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 */
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Here is where the ball gets rolling as far as the kernel is concerned.
|
|
|
|
* When control is transferred to _start, the bootload has already
|
|
|
|
* loaded us to the correct address. All that's left to do here is
|
|
|
|
* to set up the kernel's global pointer and jump to the kernel
|
|
|
|
* entry point.
|
|
|
|
*
|
|
|
|
* Copyright (C) 1998-2001, 2003, 2005 Hewlett-Packard Co
|
|
|
|
* David Mosberger-Tang <davidm@hpl.hp.com>
|
|
|
|
* Stephane Eranian <eranian@hpl.hp.com>
|
|
|
|
* Copyright (C) 1999 VA Linux Systems
|
|
|
|
* Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
|
|
|
|
* Copyright (C) 1999 Intel Corp.
|
|
|
|
* Copyright (C) 1999 Asit Mallick <Asit.K.Mallick@intel.com>
|
|
|
|
* Copyright (C) 1999 Don Dugger <Don.Dugger@intel.com>
|
|
|
|
* Copyright (C) 2002 Fenghua Yu <fenghua.yu@intel.com>
|
|
|
|
* -Optimize __ia64_save_fpu() and __ia64_load_fpu() for Itanium 2.
|
2005-04-23 05:44:40 +08:00
|
|
|
* Copyright (C) 2004 Ashok Raj <ashok.raj@intel.com>
|
|
|
|
* Support for CPU Hotplug
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
#include <asm/asmmacro.h>
|
|
|
|
#include <asm/fpu.h>
|
|
|
|
#include <asm/kregs.h>
|
|
|
|
#include <asm/mmu_context.h>
|
2005-09-10 04:03:13 +08:00
|
|
|
#include <asm/asm-offsets.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/pal.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/processor.h>
|
|
|
|
#include <asm/ptrace.h>
|
2005-04-23 05:44:40 +08:00
|
|
|
#include <asm/mca_asm.h>
|
2008-05-19 21:13:33 +08:00
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/linkage.h>
|
2016-01-17 14:13:41 +08:00
|
|
|
#include <asm/export.h>
|
2005-04-23 05:44:40 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
#define SAL_PSR_BITS_TO_SET \
|
|
|
|
(IA64_PSR_AC | IA64_PSR_BN | IA64_PSR_MFH | IA64_PSR_MFL)
|
|
|
|
|
|
|
|
#define SAVE_FROM_REG(src, ptr, dest) \
|
|
|
|
mov dest=src;; \
|
|
|
|
st8 [ptr]=dest,0x08
|
|
|
|
|
|
|
|
#define RESTORE_REG(reg, ptr, _tmp) \
|
|
|
|
ld8 _tmp=[ptr],0x08;; \
|
|
|
|
mov reg=_tmp
|
|
|
|
|
|
|
|
#define SAVE_BREAK_REGS(ptr, _idx, _breg, _dest)\
|
|
|
|
mov ar.lc=IA64_NUM_DBG_REGS-1;; \
|
|
|
|
mov _idx=0;; \
|
|
|
|
1: \
|
|
|
|
SAVE_FROM_REG(_breg[_idx], ptr, _dest);; \
|
|
|
|
add _idx=1,_idx;; \
|
|
|
|
br.cloop.sptk.many 1b
|
|
|
|
|
|
|
|
#define RESTORE_BREAK_REGS(ptr, _idx, _breg, _tmp, _lbl)\
|
|
|
|
mov ar.lc=IA64_NUM_DBG_REGS-1;; \
|
|
|
|
mov _idx=0;; \
|
|
|
|
_lbl: RESTORE_REG(_breg[_idx], ptr, _tmp);; \
|
|
|
|
add _idx=1, _idx;; \
|
|
|
|
br.cloop.sptk.many _lbl
|
|
|
|
|
|
|
|
#define SAVE_ONE_RR(num, _reg, _tmp) \
|
|
|
|
movl _tmp=(num<<61);; \
|
|
|
|
mov _reg=rr[_tmp]
|
|
|
|
|
|
|
|
#define SAVE_REGION_REGS(_tmp, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) \
|
|
|
|
SAVE_ONE_RR(0,_r0, _tmp);; \
|
|
|
|
SAVE_ONE_RR(1,_r1, _tmp);; \
|
|
|
|
SAVE_ONE_RR(2,_r2, _tmp);; \
|
|
|
|
SAVE_ONE_RR(3,_r3, _tmp);; \
|
|
|
|
SAVE_ONE_RR(4,_r4, _tmp);; \
|
|
|
|
SAVE_ONE_RR(5,_r5, _tmp);; \
|
|
|
|
SAVE_ONE_RR(6,_r6, _tmp);; \
|
|
|
|
SAVE_ONE_RR(7,_r7, _tmp);;
|
|
|
|
|
|
|
|
#define STORE_REGION_REGS(ptr, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) \
|
|
|
|
st8 [ptr]=_r0, 8;; \
|
|
|
|
st8 [ptr]=_r1, 8;; \
|
|
|
|
st8 [ptr]=_r2, 8;; \
|
|
|
|
st8 [ptr]=_r3, 8;; \
|
|
|
|
st8 [ptr]=_r4, 8;; \
|
|
|
|
st8 [ptr]=_r5, 8;; \
|
|
|
|
st8 [ptr]=_r6, 8;; \
|
|
|
|
st8 [ptr]=_r7, 8;;
|
|
|
|
|
|
|
|
#define RESTORE_REGION_REGS(ptr, _idx1, _idx2, _tmp) \
|
|
|
|
mov ar.lc=0x08-1;; \
|
|
|
|
movl _idx1=0x00;; \
|
|
|
|
RestRR: \
|
|
|
|
dep.z _idx2=_idx1,61,3;; \
|
|
|
|
ld8 _tmp=[ptr],8;; \
|
|
|
|
mov rr[_idx2]=_tmp;; \
|
|
|
|
srlz.d;; \
|
|
|
|
add _idx1=1,_idx1;; \
|
|
|
|
br.cloop.sptk.few RestRR
|
|
|
|
|
2005-04-23 05:46:24 +08:00
|
|
|
#define SET_AREA_FOR_BOOTING_CPU(reg1, reg2) \
|
|
|
|
movl reg1=sal_state_for_booting_cpu;; \
|
|
|
|
ld8 reg2=[reg1];;
|
|
|
|
|
2005-04-23 05:44:40 +08:00
|
|
|
/*
|
|
|
|
* Adjust region registers saved before starting to save
|
|
|
|
* break regs and rest of the states that need to be preserved.
