csp),
&(((struct reg_window32 __user *)rval)->ins[6])))
rval = 0;
} else {
if (put_user(((u64)csp - STACK_BIAS),
&(((struct reg_window __user *)rval)->ins[6])))
rval = 0;
else
rval = rval - STACK_BIAS;
}
return rval;
}
/* Standard stuff. */
static inline void shift_window_buffer(int first_win, int last_win,
struct thread_info *t)
{
int i;
for (i = first_win; i < last_win; i++) {
t->rwbuf_stkptrs[i] = t->rwbuf_stkptrs[i+1];
memcpy(&t->reg_window[i], &t->reg_window[i+1],
sizeof(struct reg_window));
}
}
void synchronize_user_stack(void)
{
struct thread_info *t = current_thread_info();
unsigned long window;
flush_user_windows();
if ((window = get_thread_wsaved()) != 0) {
window -= 1;
do {
struct reg_window *rwin = &t->reg_window[window];
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
int winsize = sizeof(struct reg_window);
unsigned long sp;
sp = t->rwbuf_stkptrs[window];
if (test_thread_64bit_stack(sp))
sp += STACK_BIAS;
else
winsize = sizeof(struct reg_window32);
if (!copy_to_user((char __user *)sp, rwin, winsize)) {
shift_window_buffer(window, get_thread_wsaved() - 1, t);
set_thread_wsaved(get_thread_wsaved() - 1);
}
} while (window--);
}
}
static void stack_unaligned(unsigned long sp)
{
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp, 0, current);
}
void fault_in_user_windows(void)
{
struct thread_info *t = current_thread_info();
unsigned long window;
flush_user_windows();
window = get_thread_wsaved();
if (likely(window != 0)) {
window -= 1;
do {
struct reg_window *rwin = &t->reg_window[window];
sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. The Montgomery Multiply, Montgomery Square, and Multiple-Precision Multiply instructions work by loading a combination of the floating point and multiple register windows worth of integer registers with the inputs. These values are 64-bit. But for 32-bit userland processes we only save the low 32-bits of each integer register during a register spill. This is because the register window save area is in the user stack and has a fixed layout. Therefore, the only way to use these instruction in 32-bit mode is to perform the following sequence: 1) Load the top-32bits of a choosen integer register with a sentinel, say "-1". This will be in the outer-most register window. The idea is that we're trying to see if the outer-most register window gets spilled, and thus the 64-bit values were truncated. 2) Load all the inputs for the montmul/montsqr/mpmul instruction, down to the inner-most register window. 3) Execute the opcode. 4) Traverse back up to the outer-most register window. 5) Check the sentinel, if it's still "-1" store the results. Otherwise retry the entire sequence. This retry is extremely troublesome. If you're just unlucky and an interrupt or other trap happens, it'll push that outer-most window to the stack and clear the sentinel when we restore it. We could retry forever and never make forward progress if interrupts arrive at a fast enough rate (consider perf events as one example). So we have do limited retries and fallback to software which is extremely non-deterministic. Luckily it's very straightforward to provide a mechanism to let 32-bit applications use a 64-bit stack. Stacks in 64-bit mode are biased by 2047 bytes, which means that the lowest bit is set in the actual %sp register value. So if we see bit zero set in a 32-bit application's stack we treat it like a 64-bit stack. Runtime detection of such a facility is tricky, and cumbersome at best. For example, just trying to use a biased stack and seeing if it works is hard to recover from (the signal handler will need to use an alt stack, plus something along the lines of longjmp). Therefore, we add a system call to report a bitmask of arch specific features like this in a cheap and less hairy way. With help from Andy Polyakov. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 06:18:37 +08:00
int winsize = sizeof(struct reg_window);
unsigned long sp;
sp = t->rwbuf_stkptrs[window];
if (test_thread_64bit_stack(sp))
sp += STACK_BIAS;
else
winsize = sizeof(struct reg_window32);
if (unlikely(sp & 0x7UL))
stack_unaligned(sp);
if (unlikely(copy_to_user((char __user *)sp,
rwin, winsize)))
goto barf;
} while (window--);
}
set_thread_wsaved(0);
return;
barf:
set_thread_wsaved(window + 1);
user_exit();
do_exit(SIGILL);
}
asmlinkage long sparc_do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size)
{
int __user *parent_tid_ptr, *child_tid_ptr;
unsigned long orig_i1 = regs->u_regs[UREG_I1];
long ret;
#ifdef CONFIG_COMPAT
if (test_thread_flag(TIF_32BIT)) {
parent_tid_ptr = compat_ptr(regs->u_regs[UREG_I2]);
child_tid_ptr = compat_ptr(regs->u_regs[UREG_I4]);
} else
#endif
{
parent_tid_ptr = (int __user *) regs->u_regs[UREG_I2];
child_tid_ptr = (int __user *) regs->u_regs[UREG_I4];
}
ret = do_fork(clone_flags, stack_start, stack_size,
parent_tid_ptr, child_tid_ptr);
/* If we get an error and potentially restart the system
* call, we're screwed because copy_thread() clobbered
* the parent's %o1. So detect that case and restore it
* here.
