UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/ia64/kernel/head.S

1171 lines
28 KiB
ArmAsm
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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.
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-23 05:44:40 +08:00
* Copyright (C) 2004 Ashok Raj <ashok.raj@intel.com>
* Support for CPU Hotplug
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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>
kbuild: ia64 use generic asm-offsets.h support Delete obsolete stuff from arch Makefile Rename file to asm-offsets.h The trick used in the arch Makefile to circumvent the circular dependency is kept. Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
2005-09-10 04:03:13 +08:00
#include <asm/asm-offsets.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <asm/pal.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-23 05:44:40 +08:00
#include <asm/mca_asm.h>
[IA64] pvops: add an early setup hook for pv_ops. This patch adds a setup hook in the very early boot sequence before start_kernel() to initialize paravirtualization stuff. The hook will be set by each pv loader code or by using multi entry point. Signed-off-by: Qing He <qing.he@intel.com> Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp> Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-05-19 21:13:33 +08:00
#include <linux/init.h>
#include <linux/linkage.h>
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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
[IA64] Fix build errors for !HOTPLUG case. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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];;
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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
[IA64] Fix build errors for !HOTPLUG case. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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)
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[IA64] Use standard macros for page-aligned data. Signed-off-by: Nelson Elhage <nelhage@ksplice.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-08-01 04:57:52 +08:00
__PAGE_ALIGNED_DATA
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.global empty_zero_page
empty_zero_page:
.skip PAGE_SIZE
.global swapper_pg_dir
swapper_pg_dir:
.skip PAGE_SIZE
.rodata
halt_msg:
stringz "Halting kernel\n"
[IA64] Use .ref.text, not .text.init for start_ap. It seems that start_ap doesn't need to be in a special location in the kernel, but it references some init code so it should be in .ref.text. Since this is the only thing in the .text.head section, eliminate .text.head from the linker script. Signed-off-by: Tim Abbott <tabbott@ksplice.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-08-01 04:57:51 +08:00
__REF
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
;;
[IA64] Save register stack contents on cpu start The SN PROM uses the register stack in the slave loop. The contents must be preserved for the OS to return to the slave loop via offlining a cpu or for kexec. A 'flushrs" is needed to force the stack to be written to memory prior to changing bspstore. Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2006-09-01 00:34:47 +08:00
{
flushrs // must be first insn in group
srlz.i
}
;;
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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;;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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.
*/
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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);;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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 \
[IA64] Change default PSR.ac from '1' to '0' (Fix erratum #237) April 2014 Itanium processor specification update: http://www.intel.com/content/www/us/en/processors/itanium/itanium-specification-update.html describes this erratum: ========================================================================= 237. Under a complex set of conditions, store to load forwarding for a sub 8-byte load may complete incorrectly Problem: A load instruction may complete incorrectly when a code sequence using 4-byte or smaller load and store operations to the same address is executed in combination with specific timing of all the following concurrent conditions: store to load forwarding, alignment checking enabled, a mis-predicted branch, and complex cache utilization activity. Implication: The affected sub 8-byte instruction may complete incorrectly resulting in unpredictable system behavior. There is an extremely low probability of exposure due to the significant number of complex microarchitectural concurrent conditions required to encounter the erratum. Workaround: Set PSR.ac = 0 to completely avoid the erratum. Disabling Hyper-Threading will significantly reduce exposure to the conditions that contribute to encountering the erratum. Status: See the Summary Table of Changes for the affected steppings. ========================================================================= [Table of changes essentially lists all models from McKinley to Tukwila] The PSR.ac bit controls whether the processor will always generate an unaligned reference trap (0x5a00) for a misaligned data access (when PSR.ac=1) or if it will let the access succeed when running on a cpu that implements logic to handle some unaligned accesses. Way back in 2008 in commit b704882e70d87d7f56db5ff17e2253f3fa90e4f3 [IA64] Rationalize kernel mode alignment checking we made the decision to always enable strict checking. We were already doing so in trap/interrupt context because the common preamble code set this bit - but the rest of supervisor code (and by inheritance user code) ran with PSR.ac=0. We now reverse that decision and set PSR.ac=0 everywhere in the kernel (also inherited by user processes). This will avoid the erratum using the method described in the Itanium specification update. Net effect for users is that the processor will handle unaligned access when it can (typically with a tiny performance bubble in the pipeline ... but much less invasive than taking a trap and having the OS perform the access). Signed-off-by: Tony Luck <tony.luck@intel.com>
2014-03-29 05:42:07 +08:00
|IA64_PSR_DI)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
[IA64] Fix build errors for !HOTPLUG case. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-23 05:46:24 +08:00
SET_AREA_FOR_BOOTING_CPU(r2, r16);
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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)
;;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
/*
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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()
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
* always sets the psr.dfh bit of the task it is switching to).
