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/arm/kernel/entry-armv.S

1103 lines
25 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
/*
* linux/arch/arm/kernel/entry-armv.S
*
* Copyright (C) 1996,1997,1998 Russell King.
* ARM700 fix by Matthew Godbolt (linux-user@willothewisp.demon.co.uk)
[ARM] Support register switch in nommu mode This patch adds register switch support in nommu mode. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-14 05:05:25 +08:00
* nommu support by Hyok S. Choi (hyok.choi@samsung.com)
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
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Low-level vector interface routines
*
* Note: there is a StrongARM bug in the STMIA rn, {regs}^ instruction that causes
* it to save wrong values... Be aware!
*/
[ARM] 3060/1: allow constants found in asm/memory.h to be used in asm code Patch from Nicolas Pitre This patch allows for assorted type of cleanups by letting assembly code use the same set of defines for constant values and avoid duplicated definitions that might not always be in sync, or that might simply be confusing due to the different names for the same thing. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-10-30 04:44:55 +08:00
#include <asm/memory.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/glue.h>
#include <asm/vfpmacros.h>
[PATCH] ARM: make entry*.S includes more logical Move common includes to entry-header, and file specific includes to the relevant file. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:21:02 +08:00
#include <asm/arch/entry-macro.S>
[ARM] Add thread_notify infrastructure Some machine classes need to allow VFP support to be built into the kernel, but still allow the kernel to run even though VFP isn't present. Unfortunately, the kernel hard-codes VFP instructions into the thread switch, which prevents this being run-time selectable. Solve this by introducing a notifier which things such as VFP can hook into to be informed of events which affect the VFP subsystem (eg, creation and destruction of threads, switches between threads.) Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-06-21 20:31:52 +08:00
#include <asm/thread_notify.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 "entry-header.S"
[PATCH] ARM SMP: consolidate main IRQ handler code Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:14:44 +08:00
/*
* Interrupt handling. Preserves r7, r8, r9
*/
.macro irq_handler
[ARM] 4185/2: entry: introduce get_irqnr_preamble and arch_ret_to_user get_irqnr_preamble allows machines to take some action before entering the get_irqnr_and_base loop. On iop we enable cp6 access. arch_ret_to_user is added to the userspace return path to allow individual architectures to take actions, like disabling coprocessor access, before the final return to userspace. Per Nicolas Pitre's note, there is no need to cp_wait on the return to user as the latency to return is sufficient. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-02-17 05:16:32 +08:00
get_irqnr_preamble r5, lr
[PATCH] ARM SMP: consolidate main IRQ handler code Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:14:44 +08:00
1: get_irqnr_and_base r0, r6, r5, lr
movne r1, sp
@
@ routine called with r0 = irq number, r1 = struct pt_regs *
@
adrne lr, 1b
bne asm_do_IRQ
[PATCH] ARM SMP: add IPI support Add support for inter-processor interrupts to the main IRQ handling code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:16:44 +08:00
#ifdef CONFIG_SMP
/*
* XXX
*
* this macro assumes that irqstat (r6) and base (r5) are
* preserved from get_irqnr_and_base above
*/
test_for_ipi r0, r6, r5, lr
movne r0, sp
adrne lr, 1b
bne do_IPI
[ARM SMP] Add core ARM support for local timers Add infrastructure for supporting per-cpu local timers to update the profiling information and update system time accounting. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-09 03:08:05 +08:00
#ifdef CONFIG_LOCAL_TIMERS
test_for_ltirq r0, r6, r5, lr
movne r0, sp
adrne lr, 1b
bne do_local_timer
#endif
[PATCH] ARM SMP: add IPI support Add support for inter-processor interrupts to the main IRQ handling code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:16:44 +08:00
#endif
[PATCH] ARM SMP: consolidate main IRQ handler code Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:14:44 +08:00
.endm
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
/*
* Invalid mode handlers
*/
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
.macro inv_entry, reason
sub sp, sp, #S_FRAME_SIZE
stmib sp, {r1 - lr}
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 r1, #\reason
.endm
__pabt_invalid:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
inv_entry BAD_PREFETCH
b common_invalid
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
__dabt_invalid:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
inv_entry BAD_DATA
b common_invalid
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
__irq_invalid:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
inv_entry BAD_IRQ
b common_invalid
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
__und_invalid:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
inv_entry BAD_UNDEFINSTR
@
@ XXX fall through to common_invalid
@
@
@ common_invalid - generic code for failed exception (re-entrant version of handlers)
@
common_invalid:
zero_fp
ldmia r0, {r4 - r6}
add r0, sp, #S_PC @ here for interlock avoidance
mov r7, #-1 @ "" "" "" ""
str r4, [sp] @ save preserved r0
stmia r0, {r5 - r7} @ lr_<exception>,
@ cpsr_<exception>, "old_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 r0, sp
b bad_mode
/*
* SVC mode handlers
*/
[ARM] 3102/1: ARM EABI: stack pointer must be 64-bit aligned after a CPU exception Patch from Nicolas Pitre The ARM EABI says that the stack pointer has to be 64-bit aligned for reasons already mentioned in patch #3101 when calling C functions. We therefore must verify and adjust sp accordingly when taking an exception from kernel mode since sp might not necessarily be 64-bit aligned if the exception occurs in the middle of a kernel function. If the exception occurs while in user mode then no sp fixup is needed as long as sizeof(struct pt_regs) as well as any additional syscall data stack space remain multiples of 8. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-15 00:18:08 +08:00
#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
#define SPFIX(code...) code
#else
#define SPFIX(code...)