|
|
|
|
*/
|
|
|
|
#define SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(_reg1,_reg2,_pred) \
|
|
|
|
SAVE_FROM_REG(b0,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(b1,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(b2,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(b3,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(b4,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(b5,_reg1,_reg2);; \
|
|
|
|
st8 [_reg1]=r1,0x08;; \
|
|
|
|
st8 [_reg1]=r12,0x08;; \
|
|
|
|
st8 [_reg1]=r13,0x08;; \
|
|
|
|
SAVE_FROM_REG(ar.fpsr,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(ar.pfs,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(ar.rnat,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(ar.unat,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(ar.bspstore,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.dcr,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.iva,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.pta,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.itv,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.pmv,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.cmcv,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.lrr0,_reg1,_reg2);; \
|
|
|
|
SAVE_FROM_REG(cr.lrr1,_reg1,_reg2);; \
|
|
|
|
st8 [_reg1]=r4,0x08;; \
|
|
|
|
st8 [_reg1]=r5,0x08;; \
|
|
|
|
st8 [_reg1]=r6,0x08;; \
|
|
|
|
st8 [_reg1]=r7,0x08;; \
|
|
|
|
st8 [_reg1]=_pred,0x08;; \
|
|
|
|
SAVE_FROM_REG(ar.lc, _reg1, _reg2);; \
|
|
|
|
stf.spill.nta [_reg1]=f2,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f3,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f4,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f5,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f16,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f17,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f18,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f19,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f20,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f21,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f22,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f23,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f24,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f25,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f26,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f27,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f28,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f29,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f30,16;; \
|
|
|
|
stf.spill.nta [_reg1]=f31,16;;
|
|
|
|
|
|
|
|
#else
|
2005-04-23 05:46:24 +08:00
|
|
|
#define SET_AREA_FOR_BOOTING_CPU(a1, a2)
|
|
|
|
#define SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(a1,a2, a3)
|
2005-04-23 05:44:40 +08:00
|
|
|
#define SAVE_REGION_REGS(_tmp, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7)
|
|
|
|
#define STORE_REGION_REGS(ptr, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define SET_ONE_RR(num, pgsize, _tmp1, _tmp2, vhpt) \
|
|
|
|
movl _tmp1=(num << 61);; \
|
|
|
|
mov _tmp2=((ia64_rid(IA64_REGION_ID_KERNEL, (num<<61)) << 8) | (pgsize << 2) | vhpt);; \
|
|
|
|
mov rr[_tmp1]=_tmp2
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-08-01 04:57:52 +08:00
|
|
|
__PAGE_ALIGNED_DATA
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
.global empty_zero_page
|
2016-01-17 14:13:41 +08:00
|
|
|
EXPORT_DATA_SYMBOL_GPL(empty_zero_page)
|
2005-04-17 06:20:36 +08:00
|
|
|
empty_zero_page:
|
|
|
|
.skip PAGE_SIZE
|
|
|
|
|
|
|
|
.global swapper_pg_dir
|
|
|
|
swapper_pg_dir:
|
|
|
|
.skip PAGE_SIZE
|
|
|
|
|
|
|
|
.rodata
|
|
|
|
halt_msg:
|
|
|
|
stringz "Halting kernel\n"
|
|
|
|
|
2009-08-01 04:57:51 +08:00
|
|
|
__REF
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
.global start_ap
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Start the kernel. When the bootloader passes control to _start(), r28
|
|
|
|
* points to the address of the boot parameter area. Execution reaches
|
|
|
|
* here in physical mode.
|
|
|
|
*/
|
|
|
|
GLOBAL_ENTRY(_start)
|
|
|
|
start_ap:
|
|
|
|
.prologue
|
|
|
|
.save rp, r0 // terminate unwind chain with a NULL rp
|
|
|
|
.body
|
|
|
|
|
|
|
|
rsm psr.i | psr.ic
|
|
|
|
;;
|
|
|
|
srlz.i
|
|
|
|
;;
|
2006-09-01 00:34:47 +08:00
|
|
|
{
|
|
|
|
flushrs // must be first insn in group
|
|
|
|
srlz.i
|
|
|
|
}
|
|
|
|
;;
|
2005-04-23 05:44:40 +08:00
|
|
|
/*
|
|
|
|
* Save the region registers, predicate before they get clobbered
|
|
|
|
*/
|
|
|
|
SAVE_REGION_REGS(r2, r8,r9,r10,r11,r12,r13,r14,r15);
|
|
|
|
mov r25=pr;;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Initialize kernel region registers:
|
|
|
|
* rr[0]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[1]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[2]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[3]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[4]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[5]: VHPT enabled, page size = PAGE_SHIFT
|
|
|
|
* rr[6]: VHPT disabled, page size = IA64_GRANULE_SHIFT
|
|
|
|
* rr[7]: VHPT disabled, page size = IA64_GRANULE_SHIFT
|
|
|
|
* We initialize all of them to prevent inadvertently assuming
|
|
|
|
* something about the state of address translation early in boot.
|
|
|
|
*/
|
2005-04-23 05:44:40 +08:00
|
|
|
SET_ONE_RR(0, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(1, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(2, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(3, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(4, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(5, PAGE_SHIFT, r2, r16, 1);;
|
|
|
|
SET_ONE_RR(6, IA64_GRANULE_SHIFT, r2, r16, 0);;
|
|
|
|
SET_ONE_RR(7, IA64_GRANULE_SHIFT, r2, r16, 0);;
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Now pin mappings into the TLB for kernel text and data
|
|
|
|
*/
|
|
|
|
mov r18=KERNEL_TR_PAGE_SHIFT<<2
|
|
|
|
movl r17=KERNEL_START
|
|
|
|
;;
|
|
|
|
mov cr.itir=r18
|
|
|
|
mov cr.ifa=r17
|
|
|
|
mov r16=IA64_TR_KERNEL
|
|
|
|
mov r3=ip
|
|
|
|
movl r18=PAGE_KERNEL
|
|
|
|
;;
|
|
|
|
dep r2=0,r3,0,KERNEL_TR_PAGE_SHIFT
|
|
|
|
;;
|
|
|
|
or r18=r2,r18
|
|
|
|
;;
|
|
|
|
srlz.i
|
|
|
|
;;
|
|
|
|
itr.i itr[r16]=r18
|
|
|
|
;;
|
|
|
|
itr.d dtr[r16]=r18
|
|
|
|
;;
|
|
|
|
srlz.i
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Switch into virtual mode:
|
|
|
|
*/
|
|
|
|
movl r16=(IA64_PSR_IT|IA64_PSR_IC|IA64_PSR_DT|IA64_PSR_RT|IA64_PSR_DFH|IA64_PSR_BN \
|
2014-03-29 05:42:07 +08:00
|
|
|
|IA64_PSR_DI)
|
2005-04-17 06:20:36 +08:00
|
|
|
;;
|
|
|
|
mov cr.ipsr=r16
|
|
|
|
movl r17=1f
|
|
|
|
;;
|
|
|
|
mov cr.iip=r17
|
|
|
|
mov cr.ifs=r0
|
|
|
|
;;
|
|
|
|
rfi
|
|
|
|
;;
|
|
|
|
1: // now we are in virtual mode
|
|
|
|
|
2005-04-23 05:46:24 +08:00
|
|
|
SET_AREA_FOR_BOOTING_CPU(r2, r16);
|
2005-04-23 05:44:40 +08:00
|
|
|
|
|
|
|
STORE_REGION_REGS(r16, r8,r9,r10,r11,r12,r13,r14,r15);
|
|
|
|
SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(r16,r17,r25)
|
|
|
|
;;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
// set IVT entry point---can't access I/O ports without it
|
|
|
|
movl r3=ia64_ivt
|
|
|
|
;;
|
|
|
|
mov cr.iva=r3
|
|
|
|
movl r2=FPSR_DEFAULT
|
|
|
|
;;
|
|
|
|
srlz.i
|
|
|
|
movl gp=__gp
|
|
|
|
|
|
|
|
mov ar.fpsr=r2
|
|
|
|
;;
|
|
|
|
|
|
|
|
#define isAP p2 // are we an Application Processor?
|
|
|
|
#define isBP p3 // are we the Bootstrap Processor?
