diff options
Diffstat (limited to 'arch')
41 files changed, 1717 insertions, 338 deletions
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c index cc71a26..3559803 100644 --- a/arch/arm/mach-omap1/board-palmz71.c +++ b/arch/arm/mach-omap1/board-palmz71.c @@ -288,8 +288,7 @@ palmz71_gpio_setup(int early) } gpio_direction_input(PALMZ71_USBDETECT_GPIO); if (request_irq(gpio_to_irq(PALMZ71_USBDETECT_GPIO), - palmz71_powercable, IRQF_SAMPLE_RANDOM, - "palmz71-cable", NULL)) + palmz71_powercable, 0, "palmz71-cable", NULL)) printk(KERN_ERR "IRQ request for power cable failed!\n"); palmz71_powercable(gpio_to_irq(PALMZ71_USBDETECT_GPIO), NULL); diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index 6bb3f47..0ca0db7 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -456,7 +456,7 @@ static int lubbock_mci_init(struct device *dev, init_timer(&mmc_timer); mmc_timer.data = (unsigned long) data; return request_irq(LUBBOCK_SD_IRQ, lubbock_detect_int, - IRQF_SAMPLE_RANDOM, "lubbock-sd-detect", data); + 0, "lubbock-sd-detect", data); } static int lubbock_mci_get_ro(struct device *dev) diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c index 2db697c..39561dc 100644 --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -633,9 +633,8 @@ static struct platform_device bq24022 = { static int magician_mci_init(struct device *dev, irq_handler_t detect_irq, void *data) { - return request_irq(IRQ_MAGICIAN_SD, detect_irq, - IRQF_DISABLED | IRQF_SAMPLE_RANDOM, - "mmc card detect", data); + return request_irq(IRQ_MAGICIAN_SD, detect_irq, IRQF_DISABLED, + "mmc card detect", data); } static void magician_mci_exit(struct device *dev, void *data) diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c index 2b6ac00..166dd32 100644 --- a/arch/arm/mach-pxa/trizeps4.c +++ b/arch/arm/mach-pxa/trizeps4.c @@ -332,8 +332,8 @@ static int trizeps4_mci_init(struct device *dev, irq_handler_t mci_detect_int, int err; err = request_irq(TRIZEPS4_MMC_IRQ, mci_detect_int, - IRQF_DISABLED | IRQF_TRIGGER_RISING | IRQF_SAMPLE_RANDOM, - "MMC card detect", data); + IRQF_DISABLED | IRQF_TRIGGER_RISING, + "MMC card detect", data); if (err) { printk(KERN_ERR "trizeps4_mci_init: MMC/SD: can't request" "MMC card detect IRQ\n"); diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 5c3e088..1034884 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -23,7 +23,6 @@ #include <linux/ioport.h> #include <linux/kernel_stat.h> #include <linux/ptrace.h> -#include <linux/random.h> /* for rand_initialize_irq() */ #include <linux/signal.h> #include <linux/smp.h> #include <linux/threads.h> diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts index 852e5b2..57573bd 100644 --- a/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts +++ b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts @@ -56,7 +56,7 @@ ranges = <0x0 0x0 0xffe00000 0x100000>; }; - pci0: pcie@ffe08000 { + pci2: pcie@ffe08000 { reg = <0 0xffe08000 0 0x1000>; status = "disabled"; }; @@ -76,7 +76,7 @@ }; }; - pci2: pcie@ffe0a000 { + pci0: pcie@ffe0a000 { reg = <0 0xffe0a000 0 0x1000>; ranges = <0x2000000 0x0 0xe0000000 0 0x80000000 0x0 0x20000000 0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>; diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts index b5a56ca..470247e 100644 --- a/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts +++ b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts @@ -56,7 +56,7 @@ ranges = <0x0 0xf 0xffe00000 0x100000>; }; - pci0: pcie@fffe08000 { + pci2: pcie@fffe08000 { reg = <0xf 0xffe08000 0 0x1000>; status = "disabled"; }; @@ -76,7 +76,7 @@ }; }; - pci2: pcie@fffe0a000 { + pci0: pcie@fffe0a000 { reg = <0xf 0xffe0a000 0 0x1000>; ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000 0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>; diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts index 22a215e..6cdcadc 100644 --- a/arch/powerpc/boot/dts/p3041ds.dts +++ b/arch/powerpc/boot/dts/p3041ds.dts @@ -58,7 +58,7 @@ #size-cells = <1>; compatible = "spansion,s25sl12801"; reg = <0>; - spi-max-frequency = <40000000>; /* input clock */ + spi-max-frequency = <35000000>; /* input clock */ partition@u-boot { label = "u-boot"; reg = <0x00000000 0x00100000>; diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index ab523f3..9ecf6e3 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -67,7 +67,6 @@ kvmppc_skip_Hinterrupt: #elif defined(CONFIG_PPC_BOOK3S_32) #define FUNC(name) name -#define MTMSR_EERI(reg) mtmsr (reg) .macro INTERRUPT_TRAMPOLINE intno diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 89ee02c..3c732ac 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -208,6 +208,7 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) u8 __iomem *lbc_lcs0_ba = NULL; u8 __iomem *lbc_lcs1_ba = NULL; phys_addr_t cs0_addr, cs1_addr; + u32 br0, or0, br1, or1; const __be32 *iprop; unsigned int num_laws; u8 b; @@ -256,11 +257,70 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) } num_laws = be32_to_cpup(iprop); - cs0_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[0].br)); - cs1_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[1].br)); + /* + * Indirect mode requires both BR0 and BR1 to be set to "GPCM", + * otherwise writes to these addresses won't actually appear on the + * local bus, and so the PIXIS won't see them. + * + * In FCM mode, writes go to the NAND controller, which does not pass + * them to the localbus directly. So we force BR0 and BR1 into GPCM + * mode, since we don't care about what's behind the localbus any + * more. + */ + br0 = in_be32(&lbc->bank[0].br); + br1 = in_be32(&lbc->bank[1].br); + or0 = in_be32(&lbc->bank[0].or); + or1 = in_be32(&lbc->bank[1].or); + + /* Make sure CS0 and CS1 are programmed */ + if (!(br0 & BR_V) || !(br1 & BR_V)) { + pr_err("p1022ds: CS0 and/or CS1 is not programmed\n"); + goto exit; + } + + /* + * Use the existing BRx/ORx values if it's already GPCM. Otherwise, + * force the values to simple 32KB GPCM windows with the most + * conservative timing. + */ + if ((br0 & BR_MSEL) != BR_MS_GPCM) { + br0 = (br0 & BR_BA) | BR_V; + or0 = 0xFFFF8000 | 0xFF7; + out_be32(&lbc->bank[0].br, br0); + out_be32(&lbc->bank[0].or, or0); + } + if ((br1 & BR_MSEL) != BR_MS_GPCM) { + br1 = (br1 & BR_BA) | BR_V; + or1 = 0xFFFF8000 | 0xFF7; + out_be32(&lbc->bank[1].br, br1); + out_be32(&lbc->bank[1].or, or1); + } + + cs0_addr = lbc_br_to_phys(ecm, num_laws, br0); + if (!cs0_addr) { + pr_err("p1022ds: could not determine physical address for CS0" + " (BR0=%08x)\n", br0); + goto exit; + } + cs1_addr = lbc_br_to_phys(ecm, num_laws, br1); + if (!cs0_addr) { + pr_err("p1022ds: could not determine physical address for CS1" + " (BR1=%08x)\n", br1); + goto exit; + } lbc_lcs0_ba = ioremap(cs0_addr, 1); + if (!lbc_lcs0_ba) { + pr_err("p1022ds: could not ioremap CS0 address %llx\n", + (unsigned long long)cs0_addr); + goto exit; + } lbc_lcs1_ba = ioremap(cs1_addr, 1); + if (!lbc_lcs1_ba) { + pr_err("p1022ds: could not ioremap CS1 address %llx\n", + (unsigned long long)cs1_addr); + goto exit; + } /* Make sure we're in indirect mode first. */ if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) != @@ -419,18 +479,6 @@ void __init p1022_ds_pic_init(void) #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) -/* - * Disables a node in the device tree. - * - * This function is called before kmalloc() is available, so the 'new' object - * should be allocated in the global area. The easiest way is to do that is - * to allocate one static local variable for each call to this function. - */ -static void __init disable_one_node(struct device_node *np, struct property *new) -{ - prom_update_property(np, new); -} - /* TRUE if there is a "video=fslfb" command-line parameter. */ static bool fslfb; @@ -493,28 +541,58 @@ static void __init p1022_ds_setup_arch(void) diu_ops.valid_monitor_port = p1022ds_valid_monitor_port; /* - * Disable the NOR flash node if there is video=fslfb... command-line - * parameter. When the DIU is active, NOR flash is unavailable, so we - * have to disable the node before the MTD driver loads. + * Disable the NOR and NAND flash nodes if there is video=fslfb... + * command-line parameter. When the DIU is active, the localbus is + * unavailable, so we have to disable these nodes before the MTD + * driver loads. */ if (fslfb) { struct device_node *np = of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc"); if (np) { - np = of_find_compatible_node(np, NULL, "cfi-flash"); - if (np) { + struct device_node *np2; + + of_node_get(np); + np2 = of_find_compatible_node(np, NULL, "cfi-flash"); + if (np2) { static struct property nor_status = { .name = "status", .value = "disabled", .length = sizeof("disabled"), }; + /* + * prom_update_property() is called before + * kmalloc() is available, so the 'new' object + * should be allocated in the global area. + * The easiest way is to do that is to + * allocate one static local variable for each + * call to this function. + */ pr_info("p1022ds: disabling %s node", - np->full_name); - disable_one_node(np, &nor_status); - of_node_put(np); + np2->full_name); + prom_update_property(np2, &nor_status); + of_node_put(np2); } + + of_node_get(np); + np2 = of_find_compatible_node(np, NULL, + "fsl,elbc-fcm-nand"); + if (np2) { + static struct property nand_status = { + .name = "status", + .value = "disabled", + .length = sizeof("disabled"), + }; + + pr_info("p1022ds: disabling %s node", + np2->full_name); + prom_update_property(np2, &nand_status); + of_node_put(np2); + } + + of_node_put(np); } } diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h index 60c9c0b..2aa97ddb 100644 --- a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h +++ b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h @@ -1,5 +1,5 @@ /* - * Copyright 2009-2010 Freescale Semiconductor, Inc + * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc * * QorIQ based Cache Controller Memory Mapped Registers * @@ -91,7 +91,7 @@ struct mpc85xx_l2ctlr { struct sram_parameters { unsigned int sram_size; - uint64_t sram_offset; + phys_addr_t sram_offset; }; extern int instantiate_cache_sram(struct platform_device *dev, diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c index cedabd0..68ac3aa 100644 --- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c +++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c @@ -1,5 +1,5 @@ /* - * Copyright 2009-2010 Freescale Semiconductor, Inc. + * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc. * * QorIQ (P1/P2) L2 controller init for Cache-SRAM instantiation * @@ -31,24 +31,21 @@ static char *sram_size; static char *sram_offset; struct mpc85xx_l2ctlr __iomem *l2ctlr; -static long get_cache_sram_size(void) +static int get_cache_sram_params(struct sram_parameters *sram_params) { - unsigned long val; + unsigned long long addr; + unsigned int size; - if (!sram_size || (strict_strtoul(sram_size, 0, &val) < 0)) + if (!sram_size || (kstrtouint(sram_size, 0, &size) < 0)) return -EINVAL; - return val; -} - -static long get_cache_sram_offset(void) -{ - unsigned long val; - - if (!sram_offset || (strict_strtoul(sram_offset, 0, &val) < 0)) + if (!sram_offset || (kstrtoull(sram_offset, 0, &addr) < 0)) return -EINVAL; - return val; + sram_params->sram_offset = addr; + sram_params->sram_size = size; + + return 0; } static int __init get_size_from_cmdline(char *str) @@ -93,17 +90,9 @@ static int __devinit mpc85xx_l2ctlr_of_probe(struct platform_device *dev) } l2cache_size = *prop; - sram_params.sram_size = get_cache_sram_size(); - if ((int)sram_params.sram_size <= 0) { - dev_err(&dev->dev, - "Entire L2 as cache, Aborting Cache-SRAM stuff\n"); - return -EINVAL; - } - - sram_params.sram_offset = get_cache_sram_offset(); - if ((int64_t)sram_params.sram_offset <= 0) { + if (get_cache_sram_params(&sram_params)) { dev_err(&dev->dev, - "Entire L2 as cache, provide a valid sram offset\n"); + "Entire L2 as cache, provide valid sram offset and size\n"); return -EINVAL; } @@ -125,14 +114,14 @@ static int __devinit mpc85xx_l2ctlr_of_probe(struct platform_device *dev) * Write bits[0-17] to srbar0 */ out_be32(&l2ctlr->srbar0, - sram_params.sram_offset & L2SRAM_BAR_MSK_LO18); + lower_32_bits(sram_params.sram_offset) & L2SRAM_BAR_MSK_LO18); /* * Write bits[18-21] to srbare0 */ #ifdef CONFIG_PHYS_64BIT out_be32(&l2ctlr->srbarea0, - (sram_params.sram_offset >> 32) & L2SRAM_BARE_MSK_HI4); + upper_32_bits(sram_params.sram_offset) & L2SRAM_BARE_MSK_HI4); #endif clrsetbits_be32(&l2ctlr->ctl, L2CR_L2E, L2CR_L2FI); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 296cd32..76de6b6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -90,6 +90,7 @@ config S390 select HAVE_MEMBLOCK_NODE_MAP select HAVE_CMPXCHG_LOCAL select ARCH_DISCARD_MEMBLOCK + select BUILDTIME_EXTABLE_SORT select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK diff --git a/arch/s390/defconfig b/arch/s390/defconfig index de57702..f39cd71 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -7,6 +7,9 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_RCU_FAST_NO_HZ=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_CGROUPS=y @@ -35,8 +38,6 @@ CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 5c63615..b749c57 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -11,7 +11,6 @@ #include <asm/uaccess.h> #include <asm/tlbflush.h> #include <asm/ctl_reg.h> -#include <asm-generic/mm_hooks.h> static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) @@ -58,7 +57,7 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk) pgd_t *pgd = mm->pgd; S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd); - if (user_mode != HOME_SPACE_MODE) { + if (addressing_mode != HOME_SPACE_MODE) { /* Load primary space page table origin. */ asm volatile(LCTL_OPCODE" 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); @@ -91,4 +90,17 @@ static inline void activate_mm(struct mm_struct *prev, switch_mm(prev, next, current); } +static inline void arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_64BIT + if (oldmm->context.asce_limit < mm->context.asce_limit) + crst_table_downgrade(mm, oldmm->context.asce_limit); +#endif +} + +static inline void arch_exit_mmap(struct mm_struct *mm) +{ +} + #endif /* __S390_MMU_CONTEXT_H */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c40fa91..11e4e32 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -120,7 +120,9 @@ struct stack_frame { regs->psw.mask = psw_user_bits | PSW_MASK_BA; \ regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ regs->gprs[15] = new_stackp; \ + __tlb_flush_mm(current->mm); \ crst_table_downgrade(current->mm, 1UL << 31); \ + update_mm(current->mm, current); \ } while (0) /* Forward declaration, a strange C thing */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 57e8053..e6859d1 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -60,7 +60,7 @@ void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr, #define SECONDARY_SPACE_MODE 2 #define HOME_SPACE_MODE 3 -extern unsigned int user_mode; +extern unsigned int addressing_mode; /* * Machine features detected in head.S diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 21be961..ba500d8 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -110,6 +110,7 @@ struct debug_view debug_raw_view = { NULL, NULL }; +EXPORT_SYMBOL(debug_raw_view); struct debug_view debug_hex_ascii_view = { "hex_ascii", @@ -119,6 +120,7 @@ struct debug_view debug_hex_ascii_view = { NULL, NULL }; +EXPORT_SYMBOL(debug_hex_ascii_view); static struct debug_view debug_level_view = { "level", @@ -155,6 +157,7 @@ struct debug_view debug_sprintf_view = { NULL, NULL }; +EXPORT_SYMBOL(debug_sprintf_view); /* used by dump analysis tools to determine version of debug feature */ static unsigned int __used debug_feature_version = __DEBUG_FEATURE_VERSION; @@ -730,6 +733,7 @@ debug_info_t *debug_register(const char *name, int pages_per_area, return debug_register_mode(name, pages_per_area, nr_areas, buf_size, S_IRUSR | S_IWUSR, 0, 0); } +EXPORT_SYMBOL(debug_register); /* * debug_unregister: @@ -748,6 +752,7 @@ debug_unregister(debug_info_t * id) out: return; } +EXPORT_SYMBOL(debug_unregister); /* * debug_set_size: @@ -810,7 +815,7 @@ debug_set_level(debug_info_t* id, int new_level) } spin_unlock_irqrestore(&id->lock,flags); } - +EXPORT_SYMBOL(debug_set_level); /* * proceed_active_entry: @@ -930,7 +935,7 @@ debug_stop_all(void) if (debug_stoppable) debug_active = 0; } - +EXPORT_SYMBOL(debug_stop_all); void debug_set_critical(void) { @@ -963,6 +968,7 @@ debug_event_common(debug_info_t * id, int level, const void *buf, int len) return active; } +EXPORT_SYMBOL(debug_event_common); /* * debug_exception_common: @@ -990,6 +996,7 @@ debug_entry_t return active; } +EXPORT_SYMBOL(debug_exception_common); /* * counts arguments in format string for sprintf view @@ -1043,6 +1050,7 @@ debug_sprintf_event(debug_info_t* id, int level,char *string,...) return active; } +EXPORT_SYMBOL(debug_sprintf_event); /* * debug_sprintf_exception: @@ -1081,25 +1089,7 @@ debug_sprintf_exception(debug_info_t* id, int level,char *string,...) return active; } - -/* - * debug_init: - * - is called exactly once to initialize the debug feature - */ - -static int -__init debug_init(void) -{ - int rc = 0; - - s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table); - mutex_lock(&debug_mutex); - debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT,NULL); - initialized = 1; - mutex_unlock(&debug_mutex); - - return rc; -} +EXPORT_SYMBOL(debug_sprintf_exception); /* * debug_register_view: @@ -1147,6 +1137,7 @@ debug_register_view(debug_info_t * id, struct debug_view *view) out: return rc; } +EXPORT_SYMBOL(debug_register_view); /* * debug_unregister_view: @@ -1176,6 +1167,7 @@ debug_unregister_view(debug_info_t * id, struct debug_view *view) out: return rc; } +EXPORT_SYMBOL(debug_unregister_view); static inline char * debug_get_user_string(const char __user *user_buf, size_t user_len) @@ -1485,6 +1477,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, except_str, entry->id.fields.cpuid, (void *) caller); return rc; } +EXPORT_SYMBOL(debug_dflt_header_fn); /* * prints debug data sprintf-formated: @@ -1533,33 +1526,16 @@ out: } /* - * clean up module + * debug_init: + * - is called exactly once to initialize the debug feature */ -static void __exit debug_exit(void) +static int __init debug_init(void) { - debugfs_remove(debug_debugfs_root_entry); - unregister_sysctl_table(s390dbf_sysctl_header); - return; + s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table); + mutex_lock(&debug_mutex); + debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT, NULL); + initialized = 1; + mutex_unlock(&debug_mutex); + return 0; } - -/* - * module definitions - */ postcore_initcall(debug_init); -module_exit(debug_exit); -MODULE_LICENSE("GPL"); - -EXPORT_SYMBOL(debug_register); -EXPORT_SYMBOL(debug_unregister); -EXPORT_SYMBOL(debug_set_level); -EXPORT_SYMBOL(debug_stop_all); -EXPORT_SYMBOL(debug_register_view); -EXPORT_SYMBOL(debug_unregister_view); -EXPORT_SYMBOL(debug_event_common); -EXPORT_SYMBOL(debug_exception_common); -EXPORT_SYMBOL(debug_hex_ascii_view); -EXPORT_SYMBOL(debug_raw_view); -EXPORT_SYMBOL(debug_dflt_header_fn); -EXPORT_SYMBOL(debug_sprintf_view); -EXPORT_SYMBOL(debug_sprintf_exception); -EXPORT_SYMBOL(debug_sprintf_event); diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 1f6b428..619c5d3 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1531,7 +1531,7 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) void show_code(struct pt_regs *regs) { - char *mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl"; + char *mode = user_mode(regs) ? "User" : "Krnl"; unsigned char code[64]; char buffer[64], *ptr; mm_segment_t old_fs; @@ -1540,7 +1540,7 @@ void show_code(struct pt_regs *regs) /* Get a snapshot of the 64 bytes surrounding the fault address. */ old_fs = get_fs(); - set_fs((regs->psw.mask & PSW_MASK_PSTATE) ? USER_DS : KERNEL_DS); + set_fs(user_mode(regs) ? USER_DS : KERNEL_DS); for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) { addr = regs->psw.addr - 34 + start; if (__copy_from_user(code + start - 2, diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index bc95a8e..83c3271 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -455,7 +455,6 @@ void __init