*/
if ((unsigned long)ret >= -ERESTART_RESTARTBLOCK)
regs->u_regs[UREG_I1] = orig_i1;
return ret;
}
/* Copy a Sparc thread. The fork() return value conventions
* under SunOS are nothing short of bletcherous:
* Parent --> %o0 == childs pid, %o1 == 0
* Child --> %o0 == parents pid, %o1 == 1
*/
int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p)
{
struct thread_info *t = task_thread_info(p);
struct pt_regs *regs = current_pt_regs();
struct sparc_stackf *parent_sf;
unsigned long child_stack_sz;
char *child_trap_frame;
/* Calculate offset to stack_frame & pt_regs */
child_stack_sz = (STACKFRAME_SZ + TRACEREG_SZ);
child_trap_frame = (task_stack_page(p) +
(THREAD_SIZE - child_stack_sz));
t->new_child = 1;
t->ksp = ((unsigned long) child_trap_frame) - STACK_BIAS;
t->kregs = (struct pt_regs *) (child_trap_frame +
sizeof(struct sparc_stackf));
t->fpsaved[0] = 0;
if (unlikely(p->flags & PF_KTHREAD)) {
memset(child_trap_frame, 0, child_stack_sz);
__thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] =
(current_pt_regs()->tstate + 1) & TSTATE_CWP;
t->current_ds = ASI_P;
t->kregs->u_regs[UREG_G1] = sp; /* function */
t->kregs->u_regs[UREG_G2] = arg;
return 0;
}
parent_sf = ((struct sparc_stackf *) regs) - 1;
memcpy(child_trap_frame, parent_sf, child_stack_sz);
if (t->flags & _TIF_32BIT) {
sp &= 0x00000000ffffffffUL;
regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
}
t->kregs->u_regs[UREG_FP] = sp;
__thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] =
(regs->tstate + 1) & TSTATE_CWP;
t->current_ds = ASI_AIUS;
if (sp != regs->u_regs[UREG_FP]) {
unsigned long csp;
csp = clone_stackframe(sp, regs->u_regs[UREG_FP]);
if (!csp)
return -EFAULT;
t->kregs->u_regs[UREG_FP] = csp;
}
if (t->utraps)
t->utraps[0]++;
/* Set the return value for the child. */
t->kregs->u_regs[UREG_I0] = current->pid;
t->kregs->u_regs[UREG_I1] = 1;
/* Set the second return value for the parent. */
regs->u_regs[UREG_I1] = 0;
if (clone_flags & CLONE_SETTLS)
t->kregs->u_regs[UREG_G7] = regs->u_regs[UREG_I3];
return 0;
}
/* TIF_MCDPER in thread info flags for current task is updated lazily upon
* a context switch. Update this flag in current task's thread flags
* before dup so the dup'd task will inherit the current TIF_MCDPER flag.
*/
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
if (adi_capable()) {
register unsigned long tmp_mcdper;
__asm__ __volatile__(
".word 0x83438000\n\t" /* rd %mcdper, %g1 */
"mov %%g1, %0\n\t"
: "=r" (tmp_mcdper)
:
: "g1");
if (tmp_mcdper)
set_thread_flag(TIF_MCDPER);
else
clear_thread_flag(TIF_MCDPER);
}
*dst = *src;
return 0;
}
typedef struct {
union {
unsigned int pr_regs[32];
unsigned long pr_dregs[16];
} pr_fr;
unsigned int __unused;
unsigned int pr_fsr;
unsigned char pr_qcnt;
unsigned char pr_q_entrysize;
unsigned char pr_en;
unsigned int pr_q[64];
} elf_fpregset_t32;
/*
* fill in the fpu structure for a core dump.
*/
int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs)
{
unsigned long *kfpregs = current_thread_info()->fpregs;
unsigned long fprs = current_thread_info()->fpsaved[0];
if (test_thread_flag(TIF_32BIT)) {
elf_fpregset_t32 *fpregs32 = (elf_fpregset_t32 *)fpregs;
if (fprs & FPRS_DL)
memcpy(&fpregs32->pr_fr.pr_regs[0], kfpregs,
sizeof(unsigned int) * 32);
else
memset(&fpregs32->pr_fr.pr_regs[0], 0,
sizeof(unsigned int) * 32);
fpregs32->pr_qcnt = 0;
fpregs32->pr_q_entrysize = 8;
memset(&fpregs32->pr_q[0], 0,
(sizeof(unsigned int) * 64));
if (fprs & FPRS_FEF) {
fpregs32->pr_fsr = (unsigned int) current_thread_info()->xfsr[0];
fpregs32->pr_en = 1;
} else {
fpregs32->pr_fsr = 0;
fpregs32->pr_en = 0;
}
} else {
if(fprs & FPRS_DL)
memcpy(&fpregs->pr_regs[0], kfpregs,
sizeof(unsigned int) * 32);
else
memset(&fpregs->pr_regs[0], 0,
sizeof(unsigned int) * 32);
if(fprs & FPRS_DU)
memcpy(&fpregs->pr_regs[16], kfpregs+16,
sizeof(unsigned int) * 32);
else
memset(&fpregs->pr_regs[16], 0,
sizeof(unsigned int) * 32);
if(fprs & FPRS_FEF) {
fpregs->pr_fsr = current_thread_info()->xfsr[0];
fpregs->pr_gsr = current_thread_info()->gsr[0];
} else {
fpregs->pr_fsr = fpregs->pr_gsr = 0;
}
fpregs->pr_fprs = fprs;
}
return 1;
}
EXPORT_SYMBOL(dump_fpu);
unsigned long get_wchan(struct task_struct *task)
{
unsigned long pc, fp, bias = 0;
struct thread_info *tp;
struct reg_window *rw;
unsigned long ret = 0;
int count = 0;
if (!task || task == current ||
task->state == TASK_RUNNING)
goto out;
tp = task_thread_info(task);
bias = STACK_BIAS;
fp = task_thread_info(task)->ksp + bias;
do {
if (!kstack_valid(tp, fp))
break;
rw = (struct reg_window *) fp;
pc = rw->ins[7];
if (!in_sched_functions(pc)) {
ret = pc;
goto out;
}
fp = rw->ins[6] + bias;
} while (++count < 16);
out:
return ret;
}