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
|
|
* Find the init_task for the currently booting CPU. At poweron, and in
|
|
|
|
* UP mode, task_for_booting_cpu is NULL.
|
|
|
|
*/
|
|
|
|
movl r3=task_for_booting_cpu
|
|
|
|
;;
|
|
|
|
ld8 r3=[r3]
|
|
|
|
movl r2=init_task
|
|
|
|
;;
|
|
|
|
cmp.eq isBP,isAP=r3,r0
|
|
|
|
;;
|
|
|
|
(isAP) mov r2=r3
|
|
|
|
#else
|
|
|
|
movl r2=init_task
|
|
|
|
cmp.eq isBP,isAP=r0,r0
|
|
|
|
#endif
|
|
|
|
;;
|
|
|
|
tpa r3=r2 // r3 == phys addr of task struct
|
|
|
|
mov r16=-1
|
|
|
|
(isBP) br.cond.dpnt .load_current // BP stack is on region 5 --- no need to map it
|
|
|
|
|
|
|
|
// load mapping for stack (virtaddr in r2, physaddr in r3)
|
|
|
|
rsm psr.ic
|
|
|
|
movl r17=PAGE_KERNEL
|
|
|
|
;;
|
|
|
|
srlz.d
|
|
|
|
dep r18=0,r3,0,12
|
|
|
|
;;
|
|
|
|
or r18=r17,r18
|
|
|
|
dep r2=-1,r3,61,3 // IMVA of task
|
|
|
|
;;
|
|
|
|
mov r17=rr[r2]
|
|
|
|
shr.u r16=r3,IA64_GRANULE_SHIFT
|
|
|
|
;;
|
|
|
|
dep r17=0,r17,8,24
|
|
|
|
;;
|
|
|
|
mov cr.itir=r17
|
|
|
|
mov cr.ifa=r2
|
|
|
|
|
|
|
|
mov r19=IA64_TR_CURRENT_STACK
|
|
|
|
;;
|
|
|
|
itr.d dtr[r19]=r18
|
|
|
|
;;
|
|
|
|
ssm psr.ic
|
|
|
|
srlz.d
|
|
|
|
;;
|
|
|
|
|
|
|
|
.load_current:
|
|
|
|
// load the "current" pointer (r13) and ar.k6 with the current task
|
|
|
|
mov IA64_KR(CURRENT)=r2 // virtual address
|
|
|
|
mov IA64_KR(CURRENT_STACK)=r16
|
|
|
|
mov r13=r2
|
|
|
|
/*
|
2005-04-23 05:44:40 +08:00
|
|
|
* 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 to be there because time-critical stuff such as the context
|
|
|
|
* switching can be implemented more efficiently (for example, __switch_to()
|
2005-04-17 06:20:36 +08:00
|
|
|
* always sets the psr.dfh bit of the task it is switching to).
|
|
|
|
*/
|
2005-04-23 05:44:40 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
addl r12=IA64_STK_OFFSET-IA64_PT_REGS_SIZE-16,r2
|
|
|
|
addl r2=IA64_RBS_OFFSET,r2 // initialize the RSE
|
|
|
|
mov ar.rsc=0 // place RSE in enforced lazy mode
|
|
|
|
;;
|
|
|
|
loadrs // clear the dirty partition
|
2008-08-13 01:34:20 +08:00
|
|
|
movl r19=__phys_per_cpu_start
|
|
|
|
mov r18=PERCPU_PAGE_SIZE
|
|
|
|
;;
|
|
|
|
#ifndef CONFIG_SMP
|
|
|
|
add r19=r19,r18
|
|
|
|
;;
|
|
|
|
#else
|
|
|
|
(isAP) br.few 2f
|
2008-09-30 07:39:19 +08:00
|
|
|
movl r20=__cpu0_per_cpu
|
2008-08-13 01:34:20 +08:00
|
|
|
;;
|
|
|
|
shr.u r18=r18,3
|
|
|
|
1:
|
2008-09-30 07:39:19 +08:00
|
|
|
ld8 r21=[r19],8;;
|
|
|
|
st8[r20]=r21,8
|
2008-08-13 01:34:20 +08:00
|
|
|
adds r18=-1,r18;;
|
|
|
|
cmp4.lt p7,p6=0,r18
|
|
|
|
(p7) br.cond.dptk.few 1b
|
2008-09-30 07:39:19 +08:00
|
|
|
mov r19=r20
|
|
|
|
;;
|
2008-08-13 01:34:20 +08:00
|
|
|
2:
|
|
|
|
#endif
|
|
|
|
tpa r19=r19
|
|
|
|
;;
|
|
|
|
.pred.rel.mutex isBP,isAP
|
|
|
|
(isBP) mov IA64_KR(PER_CPU_DATA)=r19 // per-CPU base for cpu0
|
|
|
|
(isAP) mov IA64_KR(PER_CPU_DATA)=r0 // clear physical per-CPU base
|
2005-04-17 06:20:36 +08:00
|
|
|
;;
|
|
|
|
mov ar.bspstore=r2 // establish the new RSE stack
|
|
|
|
;;
|
|
|
|
mov ar.rsc=0x3 // place RSE in eager mode
|
|
|
|
|
|
|
|
(isBP) dep r28=-1,r28,61,3 // make address virtual
|
|
|
|
(isBP) movl r2=ia64_boot_param
|
|
|
|
;;
|
|
|
|
(isBP) st8 [r2]=r28 // save the address of the boot param area passed by the bootloader
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
(isAP) br.call.sptk.many rp=start_secondary
|
|
|
|
.ret0:
|
|
|
|
(isAP) br.cond.sptk self
|
|
|
|
#endif
|
|
|
|
|
|
|
|
// This is executed by the bootstrap processor (bsp) only:
|
|
|
|
|
|
|
|
#ifdef CONFIG_IA64_FW_EMU
|
|
|
|
// initialize PAL & SAL emulator:
|
|
|
|
br.call.sptk.many rp=sys_fw_init
|
|
|
|
.ret1:
|
|
|
|
#endif
|
|
|
|
br.call.sptk.many rp=start_kernel
|
|
|
|
.ret2: addl r3=@ltoff(halt_msg),gp
|
|
|
|
;;
|
|
|
|
alloc r2=ar.pfs,8,0,2,0
|
|
|
|
;;
|
|
|
|
ld8 out0=[r3]
|
|
|
|
br.call.sptk.many b0=console_print
|
|
|
|
|
|
|
|
self: hint @pause
|
|
|
|
br.sptk.many self // endless loop
|
|
|
|
END(_start)
|
|
|
|
|
2007-07-21 05:39:24 +08:00
|
|
|
.text
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
GLOBAL_ENTRY(ia64_save_debug_regs)
|
|
|
|
alloc r16=ar.pfs,1,0,0,0
|
|
|
|
mov r20=ar.lc // preserve ar.lc
|
|
|
|
mov ar.lc=IA64_NUM_DBG_REGS-1
|
|
|
|
mov r18=0
|
|
|
|
add r19=IA64_NUM_DBG_REGS*8,in0
|
|
|
|
;;
|
|
|
|
1: mov r16=dbr[r18]
|
|
|
|
#ifdef CONFIG_ITANIUM
|
|
|
|
;;
|
|
|
|
srlz.d
|
|
|
|
#endif
|
|
|
|
mov r17=ibr[r18]
|
|
|
|
add r18=1,r18
|
|
|
|
;;
|
|
|
|
st8.nta [in0]=r16,8
|
|
|
|
st8.nta [r19]=r17,8
|
|
|
|
br.cloop.sptk.many 1b
|
|
|
|
;;
|
|
|
|
mov ar.lc=r20 // restore ar.lc
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(ia64_save_debug_regs)
|
|
|
|
|
|
|
|
GLOBAL_ENTRY(ia64_load_debug_regs)
|
|
|
|
alloc r16=ar.pfs,1,0,0,0
|
|
|
|
lfetch.nta [in0]
|
|
|
|
mov r20=ar.lc // preserve ar.lc
|
|
|
|
add r19=IA64_NUM_DBG_REGS*8,in0
|
|
|
|
mov ar.lc=IA64_NUM_DBG_REGS-1
|
|
|
|
mov r18=-1
|
|
|
|
;;
|
|
|
|
1: ld8.nta r16=[in0],8
|
|
|
|
ld8.nta r17=[r19],8
|
|
|
|
add r18=1,r18
|
|
|
|
;;
|
|
|
|
mov dbr[r18]=r16
|
|
|
|
#ifdef CONFIG_ITANIUM
|
|
|
|
;;
|
|
|
|
srlz.d // Errata 132 (NoFix status)
|
|
|
|
#endif
|
|
|
|
mov ibr[r18]=r17
|
|
|
|
br.cloop.sptk.many 1b
|
|
|
|
;;
|
|
|
|
mov ar.lc=r20 // restore ar.lc
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(ia64_load_debug_regs)
|
|
|
|
|
|
|
|
GLOBAL_ENTRY(__ia64_save_fpu)
|
|
|
|
alloc r2=ar.pfs,1,4,0,0
|
|
|
|
adds loc0=96*16-16,in0
|
|
|
|
adds loc1=96*16-16-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f127,-256
