From e39d5ef678045d61812c1401f04fe8edb14d6359 Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Mon, 9 Aug 2010 07:58:48 +0200 Subject: powerpc/5xxx: extend mpc8xxx_gpio driver to support mpc512x gpios The GPIO controller of MPC512x is slightly different from 8xxx GPIO controllers. The register interface is the same except the external interrupt control register. The MPC512x GPIO controller differentiates between four interrupt event types and therefore provides two interrupt control registers, GPICR1 and GPICR2. GPIO[0:15] interrupt event types are configured in GPICR1 register, GPIO[16:31] - in GPICR2 register. This patch adds MPC512x speciffic set_type() callback and updates config file and comments. Additionally the gpio chip registration function is changed to use for_each_matching_node() preventing multiple registration if a node claimes compatibility with another gpio controller type. Signed-off-by: Anatolij Gustschin Signed-off-by: Grant Likely --- arch/powerpc/platforms/Kconfig | 7 ++-- arch/powerpc/sysdev/mpc8xxx_gpio.c | 75 ++++++++++++++++++++++++++++++++++---- 2 files changed, 71 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d1663db7810f..471115a13d1b 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -304,13 +304,14 @@ config OF_RTC source "arch/powerpc/sysdev/bestcomm/Kconfig" config MPC8xxx_GPIO - bool "MPC8xxx GPIO support" - depends on PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || FSL_SOC_BOOKE || PPC_86xx + bool "MPC512x/MPC8xxx GPIO support" + depends on PPC_MPC512x || PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || \ + FSL_SOC_BOOKE || PPC_86xx select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here if you're going to use hardware that connects to the - MPC831x/834x/837x/8572/8610 GPIOs. + MPC512x/831x/834x/837x/8572/8610 GPIOs. config SIMPLE_GPIO bool "Support for simple, memory-mapped GPIO controllers" diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c index 2b69084d0f0c..36499394a161 100644 --- a/arch/powerpc/sysdev/mpc8xxx_gpio.c +++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c @@ -1,5 +1,5 @@ /* - * GPIOs on MPC8349/8572/8610 and compatible + * GPIOs on MPC512x/8349/8572/8610 and compatible * * Copyright (C) 2008 Peter Korsgaard * @@ -26,6 +26,7 @@ #define GPIO_IER 0x0c #define GPIO_IMR 0x10 #define GPIO_ICR 0x14 +#define GPIO_ICR2 0x18 struct mpc8xxx_gpio_chip { struct of_mm_gpio_chip mm_gc; @@ -37,6 +38,7 @@ struct mpc8xxx_gpio_chip { */ u32 data; struct irq_host *irq; + void *of_dev_id_data; }; static inline u32 mpc8xxx_gpio2mask(unsigned int gpio) @@ -215,6 +217,51 @@ static int mpc8xxx_irq_set_type(unsigned int virq, unsigned int flow_type) return 0; } +static int mpc512x_irq_set_type(unsigned int virq, unsigned int flow_type) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + unsigned long gpio = virq_to_hw(virq); + void __iomem *reg; + unsigned int shift; + unsigned long flags; + + if (gpio < 16) { + reg = mm->regs + GPIO_ICR; + shift = (15 - gpio) * 2; + } else { + reg = mm->regs + GPIO_ICR2; + shift = (15 - (gpio % 16)) * 2; + } + + switch (flow_type) { + case IRQ_TYPE_EDGE_FALLING: + case IRQ_TYPE_LEVEL_LOW: + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + clrsetbits_be32(reg, 3 << shift, 2 << shift); + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); + break; + + case IRQ_TYPE_EDGE_RISING: + case IRQ_TYPE_LEVEL_HIGH: + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + clrsetbits_be32(reg, 3 << shift, 1 << shift); + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); + break; + + case IRQ_TYPE_EDGE_BOTH: + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + clrbits32(reg, 3 << shift); + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); + break; + + default: + return -EINVAL; + } + + return 0; +} + static struct irq_chip mpc8xxx_irq_chip = { .name = "mpc8xxx-gpio", .unmask = mpc8xxx_irq_unmask, @@ -226,6 +273,11 @@ static struct irq_chip mpc8xxx_irq_chip = { static int mpc8xxx_gpio_irq_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hw) { + struct mpc8xxx_gpio_chip *mpc8xxx_gc = h->host_data; + + if (mpc8xxx_gc->of_dev_id_data) + mpc8xxx_irq_chip.set_type = mpc8xxx_gc->of_dev_id_data; + set_irq_chip_data(virq, h->host_data); set_irq_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_level_irq); set_irq_type(virq, IRQ_TYPE_NONE); @@ -253,11 +305,20 @@ static struct irq_host_ops mpc8xxx_gpio_irq_ops = { .xlate = mpc8xxx_gpio_irq_xlate, }; +static struct of_device_id mpc8xxx_gpio_ids[] __initdata = { + { .compatible = "fsl,mpc8349-gpio", }, + { .compatible = "fsl,mpc8572-gpio", }, + { .compatible = "fsl,mpc8610-gpio", }, + { .compatible = "fsl,mpc5121-gpio", .data = mpc512x_irq_set_type, }, + {} +}; + static void __init mpc8xxx_add_controller(struct device_node *np) { struct mpc8xxx_gpio_chip *mpc8xxx_gc; struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; + const struct of_device_id *id; unsigned hwirq; int ret; @@ -297,6 +358,10 @@ static void __init mpc8xxx_add_controller(struct device_node *np) if (!mpc8xxx_gc->irq) goto skip_irq; + id = of_match_node(mpc8xxx_gpio_ids, np); + if (id) + mpc8xxx_gc->of_dev_id_data = id->data; + mpc8xxx_gc->irq->host_data = mpc8xxx_gc; /* ack and mask all irqs */ @@ -321,13 +386,7 @@ static int __init mpc8xxx_add_gpiochips(void) { struct device_node *np; - for_each_compatible_node(np, NULL, "fsl,mpc8349-gpio") - mpc8xxx_add_controller(np); - - for_each_compatible_node(np, NULL, "fsl,mpc8572-gpio") - mpc8xxx_add_controller(np); - - for_each_compatible_node(np, NULL, "fsl,mpc8610-gpio") + for_each_matching_node(np, mpc8xxx_gpio_ids) mpc8xxx_add_controller(np); return 0; -- cgit v1.2.3 From 64ff31287693c1f325cb9cb049569c1611438ef1 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 12 Aug 2010 16:28:09 +0000 Subject: powerpc: Add support for popcnt instructions POWER5 added popcntb, and POWER7 added popcntw and popcntd. As a first step this patch does all the work out of line, but it would be nice to implement them as inlines with an out of line fallback. The performance issue with hweight was noticed when disabling SMT on a large (192 thread) POWER7 box. The patch improves that testcase by about 8%. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/bitops.h | 9 +++ arch/powerpc/include/asm/cputable.h | 9 ++- arch/powerpc/kernel/ppc_ksyms.c | 7 +++ arch/powerpc/lib/Makefile | 2 +- arch/powerpc/lib/hweight_64.S | 110 ++++++++++++++++++++++++++++++++++++ 5 files changed, 133 insertions(+), 4 deletions(-) create mode 100644 arch/powerpc/lib/hweight_64.S diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 30964ae2d096..8a7e9314c68a 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -267,7 +267,16 @@ static __inline__ int fls64(__u64 x) #include #endif /* __powerpc64__ */ +#ifdef CONFIG_PPC64 +unsigned int __arch_hweight8(unsigned int w); +unsigned int __arch_hweight16(unsigned int w); +unsigned int __arch_hweight32(unsigned int w); +unsigned long __arch_hweight64(__u64 w); +#include +#else #include +#endif + #include /* Little-endian versions */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index f3a1fdd9cf08..f0a211d96923 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -199,6 +199,8 @@ extern const char *powerpc_base_platform; #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0080000000000000) #define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0100000000000000) #define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0200000000000000) +#define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0400000000000000) +#define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0800000000000000) #ifndef __ASSEMBLY__ @@ -403,21 +405,22 @@ extern const char *powerpc_base_platform; CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ - CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS) + CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS | \ + CPU_FTR_POPCNTB) #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \ - CPU_FTR_STCX_CHECKS_ADDRESS) + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ - CPU_FTR_STCX_CHECKS_ADDRESS) + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ab3e392ac63c..ef3ef566235e 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -186,3 +186,10 @@ EXPORT_SYMBOL(__mtdcr); EXPORT_SYMBOL(__mfdcr); #endif EXPORT_SYMBOL(empty_zero_page); + +#ifdef CONFIG_PPC64 +EXPORT_SYMBOL(__arch_hweight8); +EXPORT_SYMBOL(__arch_hweight16); +EXPORT_SYMBOL(__arch_hweight32); +EXPORT_SYMBOL(__arch_hweight64); +#endif diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 889f2bc106dd..166a6a0ad544 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -16,7 +16,7 @@ obj-$(CONFIG_HAS_IOMEM) += devres.o obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \ memcpy_64.o usercopy_64.o mem_64.o string.o \ - checksum_wrappers_64.o + checksum_wrappers_64.o hweight_64.o obj-$(CONFIG_XMON) += sstep.o ldstfp.o obj-$(CONFIG_KPROBES) += sstep.o ldstfp.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += sstep.o ldstfp.o diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S new file mode 100644 index 000000000000..ee2320bb5ddf --- /dev/null +++ b/arch/powerpc/lib/hweight_64.S @@ -0,0 +1,110 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2010 + * + * Author: Anton Blanchard + */ +#include +#include + +/* Note: This code relies on -mminimal-toc */ + +_GLOBAL(__arch_hweight8) +BEGIN_FTR_SECTION + b .__sw_hweight8 + nop + nop +FTR_SECTION_ELSE + popcntb r3,r3 + clrldi r3,r3,64-8 + blr +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) + +_GLOBAL(__arch_hweight16) +BEGIN_FTR_SECTION + b .__sw_hweight16 + nop + nop + nop + nop +FTR_SECTION_ELSE + BEGIN_FTR_SECTION_NESTED(50) + popcntb r3,r3 + srdi r4,r3,8 + add r3,r4,r3 + clrldi r3,r3,64-8 + blr + FTR_SECTION_ELSE_NESTED(50) + clrlwi r3,r3,16 + popcntw r3,r3 + clrldi r3,r3,64-8 + blr + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50) +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) + +_GLOBAL(__arch_hweight32) +BEGIN_FTR_SECTION + b .__sw_hweight32 + nop + nop + nop + nop + nop + nop +FTR_SECTION_ELSE + BEGIN_FTR_SECTION_NESTED(51) + popcntb r3,r3 + srdi r4,r3,16 + add r3,r4,r3 + srdi r4,r3,8 + add r3,r4,r3 + clrldi r3,r3,64-8 + blr + FTR_SECTION_ELSE_NESTED(51) + popcntw r3,r3 + clrldi r3,r3,64-8 + blr + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51) +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) + +_GLOBAL(__arch_hweight64) +BEGIN_FTR_SECTION + b .__sw_hweight64 + nop + nop + nop + nop + nop + nop + nop + nop +FTR_SECTION_ELSE + BEGIN_FTR_SECTION_NESTED(52) + popcntb r3,r3 + srdi r4,r3,32 + add r3,r4,r3 + srdi r4,r3,16 + add r3,r4,r3 + srdi r4,r3,8 + add r3,r4,r3 + clrldi r3,r3,64-8 + blr + FTR_SECTION_ELSE_NESTED(52) + popcntd r3,r3 + clrldi r3,r3,64-8 + blr + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52) +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) -- cgit v1.2.3 From d72e063bb32c06c6c1cec14f6857b7c37ba62d7a Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 24 Aug 2010 14:23:44 +0000 Subject: powerpc/kdump: Override crash_free_reserved_phys_range to avoid freeing RTAS The crashkernel region will almost always overlap RTAS. If we free the crashkernel region via "echo 0 > /sys/kernel/kexec_crash_size" then we will free RTAS and the machine will crash in confusing and exciting ways. Override crash_free_reserved_phys_range and check for overlap with RTAS. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/crash_dump.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 8e05c16344e4..0a2af50243cb 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef DEBUG #include @@ -141,3 +142,35 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, return csize; } + +#ifdef CONFIG_PPC_RTAS +/* + * The crashkernel region will almost always overlap the RTAS region, so + * we have to be careful when shrinking the crashkernel region. + */ +void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) +{ + unsigned long addr; + const u32 *basep, *sizep; + unsigned int rtas_start = 0, rtas_end = 0; + + basep = of_get_property(rtas.dev, "linux,rtas-base", NULL); + sizep = of_get_property(rtas.dev, "rtas-size", NULL); + + if (basep && sizep) { + rtas_start = *basep; + rtas_end = *basep + *sizep; + } + + for (addr = begin; addr < end; addr += PAGE_SIZE) { + /* Does this page overlap with the RTAS region? */ + if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start)) + continue; + + ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); + init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); + free_page((unsigned long)__va(addr)); + totalram_pages++; + } +} +#endif -- cgit v1.2.3 From 56e640de12c4d9902493cd819c63cacf66515686 Mon Sep 17 00:00:00 2001 From: Christian Dietrich Date: Mon, 6 Sep 2010 04:36:12 +0000 Subject: powerpc: Removing undead ifdef __KERNEL__ The __KERNEL__ ifdef isn't necessary at this point, because it is checked in an outer ifdef level already and has no effect here. Signed-off-by: Christian Dietrich Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/processor.h | 2 -- arch/powerpc/include/asm/vdso_datapage.h | 2 -- 2 files changed, 4 deletions(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 4c14187ba02d..de1967a1ff57 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -122,7 +122,6 @@ extern struct task_struct *last_task_used_spe; TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 ) #endif -#ifdef __KERNEL__ #ifdef __powerpc64__ #define STACK_TOP_USER64 TASK_SIZE_USER64 @@ -139,7 +138,6 @@ extern struct task_struct *last_task_used_spe; #define STACK_TOP_MAX STACK_TOP #endif /* __powerpc64__ */ -#endif /* __KERNEL__ */ typedef struct { unsigned long seg; diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index 08679c5319b8..25e39220e89c 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -116,9 +116,7 @@ struct vdso_data { #endif /* CONFIG_PPC64 */ -#ifdef __KERNEL__ extern struct vdso_data *vdso_data; -#endif #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 5a71c61b7724ad0acedff254e07dc1a7dd05ee76 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 13 Sep 2010 09:47:42 +0000 Subject: drivers/char/hvc_vio: Use static const char arrays Signed-off-by: Joe Perches Reviewed-by: Stephen Rothwell Signed-off-by: Benjamin Herrenschmidt --- drivers/char/hvc_vio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/hvc_vio.c b/drivers/char/hvc_vio.c index 27370e99c66f..5e2f52b33327 100644 --- a/drivers/char/hvc_vio.c +++ b/drivers/char/hvc_vio.c @@ -39,7 +39,7 @@ #include "hvc_console.h" -char hvc_driver_name[] = "hvc_console"; +static const char hvc_driver_name[] = "hvc_console"; static struct vio_device_id hvc_driver_table[] __devinitdata = { {"serial", "hvterm1"}, -- cgit v1.2.3 From 475fc7c011ace79258c07d981d348a15614e0573 Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Tue, 21 Sep 2010 23:22:40 +0000 Subject: powerpc: Fix two typos in Documentation/powerpc/booting-without-of.txt Signed-off-by: Lennert Buytenhek Signed-off-by: Benjamin Herrenschmidt --- Documentation/powerpc/booting-without-of.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index 302db5da49b3..3272ed59dec7 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -131,7 +131,7 @@ order to avoid the degeneration that had become the ppc32 kernel entry point and the way a new platform should be added to the kernel. The legacy iSeries platform breaks those rules as it predates this scheme, but no new board support will be accepted in the main tree that -doesn't follows them properly. In addition, since the advent of the +doesn't follow them properly. In addition, since the advent of the arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit platforms and 32-bit platforms which move into arch/powerpc will be required to use these rules as well. @@ -1025,7 +1025,7 @@ dtc source code can be found at WARNING: This version is still in early development stage; the resulting device-tree "blobs" have not yet been validated with the -kernel. The current generated bloc lacks a useful reserve map (it will +kernel. The current generated block lacks a useful reserve map (it will be fixed to generate an empty one, it's up to the bootloader to fill it up) among others. The error handling needs work, bugs are lurking, etc... -- cgit v1.2.3 From 4e89a2d8e2d5ab33d73b76f16c10fdf515faabef Mon Sep 17 00:00:00 2001 From: Will Schmidt Date: Tue, 28 Sep 2010 15:33:12 +0000 Subject: powerpc/pseries: Add kernel parameter to disable batched hcalls This introduces a pair of kernel parameters that can be used to disable the MULTITCE and BULK_REMOVE h-calls. By default, those hcalls are enabled, active, and good for throughput and performance. The ability to disable them will be useful for some of the PREEMPT_RT related investigation and work occurring on Power. Signed-off-by: Will Schmidt cc: Olof Johansson cc: Anton Blanchard cc: Benjamin Herrenschmidt Signed-off-by: Benjamin Herrenschmidt --- Documentation/kernel-parameters.txt | 8 ++++++++ arch/powerpc/platforms/pseries/iommu.c | 14 ++++++++++++++ arch/powerpc/platforms/pseries/lpar.c | 12 ++++++++++++ 3 files changed, 34 insertions(+) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index cdd2a6e8a3b7..69bb6a9c871a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -403,6 +403,10 @@ and is between 256 and 4096 characters. It is defined in the file bttv.pll= See Documentation/video4linux/bttv/Insmod-options bttv.tuner= and Documentation/video4linux/bttv/CARDLIST + bulk_remove=off [PPC] This parameter disables the use of the pSeries + firmware feature for flushing multiple hpte entries + at a time. + c101= [NET] Moxa C101 synchronous serial card cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. @@ -1490,6 +1494,10 @@ and is between 256 and 4096 characters. It is defined in the file mtdparts= [MTD] See drivers/mtd/cmdlinepart.c. + multitce=off [PPC] This parameter disables the use of the pSeries + firmware feature for updating multiple TCE entries + at a time. + onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index a77bcaed80af..fa2906a103dd 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -622,3 +622,17 @@ void iommu_init_early_pSeries(void) set_pci_dma_ops(&dma_iommu_ops); } +static int __init disable_multitce(char *str) +{ + if (strcmp(str, "off") == 0 && + firmware_has_feature(FW_FEATURE_LPAR) && + firmware_has_feature(FW_FEATURE_MULTITCE)) { + printk(KERN_INFO "Disabling MULTITCE firmware feature\n"); + ppc_md.tce_build = tce_build_pSeriesLP; + ppc_md.tce_free = tce_free_pSeriesLP; + powerpc_firmware_features &= ~FW_FEATURE_MULTITCE; + } + return 1; +} + +__setup("multitce=", disable_multitce); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f129040d974c..5d3ea9f60dd7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -627,6 +627,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); } +static int __init disable_bulk_remove(char *str) +{ + if (strcmp(str, "off") == 0 && + firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { + printk(KERN_INFO "Disabling BULK_REMOVE firmware feature"); + powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE; + } + return 1; +} + +__setup("bulk_remove=", disable_bulk_remove); + void __init hpte_init_lpar(void) { ppc_md.hpte_invalidate = pSeries_lpar_hpte_invalidate; -- cgit v1.2.3 From 787d44caa5bca249d8781d21b626c417f1e3cfc4 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 1 Oct 2010 11:12:54 +0000 Subject: powerpc: enable ARCH_DMA_ADDR_T_64BIT with ARCH_PHYS_ADDR_T_64BIT Signed-off-by: FUJITA Tomonori Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e625e9e034ae..06d742c3fbcf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -20,6 +20,9 @@ config WORD_SIZE config ARCH_PHYS_ADDR_T_64BIT def_bool PPC64 || PHYS_64BIT +config ARCH_DMA_ADDR_T_64BIT + def_bool ARCH_PHYS_ADDR_T_64BIT + config MMU bool default y -- cgit v1.2.3 From 99d86705253dcf728dbbec4d694a6764b6edb70c Mon Sep 17 00:00:00 2001 From: Vaidyanathan Srinivasan Date: Wed, 6 Oct 2010 08:36:59 +0000 Subject: powerpc: Cleanup APIs for cpu/thread/core mappings These APIs take logical cpu number as input Change cpu_first_thread_in_core() to cpu_first_thread_sibling() Change cpu_last_thread_in_core() to cpu_last_thread_sibling() These APIs convert core number (index) to logical cpu/thread numbers Add cpu_first_thread_of_core(int core) Changed cpu_thread_to_core() to cpu_core_index_of_thread(int cpu) The goal is to make 'threads_per_core' accessible to the pseries_energy module. Instead of making an API to read threads_per_core, this is a higher level wrapper function to convert from logical cpu number to core number. The current APIs cpu_first_thread_in_core() and cpu_last_thread_in_core() returns logical CPU number while cpu_thread_to_core() returns core number or index which is not a logical CPU number. The new APIs are now clearly named to distinguish 'core number' versus first and last 'logical cpu number' in that core. The new APIs cpu_{first,last}_thread_sibling() work on logical cpu numbers. While cpu_first_thread_of_core() and cpu_core_index_of_thread() work on core index. Example usage: (4 threads per core system) cpu_first_thread_sibling(5) = 4 cpu_last_thread_sibling(5) = 7 cpu_core_index_of_thread(5) = 1 cpu_first_thread_of_core(1) = 4 cpu_core_index_of_thread() is used in cpu_to_drc_index() in the module and cpu_first_thread_of_core() is used in drc_index_to_cpu() in the module. Make API changes to few callers. Export symbols for use in modules. Signed-off-by: Vaidyanathan Srinivasan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputhreads.h | 15 +++++++++------ arch/powerpc/kernel/smp.c | 19 ++++++++++++++++--- arch/powerpc/mm/mmu_context_nohash.c | 12 ++++++------ 3 files changed, 31 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index a8e18447c62b..f71bb4c118b4 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -61,22 +61,25 @@ static inline cpumask_t cpu_online_cores_map(void) return cpu_thread_mask_to_cores(cpu_online_map); } -static inline int cpu_thread_to_core(int cpu) -{ - return cpu >> threads_shift; -} +#ifdef CONFIG_SMP +int cpu_core_index_of_thread(int cpu); +int cpu_first_thread_of_core(int core); +#else +static inline int cpu_core_index_of_thread(int cpu) { return cpu; } +static inline int cpu_first_thread_of_core(int core) { return core; } +#endif static inline int cpu_thread_in_core(int cpu) { return cpu & (threads_per_core - 1); } -static inline int cpu_first_thread_in_core(int cpu) +static inline int cpu_first_thread_sibling(int cpu) { return cpu & ~(threads_per_core - 1); } -static inline int cpu_last_thread_in_core(int cpu) +static inline int cpu_last_thread_sibling(int cpu) { return cpu | (threads_per_core - 1); } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 68034bbf2e4f..981360509172 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -466,7 +466,20 @@ out: return id; } -/* Must be called when no change can occur to cpu_present_mask, +/* Helper routines for cpu to core mapping */ +int cpu_core_index_of_thread(int cpu) +{ + return cpu >> threads_shift; +} +EXPORT_SYMBOL_GPL(cpu_core_index_of_thread); + +int cpu_first_thread_of_core(int core) +{ + return core << threads_shift; +} +EXPORT_SYMBOL_GPL(cpu_first_thread_of_core); + +/* Must be called when no change can occur to cpu_present_map, * i.e. during cpu online or offline. */ static struct device_node *cpu_to_l2cache(int cpu) @@ -514,7 +527,7 @@ int __devinit start_secondary(void *unused) notify_cpu_starting(cpu); set_cpu_online(cpu, true); /* Update sibling maps */ - base = cpu_first_thread_in_core(cpu); + base = cpu_first_thread_sibling(cpu); for (i = 0; i < threads_per_core; i++) { if (cpu_is_offline(base + i)) continue; @@ -600,7 +613,7 @@ int __cpu_disable(void) return err; /* Update sibling maps */ - base = cpu_first_thread_in_core(cpu); + base = cpu_first_thread_sibling(cpu); for (i = 0; i < threads_per_core; i++) { cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 5ce99848d91e..c0aab52da3a5 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -111,8 +111,8 @@ static unsigned int steal_context_smp(unsigned int id) * a core map instead but this will do for now. */ for_each_cpu(cpu, mm_cpumask(mm)) { - for (i = cpu_first_thread_in_core(cpu); - i <= cpu_last_thread_in_core(cpu); i++) + for (i = cpu_first_thread_sibling(cpu); + i <= cpu_last_thread_sibling(cpu); i++) __set_bit(id, stale_map[i]); cpu = i - 1; } @@ -264,14 +264,14 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) */ if (test_bit(id, stale_map[cpu])) { pr_hardcont(" | stale flush %d [%d..