*/
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-23 05:44:40 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
[IA64] Ensure cpu0 can access per-cpu variables in early boot code ia64 handles per-cpu variables a litle differently from other architectures in that it maps the physical memory allocated for each cpu at a constant virtual address (0xffffffffffff0000). This mapping is not enabled until the architecture specific cpu_init() function is run, which causes problems since some generic code is run before this point. In particular when CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to per-cpu memory at the first printk() call so the boot will fail without the kernel printing anything to the console. Fix this by allocating percpu memory for cpu0 in the kernel data section and doing all initialization to enable percpu access in head.S before calling any generic code. Other cpus must take care not to access per-cpu variables too early, but their code path from start_secondary() to cpu_init() is all in arch/ia64 Signed-off-by: Tony Luck <tony.luck@intel.com>
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
[IA64] Put the space for cpu0 per-cpu area into .data section Initial fix for making sure that we can access percpu variables in all C code (commit: 10617bbe84628eb18ab5f723d3ba35005adde143) inadvertantly allocated the memory in the "percpu" section of the vmlinux ELF executable. This confused kexec/dump. Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-09-30 07:39:19 +08:00
movl r20=__cpu0_per_cpu
[IA64] Ensure cpu0 can access per-cpu variables in early boot code ia64 handles per-cpu variables a litle differently from other architectures in that it maps the physical memory allocated for each cpu at a constant virtual address (0xffffffffffff0000). This mapping is not enabled until the architecture specific cpu_init() function is run, which causes problems since some generic code is run before this point. In particular when CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to per-cpu memory at the first printk() call so the boot will fail without the kernel printing anything to the console. Fix this by allocating percpu memory for cpu0 in the kernel data section and doing all initialization to enable percpu access in head.S before calling any generic code. Other cpus must take care not to access per-cpu variables too early, but their code path from start_secondary() to cpu_init() is all in arch/ia64 Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-08-13 01:34:20 +08:00
;;
shr.u r18=r18,3
1:
[IA64] Put the space for cpu0 per-cpu area into .data section Initial fix for making sure that we can access percpu variables in all C code (commit: 10617bbe84628eb18ab5f723d3ba35005adde143) inadvertantly allocated the memory in the "percpu" section of the vmlinux ELF executable. This confused kexec/dump. Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-09-30 07:39:19 +08:00
ld8 r21=[r19],8;;
st8[r20]=r21,8
[IA64] Ensure cpu0 can access per-cpu variables in early boot code ia64 handles per-cpu variables a litle differently from other architectures in that it maps the physical memory allocated for each cpu at a constant virtual address (0xffffffffffff0000). This mapping is not enabled until the architecture specific cpu_init() function is run, which causes problems since some generic code is run before this point. In particular when CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to per-cpu memory at the first printk() call so the boot will fail without the kernel printing anything to the console. Fix this by allocating percpu memory for cpu0 in the kernel data section and doing all initialization to enable percpu access in head.S before calling any generic code. Other cpus must take care not to access per-cpu variables too early, but their code path from start_secondary() to cpu_init() is all in arch/ia64 Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-08-13 01:34:20 +08:00
adds r18=-1,r18;;
cmp4.lt p7,p6=0,r18
(p7) br.cond.dptk.few 1b
[IA64] Put the space for cpu0 per-cpu area into .data section Initial fix for making sure that we can access percpu variables in all C code (commit: 10617bbe84628eb18ab5f723d3ba35005adde143) inadvertantly allocated the memory in the "percpu" section of the vmlinux ELF executable. This confused kexec/dump. Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-09-30 07:39:19 +08:00
mov r19=r20
;;
[IA64] Ensure cpu0 can access per-cpu variables in early boot code ia64 handles per-cpu variables a litle differently from other architectures in that it maps the physical memory allocated for each cpu at a constant virtual address (0xffffffffffff0000). This mapping is not enabled until the architecture specific cpu_init() function is run, which causes problems since some generic code is run before this point. In particular when CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to per-cpu memory at the first printk() call so the boot will fail without the kernel printing anything to the console. Fix this by allocating percpu memory for cpu0 in the kernel data section and doing all initialization to enable percpu access in head.S before calling any generic code. Other cpus must take care not to access per-cpu variables too early, but their code path from start_secondary() to cpu_init() is all in arch/ia64 Signed-off-by: Tony Luck <tony.luck@intel.com>
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
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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)
[IA64] fix section mismatch warnings In 741f98fe298a73c9d47ed53703c1279a29718581 Sam added full checking across the entire vmlinux image. This flushed out a dozen new section mismatch warnings. Start the whack-a-mole game again to stomp them out. Signed-off-by: Tony Luck <tony.luck@intel.com>
2007-07-21 05:39:24 +08:00
.text
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
sched: Rename sched.c as sched/core.c in comments and Documentation Most of the stuff from kernel/sched.c was moved to kernel/sched/core.c long time back and the comments/Documentation never got updated. I figured it out when I was going through sched-domains.txt and so thought of fixing it globally. I haven't crossed check if the stuff that is referenced in sched/core.c by all these files is still present and hasn't changed as that wasn't the motive behind this patch. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/cdff76a265326ab8d71922a1db5be599f20aad45.1370329560.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-04 15:40:24 +08:00
* kernel/sched/core.c ensures that.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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.