|
|
|
|
stf.spill.nta [loc1]=f119,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f111,-256
|
|
|
|
stf.spill.nta [loc1]=f103,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f95,-256
|
|
|
|
stf.spill.nta [loc1]=f87,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f79,-256
|
|
|
|
stf.spill.nta [loc1]=f71,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f63,-256
|
|
|
|
stf.spill.nta [loc1]=f55,-256
|
|
|
|
adds loc2=96*16-32,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f47,-256
|
|
|
|
stf.spill.nta [loc1]=f39,-256
|
|
|
|
adds loc3=96*16-32-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f126,-256
|
|
|
|
stf.spill.nta [loc3]=f118,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f110,-256
|
|
|
|
stf.spill.nta [loc3]=f102,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f94,-256
|
|
|
|
stf.spill.nta [loc3]=f86,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f78,-256
|
|
|
|
stf.spill.nta [loc3]=f70,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f62,-256
|
|
|
|
stf.spill.nta [loc3]=f54,-256
|
|
|
|
adds loc0=96*16-48,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f46,-256
|
|
|
|
stf.spill.nta [loc3]=f38,-256
|
|
|
|
adds loc1=96*16-48-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f125,-256
|
|
|
|
stf.spill.nta [loc1]=f117,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f109,-256
|
|
|
|
stf.spill.nta [loc1]=f101,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f93,-256
|
|
|
|
stf.spill.nta [loc1]=f85,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f77,-256
|
|
|
|
stf.spill.nta [loc1]=f69,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f61,-256
|
|
|
|
stf.spill.nta [loc1]=f53,-256
|
|
|
|
adds loc2=96*16-64,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f45,-256
|
|
|
|
stf.spill.nta [loc1]=f37,-256
|
|
|
|
adds loc3=96*16-64-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f124,-256
|
|
|
|
stf.spill.nta [loc3]=f116,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f108,-256
|
|
|
|
stf.spill.nta [loc3]=f100,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f92,-256
|
|
|
|
stf.spill.nta [loc3]=f84,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f76,-256
|
|
|
|
stf.spill.nta [loc3]=f68,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f60,-256
|
|
|
|
stf.spill.nta [loc3]=f52,-256
|
|
|
|
adds loc0=96*16-80,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f44,-256
|
|
|
|
stf.spill.nta [loc3]=f36,-256
|
|
|
|
adds loc1=96*16-80-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f123,-256
|
|
|
|
stf.spill.nta [loc1]=f115,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f107,-256
|
|
|
|
stf.spill.nta [loc1]=f99,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f91,-256
|
|
|
|
stf.spill.nta [loc1]=f83,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f75,-256
|
|
|
|
stf.spill.nta [loc1]=f67,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f59,-256
|
|
|
|
stf.spill.nta [loc1]=f51,-256
|
|
|
|
adds loc2=96*16-96,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f43,-256
|
|
|
|
stf.spill.nta [loc1]=f35,-256
|
|
|
|
adds loc3=96*16-96-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f122,-256
|
|
|
|
stf.spill.nta [loc3]=f114,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f106,-256
|
|
|
|
stf.spill.nta [loc3]=f98,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f90,-256
|
|
|
|
stf.spill.nta [loc3]=f82,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f74,-256
|
|
|
|
stf.spill.nta [loc3]=f66,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f58,-256
|
|
|
|
stf.spill.nta [loc3]=f50,-256
|
|
|
|
adds loc0=96*16-112,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f42,-256
|
|
|
|
stf.spill.nta [loc3]=f34,-256
|
|
|
|
adds loc1=96*16-112-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f121,-256
|
|
|
|
stf.spill.nta [loc1]=f113,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f105,-256
|
|
|
|
stf.spill.nta [loc1]=f97,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f89,-256
|
|
|
|
stf.spill.nta [loc1]=f81,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f73,-256
|
|
|
|
stf.spill.nta [loc1]=f65,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f57,-256
|
|
|
|
stf.spill.nta [loc1]=f49,-256
|
|
|
|
adds loc2=96*16-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc0]=f41,-256
|
|
|
|
stf.spill.nta [loc1]=f33,-256
|
|
|
|
adds loc3=96*16-128-128,in0
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f120,-256
|
|
|
|
stf.spill.nta [loc3]=f112,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f104,-256
|
|
|
|
stf.spill.nta [loc3]=f96,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f88,-256
|
|
|
|
stf.spill.nta [loc3]=f80,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f72,-256
|
|
|
|
stf.spill.nta [loc3]=f64,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f56,-256
|
|
|
|
stf.spill.nta [loc3]=f48,-256
|
|
|
|
;;
|
|
|
|
stf.spill.nta [loc2]=f40
|
|
|
|
stf.spill.nta [loc3]=f32
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(__ia64_save_fpu)
|
|
|
|
|
|
|
|
GLOBAL_ENTRY(__ia64_load_fpu)
|
|
|
|
alloc r2=ar.pfs,1,2,0,0
|
|
|
|
adds r3=128,in0
|
|
|
|
adds r14=256,in0
|
|
|
|
adds r15=384,in0
|
|
|
|
mov loc0=512
|
|
|
|
mov loc1=-1024+16
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f32=[in0],loc0
|
|
|
|
ldf.fill.nta f40=[ r3],loc0
|
|
|
|
ldf.fill.nta f48=[r14],loc0
|
|
|
|
ldf.fill.nta f56=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f64=[in0],loc0