#endif
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
.macro svc_entry
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
sub sp, sp, #S_FRAME_SIZE
[ARM] 3102/1: ARM EABI: stack pointer must be 64-bit aligned after a CPU exception Patch from Nicolas Pitre The ARM EABI says that the stack pointer has to be 64-bit aligned for reasons already mentioned in patch #3101 when calling C functions. We therefore must verify and adjust sp accordingly when taking an exception from kernel mode since sp might not necessarily be 64-bit aligned if the exception occurs in the middle of a kernel function. If the exception occurs while in user mode then no sp fixup is needed as long as sizeof(struct pt_regs) as well as any additional syscall data stack space remain multiples of 8. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-15 00:18:08 +08:00
SPFIX( tst sp, #4 )
SPFIX( bicne sp, sp, #4 )
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
stmib sp, {r1 - r12}
ldmia r0, {r1 - r3}
add r5, sp, #S_SP @ here for interlock avoidance
mov r4, #-1 @ "" "" "" ""
add r0, sp, #S_FRAME_SIZE @ "" "" "" ""
[ARM] 3102/1: ARM EABI: stack pointer must be 64-bit aligned after a CPU exception Patch from Nicolas Pitre The ARM EABI says that the stack pointer has to be 64-bit aligned for reasons already mentioned in patch #3101 when calling C functions. We therefore must verify and adjust sp accordingly when taking an exception from kernel mode since sp might not necessarily be 64-bit aligned if the exception occurs in the middle of a kernel function. If the exception occurs while in user mode then no sp fixup is needed as long as sizeof(struct pt_regs) as well as any additional syscall data stack space remain multiples of 8. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-15 00:18:08 +08:00
SPFIX( addne r0, r0, #4 )
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
str r1, [sp] @ save the "real" r0 copied
@ from the exception stack
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 r1, lr
@
@ We are now ready to fill in the remaining blanks on the stack:
@
@ r0 - sp_svc
@ r1 - lr_svc
@ r2 - lr_<exception>, already fixed up for correct return/restart
@ r3 - spsr_<exception>
@ r4 - orig_r0 (see pt_regs definition in ptrace.h)
@
stmia r5, {r0 - r4}
.endm
.align 5
__dabt_svc:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
svc_entry
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
@
@ get ready to re-enable interrupts if appropriate
@
mrs r9, cpsr
tst r3, #PSR_I_BIT
biceq r9, r9, #PSR_I_BIT
@
@ Call the processor-specific abort handler:
@
@ r2 - aborted context pc
@ r3 - aborted context cpsr
@
@ The abort handler must return the aborted address in r0, and
@ the fault status register in r1. r9 must be preserved.
@
#ifdef MULTI_ABORT
ldr r4, .LCprocfns
mov lr, pc
ldr pc, [r4]
#else
bl CPU_ABORT_HANDLER
#endif
@
@ set desired IRQ state, then call main handler
@
msr cpsr_c, r9
mov r2, sp
bl do_DataAbort
@
@ IRQs off again before pulling preserved data off the stack
@
[PATCH] ARM: Remove argument for disable_irq/enable_irq Since we do not require a register for these operations, we can remove this unnecessary argument. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:18:26 +08:00
disable_irq
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
@
@ restore SPSR and restart the instruction
@
ldr r0, [sp, #S_PSR]
msr spsr_cxsf, r0
ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
.align 5
__irq_svc:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
svc_entry
[ARM] Add ARM irqtrace support This adds support for irqtrace for lockdep on ARM. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-27 19:07:02 +08:00
#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_off
#endif
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_PREEMPT
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
get_thread_info tsk
ldr r8, [tsk, #TI_PREEMPT] @ get preempt count
add r7, r8, #1 @ increment it
str r7, [tsk, #TI_PREEMPT]
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
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
[PATCH] ARM SMP: consolidate main IRQ handler code Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:14:44 +08:00
irq_handler
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_PREEMPT
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
ldr r0, [tsk, #TI_FLAGS] @ get flags
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
tst r0, #_TIF_NEED_RESCHED
blne svc_preempt
preempt_return:
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
ldr r0, [tsk, #TI_PREEMPT] @ read preempt value
str r8, [tsk, #TI_PREEMPT] @ restore preempt count
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
teq r0, r7
strne r0, [r0, -r0] @ bug()
#endif
ldr r0, [sp, #S_PSR] @ irqs are already disabled
msr spsr_cxsf, r0
[ARM] Add ARM irqtrace support This adds support for irqtrace for lockdep on ARM. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-27 19:07:02 +08:00
#ifdef CONFIG_TRACE_IRQFLAGS
tst r0, #PSR_I_BIT
bleq trace_hardirqs_on
#endif
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
ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
.ltorg
#ifdef CONFIG_PREEMPT
svc_preempt:
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
teq r8, #0 @ was preempt count = 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
ldreq r6, .LCirq_stat
movne pc, lr @ no
ldr r0, [r6, #4] @ local_irq_count
ldr r1, [r6, #8] @ local_bh_count
adds r0, r0, r1
movne pc, lr
mov r7, #0 @ preempt_schedule_irq
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
str r7, [tsk, #TI_PREEMPT] @ expects preempt_count == 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
1: bl preempt_schedule_irq @ irq en/disable is done inside
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS
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
tst r0, #_TIF_NEED_RESCHED
beq preempt_return @ go again
b 1b
#endif
.align 5
__und_svc:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
svc_entry
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
@
@ call emulation code, which returns using r9 if it has emulated
@ the instruction, or the more conventional lr if we are to treat
@ this as a real undefined instruction
@
@ r0 - instruction
@
ldr r0, [r2, #-4]
adr r9, 1f
bl call_fpe
mov r0, sp @ struct pt_regs *regs
bl do_undefinstr
@
@ IRQs off again before pulling preserved data off the stack
@
[PATCH] ARM: Remove argument for disable_irq/enable_irq Since we do not require a register for these operations, we can remove this unnecessary argument. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:18:26 +08:00
1: disable_irq
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
@
@ restore SPSR and restart the instruction
@
ldr lr, [sp, #S_PSR] @ Get SVC cpsr
msr spsr_cxsf, lr
ldmia sp, {r0 - pc}^ @ Restore SVC registers
.align 5
__pabt_svc:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
svc_entry
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
@
@ re-enable interrupts if appropriate
@
mrs r9, cpsr
tst r3, #PSR_I_BIT
biceq r9, r9, #PSR_I_BIT
msr cpsr_c, r9
@
@ set args, then call main handler
@
@ r0 - address of faulting instruction
@ r1 - pointer to registers on stack
@
mov r0, r2 @ address (pc)
mov r1, sp @ regs
bl do_PrefetchAbort @ call abort handler
@
@ IRQs off again before pulling preserved data off the stack
@
[PATCH] ARM: Remove argument for disable_irq/enable_irq Since we do not require a register for these operations, we can remove this unnecessary argument. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:18:26 +08:00
disable_irq
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
@
