diff options
Diffstat (limited to 'arch/x86')
112 files changed, 3983 insertions, 7482 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index da34972..fc76e42 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -20,6 +20,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT @@ -70,6 +71,7 @@ config X86 select IRQ_FORCED_THREADING select USE_GENERIC_SMP_HELPERS if SMP select HAVE_BPF_JIT if (X86_64 && NET) + select CLKEVT_I8253 config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) @@ -680,33 +682,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT Calgary anyway, pass 'iommu=calgary' on the kernel command line. If unsure, say Y. -config AMD_IOMMU - bool "AMD IOMMU support" - select SWIOTLB - select PCI_MSI - select PCI_IOV - depends on X86_64 && PCI && ACPI - ---help--- - With this option you can enable support for AMD IOMMU hardware in - your system. An IOMMU is a hardware component which provides - remapping of DMA memory accesses from devices. With an AMD IOMMU you - can isolate the the DMA memory of different devices and protect the - system from misbehaving device drivers or hardware. - - You can find out if your system has an AMD IOMMU if you look into - your BIOS for an option to enable it or if you have an IVRS ACPI - table. - -config AMD_IOMMU_STATS - bool "Export AMD IOMMU statistics to debugfs" - depends on AMD_IOMMU - select DEBUG_FS - ---help--- - This option enables code in the AMD IOMMU driver to collect various - statistics about whats happening in the driver and exports that - information to userspace via debugfs. - If unsure, say N. - # need this always selected by IOMMU for the VIA workaround config SWIOTLB def_bool y if X86_64 @@ -720,9 +695,6 @@ config SWIOTLB config IOMMU_HELPER def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) -config IOMMU_API - def_bool (AMD_IOMMU || DMAR) - config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL @@ -1170,7 +1142,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" config AMD_NUMA def_bool y prompt "Old style AMD Opteron NUMA detection" - depends on NUMA && PCI + depends on X86_64 && NUMA && PCI ---help--- Enable AMD NUMA node topology detection. You should say Y here if you have a multi processor AMD system. This uses an old method to @@ -1942,55 +1914,6 @@ config PCI_CNB20LE_QUIRK You should say N unless you know you need this. -config DMAR - bool "Support for DMA Remapping Devices (EXPERIMENTAL)" - depends on PCI_MSI && ACPI && EXPERIMENTAL - help - DMA remapping (DMAR) devices support enables independent address - translations for Direct Memory Access (DMA) from devices. - These DMA remapping devices are reported via ACPI tables - and include PCI device scope covered by these DMA - remapping devices. - -config DMAR_DEFAULT_ON - def_bool y - prompt "Enable DMA Remapping Devices by default" - depends on DMAR - help - Selecting this option will enable a DMAR device at boot time if - one is found. If this option is not selected, DMAR support can - be enabled by passing intel_iommu=on to the kernel. It is - recommended you say N here while the DMAR code remains - experimental. - -config DMAR_BROKEN_GFX_WA - bool "Workaround broken graphics drivers (going away soon)" - depends on DMAR && BROKEN - ---help--- - Current Graphics drivers tend to use physical address - for DMA and avoid using DMA APIs. Setting this config - option permits the IOMMU driver to set a unity map for - all the OS-visible memory. Hence the driver can continue - to use physical addresses for DMA, at least until this - option is removed in the 2.6.32 kernel. - -config DMAR_FLOPPY_WA - def_bool y - depends on DMAR - ---help--- - Floppy disk drivers are known to bypass DMA API calls - thereby failing to work when IOMMU is enabled. This - workaround will setup a 1:1 mapping for the first - 16MiB to make floppy (an ISA device) work. - -config INTR_REMAP - bool "Support for Interrupt Remapping (EXPERIMENTAL)" - depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL - ---help--- - Supports Interrupt remapping for IO-APIC and MSI devices. - To use x2apic mode in the CPU's which support x2APIC enhancements or - to support platforms with CPU's having > 8 bit APIC ID, say Y. - source "drivers/pci/pcie/Kconfig" source "drivers/pci/Kconfig" diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 95f5826..a0e866d 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -143,7 +143,7 @@ ENTRY(ia32_sysenter_target) CFI_REL_OFFSET rip,0 pushq_cfi %rax cld - SAVE_ARGS 0,0,1 + SAVE_ARGS 0,1,0 /* no need to do an access_ok check here because rbp has been 32bit zero extended */ 1: movl (%rbp),%ebp @@ -173,7 +173,7 @@ sysexit_from_sys_call: andl $~0x200,EFLAGS-R11(%rsp) movl RIP-R11(%rsp),%edx /* User %eip */ CFI_REGISTER rip,rdx - RESTORE_ARGS 1,24,1,1,1,1 + RESTORE_ARGS 0,24,0,0,0,0 xorq %r8,%r8 xorq %r9,%r9 xorq %r10,%r10 @@ -289,7 +289,7 @@ ENTRY(ia32_cstar_target) * disabled irqs and here we enable it straight after entry: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,1,1 + SAVE_ARGS 8,0,0 movl %eax,%eax /* zero extension */ movq %rax,ORIG_RAX-ARGOFFSET(%rsp) movq %rcx,RIP-ARGOFFSET(%rsp) @@ -328,7 +328,7 @@ cstar_dispatch: jnz sysretl_audit sysretl_from_sys_call: andl $~TS_COMPAT,TI_status(%r10) - RESTORE_ARGS 1,-ARG_SKIP,1,1,1 + RESTORE_ARGS 0,-ARG_SKIP,0,0,0 movl RIP-ARGOFFSET(%rsp),%ecx CFI_REGISTER rip,rcx movl EFLAGS-ARGOFFSET(%rsp),%r11d @@ -419,7 +419,7 @@ ENTRY(ia32_syscall) cld /* note the registers are not zero extended to the sf. this could be a problem. */ - SAVE_ARGS 0,0,1 + SAVE_ARGS 0,1,0 GET_THREAD_INFO(%r10) orl $TS_COMPAT,TI_status(%r10) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10) @@ -849,4 +849,5 @@ ia32_sys_call_table: .quad compat_sys_clock_adjtime .quad sys_syncfs .quad compat_sys_sendmmsg /* 345 */ + .quad sys_setns ia32_syscall_end: diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 416d865..610001d 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -139,7 +139,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) boot_cpu_data.x86_model <= 0x05 && boot_cpu_data.x86_mask < 0x0A) return 1; - else if (c1e_detected) + else if (amd_e400_c1e_detected) return 1; else return max_cstate; diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h deleted file mode 100644 index a6863a2..0000000 --- a/arch/x86/include/asm/amd_iommu.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. - * Author: Joerg Roedel <joerg.roedel@amd.com> - * Leo Duran <leo.duran@amd.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _ASM_X86_AMD_IOMMU_H -#define _ASM_X86_AMD_IOMMU_H - -#include <linux/irqreturn.h> - -#ifdef CONFIG_AMD_IOMMU - -extern int amd_iommu_detect(void); - -#else - -static inline int amd_iommu_detect(void) { return -ENODEV; } - -#endif - -#endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h deleted file mode 100644 index 55d95eb..0000000 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright (C) 2009-2010 Advanced Micro Devices, Inc. - * Author: Joerg Roedel <joerg.roedel@amd.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _ASM_X86_AMD_IOMMU_PROTO_H -#define _ASM_X86_AMD_IOMMU_PROTO_H - -#include <asm/amd_iommu_types.h> - -extern int amd_iommu_init_dma_ops(void); -extern int amd_iommu_init_passthrough(void); -extern irqreturn_t amd_iommu_int_thread(int irq, void *data); -extern irqreturn_t amd_iommu_int_handler(int irq, void *data); -extern void amd_iommu_apply_erratum_63(u16 devid); -extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); -extern int amd_iommu_init_devices(void); -extern void amd_iommu_uninit_devices(void); -extern void amd_iommu_init_notifier(void); -extern void amd_iommu_init_api(void); -#ifndef CONFIG_AMD_IOMMU_STATS - -static inline void amd_iommu_stats_init(void) { } - -#endif /* !CONFIG_AMD_IOMMU_STATS */ - -static inline bool is_rd890_iommu(struct pci_dev *pdev) -{ - return (pdev->vendor == PCI_VENDOR_ID_ATI) && - (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); -} - -static inline bool iommu_feature(struct amd_iommu *iommu, u64 f) -{ - if (!(iommu->cap & (1 << IOMMU_CAP_EFR))) - return false; - - return !!(iommu->features & f); -} - -#endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h deleted file mode 100644 index 4c99829..0000000 --- a/arch/x86/include/asm/amd_iommu_types.h +++ /dev/null @@ -1,580 +0,0 @@ -/* - * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. - * Author: Joerg Roedel <joerg.roedel@amd.com> - * Leo Duran <leo.duran@amd.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _ASM_X86_AMD_IOMMU_TYPES_H -#define _ASM_X86_AMD_IOMMU_TYPES_H - -#include <linux/types.h> -#include <linux/mutex.h> -#include <linux/list.h> -#include <linux/spinlock.h> - -/* - * Maximum number of IOMMUs supported - */ -#define MAX_IOMMUS 32 - -/* - * some size calculation constants - */ -#define DEV_TABLE_ENTRY_SIZE 32 -#define ALIAS_TABLE_ENTRY_SIZE 2 -#define RLOOKUP_TABLE_ENTRY_SIZE (sizeof(void *)) - -/* Length of the MMIO region for the AMD IOMMU */ -#define MMIO_REGION_LENGTH 0x4000 - -/* Capability offsets used by the driver */ -#define MMIO_CAP_HDR_OFFSET 0x00 -#define MMIO_RANGE_OFFSET 0x0c -#define MMIO_MISC_OFFSET 0x10 - -/* Masks, shifts and macros to parse the device range capability */ -#define MMIO_RANGE_LD_MASK 0xff000000 -#define MMIO_RANGE_FD_MASK 0x00ff0000 -#define MMIO_RANGE_BUS_MASK 0x0000ff00 -#define MMIO_RANGE_LD_SHIFT 24 -#define MMIO_RANGE_FD_SHIFT 16 -#define MMIO_RANGE_BUS_SHIFT 8 -#define MMIO_GET_LD(x) (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT) -#define MMIO_GET_FD(x) (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT) -#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT) -#define MMIO_MSI_NUM(x) ((x) & 0x1f) - -/* Flag masks for the AMD IOMMU exclusion range */ -#define MMIO_EXCL_ENABLE_MASK 0x01ULL -#define MMIO_EXCL_ALLOW_MASK 0x02ULL - -/* Used offsets into the MMIO space */ -#define MMIO_DEV_TABLE_OFFSET 0x0000 -#define MMIO_CMD_BUF_OFFSET 0x0008 -#define MMIO_EVT_BUF_OFFSET 0x0010 -#define MMIO_CONTROL_OFFSET 0x0018 -#define MMIO_EXCL_BASE_OFFSET 0x0020 -#define MMIO_EXCL_LIMIT_OFFSET 0x0028 -#define MMIO_EXT_FEATURES 0x0030 -#define MMIO_CMD_HEAD_OFFSET 0x2000 -#define MMIO_CMD_TAIL_OFFSET 0x2008 -#define MMIO_EVT_HEAD_OFFSET 0x2010 -#define MMIO_EVT_TAIL_OFFSET 0x2018 -#define MMIO_STATUS_OFFSET 0x2020 - - -/* Extended Feature Bits */ -#define FEATURE_PREFETCH (1ULL<<0) -#define FEATURE_PPR (1ULL<<1) -#define FEATURE_X2APIC (1ULL<<2) -#define FEATURE_NX (1ULL<<3) -#define FEATURE_GT (1ULL<<4) -#define FEATURE_IA (1ULL<<6) -#define FEATURE_GA (1ULL<<7) -#define FEATURE_HE (1ULL<<8) -#define FEATURE_PC (1ULL<<9) - -/* MMIO status bits */ -#define MMIO_STATUS_COM_WAIT_INT_MASK 0x04 - -/* event logging constants */ -#define EVENT_ENTRY_SIZE 0x10 -#define EVENT_TYPE_SHIFT 28 -#define EVENT_TYPE_MASK 0xf -#define EVENT_TYPE_ILL_DEV 0x1 -#define EVENT_TYPE_IO_FAULT 0x2 -#define EVENT_TYPE_DEV_TAB_ERR 0x3 -#define EVENT_TYPE_PAGE_TAB_ERR 0x4 -#define EVENT_TYPE_ILL_CMD 0x5 -#define EVENT_TYPE_CMD_HARD_ERR 0x6 -#define EVENT_TYPE_IOTLB_INV_TO 0x7 -#define EVENT_TYPE_INV_DEV_REQ 0x8 -#define EVENT_DEVID_MASK 0xffff -#define EVENT_DEVID_SHIFT 0 -#define EVENT_DOMID_MASK 0xffff -#define EVENT_DOMID_SHIFT 0 -#define EVENT_FLAGS_MASK 0xfff -#define EVENT_FLAGS_SHIFT 0x10 - -/* feature control bits */ -#define CONTROL_IOMMU_EN 0x00ULL -#define CONTROL_HT_TUN_EN 0x01ULL -#define CONTROL_EVT_LOG_EN 0x02ULL -#define CONTROL_EVT_INT_EN 0x03ULL -#define CONTROL_COMWAIT_EN 0x04ULL -#define CONTROL_PASSPW_EN 0x08ULL -#define CONTROL_RESPASSPW_EN 0x09ULL -#define CONTROL_COHERENT_EN 0x0aULL -#define CONTROL_ISOC_EN 0x0bULL -#define CONTROL_CMDBUF_EN 0x0cULL -#define CONTROL_PPFLOG_EN 0x0dULL -#define CONTROL_PPFINT_EN 0x0eULL - -/* command specific defines */ -#define CMD_COMPL_WAIT 0x01 -#define CMD_INV_DEV_ENTRY 0x02 -#define CMD_INV_IOMMU_PAGES 0x03 -#define CMD_INV_IOTLB_PAGES 0x04 -#define CMD_INV_ALL 0x08 - -#define CMD_COMPL_WAIT_STORE_MASK 0x01 -#define CMD_COMPL_WAIT_INT_MASK 0x02 -#define CMD_INV_IOMMU_PAGES_SIZE_MASK 0x01 -#define CMD_INV_IOMMU_PAGES_PDE_MASK 0x02 - -#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS 0x7fffffffffffffffULL - -/* macros and definitions for device table entries */ -#define DEV_ENTRY_VALID 0x00 -#define DEV_ENTRY_TRANSLATION 0x01 -#define DEV_ENTRY_IR 0x3d -#define DEV_ENTRY_IW 0x3e -#define DEV_ENTRY_NO_PAGE_FAULT 0x62 -#define DEV_ENTRY_EX 0x67 -#define DEV_ENTRY_SYSMGT1 0x68 -#define DEV_ENTRY_SYSMGT2 0x69 -#define DEV_ENTRY_INIT_PASS 0xb8 -#define DEV_ENTRY_EINT_PASS 0xb9 -#define DEV_ENTRY_NMI_PASS 0xba -#define DEV_ENTRY_LINT0_PASS 0xbe -#define DEV_ENTRY_LINT1_PASS 0xbf -#define DEV_ENTRY_MODE_MASK 0x07 -#define DEV_ENTRY_MODE_SHIFT 0x09 - -/* constants to configure the command buffer */ -#define CMD_BUFFER_SIZE 8192 -#define CMD_BUFFER_UNINITIALIZED 1 -#define CMD_BUFFER_ENTRIES 512 -#define MMIO_CMD_SIZE_SHIFT 56 -#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) - -/* constants for event buffer handling */ -#define EVT_BUFFER_SIZE 8192 /* 512 entries */ -#define EVT_LEN_MASK (0x9ULL << 56) - -#define PAGE_MODE_NONE 0x00 -#define PAGE_MODE_1_LEVEL 0x01 -#define PAGE_MODE_2_LEVEL 0x02 -#define PAGE_MODE_3_LEVEL 0x03 -#define PAGE_MODE_4_LEVEL 0x04 -#define PAGE_MODE_5_LEVEL 0x05 -#define PAGE_MODE_6_LEVEL 0x06 - -#define PM_LEVEL_SHIFT(x) (12 + ((x) * 9)) -#define PM_LEVEL_SIZE(x) (((x) < 6) ? \ - ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \ - (0xffffffffffffffffULL)) -#define PM_LEVEL_INDEX(x, a) (((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL) -#define PM_LEVEL_ENC(x) (((x) << 9) & 0xe00ULL) -#define PM_LEVEL_PDE(x, a) ((a) | PM_LEVEL_ENC((x)) | \ - IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW) -#define PM_PTE_LEVEL(pte) (((pte) >> 9) & 0x7ULL) - -#define PM_MAP_4k 0 -#define PM_ADDR_MASK 0x000ffffffffff000ULL -#define PM_MAP_MASK(lvl) (PM_ADDR_MASK & \ - (~((1ULL << (12 + ((lvl) * 9))) - 1))) -#define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr)) - -/* - * Returns the page table level to use for a given page size - * Pagesize is expected to be a power-of-two - */ -#define PAGE_SIZE_LEVEL(pagesize) \ - ((__ffs(pagesize) - 12) / 9) -/* - * Returns the number of ptes to use for a given page size - * Pagesize is expected to be a power-of-two - */ -#define PAGE_SIZE_PTE_COUNT(pagesize) \ - (1ULL << ((__ffs(pagesize) - 12) % 9)) - -/* - * Aligns a given io-virtual address to a given page size - * Pagesize is expected to be a power-of-two - */ -#define PAGE_SIZE_ALIGN(address, pagesize) \ - ((address) & ~((pagesize) - 1)) -/* - * Creates an IOMMU PTE for an address an a given pagesize - * The PTE has no permission bits set - * Pagesize is expected to be a power-of-two larger than 4096 - */ -#define PAGE_SIZE_PTE(address, pagesize) \ - (((address) | ((pagesize) - 1)) & \ - (~(pagesize >> 1)) & PM_ADDR_MASK) - -/* - * Takes a PTE value with mode=0x07 and returns the page size it maps - */ -#define PTE_PAGE_SIZE(pte) \ - (1ULL << (1 + ffz(((pte) | 0xfffULL)))) - -#define IOMMU_PTE_P (1ULL << 0) -#define IOMMU_PTE_TV (1ULL << 1) -#define IOMMU_PTE_U (1ULL << 59) -#define IOMMU_PTE_FC (1ULL << 60) -#define IOMMU_PTE_IR (1ULL << 61) -#define IOMMU_PTE_IW (1ULL << 62) - -#define DTE_FLAG_IOTLB 0x01 - -#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) -#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P) -#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK)) -#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07) - -#define IOMMU_PROT_MASK 0x03 -#define IOMMU_PROT_IR 0x01 -#define IOMMU_PROT_IW 0x02 - -/* IOMMU capabilities */ -#define IOMMU_CAP_IOTLB 24 -#define IOMMU_CAP_NPCACHE 26 -#define IOMMU_CAP_EFR 27 - -#define MAX_DOMAIN_ID 65536 - -/* FIXME: move this macro to <linux/pci.h> */ -#define PCI_BUS(x) (((x) >> 8) & 0xff) - -/* Protection domain flags */ -#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */ -#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops - domain for an IOMMU */ -#define PD_PASSTHROUGH_MASK (1UL << 2) /* domain has no page - translation */ - -extern bool amd_iommu_dump; -#define DUMP_printk(format, arg...) \ - do { \ - if (amd_iommu_dump) \ - printk(KERN_INFO "AMD-Vi: " format, ## arg); \ - } while(0); - -/* global flag if IOMMUs cache non-present entries */ -extern bool amd_iommu_np_cache; -/* Only true if all IOMMUs support device IOTLBs */ -extern bool amd_iommu_iotlb_sup; - -/* - * Make iterating over all IOMMUs easier - */ -#define for_each_iommu(iommu) \ - list_for_each_entry((iommu), &amd_iommu_list, list) -#define for_each_iommu_safe(iommu, next) \ - list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list) - -#define APERTURE_RANGE_SHIFT 27 /* 128 MB */ -#define APERTURE_RANGE_SIZE (1ULL << APERTURE_RANGE_SHIFT) -#define APERTURE_RANGE_PAGES (APERTURE_RANGE_SIZE >> PAGE_SHIFT) -#define APERTURE_MAX_RANGES 32 /* allows 4GB of DMA address space */ -#define APERTURE_RANGE_INDEX(a) ((a) >> APERTURE_RANGE_SHIFT) -#define APERTURE_PAGE_INDEX(a) (((a) >> 21) & 0x3fULL) - -/* - * This structure contains generic data for IOMMU protection domains - * independent of their use. - */ -struct protection_domain { - struct list_head list; /* for list of all protection domains */ - struct list_head dev_list; /* List of all devices in this domain */ - spinlock_t lock; /* mostly used to lock the page table*/ - struct mutex api_lock; /* protect page tables in the iommu-api path */ - u16 id; /* the domain id written to the device table */ - int mode; /* paging mode (0-6 levels) */ - u64 *pt_root; /* page table root pointer */ - unsigned long flags; /* flags to find out type of domain */ - bool updated; /* complete domain flush required */ - unsigned dev_cnt; /* devices assigned to this domain */ - unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ - void *priv; /* private data */ - -}; - -/* - * This struct contains device specific data for the IOMMU - */ -struct iommu_dev_data { - struct list_head list; /* For domain->dev_list */ - struct device *dev; /* Device this data belong to */ - struct device *alias; /* The Alias Device */ - struct protection_domain *domain; /* Domain the device is bound to */ - atomic_t bind; /* Domain attach reverent count */ -}; - -/* - * For dynamic growth the aperture size is split into ranges of 128MB of - * DMA address space each. This struct represents one such range. - */ -struct aperture_range { - - /* address allocation bitmap */ - unsigned long *bitmap; - - /* - * Array of PTE pages for the aperture. In this array we save all the - * leaf pages of the domain page table used for the aperture. This way - * we don't need to walk the page table to find a specific PTE. We can - * just calculate its address in constant time. - */ - u64 *pte_pages[64]; - - unsigned long offset; -}; - -/* - * Data container for a dma_ops specific protection domain - */ -struct dma_ops_domain { - struct list_head list; - - /* generic protection domain information */ - struct protection_domain domain; - - /* size of the aperture for the mappings */ - unsigned long aperture_size; - - /* address we start to search for free addresses */ - unsigned long next_address; - - /* address space relevant data */ - struct aperture_range *aperture[APERTURE_MAX_RANGES]; - - /* This will be set to true when TLB needs to be flushed */ - bool need_flush; - - /* - * if this is a preallocated domain, keep the device for which it was - * preallocated in this variable - */ - u16 target_dev; -}; - -/* - * Structure where we save information about one hardware AMD IOMMU in the - * system. - */ -struct amd_iommu { - struct list_head list; - - /* Index within the IOMMU array */ - int index; - - /* locks the accesses to the hardware */ - spinlock_t lock; - - /* Pointer to PCI device of this IOMMU */ - struct pci_dev *dev; - - /* physical address of MMIO space */ - u64 mmio_phys; - /* virtual address of MMIO space */ - u8 *mmio_base; - - /* capabilities of that IOMMU read from ACPI */ - u32 cap; - - /* flags read from acpi table */ - u8 acpi_flags; - - /* Extended features */ - u64 features; - - /* - * Capability pointer. There could be more than one IOMMU per PCI - * device function if there are more than one AMD IOMMU capability - * pointers. - */ - u16 cap_ptr; - - /* pci domain of this IOMMU */ - u16 pci_seg; - - /* first device this IOMMU handles. read from PCI */ - u16 first_device; - /* last device this IOMMU handles. read from PCI */ - u16 last_device; - - /* start of exclusion range of that IOMMU */ - u64 exclusion_start; - /* length of exclusion range of that IOMMU */ - u64 exclusion_length; - - /* command buffer virtual address */ - u8 *cmd_buf; - /* size of command buffer */ - u32 cmd_buf_size; - - /* size of event buffer */ - u32 evt_buf_size; - /* event buffer virtual address */ - u8 *evt_buf; - /* MSI number for event interrupt */ - u16 evt_msi_num; - - /* true if interrupts for this IOMMU are already enabled */ - bool int_enabled; - - /* if one, we need to send a completion wait command */ - bool need_sync; - - /* default dma_ops domain for that IOMMU */ - struct dma_ops_domain *default_dom; - - /* - * We can't rely on the BIOS to restore all values on reinit, so we - * need to stash them - */ - - /* The iommu BAR */ - u32 stored_addr_lo; - u32 stored_addr_hi; - - /* - * Each iommu has 6 l1s, each of which is documented as having 0x12 - * registers - */ - u32 stored_l1[6][0x12]; - - /* The l2 indirect registers */ - u32 stored_l2[0x83]; -}; - -/* - * List with all IOMMUs in the system. This list is not locked because it is - * only written and read at driver initialization or suspend time - */ -extern struct list_head amd_iommu_list; - -/* - * Array with pointers to each IOMMU struct - * The indices are referenced in the protection domains - */ -extern struct amd_iommu *amd_iommus[MAX_IOMMUS]; - -/* Number of IOMMUs present in the system */ -extern int amd_iommus_present; - -/* - * Declarations for the global list of all protection domains - */ -extern spinlock_t amd_iommu_pd_lock; -extern struct list_head amd_iommu_pd_list; - -/* - * Structure defining one entry in the device table - */ -struct dev_table_entry { - u32 data[8]; -}; - -/* - * One entry for unity mappings parsed out of the ACPI table. - */ -struct unity_map_entry { - struct list_head list; - - /* starting device id this entry is used for (including) */ - u16 devid_start; - /* end device id this entry is used for (including) */ - u16 devid_end; - - /* start address to unity map (including) */ - u64 address_start; - /* end address to unity map (including) */ - u64 address_end; - - /* required protection */ - int prot; -}; - -/* - * List of all unity mappings. It is not locked because as runtime it is only - * read. It is created at ACPI table parsing time. - */ -extern struct list_head amd_iommu_unity_map; - -/* - * Data structures for device handling - */ - -/* - * Device table used by hardware. Read and write accesses by software are - * locked with the amd_iommu_pd_table lock. - */ -extern struct dev_table_entry *amd_iommu_dev_table; - -/* - * Alias table to find requestor ids to device ids. Not locked because only - * read on runtime. - */ -extern u16 *amd_iommu_alias_table; - -/* - * Reverse lookup table to find the IOMMU which translates a specific device. - */ -extern struct amd_iommu **amd_iommu_rlookup_table; - -/* size of the dma_ops aperture as power of 2 */ -extern unsigned amd_iommu_aperture_order; - -/* largest PCI device id we expect translation requests for */ -extern u16 amd_iommu_last_bdf; - -/* allocation bitmap for domain ids */ -extern unsigned long *amd_iommu_pd_alloc_bitmap; - -/* - * If true, the addresses will be flushed on unmap time, not when - * they are reused - */ -extern bool amd_iommu_unmap_flush; - -/* takes bus and device/function and returns the device id - * FIXME: should that be in generic PCI code? */ -static inline u16 calc_devid(u8 bus, u8 devfn) -{ - return (((u16)bus) << 8) | devfn; -} - -#ifdef CONFIG_AMD_IOMMU_STATS - -struct __iommu_counter { - char *name; - struct dentry *dent; - u64 value; -}; - -#define DECLARE_STATS_COUNTER(nm) \ - static struct __iommu_counter nm = { \ - .name = #nm, \ - } - -#define INC_STATS_COUNTER(name) name.value += 1 -#define ADD_STATS_COUNTER(name, x) name.value += (x) -#define SUB_STATS_COUNTER(name, x) name.value -= (x) - -#else /* CONFIG_AMD_IOMMU_STATS */ - -#define DECLARE_STATS_COUNTER(name) -#define INC_STATS_COUNTER(name) -#define ADD_STATS_COUNTER(name, x) -#define SUB_STATS_COUNTER(name, x) - -#endif /* CONFIG_AMD_IOMMU_STATS */ - -#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */ diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index 2fefa50..082cf81 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -50,7 +50,6 @@ #define APBT_DEV_USED 1 extern void apbt_time_init(void); -extern struct clock_event_device *global_clock_event; extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); @@ -62,7 +61,7 @@ extern int sfi_mtimer_num; #else /* CONFIG_APB_TIMER */ static inline unsigned long apbt_quick_calibrate(void) {return 0; } -static inline void apbt_time_init(void) {return 0; } +static inline void apbt_time_init(void) { } #endif #endif /* ASM_X86_APBT_H */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index b3ed1e1..9412d65 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -3,9 +3,11 @@ #ifdef __ASSEMBLY__ # define __ASM_FORM(x) x +# define __ASM_FORM_COMMA(x) x, # define __ASM_EX_SEC .section __ex_table, "a" #else # define __ASM_FORM(x) " " #x " " +# define __ASM_FORM_COMMA(x) " " #x "," # define __ASM_EX_SEC " .section __ex_table,\"a\"\n" #endif @@ -15,7 +17,8 @@ # define __ASM_SEL(a,b) __ASM_FORM(b) #endif -#define __ASM_SIZE(inst) __ASM_SEL(inst##l, inst##q) +#define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \ + inst##q##__VA_ARGS__) #define __ASM_REG(reg) __ASM_SEL(e##reg, r##reg) #define _ASM_PTR __ASM_SEL(.long, .quad) diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index 30af5a8..a9e3a74 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -46,6 +46,7 @@ For 32-bit we have the following conventions - kernel is built with */ +#include "dwarf2.h" /* * 64-bit system call stack frame layout defines and helpers, for @@ -84,72 +85,57 @@ For 32-bit we have the following conventions - kernel is built with #define ARGOFFSET R11 #define SWFRAME ORIG_RAX - .macro SAVE_ARGS addskip=0, norcx=0, nor891011=0 + .