|
|
|
|
ldf.fill.nta f72=[ r3],loc0
|
|
|
|
ldf.fill.nta f80=[r14],loc0
|
|
|
|
ldf.fill.nta f88=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f96=[in0],loc1
|
|
|
|
ldf.fill.nta f104=[ r3],loc1
|
|
|
|
ldf.fill.nta f112=[r14],loc1
|
|
|
|
ldf.fill.nta f120=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f33=[in0],loc0
|
|
|
|
ldf.fill.nta f41=[ r3],loc0
|
|
|
|
ldf.fill.nta f49=[r14],loc0
|
|
|
|
ldf.fill.nta f57=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f65=[in0],loc0
|
|
|
|
ldf.fill.nta f73=[ r3],loc0
|
|
|
|
ldf.fill.nta f81=[r14],loc0
|
|
|
|
ldf.fill.nta f89=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f97=[in0],loc1
|
|
|
|
ldf.fill.nta f105=[ r3],loc1
|
|
|
|
ldf.fill.nta f113=[r14],loc1
|
|
|
|
ldf.fill.nta f121=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f34=[in0],loc0
|
|
|
|
ldf.fill.nta f42=[ r3],loc0
|
|
|
|
ldf.fill.nta f50=[r14],loc0
|
|
|
|
ldf.fill.nta f58=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f66=[in0],loc0
|
|
|
|
ldf.fill.nta f74=[ r3],loc0
|
|
|
|
ldf.fill.nta f82=[r14],loc0
|
|
|
|
ldf.fill.nta f90=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f98=[in0],loc1
|
|
|
|
ldf.fill.nta f106=[ r3],loc1
|
|
|
|
ldf.fill.nta f114=[r14],loc1
|
|
|
|
ldf.fill.nta f122=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f35=[in0],loc0
|
|
|
|
ldf.fill.nta f43=[ r3],loc0
|
|
|
|
ldf.fill.nta f51=[r14],loc0
|
|
|
|
ldf.fill.nta f59=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f67=[in0],loc0
|
|
|
|
ldf.fill.nta f75=[ r3],loc0
|
|
|
|
ldf.fill.nta f83=[r14],loc0
|
|
|
|
ldf.fill.nta f91=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f99=[in0],loc1
|
|
|
|
ldf.fill.nta f107=[ r3],loc1
|
|
|
|
ldf.fill.nta f115=[r14],loc1
|
|
|
|
ldf.fill.nta f123=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f36=[in0],loc0
|
|
|
|
ldf.fill.nta f44=[ r3],loc0
|
|
|
|
ldf.fill.nta f52=[r14],loc0
|
|
|
|
ldf.fill.nta f60=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f68=[in0],loc0
|
|
|
|
ldf.fill.nta f76=[ r3],loc0
|
|
|
|
ldf.fill.nta f84=[r14],loc0
|
|
|
|
ldf.fill.nta f92=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f100=[in0],loc1
|
|
|
|
ldf.fill.nta f108=[ r3],loc1
|
|
|
|
ldf.fill.nta f116=[r14],loc1
|
|
|
|
ldf.fill.nta f124=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f37=[in0],loc0
|
|
|
|
ldf.fill.nta f45=[ r3],loc0
|
|
|
|
ldf.fill.nta f53=[r14],loc0
|
|
|
|
ldf.fill.nta f61=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f69=[in0],loc0
|
|
|
|
ldf.fill.nta f77=[ r3],loc0
|
|
|
|
ldf.fill.nta f85=[r14],loc0
|
|
|
|
ldf.fill.nta f93=[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f101=[in0],loc1
|
|
|
|
ldf.fill.nta f109=[ r3],loc1
|
|
|
|
ldf.fill.nta f117=[r14],loc1
|
|
|
|
ldf.fill.nta f125=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f38 =[in0],loc0
|
|
|
|
ldf.fill.nta f46 =[ r3],loc0
|
|
|
|
ldf.fill.nta f54 =[r14],loc0
|
|
|
|
ldf.fill.nta f62 =[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f70 =[in0],loc0
|
|
|
|
ldf.fill.nta f78 =[ r3],loc0
|
|
|
|
ldf.fill.nta f86 =[r14],loc0
|
|
|
|
ldf.fill.nta f94 =[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f102=[in0],loc1
|
|
|
|
ldf.fill.nta f110=[ r3],loc1
|
|
|
|
ldf.fill.nta f118=[r14],loc1
|
|
|
|
ldf.fill.nta f126=[r15],loc1
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f39 =[in0],loc0
|
|
|
|
ldf.fill.nta f47 =[ r3],loc0
|
|
|
|
ldf.fill.nta f55 =[r14],loc0
|
|
|
|
ldf.fill.nta f63 =[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f71 =[in0],loc0
|
|
|
|
ldf.fill.nta f79 =[ r3],loc0
|
|
|
|
ldf.fill.nta f87 =[r14],loc0
|
|
|
|
ldf.fill.nta f95 =[r15],loc0
|
|
|
|
;;
|
|
|
|
ldf.fill.nta f103=[in0]
|
|
|
|
ldf.fill.nta f111=[ r3]
|
|
|
|
ldf.fill.nta f119=[r14]
|
|
|
|
ldf.fill.nta f127=[r15]
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(__ia64_load_fpu)
|
|
|
|
|
|
|
|
GLOBAL_ENTRY(__ia64_init_fpu)
|
|
|
|
stf.spill [sp]=f0 // M3
|
|
|
|
mov f32=f0 // F
|
|
|
|
nop.b 0
|
|
|
|
|
|
|
|
ldfps f33,f34=[sp] // M0
|
|
|
|
ldfps f35,f36=[sp] // M1
|
|
|
|
mov f37=f0 // F
|
|
|
|
;;
|
|
|
|
|
|
|
|
setf.s f38=r0 // M2
|
|
|
|
setf.s f39=r0 // M3
|
|
|
|
mov f40=f0 // F
|
|
|
|
|
|
|
|
ldfps f41,f42=[sp] // M0
|
|
|
|
ldfps f43,f44=[sp] // M1
|
|
|
|
mov f45=f0 // F
|
|
|
|
|
|
|
|
setf.s f46=r0 // M2
|
|
|
|
setf.s f47=r0 // M3
|
|
|
|
mov f48=f0 // F
|
|
|
|
|
|
|
|
ldfps f49,f50=[sp] // M0
|
|
|
|
ldfps f51,f52=[sp] // M1
|
|
|
|
mov f53=f0 // F
|
|
|
|
|
|
|
|
setf.s f54=r0 // M2
|
|
|
|
setf.s f55=r0 // M3
|
|
|
|
mov f56=f0 // F
|
|
|
|
|
|
|
|
ldfps f57,f58=[sp] // M0
|
|
|
|
ldfps f59,f60=[sp] // M1
|
|
|
|
mov f61=f0 // F
|
|
|
|
|
|
|
|
setf.s f62=r0 // M2
|
|
|
|
setf.s f63=r0 // M3
|
|
|
|
mov f64=f0 // F
|
|
|
|
|
|
|
|
ldfps f65,f66=[sp] // M0
|
|
|
|
ldfps f67,f68=[sp] // M1
|
|
|
|
mov f69=f0 // F
|
|
|
|
|
|
|
|
setf.s f70=r0 // M2
|
|
|
|
setf.s f71=r0 // M3
|
|
|
|
mov f72=f0 // F
|
|
|
|
|
|
|
|
ldfps f73,f74=[sp] // M0
|
|
|
|
ldfps f75,f76=[sp] // M1
|
|
|
|
mov f77=f0 // F
|
|
|
|
|
|
|
|
setf.s f78=r0 // M2
|
|
|
|
setf.s f79=r0 // M3
|
|
|
|
mov f80=f0 // F
|
|
|
|
|
|
|
|
ldfps f81,f82=[sp] // M0
|
|
|
|
ldfps f83,f84=[sp] // M1
|
|
|
|
mov f85=f0 // F
|
|
|
|
|
|
|
|
setf.s f86=r0 // M2
|
|
|
|
setf.s f87=r0 // M3
|
|
|
|
mov f88=f0 // F
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When the instructions are cached, it would be faster to initialize
|
|
|
|
* the remaining registers with simply mov instructions (F-unit).