@ restore SPSR and restart the instruction
@
ldr r0, [sp, #S_PSR]
msr spsr_cxsf, r0
ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
.align 5
[PATCH] ARM SMP: convert alignment enable The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch makes the alignment trap enable code independent of the way we handle the save areas. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 01:02:00 +08:00
.LCcralign:
.word cr_alignment
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 MULTI_ABORT
.LCprocfns:
.word processor
#endif
.LCfp:
.word fp_enter
#ifdef CONFIG_PREEMPT
.LCirq_stat:
.word irq_stat
#endif
/*
* User mode handlers
[ARM] 3102/1: ARM EABI: stack pointer must be 64-bit aligned after a CPU exception Patch from Nicolas Pitre The ARM EABI says that the stack pointer has to be 64-bit aligned for reasons already mentioned in patch #3101 when calling C functions. We therefore must verify and adjust sp accordingly when taking an exception from kernel mode since sp might not necessarily be 64-bit aligned if the exception occurs in the middle of a kernel function. If the exception occurs while in user mode then no sp fixup is needed as long as sizeof(struct pt_regs) as well as any additional syscall data stack space remain multiples of 8. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-15 00:18:08 +08:00
*
* EABI note: sp_svc is always 64-bit aligned here, so should S_FRAME_SIZE
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
*/
[ARM] 3102/1: ARM EABI: stack pointer must be 64-bit aligned after a CPU exception Patch from Nicolas Pitre The ARM EABI says that the stack pointer has to be 64-bit aligned for reasons already mentioned in patch #3101 when calling C functions. We therefore must verify and adjust sp accordingly when taking an exception from kernel mode since sp might not necessarily be 64-bit aligned if the exception occurs in the middle of a kernel function. If the exception occurs while in user mode then no sp fixup is needed as long as sizeof(struct pt_regs) as well as any additional syscall data stack space remain multiples of 8. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-15 00:18:08 +08:00
#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (S_FRAME_SIZE & 7)
#error "sizeof(struct pt_regs) must be a multiple of 8"
#endif
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
.macro usr_entry
sub sp, sp, #S_FRAME_SIZE
stmib sp, {r1 - r12}
ldmia r0, {r1 - r3}
add r0, sp, #S_PC @ here for interlock avoidance
mov r4, #-1 @ "" "" "" ""
str r1, [sp] @ save the "real" r0 copied
@ from the exception stack
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
@
@ We are now ready to fill in the remaining blanks on the stack:
@
@ r2 - lr_<exception>, already fixed up for correct return/restart
@ r3 - spsr_<exception>
@ r4 - orig_r0 (see pt_regs definition in ptrace.h)
@
@ Also, separately save sp_usr and lr_usr
@
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
stmia r0, {r2 - r4}
stmdb r0, {sp, lr}^
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
@
@ Enable the alignment trap while in kernel mode
@
[PATCH] ARM SMP: convert alignment enable The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch makes the alignment trap enable code independent of the way we handle the save areas. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 01:02:00 +08:00
alignment_trap 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
@
@ Clear FP to mark the first stack frame
@
zero_fp
.endm
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
.macro kuser_cmpxchg_check
#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
#ifndef CONFIG_MMU
#warning "NPTL on non MMU needs fixing"
#else
@ Make sure our user space atomic helper is restarted
@ if it was interrupted in a critical region. Here we
@ perform a quick test inline since it should be false
@ 99.9999% of the time. The rest is done out of line.
cmp r2, #TASK_SIZE
blhs kuser_cmpxchg_fixup
#endif
#endif
.endm
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
.align 5
__dabt_usr:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
usr_entry
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
kuser_cmpxchg_check
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
@
@ Call the processor-specific abort handler:
@
@ r2 - aborted context pc
@ r3 - aborted context cpsr
@
@ The abort handler must return the aborted address in r0, and
@ the fault status register in r1.
@
#ifdef MULTI_ABORT
ldr r4, .LCprocfns
mov lr, pc
ldr pc, [r4]
#else
bl CPU_ABORT_HANDLER
#endif
@
@ IRQs on, then call the main handler
@
[PATCH] ARM: Remove argument for disable_irq/enable_irq Since we do not require a register for these operations, we can remove this unnecessary argument. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:18:26 +08:00
enable_irq
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 r2, sp
adr lr, ret_from_exception
b do_DataAbort
.align 5
__irq_usr:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
usr_entry
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
kuser_cmpxchg_check
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
[ARM] Add ARM irqtrace support This adds support for irqtrace for lockdep on ARM. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-27 19:07:02 +08:00
#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_off
#endif
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
get_thread_info tsk
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_PREEMPT
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
ldr r8, [tsk, #TI_PREEMPT] @ get preempt count
add r7, r8, #1 @ increment it
str r7, [tsk, #TI_PREEMPT]
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
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
[PATCH] ARM SMP: consolidate main IRQ handler code Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:14:44 +08:00
irq_handler
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_PREEMPT
[PATCH] ARM SMP: reallocate main IRQ handler code registers By changing r9 -> r8 and r8 to 'tsk' (r9) we are able to remove one instruction from the preempt path. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-05-22 01:15:45 +08:00
ldr r0, [tsk, #TI_PREEMPT]
str r8, [tsk, #TI_PREEMPT]
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
teq r0, r7
strne r0, [r0, -r0]
#endif
[ARM] Add ARM irqtrace support This adds support for irqtrace for lockdep on ARM. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-27 19:07:02 +08:00
#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_on
#endif
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +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
mov why, #0
b ret_to_user
.ltorg
.align 5
__und_usr:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
usr_entry
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
tst r3, #PSR_T_BIT @ Thumb mode?
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
bne __und_usr_unknown @ ignore FP
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
sub r4, r2, #4
@
@ fall through to the emulation code, which returns using r9 if
@ it has emulated the instruction, or the more conventional lr
@ if we are to treat this as a real undefined instruction
@
@ r0 - instruction
@
adr r9, ret_from_exception
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
adr lr, __und_usr_unknown
[ARM] 4665/1: fix __und_usr wrt accessing the undefined insn in user space The ldrt fixup code expects r9 to be set. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-24 05:38:54 +08:00
1: ldrt r0, [r4]
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
@
@ fallthrough to call_fpe
@
/*
* The out of line fixup for the ldrt above.