*/
ia64/pv_ops/pv_time_ops: add sched_clock hook. add sched_clock() hook to paravirtualize sched_clock(). ia64 sched_clock() is based on ar.itc which isn't stable on virtualized environment because vcpu may move around on pcpus. So it needs paravirtualization. Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp> Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-03-04 20:05:40 +08:00
GLOBAL_ENTRY(ia64_native_sched_clock)
percpu: make percpu symbols in ia64 unique This patch updates percpu related symbols in ia64 such that percpu symbols are unique and don't clash with local symbols. This serves two purposes of decreasing the possibility of global percpu symbol collision and allowing dropping per_cpu__ prefix from percpu symbols. * arch/ia64/kernel/setup.c: s/cpu_info/ia64_cpu_info/ Partly based on Rusty Russell's "alloc_percpu: rename percpu vars which cause name clashes" patch. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Christoph Lameter <cl@linux-foundation.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org
2009-10-29 21:34:14 +08:00
addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
ia64/pv_ops/pv_time_ops: add sched_clock hook. add sched_clock() hook to paravirtualize sched_clock(). ia64 sched_clock() is based on ar.itc which isn't stable on virtualized environment because vcpu may move around on pcpus. So it needs paravirtualization. Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp> Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-03-04 20:05:40 +08:00
END(ia64_native_sched_clock)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
cputime: Generic on-demand virtual cputime accounting If we want to stop the tick further idle, we need to be able to account the cputime without using the tick. Virtual based cputime accounting solves that problem by hooking into kernel/user boundaries. However implementing CONFIG_VIRT_CPU_ACCOUNTING require low level hooks and involves more overhead. But we already have a generic context tracking subsystem that is required for RCU needs by archs which plan to shut down the tick outside idle. This patch implements a generic virtual based cputime accounting that relies on these generic kernel/user hooks. There are some upsides of doing this: - This requires no arch code to implement CONFIG_VIRT_CPU_ACCOUNTING if context tracking is already built (already necessary for RCU in full tickless mode). - We can rely on the generic context tracking subsystem to dynamically (de)activate the hooks, so that we can switch anytime between virtual and tick based accounting. This way we don't have the overhead of the virtual accounting when the tick is running periodically. And one downside: - There is probably more overhead than a native virtual based cputime accounting. But this relies on hooks that are already set anyway. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-07-25 13:56:04 +08:00
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
[IA64] VIRT_CPU_ACCOUNTING (accurate cpu time accounting) This patch implements VIRT_CPU_ACCOUNTING for ia64, which enable us to use more accurate cpu time accounting. The VIRT_CPU_ACCOUNTING is an item of kernel config, which s390 and powerpc arch have. By turning this config on, these archs change the mechanism of cpu time accounting from tick-sampling based one to state-transition based one. The state-transition based accounting is done by checking time (cycle counter in processor) at every state-transition point, such as entrance/exit of kernel, interrupt, softirq etc. The difference between point to point is the actual time consumed during in the state. There is no doubt about that this value is more accurate than that of tick-sampling based accounting. Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-01-29 13:27:30 +08:00
GLOBAL_ENTRY(cycle_to_cputime)
alloc r16=ar.pfs,1,0,0,0
percpu: make percpu symbols in ia64 unique This patch updates percpu related symbols in ia64 such that percpu symbols are unique and don't clash with local symbols. This serves two purposes of decreasing the possibility of global percpu symbol collision and allowing dropping per_cpu__ prefix from percpu symbols. * arch/ia64/kernel/setup.c: s/cpu_info/ia64_cpu_info/ Partly based on Rusty Russell's "alloc_percpu: rename percpu vars which cause name clashes" patch. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Christoph Lameter <cl@linux-foundation.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org
2009-10-29 21:34:14 +08:00
addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
[IA64] VIRT_CPU_ACCOUNTING (accurate cpu time accounting) This patch implements VIRT_CPU_ACCOUNTING for ia64, which enable us to use more accurate cpu time accounting. The VIRT_CPU_ACCOUNTING is an item of kernel config, which s390 and powerpc arch have. By turning this config on, these archs change the mechanism of cpu time accounting from tick-sampling based one to state-transition based one. The state-transition based accounting is done by checking time (cycle counter in processor) at every state-transition point, such as entrance/exit of kernel, interrupt, softirq etc. The difference between point to point is the actual time consumed during in the state. There is no doubt about that this value is more accurate than that of tick-sampling based accounting. Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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