|
|
|
|
* This gets the time down to ~29 cycles. However, this would use up
|
|
|
|
* 33 bundles, whereas continuing with the above pattern yields
|
|
|
|
* 10 bundles and ~30 cycles.
|
|
|
|
*/
|
|
|
|
|
|
|
|
ldfps f89,f90=[sp] // M0
|
|
|
|
ldfps f91,f92=[sp] // M1
|
|
|
|
mov f93=f0 // F
|
|
|
|
|
|
|
|
setf.s f94=r0 // M2
|
|
|
|
setf.s f95=r0 // M3
|
|
|
|
mov f96=f0 // F
|
|
|
|
|
|
|
|
ldfps f97,f98=[sp] // M0
|
|
|
|
ldfps f99,f100=[sp] // M1
|
|
|
|
mov f101=f0 // F
|
|
|
|
|
|
|
|
setf.s f102=r0 // M2
|
|
|
|
setf.s f103=r0 // M3
|
|
|
|
mov f104=f0 // F
|
|
|
|
|
|
|
|
ldfps f105,f106=[sp] // M0
|
|
|
|
ldfps f107,f108=[sp] // M1
|
|
|
|
mov f109=f0 // F
|
|
|
|
|
|
|
|
setf.s f110=r0 // M2
|
|
|
|
setf.s f111=r0 // M3
|
|
|
|
mov f112=f0 // F
|
|
|
|
|
|
|
|
ldfps f113,f114=[sp] // M0
|
|
|
|
ldfps f115,f116=[sp] // M1
|
|
|
|
mov f117=f0 // F
|
|
|
|
|
|
|
|
setf.s f118=r0 // M2
|
|
|
|
setf.s f119=r0 // M3
|
|
|
|
mov f120=f0 // F
|
|
|
|
|
|
|
|
ldfps f121,f122=[sp] // M0
|
|
|
|
ldfps f123,f124=[sp] // M1
|
|
|
|
mov f125=f0 // F
|
|
|
|
|
|
|
|
setf.s f126=r0 // M2
|
|
|
|
setf.s f127=r0 // M3
|
|
|
|
br.ret.sptk.many rp // F
|
|
|
|
END(__ia64_init_fpu)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Switch execution mode from virtual to physical
|
|
|
|
*
|
|
|
|
* Inputs:
|
|
|
|
* r16 = new psr to establish
|
|
|
|
* Output:
|
|
|
|
* r19 = old virtual address of ar.bsp
|
|
|
|
* r20 = old virtual address of sp
|
|
|
|
*
|
|
|
|
* Note: RSE must already be in enforced lazy mode
|
|
|
|
*/
|
|
|
|
GLOBAL_ENTRY(ia64_switch_mode_phys)
|
|
|
|
{
|
|
|
|
rsm psr.i | psr.ic // disable interrupts and interrupt collection
|
|
|
|
mov r15=ip
|
|
|
|
}
|
|
|
|
;;
|
|
|
|
{
|
|
|
|
flushrs // must be first insn in group
|
|
|
|
srlz.i
|
|
|
|
}
|
|
|
|
;;
|
|
|
|
mov cr.ipsr=r16 // set new PSR
|
|
|
|
add r3=1f-ia64_switch_mode_phys,r15
|
|
|
|
|
|
|
|
mov r19=ar.bsp
|
|
|
|
mov r20=sp
|
|
|
|
mov r14=rp // get return address into a general register
|
|
|
|
;;
|
|
|
|
|
|
|
|
// going to physical mode, use tpa to translate virt->phys
|
|
|
|
tpa r17=r19
|
|
|
|
tpa r3=r3
|
|
|
|
tpa sp=sp
|
|
|
|
tpa r14=r14
|
|
|
|
;;
|
|
|
|
|
|
|
|
mov r18=ar.rnat // save ar.rnat
|
|
|
|
mov ar.bspstore=r17 // this steps on ar.rnat
|
|
|
|
mov cr.iip=r3
|
|
|
|
mov cr.ifs=r0
|
|
|
|
;;
|
|
|
|
mov ar.rnat=r18 // restore ar.rnat
|
|
|
|
rfi // must be last insn in group
|
|
|
|
;;
|
|
|
|
1: mov rp=r14
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(ia64_switch_mode_phys)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Switch execution mode from physical to virtual
|
|
|
|
*
|
|
|
|
* Inputs:
|
|
|
|
* r16 = new psr to establish
|
|
|
|
* r19 = new bspstore to establish
|
|
|
|
* r20 = new sp to establish
|
|
|
|
*
|
|
|
|
* Note: RSE must already be in enforced lazy mode
|
|
|
|
*/
|
|
|
|
GLOBAL_ENTRY(ia64_switch_mode_virt)
|
|
|
|
{
|
|
|
|
rsm psr.i | psr.ic // disable interrupts and interrupt collection
|
|
|
|
mov r15=ip
|
|
|
|
}
|
|
|
|
;;
|
|
|
|
{
|
|
|
|
flushrs // must be first insn in group
|
|
|
|
srlz.i
|
|
|
|
}
|
|
|
|
;;
|
|
|
|
mov cr.ipsr=r16 // set new PSR
|
|
|
|
add r3=1f-ia64_switch_mode_virt,r15
|
|
|
|
|
|
|
|
mov r14=rp // get return address into a general register
|
|
|
|
;;
|
|
|
|
|
|
|
|
// going to virtual
|
|
|
|
// - for code addresses, set upper bits of addr to KERNEL_START
|
|
|
|
// - for stack addresses, copy from input argument
|
|
|
|
movl r18=KERNEL_START
|
|
|
|
dep r3=0,r3,KERNEL_TR_PAGE_SHIFT,64-KERNEL_TR_PAGE_SHIFT
|
|
|
|
dep r14=0,r14,KERNEL_TR_PAGE_SHIFT,64-KERNEL_TR_PAGE_SHIFT
|
|
|
|
mov sp=r20
|
|
|
|
;;
|
|
|
|
or r3=r3,r18
|
|
|
|
or r14=r14,r18
|
|
|
|
;;
|
|
|
|
|
|
|
|
mov r18=ar.rnat // save ar.rnat
|
|
|
|
mov ar.bspstore=r19 // this steps on ar.rnat
|
|
|
|
mov cr.iip=r3
|
|
|
|
mov cr.ifs=r0
|
|
|
|
;;
|
|
|
|
mov ar.rnat=r18 // restore ar.rnat
|
|
|
|
rfi // must be last insn in group
|
|
|
|
;;
|
|
|
|
1: mov rp=r14
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(ia64_switch_mode_virt)
|
|
|
|
|
|
|
|
GLOBAL_ENTRY(ia64_delay_loop)
|
|
|
|
.prologue
|
|
|
|
{ nop 0 // work around GAS unwind info generation bug...