*/
.section .fixup, "ax"
2: mov pc, r9
.previous
.section __ex_table,"a"
.long 1b, 2b
.previous
/*
* Check whether the instruction is a co-processor instruction.
* If yes, we need to call the relevant co-processor handler.
*
* Note that we don't do a full check here for the co-processor
* instructions; all instructions with bit 27 set are well
* defined. The only instructions that should fault are the
* co-processor instructions. However, we have to watch out
* for the ARM6/ARM7 SWI bug.
*
* Emulators may wish to make use of the following registers:
* r0 = instruction opcode.
* r2 = PC+4
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
* r9 = normal "successful" return address
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
* r10 = this threads thread_info structure.
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
* lr = unrecognised instruction return address
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
*/
call_fpe:
tst r0, #0x08000000 @ only CDP/CPRT/LDC/STC have bit 27
#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
and r8, r0, #0x0f000000 @ mask out op-code bits
teqne r8, #0x0f000000 @ SWI (ARM6/7 bug)?
#endif
moveq pc, lr
get_thread_info r10 @ get current thread
and r8, r0, #0x00000f00 @ mask out CP number
mov r7, #1
add r6, r10, #TI_USED_CP
strb r7, [r6, r8, lsr #8] @ set appropriate used_cp[]
#ifdef CONFIG_IWMMXT
@ Test if we need to give access to iWMMXt coprocessors
ldr r5, [r10, #TI_FLAGS]
rsbs r7, r8, #(1 << 8) @ CP 0 or 1 only
movcss r7, r5, lsr #(TIF_USING_IWMMXT + 1)
bcs iwmmxt_task_enable
#endif
add pc, pc, r8, lsr #6
mov r0, r0
mov pc, lr @ CP#0
b do_fpe @ CP#1 (FPE)
b do_fpe @ CP#2 (FPE)
mov pc, lr @ CP#3
[ARM] 3370/2: ep93xx: add crunch support Patch from Lennert Buytenhek Add the necessary kernel bits for crunch task switching. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-06-28 06:03:03 +08:00
#ifdef CONFIG_CRUNCH
b crunch_task_enable @ CP#4 (MaverickCrunch)
b crunch_task_enable @ CP#5 (MaverickCrunch)
b crunch_task_enable @ CP#6 (MaverickCrunch)
#else
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 pc, lr @ CP#4
mov pc, lr @ CP#5
mov pc, lr @ CP#6
[ARM] 3370/2: ep93xx: add crunch support Patch from Lennert Buytenhek Add the necessary kernel bits for crunch task switching. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-06-28 06:03:03 +08:00
#endif
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 pc, lr @ CP#7
mov pc, lr @ CP#8
mov pc, lr @ CP#9
#ifdef CONFIG_VFP
b do_vfp @ CP#10 (VFP)
b do_vfp @ CP#11 (VFP)
#else
mov pc, lr @ CP#10 (VFP)
mov pc, lr @ CP#11 (VFP)
#endif
mov pc, lr @ CP#12
mov pc, lr @ CP#13
mov pc, lr @ CP#14 (Debug)
mov pc, lr @ CP#15 (Control)
do_fpe:
[ARM] Move IRQ enable after coprocessor number decode Allow the individual coprocessor handlers to decide when to enable interrupts, rather than unconditionally enabling them. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-03-15 20:33:43 +08:00
enable_irq
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
ldr r4, .LCfp
add r10, r10, #TI_FPSTATE @ r10 = workspace
ldr pc, [r4] @ Call FP module USR entry point
/*
* The FP module is called with these registers set:
* r0 = instruction
* r2 = PC+4
* r9 = normal "successful" return address
* r10 = FP workspace
* lr = unrecognised FP instruction return address
*/
.data
ENTRY(fp_enter)
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
.word no_fp
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
.text
[ARM] Fix kernel-mode undefined instruction aborts If the kernel attempts to execute a CP1 or CP2 instruction and it aborts, and a FP emulator is not loaded, we try to return as if to a user context, instead of the proper kernel context. Since the fault came from kernel mode, we must use the kernel return paths. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-01-07 06:53:48 +08:00
no_fp: mov pc, lr
__und_usr_unknown:
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 r0, sp
adr lr, ret_from_exception
b do_undefinstr
.align 5
__pabt_usr:
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
usr_entry
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
[PATCH] ARM: Remove argument for disable_irq/enable_irq Since we do not require a register for these operations, we can remove this unnecessary argument. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:18:26 +08:00
enable_irq @ Enable interrupts
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 r0, r2 @ address (pc)
mov r1, sp @ regs
bl do_PrefetchAbort @ call abort handler
/* fall through */
/*
* This is the return code to user mode for abort handlers
*/
ENTRY(ret_from_exception)
get_thread_info tsk
mov why, #0
b ret_to_user
/*
* Register switch for ARMv3 and ARMv4 processors
* r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
* previous and next are guaranteed not to be the same.
