From 745a14cc264b1832c638e41812e0cb04328b2db1 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 28 Apr 2008 13:52:31 +1000 Subject: [POWERPC] Add fast little-endian switch system call This adds a system call on 64-bit platforms for switching between little-endian and big-endian modes that is much faster than doing a prctl call. This system call is handled as a special case right at the start of the system call entry code, and because it is a special case, it uses a system call number which is out of the range of normal system calls, namely 0x1ebe. Measurements with lmbench on a 4.2GHz POWER6 showed no measurable change in the speed of normal system calls with this patch. Switching endianness with this new system call takes around 60ns on a 4.2GHz POWER6, compared with around 300ns to switch endian mode with a prctl. This can provide a significant performance advantage for emulators for little-endian architectures that want to switch between big-endian and little-endian mode frequently, e.g. because they are generating instructions sequences on the fly and they want to run those sequences in little-endian mode. The other thing about this system call is that it doesn't clobber as many registers as a normal system call. It only clobbers r12. Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/head_64.S | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 215973a2c8d..024805e1747 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -239,6 +239,10 @@ instruction_access_slb_pSeries: .globl system_call_pSeries system_call_pSeries: HMT_MEDIUM +BEGIN_FTR_SECTION + cmpdi r0,0x1ebe + beq- 1f +END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) mr r9,r13 mfmsr r10 mfspr r13,SPRN_SPRG3 @@ -253,6 +257,13 @@ system_call_pSeries: rfid b . /* prevent speculative execution */ +/* Fast LE/BE switch system call */ +1: mfspr r12,SPRN_SRR1 + xori r12,r12,MSR_LE + mtspr SPRN_SRR1,r12 + rfid /* return to userspace */ + b . + STD_EXCEPTION_PSERIES(0xd00, single_step) STD_EXCEPTION_PSERIES(0xe00, trap_0e) -- cgit v1.2.3 From 85218827cc4ca900867807f19345418164ffc108 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Mon, 28 Apr 2008 16:21:22 +1000 Subject: [POWERPC] Add IRQSTACKS support on ppc32 This makes it possible to use separate stacks for hard and soft IRQs on 32-bit powerpc as well as on 64-bit. The code for 32-bit is just the 32-bit analog of the 64-bit code. * Added allocation and initialization of the irq stacks. We limit the stacks to be in lowmem for ppc32. * Implemented ppc32 versions of call_do_softirq() and call_handle_irq() to switch the stack pointers * Reworked how we do stack overflow detection. We now keep around the limit of the stack in the thread_struct and compare against the limit to see if we've overflowed. We can now use this on ppc64 if desired. [ paulus@samba.org: Fixed bug on 6xx where we need to reload r9 with the thread_info pointer. ] Signed-off-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/entry_32.S | 5 +++-- arch/powerpc/kernel/irq.c | 10 ++++++++-- arch/powerpc/kernel/misc_32.S | 25 +++++++++++++++++++++++++ arch/powerpc/kernel/process.c | 2 ++ arch/powerpc/kernel/setup_32.c | 21 +++++++++++++++++++++ 6 files changed, 60 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 62134845af0..af1d2c894ee 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -67,6 +67,7 @@ int main(void) #endif /* CONFIG_PPC64 */ DEFINE(KSP, offsetof(struct thread_struct, ksp)); + DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode)); DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0])); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 84c86863306..0c8614d9875 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -137,11 +137,12 @@ transfer_to_handler: 2: /* if from kernel, check interrupted DOZE/NAP mode and * check for stack overflow */ - lwz r9,THREAD_INFO-THREAD(r12) - cmplw r1,r9 /* if r1 <= current->thread_info */ + lwz r9,KSP_LIMIT(r12) + cmplw r1,r9 /* if r1 <= ksp_limit */ ble- stack_ovf /* then the kernel stack overflowed */ 5: #ifdef CONFIG_6xx + rlwinm r9,r1,0,0,31-THREAD_SHIFT tophys(r9,r9) /* check local flags */ lwz r12,TI_LOCAL_FLAGS(r9) mtcrf 0x01,r12 diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 425616f92d1..2f73f705d56 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -307,6 +307,7 @@ void do_IRQ(struct pt_regs *regs) if (curtp != irqtp) { struct irq_desc *desc = irq_desc + irq; void *handler = desc->handle_irq; + unsigned long saved_sp_limit = current->thread.ksp_limit; if (handler == NULL) handler = &__do_IRQ; irqtp->task = curtp->task; @@ -319,7 +320,10 @@ void do_IRQ(struct pt_regs *regs) (irqtp->preempt_count & ~SOFTIRQ_MASK) | (curtp->preempt_count & SOFTIRQ_MASK); + current->thread.ksp_limit = (unsigned long)irqtp + + _ALIGN_UP(sizeof(struct thread_info), 16); call_handle_irq(irq, desc, irqtp, handler); + current->thread.ksp_limit = saved_sp_limit; irqtp->task = NULL; @@ -352,9 +356,7 @@ void __init init_IRQ(void) { if (ppc_md.init_IRQ) ppc_md.init_IRQ(); -#ifdef