|
|
|
|
.save ar.lc,r2
|
|
|
|
mov r2=ar.lc
|
|
|
|
.body
|
|
|
|
;;
|
|
|
|
mov ar.lc=r32
|
|
|
|
}
|
|
|
|
;;
|
|
|
|
// force loop to be 32-byte aligned (GAS bug means we cannot use .align
|
|
|
|
// inside function body without corrupting unwind info).
|
|
|
|
{ nop 0 }
|
|
|
|
1: br.cloop.sptk.few 1b
|
|
|
|
;;
|
|
|
|
mov ar.lc=r2
|
|
|
|
br.ret.sptk.many rp
|
|
|
|
END(ia64_delay_loop)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Return a CPU-local timestamp in nano-seconds. This timestamp is
|
|
|
|
* NOT synchronized across CPUs its return value must never be
|
|
|
|
* compared against the values returned on another CPU. The usage in
|
2013-06-04 15:40:24 +08:00
|
|
|
* kernel/sched/core.c ensures that.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* The return-value of sched_clock() is NOT supposed to wrap-around.
|
|
|
|
* If it did, it would cause some scheduling hiccups (at the worst).
|
|
|
|
* Fortunately, with a 64-bit cycle-counter ticking at 100GHz, even
|
|
|
|
* that would happen only once every 5+ years.
|
|
|
|
*
|
|
|
|
* The code below basically calculates:
|
|
|
|
*
|
|
|
|
* (ia64_get_itc() * local_cpu_data->nsec_per_cyc) >> IA64_NSEC_PER_CYC_SHIFT
|
|
|
|
*
|
|
|
|
* except that the multiplication and the shift are done with 128-bit
|
|
|
|
* intermediate precision so that we can produce a full 64-bit result.
|
|
|
|
*/
|
2009-03-04 20:05:40 +08:00
|
|
|
GLOBAL_ENTRY(ia64_native_sched_clock)
|
2009-10-29 21:34:14 +08:00
|
|
|
addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
|
2005-04-17 06:20:36 +08:00
|
|
|
mov.m r9=ar.itc // fetch cycle-counter (35 cyc)
|
|
|
|
;;
|
|
|
|
ldf8 f8=[r8]
|
|
|
|
;;
|
|
|
|
setf.sig f9=r9 // certain to stall, so issue it _after_ ldf8...
|
|
|
|
;;
|
|
|
|
xmpy.lu f10=f9,f8 // calculate low 64 bits of 128-bit product (4 cyc)
|
|
|
|
xmpy.hu f11=f9,f8 // calculate high 64 bits of 128-bit product
|
|
|
|
;;
|
|
|
|
getf.sig r8=f10 // (5 cyc)
|
|
|
|
getf.sig r9=f11
|
|
|
|
;;
|
|
|
|
shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
|
|
|
|
br.ret.sptk.many rp
|
2009-03-04 20:05:40 +08:00
|
|
|
END(ia64_native_sched_clock)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2012-07-25 13:56:04 +08:00
|
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
|
2017-01-31 11:09:45 +08:00
|
|
|
GLOBAL_ENTRY(cycle_to_nsec)
|
2008-01-29 13:27:30 +08:00
|
|
|
alloc r16=ar.pfs,1,0,0,0
|
2009-10-29 21:34:14 +08:00
|
|
|
addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
|
2008-01-29 13:27:30 +08:00
|
|
|
;;
|
|
|
|
ldf8 f8=[r8]
|
|
|
|
;;
|
|
|
|
setf.sig f9=r32
|
|
|
|
;;
|
|
|
|
xmpy.lu f10=f9,f8 // calculate low 64 bits of 128-bit product (4 cyc)
|
|
|
|
xmpy.hu f11=f9,f8 // calculate high 64 bits of 128-bit product
|
|
|
|
;;
|
|
|
|
getf.sig r8=f10 // (5 cyc)
|
|
|
|
getf.sig r9=f11
|
|
|
|
;;
|
|
|
|
shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
|
|
|
|
br.ret.sptk.many rp
|
2017-01-31 11:09:45 +08:00
|
|
|
END(cycle_to_nsec)
|
2012-07-25 13:56:04 +08:00
|
|
|
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
|
2008-01-29 13:27:30 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifdef CONFIG_IA64_BRL_EMU
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Assembly routines used by brl_emu.c to set preserved register state.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define SET_REG(reg) \
|
|
|
|
GLOBAL_ENTRY(ia64_set_##reg); \
|
|
|
|
alloc r16=ar.pfs,1,0,0,0; \
|
|
|
|
mov reg=r32; \
|
|
|
|
;; \
|
|
|
|
br.ret.sptk.many rp; \
|
|
|
|
END(ia64_set_##reg)
|
|
|
|
|
|
|
|
SET_REG(b1);
|
|
|
|
SET_REG(b2);
|
|
|
|
SET_REG(b3);
|
|
|
|
SET_REG(b4);
|
|
|
|
SET_REG(b5);
|
|
|
|
|
|
|
|
#endif /* CONFIG_IA64_BRL_EMU */
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
2005-04-23 05:44:40 +08:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
GLOBAL_ENTRY(ia64_jump_to_sal)
|
|
|
|
alloc r16=ar.pfs,1,0,0,0;;
|
|
|
|
rsm psr.i | psr.ic
|
|
|
|
{
|
|
|
|
flushrs
|
|
|
|
srlz.i
|
|
|
|
}
|
|
|
|
tpa r25=in0
|
|
|
|
movl r18=tlb_purge_done;;
|
|
|
|
DATA_VA_TO_PA(r18);;
|
|
|
|
mov b1=r18 // Return location
|
|
|
|
movl r18=ia64_do_tlb_purge;;
|
|
|
|
DATA_VA_TO_PA(r18);;
|
|
|
|
mov b2=r18 // doing tlb_flush work
|
|
|
|
mov ar.rsc=0 // Put RSE in enforced lazy, LE mode
|
|
|
|
movl r17=1f;;
|
|
|
|
DATA_VA_TO_PA(r17);;
|
|
|
|
mov cr.iip=r17
|
|
|
|
movl r16=SAL_PSR_BITS_TO_SET;;
|
|
|
|
mov cr.ipsr=r16
|
|
|
|
mov cr.ifs=r0;;
|
[IA64] kdump: Mask MCA/INIT on frozen cpus
Summary:
INIT asserted on kdump kernel invokes INIT handler not only on a
cpu that running on the kdump kernel, but also BSP of the panicked
kernel, because the (badly) frozen BSP can be thawed by INIT.
Description:
The kdump_cpu_freeze() is called on cpus except one that initiates
panic and/or kdump, to stop/offline the cpu (on ia64, it means we
pass control of cpus to SAL, or put them in spinloop). Note that
CPU0(BSP) always go to spinloop, so if panic was happened on an AP,
there are at least 2cpus (= the AP and BSP) which not back to SAL.