*/
ENTRY(__switch_to)
add ip, r1, #TI_CPU_SAVE
ldr r3, [r2, #TI_TP_VALUE]
stmia ip!, {r4 - sl, fp, sp, lr} @ Store most regs on stack
[ARM] Add thread_notify infrastructure Some machine classes need to allow VFP support to be built into the kernel, but still allow the kernel to run even though VFP isn't present. Unfortunately, the kernel hard-codes VFP instructions into the thread switch, which prevents this being run-time selectable. Solve this by introducing a notifier which things such as VFP can hook into to be informed of events which affect the VFP subsystem (eg, creation and destruction of threads, switches between threads.) Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-06-21 20:31:52 +08:00
#ifdef CONFIG_MMU
ldr r6, [r2, #TI_CPU_DOMAIN]
[ARM] Support register switch in nommu mode This patch adds register switch support in nommu mode. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-14 05:05:25 +08:00
#endif
[ARM SMP] Clear the exclusive monitor on ARMv6 CPUs on context switch Ensure that the exclusive monitor is cleared on context switch with ARMv6 CPUs. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-08-10 21:52:52 +08:00
#if __LINUX_ARM_ARCH__ >= 6
[ARM] CONFIG_CPU_MPCORE -> CONFIG_CPU_32v6K CONFIG_CPU_MPCORE has never been a configuration symbol - it should be CONFIG_CPU_32v6K. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-02-23 05:13:28 +08:00
#ifdef CONFIG_CPU_32v6K
[ARM SMP] Clear the exclusive monitor on ARMv6 CPUs on context switch Ensure that the exclusive monitor is cleared on context switch with ARMv6 CPUs. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-08-10 21:52:52 +08:00
clrex
#else
[ARM] Fix context switch with ARMv6 + TLS We accidentally corrupted the TLS value when clearing out the ARMv6 exclusive monitor. Avoid doing so. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-09-24 04:49:58 +08:00
strex r5, r4, [ip] @ Clear exclusive monitor
[ARM SMP] Clear the exclusive monitor on ARMv6 CPUs on context switch Ensure that the exclusive monitor is cleared on context switch with ARMv6 CPUs. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-08-10 21:52:52 +08:00
#endif
#endif
[PATCH] ARM: 2663/1: straightify TLS register emulation a bit more Patch from Nicolas Pitre This better express things, and should cover RMK's weird SMP toys. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-05-06 06:24:45 +08:00
#if defined(CONFIG_HAS_TLS_REG)
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
mcr p15, 0, r3, c13, c0, 3 @ set TLS register
[PATCH] ARM: 2663/1: straightify TLS register emulation a bit more Patch from Nicolas Pitre This better express things, and should cover RMK's weird SMP toys. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-05-06 06:24:45 +08:00
#elif !defined(CONFIG_TLS_REG_EMUL)
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 r4, #0xffff0fff
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
str r3, [r4, #-15] @ TLS val at 0xffff0ff0
#endif
[ARM] Support register switch in nommu mode This patch adds register switch support in nommu mode. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-14 05:05:25 +08:00
#ifdef CONFIG_MMU
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
mcr p15, 0, r6, c3, c0, 0 @ Set domain register
#endif
[ARM] Add thread_notify infrastructure Some machine classes need to allow VFP support to be built into the kernel, but still allow the kernel to run even though VFP isn't present. Unfortunately, the kernel hard-codes VFP instructions into the thread switch, which prevents this being run-time selectable. Solve this by introducing a notifier which things such as VFP can hook into to be informed of events which affect the VFP subsystem (eg, creation and destruction of threads, switches between threads.) Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-06-21 20:31:52 +08:00
mov r5, r0
add r4, r2, #TI_CPU_SAVE
ldr r0, =thread_notify_head
mov r1, #THREAD_NOTIFY_SWITCH
bl atomic_notifier_call_chain
mov r0, r5
ldmia r4, {r4 - sl, fp, sp, pc} @ Load all regs saved previously
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
__INIT
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
/*
* User helpers.
*
* These are segment of kernel provided user code reachable from user space
* at a fixed address in kernel memory. This is used to provide user space
* with some operations which require kernel help because of unimplemented
* native feature and/or instructions in many ARM CPUs. The idea is for
* this code to be executed directly in user mode for best efficiency but
* which is too intimate with the kernel counter part to be left to user
* libraries. In fact this code might even differ from one CPU to another
* depending on the available instruction set and restrictions like on
* SMP systems. In other words, the kernel reserves the right to change
* this code as needed without warning. Only the entry points and their
* results are guaranteed to be stable.
*
* Each segment is 32-byte aligned and will be moved to the top of the high
* vector page. New segments (if ever needed) must be added in front of
* existing ones. This mechanism should be used only for things that are
* really small and justified, and not be abused freely.
*
* User space is expected to implement those things inline when optimizing
* for a processor that has the necessary native support, but only if such
* resulting binaries are already to be incompatible with earlier ARM
* processors due to the use of unsupported instructions other than what
* is provided here. In other words don't make binaries unable to run on
* earlier processors just for the sake of not using these kernel helpers
* if your compiled code is not going to use the new instructions for other
* purpose.
*/
[ARM] 3746/2: Userspace helpers must be Thumb mode interworkable Patch from Nicolas Pitre The userspace helpers in clean/arch/arm/kernel/entry-armv.S are called directly in/from userspace. They need to cope with being called from Thumb code. Patch below uses the bx interworking instruction when CONFIG_ARM_THUMB=y. Based on an earlier patch from Paul Brook <paul@codesourcery.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-19 00:20:15 +08:00
.macro usr_ret, reg
#ifdef CONFIG_ARM_THUMB
bx \reg
#else
mov pc, \reg
#endif
.endm
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
.align 5
.globl __kuser_helper_start
__kuser_helper_start:
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
/*
* Reference prototype:
*
* void __kernel_memory_barrier(void)
*
* Input:
*
* lr = return address
*
* Output:
*
* none
*
* Clobbered:
*
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
* none
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
*
* Definition and user space usage example:
*
* typedef void (__kernel_dmb_t)(void);
* #define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0)
*
* Apply any needed memory barrier to preserve consistency with data modified
* manually and __kuser_cmpxchg usage.
*
* This could be used as follows:
*
* #define __kernel_dmb() \
* asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \
[ARM] 3420/1: Missing clobber in example code Patch from Paul Brook The example code in the source documentation for __kernel_dmb clobbers r0 but doesn't list it the asm clobber list. Signed-off-by: Paul Brook <paul@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-03-29 05:19:29 +08:00
* : : : "r0", "lr","cc" )
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
*/
__kuser_memory_barrier: @ 0xffff0fa0
#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
mcr p15, 0, r0, c7, c10, 5 @ dmb
#endif
[ARM] 3746/2: Userspace helpers must be Thumb mode interworkable Patch from Nicolas Pitre The userspace helpers in clean/arch/arm/kernel/entry-armv.S are called directly in/from userspace. They need to cope with being called from Thumb code. Patch below uses the bx interworking instruction when CONFIG_ARM_THUMB=y. Based on an earlier patch from Paul Brook <paul@codesourcery.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-19 00:20:15 +08:00
usr_ret lr
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
.align 5
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
/*
* Reference prototype:
*
* int __kernel_cmpxchg(int oldval, int newval, int *ptr)
*
* Input:
*
* r0 = oldval
* r1 = newval
* r2 = ptr
* lr = return address
*
* Output:
*
* r0 = returned value (zero or non-zero)
* C flag = set if r0 == 0, clear if r0 != 0
*
* Clobbered:
*
* r3, ip, flags
*
* Definition and user space usage example:
*
* typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr);
* #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0)
*
* Atomically store newval in *ptr if *ptr is equal to oldval for user space.