startup_init(void) init_kernel_storage_key(); lockdep_init(); lockdep_off(); - sort_main_extable(); setup_lowcore_early(); setup_facility_list(); detect_machine_type(); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index e64d141..6ffcd32 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1583,7 +1583,7 @@ static struct kset *vmcmd_kset; static void vmcmd_run(struct shutdown_trigger *trigger) { - char *cmd, *next_cmd; + char *cmd; if (strcmp(trigger->name, ON_REIPL_STR) == 0) cmd = vmcmd_on_reboot; @@ -1600,15 +1600,7 @@ static void vmcmd_run(struct shutdown_trigger *trigger) if (strlen(cmd) == 0) return; - do { - next_cmd = strchr(cmd, '\n'); - if (next_cmd) { - next_cmd[0] = 0; - next_cmd += 1; - } - __cpcmd(cmd, NULL, 0, NULL); - cmd = next_cmd; - } while (cmd != NULL); + __cpcmd(cmd, NULL, 0, NULL); } static int vmcmd_init(void) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 743c0f3..f86c81e 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -302,8 +302,8 @@ static int __init parse_vmalloc(char *arg) } early_param("vmalloc", parse_vmalloc); -unsigned int user_mode = HOME_SPACE_MODE; -EXPORT_SYMBOL_GPL(user_mode); +unsigned int addressing_mode = HOME_SPACE_MODE; +EXPORT_SYMBOL_GPL(addressing_mode); static int set_amode_primary(void) { @@ -328,7 +328,7 @@ static int set_amode_primary(void) */ static int __init early_parse_switch_amode(char *p) { - user_mode = PRIMARY_SPACE_MODE; + addressing_mode = PRIMARY_SPACE_MODE; return 0; } early_param("switch_amode", early_parse_switch_amode); @@ -336,9 +336,9 @@ early_param("switch_amode", early_parse_switch_amode); static int __init early_parse_user_mode(char *p) { if (p && strcmp(p, "primary") == 0) - user_mode = PRIMARY_SPACE_MODE; + addressing_mode = PRIMARY_SPACE_MODE; else if (!p || strcmp(p, "home") == 0) - user_mode = HOME_SPACE_MODE; + addressing_mode = HOME_SPACE_MODE; else return 1; return 0; @@ -347,7 +347,7 @@ early_param("user_mode", early_parse_user_mode); static void setup_addressing_mode(void) { - if (user_mode == PRIMARY_SPACE_MODE) { + if (addressing_mode == PRIMARY_SPACE_MODE) { if (set_amode_primary()) pr_info("Address spaces switched, " "mvcos available\n"); diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index af2421a..01775c0 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -185,7 +185,7 @@ void show_registers(struct pt_regs *regs) { char *mode; - mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl"; + mode = user_mode(regs) ? "User" : "Krnl"; printk("%s PSW : %p %p", mode, (void *) regs->psw.mask, (void *) regs->psw.addr); @@ -225,7 +225,7 @@ void show_regs(struct pt_regs *regs) (void *) current->thread.ksp); show_registers(regs); /* Show stack backtrace if pt_regs is from kernel mode */ - if (!(regs->psw.mask & PSW_MASK_PSTATE)) + if (!user_mode(regs)) show_trace(NULL, (unsigned long *) regs->gprs[15]); show_last_breaking_event(regs); } @@ -300,7 +300,7 @@ static void __kprobes do_trap(struct pt_regs *regs, regs->int_code, si_signo) == NOTIFY_STOP) return; - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { info.si_signo = si_signo; info.si_errno = 0; info.si_code = si_code; @@ -341,7 +341,7 @@ void __kprobes do_per_trap(struct pt_regs *regs) static void default_trap_handler(struct pt_regs *regs) { - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { report_user_fault(regs, SIGSEGV); do_exit(SIGSEGV); } else @@ -410,7 +410,7 @@ static void __kprobes illegal_op(struct pt_regs *regs) location = get_psw_address(regs); - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) return; if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) { @@ -478,7 +478,7 @@ void specification_exception(struct pt_regs *regs) location = (__u16 __user *) get_psw_address(regs); - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { get_user(*((__u16 *) opcode), location); switch (opcode[0]) { case 0x28: /* LDR Rx,Ry */ @@ -531,7 +531,7 @@ static void data_exception(struct pt_regs *regs) asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc)); #ifdef CONFIG_MATHEMU - else if (regs->psw.mask & PSW_MASK_PSTATE) { + else if (user_mode(regs)) { __u8 opcode[6]; get_user(*((__u16 *) opcode), location); switch (opcode[0]) { @@ -598,7 +598,7 @@ static void data_exception(struct pt_regs *regs) static void space_switch_exception(struct pt_regs *regs) { /* Set user psw back to home space mode. */ - if (regs->psw.mask & PSW_MASK_PSTATE) + if (user_mode(regs)) regs->psw.mask |= PSW_ASC_HOME; /* Send SIGILL. */ do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event"); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index ea5590f..9a19ca3 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -84,7 +84,8 @@ struct vdso_data *vdso_data = &vdso_data_store.data; */ static void vdso_init_data(struct vdso_data *vd) { - vd->ectg_available = user_mode != HOME_SPACE_MODE && test_facility(31); + vd->ectg_available = + addressing_mode != HOME_SPACE_MODE && test_facility(31); } #ifdef CONFIG_64BIT @@ -101,7 +102,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) lowcore->vdso_per_cpu_data = __LC_PASTE; - if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) return 0; segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); @@ -146,7 +147,7 @@ void vdso_free_per_cpu(struct _lowcore *lowcore) unsigned long segment_table, page_table, page_frame; u32 *psal, *aste; - if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) return; psal = (u32 *)(addr_t) lowcore->paste[4]; @@ -164,7 +165,7 @@ static void vdso_init_cr5(void) { unsigned long cr5; - if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) return; cr5 = offsetof(struct _lowcore, paste); __ctl_load(cr5, 5, 5); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 21109c6..de8fa9b 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -45,7 +45,7 @@ SECTIONS .dummy : { *(.dummy) } :data - RODATA + RO_DATA_SECTION(PAGE_SIZE) #ifdef CONFIG_SHARED_KERNEL . = ALIGN(0x100000); /* VM shared segments are 1MB aligned */ diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6a12d1b..6c013f5 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -49,6 +49,7 @@ #define VM_FAULT_BADCONTEXT 0x010000 #define VM_FAULT_BADMAP 0x020000 #define VM_FAULT_BADACCESS 0x040000 +#define VM_FAULT_SIGNAL 0x080000 static unsigned long store_indication; @@ -110,7 +111,7 @@ static inline int user_space_fault(unsigned long trans_exc_code) if (trans_exc_code == 2) /* Access via secondary space, set_fs setting decides */ return current->thread.mm_segment.ar4; - if (user_mode == HOME_SPACE_MODE) + if (addressing_mode == HOME_SPACE_MODE) /* User space if the access has been done via home space. */ return trans_exc_code == 3; /* @@ -219,7 +220,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) case VM_FAULT_BADACCESS: case VM_FAULT_BADMAP: /* Bad memory access. Check if it is kernel or user space. */ - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { /* User mode accesses just cause a SIGSEGV */ si_code = (fault == VM_FAULT_BADMAP) ? SEGV_MAPERR : SEGV_ACCERR; @@ -229,15 +230,19 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) case VM_FAULT_BADCONTEXT: do_no_context(regs); break; + case VM_FAULT_SIGNAL: + if (!user_mode(regs)) + do_no_context(regs); + break; default: /* fault & VM_FAULT_ERROR */ if (fault & VM_FAULT_OOM) { - if (!(regs->psw.mask & PSW_MASK_PSTATE)) + if (!user_mode(regs)) do_no_context(regs); else pagefault_out_of_memory(); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ - if (!(regs->psw.mask & PSW_MASK_PSTATE)) + if (!user_mode(regs)) do_no_context(regs); else do_sigbus(regs); @@ -286,7 +291,7 @@ static inline int do_exception(struct pt_regs *regs, int access) address = trans_exc_code & __FAIL_ADDR_MASK; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - flags = FAULT_FLAG_ALLOW_RETRY; + flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem); @@ -335,6 +340,11 @@ retry: * the fault. */ fault = handle_mm_fault(mm, vma, address, flags); + /* No reason to continue if interrupted by SIGKILL. */ + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { + fault = VM_FAULT_SIGNAL; + goto out; + } if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -426,7 +436,7 @@ void __kprobes do_asce_exception(struct pt_regs *regs) } /* User mode accesses just cause a SIGSEGV */ - if (regs->psw.mask & PSW_MASK_PSTATE) { + if (user_mode(regs)) { do_sigsegv(regs, SEGV_MAPERR); return; } @@ -441,6 +451,7 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write) struct pt_regs regs; int access, fault; + /* Emulate a uaccess fault from kernel mode. */ regs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK; if (!irqs_disabled()) regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT; @@ -450,12 +461,12 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write) regs.int_parm_long = (uaddr & PAGE_MASK) | 2; access = write ? VM_WRITE : VM_READ; fault = do_exception(®s, access); - if (unlikely(fault)) { - if (fault & VM_FAULT_OOM) - return -EFAULT; - else if (fault & VM_FAULT_SIGBUS) - do_sigbus(®s); - } + /* + * Since the fault happened in kernel mode while performing a uaccess + * all we need to do now is emulating a fixup in case "fault" is not + * zero. + * For the calling uaccess functions this results always in -EFAULT. + */ return fault ? -EFAULT : 0; } diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 5733842..c59a5ef 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -103,9 +103,15 @@ void arch_pick_mmap_layout(struct mm_struct *mm) int s390_mmap_check(unsigned long addr, unsigned long len) { + int rc; + if (!is_compat_task() && - len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) - return crst_table_upgrade(current->mm, 1UL << 53); + len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) { + rc = crst_table_upgrade(current->mm, 1UL << 53); + if (rc) + return rc; + update_mm(current->mm, current); + } return 0; } @@ -125,6 +131,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, rc = crst_table_upgrade(mm, 1UL << 53); if (rc) return (unsigned long) rc; + update_mm(mm, current); area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); } return area; @@ -147,6 +154,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, rc = crst_table_upgrade(mm, 1UL << 53); if (rc) return (unsigned long) rc; + update_mm(mm, current); area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 1cab221..18df31d 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -85,7 +85,6 @@ repeat: crst_table_free(mm, table); if (mm->context.asce_limit < limit) goto repeat; - update_mm(mm, current); return 0; } @@ -93,9 +92,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) { pgd_t *pgd; - if (mm->context.asce_limit <= limit) - return; - __tlb_flush_mm(mm); while (mm->context.asce_limit > limit) { pgd = mm->pgd; switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { @@ -118,7 +114,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) mm->task_size = mm->context.asce_limit; crst_table_free(mm, (unsigned long *) pgd); } - update_mm(mm, current); } #endif @@ -801,7 +796,7 @@ int s390_enable_sie(void) struct mm_struct *mm, *old_mm; /* Do we have switched amode? If no, we cannot do sie */ - if (user_mode == HOME_SPACE_MODE) + if (addressing_mode == HOME_SPACE_MODE) return -EINVAL; /* Do we have pgstes? if yes, we are done */ diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index c82f62f..8a6811b 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -58,7 +58,7 @@ void s390_backtrace(struct pt_regs * const regs, unsigned int depth) unsigned long head; struct stack_frame* head_sf; - if (user_mode (regs)) + if (user_mode(regs)) return; head = regs->gprs[15]; diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 435e406..81d92fc 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -1250,14 +1250,12 @@ int ldc_bind(struct ldc_channel *lp, const char *name) snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); - err = request_irq(lp->cfg.rx_irq, ldc_rx, - IRQF_SAMPLE_RANDOM | IRQF_DISABLED, + err = request_irq(lp->cfg.rx_irq, ldc_rx, IRQF_DISABLED, lp->rx_irq_name, lp); if (err) return err; - err = request_irq(lp->cfg.tx_irq, ldc_tx, - IRQF_SAMPLE_RANDOM | IRQF_DISABLED, + err = request_irq(lp->cfg.tx_irq, ldc_tx, IRQF_DISABLED, lp->tx_irq_name, lp); if (err) { free_irq(lp->cfg.rx_irq, lp); diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index acfd0e0..ac9d25c 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -362,18 +362,18 @@ static irqreturn_t line_write_interrupt(int irq, void *data) int line_setup_irq(int fd, int input, int output, struct line *line, void *data) { const struct line_driver *driver = line->driver; - int err = 0, flags = IRQF_SHARED | IRQF_SAMPLE_RANDOM; + int err = 0; if (input) err = um_request_irq(driver->read_irq, fd, IRQ_READ, - line_interrupt, flags, - driver->read_irq_name, data); + line_interrupt, IRQF_SHARED, + driver->read_irq_name, data); if (err) return err; if (output) err = um_request_irq(driver->write_irq, fd, IRQ_WRITE, - line_write_interrupt, flags, - driver->write_irq_name, data); + line_write_interrupt, IRQF_SHARED, + driver->write_irq_name, data); return err; } @@ -779,8 +779,7 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_struct *tty, .stack = stack }); if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt, - IRQF_SHARED | IRQF_SAMPLE_RANDOM, - "winch", winch) < 0) { + IRQF_SHARED, "winch", winch) < 0) { printk(KERN_ERR "register_winch_irq - failed to register " "IRQ\n"); goto out_free; diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 43b39d6..664a60e 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -774,8 +774,7 @@ static int __init mconsole_init(void) register_reboot_notifier(&reboot_notifier); err = um_request_irq(MCONSOLE_IRQ, sock, IRQ_READ, mconsole_interrupt, - IRQF_SHARED | IRQF_SAMPLE_RANDOM, - "mconsole", (void *)sock); + IRQF_SHARED, "mconsole", (void *)sock); if (err) { printk(KERN_ERR "Failed to get IRQ for management console\n"); goto out; diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c index 11866ff..1d83d50 100644 --- a/arch/um/drivers/port_kern.c +++ b/arch/um/drivers/port_kern.c @@ -100,8 +100,7 @@ static int port_accept(struct port_list *port) .port = port }); if (um_request_irq(TELNETD_IRQ, socket[0], IRQ_READ, pipe_interrupt, - IRQF_SHARED | IRQF_SAMPLE_RANDOM, - "telnetd", conn)) { + IRQF_SHARED, "telnetd", conn)) { printk(KERN_ERR "port_accept : failed to get IRQ for " "telnetd\n"); goto out_free; @@ -184,8 +183,7 @@ void *port_data(int port_num) } if (um_request_irq(ACCEPT_IRQ, fd, IRQ_READ, port_interrupt, - IRQF_SHARED | IRQF_SAMPLE_RANDOM, - "port", port)) { + IRQF_SHARED, "port", port)) { printk(KERN_ERR "Failed to get IRQ for port %d\n", port_num); goto out_close; } diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index b25296e..e32c6aa 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -131,8 +131,7 @@ static int __init rng_init (void) random_fd = err; err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt, - IRQF_SAMPLE_RANDOM, "random", - NULL); + 0, "random", NULL); if (err) goto err_out_cleanup_hw; diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c index b68bbe2..e3031e6 100644 --- a/arch/um/drivers/xterm_kern.c +++ b/arch/um/drivers/xterm_kern.c @@ -50,8 +50,7 @@ int xterm_fd(int socket, int *pid_out) init_completion(&data->ready); err = um_request_irq(XTERM_IRQ, socket, IRQ_READ, xterm_interrupt, - IRQF_SHARED | IRQF_SAMPLE_RANDOM, - "xterm", data); + IRQF_SHARED, "xterm", data); if (err) { printk(KERN_ERR "xterm_fd : failed to get IRQ for xterm, " "err = %d\n", err); diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index 2a16392..c882111 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -25,8 +25,7 @@ int write_sigio_irq(int fd) int err; err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt, - IRQF_SAMPLE_RANDOM, "write sigio", - NULL); + 0, "write sigio", NULL); if (err) { printk(KERN_ERR "write_sigio_irq : um_request_irq failed, " "err = %d\n", err); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index c78f14a..dab3935 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -234,7 +234,7 @@ extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); extern void perf_check_microcode(void); #else -static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) +static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { *nr = 0; return NULL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index a15df4b..821d53b 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -374,7 +374,7 @@ struct x86_pmu { /* * Intel DebugStore bits */ - int bts :1, + unsigned int bts :1, bts_active :1, pebs :1, pebs_active :1, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 7a8b9d0..3823669 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -138,6 +138,84 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +#define SNB_DMND_DATA_RD (1ULL << 0) +#define SNB_DMND_RFO (1ULL << 1) +#define SNB_DMND_IFETCH (1ULL << 2) +#define SNB_DMND_WB (1ULL << 3) +#define SNB_PF_DATA_RD (1ULL << 4) +#define SNB_PF_RFO (1ULL << 5) +#define SNB_PF_IFETCH (1ULL << 6) +#define SNB_LLC_DATA_RD (1ULL << 7) +#define SNB_LLC_RFO (1ULL << 8) +#define SNB_LLC_IFETCH (1ULL << 9) +#define SNB_BUS_LOCKS (1ULL << 10) +#define SNB_STRM_ST (1ULL << 11) +#define SNB_OTHER (1ULL << 15) +#define SNB_RESP_ANY (1ULL << 16) +#define SNB_NO_SUPP (1ULL << 17) +#define SNB_LLC_HITM (1ULL << 18) +#define SNB_LLC_HITE (1ULL << 19) +#define SNB_LLC_HITS (1ULL << 20) +#define SNB_LLC_HITF (1ULL << 21) +#define SNB_LOCAL (1ULL << 22) +#define SNB_REMOTE (0xffULL << 23) +#define SNB_SNP_NONE (1ULL << 31) +#define SNB_SNP_NOT_NEEDED (1ULL << 32) +#define SNB_SNP_MISS (1ULL << 33) +#define SNB_NO_FWD (1ULL << 34) +#define SNB_SNP_FWD (1ULL << 35) +#define SNB_HITM (1ULL << 36) +#define SNB_NON_DRAM (1ULL << 37) + +#define SNB_DMND_READ (SNB_DMND_DATA_RD|SNB_LLC_DATA_RD) +#define SNB_DMND_WRITE (SNB_DMND_RFO|SNB_LLC_RFO) +#define SNB_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) + +#define SNB_SNP_ANY (SNB_SNP_NONE|SNB_SNP_NOT_NEEDED| \ + SNB_SNP_MISS|SNB_NO_FWD|SNB_SNP_FWD| \ + SNB_HITM) + +#define SNB_DRAM_ANY (SNB_LOCAL|SNB_REMOTE|SNB_SNP_ANY) +#define SNB_DRAM_REMOTE (SNB_REMOTE|SNB_SNP_ANY) + +#define SNB_L3_ACCESS SNB_RESP_ANY +#define SNB_L3_MISS (SNB_DRAM_ANY|SNB_NON_DRAM) + +static __initconst const u64 snb_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS, + [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_L3_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS, + [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_L3_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS, + [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_L3_MISS, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_DRAM_ANY, + [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_DRAM_REMOTE, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_DRAM_ANY, + [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_DRAM_REMOTE, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_DRAM_ANY, + [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_DRAM_REMOTE, + }, + }, +}; + static __initconst const u64 snb_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -235,16 +313,16 @@ static __initconst const u64 snb_hw_cache_event_ids }, [ C(NODE) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, }, }, @@ -1964,6 +2042,8 @@ __init int intel_pmu_init(void) case 58: /* IvyBridge */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_snb(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 19faffc..7563fda 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -18,6 +18,7 @@ static struct event_constraint constraint_empty = EVENT_CONSTRAINT(0, 0, 0); DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -33,10 +34,81 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); -DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23"); -DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); + +static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + u64 count; + + rdmsrl(event->hw.event_base, count); + + return count; +} + +/* + * generic get constraint function for shared match/mask registers. + */ +static struct event_constraint * +uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + unsigned long flags; + bool ok = false; + + /* + * reg->alloc can be set due to existing state, so for fake box