%d]", - id, cpu_first_thread_in_core(cpu), - cpu_last_thread_in_core(cpu)); + id, cpu_first_thread_sibling(cpu), + cpu_last_thread_sibling(cpu)); local_flush_tlb_mm(next); /* XXX This clear should ultimately be part of local_flush_tlb_mm */ - for (i = cpu_first_thread_in_core(cpu); - i <= cpu_last_thread_in_core(cpu); i++) { + for (i = cpu_first_thread_sibling(cpu); + i <= cpu_last_thread_sibling(cpu); i++) { __clear_bit(id, stale_map[i]); } } -- cgit v1.2.3 From 5742bd859524793b857110a13db349d95070d2dc Mon Sep 17 00:00:00 2001 From: Vaidyanathan Srinivasan Date: Wed, 6 Oct 2010 08:37:09 +0000 Subject: powerpc: Add support for new hcall H_BEST_ENERGY Create sysfs interface to export data from H_BEST_ENERGY hcall that can be used by administrative tools on supported pseries platforms for energy management optimizations. sys/device/system/cpu/pseries_(de)activate_hint_list and sys/device/system/cpu/cpuN/pseries_(de)activate_hint will provide hints for activation and deactivation of cpus respectively. These hints are abstract number given by the hypervisor based on the extended knowledge the hypervisor has regarding the system topology and resource mappings. The activate and the deactivate sysfs entry is for the two distinct operations that we could do for energy savings. When we have more capacity than required, we could deactivate few core to save energy. The choice of the core to deactivate will be based on /sys/devices/system/cpu/deactivate_hint_list. The comma separated list of cpus (cores) will be the preferred choice. If we have to activate some of the deactivated cores, then /sys/devices/system/cpu/activate_hint_list will be used. The per-cpu file /sys/device/system/cpu/cpuN/pseries_(de)activate_hint further provide more fine grain information by exporting the value of the hint itself. Added new driver module arch/powerpc/platforms/pseries/pseries_energy.c under new config option CONFIG_PSERIES_ENERGY Signed-off-by: Vaidyanathan Srinivasan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hvcall.h | 3 +- arch/powerpc/platforms/pseries/Kconfig | 10 + arch/powerpc/platforms/pseries/Makefile | 1 + arch/powerpc/platforms/pseries/pseries_energy.c | 326 ++++++++++++++++++++++++ 4 files changed, 339 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/platforms/pseries/pseries_energy.c diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index de03ca58db5d..bf86b03d5af2 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -232,7 +232,8 @@ #define H_GET_EM_PARMS 0x2B8 #define H_SET_MPP 0x2D0 #define H_GET_MPP 0x2D4 -#define MAX_HCALL_OPCODE H_GET_MPP +#define H_BEST_ENERGY 0x2F4 +#define MAX_HCALL_OPCODE H_BEST_ENERGY #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 3139814f6439..5d1b743dbe7e 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -33,6 +33,16 @@ config PSERIES_MSI depends on PCI_MSI && EEH default y +config PSERIES_ENERGY + tristate "pSeries energy management capabilities driver" + depends on PPC_PSERIES + default y + help + Provides interface to platform energy management capabilities + on supported PSERIES platforms. + Provides: /sys/devices/system/cpu/pseries_(de)activation_hint_list + and /sys/devices/system/cpu/cpuN/pseries_(de)activation_hint + config SCANLOG tristate "Scanlog dump interface" depends on RTAS_PROC && PPC_PSERIES diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 59eb8bdaa79d..fc5237810ece 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_EEH) += eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_PCI) += pci.o pci_dlpar.o obj-$(CONFIG_PSERIES_MSI) += msi.o +obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu.o obj-$(CONFIG_MEMORY_HOTPLUG) += hotplug-memory.o diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c new file mode 100644 index 000000000000..c8b3c69fe891 --- /dev/null +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -0,0 +1,326 @@ +/* + * POWER platform energy management driver + * Copyright (C) 2010 IBM Corporation + * + * 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. + * + * This pseries platform device driver provides access to + * platform energy management capabilities. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#define MODULE_VERS "1.0" +#define MODULE_NAME "pseries_energy" + +/* Driver flags */ + +static int sysfs_entries; + +/* Helper routines */ + +/* + * Routine to detect firmware support for hcall + * return 1 if H_BEST_ENERGY is supported + * else return 0 + */ + +static int check_for_h_best_energy(void) +{ + struct device_node *rtas = NULL; + const char *hypertas, *s; + int length; + int rc = 0; + + rtas = of_find_node_by_path("/rtas"); + if (!rtas) + return 0; + + hypertas = of_get_property(rtas, "ibm,hypertas-functions", &length); + if (!hypertas) { + of_node_put(rtas); + return 0; + } + + /* hypertas will have list of strings with hcall names */ + for (s = hypertas; s < hypertas + length; s += strlen(s) + 1) { + if (!strncmp("hcall-best-energy-1", s, 19)) { + rc = 1; /* Found the string */ + break; + } + } + of_node_put(rtas); + return rc; +} + +/* Helper Routines to convert between drc_index to cpu numbers */ + +static u32 cpu_to_drc_index(int cpu) +{ + struct device_node *dn = NULL; + const int *indexes; + int i; + int rc = 1; + u32 ret = 0; + + dn = of_find_node_by_path("/cpus"); + if (dn == NULL) + goto err; + indexes = of_get_property(dn, "ibm,drc-indexes", NULL); + if (indexes == NULL) + goto err_of_node_put; + /* Convert logical cpu number to core number */ + i = cpu_core_index_of_thread(cpu); + /* + * The first element indexes[0] is the number of drc_indexes + * returned in the list. Hence i+1 will get the drc_index + * corresponding to core number i. + */ + WARN_ON(i > indexes[0]); + ret = indexes[i + 1]; + rc = 0; + +err_of_node_put: + of_node_put(dn); +err: + if (rc) + printk(KERN_WARNING "cpu_to_drc_index(%d) failed", cpu); + return ret; +} + +static int drc_index_to_cpu(u32 drc_index) +{ + struct device_node *dn = NULL; + const int *indexes; + int i, cpu = 0; + int rc = 1; + + dn = of_find_node_by_path("/cpus"); + if (dn == NULL) + goto err; + indexes = of_get_property(dn, "ibm,drc-indexes", NULL); + if (indexes == NULL) + goto err_of_node_put; + /* + * First element in the array is the number of drc_indexes + * returned. Search through the list to find the matching + * drc_index and get the core number + */ + for (i = 0; i < indexes[0]; i++) { + if (indexes[i + 1] == drc_index) + break; + } + /* Convert core number to logical cpu number */ + cpu = cpu_first_thread_of_core(i); + rc = 0; + +err_of_node_put: + of_node_put(dn); +err: + if (rc) + printk(KERN_WARNING "drc_index_to_cpu(%d) failed", drc_index); + return cpu; +} + +/* + * pseries hypervisor call H_BEST_ENERGY provides hints to OS on + * preferred logical cpus to activate or deactivate for optimized + * energy consumption. + */ + +#define FLAGS_MODE1 0x004E200000080E01 +#define FLAGS_MODE2 0x004E200000080401 +#define FLAGS_ACTIVATE 0x100 + +static ssize_t get_best_energy_list(char *page, int activate) +{ + int rc, cnt, i, cpu; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long flags = 0; + u32 *buf_page; + char *s = page; + + buf_page = (u32 *) get_zeroed_page(GFP_KERNEL); + if (!buf_page) + return -ENOMEM; + + flags = FLAGS_MODE1; + if (activate) + flags |= FLAGS_ACTIVATE; + + rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags, 0, __pa(buf_page), + 0, 0, 0, 0, 0, 0); + if (rc != H_SUCCESS) { + free_page((unsigned long) buf_page); + return -EINVAL; + } + + cnt = retbuf[0]; + for (i = 0; i < cnt; i++) { + cpu = drc_index_to_cpu(buf_page[2*i+1]); + if ((cpu_online(cpu) && !activate) || + (!cpu_online(cpu) && activate)) + s += sprintf(s, "%d,", cpu); + } + if (s > page) { /* Something to show */ + s--; /* Suppress last comma */ + s += sprintf(s, "\n"); + } + + free_page((unsigned long) buf_page); + return s-page; +} + +static ssize_t get_best_energy_data(struct sys_device *dev, + char *page, int activate) +{ + int rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long flags = 0; + + flags = FLAGS_MODE2; + if (activate) + flags |= FLAGS_ACTIVATE; + + rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags, + cpu_to_drc_index(dev->id), + 0, 0, 0, 0, 0, 0, 0); + + if (rc != H_SUCCESS) + return -EINVAL; + + return sprintf(page, "%lu\n", retbuf[1] >> 32); +} + +/* Wrapper functions */ + +static ssize_t cpu_activate_hint_list_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) +{ + return get_best_energy_list(page, 1); +} + +static ssize_t cpu_deactivate_hint_list_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) +{ + return get_best_energy_list(page, 0); +} + +static ssize_t percpu_activate_hint_show(struct sys_device *dev, + struct sysdev_attribute *attr, char *page) +{ + return get_best_energy_data(dev, page, 1); +} + +static ssize_t percpu_deactivate_hint_show(struct sys_device *dev, + struct sysdev_attribute *attr, char *page) +{ + return get_best_energy_data(dev, page, 0); +} + +/* + * Create sysfs interface: + * /sys/devices/system/cpu/pseries_activate_hint_list + * /sys/devices/system/cpu/pseries_deactivate_hint_list + * Comma separated list of cpus to activate or deactivate + * /sys/devices/system/cpu/cpuN/pseries_activate_hint + * /sys/devices/system/cpu/cpuN/pseries_deactivate_hint + * Per-cpu value of the hint + */ + +struct sysdev_class_attribute attr_cpu_activate_hint_list = + _SYSDEV_CLASS_ATTR(pseries_activate_hint_list, 0444, + cpu_activate_hint_list_show, NULL); + +struct sysdev_class_attribute attr_cpu_deactivate_hint_list = + _SYSDEV_CLASS_ATTR(pseries_deactivate_hint_list, 0444, + cpu_deactivate_hint_list_show, NULL); + +struct sysdev_attribute attr_percpu_activate_hint = + _SYSDEV_ATTR(pseries_activate_hint, 0444, + percpu_activate_hint_show, NULL); + +struct sysdev_attribute attr_percpu_deactivate_hint = + _SYSDEV_ATTR(pseries_deactivate_hint, 0444, + percpu_deactivate_hint_show, NULL); + +static int __init pseries_energy_init(void) +{ + int cpu, err; + struct sys_device *cpu_sys_dev; + + if (!check_for_h_best_energy()) { + printk(KERN_INFO "Hypercall H_BEST_ENERGY not supported\n"); + return 0; + } + /* Create the sysfs files */ + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_activate_hint_list.attr); + if (!err) + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_deactivate_hint_list.attr); + + if (err) + return err; + for_each_possible_cpu(cpu) { + cpu_sys_dev = get_cpu_sysdev(cpu); + err = sysfs_create_file(&cpu_sys_dev->kobj, + &attr_percpu_activate_hint.attr); + if (err) + break; + err = sysfs_create_file(&cpu_sys_dev->kobj, + &attr_percpu_deactivate_hint.attr); + if (err) + break; + } + + if (err) + return err; + + sysfs_entries = 1; /* Removed entries on cleanup */ + return 0; + +} + +static void __exit pseries_energy_cleanup(void) +{ + int cpu; + struct sys_device *cpu_sys_dev; + + if (!sysfs_entries) + return; + + /* Remove the sysfs files */ + sysfs_remove_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_activate_hint_list.attr); + + sysfs_remove_file(&cpu_sysdev_class.kset.kobj, + &attr_cpu_deactivate_hint_list.attr); + + for_each_possible_cpu(cpu) { + cpu_sys_dev = get_cpu_sysdev(cpu); + sysfs_remove_file(&cpu_sys_dev->kobj, + &attr_percpu_activate_hint.attr); + sysfs_remove_file(&cpu_sys_dev->kobj, + &attr_percpu_deactivate_hint.attr); + } +} + +module_init(pseries_energy_init); +module_exit(pseries_energy_cleanup); +MODULE_DESCRIPTION("Driver for pSeries platform energy management"); +MODULE_AUTHOR("Vaidyanathan Srinivasan"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 8cb7c71bda16e2d67a332642661e0b4219641a23 Mon Sep 17 00:00:00 2001 From: Srikanth Krishnakar Date: Thu, 14 Oct 2010 04:03:35 +0000 Subject: rtc-cmos.c : Fix warning on PowerPC The following warning is seen while compilation of PowerPC kernel: CC drivers/rtc/rtc-cmos.o drivers/rtc/rtc-cmos.c:697:2: warning: #warning Assuming 128 bytes of RTC+NVRAM address space, not 64 bytes. Fix it by adding defined(__powerpc__). Signed-off-by: Srikanth Krishnakar Signed-off-by: Benjamin Herrenschmidt --- drivers/rtc/rtc-cmos.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 5856167a0c90..7e6ce626b7f1 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -687,7 +687,8 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) #if defined(CONFIG_ATARI) address_space = 64; #elif defined(__i386__) || defined(__x86_64__) || defined(__arm__) \ - || defined(__sparc__) || defined(__mips__) + || defined(__sparc__) || defined(__mips__) \ + || defined(__powerpc__) address_space = 128; #else #warning Assuming 128 bytes of RTC+NVRAM address space, not 64 bytes. -- cgit v1.2.3 From 72b962d3bba19657abaa6cc8806661ecbde5ee92 Mon Sep 17 00:00:00 2001 From: Tracey Dent Date: Fri, 15 Oct 2010 17:30:48 +0000 Subject: powerpc/ps3: Replace the use of -objs with -y Changed -objs to -y in Makefile. Signed-off-by: Tracey Dent Signed-off-by: Benjamin Herrenschmidt --- drivers/ps3/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ps3/Makefile b/drivers/ps3/Makefile index ccea15c11c19..50cb1e1b4a12 100644 --- a/drivers/ps3/Makefile +++ b/drivers/ps3/Makefile @@ -1,6 +1,6 @@ obj-$(CONFIG_PS3_VUART) += ps3-vuart.o obj-$(CONFIG_PS3_PS3AV) += ps3av_mod.o -ps3av_mod-objs += ps3av.o ps3av_cmd.o +ps3av_mod-y := ps3av.o ps3av_cmd.o obj-$(CONFIG_PPC_PS3) += sys-manager-core.o obj-$(CONFIG_PS3_SYS_MANAGER) += ps3-sys-manager.o obj-$(CONFIG_PS3_STORAGE) += ps3stor_lib.o -- cgit v1.2.3 From 6d283d782f9fbafee5c672bfdaff4c10f6fdc788 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:26:59 +0000 Subject: powerpc/vio: Use dma ops helpers Use the set_dma_ops helper. Instead of modifying vio_dma_mapping_ops, just create a trivial wrapper for dma_supported. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/vio.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 441d2a722f06..b2654058f2e4 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -600,6 +600,11 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, vio_cmo_dealloc(viodev, alloc_size); } +static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask) +{ + return dma_iommu_ops.dma_supported(dev, mask); +} + struct dma_map_ops vio_dma_mapping_ops = { .alloc_coherent = vio_dma_iommu_alloc_coherent, .free_coherent = vio_dma_iommu_free_coherent, @@ -607,6 +612,7 @@ struct dma_map_ops vio_dma_mapping_ops = { .unmap_sg = vio_dma_iommu_unmap_sg, .map_page = vio_dma_iommu_map_page, .unmap_page = vio_dma_iommu_unmap_page, + .dma_supported = vio_dma_iommu_dma_supported, }; @@ -858,8 +864,7 @@ static void vio_cmo_bus_remove(struct vio_dev *viodev) static void vio_cmo_set_dma_ops(struct vio_dev *viodev) { - vio_dma_mapping_ops.dma_supported = dma_iommu_ops.dma_supported; - viodev->dev.archdata.dma_ops = &vio_dma_mapping_ops; + set_dma_ops(&viodev->dev, &vio_dma_mapping_ops); } /** @@ -1244,7 +1249,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_set_dma_ops(viodev); else - viodev->dev.archdata.dma_ops = &dma_iommu_ops; + set_dma_ops(&viodev->dev, &dma_iommu_ops); set_iommu_table_base(&viodev->dev, vio_build_iommu_table(viodev)); set_dev_node(&viodev->dev, of_node_to_nid(of_node)); -- cgit v1.2.3 From 2f9c9be2ff31670c942572cf96eb6c696362b584 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:27:00 +0000 Subject: powerpc/pasemi: Clean up pasemi iommu table initializations No need for empty helpers with iommu off, the ppc_md hooks are optional. The direct_dma_ops are the default pci_dma_ops, so no need to set in the them iommu off case. No need to set the device tree device_node pci node iommu pointer, its only used for dlpar remove. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Acked-by: Olof Johansson Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pasemi/iommu.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 1f9fb2c57761..14943ef01918 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -156,20 +156,12 @@ static void iommu_table_iobmap_setup(void) static void pci_dma_bus_setup_pasemi(struct pci_bus *bus) { - struct device_node *dn; - pr_debug("pci_dma_bus_setup, bus %p, bus->self %p\n", bus, bus->self); if (!iommu_table_iobmap_inited) { iommu_table_iobmap_inited = 1; iommu_table_iobmap_setup(); } - - dn = pci_bus_to_OF_node(bus); - - if (dn) - PCI_DN(dn)->iommu_table = &iommu_table_iobmap; - } @@ -192,9 +184,6 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) set_iommu_table_base(&dev->dev, &iommu_table_iobmap); } -static void pci_dma_bus_setup_null(struct pci_bus *b) { } -static void pci_dma_dev_setup_null(struct pci_dev *d) { } - int __init iob_init(struct device_node *dn) { unsigned long tmp; @@ -251,14 +240,8 @@ void __init iommu_init_early_pasemi(void) iommu_off = of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL); #endif - if (iommu_off) { - /* Direct I/O, IOMMU off */ - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_null; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_null; - set_pci_dma_ops(&dma_direct_ops); - + if (iommu_off) return; - } iob_init(NULL); -- cgit v1.2.3 From 741d204cee6d62bbe0f74ab57ef31702b7d90f62 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:27:01 +0000 Subject: powerpc/cell: Beat dma ops cleanup direct_dma_ops is the default pci dma ops. No need to call a function to get the pci dma ops, we know they are the dma_direct_ops. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Acked-by: Arnd Bergmann Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/cell/beat_iommu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c index beec405eb6f8..3ce685568935 100644 --- a/arch/powerpc/platforms/cell/beat_iommu.c +++ b/arch/powerpc/platforms/cell/beat_iommu.c @@ -76,7 +76,7 @@ static void __init celleb_init_direct_mapping(void) static void celleb_dma_dev_setup(struct device *dev) { - dev->archdata.dma_ops = get_pci_dma_ops(); + set_dma_ops(dev, &dma_direct_ops); set_dma_offset(dev, celleb_dma_direct_offset); } @@ -106,7 +106,6 @@ static struct notifier_block celleb_of_bus_notifier = { static int __init celleb_init_iommu(void) { celleb_init_direct_mapping(); - set_pci_dma_ops(&dma_direct_ops); ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup; bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier); -- cgit v1.2.3 From 34c4d012554ed8c99b3fb25baea9bab3507e9f76 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:27:02 +0000 Subject: powerpc/dart: iommu table cleanup No need to set the device tree device_node pci node iommu pointer, its only used for dlpar remove. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/sysdev/dart_iommu.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 17cf15ec38be..8e9e06a7ca59 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -312,17 +312,10 @@ static void pci_dma_dev_setup_dart(struct pci_dev *dev) static void pci_dma_bus_setup_dart(struct pci_bus *bus) { - struct device_node *dn; - if (!iommu_table_dart_inited) { iommu_table_dart_inited = 1; iommu_table_dart_setup(); } - - dn = pci_bus_to_OF_node(bus); - - if (dn) - PCI_DN(dn)->iommu_table = &iommu_table_dart; } static bool dart_device_on_pcie(struct device *dev) @@ -373,7 +366,7 @@ void __init iommu_init_early_dart(void) if (dn == NULL) { dn = of_find_compatible_node(NULL, "dart", "u4-dart"); if (dn == NULL) - goto bail; + return; /* use default direct_dma_ops */ dart_is_u4 = 1; } -- cgit v1.2.3 From a8daac8a517dacfea951424f67c1f07e1f76b2ad Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:27:03 +0000 Subject: powerpc/pseries: iommu cleanup No need to initialize per-cpu pointer to NULL, it is the default. Direct dma ops and no setup are the defaults, no need to set for iommu-off. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Reviewed-by: Grant Likely Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index fa2906a103dd..9fecb313a4c9 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -140,7 +140,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static DEFINE_PER_CPU(u64 *, tce_page) = NULL; +static DEFINE_PER_CPU(u64 *, tce_page); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @@ -589,13 +589,8 @@ static struct notifier_block iommu_reconfig_nb = { /* These are called very early. */ void iommu_init_early_pSeries(void) { - if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) { - /* Direct I/O, IOMMU off */ - ppc_md.pci_dma_dev_setup = NULL; - ppc_md.pci_dma_bus_setup = NULL; - set_pci_dma_ops(&dma_direct_ops); + if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) return; - } if (firmware_has_feature(FW_FEATURE_LPAR)) { if (firmware_has_feature(FW_FEATURE_MULTITCE)) { -- cgit v1.2.3 From f6aedd8606ae673f8e1f4d972fc86c451fbc8ba7 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:11 +0000 Subject: powerpc/macio: Ensure all dma routines get copied over Also add a comment to dev_archdata, indicating that changes there need to be verified against the driver code. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/device.h | 6 ++++++ drivers/macintosh/macio_asic.c | 7 +++---- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index a3954e4fcbe2..16d25c0974be 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -9,6 +9,12 @@ struct dma_map_ops; struct device_node; +/* + * Arch extensions to struct device. + * + * When adding fields, consider macio_add_one_device in + * drivers/macintosh/macio_asic.c + */ struct dev_archdata { /* DMA operations on that device */ struct dma_map_ops *dma_ops; diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index b6e7ddc09d76..4daf9e5a7736 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -387,11 +387,10 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, /* Set the DMA ops to the ones from the PCI device, this could be * fishy if we didn't know that on PowerMac it's always direct ops * or iommu ops that will work fine + * + * To get all the fields, copy all archdata */ - dev->ofdev.dev.archdata.dma_ops = - chip->lbus.pdev->dev.archdata.dma_ops; - dev->ofdev.dev.archdata.dma_data = - chip->lbus.pdev->dev.archdata.dma_data; + dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata; #endif /* CONFIG_PCI */ #ifdef DEBUG -- cgit v1.2.3 From cd34206e949b66d3c5fa3e4d2905aa4af29d1b85 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:12 +0000 Subject: powerpc: Add memory_hotplug_max() Add a function to get the maximum address that can be hotplug added. This is needed to calculate the size of the tce table needed to cover all memory in 1:1 mode. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mmzone.h | 5 +++++ arch/powerpc/mm/numa.c | 26 ++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index aac87cbceb57..fd3fd58bad84 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -33,6 +33,9 @@ extern int numa_cpu_lookup_table[]; extern cpumask_var_t node_to_cpumask_map[]; #ifdef CONFIG_MEMORY_HOTPLUG extern unsigned long max_pfn; +u64 memory_hotplug_max(void); +#else +#define memory_hotplug_max() memblock_end_of_DRAM() #endif /* @@ -42,6 +45,8 @@ extern unsigned long max_pfn; #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) +#else +#define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 74505b245374..8c0944c465f6 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1247,4 +1247,30 @@ int hot_add_scn_to_nid(unsigned long scn_addr) return nid; } +static u64 hot_add_drconf_memory_max(void) +{ + struct device_node *memory = NULL; + unsigned int drconf_cell_cnt = 0; + u64 lmb_size = 0; + const u32 *dm = 0; + + memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (memory) { + drconf_cell_cnt = of_get_drconf_memory(memory, &dm); + lmb_size = of_get_lmb_size(memory); + of_node_put(memory); + } + return lmb_size * drconf_cell_cnt; +} + +/* + * memory_hotplug_max - return max address of memory that may be added + * + * This is currently only used on systems that support drconfig memory + * hotplug. + */ +u64 memory_hotplug_max(void) +{ + return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM()); +} #endif /* CONFIG_MEMORY_HOTPLUG */ -- cgit v1.2.3 From 467d93a7ee64a5c8f675589d658ce3b8b502d288 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sat, 30 Oct 2010 08:10:41 +0000 Subject: powerpc/cell: Use vzalloc rather than vmalloc and memset in spu_alloc_lscsa_std Hi, We can get rid of a memset in arch/powerpc/platforms/cell/spufs/lscsa_alloc.c::spu_alloc_lscsa_std() by using vzalloc() rather than vmalloc()+memset(). Completely untested patch below since I have no hardware nor tools to compile this. Signed-off-by: Jesper Juhl Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/cell/spufs/lscsa_alloc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c index a101abf17504..3b894f585280 100644 --- a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c +++ b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c @@ -36,10 +36,9 @@ static int spu_alloc_lscsa_std(struct spu_state *csa) struct spu_lscsa *lscsa; unsigned char *p; - lscsa = vmalloc(sizeof(struct spu_lscsa)); + lscsa = vzalloc(sizeof(struct spu_lscsa)); if (!lscsa) return -ENOMEM; - memset(lscsa, 0, sizeof(struct spu_lscsa)); csa->lscsa = lscsa; /* Set LS pages reserved to allow for user-space mapping. */ -- cgit v1.2.3 From f7dec88781dd3ad62ebd4acc515c8938c15353ac Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Thu, 4 Nov 2010 13:29:40 +0000 Subject: powerpc/iseries: Remove unused mf_getSrcHistory function and caller. On Tue, 2 Nov 2010, Michael Ellerman wrote: > On Mon, 2010-11-01 at 22:20 +0100, Jesper Juhl wrote: > > Hi Stephen, > > > > On Tue, 2 Nov 2010, Stephen Rothwell wrote: > > > > > On Mon, 1 Nov 2010 21:06:23 +0100 (CET) Jesper Juhl wrote: > > > > > > > > Remove unused function 'mf_getSrcHistory' (that will never be used ever > > > > according to Stephen Rothwell). > > > > > > > > Signed-off-by: Jesper Juhl > > > > > > Acked-by: Stephen Rothwell > > > > > > > Ok, so if you are the (unofficial) iSeries maintainer and you don't merge > > the patch somewhere that'll eventually go up-stream, but just ACK it > > (thank you for that btw), then where do I send it to get it merged? > > Here. ie. linuxppc-dev. > > But, while you're removing it you should remove the #if 0'ed callsite as > well, see mf_src_proc_show() in that file. :) > Done. See patch below. Remove unused function 'mf_getSrcHistory' (that will never be used ever according to Stephen Rothwell) and also remove most of (under 'if 0') code from mf_src_proc_show() where the function was called. Signed-off-by: Jesper Juhl Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/iseries/mf.c | 62 ------------------------------------- 1 file changed, 62 deletions(-) diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index 42d0a886de05..b5e026bdca21 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -1045,71 +1045,9 @@ static const struct file_operations mf_side_proc_fops = { .write = mf_side_proc_write, }; -#if 0 -static void mf_getSrcHistory(char *buffer, int size) -{ - struct IplTypeReturnStuff return_stuff; - struct pending_event *ev = new_pending_event(); - int rc = 0; - char *pages[4]; - - pages[0] = kmalloc(4096, GFP_ATOMIC); - pages[1] = kmalloc(4096, GFP_ATOMIC); - pages[2] = kmalloc(4096, GFP_ATOMIC); - pages[3] = kmalloc(4096, GFP_ATOMIC); - if ((ev == NULL) || (pages[0] == NULL) || (pages[1] == NULL) - || (pages[2] == NULL) || (pages[3] == NULL)) - return -ENOMEM; - - return_stuff.xType = 0; - return_stuff.xRc = 0; - return_stuff.xDone = 0; - ev->event.hp_lp_event.xSubtype = 6; - ev->event.hp_lp_event.x.xSubtypeData = - subtype_data('M', 'F', 'V', 'I'); - ev->event.data.vsp_cmd.xEvent = &return_stuff; - ev->event.data.vsp_cmd.cmd = 4; - ev->event.data.vsp_cmd.lp_index = HvLpConfig_getLpIndex(); - ev->event.data.vsp_cmd.result_code = 0xFF; - ev->event.data.vsp_cmd.reserved = 0; - ev->event.data.vsp_cmd.sub_data.page[0] = iseries_hv_addr(pages[0]); - ev->event.data.vsp_cmd.sub_data.page[1] = iseries_hv_addr(pages[1]); - ev->event.data.vsp_cmd.sub_data.page[2] = iseries_hv_addr(pages[2]); - ev->event.data.vsp_cmd.sub_data.page[3] = iseries_hv_addr(pages[3]); - mb(); - if (signal_event(ev) != 0) - return; - - while (return_stuff.xDone != 1) - udelay(10); - if (return_stuff.xRc == 0) - memcpy(buffer, pages[0], size); - kfree(pages[0]); - kfree(pages[1]); - kfree(pages[2]); - kfree(pages[3]); -} -#endif - static int mf_src_proc_show(struct seq_file *m, void *v) { -#if 0 - int len; - - mf_getSrcHistory(page, count); - len = count; - len -= off; - if (len < count) { - *eof = 1; - if (len <= 0) - return 0; - } else - len = count; - *start = page + off; - return len; -#else return 0; -#endif } static int mf_src_proc_open(struct inode *inode, struct file *file) -- cgit v1.2.3 From 698193d85aa8aba003bacd09e40bbd78474fb00f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 8 Nov 2010 17:31:36 +0000 Subject: powerpc: Consolidate obj-y assignments No need to have three of them. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/Makefile | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 36c30f31ec93..3bb2a3e6a337 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -29,8 +29,10 @@ endif obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ - signal.o sysfs.o cacheinfo.o -obj-y += vdso32/ + signal.o sysfs.o cacheinfo.o time.o \ + prom.o traps.o setup-common.o \ + udbg.o misc.o io.o dma.o \ + misc_$(CONFIG_WORD_SIZE).o vdso32/ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o @@ -80,9 +82,6 @@ extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds -obj-y += time.o prom.o traps.o setup-common.o \ - udbg.o misc.o io.o dma.o \ - misc_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o obj-$(CONFIG_KGDB) += kgdb.o -- cgit v1.2.3 From 36f567b42932a81866bf723779703ecc84cf714b Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Tue, 9 Nov 2010 13:24:48 +0000 Subject: powerpc: Add VPHN firmware feature This simple patch adds the firmware feature for VPHN to the firmware features bitmask. Signed-off-by: Jesse Larrew Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/firmware.h | 3 ++- arch/powerpc/include/asm/hvcall.h | 1 + arch/powerpc/platforms/pseries/firmware.c | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 20778a405d7a..4ef662e4a31d 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -46,6 +46,7 @@ #define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000) #define FW_FEATURE_BEAT ASM_CONST(0x0000000001000000) #define FW_FEATURE_CMO ASM_CONST(0x0000000002000000) +#define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000) #ifndef __ASSEMBLY__ @@ -59,7 +60,7 @@ enum { FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN | FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | - FW_FEATURE_CMO, + FW_FEATURE_CMO | FW_FEATURE_VPHN, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR, FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR, diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index bf86b03d5af2..ec089acfa56b 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -232,6 +232,7 @@ #define H_GET_EM_PARMS 0x2B8 #define H_SET_MPP 0x2D0 #define H_GET_MPP 0x2D4 +#define H_HOME_NODE_ASSOCIATIVITY 0x2EC #define H_BEST_ENERGY 0x2F4 #define MAX_HCALL_OPCODE H_BEST_ENERGY diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 0a14d8cd314f..0b0eff0cce35 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -55,6 +55,7 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = { {FW_FEATURE_XDABR, "hcall-xdabr"}, {FW_FEATURE_MULTITCE, "hcall-multi-tce"}, {FW_FEATURE_SPLPAR, "hcall-splpar"}, + {FW_FEATURE_VPHN, "hcall-vphn"}, }; /* Build up the firmware features bitmask using the contents of -- cgit v1.2.3 From 93fe56e99fb946fcd4244741bfc7af6638f1cac7 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 17 Nov 2010 18:52:42 +0000 Subject: powerpc: Remove unneeded cpu_setup/restore from POWER7 cputable entry These are not needed so just remove them Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/cputable.c | 2 -- arch/powerpc/kernel/misc.S | 5 ----- 2 files changed, 7 deletions(-) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 96a908f1cd87..75062cb40e7b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -457,8 +457,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, .oprofile_mmcra_sihv = POWER6_MMCRA_SIHV, diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 2d29752cbe16..b69463ec2010 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -122,8 +122,3 @@ _GLOBAL(longjmp) mtlr r0 mr r3,r4 blr - -_GLOBAL(__setup_cpu_power7) -_GLOBAL(__restore_cpu_power7) - /* place holder */ - blr -- cgit v1.2.3 From 1d32bb1827da3ebb413f6cb492990a42ab030559 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 17 Nov 2010 18:52:43 +0000 Subject: powerpc: Remove POWER6 oprofile workarounds for POWER7 These are not needed on POWER7 so remove them. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/cputable.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 75062cb40e7b..65813ee98b7d 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -459,10 +459,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, - .oprofile_mmcra_sihv = POWER6_MMCRA_SIHV, - .oprofile_mmcra_sipr = POWER6_MMCRA_SIPR, - .oprofile_mmcra_clear = POWER6_MMCRA_THRM | - POWER6_MMCRA_OTHER, .platform = "power7", }, { /* Cell Broadband Engine */ -- cgit v1.2.3 From 6f08cb3be6345bc354e48131f7466766db4d355a Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 17 Nov 2010 18:52:44 +0000 Subject: powerpc: Add POWER7+ cputable entry This adds the POWER7+ cputable entry for the PVR 0x004a0000. Rest is the same as vanilla POWER7. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/cputable.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 65813ee98b7d..be5ab18b03b5 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -461,6 +461,22 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .platform = "power7", }, + { /* Power7+ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004A0000, + .cpu_name = "POWER7+ (raw)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .mmu_features = MMU_FTR_HPTE_TABLE | + MMU_FTR_TLBIE_206, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power7", + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power7+", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, -- cgit v1.2.3 From 0b97fee0ef9b0a0445520f90980410f905c6f9da Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 17 Nov 2010 18:52:45 +0000 Subject: powerpc/mm: Avoid avoidable void* pointer Change pgdir from a void to real type. Having this as a void is stupid and has already caused 1 bug. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/hash_utils_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 5e9584405c45..a5991facddce 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1070,7 +1070,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap) { unsigned long vsid; - void *pgdir; + pgd_t *pgdir; pte_t *ptep; unsigned long flags; int rc, ssize, local = 0; -- cgit v1.2.3 From 46f5221049bb46b0188aad6b6dfab5dbc778be22 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 18 Nov 2010 15:06:17 +0000 Subject: powerpc: Remove second definition of STACK_FRAME_OVERHEAD Since STACK_FRAME_OVERHEAD is defined in asm/ptrace.h and that is ASSEMBER safe, we can just include that instead of going via asm-offsets.h. Signed-off-by: Stephen Rothwell Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/asm-offsets.c | 1 - arch/powerpc/kernel/entry_32.S | 1 + arch/powerpc/kernel/exceptions-64s.S | 1 + arch/powerpc/kernel/fpu.S | 1 + arch/powerpc/kernel/head_40x.S | 1 + arch/powerpc/kernel/head_44x.S | 1 + arch/powerpc/kernel/head_64.S | 1 + arch/powerpc/kernel/head_8xx.S | 1 + arch/powerpc/kernel/head_fsl_booke.S | 1 + arch/powerpc/kernel/misc_32.S | 1 + arch/powerpc/kernel/misc_64.S | 1 + arch/powerpc/kernel/ppc_save_regs.S | 1 + arch/powerpc/kernel/vector.S | 1 + arch/powerpc/platforms/pseries/hvCall.S | 1 + 14 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index bd0df2e6aa8f..23e6a93145ab 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -209,7 +209,6 @@ int main(void) DEFINE(RTASENTRY, offsetof(struct rtas_t, entry)); /* Interrupt register frame */ - DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD); DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE); DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index ed4aeb96398b..c22dc1ec1c94 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -31,6 +31,7 @@ #include #include #include +#include #undef SHOW_SYSCALLS #undef SHOW_SYSCALLS_TASK diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 9f8b01d6466f..8a817995b4cd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -13,6 +13,7 @@ */ #include +#include /* * We layout physical memory as follows: diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index e86c040ae585..de369558bf0a 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -23,6 +23,7 @@ #include #include #include +#include #ifdef CONFIG_VSX #define REST_32FPVSRS(n,c,base) \ diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 8278e8bad5a0..9dd21a8c4d52 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -40,6 +40,7 @@ #include #include #include +#include /* As with the other PowerPC ports, it is expected that when code * execution begins here, the following registers contain valid, yet diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 562305b40a8e..cbb3436b592d 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -37,6 +37,7 @@ #include #include #include +#include #include #include "head_booke.h" diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f0dd577e4a5b..ce41b97eb512 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -38,6 +38,7 @@ #include #include #include +#include /* The physical memory is layed out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 1f1a04b5c2a4..1cbf64e6b416 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -29,6 +29,7 @@ #include #include #include +#include /* Macro to make the code more readable. */ #ifdef CONFIG_8xx_CPU6 diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 529b817f473b..3e02710d9562 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -41,6 +41,7 @@ #include #include #include +#include #include "head_booke.h" /* As with the other PowerPC ports, it is expected that when code diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index a7a570dcdd57..094bd9821ad4 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -30,6 +30,7 @@ #include #include #include +#include .text diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e5144906a56d..206a321a71d3 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -25,6 +25,7 @@ #include #include #include +#include .text diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S index 5113bd2285e1..e83ba3f078e4 100644 --- a/arch/powerpc/kernel/ppc_save_regs.S +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -11,6 +11,7 @@ #include #include #include +#include /* * Grab the register values as they are now. diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index fe460482fa68..9de6f396cf85 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -5,6 +5,7 @@ #include #include #include +#include /* * load_up_altivec(unused, unused, tsk) diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 48d20573e4de..fd05fdee576a 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -11,6 +11,7 @@ #include #include #include +#include #define STK_PARM(i) (48 + ((i)-3)*8) -- cgit v1.2.3 From d164f6d4f9108126f69ba2963cf6fb7ef4ba9232 Mon Sep 17 00:00:00 2001 From: Victor Gallardo Date: Fri, 8 Oct 2010 10:25:27 +0000 Subject: powerpc/4xx: Add suspend and idle support Add suspend/resume support for 4xx compatible CPUs. See /sys/power/state for available power states configured in. Add two different idle states (idle-wait and idle-doze) controlled via sysfs. Default is idle-wait. cat /sys/devices/system/cpu/cpu0/idle [wait] doze To save additional power, use idle-doze. echo doze > /sys/devices/system/cpu/cpu0/idle cat /sys/devices/system/cpu/cpu0/idle wait [doze] Signed-off-by: Victor Gallardo Signed-off-by: Josh Boyer --- Documentation/powerpc/dts-bindings/4xx/cpm.txt | 52 ++++ arch/powerpc/Kconfig | 13 +- arch/powerpc/platforms/44x/Makefile | 5 +- arch/powerpc/sysdev/Makefile | 1 + arch/powerpc/sysdev/ppc4xx_cpm.c | 346 +++++++++++++++++++++++++ 5 files changed, 413 insertions(+), 4 deletions(-) create mode 100644 Documentation/powerpc/dts-bindings/4xx/cpm.txt create mode 100644 arch/powerpc/sysdev/ppc4xx_cpm.c diff --git a/Documentation/powerpc/dts-bindings/4xx/cpm.txt b/Documentation/powerpc/dts-bindings/4xx/cpm.txt new file mode 100644 index 000000000000..ee459806d35e --- /dev/null +++ b/Documentation/powerpc/dts-bindings/4xx/cpm.txt @@ -0,0 +1,52 @@ +PPC4xx Clock Power Management (CPM) node + +Required properties: + - compatible : compatible list, currently only "ibm,cpm" + - dcr-access-method : "native" + - dcr-reg : < DCR register range > + +Optional properties: + - er-offset : All 4xx SoCs with a CPM controller have + one of two different order for the CPM + registers. Some have the CPM registers + in the following order (ER,FR,SR). The + others have them in the following order + (SR,ER,FR). For the second case set + er-offset = <1>. + - unused-units : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set to turn off unused + devices. + - idle-doze : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set to turn off unused + devices. This is usually just CPM[CPU]. + - standby : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set on standby and + restored on resume. + - suspend : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set on suspend (mem) and + restored on resume. Note, for standby + and suspend the corresponding bits can + be different or the same. Usually for + standby only class 2 and 3 units are set. + However, the interface does not care. + If they are the same, the additional + power saving will be seeing if support + is available to put the DDR in self + refresh mode and any additional power + saving techniques for the specific SoC. + +Example: + CPM0: cpm { + compatible = "ibm,cpm"; + dcr-access-method = "native"; + dcr-reg = <0x160 0x003>; + er-offset = <0>; + unused-units = <0x00000100>; + idle-doze = <0x02000000>; + standby = <0xfeff0000>; + suspend = <0xfeff791d>; +}; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 06d742c3fbcf..e16b4988f825 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -212,7 +212,7 @@ config ARCH_HIBERNATION_POSSIBLE config ARCH_SUSPEND_POSSIBLE def_bool y depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \ - PPC_85xx || PPC_86xx || PPC_PSERIES + PPC_85xx || PPC_86xx || PPC_PSERIES || 44x || 40x config PPC_DCR_NATIVE bool @@ -598,13 +598,11 @@ config EXTRA_TARGETS If unsure, leave blank -if !44x || BROKEN config ARCH_WANTS_FREEZER_CONTROL def_bool y depends on ADB_PMU source kernel/power/Kconfig -endif config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" @@ -685,6 +683,15 @@ config FSL_PMC Freescale MPC85xx/MPC86xx power management controller support (suspend/resume). For MPC83xx see platforms/83xx/suspend.c +config PPC4xx_CPM + bool + default y + depends on SUSPEND && (44x || 40x) + help + PPC4xx Clock Power Management (CPM) support (suspend/resume). + It also enables support for two different idle states (idle-wait + and idle-doze). + config 4xx_SOC bool diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index 82ff326e0795..c04d16df8488 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -1,4 +1,7 @@ -obj-$(CONFIG_44x) := misc_44x.o idle.o +obj-$(CONFIG_44x) += misc_44x.o +ifneq ($(CONFIG_PPC4xx_CPM),y) +obj-$(CONFIG_44x) += idle.o +endif obj-$(CONFIG_PPC44x_SIMPLE) += ppc44x_simple.o obj-$(CONFIG_EBONY) += ebony.o obj-$(CONFIG_SAM440EP) += sam440ep.o diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 0bef9dacb64e..9c2973479142 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_OF_RTC) += of_rtc.o ifeq ($(CONFIG_PCI),y) obj-$(CONFIG_4xx) += ppc4xx_pci.o endif +obj-$(CONFIG_PPC4xx_CPM) += ppc4xx_cpm.o obj-$(CONFIG_PPC4xx_GPIO) += ppc4xx_gpio.o obj-$(CONFIG_CPM) += cpm_common.o diff --git a/arch/powerpc/sysdev/ppc4xx_cpm.c b/arch/powerpc/sysdev/ppc4xx_cpm.c new file mode 100644 index 000000000000..73b86cc5ea74 --- /dev/null +++ b/arch/powerpc/sysdev/ppc4xx_cpm.c @@ -0,0 +1,346 @@ +/* + * PowerPC 4xx Clock and Power Management + * + * Copyright (C) 2010, Applied Micro Circuits Corporation + * Victor Gallardo (vgallardo@apm.com) + * + * Based on arch/powerpc/platforms/44x/idle.c: + * Jerone Young + * Copyright 2008 IBM Corp. + * + * Based on arch/powerpc/sysdev/fsl_pmc.c: + * Anton Vorontsov + * Copyright 2009 MontaVista Software, Inc. + * + * See file CREDITS for list of people who contributed to this + * project. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, + * MA 02111-1307 USA + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define CPM_ER 0 +#define CPM_FR 1 +#define CPM_SR 2 + +#define CPM_IDLE_WAIT 0 +#define CPM_IDLE_DOZE 1 + +struct cpm { + dcr_host_t dcr_host; + unsigned int dcr_offset[3]; + unsigned int powersave_off; + unsigned int unused; + unsigned int idle_doze; + unsigned int standby; + unsigned int suspend; +}; + +static struct cpm cpm; + +struct cpm_idle_mode { + unsigned int enabled; + const char *name; +}; + +static struct cpm_idle_mode idle_mode[] = { + [CPM_IDLE_WAIT] = { 1, "wait" }, /* default */ + [CPM_IDLE_DOZE] = { 0, "doze" }, +}; + +static unsigned int cpm_set(unsigned int cpm_reg, unsigned int mask) +{ + unsigned int value; + + /* CPM controller supports 3 different types of sleep interface + * known as class 1, 2 and 3. For class 1 units, they are + * unconditionally put to sleep when the corresponding CPM bit is + * set. For class 2 and 3 units this is not case; if they can be + * put to to sleep, they will. Here we do not verify, we just + * set them and expect them to eventually go off when they can. + */ + value = dcr_read(cpm.dcr_host, cpm.dcr_offset[cpm_reg]); + dcr_write(cpm.dcr_host, cpm.dcr_offset[cpm_reg], value | mask); + + /* return old state, to restore later if needed */ + return value; +} + +static void cpm_idle_wait(void) +{ + unsigned long msr_save; + + /* save off initial state */ + msr_save = mfmsr(); + /* sync required when CPM0_ER[CPU] is set */ + mb(); + /* set wait state MSR */ + mtmsr(msr_save|MSR_WE|MSR_EE|MSR_CE|MSR_DE); + isync(); + /* return to initial state */ + mtmsr(msr_save); + isync(); +} + +static void cpm_idle_sleep(unsigned int mask) +{ + unsigned int er_save; + + /* update CPM_ER state */ + er_save = cpm_set(CPM_ER, mask); + + /* go to wait state so that CPM0_ER[CPU] can take effect */ + cpm_idle_wait(); + + /* restore CPM_ER state */ + dcr_write(cpm.dcr_host, cpm.dcr_offset[CPM_ER], er_save); +} + +static void cpm_idle_doze(void) +{ + cpm_idle_sleep(cpm.idle_doze); +} + +static void cpm_idle_config(int mode) +{ + int i; + + if (idle_mode[mode].enabled) + return; + + for (i = 0; i < ARRAY_SIZE(idle_mode); i++) + idle_mode[i].enabled = 0; + + idle_mode[mode].enabled = 1; +} + +static ssize_t cpm_idle_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + char *s = buf; + int i; + + for (i = 0; i < ARRAY_SIZE(idle_mode); i++) { + if (idle_mode[i].enabled) + s += sprintf(s, "[%s] ", idle_mode[i].name); + else + s += sprintf(s, "%s ", idle_mode[i].name); + } + + *(s-1) = '\n'; /* convert the last space to a newline */ + + return s - buf; +} + +static ssize_t cpm_idle_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int i; + char *p; + int len; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + for (i = 0; i < ARRAY_SIZE(idle_mode); i++) { + if (strncmp(buf, idle_mode[i].name, len) == 0) { + cpm_idle_config(i); + return n; + } + } + + return -EINVAL; +} + +static struct kobj_attribute cpm_idle_attr = + __ATTR(idle, 0644, cpm_idle_show, cpm_idle_store); + +static void cpm_idle_config_sysfs(void) +{ + struct sys_device *sys_dev; + unsigned long ret; + + sys_dev = get_cpu_sysdev(0); + + ret = sysfs_create_file(&sys_dev->kobj, + &cpm_idle_attr.attr); + if (ret) + printk(KERN_WARNING + "cpm: failed to create idle sysfs entry\n"); +} + +static void cpm_idle(void) +{ + if (idle_mode[CPM_IDLE_DOZE].enabled) + cpm_idle_doze(); + else + cpm_idle_wait(); +} + +static int cpm_suspend_valid(suspend_state_t state) +{ + switch (state) { + case PM_SUSPEND_STANDBY: + return !!cpm.standby; + case PM_SUSPEND_MEM: + return !!cpm.suspend; + default: + return 0; + } +} + +static void cpm_suspend_standby(unsigned int mask) +{ + unsigned long tcr_save; + + /* disable decrement interrupt */ + tcr_save = mfspr(SPRN_TCR); + mtspr(SPRN_TCR, tcr_save & ~TCR_DIE); + + /* go to sleep state */ + cpm_idle_sleep(mask); + + /* restore decrement interrupt */ + mtspr(SPRN_TCR, tcr_save); +} + +static int cpm_suspend_enter(suspend_state_t state) +{ + switch (state) { + case PM_SUSPEND_STANDBY: + cpm_suspend_standby(cpm.standby); + break; + case PM_SUSPEND_MEM: + cpm_suspend_standby(cpm.suspend); + break; + } + + return 0; +} + +static struct platform_suspend_ops cpm_suspend_ops = { + .valid = cpm_suspend_valid, + .enter = cpm_suspend_enter, +}; + +static int cpm_get_uint_property(struct device_node *np, + const char *name) +{ + int len; + const unsigned int *prop = of_get_property(np, name, &len); + + if (prop == NULL || len < sizeof(u32)) + return 0; + + return *prop; +} + +static int __init cpm_init(void) +{ + struct device_node *np; + int dcr_base, dcr_len; + int ret = 0; + + if (!cpm.powersave_off) { + cpm_idle_config(CPM_IDLE_WAIT); + ppc_md.power_save = &cpm_idle; + } + + np = of_find_compatible_node(NULL, NULL, "ibm,cpm"); + if (!np) { + ret = -EINVAL; + goto out; + } + + dcr_base = dcr_resource_start(np, 0); + dcr_len = dcr_resource_len(np, 0); + + if (dcr_base == 0 || dcr_len == 0) { + printk(KERN_ERR "cpm: could not parse dcr property for %s\n", + np->full_name); + ret = -EINVAL; + goto out; + } + + cpm.dcr_host = dcr_map(np, dcr_base, dcr_len); + + if (!DCR_MAP_OK(cpm.dcr_host)) { + printk(KERN_ERR "cpm: failed to map dcr property for %s\n", + np->full_name); + ret = -EINVAL; + goto out; + } + + /* All 4xx SoCs with a CPM controller have one of two + * different order for the CPM registers. Some have the + * CPM registers in the following order (ER,FR,SR). The + * others