* Return zero if *ptr was changed or non-zero if no exchange happened.
* The C flag is also set if *ptr was changed to allow for assembly
* optimization in the calling code.
*
[ARM] 3310/1: add a comment about the possible __kuser_cmpxchg transient false negative Patch from Nicolas Pitre The pre ARMv5 implementation can be aborted if an exception occurs in the middle of it. Because of that, the ARMv6 implementation doesn't re-attempt the operation on a failed strex either. Let's make this transient nature of such a false positive more explicit in the definition. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-02-09 05:19:37 +08:00
* Notes:
*
* - This routine already includes memory barriers as needed.
*
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
* For example, a user space atomic_add implementation could look like this:
*
* #define atomic_add(ptr, val) \
* ({ register unsigned int *__ptr asm("r2") = (ptr); \
* register unsigned int __result asm("r1"); \
* asm volatile ( \
* "1: @ atomic_add\n\t" \
* "ldr r0, [r2]\n\t" \
* "mov r3, #0xffff0fff\n\t" \
* "add lr, pc, #4\n\t" \
* "add r1, r0, %2\n\t" \
* "add pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \
* "bcc 1b" \
* : "=&r" (__result) \
* : "r" (__ptr), "rIL" (val) \
* : "r0","r3","ip","lr","cc","memory" ); \
* __result; })
*/
__kuser_cmpxchg: @ 0xffff0fc0
[PATCH] ARM: 2664/2: add support for atomic ops on pre-ARMv6 SMP systems Patch from Nicolas Pitre Not that there might be many of them on the planet, but at least RMK apparently has one. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-06-09 02:00:47 +08:00
#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
[PATCH] ARM: 2664/2: add support for atomic ops on pre-ARMv6 SMP systems Patch from Nicolas Pitre Not that there might be many of them on the planet, but at least RMK apparently has one. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-06-09 02:00:47 +08:00
/*
* Poor you. No fast solution possible...
* The kernel itself must perform the operation.
* A special ghost syscall is used for that (see traps.c).
*/
[ARM] 3271/1: ARM EABI: fix calling of cmpxchg syscall emulation Patch from Nicolas Pitre This is kernel provided user space code. Since a syscall is used, it has to be updated to work with EABI. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-19 06:38:49 +08:00
stmfd sp!, {r7, lr}
mov r7, #0xff00 @ 0xfff0 into r7 for EABI
orr r7, r7, #0xf0
[PATCH] ARM: 2664/2: add support for atomic ops on pre-ARMv6 SMP systems Patch from Nicolas Pitre Not that there might be many of them on the planet, but at least RMK apparently has one. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-06-09 02:00:47 +08:00
swi #0x9ffff0
[ARM] 3271/1: ARM EABI: fix calling of cmpxchg syscall emulation Patch from Nicolas Pitre This is kernel provided user space code. Since a syscall is used, it has to be updated to work with EABI. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-01-19 06:38:49 +08:00
ldmfd sp!, {r7, pc}
[PATCH] ARM: 2664/2: add support for atomic ops on pre-ARMv6 SMP systems Patch from Nicolas Pitre Not that there might be many of them on the planet, but at least RMK apparently has one. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-06-09 02:00:47 +08:00
#elif __LINUX_ARM_ARCH__ < 6
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
#ifdef CONFIG_MMU
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
/*
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
* The only thing that can break atomicity in this cmpxchg
* implementation is either an IRQ or a data abort exception
* causing another process/thread to be scheduled in the middle
* of the critical sequence. To prevent this, code is added to
* the IRQ and data abort exception handlers to set the pc back
* to the beginning of the critical section if it is found to be
* within that critical section (see kuser_cmpxchg_fixup).
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
*/
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
1: ldr r3, [r2] @ load current val
subs r3, r3, r0 @ compare with oldval
2: streq r1, [r2] @ store newval if eq
rsbs r0, r3, #0 @ set return val and C flag
usr_ret lr
.text
kuser_cmpxchg_fixup:
@ Called from kuser_cmpxchg_check macro.
@ r2 = address of interrupted insn (must be preserved).
@ sp = saved regs. r7 and r8 are clobbered.
@ 1b = first critical insn, 2b = last critical insn.
@ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b.
mov r7, #0xffff0fff
sub r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
subs r8, r2, r7
rsbcss r8, r8, #(2b - 1b)
strcs r7, [sp, #S_PC]
mov pc, lr
.previous
[ARM] 3309/1: disable the pre-ARMv5 NPTL kernel helper in the non MMU case Patch from Nicolas Pitre The cmpxchg emulation on pre-ARMv5 relies on user code executed from a kernel address. If the operation cannot complete atomically, it is aborted from the usr_entry macro by clearing the Z flag. This clearing of the Z flag is done whenever the user pc is above TASK_SIZE. However this "pc >= TASK_SIZE" test cannot work in the non MMU case. Worse: the current code will corrupt the Z flag on every entry to the kernel. Let's disable it in the non MMU case for now. Using NPTL on non MMU targets needs to be worked out anyway. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-02-09 05:19:37 +08:00
#else
#warning "NPTL on non MMU needs fixing"
mov r0, #-1
adds r0, r0, #0
[ARM] 3746/2: Userspace helpers must be Thumb mode interworkable Patch from Nicolas Pitre The userspace helpers in clean/arch/arm/kernel/entry-armv.S are called directly in/from userspace. They need to cope with being called from Thumb code. Patch below uses the bx interworking instruction when CONFIG_ARM_THUMB=y. Based on an earlier patch from Paul Brook <paul@codesourcery.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-19 00:20:15 +08:00
usr_ret lr
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
#endif
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
#else
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
#ifdef CONFIG_SMP
mcr p15, 0, r0, c7, c10, 5 @ dmb
#endif
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
1: ldrex r3, [r2]
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
subs r3, r3, r0
strexeq r3, r1, [r2]
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
teqeq r3, #1
beq 1b
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
rsbs r0, r3, #0
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
/* beware -- each __kuser slot must be 8 instructions max */
[ARM] 3210/1: add missing memory barrier helper for NPTL support Patch from Nicolas Pitre Strictly speaking, the NPTL kernel helpers are required for pre ARMv6 only. They are available on ARMv6+ as well for obvious compatibility reasons. However there are cases where extra memory barriers are needed when using an SMP ARMv6 machine but not on pre-ARMv6. This patch adds a memory barrier kernel helper that glibc can use as needed for pre-ARMv6 binaries to be forward compatible with an SMP kernel on ARMv6, as well as the necessary dmb instructions to the cmpxchg helper. Signed-off-by: Nicolas Pitre <nico@cam.org> Acked-by: Daniel Jacobowitz <dan@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-12-20 06:20:51 +08:00