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1 subq $9*8+\addskip, %rsp CFI_ADJUST_CFA_OFFSET 9*8+\addskip - movq %rdi, 8*8(%rsp) - CFI_REL_OFFSET rdi, 8*8 - movq %rsi, 7*8(%rsp) - CFI_REL_OFFSET rsi, 7*8 - movq %rdx, 6*8(%rsp) - CFI_REL_OFFSET rdx, 6*8 - .if \norcx - .else - movq %rcx, 5*8(%rsp) - CFI_REL_OFFSET rcx, 5*8 + movq_cfi rdi, 8*8 + movq_cfi rsi, 7*8 + movq_cfi rdx, 6*8 + + .if \save_rcx + movq_cfi rcx, 5*8 .endif - movq %rax, 4*8(%rsp) - CFI_REL_OFFSET rax, 4*8 - .if \nor891011 - .else - movq %r8, 3*8(%rsp) - CFI_REL_OFFSET r8, 3*8 - movq %r9, 2*8(%rsp) - CFI_REL_OFFSET r9, 2*8 - movq %r10, 1*8(%rsp) - CFI_REL_OFFSET r10, 1*8 - movq %r11, (%rsp) - CFI_REL_OFFSET r11, 0*8 + + movq_cfi rax, 4*8 + + .if \save_r891011 + movq_cfi r8, 3*8 + movq_cfi r9, 2*8 + movq_cfi r10, 1*8 + movq_cfi r11, 0*8 .endif + .endm #define ARG_SKIP (9*8) - .macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \ - skipr8910=0, skiprdx=0 - .if \skipr11 - .else - movq (%rsp), %r11 - CFI_RESTORE r11 + .macro RESTORE_ARGS rstor_rax=1, addskip=0, rstor_rcx=1, rstor_r11=1, \ + rstor_r8910=1, rstor_rdx=1 + .if \rstor_r11 + movq_cfi_restore 0*8, r11 .endif - .if \skipr8910 - .else - movq 1*8(%rsp), %r10 - CFI_RESTORE r10 - movq 2*8(%rsp), %r9 - CFI_RESTORE r9 - movq 3*8(%rsp), %r8 - CFI_RESTORE r8 + + .if \rstor_r8910 + movq_cfi_restore 1*8, r10 + movq_cfi_restore 2*8, r9 + movq_cfi_restore 3*8, r8 .endif - .if \skiprax - .else - movq 4*8(%rsp), %rax - CFI_RESTORE rax + + .if \rstor_rax + movq_cfi_restore 4*8, rax .endif - .if \skiprcx - .else - movq 5*8(%rsp), %rcx - CFI_RESTORE rcx + + .if \rstor_rcx + movq_cfi_restore 5*8, rcx .endif - .if \skiprdx - .else - movq 6*8(%rsp), %rdx - CFI_RESTORE rdx + + .if \rstor_rdx + movq_cfi_restore 6*8, rdx .endif - movq 7*8(%rsp), %rsi - CFI_RESTORE rsi - movq 8*8(%rsp), %rdi - CFI_RESTORE rdi + + movq_cfi_restore 7*8, rsi + movq_cfi_restore 8*8, rdi + .if ARG_SKIP+\addskip > 0 addq $ARG_SKIP+\addskip, %rsp CFI_ADJUST_CFA_OFFSET -(ARG_SKIP+\addskip) @@ -176,33 +162,21 @@ For 32-bit we have the following conventions - kernel is built with .macro SAVE_REST subq $REST_SKIP, %rsp CFI_ADJUST_CFA_OFFSET REST_SKIP - movq %rbx, 5*8(%rsp) - CFI_REL_OFFSET rbx, 5*8 - movq %rbp, 4*8(%rsp) - CFI_REL_OFFSET rbp, 4*8 - movq %r12, 3*8(%rsp) - CFI_REL_OFFSET r12, 3*8 - movq %r13, 2*8(%rsp) - CFI_REL_OFFSET r13, 2*8 - movq %r14, 1*8(%rsp) - CFI_REL_OFFSET r14, 1*8 - movq %r15, (%rsp) - CFI_REL_OFFSET r15, 0*8 + movq_cfi rbx, 5*8 + movq_cfi rbp, 4*8 + movq_cfi r12, 3*8 + movq_cfi r13, 2*8 + movq_cfi r14, 1*8 + movq_cfi r15, 0*8 .endm .macro RESTORE_REST - movq (%rsp), %r15 - CFI_RESTORE r15 - movq 1*8(%rsp), %r14 - CFI_RESTORE r14 - movq 2*8(%rsp), %r13 - CFI_RESTORE r13 - movq 3*8(%rsp), %r12 - CFI_RESTORE r12 - movq 4*8(%rsp), %rbp - CFI_RESTORE rbp - movq 5*8(%rsp), %rbx - CFI_RESTORE rbx + movq_cfi_restore 0*8, r15 + movq_cfi_restore 1*8, r14 + movq_cfi_restore 2*8, r13 + movq_cfi_restore 3*8, r12 + movq_cfi_restore 4*8, rbp + movq_cfi_restore 5*8, rbx addq $REST_SKIP, %rsp CFI_ADJUST_CFA_OFFSET -(REST_SKIP) .endm @@ -214,7 +188,7 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_ALL addskip=0 RESTORE_REST - RESTORE_ARGS 0, \addskip + RESTORE_ARGS 1, \addskip .endm .macro icebp diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 5dc6acc..71cc380 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -125,7 +125,7 @@ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ #define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */ #define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRND (4*32+30) /* The RDRAND instruction */ +#define X86_FEATURE_RDRAND (4*32+30) /* The RDRAND instruction */ #define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 617bd56..7b439d9 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -4,30 +4,33 @@ #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> + #include <linux/smp.h> -static inline void fill_ldt(struct desc_struct *desc, - const struct user_desc *info) -{ - desc->limit0 = info->limit & 0x0ffff; - desc->base0 = info->base_addr & 0x0000ffff; - - desc->base1 = (info->base_addr & 0x00ff0000) >> 16; - desc->type = (info->read_exec_only ^ 1) << 1; - desc->type |= info->contents << 2; - desc->s = 1; - desc->dpl = 0x3; - desc->p = info->seg_not_present ^ 1; - desc->limit = (info->limit & 0xf0000) >> 16; - desc->avl = info->useable; - desc->d = info->seg_32bit; - desc->g = info->limit_in_pages; - desc->base2 = (info->base_addr & 0xff000000) >> 24; +static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info) +{ + desc->limit0 = info->limit & 0x0ffff; + + desc->base0 = (info->base_addr & 0x0000ffff); + desc->base1 = (info->base_addr & 0x00ff0000) >> 16; + + desc->type = (info->read_exec_only ^ 1) << 1; + desc->type |= info->contents << 2; + + desc->s = 1; + desc->dpl = 0x3; + desc->p = info->seg_not_present ^ 1; + desc->limit = (info->limit & 0xf0000) >> 16; + desc->avl = info->useable; + desc->d = info->seg_32bit; + desc->g = info->limit_in_pages; + + desc->base2 = (info->base_addr & 0xff000000) >> 24; /* * Don't allow setting of the lm bit. It is useless anyway * because 64bit system calls require __USER_CS: */ - desc->l = 0; + desc->l = 0; } extern struct desc_ptr idt_descr; @@ -36,6 +39,7 @@ extern gate_desc idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); + DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) @@ -48,16 +52,16 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { - gate->offset_low = PTR_LOW(func); - gate->segment = __KERNEL_CS; - gate->ist = ist; - gate->p = 1; - gate->dpl = dpl; - gate->zero0 = 0; - gate->zero1 = 0; - gate->type = type; - gate->offset_middle = PTR_MIDDLE(func); - gate->offset_high = PTR_HIGH(func); + gate->offset_low = PTR_LOW(func); + gate->segment = __KERNEL_CS; + gate->ist = ist; + gate->p = 1; + gate->dpl = dpl; + gate->zero0 = 0; + gate->zero1 = 0; + gate->type = type; + gate->offset_middle = PTR_MIDDLE(func); + gate->offset_high = PTR_HIGH(func); } #else @@ -66,8 +70,7 @@ static inline void pack_gate(gate_desc *gate, unsigned char type, unsigned short seg) { gate->a = (seg << 16) | (base & 0xffff); - gate->b = (base & 0xffff0000) | - (((0x80 | type | (dpl << 5)) & 0xff) << 8); + gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8); } #endif @@ -75,31 +78,29 @@ static inline void pack_gate(gate_desc *gate, unsigned char type, static inline int desc_empty(const void *ptr) { const u32 *desc = ptr; + return !(desc[0] | desc[1]); } #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else -#define load_TR_desc() native_load_tr_desc() -#define load_gdt(dtr) native_load_gdt(dtr) -#define load_idt(dtr) native_load_idt(dtr) -#define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) -#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) - -#define store_gdt(dtr) native_store_gdt(dtr) -#define store_idt(dtr) native_store_idt(dtr) -#define store_tr(tr) (tr = native_store_tr()) - -#define load_TLS(t, cpu) native_load_tls(t, cpu) -#define set_ldt native_set_ldt - -#define write_ldt_entry(dt, entry, desc) \ - native_write_ldt_entry(dt, entry, desc) -#define write_gdt_entry(dt, entry, desc, type) \ - native_write_gdt_entry(dt, entry, desc, type) -#define write_idt_entry(dt, entry, g) \ - native_write_idt_entry(dt, entry, g) +#define load_TR_desc() native_load_tr_desc() +#define load_gdt(dtr) native_load_gdt(dtr) +#define load_idt(dtr) native_load_idt(dtr) +#define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) +#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) + +#define store_gdt(dtr) native_store_gdt(dtr) +#define store_idt(dtr) native_store_idt(dtr) +#define store_tr(tr) (tr = native_store_tr()) + +#define load_TLS(t, cpu) native_load_tls(t, cpu) +#define set_ldt native_set_ldt + +#define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc) +#define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type) +#define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { @@ -112,33 +113,27 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) -static inline void native_write_idt_entry(gate_desc *idt, int entry, - const gate_desc *gate) +static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { memcpy(&idt[entry], gate, sizeof(*gate)); } -static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, - const void *desc) +static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc) { memcpy(&ldt[entry], desc, 8); } -static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry, - const void *desc, int type) +static inline void +native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type) { unsigned int size; + switch (type) { - case DESC_TSS: - size = sizeof(tss_desc); - break; - case DESC_LDT: - size = sizeof(ldt_desc); - break; - default: - size = sizeof(struct desc_struct); - break; + case DESC_TSS: size = sizeof(tss_desc); break; + case DESC_LDT: size = sizeof(ldt_desc); break; + default: size = sizeof(*gdt); break; } + memcpy(&gdt[entry], desc, size); } @@ -154,20 +149,21 @@ static inline void pack_descriptor(struct desc_struct *desc, unsigned long base, } -static inline void set_tssldt_descriptor(void *d, unsigned long addr, - unsigned type, unsigned size) +static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) { #ifdef CONFIG_X86_64 struct ldttss_desc64 *desc = d; + memset(desc, 0, sizeof(*desc)); - desc->limit0 = size & 0xFFFF; - desc->base0 = PTR_LOW(addr); - desc->base1 = PTR_MIDDLE(addr) & 0xFF; - desc->type = type; - desc->p = 1; - desc->limit1 = (size >> 16) & 0xF; - desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF; - desc->base3 = PTR_HIGH(addr); + + desc->limit0 = size & 0xFFFF; + desc->base0 = PTR_LOW(addr); + desc->base1 = PTR_MIDDLE(addr) & 0xFF; + desc->type = type; + desc->p = 1; + desc->limit1 = (size >> 16) & 0xF; + desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF; + desc->base3 = PTR_HIGH(addr); #else pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0); #endif @@ -237,14 +233,16 @@ static inline void native_store_idt(struct desc_ptr *dtr) static inline unsigned long native_store_tr(void) { unsigned long tr; + asm volatile("str %0":"=r" (tr)); + return tr; } static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { - unsigned int i; struct desc_struct *gdt = get_cpu_gdt_table(cpu); + unsigned int i; for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; @@ -313,6 +311,7 @@ static inline void _set_gate(int gate, unsigned type, void *addr, unsigned dpl, unsigned ist, unsigned seg) { gate_desc s; + pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); /* * does not need to be atomic because it is only done once at @@ -343,8 +342,9 @@ static inline void alloc_system_vector(int vector) set_bit(vector, used_vectors); if (first_system_vector > vector) first_system_vector = vector; - } else + } else { BUG(); + } } static inline void alloc_intr_gate(unsigned int n, void *addr) diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 2c6fc9e..3b629f4 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -1,5 +1,6 @@ #ifdef __ASSEMBLY__ +#include <asm/asm.h> #include <asm/dwarf2.h> /* The annotation hides the frame from the unwinder and makes it look @@ -7,13 +8,13 @@ frame pointer later */ #ifdef CONFIG_FRAME_POINTER .macro FRAME - pushl_cfi %ebp - CFI_REL_OFFSET ebp,0 - movl %esp,%ebp + __ASM_SIZE(push,_cfi) %__ASM_REG(bp) + CFI_REL_OFFSET __ASM_REG(bp), 0 + __ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp) .endm .macro ENDFRAME - popl_cfi %ebp - CFI_RESTORE ebp + __ASM_SIZE(pop,_cfi) %__ASM_REG(bp) + CFI_RESTORE __ASM_REG(bp) .endm #else .macro FRAME diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h deleted file mode 100644 index 65aaa91..0000000 --- a/arch/x86/include/asm/i8253.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _ASM_X86_I8253_H -#define _ASM_X86_I8253_H - -/* i8253A PIT registers */ -#define PIT_MODE 0x43 -#define PIT_CH0 0x40 -#define PIT_CH2 0x42 - -#define PIT_LATCH LATCH - -extern raw_spinlock_t i8253_lock; - -extern struct clock_event_device *global_clock_event; - -extern void setup_pit_timer(void); - -#define inb_pit inb_p -#define outb_pit outb_p - -#endif /* _ASM_X86_I8253_H */ diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h index 38d8737..f49253d7 100644 --- a/arch/x86/include/asm/idle.h +++ b/arch/x86/include/asm/idle.h @@ -16,6 +16,6 @@ static inline void enter_idle(void) { } static inline void exit_idle(void) { } #endif /* CONFIG_X86_64 */ -void c1e_remove_cpu(int cpu); +void amd_e400_remove_cpu(int cpu); #endif /* _ASM_X86_IDLE_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 5745ce8..bba3cf8 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -60,23 +60,24 @@ static inline void native_halt(void) #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ +#include <linux/types.h> -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { return native_save_fl(); } -static inline void arch_local_irq_restore(unsigned long flags) +static inline notrace void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { native_irq_disable(); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { native_irq_enable(); } @@ -102,7 +103,7 @@ static inline void halt(void) /* * For spinlocks, etc: */ -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index b60f292..879fd7d 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -61,6 +61,7 @@ hcall(unsigned long call, : "memory"); return call; } +/*:*/ /* Can't use our min() macro here: needs to be a constant */ #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h index 19ae14b..0cd3800 100644 --- a/arch/x86/include/asm/memblock.h +++ b/arch/x86/include/asm/memblock.h @@ -4,7 +4,6 @@ #define ARCH_DISCARD_MEMBLOCK u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); -void memblock_x86_to_bootmem(u64 start, u64 end); void memblock_x86_reserve_range(u64 start, u64 end, char *name); void memblock_x86_free_range(u64 start, u64 end); @@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end); u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); u64 memblock_x86_memory_in_range(u64 addr, u64 limit); +bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); #endif diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index aeff3e8..5f55e69 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -11,14 +11,14 @@ typedef struct { void *ldt; int size; - struct mutex lock; - void *vdso; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ unsigned short ia32_compat; #endif + struct mutex lock; + void *vdso; } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 5e83a41..ffa037f 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn) #endif } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - static inline int pfn_valid(int pfn) { int nid = pfn_to_nid(pfn); @@ -68,6 +57,8 @@ static inline int pfn_valid(int pfn) return 0; } +#define early_pfn_valid(pfn) pfn_valid((pfn)) + #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_NEED_MULTIPLE_NODES diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index b3f88d7..129d9aa 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -13,8 +13,5 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) #endif #endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a0a9779..3470c9d 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -388,12 +388,9 @@ do { \ #define __this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) -/* - * Generic fallback operations for __this_cpu_xchg_[1-4] are okay and much - * faster than an xchg with forced lock semantics. - */ -#define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) -#define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) +#define __this_cpu_xchg_1(pcp, val) percpu_xchg_op(pcp, val) +#define __this_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) +#define __this_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) #define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) @@ -485,6 +482,8 @@ do { \ #define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) +#define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) +#define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) #define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index d9d4dae..094fb30 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -152,6 +152,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); (regs)->bp = caller_frame_pointer(); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ + asm volatile( \ + _ASM_MOV "%%"_ASM_SP ", %0\n" \ + : "=m" ((regs)->sp) \ + :: "memory" \ + ); \ } #else diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 56fd9e3..4f7e67e 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -102,6 +102,14 @@ #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) /* + * If an event has alias it should be marked + * with a special bit. (Don't forget to check + * P4_PEBS_CONFIG_MASK and related bits on + * modification.) + */ +#define P4_CONFIG_ALIASABLE (1 << 9) + +/* * The bits we allow to pass for RAW events */ #define P4_CONFIG_MASK_ESCR \ @@ -123,6 +131,31 @@ (p4_config_pack_escr(P4_CONFIG_MASK_ESCR)) | \ (p4_config_pack_cccr(P4_CONFIG_MASK_CCCR)) +/* + * In case of event aliasing we need to preserve some + * caller bits, otherwise the mapping won't be complete. + */ +#define P4_CONFIG_EVENT_ALIAS_MASK \ + (p4_config_pack_escr(P4_CONFIG_MASK_ESCR) | \ + p4_config_pack_cccr(P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE)) + +#define P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS \ + ((P4_CONFIG_HT) | \ + p4_config_pack_escr(P4_ESCR_T0_OS | \ + P4_ESCR_T0_USR | \ + P4_ESCR_T1_OS | \ + P4_ESCR_T1_USR) | \ + p4_config_pack_cccr(P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_THREAD_ANY | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_OVF_PMI_T1 | \ + P4_CONFIG_ALIASABLE)) + static inline bool p4_is_event_cascaded(u64 config) { u32 cccr = p4_config_unpack_cccr(config); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4c25ab4..2193715 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -754,10 +754,10 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); extern void select_idle_routine(const struct cpuinfo_x86 *c); -extern void init_c1e_mask(void); +extern void init_amd_e400_c1e_mask(void); extern unsigned long boot_option_idle_override; -extern bool c1e_detected; +extern bool amd_e400_c1e_detected; enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, IDLE_POLL, IDLE_FORCE_MWAIT}; diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index 971e0b4..df12870 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -30,17 +30,6 @@ extern void add_dtb(u64 data); extern void x86_add_irq_domains(void); void __cpuinit x86_of_pci_init(void); void x86_dtb_init(void); - -static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) -{ - return pdev ? pdev->dev.of_node : NULL; -} - -static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) -{ - return pci_device_to_OF_node(bus->self); -} - #else static inline void add_dtb(u64 data) { } static inline void x86_add_irq_domains(void) { } diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 31d84ac..a518c0a 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) u64 product; #ifdef __i386__ u32 tmp1, tmp2; +#else + ulong tmp; #endif if (shift < 0) @@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); #elif defined(__x86_64__) __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); + "mul %[mul_frac] ; shrd $32, %[hi], %[lo]" + : [lo]"=a"(product), + [hi]"=d"(tmp) + : "0"(delta), + [mul_frac]"rm"((u64)mul_frac)); #else #error implement me! #endif diff --git a/arch/x86/include/asm/rwlock.h b/arch/x86/include/asm/rwlock.h index 6a8c0d6..a5370a0 100644 --- a/arch/x86/include/asm/rwlock.h +++ b/arch/x86/include/asm/rwlock.h @@ -1,7 +1,48 @@ #ifndef _ASM_X86_RWLOCK_H #define _ASM_X86_RWLOCK_H -#define RW_LOCK_BIAS 0x01000000 +#include <asm/asm.h> + +#if CONFIG_NR_CPUS <= 2048 + +#ifndef __ASSEMBLY__ +typedef union { + s32 lock; + s32 write; +} arch_rwlock_t; +#endif + +#define RW_LOCK_BIAS 0x00100000 +#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##l) +#define READ_LOCK_ATOMIC(n) atomic_##n +#define WRITE_LOCK_ADD(n) __ASM_FORM_COMMA(addl n) +#define WRITE_LOCK_SUB(n) __ASM_FORM_COMMA(subl n) +#define WRITE_LOCK_CMP RW_LOCK_BIAS + +#else /* CONFIG_NR_CPUS > 2048 */ + +#include <linux/const.h> + +#ifndef __ASSEMBLY__ +typedef union { + s64 lock; + struct { + u32 read; + s32 write; + }; +} arch_rwlock_t; +#endif + +#define RW_LOCK_BIAS (_AC(1,L) << 32) +#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##q) +#define READ_LOCK_ATOMIC(n) atomic64_##n +#define WRITE_LOCK_ADD(n) __ASM_FORM(incl) +#define WRITE_LOCK_SUB(n) __ASM_FORM(decl) +#define WRITE_LOCK_CMP 1 + +#endif /* CONFIG_NR_CPUS */ + +#define __ARCH_RW_LOCK_UNLOCKED { RW_LOCK_BIAS } /* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index cd84f72..5e64171 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -162,7 +162,7 @@ #define GDT_ENTRY_DEFAULT_USER32_CS 4 #define GDT_ENTRY_DEFAULT_USER_DS 5 #define GDT_ENTRY_DEFAULT_USER_CS 6 -#define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS * 8 + 3) +#define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8+3) #define __USER32_DS __USER_DS #define GDT_ENTRY_TSS 8 /* needs two entries */ diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 725b778..49adfd7 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -10,7 +10,11 @@ static inline void smpboot_clear_io_apic_irqs(void) static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); CMOS_WRITE(0xa, 0xf); + spin_unlock_irqrestore(&rtc_lock, flags); local_flush_tlb(); pr_debug("1.