have them in the following order (SR,ER,FR). + */ + + if (cpm_get_uint_property(np, "er-offset") == 0) { + cpm.dcr_offset[CPM_ER] = 0; + cpm.dcr_offset[CPM_FR] = 1; + cpm.dcr_offset[CPM_SR] = 2; + } else { + cpm.dcr_offset[CPM_ER] = 1; + cpm.dcr_offset[CPM_FR] = 2; + cpm.dcr_offset[CPM_SR] = 0; + } + + /* Now let's see what IPs to turn off for the following modes */ + + cpm.unused = cpm_get_uint_property(np, "unused-units"); + cpm.idle_doze = cpm_get_uint_property(np, "idle-doze"); + cpm.standby = cpm_get_uint_property(np, "standby"); + cpm.suspend = cpm_get_uint_property(np, "suspend"); + + /* If some IPs are unused let's turn them off now */ + + if (cpm.unused) { + cpm_set(CPM_ER, cpm.unused); + cpm_set(CPM_FR, cpm.unused); + } + + /* Now let's export interfaces */ + + if (!cpm.powersave_off && cpm.idle_doze) + cpm_idle_config_sysfs(); + + if (cpm.standby || cpm.suspend) + suspend_set_ops(&cpm_suspend_ops); +out: + if (np) + of_node_put(np); + return ret; +} + +late_initcall(cpm_init); + +static int __init cpm_powersave_off(char *arg) +{ + cpm.powersave_off = 1; + return 0; +} +__setup("powersave=off", cpm_powersave_off); -- cgit v1.2.3 From 05ed60874e7fc958707183b71ea47260c1dab358 Mon Sep 17 00:00:00 2001 From: Victor Gallardo Date: Fri, 8 Oct 2010 10:26:13 +0000 Subject: powerpc/4xx: Add Kilauea suspend and idle support - Add Clock Power Management (CPM) node to dts tree - Add idle-doze entry in CPM node - Add standby entry in CPM node - Add PM and SUSPEND support by default in defconfig - Add NO_HZ and CONFIG_HIGH_RES_TIMERS support by default in defconfig Signed-off-by: Victor Gallardo Signed-off-by: Josh Boyer --- arch/powerpc/boot/dts/kilauea.dts | 9 +++++++++ arch/powerpc/configs/40x/kilauea_defconfig | 5 +++++ 2 files changed, 14 insertions(+) diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts index 083e68eeaca4..89edb16649c3 100644 --- a/arch/powerpc/boot/dts/kilauea.dts +++ b/arch/powerpc/boot/dts/kilauea.dts @@ -82,6 +82,15 @@ interrupt-parent = <&UIC0>; }; + CPM0: cpm { + compatible = "ibm,cpm"; + dcr-access-method = "native"; + dcr-reg = <0x0b0 0x003>; + unused-units = <0x00000000>; + idle-doze = <0x02000000>; + standby = <0xe3e74800>; + }; + plb { compatible = "ibm,plb-405ex", "ibm,plb4"; #address-cells = <1>; diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig index 4e19ee7ce4ee..34b8c1a1e752 100644 --- a/arch/powerpc/configs/40x/kilauea_defconfig +++ b/arch/powerpc/configs/40x/kilauea_defconfig @@ -12,6 +12,8 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_KILAUEA=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y # CONFIG_WALNUT is not set CONFIG_SPARSE_IRQ=y CONFIG_PCI=y @@ -42,6 +44,9 @@ CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_NDFC=y CONFIG_PROC_DEVICETREE=y +CONFIG_PM=y +CONFIG_SUSPEND=y +CONFIG_PPC4xx_CPM=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set -- cgit v1.2.3 From ee2ffd8bbb2170f9b52fc8ff4aebe9702e0de651 Mon Sep 17 00:00:00 2001 From: Victor Gallardo Date: Fri, 8 Oct 2010 10:25:44 +0000 Subject: powerpc/4xx: Add Canyonlands suspend and idle support - Add Clock Power Management (CPM) node to dts tree - Add idle-doze entry in CPM node - Add standby entry in CPM node - Add PM and SUSPEND support by default in defconfig - Remove UART2 and UART3 as they are unused, this will allow CPM to put unused-units (UART2 and UART3) to sleep. Signed-off-by: Victor Gallardo Signed-off-by: Josh Boyer --- arch/powerpc/boot/dts/canyonlands.dts | 31 ++++++++------------------ arch/powerpc/configs/44x/canyonlands_defconfig | 3 +++ 2 files changed, 12 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts index a30370396250..5b27a4b74b79 100644 --- a/arch/powerpc/boot/dts/canyonlands.dts +++ b/arch/powerpc/boot/dts/canyonlands.dts @@ -105,6 +105,15 @@ dcr-reg = <0x00c 0x002>; }; + CPM0: cpm { + compatible = "ibm,cpm"; + dcr-access-method = "native"; + dcr-reg = <0x160 0x003>; + unused-units = <0x00000100>; + idle-doze = <0x02000000>; + standby = <0xfeff791d>; + }; + L2C0: l2c { compatible = "ibm,l2-cache-460ex", "ibm,l2-cache"; dcr-reg = <0x020 0x008 /* Internal SRAM DCR's */ @@ -270,28 +279,6 @@ interrupts = <0x1 0x4>; }; - UART2: serial@ef600500 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0xef600500 0x00000008>; - virtual-reg = <0xef600500>; - clock-frequency = <0>; /* Filled in by U-Boot */ - current-speed = <0>; /* Filled in by U-Boot */ - interrupt-parent = <&UIC1>; - interrupts = <28 0x4>; - }; - - UART3: serial@ef600600 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0xef600600 0x00000008>; - virtual-reg = <0xef600600>; - clock-frequency = <0>; /* Filled in by U-Boot */ - current-speed = <0>; /* Filled in by U-Boot */ - interrupt-parent = <&UIC1>; - interrupts = <29 0x4>; - }; - IIC0: i2c@ef600700 { compatible = "ibm,iic-460ex", "ibm,iic"; reg = <0xef600700 0x00000014>; diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig index 45c64d818b2a..17e4dd98eed7 100644 --- a/arch/powerpc/configs/44x/canyonlands_defconfig +++ b/arch/powerpc/configs/44x/canyonlands_defconfig @@ -42,6 +42,9 @@ CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_NDFC=y CONFIG_PROC_DEVICETREE=y +CONFIG_PM=y +CONFIG_SUSPEND=y +CONFIG_PPC4xx_CPM=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set -- cgit v1.2.3 From 74d51d029818eca9d1aec22dd2895e269c0044b1 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 14:45:24 +1000 Subject: powerpc/nvram: Move things out of asm/nvram.h This moves a bunch of definitions out of asm/nvram.h to the files that use them or just outright remove completely unused stuff. We leave the partition signatures definitions, they will be useful Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/nvram.h | 42 ++-------------------------------- arch/powerpc/kernel/nvram_64.c | 21 ++++++++++++++++- arch/powerpc/platforms/chrp/time.c | 4 ++++ arch/powerpc/platforms/pseries/nvram.c | 2 ++ 4 files changed, 28 insertions(+), 41 deletions(-) diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index 850b72f27445..459dc09ecbd8 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -10,31 +10,7 @@ #ifndef _ASM_POWERPC_NVRAM_H #define _ASM_POWERPC_NVRAM_H -#include - -#define NVRW_CNT 0x20 -#define NVRAM_HEADER_LEN 16 /* sizeof(struct nvram_header) */ -#define NVRAM_BLOCK_LEN 16 -#define NVRAM_MAX_REQ (2080/NVRAM_BLOCK_LEN) -#define NVRAM_MIN_REQ (1056/NVRAM_BLOCK_LEN) - -#define NVRAM_AS0 0x74 -#define NVRAM_AS1 0x75 -#define NVRAM_DATA 0x77 - - -/* RTC Offsets */ - -#define MOTO_RTC_SECONDS 0x1FF9 -#define MOTO_RTC_MINUTES 0x1FFA -#define MOTO_RTC_HOURS 0x1FFB -#define MOTO_RTC_DAY_OF_WEEK 0x1FFC -#define MOTO_RTC_DAY_OF_MONTH 0x1FFD -#define MOTO_RTC_MONTH 0x1FFE -#define MOTO_RTC_YEAR 0x1FFF -#define MOTO_RTC_CONTROLA 0x1FF8 -#define MOTO_RTC_CONTROLB 0x1FF9 - +/* Signatures for nvram partitions */ #define NVRAM_SIG_SP 0x02 /* support processor */ #define NVRAM_SIG_OF 0x50 /* open firmware config */ #define NVRAM_SIG_FW 0x51 /* general firmware */ @@ -49,25 +25,11 @@ #define NVRAM_SIG_OS 0xa0 /* OS defined */ #define NVRAM_SIG_PANIC 0xa1 /* Apple OSX "panic" */ -/* If change this size, then change the size of NVNAME_LEN */ -struct nvram_header { - unsigned char signature; - unsigned char checksum; - unsigned short length; - char name[12]; -}; - #ifdef __KERNEL__ +#include #include -struct nvram_partition { - struct list_head partition; - struct nvram_header header; - unsigned int index; -}; - - extern int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int err_seq); extern int nvram_read_error_log(char * buff, int length, diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 9cf197f01e94..a8154f1813df 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -34,6 +34,25 @@ #undef DEBUG_NVRAM +#define NVRAM_HEADER_LEN 16 /* sizeof(struct nvram_header) */ +#define NVRAM_BLOCK_LEN 16 +#define NVRAM_MAX_REQ (2080/NVRAM_BLOCK_LEN) +#define NVRAM_MIN_REQ (1056/NVRAM_BLOCK_LEN) + +/* If change this size, then change the size of NVNAME_LEN */ +struct nvram_header { + unsigned char signature; + unsigned char checksum; + unsigned short length; + char name[12]; +}; + +struct nvram_partition { + struct list_head partition; + struct nvram_header header; + unsigned int index; +}; + static struct nvram_partition * nvram_part; static long nvram_error_log_index = -1; static long nvram_error_log_size = 0; @@ -432,7 +451,7 @@ static int __init nvram_setup_partition(void) } /* try creating a partition with the free space we have */ - rc = nvram_create_os_partition(); + rc = nvram_create_partition("ppc64,linux", ); if (!rc) { return 0; } diff --git a/arch/powerpc/platforms/chrp/time.c b/arch/powerpc/platforms/chrp/time.c index 054dfe5b8e77..f803f4b8ab6f 100644 --- a/arch/powerpc/platforms/chrp/time.c +++ b/arch/powerpc/platforms/chrp/time.c @@ -29,6 +29,10 @@ extern spinlock_t rtc_lock; +#define NVRAM_AS0 0x74 +#define NVRAM_AS1 0x75 +#define NVRAM_DATA 0x77 + static int nvram_as1 = NVRAM_AS1; static int nvram_as0 = NVRAM_AS0; static int nvram_data = NVRAM_DATA; diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index bc3c7f2abd79..f4e4c06284b4 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -27,6 +27,8 @@ static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); +/* Max bytes to read/write in one go */ +#define NVRW_CNT 0x20 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { -- cgit v1.2.3 From 4e7c77a385efac81d6677a4a761b1b66cd2cb59e Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 15:28:20 +1000 Subject: powerpc/nvram: More flexible nvram_create_partition() Replace nvram_create_os_partition() with a variant that takes the partition name, signature and size as arguments. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 46 +++++++++++++++++++++------------- arch/powerpc/platforms/pseries/nvram.c | 6 ++--- 2 files changed, 31 insertions(+), 21 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index a8154f1813df..9e133355f742 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -307,13 +307,15 @@ static int __init nvram_remove_os_partition(void) return 0; } -/* nvram_create_os_partition - * - * Create a OS linux partition to buffer error logs. - * Will create a partition starting at the first free - * space found if space has enough room. +/** + * nvram_create_partition - Create a partition in nvram + * @name: name of the partition to create + * @sig: signature of the partition to create + * @req_size: size to allocate preferrably + * @min_size: minimum acceptable size (0 means req_size) */ -static int __init nvram_create_os_partition(void) +static int __init nvram_create_partition(const char *name, int sig, + int req_size, int min_size) { struct nvram_partition *part; struct nvram_partition *new_part; @@ -322,20 +324,27 @@ static int __init nvram_create_os_partition(void) loff_t tmp_index; long size = 0; int rc; - + + /* If no minimum size specified, make it the same as the + * requested size + */ + if (min_size == 0) + min_size = req_size; + /* Find a free partition that will give us the maximum needed size If can't find one that will give us the minimum size needed */ list_for_each_entry(part, &nvram_part->partition, partition) { if (part->header.signature != NVRAM_SIG_FREE) continue; - if (part->header.length >= NVRAM_MAX_REQ) { - size = NVRAM_MAX_REQ; + if (part->header.length >= req_size) { + size = req_size; free_part = part; break; } - if (!size && part->header.length >= NVRAM_MIN_REQ) { - size = NVRAM_MIN_REQ; + if (part->header.length > size && + part->header.length >= min_size) { + size = part->header.length; free_part = part; } } @@ -350,9 +359,9 @@ static int __init nvram_create_os_partition(void) } new_part->index = free_part->index; - new_part->header.signature = NVRAM_SIG_OS; + new_part->header.signature = sig; new_part->header.length = size; - strcpy(new_part->header.name, "ppc64,linux"); + strncpy(new_part->header.name, name, 12); new_part->header.checksum = nvram_checksum(&new_part->header); rc = nvram_write_header(new_part); @@ -451,10 +460,10 @@ static int __init nvram_setup_partition(void) } /* try creating a partition with the free space we have */ - rc = nvram_create_partition("ppc64,linux", ); - if (!rc) { + rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + if (!rc) return 0; - } /* need to free up some space */ rc = nvram_remove_os_partition(); @@ -463,9 +472,10 @@ static int __init nvram_setup_partition(void) } /* create a partition in this new space */ - rc = nvram_create_os_partition(); + rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); if (rc) { - printk(KERN_ERR "nvram_create_os_partition: Could not find a " + printk(KERN_ERR "nvram_create_partition: Could not find a " "NVRAM partition large enough\n"); return rc; } diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index f4e4c06284b4..2a1ef5c25344 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -22,14 +22,14 @@ #include #include +/* Max bytes to read/write in one go */ +#define NVRW_CNT 0x20 + static unsigned int nvram_size; static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); -/* Max bytes to read/write in one go */ -#define NVRW_CNT 0x20 - static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { unsigned int i; -- cgit v1.2.3 From 36673307aee535f951f4eede81049c6962bc4ba9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 18:18:44 +1000 Subject: powerpc/nvram: nvram_create_partitions() now uses bytes This converts nvram_create_partition() to use a size in bytes rather than blocks. It does the appropriate alignment internally The size passed is also the data size (ie. doesn't include the header anymore). Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 9e133355f742..a5a5587121a7 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -34,10 +34,10 @@ #undef DEBUG_NVRAM -#define NVRAM_HEADER_LEN 16 /* sizeof(struct nvram_header) */ -#define NVRAM_BLOCK_LEN 16 -#define NVRAM_MAX_REQ (2080/NVRAM_BLOCK_LEN) -#define NVRAM_MIN_REQ (1056/NVRAM_BLOCK_LEN) +#define NVRAM_HEADER_LEN sizeof(struct nvram_header) +#define NVRAM_BLOCK_LEN NVRAM_HEADER_LEN +#define NVRAM_MAX_REQ 2079 +#define NVRAM_MIN_REQ 1055 /* If change this size, then change the size of NVNAME_LEN */ struct nvram_header { @@ -311,7 +311,7 @@ static int __init nvram_remove_os_partition(void) * nvram_create_partition - Create a partition in nvram * @name: name of the partition to create * @sig: signature of the partition to create - * @req_size: size to allocate preferrably + * @req_size: size of data to allocate in bytes * @min_size: minimum acceptable size (0 means req_size) */ static int __init nvram_create_partition(const char *name, int sig, @@ -325,12 +325,20 @@ static int __init nvram_create_partition(const char *name, int sig, long size = 0; int rc; + /* Convert sizes from bytes to blocks */ + req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN; + min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN; + /* If no minimum size specified, make it the same as the * requested size */ if (min_size == 0) min_size = req_size; + /* Now add one block to each for the header */ + req_size += 1; + min_size += 1; + /* Find a free partition that will give us the maximum needed size If can't find one that will give us the minimum size needed */ list_for_each_entry(part, &nvram_part->partition, partition) { @@ -450,7 +458,7 @@ static int __init nvram_setup_partition(void) if (strcmp(part->header.name, "ppc64,linux")) continue; - if (part->header.length >= NVRAM_MIN_REQ) { + if ((part->header.length - 1) * NVRAM_BLOCK_LEN >= NVRAM_MIN_REQ) { /* found our partition */ nvram_error_log_index = part->index + NVRAM_HEADER_LEN; nvram_error_log_size = ((part->header.length - 1) * -- cgit v1.2.3 From 578914cffc283b907777796420148d582072cbae Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 17:21:17 +1000 Subject: powerpc/nvram: Ensure that the partition header/block size is right Use BUILD_BUG_ON to ensure the structure representing a partition header have the right size. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index a5a5587121a7..f7538820c03d 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -565,6 +565,8 @@ static int __init nvram_init(void) int error; int rc; + BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16); + if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0) return -ENODEV; -- cgit v1.2.3 From cef0d5ad62ec6e0c8456b8f58e898aa3219311a5 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 17:22:34 +1000 Subject: powerpc/nvram: Completely clear a new partition When creating a partition, we clear it entirely rather than just the first two words since the previous code was rather specific to the pseries log partition format. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index f7538820c03d..02737e687559 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -320,7 +320,7 @@ static int __init nvram_create_partition(const char *name, int sig, struct nvram_partition *part; struct nvram_partition *new_part; struct nvram_partition *free_part = NULL; - int seq_init[2] = { 0, 0 }; + static char nv_init_vals[16]; loff_t tmp_index; long size = 0; int rc; @@ -379,14 +379,15 @@ static int __init nvram_create_partition(const char *name, int sig, return rc; } - /* make sure and initialize to zero the sequence number and the error - type logged */ - tmp_index = new_part->index + NVRAM_HEADER_LEN; - rc = ppc_md.nvram_write((char *)&seq_init, sizeof(seq_init), &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_create_os_partition: nvram_write " - "failed (%d)\n", rc); - return rc; + /* Clear the partition */ + for (tmp_index = new_part->index + NVRAM_HEADER_LEN; + tmp_index < ((size - 1) * NVRAM_BLOCK_LEN); + tmp_index += NVRAM_BLOCK_LEN) { + rc = ppc_md.nvram_write(nv_init_vals, NVRAM_BLOCK_LEN, &tmp_index); + if (rc <= 0) { + pr_err("nvram_create_partition: nvram_write failed (%d)\n", rc); + return rc; + } } nvram_error_log_index = new_part->index + NVRAM_HEADER_LEN; -- cgit v1.2.3 From e49e2e87235518c21b1f5228809209831e6169e7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 17:38:55 +1000 Subject: powerpc/nvram: Shuffle code around in nvram_create_partition() This error log stuff is really pseries specific. As a first step we move the initialization of these variables to the caller of nvram_create_partition(), which is also slightly reorganized so we setup the free partition before we clear the new partition, so the chance of an error during clear leaving us with invalid headers is lessened. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 108 +++++++++++++++++++++++------------------ 1 file changed, 62 insertions(+), 46 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 02737e687559..eabee7c61183 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -313,9 +313,15 @@ static int __init nvram_remove_os_partition(void) * @sig: signature of the partition to create * @req_size: size of data to allocate in bytes * @min_size: minimum acceptable size (0 means req_size) + * + * Returns a negative error code or a positive nvram index + * of the beginning of the data area of the newly created + * partition. If you provided a min_size smaller than req_size + * you need to query for the actual size yourself after the + * call using nvram_partition_get_size(). */ -static int __init nvram_create_partition(const char *name, int sig, - int req_size, int min_size) +static loff_t __init nvram_create_partition(const char *name, int sig, + int req_size, int min_size) { struct nvram_partition *part; struct nvram_partition *new_part; @@ -334,6 +340,8 @@ static int __init nvram_create_partition(const char *name, int sig, */ if (min_size == 0) min_size = req_size; + if (min_size > req_size) + return -EINVAL; /* Now add one block to each for the header */ req_size += 1; @@ -362,7 +370,7 @@ static int __init nvram_create_partition(const char *name, int sig, /* Create our OS partition */ new_part = kmalloc(sizeof(*new_part), GFP_KERNEL); if (!new_part) { - printk(KERN_ERR "nvram_create_os_partition: kmalloc failed\n"); + pr_err("nvram_create_os_partition: kmalloc failed\n"); return -ENOMEM; } @@ -374,12 +382,29 @@ static int __init nvram_create_partition(const char *name, int sig, rc = nvram_write_header(new_part); if (rc <= 0) { - printk(KERN_ERR "nvram_create_os_partition: nvram_write_header " - "failed (%d)\n", rc); + pr_err("nvram_create_os_partition: nvram_write_header " + "failed (%d)\n", rc); return rc; } + list_add_tail(&new_part->partition, &free_part->partition); + + /* Adjust or remove the partition we stole the space from */ + if (free_part->header.length > size) { + free_part->index += size * NVRAM_BLOCK_LEN; + free_part->header.length -= size; + free_part->header.checksum = nvram_checksum(&free_part->header); + rc = nvram_write_header(free_part); + if (rc <= 0) { + pr_err("nvram_create_os_partition: nvram_write_header " + "failed (%d)\n", rc); + return rc; + } + } else { + list_del(&free_part->partition); + kfree(free_part); + } - /* Clear the partition */ + /* Clear the new partition */ for (tmp_index = new_part->index + NVRAM_HEADER_LEN; tmp_index < ((size - 1) * NVRAM_BLOCK_LEN); tmp_index += NVRAM_BLOCK_LEN) { @@ -390,31 +415,24 @@ static int __init nvram_create_partition(const char *name, int sig, } } - nvram_error_log_index = new_part->index + NVRAM_HEADER_LEN; - nvram_error_log_size = ((part->header.length - 1) * - NVRAM_BLOCK_LEN) - sizeof(struct err_log_info); - - list_add_tail(&new_part->partition, &free_part->partition); - - if (free_part->header.length <= size) { - list_del(&free_part->partition); - kfree(free_part); - return 0; - } + return new_part->index + NVRAM_HEADER_LEN; +} - /* Adjust the partition we stole the space from */ - free_part->index += size * NVRAM_BLOCK_LEN; - free_part->header.length -= size; - free_part->header.checksum = nvram_checksum(&free_part->header); +/** + * nvram_get_partition_size - Get the data size of an nvram partition + * @data_index: This is the offset of the start of the data of + * the partition. The same value that is returned by + * nvram_create_partition(). + */ +static int nvram_get_partition_size(loff_t data_index) +{ + struct nvram_partition *part; - rc = nvram_write_header(free_part); - if (rc <= 0) { - printk(KERN_ERR "nvram_create_os_partition: nvram_write_header " - "failed (%d)\n", rc); - return rc; + list_for_each_entry(part, &nvram_part->partition, partition) { + if (part->index + NVRAM_HEADER_LEN == data_index) + return (part->header.length - 1) * NVRAM_BLOCK_LEN; } - - return 0; + return -1; } @@ -469,30 +487,28 @@ static int __init nvram_setup_partition(void) } /* try creating a partition with the free space we have */ - rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, NVRAM_MAX_REQ, NVRAM_MIN_REQ); - if (!rc) - return 0; - - /* need to free up some space */ - rc = nvram_remove_os_partition(); - if (rc) { - return rc; - } - - /* create a partition in this new space */ - rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); - if (rc) { - printk(KERN_ERR "nvram_create_partition: Could not find a " - "NVRAM partition large enough\n"); - return rc; + if (rc < 0) { + /* need to free up some space */ + rc = nvram_remove_os_partition(); + if (rc) + return rc; + /* create a partition in this new space */ + rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + if (rc < 0) { + pr_err("nvram_create_partition: Could not find" + " enough space in NVRAM for partition\n"); + return rc; + } } + nvram_error_log_index = rc; + nvram_error_log_size = nvram_get_partition_size(rc) - sizeof(struct err_log_info); return 0; } - static int __init nvram_scan_partitions(void) { loff_t cur_index = 0; -- cgit v1.2.3 From fa2b4e54d41f3c9f1bee6a7d63ecd4f0ab161e89 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 29 Jul 2010 18:19:59 +1000 Subject: powerpc/nvram: Improve partition removal Existing code is nasty, has bugs etc... rewrite the function more simply, and make it take the signature and optional name of the partitions to remove as arguments, thus making it a more generic utility. We also try to remove a log partition that we find and is too small rather than creating a duplicate. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 91 ++++++++++++++++++++---------------------- 1 file changed, 43 insertions(+), 48 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index eabee7c61183..6dd2700852f0 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -247,61 +247,54 @@ static unsigned char __init nvram_checksum(struct nvram_header *p) return c_sum; } -static int __init nvram_remove_os_partition(void) +/** + * nvram_remove_partition - Remove one or more partitions in nvram + * @name: name of the partition to remove, or NULL for a + * signature only match + * @sig: signature of the partition(s) to remove + */ + +static int __init nvram_remove_partition(const char *name, int sig) { - struct list_head *i; - struct list_head *j; - struct nvram_partition * part; - struct nvram_partition * cur_part; + struct nvram_partition *part, *prev, *tmp; int rc; - list_for_each(i, &nvram_part->partition) { - part = list_entry(i, struct nvram_partition, partition); - if (part->header.signature != NVRAM_SIG_OS) + list_for_each_entry(part, &nvram_part->partition, partition) { + if (part->header.signature != sig) continue; - - /* Make os partition a free partition */ + if (name && strncmp(name, part->header.name, 12)) + continue; + + /* Make partition a free partition */ part->header.signature = NVRAM_SIG_FREE; sprintf(part->header.name, "wwwwwwwwwwww"); part->header.checksum = nvram_checksum(&part->header); - - /* Merge contiguous free partitions backwards */ - list_for_each_prev(j, &part->partition) { - cur_part = list_entry(j, struct nvram_partition, partition); - if (cur_part == nvram_part || cur_part->header.signature != NVRAM_SIG_FREE) { - break; - } - - part->header.length += cur_part->header.length; - part->header.checksum = nvram_checksum(&part->header); - part->index = cur_part->index; - - list_del(&cur_part->partition); - kfree(cur_part); - j = &part->partition; /* fixup our loop */ - } - - /* Merge contiguous free partitions forwards */ - list_for_each(j, &part->partition) { - cur_part = list_entry(j, struct nvram_partition, partition); - if (cur_part == nvram_part || cur_part->header.signature != NVRAM_SIG_FREE) { - break; - } - - part->header.length += cur_part->header.length; - part->header.checksum = nvram_checksum(&part->header); - - list_del(&cur_part->partition); - kfree(cur_part); - j = &part->partition; /* fixup our loop */ - } - rc = nvram_write_header(part); if (rc <= 0) { - printk(KERN_ERR "nvram_remove_os_partition: nvram_write failed (%d)\n", rc); + printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc); return rc; } + } + /* Merge contiguous ones */ + prev = NULL; + list_for_each_entry_safe(part, tmp, &nvram_part->partition, partition) { + if (part->header.signature != NVRAM_SIG_FREE) { + prev = NULL; + continue; + } + if (prev) { + prev->header.length += part->header.length; + prev->header.checksum = nvram_checksum(&part->header); + rc = nvram_write_header(part); + if (rc <= 0) { + printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc); + return rc; + } + list_del(&part->partition); + kfree(part); + } else + prev = part; } return 0; @@ -484,17 +477,19 @@ static int __init nvram_setup_partition(void) NVRAM_BLOCK_LEN) - sizeof(struct err_log_info); return 0; } + + /* Found one but it's too small, remove it */ + nvram_remove_partition("ppc64,linux", NVRAM_SIG_OS); } /* try creating a partition with the free space we have */ rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, NVRAM_MAX_REQ, NVRAM_MIN_REQ); if (rc < 0) { - /* need to free up some space */ - rc = nvram_remove_os_partition(); - if (rc) - return rc; - /* create a partition in this new space */ + /* need to free up some space, remove any "OS" partition */ + nvram_remove_partition(NULL, NVRAM_SIG_OS); + + /* Try again */ rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, NVRAM_MAX_REQ, NVRAM_MIN_REQ); if (rc < 0) { -- cgit v1.2.3 From cf5cbf9f8085eb45316d6e3c888a77cc50696701 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 2 Aug 2010 10:01:58 +1000 Subject: powerpc/nvram: Add nvram_find_partition() Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 6dd2700852f0..01e6844be8d7 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -429,6 +429,28 @@ static int nvram_get_partition_size(loff_t data_index) } +/** + * nvram_find_partition - Find an nvram partition by signature and name + * @name: Name of the partition or NULL for any name + * @sig: Signature to test against + * @out_size: if non-NULL, returns the size of the data part of the partition + */ +loff_t nvram_find_partition(const char *name, int sig, int *out_size) +{ + struct nvram_partition *p; + + list_for_each_entry(p, &nvram_part->partition, partition) { + if (p->header.signature == sig && + (!name || !strncmp(p->header.name, name, 12))) { + if (out_size) + *out_size = (p->header.length - 1) * + NVRAM_BLOCK_LEN; + return p->index + NVRAM_HEADER_LEN; + } + } + return 0; +} + /* nvram_setup_partition * * This will setup the partition we need for buffering the -- cgit v1.2.3 From d9626947f20b3dc0992e4ac28b477f7601f8f16e Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 2 Aug 2010 10:13:56 +1000 Subject: powerpc/nvram: Change nvram_setup_partition() to use new helper This changes the function to use nvram_find_partition() instead of doing the lookup "by hand". It also makes some of the logic clearer and prints out more useful diagnostic information. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 71 +++++++++++++++++++----------------------- 1 file changed, 32 insertions(+), 39 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 01e6844be8d7..76f546b9944d 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -469,9 +469,8 @@ loff_t nvram_find_partition(const char *name, int sig, int *out_size) */ static int __init nvram_setup_partition(void) { - struct list_head * p; - struct nvram_partition * part; - int rc; + loff_t p; + int size; /* For now, we don't do any of this on pmac, until I * have figured out if it's worth killing some unused stuffs @@ -481,48 +480,42 @@ static int __init nvram_setup_partition(void) if (machine_is(powermac)) return -ENOSPC; - /* see if we have an OS partition that meets our needs. - will try getting the max we need. If not we'll delete - partitions and try again. */ - list_for_each(p, &nvram_part->partition) { - part = list_entry(p, struct nvram_partition, partition); - if (part->header.signature != NVRAM_SIG_OS) - continue; - - if (strcmp(part->header.name, "ppc64,linux")) - continue; - - if ((part->header.length - 1) * NVRAM_BLOCK_LEN >= NVRAM_MIN_REQ) { - /* found our partition */ - nvram_error_log_index = part->index + NVRAM_HEADER_LEN; - nvram_error_log_size = ((part->header.length - 1) * - NVRAM_BLOCK_LEN) - sizeof(struct err_log_info); - return 0; - } + p = nvram_find_partition("ppc64,linux", NVRAM_SIG_OS, &size); - /* Found one but it's too small, remove it */ + /* Found one but too small, remove it */ + if (p && size < NVRAM_MIN_REQ) { + pr_info("nvram: Found too small ppc64,linux partition" + ",removing it..."); nvram_remove_partition("ppc64,linux", NVRAM_SIG_OS); + p = 0; } - - /* try creating a partition with the free space we have */ - rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); - if (rc < 0) { - /* need to free up some space, remove any "OS" partition */ - nvram_remove_partition(NULL, NVRAM_SIG_OS); - - /* Try again */ - rc = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); - if (rc < 0) { - pr_err("nvram_create_partition: Could not find" - " enough space in NVRAM for partition\n"); - return rc; + + /* Create one if we didn't find */ + if (!p) { + p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + /* No room for it, try to get rid of any OS partition + * and try again + */ + if (p == -ENOSPC) { + pr_info("nvram: No room to create ppc64,linux" + " partition, deleting all OS partitions..."); + nvram_remove_partition(NULL, NVRAM_SIG_OS); + p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); } } + + if (p <= 0) { + pr_err("nvram: Failed to find or create ppc64,linux" + " partition, err %d\n", (int)p); + return 0; + } + + nvram_error_log_index = p; + nvram_error_log_size = nvram_get_partition_size(p) - + sizeof(struct err_log_info); - nvram_error_log_index = rc; - nvram_error_log_size = nvram_get_partition_size(rc) - sizeof(struct err_log_info); return 0; } -- cgit v1.2.3 From edc79a2f3ee1c74d915f6a0ce3cb22bf468f5ad5 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 2 Aug 2010 11:18:09 +1000 Subject: powerpc/nvram: Move the log partition stuff to pseries The nvram log partition stuff currently in nvram_64.c is really pseries specific. It isn't actually used on anything else (despite the fact that we ran the code to setup the partition on anything except powermac) and the log format is specific to pseries RTAS implementation. So move it where it belongs Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/nvram.h | 10 +- arch/powerpc/kernel/nvram_64.c | 254 +++------------------------------ arch/powerpc/platforms/pseries/nvram.c | 200 ++++++++++++++++++++++++++ 3 files changed, 227 insertions(+), 237 deletions(-) diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index 459dc09ecbd8..92efe67d1c57 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -30,13 +30,14 @@ #include #include +#ifdef CONFIG_PPC_PSERIES extern int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int err_seq); extern int nvram_read_error_log(char * buff, int length, unsigned int * err_type, unsigned int *err_seq); extern int nvram_clear_error_log(void); - extern int pSeries_nvram_init(void); +#endif /* CONFIG_PPC_PSERIES */ #ifdef CONFIG_MMIO_NVRAM extern int mmio_nvram_init(void); @@ -47,6 +48,13 @@ static inline int mmio_nvram_init(void) } #endif +extern int __init nvram_scan_partitions(void); +extern loff_t nvram_create_partition(const char *name, int sig, + int req_size, int min_size); +extern int nvram_remove_partition(const char *name, int sig); +extern int nvram_get_partition_size(loff_t data_index); +extern loff_t nvram_find_partition(const char *name, int sig, int *out_size); + #endif /* __KERNEL__ */ /* PowerMac specific nvram stuffs */ diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 76f546b9944d..125d86cf0afc 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -36,8 +36,6 @@ #define NVRAM_HEADER_LEN sizeof(struct nvram_header) #define NVRAM_BLOCK_LEN NVRAM_HEADER_LEN -#define NVRAM_MAX_REQ 2079 -#define NVRAM_MIN_REQ 1055 /* If change this size, then change the size of NVNAME_LEN */ struct nvram_header { @@ -54,13 +52,6 @@ struct nvram_partition { }; static struct nvram_partition * nvram_part; -static long nvram_error_log_index = -1; -static long nvram_error_log_size = 0; - -struct err_log_info { - int error_type; - unsigned int seq_num; -}; static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) { @@ -254,7 +245,7 @@ static unsigned char __init nvram_checksum(struct nvram_header *p) * @sig: signature of the partition(s) to remove */ -static int __init nvram_remove_partition(const char *name, int sig) +int __init nvram_remove_partition(const char *name, int sig) { struct nvram_partition *part, *prev, *tmp; int rc; @@ -313,8 +304,8 @@ static int __init nvram_remove_partition(const char *name, int sig) * you need to query for the actual size yourself after the * call using nvram_partition_get_size(). */ -static loff_t __init nvram_create_partition(const char *name, int sig, - int req_size, int min_size) +loff_t __init nvram_create_partition(const char *name, int sig, + int req_size, int min_size) { struct nvram_partition *part; struct nvram_partition *new_part; @@ -417,7 +408,7 @@ static loff_t __init nvram_create_partition(const char *name, int sig, * the partition. The same value that is returned by * nvram_create_partition(). */ -static int nvram_get_partition_size(loff_t data_index) +int nvram_get_partition_size(loff_t data_index) { struct nvram_partition *part; @@ -451,75 +442,7 @@ loff_t nvram_find_partition(const char *name, int sig, int *out_size) return 0; } -/* nvram_setup_partition - * - * This will setup the partition we need for buffering the - * error logs and cleanup partitions if needed. - * - * The general strategy is the following: - * 1.) If there is ppc64,linux partition large enough then use it. - * 2.) If there is not a ppc64,linux partition large enough, search - * for a free partition that is large enough. - * 3.) If there is not a free partition large enough remove - * _all_ OS partitions and consolidate the space. - * 4.) Will first try getting a chunk that will satisfy the maximum - * error log size (NVRAM_MAX_REQ). - * 5.) If the max chunk cannot be allocated then try finding a chunk - * that will satisfy the minum needed (NVRAM_MIN_REQ). - */ -static int __init nvram_setup_partition(void) -{ - loff_t p; - int size; - - /* For now, we don't do any of this on pmac, until I - * have figured out if it's worth killing some unused stuffs - * in our nvram, as Apple defined partitions use pretty much - * all of the space - */ - if (machine_is(powermac)) - return -ENOSPC; - - p = nvram_find_partition("ppc64,linux", NVRAM_SIG_OS, &size); - - /* Found one but too small, remove it */ - if (p && size < NVRAM_MIN_REQ) { - pr_info("nvram: Found too small ppc64,linux partition" - ",removing it..."); - nvram_remove_partition("ppc64,linux", NVRAM_SIG_OS); - p = 0; - } - - /* Create one if we didn't find */ - if (!p) { - p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); - /* No room for it, try to get rid of any OS partition - * and try again - */ - if (p == -ENOSPC) { - pr_info("nvram: No room to create ppc64,linux" - " partition, deleting all OS partitions..."); - nvram_remove_partition(NULL, NVRAM_SIG_OS); - p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); - } - } - - if (p <= 0) { - pr_err("nvram: Failed to find or create ppc64,linux" - " partition, err %d\n", (int)p); - return 0; - } - - nvram_error_log_index = p; - nvram_error_log_size = nvram_get_partition_size(p) - - sizeof(struct err_log_info); - - return 0; -} - -static int __init nvram_scan_partitions(void) +int __init nvram_scan_partitions(void) { loff_t cur_index = 0; struct nvram_header phead; @@ -529,7 +452,15 @@ static int __init nvram_scan_partitions(void) int total_size; int err; - if (ppc_md.nvram_size == NULL) + /* Initialize our anchor for the nvram partition list */ + nvram_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); + if (!nvram_part) { + printk(KERN_ERR "nvram_init: Failed kmalloc\n"); + return -ENOMEM; + } + INIT_LIST_HEAD(&nvram_part->partition); + + if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0) return -ENODEV; total_size = ppc_md.nvram_size(); @@ -582,6 +513,10 @@ static int __init nvram_scan_partitions(void) } err = 0; +#ifdef DEBUG_NVRAM + nvram_print_partitions("NVRAM Partitions"); +#endif + out: kfree(header); return err; @@ -589,7 +524,6 @@ static int __init nvram_scan_partitions(void) static int __init nvram_init(void) { - int error; int rc; BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16); @@ -603,29 +537,6 @@ static int __init nvram_init(void) return rc; } - /* initialize our anchor for the nvram partition list */ - nvram_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); - if (!nvram_part) { - printk(KERN_ERR "nvram_init: Failed kmalloc\n"); - return -ENOMEM; - } - INIT_LIST_HEAD(&nvram_part->partition); - - /* Get all the NVRAM partitions */ - error = nvram_scan_partitions(); - if (error) { - printk(KERN_ERR "nvram_init: Failed nvram_scan_partitions\n"); - return error; - } - - if(nvram_setup_partition()) - printk(KERN_WARNING "nvram_init: Could not find nvram partition" - " for nvram buffered error logging.\n"); - -#ifdef DEBUG_NVRAM - nvram_print_partitions("NVRAM Partitions"); -#endif - return rc; } @@ -634,135 +545,6 @@ void __exit nvram_cleanup(void) misc_deregister( &nvram_dev ); } - -#ifdef CONFIG_PPC_PSERIES - -/* nvram_write_error_log - * - * We need to buffer the error logs into nvram to ensure that we have - * the failure information to decode. If we have a severe error there - * is no way to guarantee that the OS or the machine is in a state to - * get back to user land and write the error to disk. For example if - * the SCSI device driver causes a Machine Check by writing to a bad - * IO address, there is no way of guaranteeing that the device driver - * is in any state that is would also be able to write the error data - * captured to disk, thus we buffer it in NVRAM for analysis on the - * next boot. - * - * In NVRAM the partition containing the error log buffer will looks like: - * Header (in bytes): - * +-----------+----------+--------+------------+------------------+ - * | signature | checksum | length | name | data | - * |0 |1 |2 3|4 15|16 length-1| - * +-----------+----------+--------+------------+------------------+ - * - * The 'data' section would look like (in bytes): - * +--------------+------------+-----------------------------------+ - * | event_logged | sequence # | error log | - * |0 3|4 7|8 nvram_error_log_size-1| - * +--------------+------------+-----------------------------------+ - * - * event_logged: 0 if event has not been logged to syslog, 1 if it has - * sequence #: The unique sequence # for each event. (until it wraps) - * error log: The error log from event_scan - */ -int nvram_write_error_log(char * buff, int length, - unsigned int err_type, unsigned int error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (nvram_error_log_index == -1) { - return -ESPIPE; - } - - if (length > nvram_error_log_size) { - length = nvram_error_log_size; - } - - info.error_type = err_type; - info.seq_num = error_log_cnt; - - tmp_index = nvram_error_log_index; - - rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); - return rc; - } - - rc = ppc_md.nvram_write(buff, length, &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); - return rc; - } - - return 0; -} - -/* nvram_read_error_log - * - * Reads nvram for error log for at most 'length' - */ -int nvram_read_error_log(char * buff, int length, - unsigned int * err_type, unsigned int * error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (nvram_error_log_index == -1) - return -1; - - if (length > nvram_error_log_size) - length = nvram_error_log_size; - - tmp_index = nvram_error_log_index; - - rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); - return rc; - } - - rc = ppc_md.nvram_read(buff, length, &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); - return rc; - } - - *error_log_cnt = info.seq_num; - *err_type = info.error_type; - - return 0; -} - -/* This doesn't actually zero anything, but it sets the event_logged - * word to tell that this event is safely in syslog. - */ -int nvram_clear_error_log(void) -{ - loff_t tmp_index; - int clear_word = ERR_FLAG_ALREADY_LOGGED; - int rc; - - if (nvram_error_log_index == -1) - return -1; - - tmp_index = nvram_error_log_index; - - rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_clear_error_log: Failed nvram_write (%d)\n", rc); - return rc; - } - - return 0; -} - -#endif /* CONFIG_PPC_PSERIES */ - module_init(nvram_init); module_exit(nvram_cleanup); MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 2a1ef5c25344..55a7141131f1 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -30,6 +30,16 @@ static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); +static long nvram_error_log_index = -1; +static long nvram_error_log_size = 0; + +struct err_log_info { + int error_type; + unsigned int seq_num; +}; +#define NVRAM_MAX_REQ 2079 +#define NVRAM_MIN_REQ 1055 + static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { unsigned int i; @@ -121,6 +131,196 @@ static ssize_t pSeries_nvram_get_size(void) return nvram_size ? nvram_size : -ENODEV; } + +/* nvram_write_error_log + * + * We need to buffer the error logs into nvram to ensure that we have + * the failure information to decode. If we have a severe error there + * is no way to guarantee that the OS or the machine is in a state to + * get back to user land and write the error to disk. For example if + * the SCSI device driver causes a Machine Check by writing to a bad + * IO address, there is no way of guaranteeing that the device driver + * is in any state that is would also be able to write the error data + * captured to disk, thus we buffer it in NVRAM for analysis on the + * next boot. + * + * In NVRAM the partition containing the error log buffer will looks like: + * Header (in bytes): + * +-----------+----------+--------+------------+------------------+ + * | signature | checksum | length | name | data | + * |0 |1 |2 3|4 15|16 length-1| + * +-----------+----------+--------+------------+------------------+ + * + * The 'data' section would look like (in bytes): + * +--------------+------------+-----------------------------------+ + * | event_logged | sequence # | error log | + * |0 3|4 7|8 nvram_error_log_size-1| + * +--------------+------------+-----------------------------------+ + * + * event_logged: 0 if event has not been logged to syslog, 1 if it has + * sequence #: The unique sequence # for each event. (until it wraps) + * error log: The error log from event_scan + */ +int nvram_write_error_log(char * buff, int length, + unsigned int err_type, unsigned int error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (nvram_error_log_index == -1) { + return -ESPIPE; + } + + if (length > nvram_error_log_size) { + length = nvram_error_log_size; + } + + info.error_type = err_type; + info.seq_num = error_log_cnt; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + rc = ppc_md.nvram_write(buff, length, &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + return 0; +} + +/* nvram_read_error_log + * + * Reads nvram for error log for at most 'length' + */ +int nvram_read_error_log(char * buff, int length, + unsigned int * err_type, unsigned int * error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (nvram_error_log_index == -1) + return -1; + + if (length > nvram_error_log_size) + length = nvram_error_log_size; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); + return rc; + } + + rc = ppc_md.nvram_read(buff, length, &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); + return rc; + } + + *error_log_cnt = info.seq_num; + *err_type = info.error_type; + + return 0; +} + +/* This doesn't actually zero anything, but it sets the event_logged + * word to tell that this event is safely in syslog. + */ +int nvram_clear_error_log(void) +{ + loff_t tmp_index; + int clear_word = ERR_FLAG_ALREADY_LOGGED; + int rc; + + if (nvram_error_log_index == -1) + return -1; + + tmp_index = nvram_error_log_index; + + rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index); + if (rc <= 0) { + printk(KERN_ERR "nvram_clear_error_log: Failed nvram_write (%d)\n", rc); + return rc; + } + + return 0; +} + +/* pseries_nvram_init_log_partition + * + * This will setup the partition we need for buffering the + * error logs and cleanup partitions if needed. + * + * The general strategy is the following: + * 1.) If there is ppc64,linux partition large enough then use it. + * 2.) If there is not a ppc64,linux partition large enough, search + * for a free partition that is large enough. + * 3.) If there is not a free partition large enough remove + * _all_ OS partitions and consolidate the space. + * 4.) Will first try getting a chunk that will satisfy the maximum + * error log size (NVRAM_MAX_REQ). + * 5.) If the max chunk cannot be allocated then try finding a chunk + * that will satisfy the minum needed (NVRAM_MIN_REQ). + */ +static int __init pseries_nvram_init_log_partition(void) +{ + loff_t p; + int size; + + /* Scan nvram for partitions */ + nvram_scan_partitions(); + + /* Lookg for ours */ + p = nvram_find_partition("ppc64,linux", NVRAM_SIG_OS, &size); + + /* Found one but too small, remove it */ + if (p && size < NVRAM_MIN_REQ) { + pr_info("nvram: Found too small ppc64,linux partition" + ",removing it..."); + nvram_remove_partition("ppc64,linux", NVRAM_SIG_OS); + p = 0; + } + + /* Create one if we didn't find */ + if (!p) { + p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + /* No room for it, try to get rid of any OS partition + * and try again + */ + if (p == -ENOSPC) { + pr_info("nvram: No room to create ppc64,linux" + " partition, deleting all OS partitions..."); + nvram_remove_partition(NULL, NVRAM_SIG_OS); + p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + NVRAM_MAX_REQ, NVRAM_MIN_REQ); + } + } + + if (p <= 0) { + pr_err("nvram: Failed to find or create ppc64,linux" + " partition, err %d\n", (int)p); + return 0; + } + + nvram_error_log_index = p; + nvram_error_log_size = nvram_get_partition_size(p) - + sizeof(struct err_log_info); + + return 0; +} +machine_arch_initcall(pseries, pseries_nvram_init_log_partition); + int __init pSeries_nvram_init(void) { struct device_node *nvram; -- cgit v1.2.3 From 9a866b870880065364c894823257e6982103d4e4 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 2 Aug 2010 10:51:25 +1000 Subject: powerpc/nvram: Rename ppc64,linux partition to ibm,rtas-log I'm not aware of any userspace tool accessing it by its name anyways, it's read back by the kernel itself on the next boot to get back older log entries Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/nvram.