#ifdef CONFIG_SMP
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
b __kuser_memory_barrier
#else
[ARM] 3746/2: Userspace helpers must be Thumb mode interworkable Patch from Nicolas Pitre The userspace helpers in clean/arch/arm/kernel/entry-armv.S are called directly in/from userspace. They need to cope with being called from Thumb code. Patch below uses the bx interworking instruction when CONFIG_ARM_THUMB=y. Based on an earlier patch from Paul Brook <paul@codesourcery.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-19 00:20:15 +08:00
usr_ret lr
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
#endif
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
#endif
.align 5
/*
* Reference prototype:
*
* int __kernel_get_tls(void)
*
* Input:
*
* lr = return address
*
* Output:
*
* r0 = TLS value
*
* Clobbered:
*
[ARM] 4659/1: remove possibilities for spurious false negative with __kuser_cmpxchg The ARM __kuser_cmpxchg routine is meant to implement an atomic cmpxchg in user space. It however can produce spurious false negative if a processor exception occurs in the middle of the operation. Normally this is not a problem since cmpxchg is typically called in a loop until it succeeds to implement an atomic increment for example. Some use cases which don't involve a loop require that the operation be 100% reliable though. This patch changes the implementation so to reattempt the operation after an exception has occurred in the critical section rather than abort it. Here's a simple program to test the fix (don't use CONFIG_NO_HZ in your kernel as this depends on a sufficiently high interrupt rate): #include <stdio.h> typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) int main() { int i, x = 0; for (i = 0; i < 100000000; i++) { int v = x; if (__kernel_cmpxchg(v, v+1, &x)) printf("failed at %d: %d vs %d\n", i, v, x); } printf("done with %d vs %d\n", i, x); return 0; } Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2007-11-21 00:20:29 +08:00
* none
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
*
* Definition and user space usage example:
*
* typedef int (__kernel_get_tls_t)(void);
* #define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0)
*
* Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
*
* This could be used as follows:
*
* #define __kernel_get_tls() \
* ({ register unsigned int __val asm("r0"); \
* asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \
* : "=r" (__val) : : "lr","cc" ); \
* __val; })
*/
__kuser_get_tls: @ 0xffff0fe0
[PATCH] ARM: 2663/1: straightify TLS register emulation a bit more Patch from Nicolas Pitre This better express things, and should cover RMK's weird SMP toys. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-05-06 06:24:45 +08:00
#if !defined(CONFIG_HAS_TLS_REG) && !defined(CONFIG_TLS_REG_EMUL)
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
ldr r0, [pc, #(16 - 8)] @ TLS stored at 0xffff0ff0
#else
mrc p15, 0, r0, c13, c0, 3 @ read TLS register
#endif
[ARM] 3746/2: Userspace helpers must be Thumb mode interworkable Patch from Nicolas Pitre The userspace helpers in clean/arch/arm/kernel/entry-armv.S are called directly in/from userspace. They need to cope with being called from Thumb code. Patch below uses the bx interworking instruction when CONFIG_ARM_THUMB=y. Based on an earlier patch from Paul Brook <paul@codesourcery.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2006-08-19 00:20:15 +08:00
usr_ret lr
[PATCH] ARM: 2651/3: kernel helpers for NPTL support Patch from Nicolas Pitre This patch entirely reworks the kernel assistance for NPTL on ARM. In particular this provides an efficient way to retrieve the TLS value and perform atomic operations without any instruction emulation nor special system call. This even allows for pre ARMv6 binaries to be forward compatible with SMP systems without any penalty. The problematic and performance critical operations are performed through segment of kernel provided user code reachable from user space at a fixed address in kernel memory. Those fixed entry points are within the vector page so we basically get it for free as no extra memory page is required and nothing else may be mapped at that location anyway. This is different from (but doesn't preclude) a full blown VDSO implementation, however a VDSO would prevent some assembly tricks with constants that allows for efficient branching to those code segments. And since those code segments only use a few cycles before returning to user code, the overhead of a VDSO far call would add a significant overhead to such minimalistic operations. The ARM_NR_set_tls syscall also changed number. This is done for two reasons: 1) this patch changes the way the TLS value was previously meant to be retrieved, therefore we ensure whatever library using the old way gets fixed (they only exist in private tree at the moment since the NPTL work is still progressing). 2) the previous number was allocated in a range causing an undefined instruction trap on kernels not supporting that syscall and it was determined that allocating it in a range returning -ENOSYS would be much nicer for libraries trying to determine if the feature is present or not. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-04-30 05:08:33 +08:00
.rep 5
.word 0 @ pad up to __kuser_helper_version
.endr
/*
* Reference declaration:
*
* extern unsigned int __kernel_helper_version;
*
* Definition and user space usage example:
*
* #define __kernel_helper_version (*(unsigned int *)0xffff0ffc)
*
* User space may read this to determine the curent number of helpers
* available.
*/
__kuser_helper_version: @ 0xffff0ffc
.word ((__kuser_helper_end - __kuser_helper_start) >> 5)
.globl __kuser_helper_end
__kuser_helper_end:
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
/*
* Vector stubs.
*
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
* This code is copied to 0xffff0200 so we can use branches in the
* vectors, rather than ldr's. Note that this code must not
* exceed 0x300 bytes.
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
*
* Common stub entry macro:
* Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
*
* SP points to a minimal amount of processor-private memory, the address
* of which is copied into r0 for the mode specific abort handler.
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
*/
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
.macro vector_stub, name, mode, correction=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
.align 5
vector_\name:
.if \correction
sub lr, lr, #\correction
.endif
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
@
@ Save r0, lr_<exception> (parent PC) and spsr_<exception>
@ (parent CPSR)
@
stmia sp, {r0, lr} @ save r0, lr
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
mrs lr, spsr
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
str lr, [sp, #8] @ save spsr
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
@
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
@ Prepare for SVC32 mode. IRQs remain disabled.