we + * need to ignore this, otherwise we might fail to allocate proper + * fake state for this extra reg constraint. + */ + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; + + er = &box->shared_regs[reg1->idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || + (er->config1 == reg1->config && er->config2 == reg2->config)) { + atomic_inc(&er->ref); + er->config1 = reg1->config; + er->config2 = reg2->config; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (ok) { + if (!uncore_box_is_fake(box)) + reg1->alloc = 1; + return NULL; + } + + return &constraint_empty; +} + +static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + + /* + * Only put constraint if extra reg was actually allocated. Also + * takes care of event which do not use an extra shared reg. + * + * Also, if this is a fake box we shouldn't touch any event state + * (reg->alloc) and we don't care about leaving inconsistent box + * state either since it will be thrown out. + */ + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + er = &box->shared_regs[reg1->idx]; + atomic_dec(&er->ref); + reg1->alloc = 0; +} /* Sandy Bridge-EP uncore support */ static struct intel_uncore_type snbep_uncore_cbox; @@ -64,18 +136,15 @@ static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) pci_write_config_dword(pdev, box_ctl, config); } -static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; - pci_write_config_dword(pdev, hwc->config_base, hwc->config | - SNBEP_PMON_CTL_EN); + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); } -static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; @@ -83,8 +152,7 @@ static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, pci_write_config_dword(pdev, hwc->config_base, hwc->config); } -static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, - struct perf_event *event) +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; @@ -92,14 +160,15 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + return count; } static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, - SNBEP_PMON_BOX_CTL_INT); + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -112,7 +181,6 @@ static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) rdmsrl(msr, config); config |= SNBEP_PMON_BOX_CTL_FRZ; wrmsrl(msr, config); - return; } } @@ -126,12 +194,10 @@ static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) rdmsrl(msr, config); config &= ~SNBEP_PMON_BOX_CTL_FRZ; wrmsrl(msr, config); - return; } } -static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -150,68 +216,15 @@ static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, wrmsrl(hwc->config_base, hwc->config); } -static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - u64 count; - - rdmsrl(hwc->event_base, count); - return count; -} - static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) { unsigned msr = uncore_msr_box_ctl(box); + if (msr) wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); } -static struct event_constraint * -snbep_uncore_get_constraint(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct intel_uncore_extra_reg *er; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - unsigned long flags; - bool ok = false; - - if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc)) - return NULL; - - er = &box->shared_regs[reg1->idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (!atomic_read(&er->ref) || er->config1 == reg1->config) { - atomic_inc(&er->ref); - er->config1 = reg1->config; - ok = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (ok) { - if (box->phys_id >= 0) - reg1->alloc = 1; - return NULL; - } - return &constraint_empty; -} - -static void snbep_uncore_put_constraint(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct intel_uncore_extra_reg *er; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - - if (box->phys_id < 0 || !reg1->alloc) - return; - - er = &box->shared_regs[reg1->idx]; - atomic_dec(&er->ref); - reg1->alloc = 0; -} - -static int snbep_uncore_hw_config(struct intel_uncore_box *box, - struct perf_event *event) +static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -221,14 +234,16 @@ static int snbep_uncore_hw_config(struct intel_uncore_box *box, SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; reg1->config = event->attr.config1 & SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK; - } else if (box->pmu->type == &snbep_uncore_pcu) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->config = event->attr.config1 & - SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; } else { - return 0; + if (box->pmu->type == &snbep_uncore_pcu) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; + } else { + return 0; + } } reg1->idx = 0; + return 0; } @@ -272,10 +287,19 @@ static struct attribute *snbep_uncore_pcu_formats_attr[] = { &format_attr_thresh5.attr, &format_attr_occ_invert.attr, &format_attr_occ_edge.attr, - &format_attr_filter_brand0.attr, - &format_attr_filter_brand1.attr, - &format_attr_filter_brand2.attr, - &format_attr_filter_brand3.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *snbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, NULL, }; @@ -314,15 +338,20 @@ static struct attribute_group snbep_uncore_pcu_format_group = { .attrs = snbep_uncore_pcu_formats_attr, }; +static struct attribute_group snbep_uncore_qpi_format_group = { + .name = "format", + .attrs = snbep_uncore_qpi_formats_attr, +}; + static struct intel_uncore_ops snbep_uncore_msr_ops = { .init_box = snbep_uncore_msr_init_box, .disable_box = snbep_uncore_msr_disable_box, .enable_box = snbep_uncore_msr_enable_box, .disable_event = snbep_uncore_msr_disable_event, .enable_event = snbep_uncore_msr_enable_event, - .read_counter = snbep_uncore_msr_read_counter, - .get_constraint = snbep_uncore_get_constraint, - .put_constraint = snbep_uncore_put_constraint, + .read_counter = uncore_msr_read_counter, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, .hw_config = snbep_uncore_hw_config, }; @@ -485,8 +514,13 @@ static struct intel_uncore_type snbep_uncore_qpi = { .num_counters = 4, .num_boxes = 2, .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, .event_descs = snbep_uncore_qpi_events, - SNBEP_UNCORE_PCI_COMMON_INIT(), + .format_group = &snbep_uncore_qpi_format_group, }; @@ -603,10 +637,8 @@ static void snbep_pci2phy_map_init(void) } /* end of Sandy Bridge-EP uncore support */ - /* Sandy Bridge uncore support */ -static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -616,20 +648,11 @@ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); } -static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) { wrmsrl(event->hw.config_base, 0); } -static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box, - struct perf_event *event) -{ - u64 count; - rdmsrl(event->hw.event_base, count); - return count; -} - static void snb_uncore_msr_init_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) { @@ -648,15 +671,15 @@ static struct attribute *snb_uncore_formats_attr[] = { }; static struct attribute_group snb_uncore_format_group = { - .name = "format", - .attrs = snb_uncore_formats_attr, + .name = "format", + .attrs = snb_uncore_formats_attr, }; static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, - .read_counter = snb_uncore_msr_read_counter, + .read_counter = uncore_msr_read_counter, }; static struct event_constraint snb_uncore_cbox_constraints[] = { @@ -697,12 +720,10 @@ static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) { - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, - NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); } -static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -744,7 +765,7 @@ static struct intel_uncore_ops nhm_uncore_msr_ops = { .enable_box = nhm_uncore_msr_enable_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = nhm_uncore_msr_enable_event, - .read_counter = snb_uncore_msr_read_counter, + .read_counter = uncore_msr_read_counter, }; static struct intel_uncore_type nhm_uncore = { @@ -769,8 +790,1041 @@ static struct intel_uncore_type *nhm_msr_uncores[] = { }; /* end of Nehalem uncore support */ -static void uncore_assign_hw_event(struct intel_uncore_box *box, - struct perf_event *event, int idx) +/* Nehalem-EX uncore support */ +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); +DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); +DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63"); +DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); + +static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); +} + +static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config &= ~((1ULL << uncore_num_counters(box)) - 1); + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config |= (1ULL << uncore_num_counters(box)) - 1; + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx >= UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); + else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); + else + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +#define NHMEX_UNCORE_OPS_COMMON_INIT() \ + .init_box = nhmex_uncore_msr_init_box, \ + .disable_box = nhmex_uncore_msr_disable_box, \ + .enable_box = nhmex_uncore_msr_enable_box, \ + .disable_event = nhmex_uncore_msr_disable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops nhmex_uncore_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_uncore_msr_enable_event, +}; + +static struct attribute *nhmex_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_edge.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_ubox_format_group = { + .name = "format", + .attrs = nhmex_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type nhmex_uncore_ubox = { + .name = "ubox", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, + .perf_ctr = NHMEX_U_MSR_PMON_CTR, + .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_ubox_format_group +}; + +static struct attribute *nhmex_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_cbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_cbox_formats_attr, +}; + +static struct intel_uncore_type nhmex_uncore_cbox = { + .name = "cbox", + .num_counters = 6, + .num_boxes = 8, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, + .