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 55a7141131f1..7e828ba29bc3 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -40,6 +40,8 @@ struct err_log_info { #define NVRAM_MAX_REQ 2079 #define NVRAM_MIN_REQ 1055 +#define NVRAM_LOG_PART_NAME "ibm,rtas-log" + static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { unsigned int i; @@ -262,8 +264,8 @@ int nvram_clear_error_log(void) * error logs and cleanup partitions if needed. * * The general strategy is the following: - * 1.) If there is ppc64,linux partition large enough then use it. - * 2.) If there is not a ppc64,linux partition large enough, search + * 1.) If there is log partition large enough then use it. + * 2.) If there is none large enough, search * for a free partition that is large enough. * 3.) If there is not a free partition large enough remove * _all_ OS partitions and consolidate the space. @@ -281,34 +283,35 @@ static int __init pseries_nvram_init_log_partition(void) nvram_scan_partitions(); /* Lookg for ours */ - p = nvram_find_partition("ppc64,linux", NVRAM_SIG_OS, &size); + p = nvram_find_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS, &size); /* Found one but too small, remove it */ if (p && size < NVRAM_MIN_REQ) { - pr_info("nvram: Found too small ppc64,linux partition" + pr_info("nvram: Found too small "NVRAM_LOG_PART_NAME" partition" ",removing it..."); - nvram_remove_partition("ppc64,linux", NVRAM_SIG_OS); + nvram_remove_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS); p = 0; } /* Create one if we didn't find */ if (!p) { - p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, + p = nvram_create_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS, NVRAM_MAX_REQ, NVRAM_MIN_REQ); /* No room for it, try to get rid of any OS partition * and try again */ if (p == -ENOSPC) { - pr_info("nvram: No room to create ppc64,linux" + pr_info("nvram: No room to create "NVRAM_LOG_PART_NAME " partition, deleting all OS partitions..."); nvram_remove_partition(NULL, NVRAM_SIG_OS); - p = nvram_create_partition("ppc64,linux", NVRAM_SIG_OS, - NVRAM_MAX_REQ, NVRAM_MIN_REQ); + p = nvram_create_partition(NVRAM_LOG_PART_NAME, + NVRAM_SIG_OS, NVRAM_MAX_REQ, + NVRAM_MIN_REQ); } } if (p <= 0) { - pr_err("nvram: Failed to find or create ppc64,linux" + pr_err("nvram: Failed to find or create "NVRAM_LOG_PART_NAME " partition, err %d\n", (int)p); return 0; } -- cgit v1.2.3 From 690d1a9bd14bd861328ca66473a223f60cf1ad31 Mon Sep 17 00:00:00 2001 From: Jim Keniston Date: Thu, 11 Nov 2010 18:54:22 +0000 Subject: powerpc/nvram: Fix NVRAM partition list setup Simplify creation and use of the NVRAM partition list. Signed-off-by: Jim Keniston Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 125d86cf0afc..b8a50fa5875b 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -51,7 +51,7 @@ struct nvram_partition { unsigned int index; }; -static struct nvram_partition * nvram_part; +static LIST_HEAD(nvram_partitions); static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) { @@ -196,13 +196,11 @@ static struct miscdevice nvram_dev = { #ifdef DEBUG_NVRAM static void __init nvram_print_partitions(char * label) { - struct list_head * p; struct nvram_partition * tmp_part; printk(KERN_WARNING "--------%s---------\n", label); printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n"); - list_for_each(p, &nvram_part->partition) { - tmp_part = list_entry(p, struct nvram_partition, partition); + list_for_each_entry(tmp_part, &nvram_partitions, partition) { printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%s\n", tmp_part->index, tmp_part->header.signature, tmp_part->header.checksum, tmp_part->header.length, @@ -250,7 +248,7 @@ int __init nvram_remove_partition(const char *name, int sig) struct nvram_partition *part, *prev, *tmp; int rc; - list_for_each_entry(part, &nvram_part->partition, partition) { + list_for_each_entry(part, &nvram_partitions, partition) { if (part->header.signature != sig) continue; if (name && strncmp(name, part->header.name, 12)) @@ -269,7 +267,7 @@ int __init nvram_remove_partition(const char *name, int sig) /* Merge contiguous ones */ prev = NULL; - list_for_each_entry_safe(part, tmp, &nvram_part->partition, partition) { + list_for_each_entry_safe(part, tmp, &nvram_partitions, partition) { if (part->header.signature != NVRAM_SIG_FREE) { prev = NULL; continue; @@ -333,7 +331,7 @@ loff_t __init nvram_create_partition(const char *name, int sig, /* Find a free partition that will give us the maximum needed size If can't find one that will give us the minimum size needed */ - list_for_each_entry(part, &nvram_part->partition, partition) { + list_for_each_entry(part, &nvram_partitions, partition) { if (part->header.signature != NVRAM_SIG_FREE) continue; @@ -412,7 +410,7 @@ int nvram_get_partition_size(loff_t data_index) { struct nvram_partition *part; - list_for_each_entry(part, &nvram_part->partition, partition) { + list_for_each_entry(part, &nvram_partitions, partition) { if (part->index + NVRAM_HEADER_LEN == data_index) return (part->header.length - 1) * NVRAM_BLOCK_LEN; } @@ -430,7 +428,7 @@ loff_t nvram_find_partition(const char *name, int sig, int *out_size) { struct nvram_partition *p; - list_for_each_entry(p, &nvram_part->partition, partition) { + list_for_each_entry(p, &nvram_partitions, partition) { if (p->header.signature == sig && (!name || !strncmp(p->header.name, name, 12))) { if (out_size) @@ -452,14 +450,6 @@ int __init nvram_scan_partitions(void) int total_size; int err; - /* Initialize our anchor for the nvram partition list */ - nvram_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); - if (!nvram_part) { - printk(KERN_ERR "nvram_init: Failed kmalloc\n"); - return -ENOMEM; - } - INIT_LIST_HEAD(&nvram_part->partition); - if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0) return -ENODEV; total_size = ppc_md.nvram_size(); @@ -507,7 +497,7 @@ int __init nvram_scan_partitions(void) memcpy(&tmp_part->header, &phead, NVRAM_HEADER_LEN); tmp_part->index = cur_index; - list_add_tail(&tmp_part->partition, &nvram_part->partition); + list_add_tail(&tmp_part->partition, &nvram_partitions); cur_index += phead.length * NVRAM_BLOCK_LEN; } -- cgit v1.2.3 From 6024ede9ba84aa1b891c2d6bc98eda07801235e5 Mon Sep 17 00:00:00 2001 From: Jim Keniston Date: Thu, 11 Nov 2010 18:54:27 +0000 Subject: powerpc/nvram: Handle partition names >= 12 chars The name field in the nvram_header can be < 12 chars, null-terminated, or 12 chars without the null. Handle this safely. Signed-off-by: Jim Keniston Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index b8a50fa5875b..bb12b3248f13 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -42,6 +42,7 @@ struct nvram_header { unsigned char signature; unsigned char checksum; unsigned short length; + /* Terminating null required only for names < 12 chars. */ char name[12]; }; @@ -201,7 +202,7 @@ static void __init nvram_print_partitions(char * label) printk(KERN_WARNING "--------%s---------\n", label); printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n"); list_for_each_entry(tmp_part, &nvram_partitions, partition) { - printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%s\n", + printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12s\n", tmp_part->index, tmp_part->header.signature, tmp_part->header.checksum, tmp_part->header.length, tmp_part->header.name); @@ -256,7 +257,7 @@ int __init nvram_remove_partition(const char *name, int sig) /* Make partition a free partition */ part->header.signature = NVRAM_SIG_FREE; - sprintf(part->header.name, "wwwwwwwwwwww"); + strncpy(part->header.name, "wwwwwwwwwwww", 12); part->header.checksum = nvram_checksum(&part->header); rc = nvram_write_header(part); if (rc <= 0) { -- cgit v1.2.3 From b3c73856ae47d43d0d181f9de1c1c6c0820c4515 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 18 Oct 2010 07:27:04 +0000 Subject: powerpc/iommu: Use coherent_dma_mask for alloc_coherent The IOMMU code has been passing the dma-mask instead of the coherent_dma_mask to the iommu allocator. Coherent allocations should be made using the coherent_dma_mask. Also update the vio code to ensure the coherent_dma_mask is set. Without this change drivers, such as ibmvscsi, fail to load with the corrected dma_iommu_alloc_coherent(). Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/dma-iommu.c | 2 +- arch/powerpc/kernel/vio.c | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 6e54a0fd31aa..e7554154a6de 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -19,7 +19,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size, - dma_handle, device_to_mask(dev), flag, + dma_handle, dev->coherent_dma_mask, flag, dev_to_node(dev)); } diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index b2654058f2e4..1b695fdc362b 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1257,6 +1257,10 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) viodev->dev.parent = &vio_bus_device.dev; viodev->dev.bus = &vio_bus_type; viodev->dev.release = vio_dev_release; + /* needed to ensure proper operation of coherent allocations + * later, in case driver doesn't set it explicitly */ + dma_set_mask(&viodev->dev, DMA_BIT_MASK(64)); + dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64)); /* register with generic device framework */ if (device_register(&viodev->dev)) { -- cgit v1.2.3 From 7372cfb88f71ed975c8588d1ca5ecc8bb9ec7c7b Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:13 +0000 Subject: powerpc/pseries: Do not search for dma-window property on dlpar remove The iommu_table pointer in the pci auxiliary struct of device_node has not been used by the iommu ops since the dma refactor of 12d04eef927bf61328af2c7cbe756c96f98ac3bf, however this code still uses it to find tables for dlpar. By only setting the PCI_DN iommu_table pointer on nodes with dma window properties, we will be able to quickly find the node for later checks, and can remove the table without looking for the the dma window property on dlpar remove. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 9fecb313a4c9..0dbadbb34f3a 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -455,9 +455,6 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node); pr_debug(" created table: %p\n", ppci->iommu_table); } - - if (pdn != dn) - PCI_DN(dn)->iommu_table = ppci->iommu_table; } @@ -571,8 +568,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti switch (action) { case PSERIES_RECONFIG_REMOVE: - if (pci && pci->iommu_table && - of_get_property(np, "ibm,dma-window", NULL)) + if (pci && pci->iommu_table) iommu_free_table(pci->iommu_table, np->full_name); break; default: -- cgit v1.2.3 From f4133236d6473072b5982c1182991eade6ff5bae Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:14 +0000 Subject: powerpc/pseries: Checking for pdn->parent is redundant The device tree root is never a pci bus, and will not have a PCI_DN(pdn), so the check for PCI_DN added in 650f7b3b2f0ead0673e90452cf3dedde97c537ba makes the check for pdn->parent redundant and it can be removed. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0dbadbb34f3a..dae3f8847117 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -530,10 +530,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) } pr_debug(" parent is %s\n", pdn->full_name); - /* Check for parent == NULL so we don't try to setup the empty EADS - * slots on POWER4 machines. - */ - if (dma_window == NULL || pdn->parent == NULL) { + if (dma_window == NULL) { pr_debug(" no dma window for device, linking to parent\n"); set_iommu_table_base(&dev->dev, PCI_DN(pdn)->iommu_table); return; -- cgit v1.2.3 From 4af2da25ede8af6536254e92b6ed5c4026105870 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:15 +0000 Subject: powerpc/pseries: Do not need to check for dma_window == NULL The block in pci_dma_dev_setup_pSeriesLP for dma_window == NULL can be removed because we will only teminate the loop if we had already allocated a iommu table for that node or we found a window. While there may be no window for the device, the intresting part is if we are reusing a table or creating it for the first device under it. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index dae3f8847117..0c1958ac1011 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -530,12 +530,6 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) } pr_debug(" parent is %s\n", pdn->full_name); - if (dma_window == NULL) { - pr_debug(" no dma window for device, linking to parent\n"); - set_iommu_table_base(&dev->dev, PCI_DN(pdn)->iommu_table); - return; - } - pci = PCI_DN(pdn); if (!pci->iommu_table) { tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, -- cgit v1.2.3 From b8c49def6d73321724bab66dd30526744b482f0a Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 9 Dec 2010 15:24:01 +1100 Subject: powerpc/pseries: Pass phb only to iommu_table_setparms_lpar iommu_table_setparms_lpar needs either the phb or the subbusnumber (not both), pass the phb to make it similar to iommu_table_setparms. Note: In cases where a caller was passing bus->number previously to iommu_table_setparms_lpar() rather than phb->bus->number, this can lead to a different value in tbl->it_busno. The only example of this was the removed pci_dma_dev_setup_pSeriesLP(), removed in "ppc/iommu: remove unneeded pci_dma_dev_setup_pSeriesLP". [BenH: You updated only one of the two callers. Fixed that for you] Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0c1958ac1011..edea60b7ee90 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -323,14 +323,13 @@ static void iommu_table_setparms(struct pci_controller *phb, static void iommu_table_setparms_lpar(struct pci_controller *phb, struct device_node *dn, struct iommu_table *tbl, - const void *dma_window, - int bussubno) + const void *dma_window) { unsigned long offset, size; - tbl->it_busno = bussubno; of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); + tbl->it_busno = phb->bus->number; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; @@ -450,8 +449,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->iommu_table) { tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, ppci->phb->node); - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window, - bus->number); + iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window); ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node); pr_debug(" created table: %p\n", ppci->iommu_table); } @@ -534,8 +532,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->iommu_table) { tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, pci->phb->node); - iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window, - pci->phb->bus->number); + iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); pr_debug(" created table: %p\n", pci->iommu_table); } else { -- cgit v1.2.3 From b5f9b6665b70b4c844bed5452f6a14743eefa57c Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 7 Dec 2010 19:58:17 +0000 Subject: powerpc: Hardcode popcnt instructions for old assemblers The popcnt instructions went into binutils relatively recently. As with a number of other instructions, create macros and hardcode them. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/ppc-opcode.h | 8 ++++++++ arch/powerpc/lib/hweight_64.S | 14 +++++++------- 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 43adc8b819ed..1255569387b6 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -36,6 +36,8 @@ #define PPC_INST_NOP 0x60000000 #define PPC_INST_POPCNTB 0x7c0000f4 #define PPC_INST_POPCNTB_MASK 0xfc0007fe +#define PPC_INST_POPCNTD 0x7c0003f4 +#define PPC_INST_POPCNTW 0x7c0002f4 #define PPC_INST_RFCI 0x4c000066 #define PPC_INST_RFDI 0x4c00004e #define PPC_INST_RFMCI 0x4c00004c @@ -88,6 +90,12 @@ __PPC_RB(b) | __PPC_EH(eh)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ __PPC_RB(b)) +#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ + __PPC_RA(a) | __PPC_RS(s)) +#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \ + __PPC_RA(a) | __PPC_RS(s)) +#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_INST_POPCNTW | \ + __PPC_RA(a) | __PPC_RS(s)) #define PPC_RFCI stringify_in_c(.long PPC_INST_RFCI) #define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI) #define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI) diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index ee2320bb5ddf..fda27868cf8c 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -28,7 +28,7 @@ BEGIN_FTR_SECTION nop nop FTR_SECTION_ELSE - popcntb r3,r3 + PPC_POPCNTB(r3,r3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) @@ -42,14 +42,14 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(50) - popcntb r3,r3 + PPC_POPCNTB(r3,r3) srdi r4,r3,8 add r3,r4,r3 clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(50) clrlwi r3,r3,16 - popcntw r3,r3 + PPC_POPCNTW(r3,r3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50) @@ -66,7 +66,7 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(51) - popcntb r3,r3 + PPC_POPCNTB(r3,r3) srdi r4,r3,16 add r3,r4,r3 srdi r4,r3,8 @@ -74,7 +74,7 @@ FTR_SECTION_ELSE clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(51) - popcntw r3,r3 + PPC_POPCNTW(r3,r3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51) @@ -93,7 +93,7 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(52) - popcntb r3,r3 + PPC_POPCNTB(r3,r3) srdi r4,r3,32 add r3,r4,r3 srdi r4,r3,16 @@ -103,7 +103,7 @@ FTR_SECTION_ELSE clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(52) - popcntd r3,r3 + PPC_POPCNTD(r3,r3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52) -- cgit v1.2.3 From 8f4da26e9bf89f54b68d5cc3f3596f45e5f43911 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 8 Dec 2010 00:55:03 +0000 Subject: powerpc: Fix incorrect comment about interrupt stack allocation We now allow interrupt stacks anywhere in the first segment which can be 256M or 1TB. Fix the comment. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/setup_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ce6f61c6f871..5a0401fcaebd 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -437,8 +437,8 @@ static void __init irqstack_early_init(void) unsigned int i; /* - * interrupt stacks must be under 256MB, we cannot afford to take - * SLB misses on them. + * Interrupt stacks must be in the first segment since we + * cannot afford to take SLB misses on them. */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) -- cgit v1.2.3 From 928a31978115b48ad634a97755915e8ab23c4749 Mon Sep 17 00:00:00 2001 From: Sonny Rao Date: Thu, 18 Nov 2010 00:35:07 +0000 Subject: Powerpc: separate CONFIG_RELOCATABLE from CONFIG_CRASHDUMP in boot code Fix head_64.S so that we can build a relocatable kernel that isn't necessarily a crash-dump kernel Signed-off-by: Milton Miller Signed-off-by: Sonny Rao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/head_64.S | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index ce41b97eb512..782f23df7c85 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -97,7 +97,7 @@ __secondary_hold_acknowledge: .llong hvReleaseData-KERNELBASE #endif /* CONFIG_PPC_ISERIES */ -#ifdef CONFIG_CRASH_DUMP +#ifdef CONFIG_RELOCATABLE /* This flag is set to 1 by a loader if the kernel should run * at the loaded address instead of the linked address. This * is used by kexec-tools to keep the the kdump kernel in the @@ -385,12 +385,10 @@ _STATIC(__after_prom_start) /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ sldi r25,r25,32 -#ifdef CONFIG_CRASH_DUMP lwz r7,__run_at_load-_stext(r26) - cmplwi cr0,r7,1 /* kdump kernel ? - stay where we are */ + cmplwi cr0,r7,1 /* flagged to stay where we are ? */ bne 1f add r25,r25,r26 -#endif 1: mr r3,r25 bl .relocate #endif -- cgit v1.2.3 From bee376ff4c1fc178031dad51ba38ff18a98a39c8 Mon Sep 17 00:00:00 2001 From: Sonny Rao Date: Thu, 18 Nov 2010 00:39:23 +0000 Subject: powerpc: Minor cleanups for machdep.h Remove stale declaration of setup_pci_ptrs, aparently from ppc before 2.4.0 Remove #ifdef around struct existance delcaration Fix spelling of "linear" Signed-off-by: Milton Miller Signed-off-by: Sonny Rao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/machdep.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index d045b0145537..8433d36619a1 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -27,9 +27,7 @@ struct iommu_table; struct rtc_time; struct file; struct pci_controller; -#ifdef CONFIG_KEXEC struct kimage; -#endif #ifdef CONFIG_SMP struct smp_ops_t { @@ -72,7 +70,7 @@ struct machdep_calls { int psize, int ssize); void (*flush_hash_range)(unsigned long number, int local); - /* special for kexec, to be called in real mode, linar mapping is + /* special for kexec, to be called in real mode, linear mapping is * destroyed as well */ void (*hpte_clear_all)(void); @@ -324,8 +322,6 @@ extern sys_ctrler_t sys_ctrler; #endif /* CONFIG_PPC_PMAC */ -extern void setup_pci_ptrs(void); - #ifdef CONFIG_SMP /* Poor default implementations */ extern void __devinit smp_generic_give_timebase(void); -- cgit v1.2.3 From 364a1246522f99cbe58040e99af007ada31034ed Mon Sep 17 00:00:00 2001 From: Heiko Schocher Date: Mon, 22 Nov 2010 21:30:33 +0000 Subject: powerpc/time: printk time stamp init not correct problem: I see sometimes on my mpc5200 based board such printk timing information: [ 0.000000] NR_IRQS:512 nr_irqs:512 16 [ 0.000000] MPC52xx PIC is up and running! [ 0.000000] clocksource: timebase mult[79364d9] shift[22] registered [ 0.000000] console [ttyPSC0] enabled [ 130.300633] pid_max: default: 32768 minimum: 301 [ 130.305647] Mount-cache hash table entries: 512 [ 130.315818] NET: Registered protocol family 16 reason: if the tbu not starts from 0 when linux boots, boot_tb maybe could not store the real 64 bit tbu value, because boot_tp is only a 32 bit unsigned long. solution: change boot_tb to u64 [BenH: Made it u64 instead of unsigned long long] Signed-off-by: Heiko Schocher cc: Wolfgang Denk Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 010406958d97..09e4dea4a85a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -155,7 +155,7 @@ EXPORT_SYMBOL_GPL(rtc_lock); static u64 tb_to_ns_scale __read_mostly; static unsigned tb_to_ns_shift __read_mostly; -static unsigned long boot_tb __read_mostly; +static u64 boot_tb __read_mostly; extern struct timezone sys_tz; static long timezone_offset; -- cgit v1.2.3 From 4dfbf290aeb9d63a058d9d8237203b0b72bfbbe3 Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Sat, 27 Nov 2010 14:24:53 +0000 Subject: powerpc: Fix PPC_PTRACE_SETHWDEBUG on PPC_BOOK3S Properly set the DABR_TRANSLATION/DABR_DATA_READ/DABR_DATA_READ bits in the dabr when setting the debug register via PPC_PTRACE_SETHWDEBUG. Also don't reject trigger type of PPC_BREAKPOINT_TRIGGER_READ. Signed-off-by: Andreas Schwab Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ptrace.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index a9b32967cff6..906536998291 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1316,6 +1316,10 @@ static int set_dac_range(struct task_struct *child, static long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) { +#ifndef CONFIG_PPC_ADV_DEBUG_REGS + unsigned long dabr; +#endif + if (bp_info->version != 1) return -ENOTSUPP; #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -1353,11 +1357,10 @@ static long ppc_set_hwdebug(struct task_struct *child, /* * We only support one data breakpoint */ - if (((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0) || - ((bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0) || - (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_WRITE) || - (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) || - (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)) + if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 || + (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 || + bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT || + bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE) return -EINVAL; if (child->thread.dabr) @@ -1366,7 +1369,14 @@ static long ppc_set_hwdebug(struct task_struct *child, if ((unsigned long)bp_info->addr >= TASK_SIZE) return -EIO; - child->thread.dabr = (unsigned long)bp_info->addr; + dabr = (unsigned long)bp_info->addr & ~7UL; + dabr |= DABR_TRANSLATION; + if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) + dabr |= DABR_DATA_READ; + if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) + dabr |= DABR_DATA_WRITE; + + child->thread.dabr = dabr; return 1; #endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */ -- cgit v1.2.3 From bb2c458b8b8c8a53f65b78051d22a0f13d53abcb Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Sun, 28 Nov 2010 06:33:14 +0000 Subject: powerpc: Update compat_arch_ptrace Update compat_arch_ptrace to follow recent changes in PTRACE_GET_DEBUGREG and the addition of PPC_PTRACE_{GETHWDBGINFO|{SET|DEL}HWDEBUG}. The latter three can be forwarded to arch_ptrace unchanged. Signed-off-by: Andreas Schwab Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ptrace32.