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
@
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
mrs r0, cpsr
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
eor r0, r0, #(\mode ^ SVC_MODE)
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
msr spsr_cxsf, 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
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
@
@ the branch table must immediately follow this code
@
and lr, lr, #0x0f
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
mov r0, sp
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
ldr lr, [pc, lr, lsl #2]
[PATCH] ARM SMP: Fix vector entry The current vector entry system does not allow for SMP. In order to work around this, we need to eliminate our reliance on the fixed save areas, which breaks the way we enable alignment traps. This patch changes the way we handle the save areas such that we can have one per CPU. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-06-01 05:22:32 +08:00
movs pc, lr @ branch to handler in SVC mode
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
.endm
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
.globl __stubs_start
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
__stubs_start:
/*
* Interrupt dispatcher
*/
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
vector_stub irq, IRQ_MODE, 4
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
.long __irq_usr @ 0 (USR_26 / USR_32)
.long __irq_invalid @ 1 (FIQ_26 / FIQ_32)
.long __irq_invalid @ 2 (IRQ_26 / IRQ_32)
.long __irq_svc @ 3 (SVC_26 / SVC_32)
.long __irq_invalid @ 4
.long __irq_invalid @ 5
.long __irq_invalid @ 6
.long __irq_invalid @ 7
.long __irq_invalid @ 8
.long __irq_invalid @ 9
.long __irq_invalid @ a
.long __irq_invalid @ b
.long __irq_invalid @ c
.long __irq_invalid @ d
.long __irq_invalid @ e
.long __irq_invalid @ f
/*
* Data abort dispatcher
* Enter in ABT mode, spsr = USR CPSR, lr = USR PC
*/
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
vector_stub dabt, ABT_MODE, 8
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
.long __dabt_usr @ 0 (USR_26 / USR_32)
.long __dabt_invalid @ 1 (FIQ_26 / FIQ_32)
.long __dabt_invalid @ 2 (IRQ_26 / IRQ_32)
.long __dabt_svc @ 3 (SVC_26 / SVC_32)
.long __dabt_invalid @ 4
.long __dabt_invalid @ 5
.long __dabt_invalid @ 6
.long __dabt_invalid @ 7
.long __dabt_invalid @ 8
.long __dabt_invalid @ 9
.long __dabt_invalid @ a
.long __dabt_invalid @ b
.long __dabt_invalid @ c
.long __dabt_invalid @ d
.long __dabt_invalid @ e
.long __dabt_invalid @ f
/*
* Prefetch abort dispatcher
* Enter in ABT mode, spsr = USR CPSR, lr = USR PC
*/
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
vector_stub pabt, ABT_MODE, 4
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
.long __pabt_usr @ 0 (USR_26 / USR_32)
.long __pabt_invalid @ 1 (FIQ_26 / FIQ_32)
.long __pabt_invalid @ 2 (IRQ_26 / IRQ_32)
.long __pabt_svc @ 3 (SVC_26 / SVC_32)
.long __pabt_invalid @ 4
.long __pabt_invalid @ 5
.long __pabt_invalid @ 6
.long __pabt_invalid @ 7
.long __pabt_invalid @ 8
.long __pabt_invalid @ 9
.long __pabt_invalid @ a
.long __pabt_invalid @ b
.long __pabt_invalid @ c
.long __pabt_invalid @ d
.long __pabt_invalid @ e
.long __pabt_invalid @ f
/*
* Undef instr entry dispatcher
* Enter in UND mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
*/
[ARM] 3115/1: small optimizations to exception vector entry code Patch from Nicolas Pitre Since we know the value of cpsr on entry, we can replace the bic+orr with a single eor. Also remove a possible result delay (at least on XScale). Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2005-11-06 22:42:37 +08:00
vector_stub und, UND_MODE
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
.long __und_usr @ 0 (USR_26 / USR_32)
.long __und_invalid @ 1 (FIQ_26 / FIQ_32)
.long __und_invalid @ 2 (IRQ_26 / IRQ_32)
.long __und_svc @ 3 (SVC_26 / SVC_32)
.long __und_invalid @ 4
.long __und_invalid @ 5
.long __und_invalid @ 6
.long __und_invalid @ 7
.long __und_invalid @ 8
.long __und_invalid @ 9
.long __und_invalid @ a
.long __und_invalid @ b
.long __und_invalid @ c
.long __und_invalid @ d
.long __und_invalid @ e
.long __und_invalid @ f
.align 5
/*=============================================================================
* Undefined FIQs
*-----------------------------------------------------------------------------
* Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC
* MUST PRESERVE SVC SPSR, but need to switch to SVC mode to show our msg.
* Basically to switch modes, we *HAVE* to clobber one register... brain
* damage alert! I don't think that we can execute any code in here in any
* other mode than FIQ... Ok you can switch to another mode, but you can't
* get out of that mode without clobbering one register.
*/
vector_fiq:
disable_fiq
subs pc, lr, #4
/*=============================================================================
* Address exception handler
*-----------------------------------------------------------------------------
* These aren't too critical.
* (they're not supposed to happen, and won't happen in 32-bit data mode).
*/
vector_addrexcptn:
b vector_addrexcptn
/*
* We group all the following data together to optimise
* for CPUs with separate I & D caches.
*/
.align 5
.LCvswi:
.word vector_swi
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
.globl __stubs_end
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
__stubs_end:
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
.equ stubs_offset, __vectors_start + 0x200 - __stubs_start
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
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
.globl __vectors_start
__vectors_start:
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
swi SYS_ERROR0
[PATCH] ARM: remove some entry initialisation asm code Convert the trivial vector entry initialisation code to C code. Signed-off-by: Russell King <rmk@arm.linux.org.uk>
2005-04-26 22:17:42 +08:00
b vector_und + stubs_offset
ldr pc, .LCvswi + stubs_offset
b vector_pabt + stubs_offset
b vector_dabt + stubs_offset
b vector_addrexcptn + stubs_offset
b vector_irq + stubs_offset
b vector_fiq + stubs_offset
.globl __vectors_end
__vectors_end:
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
.data
.globl cr_alignment
.globl cr_no_alignment
cr_alignment:
.space 4
cr_no_alignment:
.space 4