END(cycle_to_cputime)
cputime: Generic on-demand virtual cputime accounting If we want to stop the tick further idle, we need to be able to account the cputime without using the tick. Virtual based cputime accounting solves that problem by hooking into kernel/user boundaries. However implementing CONFIG_VIRT_CPU_ACCOUNTING require low level hooks and involves more overhead. But we already have a generic context tracking subsystem that is required for RCU needs by archs which plan to shut down the tick outside idle. This patch implements a generic virtual based cputime accounting that relies on these generic kernel/user hooks. There are some upsides of doing this: - This requires no arch code to implement CONFIG_VIRT_CPU_ACCOUNTING if context tracking is already built (already necessary for RCU in full tickless mode). - We can rely on the generic context tracking subsystem to dynamically (de)activate the hooks, so that we can switch anytime between virtual and tick based accounting. This way we don't have the overhead of the virtual accounting when the tick is running periodically. And one downside: - There is probably more overhead than a native virtual based cputime accounting. But this relies on hooks that are already set anyway. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-07-25 13:56:04 +08:00
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
[IA64] VIRT_CPU_ACCOUNTING (accurate cpu time accounting) This patch implements VIRT_CPU_ACCOUNTING for ia64, which enable us to use more accurate cpu time accounting. The VIRT_CPU_ACCOUNTING is an item of kernel config, which s390 and powerpc arch have. By turning this config on, these archs change the mechanism of cpu time accounting from tick-sampling based one to state-transition based one. The state-transition based accounting is done by checking time (cycle counter in processor) at every state-transition point, such as entrance/exit of kernel, interrupt, softirq etc. The difference between point to point is the actual time consumed during in the state. There is no doubt about that this value is more accurate than that of tick-sampling based accounting. Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2008-01-29 13:27:30 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
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
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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)
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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);;
[IA64] Remove assembler warnings on head.S This patch removes the following assembler warning messages. AS arch/ia64/kernel/head.o arch/ia64/kernel/head.S: Assembler messages: arch/ia64/kernel/head.S:1179: Warning: Use of 'ld8' violates RAW dependency 'CR[PTA]' (data) arch/ia64/kernel/head.S:1179: Warning: Only the first path encountering the conflict is reported arch/ia64/kernel/head.S:1178: Warning: This is the location of the conflicting usage arch/ia64/kernel/head.S:1180: Warning: Use of 'ld8' violates RAW dependency 'CR[PTA]' (data) arch/ia64/kernel/head.S:1180: Warning: Only the first path encountering the conflict is reported arch/ia64/kernel/head.S:1178: Warning: This is the location of the conflicting usage : arch/ia64/kernel/head.S:1213: Warning: Use of 'ldf.fill.nta' violates RAW dependency 'CR[PTA]' (data) arch/ia64/kernel/head.S:1213: Warning: Only the first path encountering the conflict is reported arch/ia64/kernel/head.S:1178: Warning: This is the location of the conflicting usage Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2007-12-12 15:28:52 +08:00
srlz.d;; // required not to violate RAW dependency
[IA64] cpu hotplug: return offlined cpus to SAL This patch is required to support cpu removal for IPF systems. Existing code just fakes the real offline by keeping it run the idle thread, and polling for the bit to re-appear in the cpu_state to get out of the idle loop. For the cpu-offline to work correctly, we need to pass control of this CPU back to SAL so it can continue in the boot-rendez mode. This gives the SAL control to not pick this cpu as the monarch processor for global MCA events, and addition does not wait for this cpu to checkin with SAL for global MCA events as well. The handoff is implemented as documented in SAL specification section 3.2.5.1 "OS_BOOT_RENDEZ to SAL return State" Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
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 */
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#endif /* CONFIG_SMP */