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_C_MSR_OFFSET, + .pair_ctr_ctl = 1, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static struct uncore_event_desc nhmex_uncore_wbox_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type nhmex_uncore_wbox = { + .name = "wbox", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_W_MSR_PMON_CNT0, + .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, + .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, + .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, + .pair_ctr_ctl = 1, + .event_descs = nhmex_uncore_wbox_events, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int ctr, ev_sel; + + ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> + NHMEX_B_PMON_CTR_SHIFT; + ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> + NHMEX_B_PMON_CTL_EV_SEL_SHIFT; + + /* events that do not use the match/mask registers */ + if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || + (ctr == 2 && ev_sel != 0x4) || ctr == 3) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_B0_MSR_MATCH; + else + reg1->reg = NHMEX_B1_MSR_MATCH; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg + 1, reg2->config); + } + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); +} + +/* + * The Bbox has 4 counters, but each counter monitors different events. + * Use bits 6-7 in the event config to select counter. + */ +static struct event_constraint nhmex_uncore_bbox_constraints[] = { + EVENT_CONSTRAINT(0 , 1, 0xc0), + EVENT_CONSTRAINT(0x40, 2, 0xc0), + EVENT_CONSTRAINT(0x80, 4, 0xc0), + EVENT_CONSTRAINT(0xc0, 8, 0xc0), + EVENT_CONSTRAINT_END, +}; + +static struct attribute *nhmex_uncore_bbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_counter.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_bbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_bbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_bbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_bbox_msr_enable_event, + .hw_config = nhmex_bbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_bbox = { + .name = "bbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_B0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, + .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_B_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .constraints = nhmex_uncore_bbox_constraints, + .ops = &nhmex_uncore_bbox_ops, + .format_group = &nhmex_uncore_bbox_format_group +}; + +static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + + if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) { + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + } else { + reg1->config = ~0ULL; + reg2->config = ~0ULL; + } + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_S0_MSR_MM_CFG; + else + reg1->reg = NHMEX_S1_MSR_MM_CFG; + + reg1->idx = 0; + + return 0; +} + +static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + wrmsrl(reg1->reg, 0); + if (reg1->config != ~0ULL || reg2->config != ~0ULL) { + wrmsrl(reg1->reg + 1, reg1->config); + wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); + } + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); +} + +static struct attribute *nhmex_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_mm_cfg.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_sbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_sbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_sbox_msr_enable_event, + .hw_config = nhmex_sbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_S0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_S_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .ops = &nhmex_uncore_sbox_ops, + .format_group = &nhmex_uncore_sbox_format_group +}; + +enum { + EXTRA_REG_NHMEX_M_FILTER, + EXTRA_REG_NHMEX_M_DSP, + EXTRA_REG_NHMEX_M_ISS, + EXTRA_REG_NHMEX_M_MAP, + EXTRA_REG_NHMEX_M_MSC_THR, + EXTRA_REG_NHMEX_M_PGT, + EXTRA_REG_NHMEX_M_PLD, + EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, +}; + +static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { + MBOX_INC_SEL_EXTAR_REG(0x0, DSP), + MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x9, ISS), + /* event 0xa uses two extra registers */ + MBOX_INC_SEL_EXTAR_REG(0xa, ISS), + MBOX_INC_SEL_EXTAR_REG(0xa, PLD), + MBOX_INC_SEL_EXTAR_REG(0xb, PLD), + /* events 0xd ~ 0x10 use the same extra register */ + MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x16, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), + EVENT_EXTRA_END +}; + +static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + bool ret = false; + u64 mask; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config == config) { + atomic_inc(&er->ref); + er->config = config; + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; + } + /* + * The ZDP_CTL_FVC MSR has 4 fields which are used to control + * events 0xd ~ 0x10. Besides these 4 fields, there are additional + * fields which are shared. + */ + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (WARN_ON_ONCE(idx >= 4)) + return false; + + /* mask of the shared fields */ + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + + raw_spin_lock_irqsave(&er->lock, flags); + /* add mask of the non-shared field if it's in use */ + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + + if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + er->config &= ~mask; + er->config |= (config & mask); + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; +} + +static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + atomic_dec(&er->ref); + return; + } + + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + atomic_sub(1 << (idx * 8), &er->ref); +} + +u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 config = reg1->config; + + /* get the non-shared control bits and shift them */ + idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (new_idx > orig_idx) { + idx = new_idx - orig_idx; + config <<= 3 * idx; + } else { + idx = orig_idx - new_idx; + config >>= 3 * idx; + } + + /* add the shared control bits back */ + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + if (modify) { + /* adjust the main event selector */ + if (new_idx > orig_idx) + hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + else + hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + reg1->config = config; + reg1->idx = ~0xff | new_idx; + } + return config; +} + +static struct event_constraint * +nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int i, idx[2], alloc = 0; + u64 config1 = reg1->config; + + idx[0] = __BITS_VALUE(reg1->idx, 0, 8); + idx[1] = __BITS_VALUE(reg1->idx, 1, 8); +again: + for (i = 0; i < 2; i++) { + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + idx[i] = 0xff; + + if (idx[i] == 0xff) + continue; + + if (!nhmex_mbox_get_shared_reg(box, idx[i], + __BITS_VALUE(config1, i, 32))) + goto fail; + alloc |= (0x1 << i); + } + + /* for the match/mask registers */ + if ((uncore_box_is_fake(box) || !reg2->alloc) && + !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) + goto fail; + + /* + * If it's a fake box -- as per validate_{group,event}() we + * shouldn't touch event state and we can avoid doing so + * since both will only call get_event_constraints() once + * on each event, this avoids the need for reg->alloc. + */ + if (!uncore_box_is_fake(box)) { + if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) + nhmex_mbox_alter_er(event, idx[0], true); + reg1->alloc |= alloc; + reg2->alloc = 1; + } + return NULL; +fail: + if (idx[0] != 0xff && !(alloc & 0x1) && + idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + /* + * events 0xd ~ 0x10 are functional identical, but are + * controlled by different fields in the ZDP_CTL_FVC + * register. If we failed to take one field, try the + * rest 3 choices. + */ + BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); + idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + idx[0] = (idx[0] + 1) % 4; + idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { + config1 = nhmex_mbox_alter_er(event, idx[0], false); + goto again; + } + } + + if (alloc & 0x1) + nhmex_mbox_put_shared_reg(box, idx[0]); + if (alloc & 0x2) + nhmex_mbox_put_shared_reg(box, idx[1]); + return &constraint_empty; +} + +static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + + if (uncore_box_is_fake(box)) + return; + + if (reg1->alloc & 0x1) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); + if (reg1->alloc & 0x2) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); + reg1->alloc = 0; + + if (reg2->alloc) { + nhmex_mbox_put_shared_reg(box, reg2->idx); + reg2->alloc = 0; + } +} + +static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) +{ + if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return er->idx; + return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; +} + +static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct extra_reg *er; + unsigned msr; + int reg_idx = 0; + + if (WARN_ON_ONCE(reg1->idx != -1)) + return -EINVAL; + /* + * The mbox events may require 2 extra MSRs at the most. But only + * the lower 32 bits in these MSRs are significant, so we can use + * config1 to pass two MSRs' config. + */ + for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) || + er->idx == __BITS_VALUE(reg1->idx, 1, 8)) + continue; + if (WARN_ON_ONCE(reg_idx >= 2)) + return -EINVAL; + + msr = er->msr + type->msr_offset * box->pmu->pmu_idx; + if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) + return -EINVAL; + + /* always use the 32~63 bits to pass the PLD config */ + if (er->idx == EXTRA_REG_NHMEX_M_PLD) + reg_idx = 1; + + reg1->idx &= ~(0xff << (reg_idx * 8)); + reg1->reg &= ~(0xffff << (reg_idx * 16)); + reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); + reg1->reg |= msr << (reg_idx * 16); + reg1->config = event->attr.config1; + reg_idx++; + } + /* use config2 to pass the filter config */ + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + + return 0; +} + +static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return box->shared_regs[idx].config; + + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + return config; +} + +static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx; + + idx = __BITS_VALUE(reg1->idx, 0, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), + nhmex_mbox_shared_reg_config(box, idx)); + idx = __BITS_VALUE(reg1->idx, 1, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), + nhmex_mbox_shared_reg_config(box, idx)); + + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } + + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg, filter_cfg, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); + +static struct attribute *nhmex_uncore_mbox_formats_attr[] = { + &format_attr_count_mode.attr, + &format_attr_storage_mode.attr, + &format_attr_wrap_mode.attr, + &format_attr_flag_mode.attr, + &format_attr_inc_sel.attr, + &format_attr_set_flag_sel.attr, + &format_attr_filter_cfg.attr, + &format_attr_filter_match.attr, + &format_attr_filter_mask.attr, + &format_attr_dsp.attr, + &format_attr_thr.attr, + &format_attr_fvc.attr, + &format_attr_pgt.attr, + &format_attr_map.attr, + &format_attr_iss.attr, + &format_attr_pld.