On the spinning cpus, interrupts are disabled (rsm psr.i), but INIT
is still interruptible because psr.mc for mask them is not set unless
kdump_cpu_freeze() is not called from MCA/INIT context.
Therefore, assume that a panic was happened on an AP, kdump was
invoked, new INIT handlers for kdump kernel was registered and then
an INIT is asserted. From the viewpoint of SAL, there are 2 online
cpus, so INIT will be delivered to both of them. It likely means
that not only the AP (= a cpu executing kdump) enters INIT handler
which is newly registered, but also BSP (= another cpu spinning in
panicked kernel) enters the same INIT handler. Of course setting of
registers in BSP are still old (for panicked kernel), so what happen
with running handler with wrong setting will be extremely unexpected.
I believe this is not desirable behavior.
How to Reproduce:
Start kdump on one of APs (e.g. cpu1)
# taskset 0x2 echo c > /proc/sysrq-trigger
Then assert INIT after kdump kernel is booted, after new INIT handler
for kdump kernel is registered.
Expected results:
An INIT handler is invoked only on the AP.
Actual results:
An INIT handler is invoked on the AP and BSP.
Sample of results:
I got following console log by asserting INIT after prompt "root:/>".
It seems that two monarchs appeared by one INIT, and one panicked at
last. And it also seems that the panicked one supposed there were
4 online cpus and no one did rendezvous:
:
[ 0 %]dropping to initramfs shell
exiting this shell will reboot your system
root:/> Entered OS INIT handler. PSP=fff301a0 cpu=0 monarch=0
ia64_init_handler: Promoting cpu 0 to monarch.
Delaying for 5 seconds...
All OS INIT slaves have reached rendezvous
Processes interrupted by INIT - 0 (cpu 0 task 0xa000000100af0000)
:
<<snip>>
:
Entered OS INIT handler. PSP=fff301a0 cpu=0 monarch=1
Delaying for 5 seconds...
mlogbuf_finish: printing switched to urgent mode, MCA/INIT might be dodgy or fail.
OS INIT slave did not rendezvous on cpu 1 2 3
INIT swapper 0[0]: bugcheck! 0 [1]
:
<<snip>>
:
Kernel panic - not syncing: Attempted to kill the idle task!
Proposed fix:
To avoid this problem, this patch inserts ia64_set_psr_mc() to mask
INIT on cpus going to be frozen. This masking have no effect if the
kdump_cpu_freeze() is called from INIT handler when kdump_on_init == 1,
because psr.mc is already turned on to 1 before entering OS_INIT.
I confirmed that weird log like above are disappeared after applying
this patch.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Haren Myneni <hbabu@us.ibm.com>
Cc: kexec@lists.infradead.org
Acked-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-08-07 05:51:56 +08:00
|
|
|
rfi;; // note: this unmask MCA/INIT (psr.mc)
|
2005-04-23 05:44:40 +08:00
|
|
|
1:
|
|
|
|
/*
|
|
|
|
* Invalidate all TLB data/inst
|
|
|
|
*/
|
|
|
|
br.sptk.many b2;; // jump to tlb purge code
|
|
|
|
|
|
|
|
tlb_purge_done:
|
|
|
|
RESTORE_REGION_REGS(r25, r17,r18,r19);;
|
|
|
|
RESTORE_REG(b0, r25, r17);;
|
|
|
|
RESTORE_REG(b1, r25, r17);;
|
|
|
|
RESTORE_REG(b2, r25, r17);;
|
|
|
|
RESTORE_REG(b3, r25, r17);;
|
|
|
|
RESTORE_REG(b4, r25, r17);;
|
|
|
|
RESTORE_REG(b5, r25, r17);;
|
|
|
|
ld8 r1=[r25],0x08;;
|
|
|
|
ld8 r12=[r25],0x08;;
|
|
|
|
ld8 r13=[r25],0x08;;
|
|
|
|
RESTORE_REG(ar.fpsr, r25, r17);;
|
|
|
|
RESTORE_REG(ar.pfs, r25, r17);;
|
|
|
|
RESTORE_REG(ar.rnat, r25, r17);;
|
|
|
|
RESTORE_REG(ar.unat, r25, r17);;
|
|
|
|
RESTORE_REG(ar.bspstore, r25, r17);;
|
|
|
|
RESTORE_REG(cr.dcr, r25, r17);;
|
|
|
|
RESTORE_REG(cr.iva, r25, r17);;
|
|
|
|
RESTORE_REG(cr.pta, r25, r17);;
|
2007-12-12 15:28:52 +08:00
|
|
|
srlz.d;; // required not to violate RAW dependency
|
2005-04-23 05:44:40 +08:00
|
|
|
RESTORE_REG(cr.itv, r25, r17);;
|
|
|
|
RESTORE_REG(cr.pmv, r25, r17);;
|
|
|
|
RESTORE_REG(cr.cmcv, r25, r17);;
|
|
|
|
RESTORE_REG(cr.lrr0, r25, r17);;
|
|
|
|
RESTORE_REG(cr.lrr1, r25, r17);;
|
|
|
|
ld8 r4=[r25],0x08;;
|
|
|
|
ld8 r5=[r25],0x08;;
|
|
|
|
ld8 r6=[r25],0x08;;
|
|
|
|
ld8 r7=[r25],0x08;;
|
|
|
|
ld8 r17=[r25],0x08;;
|
|
|
|
mov pr=r17,-1;;
|
|
|
|
RESTORE_REG(ar.lc, r25, r17);;
|
|
|
|
/*
|
|
|
|
* Now Restore floating point regs
|
|
|
|
*/
|
|
|
|
ldf.fill.nta f2=[r25],16;;
|
|
|
|
ldf.fill.nta f3=[r25],16;;
|
|
|
|
ldf.fill.nta f4=[r25],16;;
|
|
|
|
ldf.fill.nta f5=[r25],16;;
|
|
|
|
ldf.fill.nta f16=[r25],16;;
|
|
|
|
ldf.fill.nta f17=[r25],16;;
|
|
|
|
ldf.fill.nta f18=[r25],16;;
|
|
|
|
ldf.fill.nta f19=[r25],16;;
|
|
|
|
ldf.fill.nta f20=[r25],16;;
|
|
|
|
ldf.fill.nta f21=[r25],16;;
|
|
|
|
ldf.fill.nta f22=[r25],16;;
|
|
|
|
ldf.fill.nta f23=[r25],16;;
|
|
|
|
ldf.fill.nta f24=[r25],16;;
|
|
|
|
ldf.fill.nta f25=[r25],16;;
|
|
|
|
ldf.fill.nta f26=[r25],16;;
|
|
|
|
ldf.fill.nta f27=[r25],16;;
|
|
|
|
ldf.fill.nta f28=[r25],16;;
|
|
|
|
ldf.fill.nta f29=[r25],16;;
|
|
|
|
ldf.fill.nta f30=[r25],16;;
|
|
|
|
ldf.fill.nta f31=[r25],16;;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now that we have done all the register restores
|
|
|
|
* we are now ready for the big DIVE to SAL Land
|
|
|
|
*/
|
|
|
|
ssm psr.ic;;
|
|
|
|
srlz.d;;
|
|
|
|
br.ret.sptk.many b0;;
|
|
|
|
END(ia64_jump_to_sal)
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* CONFIG_SMP */
|