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 8a6daf4129f6..69c4be917d07 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -280,7 +280,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, /* We only support one DABR and no IABRS at the moment */ if (addr > 0) break; +#ifdef CONFIG_PPC_ADV_DEBUG_REGS + ret = put_user(child->thread.dac1, (u32 __user *)data); +#else ret = put_user(child->thread.dabr, (u32 __user *)data); +#endif break; } @@ -312,6 +316,9 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_SET_DEBUGREG: case PTRACE_SYSCALL: case PTRACE_CONT: + case PPC_PTRACE_GETHWDBGINFO: + case PPC_PTRACE_SETHWDEBUG: + case PPC_PTRACE_DELHWDEBUG: ret = arch_ptrace(child, request, addr, data); break; -- cgit v1.2.3 From 7a9d12568e34e37a72d9e00ce01b62dec527e663 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Sun, 28 Nov 2010 18:26:36 +0000 Subject: powerpc: Record vma->phys_addr in ioremap() The vmalloc code can track the physical address of a vma, when the vma is used for ioremap, if set it is displayed in /proc/vmallocinfo. Because get_vm_area_caller() doesn't know it's being called for ioremap() it's up to the arch code to set the phys_addr. A bunch of other arch's do this, I'm not sure why powerpc doesn't? Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/pgtable_32.c | 1 + arch/powerpc/mm/pgtable_64.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index a87ead0138b4..71932d000a72 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -230,6 +230,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, area = get_vm_area_caller(size, VM_IOREMAP, caller); if (area == 0) return NULL; + area->phys_addr = p; v = (unsigned long) area->addr; } else { v = (ioremap_bot -= size); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 21d6dfab7942..88927a05cdc2 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -223,6 +223,8 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size, caller); if (area == NULL) return NULL; + + area->phys_addr = paligned; ret = __ioremap_at(paligned, area->addr, size, flags); if (!ret) vunmap(area->addr); -- cgit v1.2.3 From 4dfa9c474859629a2c4a3f8d29804d6a6c994908 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 7 Dec 2010 14:36:05 +0000 Subject: powerpc: iommu: Add device name to iommu error printks Right now its difficult to see which device is running out of iommu space: iommu_alloc failed, tbl c00000076e096660 vaddr c000000768806600 npages 1 Use dev_info() so we get the device name and location: ipr 0000:00:01.0: iommu_alloc failed, tbl c00000076e096660 vaddr c000000768806600 npages 1 Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/iommu.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d5839179ec77..961bb03413f3 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -311,8 +311,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Handle failure */ if (unlikely(entry == DMA_ERROR_CODE)) { if (printk_ratelimit()) - printk(KERN_INFO "iommu_alloc failed, tbl %p vaddr %lx" - " npages %lx\n", tbl, vaddr, npages); + dev_info(dev, "iommu_alloc failed, tbl %p " + "vaddr %lx npages %lu\n", tbl, vaddr, + npages); goto failure; } @@ -579,9 +580,9 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, attrs); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { - printk(KERN_INFO "iommu_alloc failed, " - "tbl %p vaddr %p npages %d\n", - tbl, vaddr, npages); + dev_info(dev, "iommu_alloc failed, tbl %p " + "vaddr %p npages %d\n", tbl, vaddr, + npages); } } else dma_handle |= (uaddr & ~IOMMU_PAGE_MASK); @@ -627,7 +628,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, * the tce tables. */ if (order >= IOMAP_MAX_ORDER) { - printk("iommu_alloc_consistent size too large: 0x%lx\n", size); + dev_info(dev, "iommu_alloc_consistent size too large: 0x%lx\n", + size); return NULL; } -- cgit v1.2.3 From 9eff1a38407c051273fe1a20f03f8155bd32de35 Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Wed, 1 Dec 2010 12:31:15 +0000 Subject: powerpc/pseries: Poll VPA for topology changes and update NUMA maps This patch sets a timer during boot that will periodically poll the associativity change counters in the VPA. When a change in associativity is detected, it retrieves the new associativity domain information via the H_HOME_NODE_ASSOCIATIVITY hcall and updates the NUMA node maps and sysfs entries accordingly. Note that since the ibm,associativity device tree property does not exist on configurations with both NUMA and SPLPAR enabled, no device tree updates are necessary. Signed-off-by: Jesse Larrew Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/lppaca.h | 5 +- arch/powerpc/mm/numa.c | 277 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 271 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 7f5e0fefebb0..380d48bacd16 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -62,7 +62,10 @@ struct lppaca { volatile u32 dyn_pir; // Dynamic ProcIdReg value x20-x23 u32 dsei_data; // DSEI data x24-x27 u64 sprg3; // SPRG3 value x28-x2F - u8 reserved3[80]; // Reserved x30-x7F + u8 reserved3[40]; // Reserved x30-x57 + volatile u8 vphn_assoc_counts[8]; // Virtual processor home node + // associativity change counters x58-x5F + u8 reserved4[32]; // Reserved x60-x7F //============================================================================= // CACHE_LINE_2 0x0080 - 0x00FF Contains local read-write data diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 8c0944c465f6..d644ba7e8aba 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -20,10 +20,14 @@ #include #include #include +#include +#include #include #include #include #include +#include +#include static int numa_enabled = 1; @@ -246,32 +250,41 @@ static void initialize_distance_lookup_table(int nid, /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa * info is found. */ -static int of_node_to_nid_single(struct device_node *device) +static int associativity_to_nid(const unsigned int *associativity) { int nid = -1; - const unsigned int *tmp; if (min_common_depth == -1) goto out; - tmp = of_get_associativity(device); - if (!tmp) - goto out; - - if (tmp[0] >= min_common_depth) - nid = tmp[min_common_depth]; + if (associativity[0] >= min_common_depth) + nid = associativity[min_common_depth]; /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= MAX_NUMNODES) nid = -1; - if (nid > 0 && tmp[0] >= distance_ref_points_depth) - initialize_distance_lookup_table(nid, tmp); + if (nid > 0 && associativity[0] >= distance_ref_points_depth) + initialize_distance_lookup_table(nid, associativity); out: return nid; } +/* Returns the nid associated with the given device tree node, + * or -1 if not found. + */ +static int of_node_to_nid_single(struct device_node *device) +{ + int nid = -1; + const unsigned int *tmp; + + tmp = of_get_associativity(device); + if (tmp) + nid = associativity_to_nid(tmp); + return nid; +} + /* Walk the device tree upwards, looking for an associativity id */ int of_node_to_nid(struct device_node *device) { @@ -1274,3 +1287,247 @@ u64 memory_hotplug_max(void) return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM()); } #endif /* CONFIG_MEMORY_HOTPLUG */ + +/* Vrtual Processor Home Node (VPHN) support */ +#define VPHN_NR_CHANGE_CTRS (8) +static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; +static cpumask_t cpu_associativity_changes_mask; +static int vphn_enabled; +static void set_topology_timer(void); +int stop_topology_update(void); + +/* + * Store the current values of the associativity change counters in the + * hypervisor. + */ +static void setup_cpu_associativity_change_counters(void) +{ + int cpu = 0; + + for_each_possible_cpu(cpu) { + int i = 0; + u8 *counts = vphn_cpu_change_counts[cpu]; + volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; + + for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { + counts[i] = hypervisor_counts[i]; + } + } +} + +/* + * The hypervisor maintains a set of 8 associativity change counters in + * the VPA of each cpu that correspond to the associativity levels in the + * ibm,associativity-reference-points property. When an associativity + * level changes, the corresponding counter is incremented. + * + * Set a bit in cpu_associativity_changes_mask for each cpu whose home + * node associativity levels have changed. + * + * Returns the number of cpus with unhandled associativity changes. + */ +static int update_cpu_associativity_changes_mask(void) +{ + int cpu = 0, nr_cpus = 0; + cpumask_t *changes = &cpu_associativity_changes_mask; + + cpumask_clear(changes); + + for_each_possible_cpu(cpu) { + int i, changed = 0; + u8 *counts = vphn_cpu_change_counts[cpu]; + volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; + + for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { + if (hypervisor_counts[i] > counts[i]) { + counts[i] = hypervisor_counts[i]; + changed = 1; + } + } + if (changed) { + cpumask_set_cpu(cpu, changes); + nr_cpus++; + } + } + + return nr_cpus; +} + +/* 6 64-bit registers unpacked into 12 32-bit associativity values */ +#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32)) + +/* + * Convert the associativity domain numbers returned from the hypervisor + * to the sequence they would appear in the ibm,associativity property. + */ +static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) +{ + int i = 0; + int nr_assoc_doms = 0; + const u16 *field = (const u16*) packed; + +#define VPHN_FIELD_UNUSED (0xffff) +#define VPHN_FIELD_MSB (0x8000) +#define VPHN_FIELD_MASK (~VPHN_FIELD_MSB) + + for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) { + if (*field == VPHN_FIELD_UNUSED) { + /* All significant fields processed, and remaining + * fields contain the reserved value of all 1's. + * Just store them. + */ + unpacked[i] = *((u32*)field); + field += 2; + } + else if (*field & VPHN_FIELD_MSB) { + /* Data is in the lower 15 bits of this field */ + unpacked[i] = *field & VPHN_FIELD_MASK; + field++; + nr_assoc_doms++; + } + else { + /* Data is in the lower 15 bits of this field + * concatenated with the next 16 bit field + */ + unpacked[i] = *((u32*)field); + field += 2; + nr_assoc_doms++; + } + } + + return nr_assoc_doms; +} + +/* + * Retrieve the new associativity information for a virtual processor's + * home node. + */ +static long hcall_vphn(unsigned long cpu, unsigned int *associativity) +{ + long rc = 0; + long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + u64 flags = 1; + int hwcpu = get_hard_smp_processor_id(cpu); + + rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); + vphn_unpack_associativity(retbuf, associativity); + + return rc; +} + +static long vphn_get_associativity(unsigned long cpu, + unsigned int *associativity) +{ + long rc = 0; + + rc = hcall_vphn(cpu, associativity); + + switch (rc) { + case H_FUNCTION: + printk(KERN_INFO + "VPHN is not supported. Disabling polling...\n"); + stop_topology_update(); + break; + case H_HARDWARE: + printk(KERN_ERR + "hcall_vphn() experienced a hardware fault " + "preventing VPHN. Disabling polling...\n"); + stop_topology_update(); + } + + return rc; +} + +/* + * Update the node maps and sysfs entries for each cpu whose home node + * has changed. + */ +int arch_update_cpu_topology(void) +{ + int cpu = 0, nid = 0, old_nid = 0; + unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; + struct sys_device *sysdev = NULL; + + for_each_cpu_mask(cpu, cpu_associativity_changes_mask) { + vphn_get_associativity(cpu, associativity); + nid = associativity_to_nid(associativity); + + if (nid < 0 || !node_online(nid)) + nid = first_online_node; + + old_nid = numa_cpu_lookup_table[cpu]; + + /* Disable hotplug while we update the cpu + * masks and sysfs. + */ + get_online_cpus(); + unregister_cpu_under_node(cpu, old_nid); + unmap_cpu_from_node(cpu); + map_cpu_to_node(cpu, nid); + register_cpu_under_node(cpu, nid); + put_online_cpus(); + + sysdev = get_cpu_sysdev(cpu); + if (sysdev) + kobject_uevent(&sysdev->kobj, KOBJ_CHANGE); + } + + return 1; +} + +static void topology_work_fn(struct work_struct *work) +{ + rebuild_sched_domains(); +} +static DECLARE_WORK(topology_work, topology_work_fn); + +void topology_schedule_update(void) +{ + schedule_work(&topology_work); +} + +static void topology_timer_fn(unsigned long ignored) +{ + if (!vphn_enabled) + return; + if (update_cpu_associativity_changes_mask() > 0) + topology_schedule_update(); + set_topology_timer(); +} +static struct timer_list topology_timer = + TIMER_INITIALIZER(topology_timer_fn, 0, 0); + +static void set_topology_timer(void) +{ + topology_timer.data = 0; + topology_timer.expires = jiffies + 60 * HZ; + add_timer(&topology_timer); +} + +/* + * Start polling for VPHN associativity changes. + */ +int start_topology_update(void) +{ + int rc = 0; + + if (firmware_has_feature(FW_FEATURE_VPHN)) { + vphn_enabled = 1; + setup_cpu_associativity_change_counters(); + init_timer_deferrable(&topology_timer); + set_topology_timer(); + rc = 1; + } + + return rc; +} +__initcall(start_topology_update); + +/* + * Disable polling for VPHN associativity changes. + */ +int stop_topology_update(void) +{ + vphn_enabled = 0; + return del_timer_sync(&topology_timer); +} -- cgit v1.2.3 From 3b7a27db3b6b5501e3d1c1628e6d5a547ffe76c6 Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Wed, 1 Dec 2010 12:31:26 +0000 Subject: powerpc: Disable VPHN polling during a suspend operation Tie the polling mechanism into the ibm,suspend-me rtas call to stop/restart polling before/after a suspend, hibernate, migrate, or checkpoint restart operation. This ensures that the system has a chance to disable the polling if the partition is migrated to a system that does not support VPHN (and vice versa). Signed-off-by: Jesse Larrew Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/topology.h | 10 ++++++++++ arch/powerpc/kernel/rtas.c | 3 +++ 2 files changed, 13 insertions(+) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index afe4aaa65c3b..aed188bd70db 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -93,6 +93,8 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct sys_device *dev, int nid); extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); +extern int start_topology_update(void); +extern int stop_topology_update(void); #else static inline void dump_numa_cpu_topology(void) {} @@ -107,6 +109,14 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, { } +static inline int start_topology_update(void) +{ + return 0; +} +static inline int stop_topology_update(void) +{ + return 0; +} #endif /* CONFIG_NUMA */ #include diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 8fe8bc61c10a..2097f2b3cba8 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -41,6 +41,7 @@ #include #include #include +#include struct rtas_t rtas = { .lock = __ARCH_SPIN_LOCK_UNLOCKED @@ -713,6 +714,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w int cpu; slb_set_size(SLB_MIN_SIZE); + stop_topology_update(); printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id()); while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) && @@ -728,6 +730,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w rc = atomic_read(&data->error); atomic_set(&data->error, rc); + start_topology_update(); if (wake_when_done) { atomic_set(&data->done, 1); -- cgit v1.2.3 From ae9fd31a3668ca97e8f37698b927ae7c0b70807a Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Mon, 8 Nov 2010 13:07:57 +0000 Subject: powerpc: Remove unnecessary casts of void ptr Hi, The [vk][cmz]alloc(_node) family of functions return void pointers which it's completely unnecessary/pointless to cast to other pointer types since that happens implicitly. This patch removes such casts from arch/powerpc/ Signed-off-by: Jesper Juhl Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/pgtable_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 71932d000a72..8dc41c0157fe 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -78,7 +78,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) /* pgdir take page or two with 4K pages and a page fraction otherwise */ #ifndef CONFIG_PPC_4K_PAGES - ret = (pgd_t *)kzalloc(1 << PGDIR_ORDER, GFP_KERNEL); + ret = kzalloc(1 << PGDIR_ORDER, GFP_KERNEL); #else ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, PGDIR_ORDER - PAGE_SHIFT); -- cgit v1.2.3 From 518fdae26a530d3f0f11e3650348ab75e5891cfd Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 12 Nov 2010 14:49:19 +0000 Subject: powerpc/pci: Use printf extension %pR for struct resource Using %pR standardizes the struct resource output. Signed-off-by: Joe Perches Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/pci_64.c | 3 +-- arch/powerpc/sysdev/tsi108_dev.c | 8 ++++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index d43fc65749c1..851577608a78 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -193,8 +193,7 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) hose->io_resource.start += io_virt_offset; hose->io_resource.end += io_virt_offset; - pr_debug(" hose->io_resource=0x%016llx...0x%016llx\n", - hose->io_resource.start, hose->io_resource.end); + pr_debug(" hose->io_resource=%pR\n", &hose->io_resource); return 0; } diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c index d4d15aaf18fa..5e249a85c1c0 100644 --- a/arch/powerpc/sysdev/tsi108_dev.c +++ b/arch/powerpc/sysdev/tsi108_dev.c @@ -83,8 +83,8 @@ static int __init tsi108_eth_of_init(void) memset(&tsi_eth_data, 0, sizeof(tsi_eth_data)); ret = of_address_to_resource(np, 0, &r[0]); - DBG("%s: name:start->end = %s:0x%lx-> 0x%lx\n", - __func__,r[0].name, r[0].start, r[0].end); + DBG("%s: name:start->end = %s:%pR\n", + __func__, r[0].name, &r[0]); if (ret) goto err; @@ -92,8 +92,8 @@ static int __init tsi108_eth_of_init(void) r[1].start = irq_of_parse_and_map(np, 0); r[1].end = irq_of_parse_and_map(np, 0); r[1].flags = IORESOURCE_IRQ; - DBG("%s: name:start->end = %s:0x%lx-> 0x%lx\n", - __func__,r[1].name, r[1].start, r[1].end); + DBG("%s: name:start->end = %s:%pR\n", + __func__, r[1].name, &r[1]); tsi_eth_dev = platform_device_register_simple("tsi-ethernet", i++, &r[0], -- cgit v1.2.3 From 982cf00412a890ca738c2d78528b652ca431ad1a Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Tue, 30 Nov 2010 23:54:46 +0000 Subject: of/address: Use propper endianess in get_flags This patch changes u32 to __be32 for all "ranges", "prop" and "addr" and such. Those variables are pointing to the device tree which containts intergers in big endian format. Most functions are doing it right because of_read_number() is doing the right thing for them. of_bus_isa_get_flags(), of_bus_pci_get_flags() and of_bus_isa_map() were accessing the data directly and were doing it wrong. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Benjamin Herrenschmidt Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/prom.h | 2 +- drivers/of/address.c | 54 +++++++++++++++++++++-------------------- include/linux/of_address.h | 6 ++--- 3 files changed, 32 insertions(+), 30 deletions(-) diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index ae26f2efd089..ab34f6072095 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -42,7 +42,7 @@ extern void pci_create_OF_bus_map(void); /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, - const u32 *in_addr); + const __be32 *in_addr); #ifdef CONFIG_PCI extern unsigned long pci_address_to_pio(phys_addr_t address); diff --git a/drivers/of/address.c b/drivers/of/address.c index 3a1c7e70b192..b4559c58c095 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -12,13 +12,13 @@ (ns) > 0) static struct of_bus *of_match_bus(struct device_node *np); -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, +static int __of_address_to_resource(struct device_node *dev, + const __be32 *addrp, u64 size, unsigned int flags, struct resource *r); /* Debug utility */ #ifdef DEBUG -static void of_dump_addr(const char *s, const u32 *addr, int na) +static void of_dump_addr(const char *s, const __be32 *addr, int na) { printk(KERN_DEBUG "%s", s); while (na--) @@ -26,7 +26,7 @@ static void of_dump_addr(const char *s, const u32 *addr, int na) printk("\n"); } #else -static void of_dump_addr(const char *s, const u32 *addr, int na) { } +static void of_dump_addr(const char *s, const __be32 *addr, int na) { } #endif /* Callbacks for bus specific translators */ @@ -36,10 +36,10 @@ struct of_bus { int (*match)(struct device_node *parent); void (*count_cells)(struct device_node *child, int *addrc, int *sizec); - u64 (*map)(u32 *addr, const u32 *range, + u64 (*map)(u32 *addr, const __be32 *range, int na, int ns, int pna); int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(const u32 *addr); + unsigned int (*get_flags)(const __be32 *addr); }; /* @@ -55,7 +55,7 @@ static void of_bus_default_count_cells(struct device_node *dev, *sizec = of_n_size_cells(dev); } -static u64 of_bus_default_map(u32 *addr, const u32 *range, +static u64 of_bus_default_map(u32 *addr, const __be32 *range, int na, int ns, int pna) { u64 cp, s, da; @@ -85,7 +85,7 @@ static int of_bus_default_translate(u32 *addr, u64 offset, int na) return 0; } -static unsigned int of_bus_default_get_flags(const u32 *addr) +static unsigned int of_bus_default_get_flags(const __be32 *addr) { return IORESOURCE_MEM; } @@ -110,10 +110,10 @@ static void of_bus_pci_count_cells(struct device_node *np, *sizec = 2; } -static unsigned int of_bus_pci_get_flags(const u32 *addr) +static unsigned int of_bus_pci_get_flags(const __be32 *addr) { unsigned int flags = 0; - u32 w = addr[0]; + u32 w = be32_to_cpup(addr); switch((w >> 24) & 0x03) { case 0x01: @@ -129,7 +129,8 @@ static unsigned int of_bus_pci_get_flags(const u32 *addr) return flags; } -static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) +static u64 of_bus_pci_map(u32 *addr, const __be32 *range, int na, int ns, + int pna) { u64 cp, s, da; unsigned int af, rf; @@ -160,7 +161,7 @@ static int of_bus_pci_translate(u32 *addr, u64 offset, int na) return of_bus_default_translate(addr + 1, offset, na - 1); } -const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, +const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags) { const __be32 *prop; @@ -207,7 +208,7 @@ EXPORT_SYMBOL(of_get_pci_address); int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r) { - const u32 *addrp; + const __be32 *addrp; u64 size; unsigned int flags; @@ -237,12 +238,13 @@ static void of_bus_isa_count_cells(struct device_node *child, *sizec = 1; } -static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) +static u64 of_bus_isa_map(u32 *addr, const __be32 *range, int na, int ns, + int pna) { u64 cp, s, da; /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x00000001) + if ((addr[0] ^ range[0]) & cpu_to_be32(1)) return OF_BAD_ADDR; /* Read address values, skipping high cell */ @@ -264,10 +266,10 @@ static int of_bus_isa_translate(u32 *addr, u64 offset, int na) return of_bus_default_translate(addr + 1, offset, na - 1); } -static unsigned int of_bus_isa_get_flags(const u32 *addr) +static unsigned int of_bus_isa_get_flags(const __be32 *addr) { unsigned int flags = 0; - u32 w = addr[0]; + u32 w = be32_to_cpup(addr); if (w & 1) flags |= IORESOURCE_IO; @@ -330,7 +332,7 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, struct of_bus *pbus, u32 *addr, int na, int ns, int pna, const char *rprop) { - const u32 *ranges; + const __be32 *ranges; unsigned int rlen; int rone; u64 offset = OF_BAD_ADDR; @@ -398,7 +400,7 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, * that can be mapped to a cpu physical address). This is not really specified * that way, but this is traditionally the way IBM at least do things */ -u64 __of_translate_address(struct device_node *dev, const u32 *in_addr, +u64 __of_translate_address(struct device_node *dev, const __be32 *in_addr, const char *rprop) { struct device_node *parent = NULL; @@ -475,22 +477,22 @@ u64 __of_translate_address(struct device_node *dev, const u32 *in_addr, return result; } -u64 of_translate_address(struct device_node *dev, const u32 *in_addr) +u64 of_translate_address(struct device_node *dev, const __be32 *in_addr) { return __of_translate_address(dev, in_addr, "ranges"); } EXPORT_SYMBOL(of_translate_address); -u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr) +u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr) { return __of_translate_address(dev, in_addr, "dma-ranges"); } EXPORT_SYMBOL(of_translate_dma_address); -const u32 *of_get_address(struct device_node *dev, int index, u64 *size, +const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { - const u32 *prop; + const __be32 *prop; unsigned int psize; struct device_node *parent; struct of_bus *bus; @@ -525,8 +527,8 @@ const u32 *of_get_address(struct device_node *dev, int index, u64 *size, } EXPORT_SYMBOL(of_get_address); -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, +static int __of_address_to_resource(struct device_node *dev, + const __be32 *addrp, u64 size, unsigned int flags, struct resource *r) { u64 taddr; @@ -564,7 +566,7 @@ static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { - const u32 *addrp; + const __be32 *addrp; u64 size; unsigned int flags; diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 8aea06f0564c..2feda6ee6140 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,7 +3,7 @@ #include #include -extern u64 of_translate_address(struct device_node *np, const u32 *addr); +extern u64 of_translate_address(struct device_node *np, const __be32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); extern void __iomem *of_iomap(struct device_node *device, int index); @@ -21,7 +21,7 @@ static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } #endif #ifdef CONFIG_PCI -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, +extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags); extern int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r); @@ -32,7 +32,7 @@ static inline int of_pci_address_to_resource(struct device_node *dev, int bar, return -ENOSYS; } -static inline const u32 *of_get_pci_address(struct device_node *dev, +static inline const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags) { return NULL; -- cgit v1.2.3 From 98b14d6b290d96b24ae993ceaccc59b2aa4b130c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 5 Dec 2010 05:05:37 +0000 Subject: powerpc/powermac: Make auto-loading of therm_pm72 possible The therm_pm72 driver, used on the PowerMac G5 range, cannot be auto-loaded, since the driver itself creates both the device node and the driver instance. Moving the device node creation to the platform setup code and adding the necessary MODULE_DEVICE_TABLE() information allows the driver to be automatically loaded by udev on any semi-modern distribution. It "fixes" a major source of problem on G5 machines where the driver wasn't explicitely loaded by default, and the system would automatically shutdown under load. Tested on an Xserve G5. Signed-off-by: Marc Zyngier Cc: Benjamin Herrenschmidt Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powermac/setup.c | 9 +++++++++ drivers/macintosh/therm_pm72.c | 30 +++++------------------------- 2 files changed, 14 insertions(+), 25 deletions(-) diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 9deb274841f1..d5aceb7fb125 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -506,6 +506,15 @@ static int __init pmac_declare_of_platform_devices(void) of_platform_device_create(np, "smu", NULL); of_node_put(np); } + np = of_find_node_by_type(NULL, "fcu"); + if (np == NULL) { + /* Some machines have strangely broken device-tree */ + np = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/fan@15e"); + } + if (np) { + of_platform_device_create(np, "temperature", NULL); + of_node_put(np); + } return 0; } diff --git a/drivers/macintosh/therm_pm72.c b/drivers/macintosh/therm_pm72.c index 44549272333c..2e041fd0a00c 100644 --- a/drivers/macintosh/therm_pm72.c +++ b/drivers/macintosh/therm_pm72.c @@ -2213,6 +2213,9 @@ static void fcu_lookup_fans(struct device_node *fcu_node) static int fcu_of_probe(struct platform_device* dev, const struct of_device_id *match) { state = state_detached; + of_dev = dev; + + dev_info(&dev->dev, "PowerMac G5 Thermal control driver %s\n", VERSION); /* Lookup the fans in the device tree */ fcu_lookup_fans(dev->dev.of_node); @@ -2235,6 +2238,7 @@ static const struct of_device_id fcu_match[] = }, {}, }; +MODULE_DEVICE_TABLE(of, fcu_match); static struct of_platform_driver fcu_of_platform_driver = { @@ -2252,8 +2256,6 @@ static struct of_platform_driver fcu_of_platform_driver = */ static int __init therm_pm72_init(void) { - struct device_node *np; - rackmac = of_machine_is_compatible("RackMac3,1"); if (!of_machine_is_compatible("PowerMac7,2") && @@ -2261,34 +2263,12 @@ static int __init therm_pm72_init(void) !rackmac) return -ENODEV; - printk(KERN_INFO "PowerMac G5 Thermal control driver %s\n", VERSION); - - np = of_find_node_by_type(NULL, "fcu"); - if (np == NULL) { - /* Some machines have strangely broken device-tree */ - np = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/fan@15e"); - if (np == NULL) { - printk(KERN_ERR "Can't find FCU in device-tree !\n"); - return -ENODEV; - } - } - of_dev = of_platform_device_create(np, "temperature", NULL); - if (of_dev == NULL) { - printk(KERN_ERR "Can't register FCU platform device !\n"); - return -ENODEV; - } - - of_register_platform_driver(&fcu_of_platform_driver); - - return 0; + return of_register_platform_driver(&fcu_of_platform_driver); } static void __exit therm_pm72_exit(void) { of_unregister_platform_driver(&fcu_of_platform_driver); - - if (of_dev) - of_device_unregister(of_dev); } module_init(therm_pm72_init); -- cgit v1.2.3 From 6504cf3412373f42b53a675363c056901c1596cf Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:52:55 +0200 Subject: powerpc/512x: scatter/gather dma fix While testing mpc512x-dma driver with dmatest module I've found that I can hang the mpc512x-dma issuing request from multiple threads to the single channel. insmod dmatest.ko max_channels=1 threads_per_chan=16 After investigating this case I've managed to find that this happens if and only if we have more than one queued requests. In this case the driver tries to make use of hardware scatter/gather functionality. I've found two problems with scatter/gather: 1. When TCD is copied form RAM to the TCD register space with memcpy_io() e_sg bit eventually gets cleared. This results in only first TCD being executed. I've added setting of e_sg bit explicitly in the TCD registers. BTW, what is the correct way to do this? (How can I use setbits with bitfield structure?) After that hardware loads consecutive TCDs and we hit the second issue. 2. Existing code clears int_maj bit in the last TCD so we never get an interrupt on transfer completion. With these fixes my tests with many threads of single channel succeed but tests that use many channels simultaneously still don't work reliable. Signed-off-by: Ilya Yanok Acked-by: Wolfgang Denk Signed-off-by: Grant Likely --- drivers/dma/mpc512x_dma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 4e9cbf300594..1bc04aa27b14 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -252,11 +252,13 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan) prev = mdesc; } - prev->tcd->start = 0; prev->tcd->int_maj = 1; /* Send first descriptor in chain into hardware */ memcpy_toio(&mdma->tcd[cid], first->tcd, sizeof(struct mpc_dma_tcd)); + + if (first != prev) + mdma->tcd[cid].e_sg = 1; out_8(&mdma->regs->dmassrt, cid); } -- cgit v1.2.3 From 2862559e8a1e7c47bb3003f0edbc9db9009dc32b Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:52:56 +0200 Subject: powerpc/512x: fix the hanged dma transfer issue Current code clears interrupt active status _after_ submitting new transfers. This leaves a possibility of clearing the interrupt for this new transfer (if it is triggered fast enough) and thus lose this interrupt. We want to clear interrupt active status _before_ new transfers is submitted and for current channel only. Signed-off-by: Ilya Yanok Acked-by: Wolfgang Denk Signed-off-by: Grant Likely --- drivers/dma/mpc512x_dma.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 1bc04aa27b14..071752727718 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -276,6 +276,9 @@ static void mpc_dma_irq_process(struct mpc_dma *mdma, u32 is, u32 es, int off) spin_lock(&mchan->lock); + out_8(&mdma->regs->dmacint, ch + off); + out_8(&mdma->regs->dmacerr, ch + off); + /* Check error status */ if (es & (1 << ch)) list_for_each_entry(mdesc, &mchan->active, node) @@ -309,12 +312,6 @@ static irqreturn_t mpc_dma_irq(int irq, void *data) mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmaintl), in_be32(&mdma->regs->dmaerrl), 0); - /* Ack interrupt on all channels */ - out_be32(&mdma->regs->dmainth, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF); - /* Schedule tasklet */ tasklet_schedule(&mdma->tasklet); -- cgit v1.2.3 From ba2eea251f815b3674cde13ecdba4772332bf56e Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:52:57 +0200 Subject: powerpc/512x: add MPC8308 dma support MPC8308 has pretty much the same DMA controller as MPC5121 and this patch adds support for MPC8308 to the mpc512x_dma driver. Signed-off-by: Ilya Yanok Acked-by: Wolfgang Denk Signed-off-by: Grant Likely --- drivers/dma/Kconfig | 2 +- drivers/dma/mpc512x_dma.c | 95 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 72 insertions(+), 25 deletions(-) diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 6ee23592700a..ef138731c0ea 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -109,7 +109,7 @@ config FSL_DMA config MPC512X_DMA tristate "Freescale MPC512x built-in DMA engine support" - depends on PPC_MPC512x + depends on PPC_MPC512x || PPC_MPC831x select DMA_ENGINE ---help--- Enable support for the Freescale MPC512x built-in DMA engine. diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 071752727718..97b92ecb1427 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -1,6 +1,7 @@ /* * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008. * Copyright (C) Semihalf 2009 + * Copyright (C) Ilya Yanok, Emcraft Systems 2010 * * Written by Piotr Ziecik . Hardware description * (defines, structures and comments) was taken from MPC5121 DMA driver @@ -70,6 +71,8 @@ #define MPC_DMA_DMAES_SBE (1 << 1) #define MPC_DMA_DMAES_DBE (1 << 0) +#define MPC_DMA_DMAGPOR_SNOOP_ENABLE (1 << 6) + #define MPC_DMA_TSIZE_1 0x00 #define MPC_DMA_TSIZE_2 0x01 #define MPC_DMA_TSIZE_4 0x02 @@ -104,7 +107,10 @@ struct __attribute__ ((__packed__)) mpc_dma_regs { /* 0x30 */ u32 dmahrsh; /* DMA hw request status high(ch63~32) */ u32 dmahrsl; /* DMA hardware request status low(ch31~0) */ - u32 dmaihsa; /* DMA interrupt high select AXE(ch63~32) */ + union { + u32 dmaihsa; /* DMA interrupt high select AXE(ch63~32) */ + u32 dmagpor; /* (General purpose register on MPC8308) */ + }; u32 dmailsa; /* DMA interrupt low select AXE(ch31~0) */ /* 0x40 ~ 0xff */ u32 reserve0[48]; /* Reserved */ @@ -195,7 +201,9 @@ struct mpc_dma { struct mpc_dma_regs __iomem *regs; struct mpc_dma_tcd __iomem *tcd; int irq; + int irq2; uint error_status; + int is_mpc8308; /* Lock for error_status field in this structure */ spinlock_t error_status_lock; @@ -307,8 +315,10 @@ static irqreturn_t mpc_dma_irq(int irq, void *data) spin_unlock(&mdma->error_status_lock); /* Handle interrupt on each channel */ - mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth), + if (mdma->dma.chancnt > 32) { + mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth), in_be32(&mdma->regs->dmaerrh), 32); + } mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmaintl), in_be32(&mdma->regs->dmaerrl), 0); @@ -562,6 +572,7 @@ static struct dma_async_tx_descriptor * mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, size_t len, unsigned long flags) { + struct mpc_dma *mdma = dma_chan_to_mpc_dma(chan); struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan); struct mpc_dma_desc *mdesc = NULL; struct mpc_dma_tcd *tcd; @@ -590,7 +601,8 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, tcd->dsize = MPC_DMA_TSIZE_32; tcd->soff = 32; tcd->doff = 32; - } else if (IS_ALIGNED(src | dst | len, 16)) { + } else if (!mdma->is_mpc8308 && IS_ALIGNED(src | dst | len, 16)) { + /* MPC8308 doesn't support 16 byte transfers */ tcd->ssize = MPC_DMA_TSIZE_16; tcd->dsize = MPC_DMA_TSIZE_16; tcd->soff = 16; @@ -650,6 +662,15 @@ static int __devinit mpc_dma_probe(struct platform_device *op, return -EINVAL; } + if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) { + mdma->is_mpc8308 = 1; + mdma->irq2 = irq_of_parse_and_map(dn, 1); + if (mdma->irq2 == NO_IRQ) { + dev_err(dev, "Error mapping IRQ!\n"); + return -EINVAL; + } + } + retval = of_address_to_resource(dn, 0, &res); if (retval) { dev_err(dev, "Error parsing memory region!\n"); @@ -680,11 +701,23 @@ static int __devinit mpc_dma_probe(struct platform_device *op, return -EINVAL; } + if (mdma->is_mpc8308) { + retval = devm_request_irq(dev, mdma->irq2, &mpc_dma_irq, 0, + DRV_NAME, mdma); + if (retval) { + dev_err(dev, "Error requesting IRQ2!\n"); + return -EINVAL; + } + } + spin_lock_init(&mdma->error_status_lock); dma = &mdma->dma; dma->dev = dev; - dma->chancnt = MPC_DMA_CHANNELS; + if (!mdma->is_mpc8308) + dma->chancnt = MPC_DMA_CHANNELS; + else + dma->chancnt = 16; /* MPC8308 DMA has only 16 channels */ dma->device_alloc_chan_resources = mpc_dma_alloc_chan_resources; dma->device_free_chan_resources = mpc_dma_free_chan_resources; dma->device_issue_pending = mpc_dma_issue_pending; @@ -720,26 +753,40 @@ static int __devinit mpc_dma_probe(struct platform_device *op, * - Round-robin group arbitration, * - Round-robin channel arbitration. */ - out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG | - MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA); - - /* Disable hardware DMA requests */ - out_be32(&mdma->regs->dmaerqh, 0); - out_be32(&mdma->regs->dmaerql, 0); - - /* Disable error interrupts */ - out_be32(&mdma->regs->dmaeeih, 0); - out_be32(&mdma->regs->dmaeeil, 0); - - /* Clear interrupts status */ - out_be32(&mdma->regs->dmainth, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF); - out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF); - - /* Route interrupts to IPIC */ - out_be32(&mdma->regs->dmaihsa, 0); - out_be32(&mdma->regs->dmailsa, 0); + if (!mdma->is_mpc8308) { + out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG | + MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA); + + /* Disable hardware DMA requests */ + out_be32(&mdma->regs->dmaerqh, 0); + out_be32(&mdma->regs->dmaerql, 0); + + /* Disable error interrupts */ + out_be32(&mdma->regs->dmaeeih, 0); + out_be32(&mdma->regs->dmaeeil, 0); + + /* Clear interrupts status */ + out_be32(&mdma->regs->dmainth, 0xFFFFFFFF); + out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF); + out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF); + out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF); + + /* Route interrupts to IPIC */ + out_be32(&mdma->regs->dmaihsa, 0); + out_be32(&mdma->regs->dmailsa, 0); + } else { + /* MPC8308 has 16 channels and lacks some registers */ + out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA); + + /* enable snooping */ + out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE); + /* Disable error interrupts */ + out_be32(&mdma->regs->dmaeeil, 0); + + /* Clear interrupts status */ + out_be32(&mdma->regs->dmaintl, 0xFFFF); + out_be32(&mdma->regs->dmaerrl, 0xFFFF); + } /* Register DMA engine */ dev_set_drvdata(dev, mdma); -- cgit v1.2.3 From a276991357c63bfb8d3ffdf5800054dba4f8d558 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:52:58 +0200 Subject: powerpc/512x: try to free dma descriptors in case of allocation failure Currently completed descriptors are processed in the tasklet. This can lead to dead lock in case of CONFIG_NET_DMA enabled (new requests are submitted from softirq context and dma_memcpy_to_iovec() busy loops until the requests is submitted). To prevent this we should process completed descriptors from the allocation failure path in prepare_memcpy too. Signed-off-by: Ilya Yanok Cc: Piotr Ziecik Signed-off-by: Grant Likely --- drivers/dma/mpc512x_dma.c | 79 +++++++++++++++++++++++++++-------------------- 1 file changed, 45 insertions(+), 34 deletions(-) diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 97b92ecb1427..59c270192ccc 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -328,19 +328,55 @@ static irqreturn_t mpc_dma_irq(int irq, void *data) return IRQ_HANDLED; } -/* DMA Tasklet */ -static void mpc_dma_tasklet(unsigned long data) +/* proccess completed descriptors */ +static void mpc_dma_process_completed(struct mpc_dma *mdma) { - struct mpc_dma *mdma = (void *)data; dma_cookie_t last_cookie = 0; struct mpc_dma_chan *mchan; struct mpc_dma_desc *mdesc; struct dma_async_tx_descriptor *desc; unsigned long flags; LIST_HEAD(list); - uint es; int i; + for (i = 0; i < mdma->dma.chancnt; i++) { + mchan = &mdma->channels[i]; + + /* Get all completed descriptors */ + spin_lock_irqsave(&mchan->lock, flags); + if (!list_empty(&mchan->completed)) + list_splice_tail_init(&mchan->completed, &list); + spin_unlock_irqrestore(&mchan->lock, flags); + + if (list_empty(&list)) + continue; + + /* Execute callbacks and run dependencies */ + list_for_each_entry(mdesc, &list, node) { + desc = &mdesc->desc; + + if (desc->callback) + desc->callback(desc->callback_param); + + last_cookie = desc->cookie; + dma_run_dependencies(desc); + } + + /* Free descriptors */ + spin_lock_irqsave(&mchan->lock, flags); + list_splice_tail_init(&list, &mchan->free); + mchan->completed_cookie = last_cookie; + spin_unlock_irqrestore(&mchan->lock, flags); + } +} + +/* DMA Tasklet */ +static void mpc_dma_tasklet(unsigned long data) +{ + struct mpc_dma *mdma = (void *)data; + unsigned long flags; + uint es; + spin_lock_irqsave(&mdma->error_status_lock, flags); es = mdma->error_status; mdma->error_status = 0; @@ -379,35 +415,7 @@ static void mpc_dma_tasklet(unsigned long data) dev_err(mdma->dma.dev, "- Destination Bus Error\n"); } - for (i = 0; i < mdma->dma.chancnt; i++) { - mchan = &mdma->channels[i]; - - /* Get all completed descriptors */ - spin_lock_irqsave(&mchan->lock, flags); - if (!list_empty(&mchan->completed)) - list_splice_tail_init(&mchan->completed, &list); - spin_unlock_irqrestore(&mchan->lock, flags); - - if (list_empty(&list)) - continue; - - /* Execute callbacks and run dependencies */ - list_for_each_entry(mdesc, &list, node) { - desc = &mdesc->desc; - - if (desc->callback) - desc->callback(desc->callback_param); - - last_cookie = desc->cookie; - dma_run_dependencies(desc); - } - - /* Free descriptors */ - spin_lock_irqsave(&mchan->lock, flags); - list_splice_tail_init(&list, &mchan->free); - mchan->completed_cookie = last_cookie; - spin_unlock_irqrestore(&mchan->lock, flags); - } + mpc_dma_process_completed(mdma); } /* Submit descriptor to hardware */ @@ -587,8 +595,11 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, } spin_unlock_irqrestore(&mchan->lock, iflags); - if (!mdesc) + if (!mdesc) { + /* try to free completed descriptors */ + mpc_dma_process_completed(mdma); return NULL; + } mdesc->error = 0; tcd = mdesc->tcd; -- cgit v1.2.3 From 9d6599441837fc375ce768160e3c6f2f74eb5348 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:52:59 +0200 Subject: powerpc/83xx: add DMA controller to mpc8308 device-tree node MPC8308 has DMA controller compatible with mpc512x_dma driver. This patch adds device-tree node to support DMA controller on MPC8308RDB board. Signed-off-by: Ilya Yanok Acked-by: Wolfgang Denk Signed-off-by: Grant Likely --- arch/powerpc/boot/dts/mpc8308rdb.dts | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts index a97eb2db5a18..d3db02f98ddd 100644 --- a/arch/powerpc/boot/dts/mpc8308rdb.dts +++ b/arch/powerpc/boot/dts/mpc8308rdb.dts @@ -265,6 +265,14 @@ interrupt-parent = < &ipic >; }; + dma@2c000 { + compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma"; + reg = <0x2c000 0x1800>; + interrupts = <3 0x8 + 94 0x8>; + interrupt-parent = < &ipic >; + }; + }; pci0: pcie@e0009000 { -- cgit v1.2.3 From c9de9333f5a860cab82052bce6ac28bcac9b2c26 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Wed, 27 Oct 2010 01:53:00 +0200 Subject: powerpc/83xx: add mpc8308_p1m DMA controller device-tree node MPC8308 has DMA controller compatible with mpc512x_dma driver. This patch adds device-tree node to support DMA controller on MPC8308 P1M board. Signed-off-by: Ilya Yanok Acked-by: Wolfgang Denk Signed-off-by: Grant Likely --- arch/powerpc/boot/dts/mpc8308_p1m.dts | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts index 05a76ccfd499..697b3f6b78bf 100644 --- a/arch/powerpc/boot/dts/mpc8308_p1m.dts +++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts @@ -297,6 +297,14 @@ interrupt-parent = < &ipic >; }; + dma@2c000 { + compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma"; + reg = <0x2c000 0x1800>; + interrupts = <3 0x8 + 94 0x8>; + interrupt-parent = < &ipic >; + }; + }; pci0: pcie@e0009000 { -- cgit v1.2.3 From 39bf990ead35c7263652ca5dd8262b2b2cd147ac Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Fri, 17 Dec 2010 22:07:47 +0000 Subject: powerpc/pseries: Fix VPHN build errors on non-SMP systems The header asm/hvcall.h was previously included indirectly via smp.h. On non-SMP systems, however, these declarations are excluded and the build breaks. This is easily fixed by including asm/hvcall.h directly. The VPHN feature is only meaningful on NUMA systems that implement the SPLPAR option, so exclude the VPHN code on systems without SPLPAR enabled. Also, expose unmap_cpu_from_node() on systems with SPLPAR enabled, even if CONFIG_HOTPLUG_CPU is disabled. Lastly, map_cpu_to_node() is now needed by VPHN to manipulate the node masks after boot time, so remove the __cpuinit annotation to fix a section mismatch. Signed-off-by: Jesse Larrew --- arch/powerpc/include/asm/topology.h | 20 +++++++++++--------- arch/powerpc/mm/numa.c | 9 ++++++--- 2 files changed, 17 insertions(+), 12 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index aed188bd70db..fbfcfd04d25a 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -93,9 +93,20 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct sys_device *dev, int nid); extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); +#ifdef CONFIG_PPC_SPLPAR extern int start_topology_update(void); extern int stop_topology_update(void); #else +static inline int start_topology_update(void) +{ + return 0; +} +static inline int stop_topology_update(void) +{ + return 0; +} +#endif /* CONFIG_PPC_SPLPAR */ +#else static inline void dump_numa_cpu_topology(void) {} @@ -108,15 +119,6 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, int nid) { } - -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} #endif /* CONFIG_NUMA */ #include diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index d644ba7e8aba..3c0d20c9161a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -28,6 +28,7 @@ #include #include #include +#include static int numa_enabled = 1; @@ -167,7 +168,7 @@ static void __init get_node_active_region(unsigned long start_pfn, work_with_active_regions(nid, get_active_region_work_fn, node_ar); } -static void __cpuinit map_cpu_to_node(int cpu, int node) +static void map_cpu_to_node(int cpu, int node) { numa_cpu_lookup_table[cpu] = node; @@ -177,7 +178,7 @@ static void __cpuinit map_cpu_to_node(int cpu, int node) cpumask_set_cpu(cpu, node_to_cpumask_map[node]); } -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR) static void unmap_cpu_from_node(unsigned long cpu) { int node = numa_cpu_lookup_table[cpu]; @@ -191,7 +192,7 @@ static void unmap_cpu_from_node(unsigned long cpu) cpu, node); } } -#endif /* CONFIG_HOTPLUG_CPU */ +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ /* must hold reference to node during call */ static const int *of_get_associativity(struct device_node *dev) @@ -1289,6 +1290,7 @@ u64 memory_hotplug_max(void) #endif /* CONFIG_MEMORY_HOTPLUG */ /* Vrtual Processor Home Node (VPHN) support */ +#ifdef CONFIG_PPC_SPLPAR #define VPHN_NR_CHANGE_CTRS (8) static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; static cpumask_t cpu_associativity_changes_mask; @@ -1531,3 +1533,4 @@ int stop_topology_update(void) vphn_enabled = 0; return del_timer_sync(&topology_timer); } +#endif /* CONFIG_PPC_SPLPAR */ -- cgit v1.2.3 From 5d7d8072edc11080a7cf6cc37c9f4e61ca1e93c9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 12 Jan 2011 10:56:29 +1100 Subject: powerpc/pseries: Fix build of topology stuff without CONFIG_NUMA Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/topology.h | 27 ++++++++++++++------------- arch/powerpc/mm/numa.c | 1 - 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index fbfcfd04d25a..7ef0d90defc8 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -93,19 +93,6 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct sys_device *dev, int nid); extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); -#ifdef CONFIG_PPC_SPLPAR -extern int start_topology_update(void); -extern int stop_topology_update(void); -#else -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} -#endif /* CONFIG_PPC_SPLPAR */ #else static inline void dump_numa_cpu_topology(void) {} @@ -121,6 +108,20 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, } #endif /* CONFIG_NUMA */ +#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) +extern int start_topology_update(void); +extern int stop_topology_update(void); +#else +static inline int start_topology_update(void) +{ + return 0; +} +static inline int stop_topology_update(void) +{ + return 0; +} +#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ + #include #ifdef CONFIG_SMP diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 3c0d20c9161a..bf5cb91f07de 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1296,7 +1296,6 @@ static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; static cpumask_t cpu_associativity_changes_mask; static int vphn_enabled; static void set_topology_timer(void); -int stop_topology_update(void); /* * Store the current values of the associativity change counters in the -- cgit v1.2.3