CONFIG_PPC64 irq_ctx_init(); -#endif } @@ -383,11 +385,15 @@ void irq_ctx_init(void) static inline void do_softirq_onstack(void) { struct thread_info *curtp, *irqtp; + unsigned long saved_sp_limit = current->thread.ksp_limit; curtp = current_thread_info(); irqtp = softirq_ctx[smp_processor_id()]; irqtp->task = curtp->task; + current->thread.ksp_limit = (unsigned long)irqtp + + _ALIGN_UP(sizeof(struct thread_info), 16); call_do_softirq(irqtp); + current->thread.ksp_limit = saved_sp_limit; irqtp->task = NULL; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 92ccc6fcc5b..89aaaa6f356 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -32,6 +32,31 @@ .text +#ifdef CONFIG_IRQSTACKS +_GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) + stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3) + mr r1,r3 + bl __do_softirq + lwz r1,0(r1) + lwz r0,4(r1) + mtlr r0 + blr + +_GLOBAL(call_handle_irq) + mflr r0 + stw r0,4(r1) + mtctr r6 + stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5) + mr r1,r5 + bctrl + lwz r1,0(r1) + lwz r0,4(r1) + mtlr r0 + blr +#endif /* CONFIG_IRQSTACKS */ + /* * This returns the high 64 bits of the product of two 64-bit numbers. */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 6caad17ea72..7de41c3948e 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -589,6 +589,8 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, kregs = (struct pt_regs *) sp; sp -= STACK_FRAME_OVERHEAD; p->thread.ksp = sp; + p->thread.ksp_limit = (unsigned long)task_stack_page(p) + + _ALIGN_UP(sizeof(struct thread_info), 16); #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_SLB)) { diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 36f6779c88d..5112a4aa801 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -229,6 +230,24 @@ int __init ppc_init(void) arch_initcall(ppc_init); +#ifdef CONFIG_IRQSTACKS +static void __init irqstack_early_init(void) +{ + unsigned int i; + + /* interrupt stacks must be in lowmem, we get that for free on ppc32 + * as the lmb is limited to lowmem by LMB_REAL_LIMIT */ + for_each_possible_cpu(i) { + softirq_ctx[i] = (struct thread_info *) + __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + hardirq_ctx[i] = (struct thread_info *) + __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + } +} +#else +#define irqstack_early_init() +#endif + /* Warning, IO base is not yet inited */ void __init setup_arch(char **cmdline_p) { @@ -286,6 +305,8 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) _edata; init_mm.brk = klimit; + irqstack_early_init(); + /* set up the bootmem stuff with available memory */ do_init_bootmem(); if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab); -- cgit v1.2.3 From cc2bb6968a2c842149d285d77cb35200d2d37b15 Mon Sep 17 00:00:00 2001 From: Zhang Wei Date: Fri, 18 Apr 2008 13:33:41 -0700 Subject: [RAPIDIO] Add OF-tree support to RapidIO controller driver This initializes the RapidIO controller driver using addresses and interrupt numbers obtained from the firmware device tree, rather than using hardcoded constants. Signed-off-by: Zhang Wei Signed-off-by: Andrew Morton Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/Makefile | 1 - arch/powerpc/kernel/rio.c | 52 -------------------------------------------- 2 files changed, 53 deletions(-) delete mode 100644 arch/powerpc/kernel/rio.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 9177b21b1a9..d14cebf62bb 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -73,7 +73,6 @@ pci64-$(CONFIG_PPC64) += pci_dn.o isa-bridge.o obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \ pci-common.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_RAPIDIO) += rio.o obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ machine_kexec_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_AUDIT) += audit.o diff --git a/arch/powerpc/kernel/rio.c b/arch/powerpc/kernel/rio.c deleted file mode 100644 index 29487fedfc7..00000000000 --- a/arch/powerpc/kernel/rio.c +++ /dev/null @@ -1,52 +0,0 @@ -/* - * RapidIO PPC32 support - * - * Copyright 2005 MontaVista Software, Inc. - * Matt Porter - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include - -#include - -/** - * platform_rio_init - Do platform specific RIO init - * - * Any platform specific initialization of RapdIO - * hardware is done here as well as registration - * of any active master ports in the system. - */ -void __attribute__ ((weak)) - platform_rio_init(void) -{ - printk(KERN_WARNING "RIO: No platform_rio_init() present\n"); -} - -/** - * ppc_rio_init - Do PPC32 RIO init - * - * Calls platform-specific RIO init code and then calls - * rio_init_mports() to initialize any master ports that - * have been registered with the RIO subsystem. - */ -static int __init ppc_rio_init(void) -{ - printk(KERN_INFO "RIO: RapidIO init\n"); - - /* Platform specific initialization */ - platform_rio_init(); - - /* Enumerate all registered ports */ - rio_init_mports(); - - return 0; -} - -subsys_initcall(ppc_rio_init); -- cgit v1.2.3