\n"); *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_high)) = @@ -23,6 +27,8 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) static inline void smpboot_restore_warm_reset_vector(void) { + unsigned long flags; + /* * Install writable page 0 entry to set BIOS data area. */ @@ -32,7 +38,9 @@ static inline void smpboot_restore_warm_reset_vector(void) * Paranoid: Set warm reset code and vector here back * to default values. */ + spin_lock_irqsave(&rtc_lock, flags); CMOS_WRITE(0, 0xf); + spin_unlock_irqrestore(&rtc_lock, flags); *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0; } diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3089f70..e9e51f7 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -2,7 +2,6 @@ #define _ASM_X86_SPINLOCK_H #include <asm/atomic.h> -#include <asm/rwlock.h> #include <asm/page.h> #include <asm/processor.h> #include <linux/compiler.h> @@ -234,7 +233,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) */ static inline int arch_read_can_lock(arch_rwlock_t *lock) { - return (int)(lock)->lock > 0; + return lock->lock > 0; } /** @@ -243,12 +242,12 @@ static inline int arch_read_can_lock(arch_rwlock_t *lock) */ static inline int arch_write_can_lock(arch_rwlock_t *lock) { - return (lock)->lock == RW_LOCK_BIAS; + return lock->write == WRITE_LOCK_CMP; } static inline void arch_read_lock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t" + asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t" "jns 1f\n" "call __read_lock_failed\n\t" "1:\n" @@ -257,47 +256,55 @@ static inline void arch_read_lock(arch_rwlock_t *rw) static inline void arch_write_lock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t" + asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t" "jz 1f\n" "call __write_lock_failed\n\t" "1:\n" - ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory"); + ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS) + : "memory"); } static inline int arch_read_trylock(arch_rwlock_t *lock) { - atomic_t *count = (atomic_t *)lock; + READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock; - if (atomic_dec_return(count) >= 0) + if (READ_LOCK_ATOMIC(dec_return)(count) >= 0) return 1; - atomic_inc(count); + READ_LOCK_ATOMIC(inc)(count); return 0; } static inline int arch_write_trylock(arch_rwlock_t *lock) { - atomic_t *count = (atomic_t *)lock; + atomic_t *count = (atomic_t *)&lock->write; - if (atomic_sub_and_test(RW_LOCK_BIAS, count)) + if (atomic_sub_and_test(WRITE_LOCK_CMP, count)) return 1; - atomic_add(RW_LOCK_BIAS, count); + atomic_add(WRITE_LOCK_CMP, count); return 0; } static inline void arch_read_unlock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory"); + asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0" + :"+m" (rw->lock) : : "memory"); } static inline void arch_write_unlock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX "addl %1, %0" - : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); + asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0" + : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory"); } #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) +#undef READ_LOCK_SIZE +#undef READ_LOCK_ATOMIC +#undef WRITE_LOCK_ADD +#undef WRITE_LOCK_SUB +#undef WRITE_LOCK_CMP + #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index dcb48b2..7c7a486 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -11,10 +11,6 @@ typedef struct arch_spinlock { #define __ARCH_SPIN_LOCK_UNLOCKED { 0 } -typedef struct { - unsigned int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { RW_LOCK_BIAS } +#include <asm/rwlock.h> #endif /* _ASM_X86_SPINLOCK_TYPES_H */ diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 7bdec4e..92b8aec 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -1,10 +1,12 @@ #ifndef _ASM_X86_TIME_H #define _ASM_X86_TIME_H -extern void hpet_time_init(void); - +#include <linux/clocksource.h> #include <asm/mc146818rtc.h> +extern void hpet_time_init(void); extern void time_init(void); +extern struct clock_event_device *global_clock_event; + #endif /* _ASM_X86_TIME_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 99ddd14..36361bf 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -555,6 +555,9 @@ struct __large_struct { unsigned long buf[100]; }; #endif /* CONFIG_X86_WP_WORKS_OK */ +extern unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n); + /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index fb6a625..593485b3 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -351,10 +351,11 @@ #define __NR_clock_adjtime 343 #define __NR_syncfs 344 #define __NR_sendmmsg 345 +#define __NR_setns 346 #ifdef __KERNEL__ -#define NR_syscalls 346 +#define NR_syscalls 347 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 79f90eb..705bf13 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -679,6 +679,8 @@ __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_sendmmsg 307 __SYSCALL(__NR_sendmmsg, sys_sendmmsg) +#define __NR_setns 308 +__SYSCALL(__NR_setns, sys_setns) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 130f1ee..a291c40 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -5,7 +5,7 @@ * * SGI UV Broadcast Assist Unit definitions * - * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2008-2011 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_BAU_H @@ -35,17 +35,20 @@ #define MAX_CPUS_PER_UVHUB 64 #define MAX_CPUS_PER_SOCKET 32 -#define UV_ADP_SIZE 64 /* hardware-provided max. */ -#define UV_CPUS_PER_ACT_STATUS 32 /* hardware-provided max. */ -#define UV_ITEMS_PER_DESCRIPTOR 8 +#define ADP_SZ 64 /* hardware-provided max. */ +#define UV_CPUS_PER_AS 32 /* hardware-provided max. */ +#define ITEMS_PER_DESC 8 /* the 'throttle' to prevent the hardware stay-busy bug */ #define MAX_BAU_CONCURRENT 3 #define UV_ACT_STATUS_MASK 0x3 #define UV_ACT_STATUS_SIZE 2 #define UV_DISTRIBUTION_SIZE 256 #define UV_SW_ACK_NPENDING 8 -#define UV_NET_ENDPOINT_INTD 0x38 -#define UV_DESC_BASE_PNODE_SHIFT 49 +#define UV1_NET_ENDPOINT_INTD 0x38 +#define UV2_NET_ENDPOINT_INTD 0x28 +#define UV_NET_ENDPOINT_INTD (is_uv1_hub() ? \ + UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD) +#define UV_DESC_PSHIFT 49 #define UV_PAYLOADQ_PNODE_SHIFT 49 #define UV_PTC_BASENAME "sgi_uv/ptc_statistics" #define UV_BAU_BASENAME "sgi_uv/bau_tunables" @@ -53,29 +56,64 @@ #define UV_BAU_TUNABLES_FILE "bau_tunables" #define WHITESPACE " \t\n" #define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) -#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL +#define cpubit_isset(cpu, bau_local_cpumask) \ + test_bit((cpu), (bau_local_cpumask).bits) + /* [19:16] SOFT_ACK timeout period 19: 1 is urgency 7 17:16 1 is multiplier */ -#define BAU_MISC_CONTROL_MULT_MASK 3 +/* + * UV2: Bit 19 selects between + * (0): 10 microsecond timebase and + * (1): 80 microseconds + * we're using 655us, similar to UV1: 65 units of 10us + */ +#define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL) +#define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (65*10UL) + +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD (is_uv1_hub() ? \ + UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD : \ + UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD) -#define UVH_AGING_PRESCALE_SEL 0x000000b000UL +#define BAU_MISC_CONTROL_MULT_MASK 3 + +#define UVH_AGING_PRESCALE_SEL 0x000000b000UL /* [30:28] URGENCY_7 an index into a table of times */ -#define BAU_URGENCY_7_SHIFT 28 -#define BAU_URGENCY_7_MASK 7 +#define BAU_URGENCY_7_SHIFT 28 +#define BAU_URGENCY_7_MASK 7 -#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL +#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL /* [45:40] BAU - BAU transaction timeout select - a multiplier */ -#define BAU_TRANS_SHIFT 40 -#define BAU_TRANS_MASK 0x3f +#define BAU_TRANS_SHIFT 40 +#define BAU_TRANS_MASK 0x3f + +/* + * shorten some awkward names + */ +#define AS_PUSH_SHIFT UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT +#define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT +#define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT +#define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD +#define write_gmmr uv_write_global_mmr64 +#define write_lmmr uv_write_local_mmr +#define read_lmmr uv_read_local_mmr +#define read_gmmr uv_read_global_mmr64 /* * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1 */ -#define DESC_STATUS_IDLE 0 -#define DESC_STATUS_ACTIVE 1 -#define DESC_STATUS_DESTINATION_TIMEOUT 2 -#define DESC_STATUS_SOURCE_TIMEOUT 3 +#define DS_IDLE 0 +#define DS_ACTIVE 1 +#define DS_DESTINATION_TIMEOUT 2 +#define DS_SOURCE_TIMEOUT 3 +/* + * bits put together from HRP_LB_BAU_SB_ACTIVATION_STATUS_0/1/2 + * values 1 and 5 will not occur + */ +#define UV2H_DESC_IDLE 0 +#define UV2H_DESC_DEST_TIMEOUT 2 +#define UV2H_DESC_DEST_STRONG_NACK 3 +#define UV2H_DESC_BUSY 4 +#define UV2H_DESC_SOURCE_TIMEOUT 6 +#define UV2H_DESC_DEST_PUT_ERR 7 /* * delay for 'plugged' timeout retries, in microseconds @@ -86,15 +124,24 @@ * threshholds at which to use IPI to free resources */ /* after this # consecutive 'plugged' timeouts, use IPI to release resources */ -#define PLUGSB4RESET 100 +#define PLUGSB4RESET 100 /* after this many consecutive timeouts, use IPI to release resources */ -#define TIMEOUTSB4RESET 1 +#define TIMEOUTSB4RESET 1 /* at this number uses of IPI to release resources, giveup the request */ -#define IPI_RESET_LIMIT 1 +#define IPI_RESET_LIMIT 1 /* after this # consecutive successes, bump up the throttle if it was lowered */ -#define COMPLETE_THRESHOLD 5 +#define COMPLETE_THRESHOLD 5 + +#define UV_LB_SUBNODEID 0x10 -#define UV_LB_SUBNODEID 0x10 +/* these two are the same for UV1 and UV2: */ +#define UV_SA_SHFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT +#define UV_SA_MASK UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK +/* 4 bits of software ack period */ +#define UV2_ACK_MASK 0x7UL +#define UV2_ACK_UNITS_SHFT 3 +#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT +#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT /* * number of entries in the destination side payload queue @@ -115,9 +162,16 @@ /* * tuning the action when the numalink network is extremely delayed */ -#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */ -#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */ -#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */ +#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in + microseconds */ +#define CONGESTED_REPS 10 /* long delays averaged over + this many broadcasts */ +#define CONGESTED_PERIOD 30 /* time for the bau to be + disabled, in seconds */ +/* see msg_type: */ +#define MSG_NOOP 0 +#define MSG_REGULAR 1 +#define MSG_RETRY 2 /* * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor) @@ -129,8 +183,8 @@ * 'base_dest_nasid' field of the header corresponds to the * destination nodeID associated with that specified bit. */ -struct bau_target_uvhubmask { - unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)]; +struct bau_targ_hubmask { + unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)]; }; /* @@ -139,7 +193,7 @@ struct bau_target_uvhubmask { * enough bits for max. cpu's per uvhub) */ struct bau_local_cpumask { - unsigned long bits; + unsigned long bits; }; /* @@ -160,14 +214,14 @@ struct bau_local_cpumask { * The payload is software-defined for INTD transactions */ struct bau_msg_payload { - unsigned long address; /* signifies a page or all TLB's - of the cpu */ + unsigned long address; /* signifies a page or all + TLB's of the cpu */ /* 64 bits */ - unsigned short sending_cpu; /* filled in by sender */ + unsigned short sending_cpu; /* filled in by sender */ /* 16 bits */ - unsigned short acknowledge_count;/* filled in by destination */ + unsigned short acknowledge_count; /* filled in by destination */ /* 16 bits */ - unsigned int reserved1:32; /* not usable */ + unsigned int reserved1:32; /* not usable */ }; @@ -176,93 +230,96 @@ struct bau_msg_payload { * see table 4.2.3.0.1 in broacast_assist spec. */ struct bau_msg_header { - unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ + unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ - unsigned int base_dest_nasid:15; /* nasid of the */ - /* bits 20:6 */ /* first bit in uvhub map */ - unsigned int command:8; /* message type */ + unsigned int base_dest_nasid:15; /* nasid of the first bit */ + /* bits 20:6 */ /* in uvhub map */ + unsigned int command:8; /* message type */ /* bits 28:21 */ - /* 0x38: SN3net EndPoint Message */ - unsigned int rsvd_1:3; /* must be zero */ + /* 0x38: SN3net EndPoint Message */ + unsigned int rsvd_1:3; /* must be zero */ /* bits 31:29 */ - /* int will align on 32 bits */ - unsigned int rsvd_2:9; /* must be zero */ + /* int will align on 32 bits */ + unsigned int rsvd_2:9; /* must be zero */ /* bits 40:32 */ - /* Suppl_A is 56-41 */ - unsigned int sequence:16;/* message sequence number */ - /* bits 56:41 */ /* becomes bytes 16-17 of msg */ - /* Address field (96:57) is never used as an - address (these are address bits 42:3) */ - - unsigned int rsvd_3:1; /* must be zero */ + /* Suppl_A is 56-41 */ + unsigned int sequence:16; /* message sequence number */ + /* bits 56:41 */ /* becomes bytes 16-17 of msg */ + /* Address field (96:57) is + never used as an address + (these are address bits + 42:3) */ + + unsigned int rsvd_3:1; /* must be zero */ /* bit 57 */ - /* address bits 27:4 are payload */ + /* address bits 27:4 are payload */ /* these next 24 (58-81) bits become bytes 12-14 of msg */ - /* bits 65:58 land in byte 12 */ - unsigned int replied_to:1;/* sent as 0 by the source to byte 12 */ + unsigned int replied_to:1; /* sent as 0 by the source to + byte 12 */ /* bit 58 */ - unsigned int msg_type:3; /* software type of the message*/ + unsigned int msg_type:3; /* software type of the + message */ /* bits 61:59 */ - unsigned int canceled:1; /* message canceled, resource to be freed*/ + unsigned int canceled:1; /* message canceled, resource + is to be freed*/ /* bit 62 */ - unsigned int payload_1a:1;/* not currently used */ + unsigned int payload_1a:1; /* not currently used */ /* bit 63 */ - unsigned int payload_1b:2;/* not currently used */ + unsigned int payload_1b:2; /* not currently used */ /* bits 65:64 */ /* bits 73:66 land in byte 13 */ - unsigned int payload_1ca:6;/* not currently used */ + unsigned int payload_1ca:6; /* not currently used */ /* bits 71:66 */ - unsigned int payload_1c:2;/* not currently used */ + unsigned int payload_1c:2; /* not currently used */ /* bits 73:72 */ /* bits 81:74 land in byte 14 */ - unsigned int payload_1d:6;/* not currently used */ + unsigned int payload_1d:6; /* not currently used */ /* bits 79:74 */ - unsigned int payload_1e:2;/* not currently used */ + unsigned int payload_1e:2; /* not currently used */ /* bits 81:80 */ - unsigned int rsvd_4:7; /* must be zero */ + unsigned int rsvd_4:7; /* must be zero */ /* bits 88:82 */ - unsigned int sw_ack_flag:1;/* software acknowledge flag */ + unsigned int swack_flag:1; /* software acknowledge flag */ /* bit 89 */ - /* INTD trasactions at destination are to - wait for software acknowledge */ - unsigned int rsvd_5:6; /* must be zero */ + /* INTD trasactions at + destination are to wait for + software acknowledge */ + unsigned int rsvd_5:6; /* must be zero */ /* bits 95:90 */ - unsigned int rsvd_6:5; /* must be zero */ + unsigned int rsvd_6:5; /* must be zero */ /* bits 100:96 */ - unsigned int int_both:1;/* if 1, interrupt both sockets on the uvhub */ + unsigned int int_both:1; /* if 1, interrupt both sockets + on the uvhub */ /* bit 101*/ - unsigned int fairness:3;/* usually zero */ + unsigned int fairness:3; /* usually zero */ /* bits 104:102 */ - unsigned int multilevel:1; /* multi-level multicast format */ + unsigned int multilevel:1; /* multi-level multicast + format */ /* bit 105 */ - /* 0 for TLB: endpoint multi-unicast messages */ - unsigned int chaining:1;/* next descriptor is part of this activation*/ + /* 0 for TLB: endpoint multi-unicast messages */ + unsigned int chaining:1; /* next descriptor is part of + this activation*/ /* bit 106 */ - unsigned int rsvd_7:21; /* must be zero */ + unsigned int rsvd_7:21; /* must be zero */ /* bits 127:107 */ }; -/* see msg_type: */ -#define MSG_NOOP 0 -#define MSG_REGULAR 1 -#define MSG_RETRY 2 - /* * The activation descriptor: * The format of the message to send, plus all accompanying control * Should be 64 bytes */ struct bau_desc { - struct bau_target_uvhubmask distribution; + struct bau_targ_hubmask distribution; /* * message template, consisting of header and payload: */ - struct bau_msg_header header; - struct bau_msg_payload payload; + struct bau_msg_header header; + struct bau_msg_payload payload; }; /* * -payload-- ---------header------ @@ -281,59 +338,51 @@ struct bau_desc { * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17 * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120) * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from - * sw_ack_vector and payload_2) + * swack_vec and payload_2) * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software * Acknowledge Processing) also selects 32 byte (17 bytes usable) payload * operation." */ -struct bau_payload_queue_entry { - unsigned long address; /* signifies a page or all TLB's - of the cpu */ +struct bau_pq_entry { + unsigned long address; /* signifies a page or all TLB's + of the cpu */ /* 64 bits, bytes 0-7 */ - - unsigned short sending_cpu; /* cpu that sent the message */ + unsigned short sending_cpu; /* cpu that sent the message */ /* 16 bits, bytes 8-9 */ - - unsigned short acknowledge_count; /* filled in by destination */ + unsigned short acknowledge_count; /* filled in by destination */ /* 16 bits, bytes 10-11 */ - /* these next 3 bytes come from bits 58-81 of the message header */ - unsigned short replied_to:1; /* sent as 0 by the source */ - unsigned short msg_type:3; /* software message type */ - unsigned short canceled:1; /* sent as 0 by the source */ - unsigned short unused1:3; /* not currently using */ + unsigned short replied_to:1; /* sent as 0 by the source */ + unsigned short msg_type:3; /* software message type */ + unsigned short canceled:1; /* sent as 0 by the source */ + unsigned short unused1:3; /* not currently using */ /* byte 12 */ - - unsigned char unused2a; /* not currently using */ + unsigned char unused2a; /* not currently using */ /* byte 13 */ - unsigned char unused2; /* not currently using */ + unsigned char unused2; /* not currently using */ /* byte 14 */ - - unsigned char sw_ack_vector; /* filled in by the hardware */ + unsigned char swack_vec; /* filled in by the hardware */ /* byte 15 (bits 127:120) */ - - unsigned short sequence; /* message sequence number */ + unsigned short sequence; /* message sequence number */ /* bytes 16-17 */ - unsigned char unused4[2]; /* not currently using bytes 18-19 */ + unsigned char unused4[2]; /* not currently using bytes 18-19 */ /* bytes 18-19 */ - - int number_of_cpus; /* filled in at destination */ + int number_of_cpus; /* filled in at destination */ /* 32 bits, bytes 20-23 (aligned) */ - - unsigned char unused5[8]; /* not using */ + unsigned char unused5[8]; /* not using */ /* bytes 24-31 */ }; struct msg_desc { - struct bau_payload_queue_entry *msg; - int msg_slot; - int sw_ack_slot; - struct bau_payload_queue_entry *va_queue_first; - struct bau_payload_queue_entry *va_queue_last; + struct bau_pq_entry *msg; + int msg_slot; + int swack_slot; + struct bau_pq_entry *queue_first; + struct bau_pq_entry *queue_last; }; struct reset_args { - int sender; + int sender; }; /* @@ -341,112 +390,226 @@ struct reset_args { */ struct ptc_stats { /* sender statistics */ - unsigned long s_giveup; /* number of fall backs to IPI-style flushes */ - unsigned long s_requestor; /* number of shootdown requests */ - unsigned long s_stimeout; /* source side timeouts */ - unsigned long s_dtimeout; /* destination side timeouts */ - unsigned long s_time; /* time spent in sending side */ - unsigned long s_retriesok; /* successful retries */ - unsigned long s_ntargcpu; /* total number of cpu's targeted */ - unsigned long s_ntargself; /* times the sending cpu was targeted */ - unsigned long s_ntarglocals; /* targets of cpus on the local blade */ - unsigned long s_ntargremotes; /* targets of cpus on remote blades */ - unsigned long s_ntarglocaluvhub; /* targets of the local hub */ - unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */ - unsigned long s_ntarguvhub; /* total number of uvhubs targeted */ - unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/ - unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */ - unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */ - unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */ - unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */ - unsigned long s_resets_plug; /* ipi-style resets from plug state */ - unsigned long s_resets_timeout; /* ipi-style resets from timeouts */ - unsigned long s_busy; /* status stayed busy past s/w timer */ - unsigned long s_throttles; /* waits in throttle */ - unsigned long s_retry_messages; /* retry broadcasts */ - unsigned long s_bau_reenabled; /* for bau enable/disable */ - unsigned long s_bau_disabled; /* for bau enable/disable */ + unsigned long s_giveup; /* number of fall backs to + IPI-style flushes */ + unsigned long s_requestor; /* number of shootdown + requests */ + unsigned long s_stimeout; /* source side timeouts */ + unsigned long s_dtimeout; /* destination side timeouts */ + unsigned long s_time; /* time spent in sending side */ + unsigned long s_retriesok; /* successful retries */ + unsigned long s_ntargcpu; /* total number of cpu's + targeted */ + unsigned long s_ntargself; /* times the sending cpu was + targeted */ + unsigned long s_ntarglocals; /* targets of cpus on the local + blade */ + unsigned long s_ntargremotes; /* targets of cpus on remote + blades */ + unsigned long s_ntarglocaluvhub; /* targets of the local hub */ + unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */ + unsigned long s_ntarguvhub; /* total number of uvhubs + targeted */ + unsigned long s_ntarguvhub16; /* number of times target + hubs >= 16*/ + unsigned long s_ntarguvhub8; /* number of times target + hubs >= 8 */ + unsigned long s_ntarguvhub4; /* number of times target + hubs >= 4 */ + unsigned long s_ntarguvhub2; /* number of times target + hubs >= 2 */ + unsigned long s_ntarguvhub1; /* number of times target + hubs == 1 */ + unsigned long s_resets_plug; /* ipi-style resets from plug + state */ + unsigned long s_resets_timeout; /* ipi-style resets from + timeouts */ + unsigned long s_busy; /* status stayed busy past + s/w timer */ + unsigned long s_throttles; /* waits in throttle */ + unsigned long s_retry_messages; /* retry broadcasts */ + unsigned long s_bau_reenabled; /* for bau enable/disable */ + unsigned long s_bau_disabled; /* for bau enable/disable */ /* destination statistics */ - unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ - unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */ - unsigned long d_multmsg; /* interrupts with multiple messages */ - unsigned long d_nomsg; /* interrupts with no message */ - unsigned long d_time; /* time spent on destination side */ - unsigned long d_requestee; /* number of messages processed */ - unsigned long d_retries; /* number of retry messages processed */ - unsigned long d_canceled; /* number of messages canceled by retries */ - unsigned long d_nocanceled; /* retries that found nothing to cancel */ - unsigned long d_resets; /* number of ipi-style requests processed */ - unsigned long d_rcanceled; /* number of messages canceled by resets */ + unsigned long d_alltlb; /* times all tlb's on this + cpu were flushed */ + unsigned long d_onetlb; /* times just one tlb on this + cpu was flushed */ + unsigned long d_multmsg; /* interrupts with multiple + messages */ + unsigned long d_nomsg; /* interrupts with no message */ + unsigned long d_time; /* time spent on destination + side */ + unsigned long d_requestee; /* number of messages + processed */ + unsigned long d_retries; /* number of retry messages + processed */ + unsigned long d_canceled; /* number of messages canceled + by retries */ + unsigned long d_nocanceled; /* retries that found nothing + to cancel */ + unsigned long d_resets; /* number of ipi-style requests + processed */ + unsigned long d_rcanceled; /* number of messages canceled + by resets */ +}; + +struct tunables { + int *tunp; + int deflt; }; struct hub_and_pnode { - short uvhub; - short pnode; + short uvhub; + short pnode; }; + +struct socket_desc { + short num_cpus; + short cpu_number[MAX_CPUS_PER_SOCKET]; +}; + +struct uvhub_desc { + unsigned short socket_mask; + short num_cpus; + short uvhub; + short pnode; + struct socket_desc socket[2]; +}; + /* * one per-cpu; to locate the software tables */ struct bau_control { - struct bau_desc *descriptor_base; - struct bau_payload_queue_entry *va_queue_first; - struct bau_payload_queue_entry *va_queue_last; - struct bau_payload_queue_entry *bau_msg_head; - struct bau_control *uvhub_master; - struct bau_control *socket_master; - struct ptc_stats *statp; - unsigned long timeout_interval; - unsigned long set_bau_on_time; - atomic_t active_descriptor_count; - int plugged_tries; - int timeout_tries; - int ipi_attempts; - int conseccompletes; - int baudisabled; - int set_bau_off; - short cpu; - short osnode; - short uvhub_cpu; - short uvhub; - short cpus_in_socket; - short cpus_in_uvhub; - short partition_base_pnode; - unsigned short message_number; - unsigned short uvhub_quiesce; - short socket_acknowledge_count[DEST_Q_SIZE]; - cycles_t send_message; - spinlock_t uvhub_lock; - spinlock_t queue_lock; + struct bau_desc *descriptor_base; + struct bau_pq_entry *queue_first; + struct bau_pq_entry *queue_last; + struct bau_pq_entry *bau_msg_head; + struct bau_control *uvhub_master; + struct bau_control *socket_master; + struct ptc_stats *statp; + unsigned long timeout_interval; + unsigned long set_bau_on_time; + atomic_t active_descriptor_count; + int plugged_tries; + int timeout_tries; + int ipi_attempts; + int conseccompletes; + int baudisabled; + int set_bau_off; + short cpu; + short osnode; + short uvhub_cpu; + short uvhub; + short cpus_in_socket; + short cpus_in_uvhub; + short partition_base_pnode; + unsigned short message_number; + unsigned short uvhub_quiesce; + short socket_acknowledge_count[DEST_Q_SIZE]; + cycles_t send_message; + spinlock_t uvhub_lock; + spinlock_t queue_lock; /* tunables */ - int max_bau_concurrent; - int max_bau_concurrent_constant; - int plugged_delay; - int plugsb4reset; - int timeoutsb4reset; - int ipi_reset_limit; - int complete_threshold; - int congested_response_us; - int congested_reps; - int congested_period; - cycles_t period_time; - long period_requests; - struct hub_and_pnode *target_hub_and_pnode; + int max_concurr; + int max_concurr_const; + int plugged_delay; + int plugsb4reset; + int timeoutsb4reset; + int ipi_reset_limit; + int complete_threshold; + int cong_response_us; + int cong_reps; + int cong_period; + cycles_t period_time; + long period_requests; + struct hub_and_pnode *thp; }; -static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp) +static unsigned long read_mmr_uv2_status(void) +{ + return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2); +} + +static void write_mmr_data_broadcast(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image); +} + +static void write_mmr_descriptor_base(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, mmr_image); +} + +static void write_mmr_activation(unsigned long index) +{ + write_lmmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index); +} + +static void write_gmmr_activation(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image); +} + +static void write_mmr_payload_first(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image); +} + +static void write_mmr_payload_tail(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, mmr_image); +} + +static void write_mmr_payload_last(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, mmr_image); +} + +static void