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_mbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_mbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_mbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_mbox_msr_enable_event, + .hw_config = nhmex_mbox_hw_config, + .get_constraint = nhmex_mbox_get_constraint, + .put_constraint = nhmex_mbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_mbox = { + .name = "mbox", + .num_counters = 6, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_M0_MSR_PMU_CTL0, + .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, + .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_M_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 8, + .event_descs = nhmex_uncore_mbox_events, + .ops = &nhmex_uncore_mbox_ops, + .format_group = &nhmex_uncore_mbox_format_group, +}; + +void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int port; + + /* adjust the main event selector */ + if (reg1->idx % 2) { + reg1->idx--; + hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } else { + reg1->idx++; + hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } + + /* adjust address or config of extra register */ + port = reg1->idx / 6 + box->pmu->pmu_idx * 4; + switch (reg1->idx % 6) { + case 0: + reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); + break; + case 1: + reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); + break; + case 2: + /* the 8~15 bits to the 0~7 bits */ + reg1->config >>= 8; + break; + case 3: + /* the 0~7 bits to the 8~15 bits */ + reg1->config <<= 8; + break; + case 4: + reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); + break; + case 5: + reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); + break; + }; +} + +/* + * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. + * An event set consists of 6 events, the 3rd and 4th events in + * an event set use the same extra register. So an event set uses + * 5 extra registers. + */ +static struct event_constraint * +nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + struct intel_uncore_extra_reg *er; + unsigned long flags; + int idx, er_idx; + u64 config1; + bool ok = false; + + if (!uncore_box_is_fake(box) && reg1->alloc) + return NULL; + + idx = reg1->idx % 6; + config1 = reg1->config; +again: + er_idx = idx; + /* the 3rd and 4th events use the same extra register */ + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (idx < 2) { + if (!atomic_read(&er->ref) || er->config == reg1->config) { + atomic_inc(&er->ref); + er->config = reg1->config; + ok = true; + } + } else if (idx == 2 || idx == 3) { + /* + * these two events use different fields in a extra register, + * the 0~7 bits and the 8~15 bits respectively. + */ + u64 mask = 0xff << ((idx - 2) * 8); + if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || + !((er->config ^ config1) & mask)) { + atomic_add(1 << ((idx - 2) * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + } else { + if (!atomic_read(&er->ref) || + (er->config == (hwc->config >> 32) && + er->config1 == reg1->config && + er->config2 == reg2->config)) { + atomic_inc(&er->ref); + er->config = (hwc->config >> 32); + er->config1 = reg1->config; + er->config2 = reg2->config; + ok = true; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + /* + * The Rbox events are always in pairs. The paired + * events are functional identical, but use different + * extra registers. If we failed to take an extra + * register, try the alternative. + */ + if (idx % 2) + idx--; + else + idx++; + if (idx != reg1->idx % 6) { + if (idx == 2) + config1 >>= 8; + else if (idx == 3) + config1 <<= 8; + goto again; + } + } else { + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx % 6) + nhmex_rbox_alter_er(box, event); + reg1->alloc = 1; + } + return NULL; + } + return &constraint_empty; +} + +static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + int idx, er_idx; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + idx = reg1->idx % 6; + er_idx = idx; + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + if (idx == 2 || idx == 3) + atomic_sub(1 << ((idx - 2) * 8), &er->ref); + else + atomic_dec(&er->ref); + + reg1->alloc = 0; +} + +static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int port, idx; + + idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> + NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + if (idx >= 0x18) + return -EINVAL; + + reg1->idx = idx; + reg1->config = event->attr.config1; + + port = idx / 6 + box->pmu->pmu_idx * 4; + idx %= 6; + switch (idx) { + case 0: + reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); + break; + case 1: + reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); + break; + case 2: + case 3: + reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port); + break; + case 4: + case 5: + if (idx == 4) + reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); + else + reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); + reg2->config = event->attr.config2; + hwc->config |= event->attr.config & (~0ULL << 32); + break; + }; + return 0; +} + +static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + er = &box->shared_regs[idx]; + + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + + return config; +} + +static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx, er_idx; + + idx = reg1->idx % 6; + er_idx = idx; + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + switch (idx) { + case 0: + case 1: + wrmsrl(reg1->reg, reg1->config); + break; + case 2: + case 3: + wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx)); + break; + case 4: + case 5: + wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg + 1, hwc->config >> 32); + wrmsrl(reg1->reg + 2, reg2->config); + break; + }; + + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); +} + +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); +DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); + +static struct attribute *nhmex_uncore_rbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_xbr_mm_cfg.attr, + &format_attr_xbr_match.attr, + &format_attr_xbr_mask.attr, + &format_attr_qlx_cfg.attr, + &format_attr_iperf_cfg.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_rbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_rbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_rbox_events[] = { + INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), + INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_rbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_rbox_msr_enable_event, + .hw_config = nhmex_rbox_hw_config, + .get_constraint = nhmex_rbox_get_constraint, + .put_constraint = nhmex_rbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_rbox = { + .name = "rbox", + .num_counters = 8, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_R_MSR_PMON_CTL0, + .perf_ctr = NHMEX_R_MSR_PMON_CNT0, + .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_R_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 20, + .event_descs = nhmex_uncore_rbox_events, + .ops = &nhmex_uncore_rbox_ops, + .format_group = &nhmex_uncore_rbox_format_group +}; + +static struct intel_uncore_type *nhmex_msr_uncores[] = { + &nhmex_uncore_ubox, + &nhmex_uncore_cbox, + &nhmex_uncore_bbox, + &nhmex_uncore_sbox, + &nhmex_uncore_mbox, + &nhmex_uncore_rbox, + &nhmex_uncore_wbox, + NULL, +}; +/* end of Nehalem-EX uncore support */ + +static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -787,8 +1841,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, hwc->event_base = uncore_perf_ctr(box, hwc->idx); } -static void uncore_perf_event_update(struct intel_uncore_box *box, - struct perf_event *event) +static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) { u64 prev_count, new_count, delta; int shift; @@ -858,14 +1911,12 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, - int cpu) +struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) { struct intel_uncore_box *box; int i, size; - size = sizeof(*box) + type->num_shared_regs * - sizeof(struct intel_uncore_extra_reg); + size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); if (!box) @@ -915,12 +1966,11 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) * perf core schedules event on the basis of cpu, uncore events are * collected by one of the cpus inside a physical package. */ - return uncore_pmu_to_box(uncore_event_to_pmu(event), - smp_processor_id()); + return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } -static int uncore_collect_events(struct intel_uncore_box *box, - struct perf_event *leader, bool dogrp) +static int +uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { struct perf_event *event; int n, max_count; @@ -952,8 +2002,7 @@ static int uncore_collect_events(struct intel_uncore_box *box, } static struct event_constraint * -uncore_get_event_constraint(struct intel_uncore_box *box, - struct perf_event *event) +uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_type *type = box->pmu->type; struct event_constraint *c; @@ -977,15 +2026,13 @@ uncore_get_event_constraint(struct intel_uncore_box *box, return &type->unconstrainted; } -static void uncore_put_event_constraint(struct intel_uncore_box *box, - struct perf_event *event) +static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event) { if (box->pmu->type->ops->put_constraint) box->pmu->type->ops->put_constraint(box, event); } -static int uncore_assign_events(struct intel_uncore_box *box, - int assign[], int n) +static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n) { unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX]; @@ -1407,8 +2454,7 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int __devinit uncore_pci_add(struct intel_uncore_type *type, - struct pci_dev *pdev) +static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; @@ -1485,6 +2531,7 @@ static int __devinit uncore_pci_probe(struct pci_dev *pdev, struct intel_uncore_type *type; type = (struct intel_uncore_type *)id->driver_data; + return uncore_pci_add(type, pdev); } @@ -1612,8 +2659,8 @@ static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) return 0; } -static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores, - int old_cpu, int new_cpu) +static void __cpuinit +uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu) { struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; @@ -1694,8 +2741,8 @@ static void __cpuinit uncore_event_init_cpu(int cpu) uncore_change_context(pci_uncores, -1, cpu); } -static int __cpuinit uncore_cpu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) +static int + __cpuinit uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; @@ -1732,12 +2779,12 @@ static int __cpuinit uncore_cpu_notifier(struct notifier_block *self, } static struct notifier_block uncore_cpu_nb __cpuinitdata = { - .notifier_call = uncore_cpu_notifier, + .notifier_call = uncore_cpu_notifier, /* * to migrate uncore events, our notifier should be executed * before perf core's notifier. */ - .priority = CPU_PRI_PERF + 1, + .priority = CPU_PRI_PERF + 1, }; static void __init uncore_cpu_setup(void *dummy) @@ -1767,6 +2814,9 @@ static int __init uncore_cpu_init(void) snbep_uncore_cbox.num_boxes = max_cores; msr_uncores = snbep_msr_uncores; break; + case 46: + msr_uncores = nhmex_msr_uncores; + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index b13e9ea..f385189 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -5,8 +5,6 @@ #include "perf_event.h" #define UNCORE_PMU_NAME_LEN 32 -#define UNCORE_BOX_HASH_SIZE 8 - #define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff @@ -115,6 +113,10 @@ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + /* SNB-EP pci control register */ #define SNBEP_PCI_PMON_BOX_CTL 0xf4 #define SNBEP_PCI_PMON_CTL0 0xd8 @@ -158,6 +160,193 @@ #define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc #define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd +/* NHM-EX event control */ +#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff +#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 +#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) +#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) +#define NHMEX_PMON_CTL_PMI_EN (1 << 20) +#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) +#define NHMEX_PMON_CTL_INVERT (1 << 23) +#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 +#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_UMASK_MASK | \ + NHMEX_PMON_CTL_EDGE_DET | \ + NHMEX_PMON_CTL_INVERT | \ + NHMEX_PMON_CTL_TRESH_MASK) + +/* NHM-EX Ubox */ +#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define NHMEX_U_MSR_PMON_CTR 0xc11 +#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 + +#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) +#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e +#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) +#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) +#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) + +#define NHMEX_U_PMON_RAW_EVENT_MASK \ + (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_EDGE_DET) + +/* NHM-EX Cbox */ +#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 +#define NHMEX_C0_MSR_PMON_CTR0 0xd11 +#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 +#define NHMEX_C_MSR_OFFSET 0x20 + +/* NHM-EX Bbox */ +#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 +#define NHMEX_B0_MSR_PMON_CTR0 0xc31 +#define NHMEX_B0_MSR_PMON_CTL0 0xc30 +#define NHMEX_B_MSR_OFFSET 0x40 +#define NHMEX_B0_MSR_MATCH 0xe45 +#define NHMEX_B0_MSR_MASK 0xe46 +#define NHMEX_B1_MSR_MATCH 0xe4d +#define NHMEX_B1_MSR_MASK 0xe4e + +#define NHMEX_B_PMON_CTL_EN (1 << 0) +#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_B_PMON_CTR_SHIFT 6 +#define NHMEX_B_PMON_CTR_MASK \ + (0x3 << NHMEX_B_PMON_CTR_SHIFT) +#define NHMEX_B_PMON_RAW_EVENT_MASK \ + (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ + NHMEX_B_PMON_CTR_MASK) + +/* NHM-EX Sbox */ +#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 +#define NHMEX_S0_MSR_PMON_CTR0 0xc51 +#define NHMEX_S0_MSR_PMON_CTL0 0xc50 +#define NHMEX_S_MSR_OFFSET 0x80 +#define NHMEX_S0_MSR_MM_CFG 0xe48 +#define NHMEX_S0_MSR_MATCH 0xe49 +#define NHMEX_S0_MSR_MASK 0xe4a +#define NHMEX_S1_MSR_MM_CFG 0xe58 +#define NHMEX_S1_MSR_MATCH 0xe59 +#define NHMEX_S1_MSR_MASK 0xe5a + +#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) + +/* NHM-EX Mbox */ +#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 +#define NHMEX_M0_MSR_PMU_DSP 0xca5 +#define NHMEX_M0_MSR_PMU_ISS 0xca6 +#define NHMEX_M0_MSR_PMU_MAP 0xca7 +#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 +#define NHMEX_M0_MSR_PMU_PGT 0xca9 +#define NHMEX_M0_MSR_PMU_PLD 0xcaa +#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab +#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 +#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 +#define NHMEX_M_MSR_OFFSET 0x40 +#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 +#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c + +#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) +#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL +#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL +#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 + +#define NHMEX_M_PMON_CTL_EN (1 << 0) +#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) +#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 +#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 +#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) +#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) +#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 +#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ + (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ + (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) +#define NHMEX_M_PMON_RAW_EVENT_MASK \ + (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ + NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ + NHMEX_M_PMON_CTL_WRAP_MODE | \ + NHMEX_M_PMON_CTL_FLAG_MODE | \ + NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) + + +#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK 0x1f +#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK (0x7 << 5) +#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK (0x7 << 8) +#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR (1 << 23) +#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK \ + (NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK | \ + NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK | \ + NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK | \ + NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR) +#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n))) + +/* + * use the 9~13 bits to select event If the 7th bit is not set, + * otherwise use the 19~21 bits to select event. + */ +#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_EXTAR_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) +#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_SET_FLAG_SEL_MASK, \ + (u64)-1, NHMEX_M_##r) + +/* NHM-EX Rbox */ +#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 +#define NHMEX_R_MSR_PMON_CTL0 0xe10 +#define NHMEX_R_MSR_PMON_CNT0 0xe11 +#define NHMEX_R_MSR_OFFSET 0x20 + +#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ + ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) +#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ + (((n) < 4 ? 0 : 0x10) + (n) * 4) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ + (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ + (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) + +#define NHMEX_R_PMON_CTL_EN (1 << 0) +#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) +#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK + +/* NHM-EX Wbox */ +#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 +#define NHMEX_W_MSR_PMON_CNT0 0xc90 +#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 +#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 +#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 + +#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) + struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -178,6 +367,7 @@ struct intel_uncore_type { unsigned msr_offset; unsigned num_shared_regs:8; unsigned single_fixed:1; + unsigned pair_ctr_ctl:1; struct event_constraint unconstrainted; struct event_constraint *constraints; struct intel_uncore_pmu *pmus; @@ -213,7 +403,7 @@ struct intel_uncore_pmu { struct intel_uncore_extra_reg { raw_spinlock_t lock; - u64 config1; + u64 config, config1, config2; atomic_t ref; }; @@ -323,14 +513,16 @@ unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) static inline unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) { - return idx + box->pmu->type->event_ctl + + return box->pmu->type->event_ctl + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + box->pmu->type->msr_offset * box->pmu->pmu_idx; } static inline unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) { - return idx + box->pmu->type->perf_ctr + + return box->pmu->type->perf_ctr + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + box->pmu->type->msr_offset * box->pmu->pmu_idx; } @@ -422,3 +614,8 @@ static inline void uncore_box_init(struct intel_uncore_box *box) box->pmu->type->ops->init_box(box); } } + +static inline bool uncore_box_is_fake(struct intel_uncore_box *box) +{ + return (box->phys_id < 0); +} |