write_mmr_misc_control(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); +} + +static unsigned long read_mmr_misc_control(int pnode) +{ + return read_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL); +} + +static void write_mmr_sw_ack(unsigned long mr) +{ + uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr); +} + +static unsigned long read_mmr_sw_ack(void) +{ + return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); +} + +static unsigned long read_gmmr_sw_ack(int pnode) +{ + return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); +} + +static void write_mmr_data_config(int pnode, unsigned long mr) +{ + uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr); +} + +static inline int bau_uvhub_isset(int uvhub, struct bau_targ_hubmask *dstp) { return constant_test_bit(uvhub, &dstp->bits[0]); } -static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp) +static inline void bau_uvhub_set(int pnode, struct bau_targ_hubmask *dstp) { __set_bit(pnode, &dstp->bits[0]); } -static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp, +static inline void bau_uvhubs_clear(struct bau_targ_hubmask *dstp, int nbits) { bitmap_zero(&dstp->bits[0], nbits); } -static inline int bau_uvhub_weight(struct bau_target_uvhubmask *dstp) +static inline int bau_uvhub_weight(struct bau_targ_hubmask *dstp) { return bitmap_weight((unsigned long *)&dstp->bits[0], UV_DISTRIBUTION_SIZE); @@ -457,9 +620,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits) bitmap_zero(&dstp->bits, nbits); } -#define cpubit_isset(cpu, bau_local_cpumask) \ - test_bit((cpu), (bau_local_cpumask).bits) - extern void uv_bau_message_intr1(void); extern void uv_bau_timeout_intr1(void); @@ -467,7 +627,7 @@ struct atomic_short { short counter; }; -/** +/* * atomic_read_short - read a short atomic variable * @v: pointer of type atomic_short * @@ -478,14 +638,14 @@ static inline int atomic_read_short(const struct atomic_short *v) return v->counter; } -/** - * atomic_add_short_return - add and return a short int +/* + * atom_asr - add and return a short int * @i: short value to add * @v: pointer of type atomic_short * * Atomically adds @i to @v and returns @i + @v */ -static inline int atomic_add_short_return(short i, struct atomic_short *v) +static inline int atom_asr(short i, struct atomic_short *v) { short __i = i; asm volatile(LOCK_PREFIX "xaddw %0, %1" @@ -494,4 +654,26 @@ static inline int atomic_add_short_return(short i, struct atomic_short *v) return i + __i; } +/* + * conditionally add 1 to *v, unless *v is >= u + * return 0 if we cannot add 1 to *v because it is >= u + * return 1 if we can add 1 to *v because it is < u + * the add is atomic + * + * This is close to atomic_add_unless(), but this allows the 'u' value + * to be lowered below the current 'v'. atomic_add_unless can only stop + * on equal. + */ +static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) +{ + spin_lock(lock); + if (atomic_read(v) >= u) { + spin_unlock(lock); + return 0; + } + atomic_inc(v); + spin_unlock(lock); + return 1; +} + #endif /* _ASM_X86_UV_UV_BAU_H */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 4298002..f26544a 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -77,8 +77,9 @@ * * 1111110000000000 * 5432109876543210 - * pppppppppplc0cch Nehalem-EX - * ppppppppplcc0cch Westmere-EX + * pppppppppplc0cch Nehalem-EX (12 bits in hdw reg) + * ppppppppplcc0cch Westmere-EX (12 bits in hdw reg) + * pppppppppppcccch SandyBridge (15 bits in hdw reg) * sssssssssss * * p = pnode bits @@ -87,7 +88,7 @@ * h = hyperthread * s = bits that are in the SOCKET_ID CSR * - * Note: Processor only supports 12 bits in the APICID register. The ACPI + * Note: Processor may support fewer bits in the APICID register. The ACPI * tables hold all 16 bits. Software needs to be aware of this. * * Unless otherwise specified, all references to APICID refer to @@ -138,6 +139,8 @@ struct uv_hub_info_s { unsigned long global_mmr_base; unsigned long gpa_mask; unsigned int gnode_extra; + unsigned char hub_revision; + unsigned char apic_pnode_shift; unsigned long gnode_upper; unsigned long lowmem_remap_top; unsigned long lowmem_remap_base; @@ -149,13 +152,31 @@ struct uv_hub_info_s { unsigned char m_val; unsigned char n_val; struct uv_scir_s scir; - unsigned char apic_pnode_shift; }; DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); #define uv_hub_info (&__get_cpu_var(__uv_hub_info)) #define uv_cpu_hub_info(cpu) (&per_cpu(__uv_hub_info, cpu)) +/* + * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2 + * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE. + * This is a software convention - NOT the hardware revision numbers in + * the hub chip. + */ +#define UV1_HUB_REVISION_BASE 1 +#define UV2_HUB_REVISION_BASE 3 + +static inline int is_uv1_hub(void) +{ + return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE; +} + +static inline int is_uv2_hub(void) +{ + return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; +} + union uvh_apicid { unsigned long v; struct uvh_apicid_s { @@ -180,11 +201,25 @@ union uvh_apicid { #define UV_PNODE_TO_GNODE(p) ((p) |uv_hub_info->gnode_extra) #define UV_PNODE_TO_NASID(p) (UV_PNODE_TO_GNODE(p) << 1) -#define UV_LOCAL_MMR_BASE 0xf4000000UL -#define UV_GLOBAL_MMR32_BASE 0xf8000000UL +#define UV1_LOCAL_MMR_BASE 0xf4000000UL +#define UV1_GLOBAL_MMR32_BASE 0xf8000000UL +#define UV1_LOCAL_MMR_SIZE (64UL * 1024 * 1024) +#define UV1_GLOBAL_MMR32_SIZE (64UL * 1024 * 1024) + +#define UV2_LOCAL_MMR_BASE 0xfa000000UL +#define UV2_GLOBAL_MMR32_BASE 0xfc000000UL +#define UV2_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV2_GLOBAL_MMR32_SIZE (32UL * 1024 * 1024) + +#define UV_LOCAL_MMR_BASE (is_uv1_hub() ? UV1_LOCAL_MMR_BASE \ + : UV2_LOCAL_MMR_BASE) +#define UV_GLOBAL_MMR32_BASE (is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE \ + : UV2_GLOBAL_MMR32_BASE) +#define UV_LOCAL_MMR_SIZE (is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \ + UV2_LOCAL_MMR_SIZE) +#define UV_GLOBAL_MMR32_SIZE (is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\ + UV2_GLOBAL_MMR32_SIZE) #define UV_GLOBAL_MMR64_BASE (uv_hub_info->global_mmr_base) -#define UV_LOCAL_MMR_SIZE (64UL * 1024 * 1024) -#define UV_GLOBAL_MMR32_SIZE (64UL * 1024 * 1024) #define UV_GLOBAL_GRU_MMR_BASE 0x4000000 @@ -301,6 +336,17 @@ static inline int uv_apicid_to_pnode(int apicid) } /* + * Convert an apicid to the socket number on the blade + */ +static inline int uv_apicid_to_socket(int apicid) +{ + if (is_uv1_hub()) + return (apicid >> (uv_hub_info->apic_pnode_shift - 1)) & 1; + else + return 0; +} + +/* * Access global MMRs using the low memory MMR32 space. This region supports * faster MMR access but not all MMRs are accessible in this space. */ @@ -519,14 +565,13 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) /* * Get the minimum revision number of the hub chips within the partition. - * 1 - initial rev 1.0 silicon - * 2 - rev 2.0 production silicon + * 1 - UV1 rev 1.0 initial silicon + * 2 - UV1 rev 2.0 production silicon + * 3 - UV2 rev 1.0 initial silicon */ static inline int uv_get_min_hub_revision_id(void) { - extern int uv_min_hub_revision_id; - - return uv_min_hub_revision_id; + return uv_hub_info->hub_revision; } #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index f5bb64a..4be52c8 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -11,13 +11,64 @@ #ifndef _ASM_X86_UV_UV_MMRS_H #define _ASM_X86_UV_UV_MMRS_H +/* + * This file contains MMR definitions for both UV1 & UV2 hubs. + * + * In general, MMR addresses and structures are identical on both hubs. + * These MMRs are identified as: + * #define UVH_xxx <address> + * union uvh_xxx { + * unsigned long v; + * struct uvh_int_cmpd_s { + * } s; + * }; + * + * If the MMR exists on both hub type but has different addresses or + * contents, the MMR definition is similar to: + * #define UV1H_xxx <uv1 address> + * #define UV2H_xxx <uv2address> + * #define UVH_xxx (is_uv1_hub() ? UV1H_xxx : UV2H_xxx) + * union uvh_xxx { + * unsigned long v; + * struct uv1h_int_cmpd_s { (Common fields only) + * } s; + * struct uv1h_int_cmpd_s { (Full UV1 definition) + * } s1; + * struct uv2h_int_cmpd_s { (Full UV2 definition) + * } s2; + * }; + * + * Only essential difference are enumerated. For example, if the address is + * the same for both UV1 & UV2, only a single #define is generated. Likewise, + * if the contents is the same for both hubs, only the "s" structure is + * generated. + * + * If the MMR exists on ONLY 1 type of hub, no generic definition is + * generated: + * #define UVnH_xxx <uvn address> + * union uvnh_xxx { + * unsigned long v; + * struct uvh_int_cmpd_s { + * } sn; + * }; + */ + #define UV_MMR_ENABLE (1UL << 63) +#define UV1_HUB_PART_NUMBER 0x88a5 +#define UV2_HUB_PART_NUMBER 0x8eb8 + +/* Compat: if this #define is present, UV headers support UV2 */ +#define UV2_HUB_IS_SUPPORTED 1 + +/* KABI compat: if this #define is present, KABI hacks are present */ +#define UV2_HUB_KABI_HACKS 1 + /* ========================================================================= */ /* UVH_BAU_DATA_BROADCAST */ /* ========================================================================= */ #define UVH_BAU_DATA_BROADCAST 0x61688UL -#define UVH_BAU_DATA_BROADCAST_32 0x0440 +#define UVH_BAU_DATA_BROADCAST_32 0x440 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL @@ -34,7 +85,7 @@ union uvh_bau_data_broadcast_u { /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ #define UVH_BAU_DATA_CONFIG 0x61680UL -#define UVH_BAU_DATA_CONFIG_32 0x0438 +#define UVH_BAU_DATA_CONFIG_32 0x438 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0 #define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL @@ -73,125 +124,245 @@ union uvh_bau_data_config_u { /* UVH_EVENT_OCCURRED0 */ /* ========================================================================= */ #define UVH_EVENT_OCCURRED0 0x70000UL -#define UVH_EVENT_OCCURRED0_32 0x005e8 - -#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0 -#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL -#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1 -#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL -#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2 -#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL -#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3 -#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL -#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4 -#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL -#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5 -#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL -#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6 -#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL -#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7 -#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL -#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8 -#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL -#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9 -#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL -#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10 -#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL -#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 -#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL -#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12 -#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL -#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13 -#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL -#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14 -#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL -#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15 -#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL -#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16 -#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL -#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17 -#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL -#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18 -#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL -#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19 -#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL -#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20 -#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL -#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21 -#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL -#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22 -#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38 -#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL -#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39 -#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL -#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40 -#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL -#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41 -#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL -#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42 -#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL -#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43 -#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL -#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44 -#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL -#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45 -#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL -#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46 -#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL -#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47 -#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL -#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48 -#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL -#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49 -#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL -#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50 -#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL -#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51 -#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL -#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52 -#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL -#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53 -#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL -#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54 -#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL -#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55 -#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL -#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56 -#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL +#define UVH_EVENT_OCCURRED0_32 0x5e8 + +#define UV1H_EVENT_OCCURRED0_LB_HCERR_SHFT 0 +#define UV1H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL +#define UV1H_EVENT_OCCURRED0_GR0_HCERR_SHFT 1 +#define UV1H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL +#define UV1H_EVENT_OCCURRED0_GR1_HCERR_SHFT 2 +#define UV1H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL +#define UV1H_EVENT_OCCURRED0_LH_HCERR_SHFT 3 +#define UV1H_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL +#define UV1H_EVENT_OCCURRED0_RH_HCERR_SHFT 4 +#define UV1H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL +#define UV1H_EVENT_OCCURRED0_XN_HCERR_SHFT 5 +#define UV1H_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL +#define UV1H_EVENT_OCCURRED0_SI_HCERR_SHFT 6 +#define UV1H_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL +#define UV1H_EVENT_OCCURRED0_LB_AOERR0_SHFT 7 +#define UV1H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL +#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8 +#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL +#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9 +#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL +#define UV1H_EVENT_OCCURRED0_LH_AOERR0_SHFT 10 +#define UV1H_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL +#define UV1H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 +#define UV1H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL +#define UV1H_EVENT_OCCURRED0_XN_AOERR0_SHFT 12 +#define UV1H_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL +#define UV1H_EVENT_OCCURRED0_SI_AOERR0_SHFT 13 +#define UV1H_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL +#define UV1H_EVENT_OCCURRED0_LB_AOERR1_SHFT 14 +#define UV1H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL +#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15 +#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL +#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16 +#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL +#define UV1H_EVENT_OCCURRED0_LH_AOERR1_SHFT 17 +#define UV1H_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL +#define UV1H_EVENT_OCCURRED0_RH_AOERR1_SHFT 18 +#define UV1H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL +#define UV1H_EVENT_OCCURRED0_XN_AOERR1_SHFT 19 +#define UV1H_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL +#define UV1H_EVENT_OCCURRED0_SI_AOERR1_SHFT 20 +#define UV1H_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL +#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21 +#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL +#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22 +#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38 +#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL +#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39 +#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL +#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40 +#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL +#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41 +#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL +#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42 +#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL +#define UV1H_EVENT_OCCURRED0_LTC_INT_SHFT 43 +#define UV1H_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL +#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44 +#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL +#define UV1H_EVENT_OCCURRED0_IPI_INT_SHFT 45 +#define UV1H_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL +#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46 +#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL +#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47 +#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL +#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48 +#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL +#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49 +#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL +#define UV1H_EVENT_OCCURRED0_PROFILE_INT_SHFT 50 +#define UV1H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL +#define UV1H_EVENT_OCCURRED0_RTC0_SHFT 51 +#define UV1H_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL +#define UV1H_EVENT_OCCURRED0_RTC1_SHFT 52 +#define UV1H_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL +#define UV1H_EVENT_OCCURRED0_RTC2_SHFT 53 +#define UV1H_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL +#define UV1H_EVENT_OCCURRED0_RTC3_SHFT 54 +#define UV1H_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL +#define UV1H_EVENT_OCCURRED0_BAU_DATA_SHFT 55 +#define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL +#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56 +#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL + +#define UV2H_EVENT_OCCURRED0_LB_HCERR_SHFT 0 +#define UV2H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL +#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1 +#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL +#define UV2H_EVENT_OCCURRED0_RH_HCERR_SHFT 2 +#define UV2H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL +#define UV2H_EVENT_OCCURRED0_LH0_HCERR_SHFT 3 +#define UV2H_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL +#define UV2H_EVENT_OCCURRED0_LH1_HCERR_SHFT 4 +#define UV2H_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL +#define UV2H_EVENT_OCCURRED0_GR0_HCERR_SHFT 5 +#define UV2H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL +#define UV2H_EVENT_OCCURRED0_GR1_HCERR_SHFT 6 +#define UV2H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL +#define UV2H_EVENT_OCCURRED0_NI0_HCERR_SHFT 7 +#define UV2H_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL +#define UV2H_EVENT_OCCURRED0_NI1_HCERR_SHFT 8 +#define UV2H_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL +#define UV2H_EVENT_OCCURRED0_LB_AOERR0_SHFT 9 +#define UV2H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL +#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10 +#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL +#define UV2H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 +#define UV2H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL +#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12 +#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL +#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13 +#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL +#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14 +#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL +#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15 +#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL +#define UV2H_EVENT_OCCURRED0_XB_AOERR0_SHFT 16 +#define UV2H_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL +#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17 +#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL +#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18 +#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL +#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19 +#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL +#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20 +#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL +#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21 +#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL +#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22 +#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL +#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23 +#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL +#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24 +#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL +#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25 +#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL +#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26 +#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL +#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27 +#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL +#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28 +#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL +#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29 +#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL +#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30 +#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL +#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31 +#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL +#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48 +#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL +#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49 +#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL +#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50 +#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL +#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51 +#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL +#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52 +#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL +#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53 +#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL +#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58 +#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL + union uvh_event_occurred0_u { unsigned long v; - struct uvh_event_occurred0_s { + struct uv1h_event_occurred0_s { unsigned long lb_hcerr : 1; /* RW, W1C */ unsigned long gr0_hcerr : 1; /* RW, W1C */ unsigned long gr1_hcerr : 1; /* RW, W1C */ @@ -250,14 +421,76 @@ union uvh_event_occurred0_u { unsigned long bau_data : 1; /* RW, W1C */ unsigned long power_management_req : 1; /* RW, W1C */ unsigned long rsvd_57_63 : 7; /* */ - } s; + } s1; + struct uv2h_event_occurred0_s { + unsigned long lb_hcerr : 1; /* RW */ + unsigned long qp_hcerr : 1; /* RW */ + unsigned long rh_hcerr : 1; /* RW */ + unsigned long lh0_hcerr : 1; /* RW */ + unsigned long lh1_hcerr : 1; /* RW */ + unsigned long gr0_hcerr : 1; /* RW */ + unsigned long gr1_hcerr : 1; /* RW */ + unsigned long ni0_hcerr : 1; /* RW */ + unsigned long ni1_hcerr : 1; /* RW */ + unsigned long lb_aoerr0 : 1; /* RW */ + unsigned long qp_aoerr0 : 1; /* RW */ + unsigned long rh_aoerr0 : 1; /* RW */ + unsigned long lh0_aoerr0 : 1; /* RW */ + unsigned long lh1_aoerr0 : 1; /* RW */ + unsigned long gr0_aoerr0 : 1; /* RW */ + unsigned long gr1_aoerr0 : 1; /* RW */ + unsigned long xb_aoerr0 : 1; /* RW */ + unsigned long rt_aoerr0 : 1; /* RW */ + unsigned long ni0_aoerr0 : 1; /* RW */ + unsigned long ni1_aoerr0 : 1; /* RW */ + unsigned long lb_aoerr1 : 1; /* RW */ + unsigned long qp_aoerr1 : 1; /* RW */ + unsigned long rh_aoerr1 : 1; /* RW */ + unsigned long lh0_aoerr1 : 1; /* RW */ + unsigned long lh1_aoerr1 : 1; /* RW */ + unsigned long gr0_aoerr1 : 1; /* RW */ + unsigned long gr1_aoerr1 : 1; /* RW */ + unsigned long xb_aoerr1 : 1; /* RW */ + unsigned long rt_aoerr1 : 1; /* RW */ + unsigned long ni0_aoerr1 : 1; /* RW */ + unsigned long ni1_aoerr1 : 1; /* RW */ + unsigned long system_shutdown_int : 1; /* RW */ + unsigned long lb_irq_int_0 : 1; /* RW */ + unsigned long lb_irq_int_1 : 1; /* RW */ + unsigned long lb_irq_int_2 : 1; /* RW */ + unsigned long lb_irq_int_3 : 1; /* RW */ + unsigned long lb_irq_int_4 : 1; /* RW */ + unsigned long lb_irq_int_5 : 1; /* RW */ + unsigned long lb_irq_int_6 : 1; /* RW */ + unsigned long lb_irq_int_7 : 1; /* RW */ + unsigned long lb_irq_int_8 : 1; /* RW */ + unsigned long lb_irq_int_9 : 1; /* RW */ + unsigned long lb_irq_int_10 : 1; /* RW */ + unsigned long lb_irq_int_11 : 1; /* RW */ + unsigned long lb_irq_int_12 : 1; /* RW */ + unsigned long lb_irq_int_13 : 1; /* RW */ + unsigned long lb_irq_int_14 : 1; /* RW */ + unsigned long lb_irq_int_15 : 1; /* RW */ + unsigned long l1_nmi_int : 1; /* RW */ + unsigned long stop_clock : 1; /* RW */ + unsigned long asic_to_l1 : 1; /* RW */ + unsigned long l1_to_asic : 1; /* RW */ + unsigned long la_seq_trigger : 1; /* RW */ + unsigned long ipi_int : 1; /* RW */ + unsigned long extio_int0 : 1; /* RW */ + unsigned long extio_int1 : 1; /* RW */ + unsigned long extio_int2 : 1; /* RW */ + unsigned long extio_int3 : 1; /* RW */ + unsigned long profile_int : 1; /* RW */ + unsigned long rsvd_59_63 : 5; /* */ + } s2; }; /* ========================================================================= */ /* UVH_EVENT_OCCURRED0_ALIAS */ /* ========================================================================= */ #define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL -#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0 +#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0 /* ========================================================================= */ /* UVH_GR0_TLB_INT0_CONFIG */ @@ -432,8 +665,16 @@ union uvh_int_cmpb_u { /* ========================================================================= */ #define UVH_INT_CMPC 0x22100UL -#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0 -#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL +#define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT 0 +#define UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT 0 +#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT (is_uv1_hub() ? \ + UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT : \ + UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT) +#define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK 0xffffffffffffffUL +#define UV2H_INT_CMPC_REAL_TIME_CMPC_MASK 0xffffffffffffffUL +#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK (is_uv1_hub() ? \ + UV1H_INT_CMPC_REAL_TIME_CMPC_MASK : \ + UV2H_INT_CMPC_REAL_TIME_CMPC_MASK) union uvh_int_cmpc_u { unsigned long v; @@ -448,8 +689,16 @@ union uvh_int_cmpc_u { /* ========================================================================= */ #define UVH_INT_CMPD 0x22180UL -#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0 -#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL +#define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT 0 +#define UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT 0 +#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT (is_uv1_hub() ? \ + UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT : \ + UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT) +#define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK 0xffffffffffffffUL +#define UV2H_INT_CMPD_REAL_TIME_CMPD_MASK 0xffffffffffffffUL +#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK (is_uv1_hub() ? \ + UV1H_INT_CMPD_REAL_TIME_CMPD_MASK : \ + UV2H_INT_CMPD_REAL_TIME_CMPD_MASK) union uvh_int_cmpd_u { unsigned long v; @@ -463,7 +712,7 @@ union uvh_int_cmpd_u { /* UVH_IPI_INT */ /* ========================================================================= */ #define UVH_IPI_INT 0x60500UL -#define UVH_IPI_INT_32 0x0348 +#define UVH_IPI_INT_32 0x348 #define UVH_IPI_INT_VECTOR_SHFT 0 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL @@ -493,7 +742,7 @@ union uvh_ipi_int_u { /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST */ /* ========================================================================= */ #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL @@ -515,7 +764,7 @@ union uvh_lb_bau_intd_payload_queue_first_u { /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST */ /* ========================================================================= */ #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL @@ -533,7 +782,7 @@ union uvh_lb_bau_intd_payload_queue_last_u { /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL */ /* ========================================================================= */ #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL @@ -551,7 +800,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u { /* UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE */ /* ========================================================================= */ #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68 +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL @@ -585,6 +834,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u { #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL + union uvh_lb_bau_intd_software_acknowledge_u { unsigned long v; struct uvh_lb_bau_intd_software_acknowledge_s { @@ -612,13 +862,13 @@ union uvh_lb_bau_intd_software_acknowledge_u { /* UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS */ /* ========================================================================= */ #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70 +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70 /* ========================================================================= */ /* UVH_LB_BAU_MISC_CONTROL */ /* ========================================================================= */ #define UVH_LB_BAU_MISC_CONTROL 0x320170UL -#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10 +#define UVH_LB_BAU_MISC_CONTROL_32 0xa10 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL @@ -628,8 +878,8 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL -#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11 -#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL #define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 @@ -650,8 +900,86 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL -#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48 -#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL + +#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 +#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL +#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 +#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL +#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 +#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL +#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 +#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL +#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 +#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL +#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16 +#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20 +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL +#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21 +#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL +#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22 +#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL +#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23 +#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL +#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 +#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL +#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 +#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UV1H_LB_BAU_MISC_CONTROL_FUN_SHFT 48 +#define UV1H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL + +#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 +#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL +#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 +#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL +#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 +#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL +#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 +#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL +#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 +#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL +#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16 +#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL +#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21 +#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL +#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22 +#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23 +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL +#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 +#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL +#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 +#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL +#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30 +#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31 +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33 +#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34 +#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL +#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35 +#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL +#define UV2H_LB_BAU_MISC_CONTROL_FUN_SHFT 48 +#define UV2H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL union uvh_lb_bau_misc_control_u { unsigned long v; @@ -660,7 +988,25 @@ union uvh_lb_bau_misc_control_u { unsigned long apic_mode : 1; /* RW */ unsigned long force_broadcast : 1; /* RW */ unsigned long force_lock_nop : 1; /* RW */ - unsigned long csi_agent_presence_vector : 3; /* RW */ + unsigned long qpi_agent_presence_vector : 3; /* RW */ + unsigned long descriptor_fetch_mode : 1; /* RW */ + unsigned long enable_intd_soft_ack_mode : 1; /* RW */ + unsigned long intd_soft_ack_timeout_period : 4; /* RW */ + unsigned long enable_dual_mapping_mode : 1; /* RW */ + unsigned long vga_io_port_decode_enable : 1; /* RW */ + unsigned long vga_io_port_16_bit_decode : 1; /* RW */ + unsigned long suppress_dest_registration : 1; /* RW */ + unsigned long programmed_initial_priority : 3; /* RW */ + unsigned long use_incoming_priority : 1; /* RW */ + unsigned long enable_programmed_initial_priority : 1; /* RW */ + unsigned long rsvd_29_63 : 35; + } s; + struct uv1h_lb_bau_misc_control_s { + unsigned long rejection_delay : 8; /* RW */ + unsigned long apic_mode : 1; /* RW */ + unsigned long force_broadcast : 1; /* RW */ + unsigned long force_lock_nop : 1; /* RW */ + unsigned long qpi_agent_presence_vector : 3; /* RW */ unsigned long descriptor_fetch_mode : 1; /* RW */ unsigned long enable_intd_soft_ack_mode : 1; /* RW */ unsigned long intd_soft_ack_timeout_period : 4; /* RW */ @@ -673,14 +1019,40 @@ union uvh_lb_bau_misc_control_u { unsigned long enable_programmed_initial_priority : 1; /* RW */ unsigned long rsvd_29_47 : 19; /* */ unsigned long fun : 16; /* RW */ - } s; + } s1; + struct uv2h_lb_bau_misc_control_s { + unsigned long rejection_delay : 8; /* RW */ + unsigned long apic_mode : 1; /* RW */ + unsigned long force_broadcast : 1; /* RW */ + unsigned long force_lock_nop : 1; /* RW */ + unsigned long qpi_agent_presence_vector : 3; /* RW */ + unsigned long descriptor_fetch_mode : 1; /* RW */ + unsigned long enable_intd_soft_ack_mode : 1; /* RW */ + unsigned long intd_soft_ack_timeout_period : 4; /* RW */ + unsigned long enable_dual_mapping_mode : 1; /* RW */ + unsigned long vga_io_port_decode_enable : 1; /* RW */ + unsigned long vga_io_port_16_bit_decode : 1; /* RW */ + unsigned long suppress_dest_registration : 1; /* RW */ + unsigned long programmed_initial_priority : 3; /* RW */ + unsigned long use_incoming_priority : 1; /* RW */ + unsigned long enable_programmed_initial_priority : 1; /* RW */ + unsigned long enable_automatic_apic_mode_selection : 1; /* RW */ + unsigned long apic_mode_status : 1; /* RO */ + unsigned long suppress_interrupts_to_self : 1; /* RW */ + unsigned long enable_lock_based_system_flush : 1; /* RW */ + unsigned long enable_extended_sb_status : 1; /* RW */ + unsigned long suppress_int_prio_udt_to_self : 1; /* RW */ + unsigned long use_legacy_descriptor_formats : 1; /* RW */ + unsigned long rsvd_36_47 : 12; /* */ + unsigned long fun : 16; /* RW */ + } s2; }; /* ========================================================================= */ /* UVH_LB_BAU_SB_ACTIVATION_CONTROL */ /* ========================================================================= */ #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL -#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8 +#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL @@ -703,7 +1075,7 @@ union uvh_lb_bau_sb_activation_control_u { /* UVH_LB_BAU_SB_ACTIVATION_STATUS_0 */ /* ========================================================================= */ #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0 +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL @@ -719,7 +1091,7 @@ union uvh_lb_bau_sb_activation_status_0_u { /* UVH_LB_BAU_SB_ACTIVATION_STATUS_1 */ /* ========================================================================= */ #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8 +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL @@ -735,7 +1107,7 @@ union uvh_lb_bau_sb_activation_status_1_u { /* UVH_LB_BAU_SB_DESCRIPTOR_BASE */ /* ========================================================================= */ #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL -#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0 +#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL @@ -754,23 +1126,6 @@ union uvh_lb_bau_sb_descriptor_base_u { }; /* ========================================================================= */ -/* UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK */ -/* ========================================================================= */ -#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL -#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0 - -#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0 -#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL - -union uvh_lb_target_physical_apic_id_mask_u { - unsigned long v; - struct uvh_lb_target_physical_apic_id_mask_s { - unsigned long bit_enables : 32; /* RW */ - unsigned long rsvd_32_63 : 32; /* */ - } s; -}; - -/* ========================================================================= */ /* UVH_NODE_ID */ /* ========================================================================= */ #define UVH_NODE_ID 0x0UL @@ -785,10 +1140,36 @@ union uvh_lb_target_physical_apic_id_mask_u { #define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL #define UVH_NODE_ID_NODE_ID_SHFT 32 #define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL -#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48 -#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL -#define UVH_NODE_ID_NI_PORT_SHFT 56 -#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL + +#define UV1H_NODE_ID_FORCE1_SHFT 0 +#define UV1H_NODE_ID_FORCE1_MASK 0x0000000000000001UL +#define UV1H_NODE_ID_MANUFACTURER_SHFT 1 +#define UV1H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL +#define UV1H_NODE_ID_PART_NUMBER_SHFT 12 +#define UV1H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL +#define UV1H_NODE_ID_REVISION_SHFT 28 +#define UV1H_NODE_ID_REVISION_MASK 0x00000000f0000000UL +#define UV1H_NODE_ID_NODE_ID_SHFT 32 +#define UV1H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL +#define UV1H_NODE_ID_NODES_PER_BIT_SHFT 48 +#define UV1H_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL +#define UV1H_NODE_ID_NI_PORT_SHFT 56 +#define UV1H_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL + +#define UV2H_NODE_ID_FORCE1_SHFT 0 +#define UV2H_NODE_ID_FORCE1_MASK 0x0000000000000001UL +#define UV2H_NODE_ID_MANUFACTURER_SHFT 1 +#define UV2H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL +#define UV2H_NODE_ID_PART_NUMBER_SHFT 12 +#define UV2H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL +#define UV2H_NODE_ID_REVISION_SHFT 28 +#define UV2H_NODE_ID_REVISION_MASK 0x00000000f0000000UL +#define UV2H_NODE_ID_NODE_ID_SHFT 32 +#define UV2H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL +#define UV2H_NODE_ID_NODES_PER_BIT_SHFT 50 +#define UV2H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL +#define UV2H_NODE_ID_NI_PORT_SHFT 57 +#define UV2H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL union uvh_node_id_u { unsigned long v; @@ -798,12 +1179,31 @@ union uvh_node_id_u { unsigned long part_number : 16; /* RO */ unsigned long revision : 4; /* RO */ unsigned long node_id : 15; /* RW */ + unsigned long rsvd_47_63 : 17; + } s; + struct uv1h_node_id_s { + unsigned long force1 : 1; /* RO */ + unsigned long manufacturer : 11; /* RO */ + unsigned long part_number : 16; /* RO */ + unsigned long revision : 4; /* RO */ + unsigned long node_id : 15; /* RW */ unsigned long rsvd_47 : 1; /* */ unsigned long nodes_per_bit : 7; /* RW */ unsigned long rsvd_55 : 1; /* */ unsigned long ni_port : 4; /* RO */ unsigned long rsvd_60_63 : 4; /* */ - } s; + } s1; + struct uv2h_node_id_s { + unsigned long force1 : 1; /* RO */ + unsigned long manufacturer : 11; /* RO */ + unsigned long part_number : 16; /* RO */ + unsigned long revision : 4; /* RO */ + unsigned long node_id : 15; /* RW */ + unsigned long rsvd_47_49 : 3; /* */ + unsigned long nodes_per_bit : 7; /* RO */ + unsigned long ni_port : 5; /* RO */ + unsigned long rsvd_62_63 : 2; /* */ + } s2; }; /* ========================================================================= */ @@ -954,18 +1354,38 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u { #define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL #define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL -#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12 -#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL + +#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 +#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL +#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 +#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL +#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12 +#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL + +#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 +#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL +#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 +#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL union uvh_rh_gam_config_mmr_u { unsigned long v; struct uvh_rh_gam_config_mmr_s { unsigned long m_skt : 6; /* RW */ unsigned long n_skt : 4; /* RW */ + unsigned long rsvd_10_63 : 54; + } s; + struct uv1h_rh_gam_config_mmr_s { + unsigned long m_skt : 6; /* RW */ + unsigned long n_skt : 4; /* RW */ unsigned long rsvd_10_11: 2; /* */ unsigned long mmiol_cfg : 1; /* RW */ unsigned long rsvd_13_63: 51; /* */ - } s; + } s1; + struct uv2h_rh_gam_config_mmr_s { + unsigned long m_skt : 6; /* RW */ + unsigned long n_skt : 4; /* RW */ + unsigned long rsvd_10_63: 54; /* */ + } s2; }; /* ========================================================================= */ @@ -975,25 +1395,49 @@ union uvh_rh_gam_config_mmr_u { #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48 -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48 +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL union uvh_rh_gam_gru_overlay_config_mmr_u { unsigned long v; struct uvh_rh_gam_gru_overlay_config_mmr_s { unsigned long rsvd_0_27: 28; /* */ unsigned long base : 18; /* RW */ + unsigned long rsvd_46_62 : 17; + unsigned long enable : 1; /* RW */ + } s; + struct uv1h_rh_gam_gru_overlay_config_mmr_s { + unsigned long rsvd_0_27: 28; /* */ + unsigned long base : 18; /* RW */ unsigned long rsvd_46_47: 2; /* */ unsigned long gr4 : 1; /* RW */ unsigned long rsvd_49_51: 3; /* */ unsigned long n_gru : 4; /* RW */ unsigned long rsvd_56_62: 7; /* */ unsigned long enable : 1; /* RW */ - } s; + } s1; + struct uv2h_rh_gam_gru_overlay_config_mmr_s { + unsigned long rsvd_0_27: 28; /* */ + unsigned long base : 18; /* RW */ + unsigned long rsvd_46_51: 6; /* */ + unsigned long n_gru : 4; /* RW */ + unsigned long rsvd_56_62: 7; /* */ + unsigned long enable : 1; /* RW */ + } s2; }; /* ========================================================================= */ @@ -1001,25 +1445,42 @@ union uvh_rh_gam_gru_overlay_config_mmr_u { /* ========================================================================= */ #define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30 -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46 -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52 -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30 +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46 +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52 +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 27 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff8000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL union uvh_rh_gam_mmioh_overlay_config_mmr_u { unsigned long v; - struct uvh_rh_gam_mmioh_overlay_config_mmr_s { + struct uv1h_rh_gam_mmioh_overlay_config_mmr_s { unsigned long rsvd_0_29: 30; /* */ unsigned long base : 16; /* RW */ unsigned long m_io : 6; /* RW */ unsigned long n_io : 4; /* RW */ unsigned long rsvd_56_62: 7; /* */ unsigned long enable : 1; /* RW */ - } s; + } s1; + struct uv2h_rh_gam_mmioh_overlay_config_mmr_s { + unsigned long rsvd_0_26: 27; /* */ + unsigned long base : 19; /* RW */ + unsigned long m_io : 6; /* RW */ + unsigned long n_io : 4; /* RW */ + unsigned long rsvd_56_62: 7; /* */ + unsigned long enable : 1; /* RW */ + } s2; }; /* ========================================================================= */ @@ -1029,20 +1490,40 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u { #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL -#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46 -#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL -#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 -#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46 +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + +#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 +#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL +#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL union uvh_rh_gam_mmr_overlay_config_mmr_u { unsigned long v; struct uvh_rh_gam_mmr_overlay_config_mmr_s { unsigned long rsvd_0_25: 26; /* */ unsigned long base : 20; /* RW */ + unsigned long rsvd_46_62 : 17; + unsigned long enable : 1; /* RW */ + } s; + struct uv1h_rh_gam_mmr_overlay_config_mmr_s { + unsigned long rsvd_0_25: 26; /* */ + unsigned long base : 20; /* RW */ unsigned long dual_hub : 1; /* RW */ unsigned long rsvd_47_62: 16; /* */ unsigned long enable : 1; /* RW */ - } s; + } s1; + struct uv2h_rh_gam_mmr_overlay_config_mmr_s { + unsigned long rsvd_0_25: 26; /* */ + unsigned long base : 20; /* RW */ + unsigned long rsvd_46_62: 17; /* */ + unsigned long enable : 1; /* RW */ + } s2; }; /* ========================================================================= */ @@ -1103,10 +1584,11 @@ union uvh_rtc1_int_config_u { /* UVH_SCRATCH5 */ /* ========================================================================= */ #define UVH_SCRATCH5 0x2d0200UL -#define UVH_SCRATCH5_32 0x00778 +#define UVH_SCRATCH5_32 0x778 #define UVH_SCRATCH5_SCRATCH5_SHFT 0 #define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + union uvh_scratch5_u { unsigned long v; struct uvh_scratch5_s { @@ -1114,4 +1596,154 @@ union uvh_scratch5_u { } s; }; +/* ========================================================================= */ +/* UV2H_EVENT_OCCURRED2 */ +/* ========================================================================= */ +#define UV2H_EVENT_OCCURRED2 0x70100UL +#define UV2H_EVENT_OCCURRED2_32 0xb68 + +#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0 +#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL +#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1 +#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL +#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2 +#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL +#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3 +#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL +#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4 +#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL +#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5 +#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL +#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6 +#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL +#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7 +#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL +#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8 +#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL +#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9 +#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL +#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10 +#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL +#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11 +#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL +#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12 +#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL +#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13 +#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL +#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14 +#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL +#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15 +#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL +#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16 +#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL +#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17 +#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL +#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18 +#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL +#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19 +#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL +#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20 +#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL +#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21 +#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL +#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22 +#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL +#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23 +#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL +#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24 +#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL +#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25 +#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL +#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26 +#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL +#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27 +#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL +#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28 +#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL +#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29 +#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL +#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30 +#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL +#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31 +#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL + +union uv2h_event_occurred2_u { + unsigned long v; + struct uv2h_event_occurred2_s { + unsigned long rtc_0 : 1; /* RW */ + unsigned long rtc_1 : 1; /* RW */ + unsigned long rtc_2 : 1; /* RW */ + unsigned long rtc_3 : 1; /* RW */ + unsigned long rtc_4 : 1; /* RW */ + unsigned long rtc_5 : 1; /* RW */ + unsigned long rtc_6 : 1; /* RW */ + unsigned long rtc_7 : 1; /* RW */ + unsigned long rtc_8 : 1; /* RW */ + unsigned long rtc_9 : 1; /* RW */ + unsigned long rtc_10 : 1; /* RW */ + unsigned long rtc_11 : 1; /* RW */ + unsigned long rtc_12 : 1; /* RW */ + unsigned long rtc_13 : 1; /* RW */ + unsigned long rtc_14 : 1; /* RW */ + unsigned long rtc_15 : 1; /* RW */ + unsigned long rtc_16 : 1; /* RW */ + unsigned long rtc_17 : 1; /* RW */ + unsigned long rtc_18 : 1; /* RW */ + unsigned long rtc_19 : 1; /* RW */ + unsigned long rtc_20 : 1; /* RW */ + unsigned long rtc_21 : 1; /* RW */ + unsigned long rtc_22 : 1; /* RW */ + unsigned long rtc_23 : 1; /* RW */ + unsigned long rtc_24 : 1; /* RW */ + unsigned long rtc_25 : 1; /* RW */ + unsigned long rtc_26 : 1; /* RW */ + unsigned long rtc_27 : 1; /* RW */ + unsigned long rtc_28 : 1; /* RW */ + unsigned long rtc_29 : 1; /* RW */ + unsigned long rtc_30 : 1; /* RW */ + unsigned long rtc_31 : 1; /* RW */ + unsigned long rsvd_32_63: 32; /* */ + } s1; +}; + +/* ========================================================================= */ +/* UV2H_EVENT_OCCURRED2_ALIAS */ +/* ========================================================================= */ +#define UV2H_EVENT_OCCURRED2_ALIAS 0x70108UL +#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70 + +/* ========================================================================= */ +/* UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 */ +/* ========================================================================= */ +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0 + +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0 +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL + +union uv2h_lb_bau_sb_activation_status_2_u { + unsigned long v; + struct uv2h_lb_bau_sb_activation_status_2_s { + unsigned long aux_error : 64; /* RW */ + } s1; +}; + +/* ========================================================================= */ +/* UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK */ +/* ========================================================================= */ +#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL +#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x9f0 + +#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0 +#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL + +union uv1h_lb_target_physical_apic_id_mask_u { + unsigned long v; + struct uv1h_lb_target_physical_apic_id_mask_s { + unsigned long bit_enables : 32; /* RW */ + unsigned long rsvd_32_63 : 32; /* */ + } s1; +}; + + #endif /* __ASM_UV_MMRS_X86_H__ */ diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 4fbda9a..968d57d 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -14,13 +14,14 @@ static inline int pci_xen_hvm_init(void) } #endif #if defined(CONFIG_XEN_DOM0) -void __init xen_setup_pirqs(void); +int __init pci_xen_initial_domain(void); int xen_find_device_domain_owner(struct pci_dev *dev); int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); int xen_unregister_device_domain_owner(struct pci_dev *dev); #else -static inline void __init xen_setup_pirqs(void) +static inline int __init pci_xen_initial_domain(void) { + return -1; } static inline int xen_find_device_domain_owner(struct pci_dev *dev) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f5abe3a..11817ff 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -8,6 +8,7 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities +CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg @@ -28,6 +29,7 @@ CFLAGS_paravirt.o := $(nostackp) GCOV_PROFILE_vsyscall_64.o := n GCOV_PROFILE_hpet.o := n GCOV_PROFILE_tsc.o := n +GCOV_PROFILE_vread_tsc_64.o := n GCOV_PROFILE_paravirt.o := n # vread_tsc_64 is hot and should be fully optimized: @@ -121,7 +123,6 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o - obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o obj-y += vsmp_64.o diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index ead21b6..b4fd836 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -28,6 +28,8 @@ pmode_cr3: .long 0 /* Saved %cr3 */ pmode_cr4: .long 0 /* Saved %cr4 */ pmode_efer: .quad 0 /* Saved EFER */ pmode_gdt: .quad 0 +pmode_misc_en: .quad 0 /* Saved MISC_ENABLE MSR */ +pmode_behavior: .long 0 /* Wakeup behavior flags */ realmode_flags: .long 0 real_magic: .long 0 trampoline_segment: .word 0 @@ -91,6 +93,18 @@ wakeup_code: /* Call the C code */ calll main + /* Restore MISC_ENABLE before entering protected mode, in case + BIOS decided to clear XD_DISABLE during S3. */ + movl pmode_behavior, %eax + btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax + jnc 1f + + movl pmode_misc_en, %eax + movl pmode_misc_en + 4, %edx + movl $MSR_IA32_MISC_ENABLE, %ecx + wrmsr +1: + /* Do any other stuff... */ #ifndef CONFIG_64BIT diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h index e1828c0..97a29e1 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.h +++ b/arch/x86/kernel/acpi/realmode/wakeup.h @@ -21,6 +21,9 @@ struct wakeup_header { u32 pmode_efer_low; /* Protected mode EFER */ u32 pmode_efer_high; u64 pmode_gdt; + u32 pmode_misc_en_low; /* Protected mode MISC_ENABLE */ + u32 pmode_misc_en_high; + u32 pmode_behavior; /* Wakeup routine behavior flags */ u32 realmode_flags; u32 real_magic; u16 trampoline_segment; /* segment with trampoline code, 64-bit only */ @@ -39,4 +42,7 @@ extern struct wakeup_header wakeup_header; #define WAKEUP_HEADER_SIGNATURE 0x51ee1111 #define WAKEUP_END_SIGNATURE 0x65a22c82 +/* Wakeup behavior bits */ +#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE 0 + #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 18a857b..103b6ab 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -77,6 +77,12 @@ int acpi_suspend_lowlevel(void) header->pmode_cr0 = read_cr0(); header->pmode_cr4 = read_cr4_safe(); + header->pmode_behavior = 0; + if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, + &header->pmode_misc_en_low, + &header->pmode_misc_en_high)) + header->pmode_behavior |= + (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; header->real_magic = 0x12345678; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c deleted file mode 100644 index cd8cbeb..0000000 --- a/arch/x86/kernel/amd_iommu.c +++ /dev/null @@ -1,2722 +0,0 @@ -/* - * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. - * Author: Joerg Roedel <joerg.roedel@amd.com> - * Leo Duran <leo.duran@amd.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/pci.h> -#include <linux/pci-ats.h> -#include <linux/bitmap.h> -#include <linux/slab.h> -#include <linux/debugfs.h> -#include <linux/scatterlist.h> -#include <linux/dma-mapping.h> -#include <linux/iommu-helper.h> -#include <linux/iommu.h> -#include <linux/delay.h> -#include <asm/proto.h> -#include <asm/iommu.h> -#include <asm/gart.h> -#include <asm/amd_iommu_proto.h> -#include <asm/amd_iommu_types.h> -#include <asm/amd_iommu.h> - -#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28)) - -#define LOOP_TIMEOUT 100000 - -static DEFINE_RWLOCK(amd_iommu_devtable_lock); - -/* A list of preallocated protection domains */ -static LIST_HEAD(iommu_pd_list); -static DEFINE_SPINLOCK(iommu_pd_list_lock); - -/* - * Domain for untranslated devices - only allocated - * if iommu=pt passed on kernel cmd line. - */ -static struct protection_domain *pt_domain; - -static struct iommu_ops amd_iommu_ops; - -/* - * general struct to manage commands send to an IOMMU - */ -struct iommu_cmd { - u32 data[4]; -}; - -static void update_domain(struct protection_domain *domain); - -/**************************************************************************** - * - * Helper functions - * - ****************************************************************************/ - -static inline u16 get_device_id(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - - return calc_devid(pdev->bus->number, pdev->devfn); -} - -static struct iommu_dev_data *get_dev_data(struct device *dev) -{ - return dev->archdata.iommu; -} - -/* - * In this function the list of preallocated protection domains is traversed to - * find the domain for a specific device - */ -static struct dma_ops_domain *find_protection_domain(u16 devid) -{ - struct dma_ops_domain *entry, *ret = NULL; - unsigned long flags; - u16 alias = amd_iommu_alias_table[devid]; - - if (list_empty(&iommu_pd_list)) - return NULL; - - spin_lock_irqsave(&iommu_pd_list_lock, flags); - - list_for_each_entry(entry, &iommu_pd_list, list) { - if (entry->target_dev == devid || - entry->target_dev == alias) { - ret = entry; - break; - } - } - - spin_unlock_irqrestore(&iommu_pd_list_lock, flags); - - return ret; -} - -/* - * This function checks if the driver got a valid device from the caller to - * avoid dereferencing invalid pointers. - */ -static bool check_device(struct device *dev) -{ - u16 devid; - - if (!dev || !dev->dma_mask) - return false; - - /* No device or no PCI device */ - if (dev->bus != &pci_bus_type) - return false; - - devid = get_device_id(dev); - - /* Out of our scope? */ - if (devid > amd_iommu_last_bdf) - return false; - - if (amd_iommu_rlookup_table[devid] == NULL) - return false; - - return true; -} - -static int iommu_init_device(struct device *dev) -{ - struct iommu_dev_data *dev_data; - struct pci_dev *pdev; - u16 devid, alias; - - if (dev->archdata.iommu) - return 0; - - dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL); - if (!dev_data) - return -ENOMEM; - - dev_data->dev = dev; - - devid = get_device_id(dev); - alias = amd_iommu_alias_table[devid]; - pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff); - if (pdev) - dev_data->alias = &pdev->dev; - - atomic_set(&dev_data->bind, 0); - - dev->archdata.iommu = dev_data; - - - return 0; -} - -static void iommu_uninit_device(struct device *dev) -{ - kfree(dev->archdata.iommu); -} - -void __init amd_iommu_uninit_devices(void) -{ - struct pci_dev *pdev = NULL; - - for_each_pci_dev(pdev) { - - if (!check_device(&pdev->dev)) - continue; - - iommu_uninit_device(&pdev->dev); - } -} - -int __init amd_iommu_init_devices(void) -{ - struct pci_dev *pdev = NULL; - int ret = 0; - - for_each_pci_dev(pdev) { - - if (!check_device(&pdev->dev)) - continue; - - ret = iommu_init_device(&pdev->dev); - if (ret) - goto out_free; - } - - return 0; - -out_free: - - amd_iommu_uninit_devices(); - - return ret; -} -#ifdef CONFIG_AMD_IOMMU_STATS - -/* - * Initialization code for statistics collection - */ - -DECLARE_STATS_COUNTER(compl_wait); -DECLARE_STATS_COUNTER(cnt_map_single); -DECLARE_STATS_COUNTER(cnt_unmap_single); -DECLARE_STATS_COUNTER(cnt_map_sg); -DECLARE_STATS_COUNTER(cnt_unmap_sg); -DECLARE_STATS_COUNTER(cnt_alloc_coherent); -DECLARE_STATS_COUNTER(cnt_free_coherent); -DECLARE_STATS_COUNTER(cross_page); -DECLARE_STATS_COUNTER(domain_flush_single); -DECLARE_STATS_COUNTER(domain_flush_all); -DECLARE_STATS_COUNTER(alloced_io_mem); -DECLARE_STATS_COUNTER(total_map_requests); - -static struct dentry *stats_dir; -static struct dentry *de_fflush; - -static void amd_iommu_stats_add(struct __iommu_counter *cnt) -{ - if (stats_dir == NULL) - return; - - cnt->dent = debugfs_create_u64(cnt->name, 0444, stats_dir, - &cnt->value); -} - -static void amd_iommu_stats_init(void) -{ - stats_dir = debugfs_create_dir("amd-iommu", NULL); - if (stats_dir == NULL) - return; - - de_fflush = debugfs_create_bool("fullflush", 0444, stats_dir, - (u32 *)&amd_iommu_unmap_flush); - - amd_iommu_stats_add(&compl_wait); - amd_iommu_stats_add(&cnt_map_single); - amd_iommu_stats_add(&cnt_unmap_single); - amd_iommu_stats_add(&cnt_map_sg); - amd_iommu_stats_add(&cnt_unmap_sg); - amd_iommu_stats_add(&cnt_alloc_coherent); - amd_iommu_stats_add(&cnt_free_coherent); - amd_iommu_stats_add(&cross_page); - amd_iommu_stats_add(&domain_flush_single); - amd_iommu_stats_add(&domain_flush_all); - amd_iommu_stats_add(&alloced_io_mem); - amd_iommu_stats_add(&total_map_requests); -} - -#endif - -/**************************************************************************** - * - * Interrupt handling functions - * - ****************************************************************************/ - -static void dump_dte_entry(u16 devid) -{ - int i; - - for (i = 0; i < 8; ++i) - pr_err("AMD-Vi: DTE[%d]: %08x\n", i, - amd_iommu_dev_table[devid].data[i]); -} - -static void dump_command(unsigned long phys_addr) -{ - struct iommu_cmd *cmd = phys_to_virt(phys_addr); - int i; - - for (i = 0; i < 4; ++i) - pr_err("AMD-Vi: CMD[%d]: %08x\n", i, cmd->data[i]); -} - -static void iommu_print_event(struct amd_iommu *iommu, void *__evt) -{ - u32 *event = __evt; - int type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK; - int devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; - int domid = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK; - int flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; - u64 address = (u64)(((u64)event[3]) << 32) | event[2]; - - printk(KERN_ERR "AMD-Vi: Event logged ["); - - switch (type) { - case EVENT_TYPE_ILL_DEV: - printk("ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); - dump_dte_entry(devid); - break; - case EVENT_TYPE_IO_FAULT: - printk("IO_PAGE_FAULT device=%02x:%02x.%x " - "domain=0x%04x address=0x%016llx flags=0x%04x]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - domid, address, flags); - break; - case EVENT_TYPE_DEV_TAB_ERR: - printk("DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); - break; - case EVENT_TYPE_PAGE_TAB_ERR: - printk("PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x " - "domain=0x%04x address=0x%016llx flags=0x%04x]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - domid, address, flags); - break; - case EVENT_TYPE_ILL_CMD: - printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address); - dump_command(address); - break; - case EVENT_TYPE_CMD_HARD_ERR: - printk("COMMAND_HARDWARE_ERROR address=0x%016llx " - "flags=0x%04x]\n", address, flags); - break; - case EVENT_TYPE_IOTLB_INV_TO: - printk("IOTLB_INV_TIMEOUT device=%02x:%02x.%x " - "address=0x%016llx]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address); - break; - case EVENT_TYPE_INV_DEV_REQ: - printk("INVALID_DEVICE_REQUEST device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); - break; - default: - printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type); - } -} - -static void iommu_poll_events(struct amd_iommu *iommu) -{ - u32 head, tail; - unsigned long flags; - - spin_lock_irqsave(&iommu->lock, flags); - - head = readl(iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); - tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); - - while (head != tail) { - iommu_print_event(iommu, iommu->evt_buf + head); - head = (head + EVENT_ENTRY_SIZE) % iommu->evt_buf_size; - } - - writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); - - spin_unlock_irqrestore(&iommu->lock, flags); -} - -irqreturn_t amd_iommu_int_thread(int irq, void *data) -{ - struct amd_iommu *iommu; - - for_each_iommu(iommu) - iommu_poll_events(iommu); - - return IRQ_HANDLED; -} - -irqreturn_t amd_iommu_int_handler(int irq, void *data) -{ - return IRQ_WAKE_THREAD; -} - -/**************************************************************************** - * - * IOMMU command queuing functions - * - ****************************************************************************/ - -static int wait_on_sem(volatile u64 *sem) -{ - int i = 0; - - while (*sem == 0 && i < LOOP_TIMEOUT) { - udelay(1); - i += 1; - } - - if (i == LOOP_TIMEOUT) { - pr_alert("AMD-Vi: Completion-Wait loop timed out\n"); - return -EIO; - } - - return 0; -} - -static void copy_cmd_to_buffer(struct amd_iommu *iommu, - struct iommu_cmd *cmd, - u32 tail) -{ - u8 *target; - - target = iommu->cmd_buf + tail; - tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size; - - /* Copy command to buffer */ - memcpy(target, cmd, sizeof(*cmd)); - - /* Tell the IOMMU about it */ - writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); -} - -static void build_completion_wait(struct iommu_cmd *cmd, u64 address) -{ - WARN_ON(address & 0x7ULL); - - memset(cmd, 0, sizeof(*cmd)); - cmd->data[0] = lower_32_bits(__pa(address)) | CMD_COMPL_WAIT_STORE_MASK; - cmd->data[1] = upper_32_bits(__pa(address)); - cmd->data[2] = 1; - CMD_SET_TYPE(cmd, CMD_COMPL_WAIT); -} - -static void build_inv_dte(struct iommu_cmd *cmd, u16 devid) -{ - memset(cmd, 0, sizeof(*cmd)); - cmd->data[0] = devid; - CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY); -} - -static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, - size_t size, u16 domid, int pde) -{ - u64 pages; - int s; - - pages = iommu_num_pages(address, size, PAGE_SIZE); - s = 0; - - if (pages > 1) { - /* - * If we have to flush more than one page, flush all - * TLB entries for this domain - */ - address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - s = 1; - } - - address &= PAGE_MASK; - - memset(cmd, 0, sizeof(*cmd)); - cmd->data[1] |= domid; - cmd->data[2] = lower_32_bits(address); - cmd->data[3] = upper_32_bits(address); - CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); - if (s) /* size bit - we flush more than one 4kb page */ - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; - if (pde) /* PDE bit - we wan't flush everything not only the PTEs */ - cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; -} - -static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep, - u64 address, size_t size) -{ - u64 pages; - int s; - - pages = iommu_num_pages(address, size, PAGE_SIZE); - s = 0; - - if (pages > 1) { - /* - * If we have to flush more than one page, flush all - * TLB entries for this domain - */ - address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - s = 1; - } - - address &= PAGE_MASK; - - memset(cmd, 0, sizeof(*cmd)); - cmd->data[0] = devid; - cmd->data[0] |= (qdep & 0xff) << 24; - cmd->data[1] = devid; - cmd->data[2] = lower_32_bits(address); - cmd->data[3] = upper_32_bits(address); - CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); - if (s) - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; -} - -static void build_inv_all(struct iommu_cmd *cmd) -{ - memset(cmd, 0, sizeof(*cmd)); - CMD_SET_TYPE(cmd, CMD_INV_ALL); -} - -/* - * Writes the command to the IOMMUs command buffer and informs the - * hardware about the new command. - */ -static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) -{ - u32 left, tail, head, next_tail; - unsigned long flags; - - WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED); - -again: - spin_lock_irqsave(&iommu->lock, flags); - - head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); - tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); - next_tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size; - left = (head - next_tail) % iommu->cmd_buf_size; - - if (left <= 2) { - struct iommu_cmd sync_cmd; - volatile u64 sem = 0; - int ret; - - build_completion_wait(&sync_cmd, (u64)&sem); - copy_cmd_to_buffer(iommu, &sync_cmd, tail); - - spin_unlock_irqrestore(&iommu->lock, flags); - - if ((ret = wait_on_sem(&sem)) != 0) - return ret; - - goto again; - } - - copy_cmd_to_buffer(iommu, cmd, tail); - - /* We need to sync now to make sure all commands are processed */ - iommu->need_sync = true; - - spin_unlock_irqrestore(&iommu->lock, flags); - - return 0; -} - -/* - * This function queues a completion wait command into the command - * buffer of an IOMMU - */ -static int iommu_completion_wait(struct amd_iommu *iommu) -{ - struct iommu_cmd cmd; - volatile u64 sem = 0; - int ret; - - if (!iommu->need_sync) - return 0; - - build_completion_wait(&cmd, (u64)&sem); - - ret = iommu_queue_command(iommu, &cmd); - if (ret) - return ret; - - return wait_on_sem(&sem); -} - -static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid) -{ - struct iommu_cmd cmd; - - build_inv_dte(&cmd, devid); - - return iommu_queue_command(iommu, &cmd); -} - -static void iommu_flush_dte_all(struct amd_iommu *iommu) -{ - u32 devid; - - for (devid = 0; devid <= 0xffff; ++devid) - iommu_flush_dte(iommu, devid); - - iommu_completion_wait(iommu); -} - -/* - * This function uses heavy locking and may disable irqs for some time. But - * this is no issue because it is only called during resume. - */ -static void iommu_flush_tlb_all(struct amd_iommu *iommu) -{ - u32 dom_id; - - for (dom_id = 0; dom_id <= 0xffff; ++dom_id) { - struct iommu_cmd cmd; - build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, - dom_id, 1); - iommu_queue_command(iommu, &cmd); - } - - iommu_completion_wait(iommu); -} - -static void iommu_flush_all(struct amd_iommu *iommu) -{ - struct iommu_cmd cmd; - - build_inv_all(&cmd); - - iommu_queue_command(iommu, &cmd); - iommu_completion_wait(iommu); -} - -void iommu_flush_all_caches(struct amd_iommu *iommu) -{ - if (iommu_feature(iommu, FEATURE_IA)) { - iommu_flush_all(iommu); - } else { - iommu_flush_dte_all(iommu); - iommu_flush_tlb_all(iommu); - } -} - -/* - * Command send function for flushing on-device TLB - */ -static int device_flush_iotlb(struct device *dev, u64 address, size_t size) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct amd_iommu *iommu; - struct iommu_cmd cmd; - u16 devid; - int qdep; - - qdep = pci_ats_queue_depth(pdev); - devid = get_device_id(dev); - iommu = amd_iommu_rlookup_table[devid]; - - build_inv_iotlb_pages(&cmd, devid, qdep, address, size); - - return iommu_queue_command(iommu, &cmd); -} - -/* - * Command send function for invalidating a device table entry - */ -static int device_flush_dte(struct device *dev) -{ - struct amd_iommu *iommu; - struct pci_dev *pdev; - u16 devid; - int ret; - - pdev = to_pci_dev(dev); - devid = get_device_id(dev); - iommu = amd_iommu_rlookup_table[devid]; - - ret = iommu_flush_dte(iommu, devid); - if (ret) - return ret; - - if (pci_ats_enabled(pdev)) - ret = device_flush_iotlb(dev, 0, ~0UL); - - return ret; -} - -/* - * TLB invalidation function which is called from the mapping functions. - * It invalidates a single PTE if the range to flush is within a single - * page. Otherwise it flushes the whole TLB of the IOMMU. - */ -static void __domain_flush_pages(struct protection_domain *domain, - u64 address, size_t size, int pde) -{ - struct iommu_dev_data *dev_data; - struct iommu_cmd cmd; - int ret = 0, i; - - build_inv_iommu_pages(&cmd, address, size, domain->id, pde); - - for (i = 0; i < amd_iommus_present; ++i) { - if (!domain->dev_iommu[i]) - continue; - - /* - * Devices of this domain are behind this IOMMU - * We need a TLB flush - */ - ret |= iommu_queue_command(amd_iommus[i], &cmd); - } - - list_for_each_entry(dev_data, &domain->dev_list, list) { - struct pci_dev *pdev = to_pci_dev(dev_data->dev); - - if (!pci_ats_enabled(pdev)) - continue; - - ret |= device_flush_iotlb(dev_data->dev, address, size); - } - - WARN_ON(ret); -} - -static void domain_flush_pages(struct protection_domain *domain, - u64 address, size_t size) -{ - __domain_flush_pages(domain, address, size, 0); -} - -/* Flush the whole IO/TLB for a given protection domain */ -static void domain_flush_tlb(struct protection_domain *domain) -{ - __domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0); -} - -/* Flush the whole IO/TLB for a given protection domain - including PDE */ -static void domain_flush_tlb_pde(struct protection_domain *domain) -{ - __domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1); -} - -static void domain_flush_complete(struct protection_domain *domain) -{ - int i; - - for (i = 0; i < amd_iommus_present; ++i) { - if (!domain->dev_iommu[i]) - continue; - - /* - * Devices of this domain are behind this IOMMU - * We need to wait for completion of all commands. - */ - iommu_completion_wait(amd_iommus[i]); - } -} - - -/* - * This function flushes the DTEs for all devices in domain - */ -static void domain_flush_devices(struct protection_domain *domain) -{ - struct iommu_dev_data *dev_data; - unsigned long flags; - - spin_lock_irqsave(&domain->lock, flags); - - list_for_each_entry(dev_data, &domain->dev_list, list) - device_flush_dte(dev_data->dev); - - spin_unlock_irqrestore(&domain->lock, flags); -} - -/**************************************************************************** - * - * The functions below are used the create the page table mappings for - * unity mapped regions. - * - ****************************************************************************/ - -/* - * This function is used to add another level to an IO page table. Adding - * another level increases the size of the address space by 9 bits to a size up - * to 64 bits. - */ -static bool increase_address_space(struct protection_domain *domain, - gfp_t gfp) -{ - u64 *pte; - - if (domain->mode == PAGE_MODE_6_LEVEL) - /* address space already 64 bit large */ - return false; - - pte = (void *)get_zeroed_page(gfp); - if (!pte) - return false; - - *pte = PM_LEVEL_PDE(domain->mode, - virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; - domain->updated = true; - - return true; -} - -static u64 *alloc_pte(struct protection_domain *domain, - unsigned long address, - unsigned long page_size, - u64 **pte_page, - gfp_t gfp) -{ - int level, end_lvl; - u64 *pte, *page; - - BUG_ON(!is_power_of_2(page_size)); - - while (address > PM_LEVEL_SIZE(domain->mode)) - increase_address_space(domain, gfp); - - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - address = PAGE_SIZE_ALIGN(address, page_size); - end_lvl = PAGE_SIZE_LEVEL(page_size); - - while (level > end_lvl) { - if (!IOMMU_PTE_PRESENT(*pte)) { - page = (u64 *)get_zeroed_page(gfp); - if (!page) - return NULL; - *pte = PM_LEVEL_PDE(level, virt_to_phys(page)); - } - - /* No level skipping support yet */ - if (PM_PTE_LEVEL(*pte) != level) - return NULL; - - level -= 1; - - pte = IOMMU_PTE_PAGE(*pte); - - if (pte_page && level == end_lvl) - *pte_page = pte; - - pte = &pte[PM_LEVEL_INDEX(level, address)]; - } - - return pte; -} - -/* - * This function checks if there is a PTE for a given dma address. If - * there is one, it returns the pointer to it. - */ -static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) -{ - int level; - u64 *pte; - - if (address > PM_LEVEL_SIZE(domain->mode)) - return NULL; - - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - - while (level > 0) { - - /* Not Present */ - if (!IOMMU_PTE_PRESENT(*pte)) - return NULL; - - /* Large PTE */ - if (PM_PTE_LEVEL(*pte) == 0x07) { - unsigned long pte_mask, __pte; - - /* - * If we have a series of large PTEs, make - * sure to return a pointer to the first one. - */ - pte_mask = PTE_PAGE_SIZE(*pte); - pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1); - __pte = ((unsigned long)pte) & pte_mask; - - return (u64 *)__pte; - } - - /* No level skipping support yet */ - if (PM_PTE_LEVEL(*pte) != level) - return NULL; - - level -= 1; - - /* Walk to the next level */ - pte = IOMMU_PTE_PAGE(*pte); - pte = &pte[PM_LEVEL_INDEX(level, address)]; - } - - return pte; -} - -/* - * Generic mapping functions. It maps a physical address into a DMA - * address space. It allocates the page table pages if necessary. - * In the future it can be extended to a generic mapping function - * supporting all features of AMD IOMMU page tables like level skipping - * and full 64 bit address spaces. - */ -static int iommu_map_page(struct protection_domain *dom, - unsigned long bus_addr, - unsigned long phys_addr, - int prot, - unsigned long page_size) -{ - u64 __pte, *pte; - int i, count; - - if (!(prot & IOMMU_PROT_MASK)) - return -EINVAL; - - bus_addr = PAGE_ALIGN(bus_addr); - phys_addr = PAGE_ALIGN(phys_addr); - count = PAGE_SIZE_PTE_COUNT(page_size); - pte = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL); - - for (i = 0; i < count; ++i) - if (IOMMU_PTE_PRESENT(pte[i])) - return -EBUSY; - - if (page_size > PAGE_SIZE) { - __pte = PAGE_SIZE_PTE(phys_addr, page_size); - __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC; - } else - __pte = phys_addr | IOMMU_PTE_P | IOMMU_PTE_FC; - - if (prot & IOMMU_PROT_IR) - __pte |= IOMMU_PTE_IR; - if (prot & IOMMU_PROT_IW) - __pte |= IOMMU_PTE_IW; - - for (i = 0; i < count; ++i) - pte[i] = __pte; - - update_domain(dom); - - return 0; -} - -static unsigned long iommu_unmap_page(struct protection_domain *dom, - unsigned long bus_addr, - unsigned long page_size) -{ - unsigned long long unmap_size, unmapped; - u64 *pte; - - BUG_ON(!is_power_of_2(page_size)); - - unmapped = 0; - - while (unmapped < page_size) { - - pte = fetch_pte(dom, bus_addr); - - if (!pte) { - /* - * No PTE for this address - * move forward in 4kb steps - */ - unmap_size = PAGE_SIZE; - } else if (PM_PTE_LEVEL(*pte) == 0) { - /* 4kb PTE found for this address */ - unmap_size = PAGE_SIZE; - *pte = 0ULL; - } else { - int count, i; - - /* Large PTE found which maps this address */ - unmap_size = PTE_PAGE_SIZE(*pte); - count = PAGE_SIZE_PTE_COUNT(unmap_size); - for (i = 0; i < count; i++) - pte[i] = 0ULL; - } - - bus_addr = (bus_addr & ~(unmap_size - 1)) + unmap_size; - unmapped += unmap_size; - } - - BUG_ON(!is_power_of_2(unmapped)); - - return unmapped; -} - -/* - * This function checks if a specific unity mapping entry is needed for - * this specific IOMMU. - */ -static int iommu_for_unity_map(struct amd_iommu *iommu, - struct unity_map_entry *entry) -{ - u16 bdf, i; - - for (i = entry->devid_start; i <= entry->devid_end; ++i) { - bdf = amd_iommu_alias_table[i]; - if (amd_iommu_rlookup_table[bdf] == iommu) - return 1; - } - - return 0; -} - -/* - * This function actually applies the mapping to the page table of the - * dma_ops domain. - */ -static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, - struct unity_map_entry *e) -{ - u64 addr; - int ret; - - for (addr = e->address_start; addr < e->address_end; - addr += PAGE_SIZE) { - ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot, - PAGE_SIZE); - if (ret) - return ret; - /* - * if unity mapping is in aperture range mark the page - * as allocated in the aperture - */ - if (addr < dma_dom->aperture_size) - __set_bit(addr >> PAGE_SHIFT, - dma_dom->aperture[0]->bitmap); - } - - return 0; -} - -/* - * Init the unity mappings for a specific IOMMU in the system - * - * Basically iterates over all unity mapping entries and applies them to - * the default domain DMA of that IOMMU if necessary. - */ -static int iommu_init_unity_mappings(struct amd_iommu *iommu) -{ - struct unity_map_entry *entry; - int ret; - - list_for_each_entry(entry, &amd_iommu_unity_map, list) { - if (!iommu_for_unity_map(iommu, entry)) - continue; - ret = dma_ops_unity_map(iommu->default_dom, entry); - if (ret) - return ret; - } - - return 0; -} - -/* - * Inits the unity mappings required for a specific device - */ -static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom, - u16 devid) -{ - struct unity_map_entry *e; - int ret; - - list_for_each_entry(e, &amd_iommu_unity_map, list) { - if (!(devid >= e->devid_start && devid <= e->devid_end)) - continue; - ret = dma_ops_unity_map(dma_dom, e); - if (ret) - return ret; - } - - return 0; -} - -/**************************************************************************** - * - * The next functions belong to the address allocator for the dma_ops - * interface functions. They work like the allocators in the other IOMMU - * drivers. Its basically a bitmap which marks the allocated pages in - * the aperture. Maybe it could be enhanced in the future to a more - * efficient allocator. - * - ****************************************************************************/ - -/* - * The address allocator core functions. - * - * called with domain->lock held - */ - -/* - * Used to reserve address ranges in the aperture (e.g. for exclusion - * ranges. - */ -static void dma_ops_reserve_addresses(struct dma_ops_domain *dom, - unsigned long start_page, - unsigned int pages) -{ - unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT; - - if (start_page + pages > last_page) - pages = last_page - start_page; - - for (i = start_page; i < start_page + pages; ++i) { - int index = i / APERTURE_RANGE_PAGES; - int page = i % APERTURE_RANGE_PAGES; - __set_bit(page, dom->aperture[index]->bitmap); - } -} - -/* - * This function is used to add a new aperture range to an existing - * aperture in case of dma_ops domain allocation or address allocation - * failure. - */ -static int alloc_new_range(struct dma_ops_domain *dma_dom, - bool populate, gfp_t gfp) -{ - int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; - struct amd_iommu *iommu; - unsigned long i; - -#ifdef CONFIG_IOMMU_STRESS - populate = false; -#endif - - if (index >= APERTURE_MAX_RANGES) - return -ENOMEM; - - dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp); - if (!dma_dom->aperture[index]) - return -ENOMEM; - - dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp); - if (!dma_dom->aperture[index]->bitmap) - goto out_free; - - dma_dom->aperture[index]->offset = dma_dom->aperture_size; - - if (populate) { - unsigned long address = dma_dom->aperture_size; - int i, num_ptes = APERTURE_RANGE_PAGES / 512; - u64 *pte, *pte_page; - - for (i = 0; i < num_ptes; ++i) { - pte = alloc_pte(&dma_dom->domain, address, PAGE_SIZE, - &pte_page, gfp); - if (!pte) - goto out_free; - - dma_dom->aperture[index]->pte_pages[i] = pte_page; - - address += APERTURE_RANGE_SIZE / 64; - } - } - - dma_dom->aperture_size += APERTURE_RANGE_SIZE; - - /* Initialize the exclusion range if necessary */ - for_each_iommu(iommu) { - if (iommu->exclusion_start && - iommu->exclusion_start >= dma_dom->aperture[index]->offset - && iommu->exclusion_start < dma_dom->aperture_size) { - unsigned long startpage; - int pages = iommu_num_pages(iommu->exclusion_start, - iommu->exclusion_length, - PAGE_SIZE); - startpage = iommu->exclusion_start >> PAGE_SHIFT; - dma_ops_reserve_addresses(dma_dom, startpage, pages); - } - } - - /* - * Check for areas already mapped as present in the new aperture - * range and mark those pages as reserved in the allocator. Such - * mappings may already exist as a result of requested unity - * mappings for devices. - */ - for (i = dma_dom->aperture[index]->offset; - i < dma_dom->aperture_size; - i += PAGE_SIZE) { - u64 *pte = fetch_pte(&dma_dom->domain, i); - if (!pte || !IOMMU_PTE_PRESENT(*pte)) - continue; - - dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1); - } - - update_domain(&dma_dom->domain); - - return 0; - -out_free: - update_domain(&dma_dom->domain); - - free_page((unsigned long)dma_dom->aperture[index]->bitmap); - - kfree(dma_dom->aperture[index]); - dma_dom->aperture[index] = NULL; - - return -ENOMEM; -} - -static unsigned long dma_ops_area_alloc(struct device *dev, - struct dma_ops_domain *dom, - unsigned int pages, - unsigned long align_mask, - u64 dma_mask, - unsigned long start) -{ - unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE; - int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT; - int i = start >> APERTURE_RANGE_SHIFT; - unsigned long boundary_size; - unsigned long address = -1; - unsigned long limit; - - next_bit >>= PAGE_SHIFT; - - boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - PAGE_SIZE) >> PAGE_SHIFT; - - for (;i < max_index; ++i) { - unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT; - - if (dom->aperture[i]->offset >= dma_mask) - break; - - limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset, - dma_mask >> PAGE_SHIFT); - - address = iommu_area_alloc(dom->aperture[i]->bitmap, - limit, next_bit, pages, 0, - boundary_size, align_mask); - if (address != -1) { - address = dom->aperture[i]->offset + - (address << PAGE_SHIFT); - dom->next_address = address + (pages << PAGE_SHIFT); - break; - } - - next_bit = 0; - } - - return address; -} - -static unsigned long dma_ops_alloc_addresses(struct device *dev, - struct dma_ops_domain *dom, - unsigned int pages, - unsigned long align_mask, - u64 dma_mask) -{ - unsigned long address; - -#ifdef CONFIG_IOMMU_STRESS - dom->next_address = 0; - dom->need_flush = true; -#endif - - address = dma_ops_area_alloc(dev, dom, pages, align_mask, - dma_mask, dom->next_address); - - if (address == -1) { - dom->next_address = 0; - address = dma_ops_area_alloc(dev, dom, pages, align_mask, - dma_mask, 0); - dom->need_flush = true; - } - - if (unlikely(address == -1)) - address = DMA_ERROR_CODE; - - WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size); - - return address; -} - -/* - * The address free function. - * - * called with domain->lock held - */ -static void dma_ops_free_addresses(struct dma_ops_domain *dom, - unsigned long address, - unsigned int pages) -{ - unsigned i = address >> APERTURE_RANGE_SHIFT; - struct aperture_range *range = dom->aperture[i]; - - BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL); - -#ifdef CONFIG_IOMMU_STRESS - if (i < 4) - return; -#endif - - if (address >= dom->next_address) - dom->need_flush = true; - - address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT; - - bitmap_clear(range->bitmap, address, pages); - -} - -/**************************************************************************** - * - * The next functions belong to the domain allocation. A domain is - * allocated for every IOMMU as the default domain. If device isolation - * is enabled, every device get its own domain. The most important thing - * about domains is the page table mapping the DMA address space they - * contain. - * - ****************************************************************************/ - -/* - * This function adds a protection domain to the global protection domain list - */ -static void add_domain_to_list(struct protection_domain *domain) -{ - unsigned long flags; - - spin_lock_irqsave(&amd_iommu_pd_lock, flags); - list_add(&domain->list, &amd_iommu_pd_list); - spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); -} - -/* - * This function removes a protection domain to the global - * protection domain list - */ -static void del_domain_from_list(struct protection_domain *domain) -{ - unsigned long flags; - - spin_lock_irqsave(&amd_iommu_pd_lock, flags); - list_del(&domain->list); - spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); -} - -static u16 domain_id_alloc(void) -{ - unsigned long flags; - int id; - - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); - BUG_ON(id == 0); - if (id > 0 && id < MAX_DOMAIN_ID) - __set_bit(id, amd_iommu_pd_alloc_bitmap); - else - id = 0; - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - - return id; -} - -static void domain_id_free(int id) -{ - unsigned long flags; - - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - if (id > 0 && id < MAX_DOMAIN_ID) - __clear_bit(id, amd_iommu_pd_alloc_bitmap); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); -} - -static void free_pagetable(struct protection_domain *domain) -{ - int i, j; - u64 *p1, *p2, *p3; - - p1 = domain->pt_root; - - if (!p1) - return; - - for (i = 0; i < 512; ++i) { - if (!IOMMU_PTE_PRESENT(p1[i])) - continue; - - p2 = IOMMU_PTE_PAGE(p1[i]); - for (j = 0; j < 512; ++j) { - if (!IOMMU_PTE_PRESENT(p2[j])) - continue; - p3 = IOMMU_PTE_PAGE(p2[j]); - free_page((unsigned long)p3); - } - - free_page((unsigned long)p2); - } - - free_page((unsigned long)p1); - - domain->pt_root = NULL; -} - -/* - * Free a domain, only used if something went wrong in the - * allocation path and we need to free an already allocated page table - */ -static void dma_ops_domain_free(struct dma_ops_domain *dom) -{ - int i; - - if (!dom) - return; - - del_domain_from_list(&dom->domain); - - free_pagetable(&dom->domain); - - for (i = 0; i < APERTURE_MAX_RANGES; ++i) { - if (!dom->aperture[i]) - continue; - free_page((unsigned long)dom->aperture[i]->bitmap); - kfree(dom->aperture[i]); - } - - kfree(dom); -} - -/* - * Allocates a new protection domain usable for the dma_ops functions. - * It also initializes the page table and the address allocator data - * structures required for the dma_ops interface - */ -static struct dma_ops_domain *dma_ops_domain_alloc(void) -{ - struct dma_ops_domain *dma_dom; - - dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL); - if (!dma_dom) - return NULL; - - spin_lock_init(&dma_dom->domain.lock); - - dma_dom->domain.id = domain_id_alloc(); - if (dma_dom->domain.id == 0) - goto free_dma_dom; - INIT_LIST_HEAD(&dma_dom->domain.dev_list); - dma_dom->domain.mode = PAGE_MODE_2_LEVEL; - dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL); - dma_dom->domain.flags = PD_DMA_OPS_MASK; - dma_dom->domain.priv = dma_dom; - if (!dma_dom->domain.pt_root) - goto free_dma_dom; - - dma_dom->need_flush = false; - dma_dom->target_dev = 0xffff; - - add_domain_to_list(&dma_dom->domain); - - if (alloc_new_range(dma_dom, true, GFP_KERNEL)) - goto free_dma_dom; - - /* - * mark the first page as allocated so we never return 0 as - * a valid dma-address. So we can use 0 as error value - */ - dma_dom->aperture[0]->bitmap[0] = 1; - dma_dom->next_address = 0; - - - return dma_dom; - -free_dma_dom: - dma_ops_domain_free(dma_dom); - - return NULL; -} - -/* - * little helper function to check whether a given protection domain is a - * dma_ops domain - */ -static bool dma_ops_domain(struct protection_domain *domain) -{ - return domain->flags & PD_DMA_OPS_MASK; -} - -static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats) -{ - u64 pte_root = virt_to_phys(domain->pt_root); - u32 flags = 0; - - pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK) - << DEV_ENTRY_MODE_SHIFT; - pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV; - - if (ats) - flags |= DTE_FLAG_IOTLB; - - amd_iommu_dev_table[devid].data[3] |= flags; - amd_iommu_dev_table[devid].data[2] = domain->id; - amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root); - amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root); -} - -static void clear_dte_entry(u16 devid) -{ - /* remove entry from the device table seen by the hardware */ - amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; - amd_iommu_dev_table[devid].data[1] = 0; - amd_iommu_dev_table[devid].data[2] = 0; - - amd_iommu_apply_erratum_63(devid); -} - -static void do_attach(struct device *dev, struct protection_domain *domain) -{ - struct iommu_dev_data *dev_data; - struct amd_iommu *iommu; - struct pci_dev *pdev; - bool ats = false; - u16 devid; - - devid = get_device_id(dev); - iommu = amd_iommu_rlookup_table[devid]; - dev_data = get_dev_data(dev); - pdev = to_pci_dev(dev); - - if (amd_iommu_iotlb_sup) - ats = pci_ats_enabled(pdev); - - /* Update data structures */ - dev_data->domain = domain; - list_add(&dev_data->list, &domain->dev_list); - set_dte_entry(devid, domain, ats); - - /* Do reference counting */ - domain->dev_iommu[iommu->index] += 1; - domain->dev_cnt += 1; - - /* Flush the DTE entry */ - device_flush_dte(dev); -} - -static void do_detach(struct device *dev) -{ - struct iommu_dev_data *dev_data; - struct amd_iommu *iommu; - u16 devid; - - devid = get_device_id(dev); - iommu = amd_iommu_rlookup_table[devid]; - dev_data = get_dev_data(dev); - - /* decrease reference counters */ - dev_data->domain->dev_iommu[iommu->index] -= 1; - dev_data->domain->dev_cnt -= 1; - - /* Update data structures */ - dev_data->domain = NULL; - list_del(&dev_data->list); - clear_dte_entry(devid); - - /* Flush the DTE entry */ - device_flush_dte(dev); -} - -/* - * If a device is not yet associated with a domain, this function does - * assigns it visible for the hardware - */ -static int __attach_device(struct device *dev, - struct protection_domain *domain) -{ - struct iommu_dev_data *dev_data, *alias_data; - int ret; - - dev_data = get_dev_data(dev); - alias_data = get_dev_data(dev_data->alias); - - if (!alias_data) - return -EINVAL; - - /* lock domain */ - spin_lock(&domain->lock); - - /* Some sanity checks */ - ret = -EBUSY; - if (alias_data->domain != NULL && - alias_data->domain != domain) - goto out_unlock; - - if (dev_data->domain != NULL && - dev_data->domain != domain) - goto out_unlock; - - /* Do real assignment */ - if (dev_data->alias != dev) { - alias_data = get_dev_data(dev_data->alias); - if (alias_data->domain == NULL) - do_attach(dev_data->alias, domain); - - atomic_inc(&alias_data->bind); - } - - if (dev_data->domain == NULL) - do_attach(dev, domain); - - atomic_inc(&dev_data->bind); - - ret = 0; - -out_unlock: - - /* ready */ - spin_unlock(&domain->lock); - - return ret; -} - -/* - * If a device is not yet associated with a domain, this function does - * assigns it visible for the hardware - */ -static int attach_device(struct device *dev, - struct protection_domain *domain) -{ - struct pci_dev *pdev = to_pci_dev(dev); - unsigned long flags; - int ret; - - if (amd_iommu_iotlb_sup) - pci_enable_ats(pdev, PAGE_SHIFT); - - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - ret = __attach_device(dev, domain); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - - /* - * We might boot into a crash-kernel here. The crashed kernel - * left the caches in the IOMMU dirty. So we have to flush - * here to evict all dirty stuff. - */ - domain_flush_tlb_pde(domain); - - return ret; -} - -/* - * Removes a device from a protection domain (unlocked) - */ -static void __detach_device(struct device *dev) -{ - struct iommu_dev_data *dev_data = get_dev_data(dev); - struct iommu_dev_data *alias_data; - struct protection_domain *domain; - unsigned long flags; - - BUG_ON(!dev_data->domain); - - domain = dev_data->domain; - - spin_lock_irqsave(&domain->lock, flags); - - if (dev_data->alias != dev) { - alias_data = get_dev_data(dev_data->alias); - if (atomic_dec_and_test(&alias_data->bind)) - do_detach(dev_data->alias); - } - - if (atomic_dec_and_test(&dev_data->bind)) - do_detach(dev); - - spin_unlock_irqrestore(&domain->lock, flags); - - /* - * If we run in passthrough mode the device must be assigned to the - * passthrough domain if it is detached from any other domain. - * Make sure we can deassign from the pt_domain itself. - */ - if (iommu_pass_through && - (dev_data->domain == NULL && domain != pt_domain)) - __attach_device(dev, pt_domain); -} - -/* - * Removes a device from a protection domain (with devtable_lock held) - */ -static void detach_device(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - unsigned long flags; - - /* lock device table */ - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - __detach_device(dev); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - - if (amd_iommu_iotlb_sup && pci_ats_enabled(pdev)) - pci_disable_ats(pdev); -} - -/* - * Find out the protection domain structure for a given PCI device. This - * will give us the pointer to the page table root for example. - */ -static struct protection_domain *domain_for_device(struct device *dev) -{ - struct protection_domain *dom; - struct iommu_dev_data *dev_data, *alias_data; - unsigned long flags; - u16 devid; - - devid = get_device_id(dev); - dev_data = get_dev_data(dev); - alias_data = get_dev_data(dev_data->alias); - if (!alias_data) - return NULL; - - read_lock_irqsave(&amd_iommu_devtable_lock, flags); - dom = dev_data->domain; - if (dom == NULL && - alias_data->domain != NULL) { - __attach_device(dev, alias_data->domain); - dom = alias_data->domain; - } - - read_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - - return dom; -} - -static int device_change_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - u16 devid; - struct protection_domain *domain; - struct dma_ops_domain *dma_domain; - struct amd_iommu *iommu; - unsigned long flags; - - if (!check_device(dev)) - return 0; - - devid = get_device_id(dev); - iommu = amd_iommu_rlookup_table[devid]; - - switch (action) { - case BUS_NOTIFY_UNBOUND_DRIVER: - - domain = domain_for_device(dev); - - if (!domain) - goto out; - if (iommu_pass_through) - break; - detach_device(dev); - break; - case BUS_NOTIFY_ADD_DEVICE: - - iommu_init_device(dev); - - domain = domain_for_device(dev); - - /* allocate a protection domain if a device is added */ - dma_domain = find_protection_domain(devid); - if (dma_domain) - goto out; - dma_domain = dma_ops_domain_alloc(); - if (!dma_domain) - goto out; - dma_domain->target_dev = devid; - - spin_lock_irqsave(&iommu_pd_list_lock, flags); - list_add_tail(&dma_domain->list, &iommu_pd_list); - spin_unlock_irqrestore(&iommu_pd_list_lock, flags); - - break; - case BUS_NOTIFY_DEL_DEVICE: - - iommu_uninit_device(dev); - - default: - goto out; - } - - device_flush_dte(dev); - iommu_completion_wait(iommu); - -out: - return 0; -} - -static struct notifier_block device_nb = { - .notifier_call = device_change_notifier, -}; - -void amd_iommu_init_notifier(void) -{ - bus_register_notifier(&pci_bus_type, &device_nb); -} - -/***************************************************************************** - * - * The next functions belong to the dma_ops mapping/unmapping code. - * - *****************************************************************************/ - -/* - * In the dma_ops path we only have the struct device. This function - * finds the corresponding IOMMU, the protection domain and the - * requestor id for a given device. - * If the device is not yet associated with a domain this is also done - * in this function. - */ -static struct protection_domain *get_domain(struct device *dev) -{ - struct protection_domain *domain; - struct dma_ops_domain *dma_dom; - u16 devid = get_device_id(dev); - - if (!check_device(dev)) - return ERR_PTR(-EINVAL); - - domain = domain_for_device(dev); - if (domain != NULL && !dma_ops_domain(domain)) - return ERR_PTR(-EBUSY); - - if (domain != NULL) - return domain; - - /* Device not bount yet - bind it */ - dma_dom = find_protection_domain(devid); - if (!dma_dom) - dma_dom = amd_iommu_rlookup_table[devid]->default_dom; - attach_device(dev, &dma_dom->domain); - DUMP_printk("Using protection domain %d for device %s\n", - dma_dom->domain.id, dev_name(dev)); - - return &dma_dom->domain; -} - -static void update_device_table(struct protection_domain *domain) -{ - struct iommu_dev_data *dev_data; - - list_for_each_entry(dev_data, &domain->dev_list, list) { - struct pci_dev *pdev = to_pci_dev(dev_data->dev); - u16 devid = get_device_id(dev_data->dev); - set_dte_entry(devid, domain, pci_ats_enabled(pdev)); - } -} - -static void update_domain(struct protection_domain *domain) -{ - if (!domain->updated) - return; - - update_device_table(domain); - - domain_flush_devices(domain); - domain_flush_tlb_pde(domain); - - domain->updated = false; -} - -/* - * This function fetches the PTE for a given address in the aperture - */ -static u64* dma_ops_get_pte(struct dma_ops_domain *dom, - unsigned long address) -{ - struct aperture_range *aperture; - u64 *pte, *pte_page; - - aperture = dom->aperture[APERTURE_RANGE_INDEX(address)]; - if (!aperture) - return NULL; - - pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)]; - if (!pte) { - pte = alloc_pte(&dom->domain, address, PAGE_SIZE, &pte_page, - GFP_ATOMIC); - aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page; - } else - pte += PM_LEVEL_INDEX(0, address); - - update_domain(&dom->domain); - - return pte; -} - -/* - * This is the generic map function. It maps one 4kb page at paddr to - * the given address in the DMA address space for the domain. - */ -static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom, - unsigned long address, - phys_addr_t paddr, - int direction) -{ - u64 *pte, __pte; - - WARN_ON(address > dom->aperture_size); - - paddr &= PAGE_MASK; - - pte = dma_ops_get_pte(dom, address); - if (!pte) - return DMA_ERROR_CODE; - - __pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC; - - if (direction == DMA_TO_DEVICE) - __pte |= IOMMU_PTE_IR; - else if (direction == DMA_FROM_DEVICE) - __pte |= IOMMU_PTE_IW; - else if (direction == DMA_BIDIRECTIONAL) - __pte |= IOMMU_PTE_IR | IOMMU_PTE_IW; - - WARN_ON(*pte); - - *pte = __pte; - - return (dma_addr_t)address; -} - -/* - * The generic unmapping function for on page in the DMA address space. - */ -static void dma_ops_domain_unmap(struct dma_ops_domain *dom, - unsigned long address) -{ - struct aperture_range *aperture; - u64 *pte; - - if (address >= dom->aperture_size) - return; - - aperture = dom->aperture[APERTURE_RANGE_INDEX(address)]; - if (!aperture) - return; - - pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)]; - if (!pte) - return; - - pte += PM_LEVEL_INDEX(0, address); - - WARN_ON(!*pte); - - *pte = 0ULL; -} - -/* - * This function contains common code for mapping of a physically - * contiguous memory region into DMA address space. It is used by all - * mapping functions provided with this IOMMU driver. - * Must be called with the domain lock held. - */ -static dma_addr_t __map_single(struct device *dev, - struct dma_ops_domain *dma_dom, - phys_addr_t paddr, - size_t size, - int dir, - bool align, - u64 dma_mask) -{ - dma_addr_t offset = paddr & ~PAGE_MASK; - dma_addr_t address, start, ret; - unsigned int pages; - unsigned long align_mask = 0; - int i; - - pages = iommu_num_pages(paddr, size, PAGE_SIZE); - paddr &= PAGE_MASK; - - INC_STATS_COUNTER(total_map_requests); - - if (pages > 1) - INC_STATS_COUNTER(cross_page); - - if (align) - align_mask = (1UL << get_order(size)) - 1; - -retry: - address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask, - dma_mask); - if (unlikely(address == DMA_ERROR_CODE)) { - /* - * setting next_address here will let the address - * allocator only scan the new allocated range in the - * first run. This is a small optimization. - */ - dma_dom->next_address = dma_dom->aperture_size; - - if (alloc_new_range(dma_dom, false, GFP_ATOMIC)) - goto out; - - /* - * aperture was successfully enlarged by 128 MB, try - * allocation again - */ - goto retry; - } - - start = address; - for (i = 0; i < pages; ++i) { - ret = dma_ops_domain_map(dma_dom, start, paddr, dir); - if (ret == DMA_ERROR_CODE) - goto out_unmap; - - paddr += PAGE_SIZE; - start += PAGE_SIZE; - } - address += offset; - - ADD_STATS_COUNTER(alloced_io_mem, size); - - if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) { - domain_flush_tlb(&dma_dom->domain); - dma_dom->need_flush = false; - } else if (unlikely(amd_iommu_np_cache)) - domain_flush_pages(&dma_dom->domain, address, size); - -out: - return address; - -out_unmap: - - for (--i; i >= 0; --i) { - start -= PAGE_SIZE; - dma_ops_domain_unmap(dma_dom, start); - } - - dma_ops_free_addresses(dma_dom, address, pages); - - return DMA_ERROR_CODE; -} - -/* - * Does the reverse of the __map_single function. Must be called with - * the domain lock held too - */ -static void __unmap_single(struct dma_ops_domain *dma_dom, - dma_addr_t dma_addr, - size_t size, - int dir) -{ - dma_addr_t flush_addr; - dma_addr_t i, start; - unsigned int pages; - - if ((dma_addr == DMA_ERROR_CODE) || - (dma_addr + size > dma_dom->aperture_size)) - return; - - flush_addr = dma_addr; - pages = iommu_num_pages(dma_addr, size, PAGE_SIZE); - dma_addr &= PAGE_MASK; - start = dma_addr; - - for (i = 0; i < pages; ++i) { - dma_ops_domain_unmap(dma_dom, start); - start += PAGE_SIZE; - } - - SUB_STATS_COUNTER(alloced_io_mem, size); - - dma_ops_free_addresses(dma_dom, dma_addr, pages); - - if (amd_iommu_unmap_flush || dma_dom->need_flush) { - domain_flush_pages(&dma_dom->domain, flush_addr, size); - dma_dom->need_flush = false; - } -} - -/* - * The exported map_single function for dma_ops. - */ -static dma_addr_t map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - unsigned long flags; - struct protection_domain *domain; - dma_addr_t addr; - u64 dma_mask; - phys_addr_t paddr = page_to_phys(page) + offset; - - INC_STATS_COUNTER(cnt_map_single); - - domain = get_domain(dev); - if (PTR_ERR(domain) == -EINVAL) - return (dma_addr_t)paddr; - else if (IS_ERR(domain)) - return DMA_ERROR_CODE; - - dma_mask = *dev->dma_mask; - - spin_lock_irqsave(&domain->lock, flags); - - addr = __map_single(dev, domain->priv, paddr, size, dir, false, - dma_mask); - if (addr == DMA_ERROR_CODE) - goto out; - - domain_flush_complete(domain); - -out: - spin_unlock_irqrestore(&domain->lock, flags); - - return addr; -} - -/* - * The exported unmap_single function for dma_ops. - */ -static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) -{ - unsigned long flags; - struct protection_domain *domain; - - INC_STATS_COUNTER(cnt_unmap_single); - - domain = get_domain(dev); - if (IS_ERR(domain)) - return; - - spin_lock_irqsave(&domain->lock, flags); - - __unmap_single(domain->priv, dma_addr, size, dir); - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); -} - -/* - * This is a special map_sg function which is used if we should map a - * device which is not handled by an AMD IOMMU in the system. - */ -static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) -{ - struct scatterlist *s; - int i; - - for_each_sg(sglist, s, nelems, i) { - s->dma_address = (dma_addr_t)sg_phys(s); - s->dma_length = s->length; - } - - return nelems; -} - -/* - * The exported map_sg function for dma_ops (handles scatter-gather - * lists). - */ -static int map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - unsigned long flags; - struct protection_domain *domain; - int i; - struct scatterlist *s; - phys_addr_t paddr; - int mapped_elems = 0; - u64 dma_mask; - - INC_STATS_COUNTER(cnt_map_sg); - - domain = get_domain(dev); - if (PTR_ERR(domain) == -EINVAL) - return map_sg_no_iommu(dev, sglist, nelems, dir); - else if (IS_ERR(domain)) - return 0; - - dma_mask = *dev->dma_mask; - - spin_lock_irqsave(&domain->lock, flags); - - for_each_sg(sglist, s, nelems, i) { - paddr = sg_phys(s); - - s->dma_address = __map_single(dev, domain->priv, - paddr, s->length, dir, false, - dma_mask); - - if (s->dma_address) { - s->dma_length = s->length; - mapped_elems++; - } else - goto unmap; - } - - domain_flush_complete(domain); - -out: - spin_unlock_irqrestore(&domain->lock, flags); - - return mapped_elems; -unmap: - for_each_sg(sglist, s, mapped_elems, i) { - if (s->dma_address) - __unmap_single(domain->priv, s->dma_address, - s->dma_length, dir); - s->dma_address = s->dma_length = 0; - } - - mapped_elems = 0; - - goto out; -} - -/* - * The exported map_sg function for dma_ops (handles scatter-gather - * lists). - */ -static void unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - unsigned long flags; - struct protection_domain *domain; - struct scatterlist *s; - int i; - - INC_STATS_COUNTER(cnt_unmap_sg); - - domain = get_domain(dev); - if (IS_ERR(domain)) - return; - - spin_lock_irqsave(&domain->lock, flags); - - for_each_sg(sglist, s, nelems, i) { - __unmap_single(domain->priv, s->dma_address, - s->dma_length, dir); - s->dma_address = s->dma_length = 0; - } - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); -} - -/* - * The exported alloc_coherent function for dma_ops. - */ -static void *alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag) -{ - unsigned long flags; - void *virt_addr; - struct protection_domain *domain; - phys_addr_t paddr; - u64 dma_mask = dev->coherent_dma_mask; - - INC_STATS_COUNTER(cnt_alloc_coherent); - - domain = get_domain(dev); - if (PTR_ERR(domain) == -EINVAL) { - virt_addr = (void *)__get_free_pages(flag, get_order(size)); - *dma_addr = __pa(virt_addr); - return virt_addr; - } else if (IS_ERR(domain)) - return NULL; - - dma_mask = dev->coherent_dma_mask; - flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - flag |= __GFP_ZERO; - - virt_addr = (void *)__get_free_pages(flag, get_order(size)); - if (!virt_addr) - return NULL; - - paddr = virt_to_phys(virt_addr); - - if (!dma_mask) - dma_mask = *dev->dma_mask; - - spin_lock_irqsave(&domain->lock, flags); - - *dma_addr = __map_single(dev, domain->priv, paddr, - size, DMA_BIDIRECTIONAL, true, dma_mask); - - if (*dma_addr == DMA_ERROR_CODE) { - spin_unlock_irqrestore(&domain->lock, flags); - goto out_free; - } - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); - - return virt_addr; - -out_free: - - free_pages((unsigned long)virt_addr, get_order(size)); - - return NULL; -} - -/* - * The exported free_coherent function for dma_ops. - */ -static void free_coherent(struct device *dev, size_t size, - void *virt_addr, dma_addr_t dma_addr) -{ - unsigned long flags; - struct protection_domain *domain; - - INC_STATS_COUNTER(cnt_free_coherent); - - domain = get_domain(dev); - if (IS_ERR(domain)) - goto free_mem; - - spin_lock_irqsave(&domain->lock, flags); - - __unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); - -free_mem: - free_pages((unsigned long)virt_addr, get_order(size)); -} - -/* - * This function is called by the DMA layer to find out if we can handle a - * particular device. It is part of the dma_ops. - */ -static int amd_iommu_dma_supported(struct device *dev, u64 mask) -{ - return check_device(dev); -} - -/* - * The function for pre-allocating protection domains. - * - * If the driver core informs the DMA layer if a driver grabs a device - * we don't need to preallocate the protection domains anymore. - * For now we have to. - */ -static void prealloc_protection_domains(void) -{ - struct pci_dev *dev = NULL; - struct dma_ops_domain *dma_dom; - u16 devid; - - for_each_pci_dev(dev) { - - /* Do we handle this device? */ - if (!check_device(&dev->dev)) - continue; - - /* Is there already any domain for it? */ - if (domain_for_device(&dev->dev)) - continue; - - devid = get_device_id(&dev->dev); - - dma_dom = dma_ops_domain_alloc(); - if (!dma_dom) - continue; - init_unity_mappings_for_device(dma_dom, devid); - dma_dom->target_dev = devid; - - attach_device(&dev->dev, &dma_dom->domain); - - list_add_tail(&dma_dom->list, &iommu_pd_list); - } -} - -static struct dma_map_ops amd_iommu_dma_ops = { - .alloc_coherent = alloc_coherent, - .free_coherent = free_coherent, - .map_page = map_page, - .unmap_page = unmap_page, - .map_sg = map_sg, - .unmap_sg = unmap_sg, - .dma_supported = amd_iommu_dma_supported, -}; - -/* - * The function which clues the AMD IOMMU driver into dma_ops. - */ - -void __init amd_iommu_init_api(void) -{ - register_iommu(&amd_iommu_ops); -} - -int __init amd_iommu_init_dma_ops(void) -{ - struct amd_iommu *iommu; - int ret; - - /* - * first allocate a default protection domain for every IOMMU we - * found in the system. Devices not assigned to any other - * protection domain will be assigned to the default one. - */ - for_each_iommu(iommu) { - iommu->default_dom = dma_ops_domain_alloc(); - if (iommu->default_dom == NULL) - return -ENOMEM; - iommu->default_dom->domain.flags |= PD_DEFAULT_MASK; - ret = iommu_init_unity_mappings(iommu); - if (ret) - goto free_domains; - } - - /* - * Pre-allocate the protection domains for each device. - */ - prealloc_protection_domains(); - - iommu_detected = 1; - swiotlb = 0; - - /* Make the driver finally visible to the drivers */ - dma_ops = &amd_iommu_dma_ops; - - amd_iommu_stats_init(); - - return 0; - -free_domains: - - for_each_iommu(iommu) { - if (iommu->default_dom) - dma_ops_domain_free(iommu->default_dom); - } - - return ret; -} - -/***************************************************************************** - * - * The following functions belong to the exported interface of AMD IOMMU - * - * This interface allows access to lower level functions of the IOMMU - * like protection domain handling and assignement of devices to domains - * which is not possible with the dma_ops interface. - * - *****************************************************************************/ - -static void cleanup_domain(struct protection_domain *domain) -{ - struct iommu_dev_data *dev_data, *next; - unsigned long flags; - - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - - list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { - struct device *dev = dev_data->dev; - - __detach_device(dev); - atomic_set(&dev_data->bind, 0); - } - - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); -} - -static void protection_domain_free(struct protection_domain *domain) -{ - if (!domain) - return; - - del_domain_from_list(domain); - - if (domain->id) - domain_id_free(domain->id); - - kfree(domain); -} - -static struct protection_domain *protection_domain_alloc(void) -{ - struct protection_domain *domain; - - domain = kzalloc(sizeof(*domain), GFP_KERNEL); - if (!domain) - return NULL; - - spin_lock_init(&domain->lock); - mutex_init(&domain->api_lock); - domain->id = domain_id_alloc(); - if (!domain->id) - goto out_err; - INIT_LIST_HEAD(&domain->dev_list); - - add_domain_to_list(domain); - - return domain; - -out_err: - kfree(domain); - - return NULL; -} - -static int amd_iommu_domain_init(struct iommu_domain *dom) -{ - struct protection_domain *domain; - - domain = protection_domain_alloc(); - if (!domain) - goto out_free; - - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!domain->pt_root) - goto out_free; - - dom->priv = domain; - - return 0; - -out_free: - protection_domain_free(domain); - - return -ENOMEM; -} - -static void amd_iommu_domain_destroy(struct iommu_domain *dom) -{ - struct protection_domain *domain = dom->priv; - - if (!domain) - return; - - if (domain->dev_cnt > 0) - cleanup_domain(domain); - - BUG_ON(domain->dev_cnt != 0); - - free_pagetable(domain); - - protection_domain_free(domain); - - dom->priv = NULL; -} - -static void amd_iommu_detach_device(struct iommu_domain *dom, - struct device *dev) -{ - struct iommu_dev_data *dev_data = dev->archdata.iommu; - struct amd_iommu *iommu; - u16 devid; - - if (!check_device(dev)) - return; - - devid = get_device_id(dev); - - if (dev_data->domain != NULL) - detach_device(dev); - - iommu = amd_iommu_rlookup_table[devid]; - if (!iommu) - return; - - device_flush_dte(dev); - iommu_completion_wait(iommu); -} - -static int amd_iommu_attach_device(struct iommu_domain *dom, - struct device *dev) -{ - struct protection_domain *domain = dom->priv; - struct iommu_dev_data *dev_data; - struct amd_iommu *iommu; - int ret; - u16 devid; - - if (!check_device(dev)) - return -EINVAL; - - dev_data = dev->archdata.iommu; - - devid = get_device_id(dev); - - iommu = amd_iommu_rlookup_table[devid]; - if (!iommu) - return -EINVAL; - - if (dev_data->domain) - detach_device(dev); - - ret = attach_device(dev, domain); - - iommu_completion_wait(iommu); - - return ret; -} - -static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, - phys_addr_t paddr, int gfp_order, int iommu_prot) -{ - unsigned long page_size = 0x1000UL << gfp_order; - struct protection_domain *domain = dom->priv; - int prot = 0; - int ret; - - if (iommu_prot & IOMMU_READ) - prot |= IOMMU_PROT_IR; - if (iommu_prot & IOMMU_WRITE) - prot |= IOMMU_PROT_IW; - - mutex_lock(&domain->api_lock); - ret = iommu_map_page(domain, iova, paddr, prot, page_size); - mutex_unlock(&domain->api_lock); - - return ret; -} - -static int amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, - int gfp_order) -{ - struct protection_domain *domain = dom->priv; - unsigned long page_size, unmap_size; - - page_size = 0x1000UL << gfp_order; - - mutex_lock(&domain->api_lock); - unmap_size = iommu_unmap_page(domain, iova, page_size); - mutex_unlock(&domain->api_lock); - - domain_flush_tlb_pde(domain); - - return get_order(unmap_size); -} - -static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, - unsigned long iova) -{ - struct protection_domain *domain = dom->priv; - unsigned long offset_mask; - phys_addr_t paddr; - u64 *pte, __pte; - - pte = fetch_pte(domain, iova); - - if (!pte || !IOMMU_PTE_PRESENT(*pte)) - return 0; - - if (PM_PTE_LEVEL(*pte) == 0) - offset_mask = PAGE_SIZE - 1; - else - offset_mask = PTE_PAGE_SIZE(*pte) - 1; - - __pte = *pte & PM_ADDR_MASK; - paddr = (__pte & ~offset_mask) | (iova & offset_mask); - - return paddr; -} - -static int amd_iommu_domain_has_cap(struct iommu_domain *domain, - unsigned long cap) -{ - switch (cap) { - case IOMMU_CAP_CACHE_COHERENCY: - return 1; - } - - return 0; -} - -static struct iommu_ops amd_iommu_ops = { - .domain_init = amd_iommu_domain_init, - .domain_destroy = amd_iommu_domain_destroy, - .attach_dev = amd_iommu_attach_device, - .detach_dev = amd_iommu_detach_device, - .map = amd_iommu_map, - .unmap = amd_iommu_unmap, - .iova_to_phys = amd_iommu_iova_to_phys, - .domain_has_cap = amd_iommu_domain_has_cap, -}; - -/***************************************************************************** - * - * The next functions do a basic initialization of IOMMU for pass through - * mode - * - * In passthrough mode the IOMMU is initialized and enabled but not used for - * DMA-API translation. - * - *****************************************************************************/ - -int __init amd_iommu_init_passthrough(void) -{ - struct amd_iommu *iommu; - struct pci_dev *dev = NULL; - u16 devid; - - /* allocate passthrough domain */ - pt_domain = protection_domain_alloc(); - if (!pt_domain) - return -ENOMEM; - - pt_domain->mode |= PAGE_MODE_NONE; - - for_each_pci_dev(dev) { - if (!check_device(&dev->dev)) - continue; - - devid = get_device_id(&dev->dev); - - iommu = amd_iommu_rlookup_table[devid]; - if (!iommu) - continue; - - attach_device(&dev->dev, pt_domain); - } - - pr_info("AMD-Vi: Initialized for Passthrough Mode\n"); - - return 0; -} diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c deleted file mode 100644 index 9179c21..0000000 --- a/arch/x86/kernel/amd_iommu_init.c +++ /dev/null @@ -1,1572 +0,0 @@ -/* - * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. - * Author: Joerg Roedel <joerg.roedel@amd.com> - * Leo Duran <leo.duran@amd.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/pci.h> -#include <linux/acpi.h> -#include <linux/list.h> -#include <linux/slab.h> -#include <linux/syscore_ops.h> -#include <linux/interrupt.h> -#include <linux/msi.h> -#include <asm/pci-direct.h> -#include <asm/amd_iommu_proto.h> -#include <asm/amd_iommu_types.h> -#include <asm/amd_iommu.h> -#include <asm/iommu.h> -#include <asm/gart.h> -#include <asm/x86_init.h> -#include <asm/iommu_table.h> -/* - * definitions for the ACPI scanning code - */ -#define IVRS_HEADER_LENGTH 48 - -#define ACPI_IVHD_TYPE 0x10 -#define ACPI_IVMD_TYPE_ALL 0x20 -#define ACPI_IVMD_TYPE 0x21 -#define ACPI_IVMD_TYPE_RANGE 0x22 - -#define IVHD_DEV_ALL 0x01 -#define IVHD_DEV_SELECT 0x02 -#define IVHD_DEV_SELECT_RANGE_START 0x03 -#define IVHD_DEV_RANGE_END 0x04 -#define IVHD_DEV_ALIAS 0x42 -#define IVHD_DEV_ALIAS_RANGE 0x43 -#define IVHD_DEV_EXT_SELECT 0x46 -#define IVHD_DEV_EXT_SELECT_RANGE 0x47 - -#define IVHD_FLAG_HT_TUN_EN_MASK 0x01 -#define IVHD_FLAG_PASSPW_EN_MASK 0x02 -#define IVHD_FLAG_RESPASSPW_EN_MASK 0x04 -#define IVHD_FLAG_ISOC_EN_MASK 0x08 - -#define IVMD_FLAG_EXCL_RANGE 0x08 -#define IVMD_FLAG_UNITY_MAP 0x01 - -#define ACPI_DEVFLAG_INITPASS 0x01 -#define ACPI_DEVFLAG_EXTINT 0x02 -#define ACPI_DEVFLAG_NMI 0x04 -#define ACPI_DEVFLAG_SYSMGT1 0x10 -#define ACPI_DEVFLAG_SYSMGT2 0x20 -#define ACPI_DEVFLAG_LINT0 0x40 -#define ACPI_DEVFLAG_LINT1 0x80 -#define ACPI_DEVFLAG_ATSDIS 0x10000000 - -/* - * ACPI table definitions - * - * These data structures are laid over the table to parse the important values - * out of it. - */ - -/* - * structure describing one IOMMU in the ACPI table. Typically followed by one - * or more ivhd_entrys. - */ -struct ivhd_header { - u8 type; - u8 flags; - u16 length; - u16 devid; - u16 cap_ptr; - u64 mmio_phys; - u16 pci_seg; - u16 info; - u32 reserved; -} __attribute__((packed)); - -/* - * A device entry describing which devices a specific IOMMU translates and - * which requestor ids they use. - */ -struct ivhd_entry { - u8 type; - u16 devid; - u8 flags; - u32 ext; -} __attribute__((packed)); - -/* - * An AMD IOMMU memory definition structure. It defines things like exclusion - * ranges for devices and regions that should be unity mapped. - */ -struct ivmd_header { - u8 type; - u8 flags; - u16 length; - u16 devid; - u16 aux; - u64 resv; - u64 range_start; - u64 range_length; -} __attribute__((packed)); - -bool amd_iommu_dump; - -static int __initdata amd_iommu_detected; -static bool __initdata amd_iommu_disabled; - -u16 amd_iommu_last_bdf; /* largest PCI device id we have - to handle */ -LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings - we find in ACPI */ -bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ - -LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the - system */ - -/* Array to assign indices to IOMMUs*/ -struct amd_iommu *amd_iommus[MAX_IOMMUS]; -int amd_iommus_present; - -/* IOMMUs have a non-present cache? */ -bool amd_iommu_np_cache __read_mostly; -bool amd_iommu_iotlb_sup __read_mostly = true; - -/* - * The ACPI table parsing functions set this variable on an error - */ -static int __initdata amd_iommu_init_err; - -/* - * List of protection domains - used during resume - */ -LIST_HEAD(amd_iommu_pd_list); -spinlock_t amd_iommu_pd_lock; - -/* - * Pointer to the device table which is shared by all AMD IOMMUs - * it is indexed by the PCI device id or the HT unit id and contains - * information about the domain the device belongs to as well as the - * page table root pointer. - */ -struct dev_table_entry *amd_iommu_dev_table; - -/* - * The alias table is a driver specific data structure which contains the - * mappings of the PCI device ids to the actual requestor ids on the IOMMU. - * More than one device can share the same requestor id. - */ -u16 *amd_iommu_alias_table; - -/* - * The rlookup table is used to find the IOMMU which is responsible - * for a specific device. It is also indexed by the PCI device id. - */ -struct amd_iommu **amd_iommu_rlookup_table; - -/* - * AMD IOMMU allows up to 2^16 differend protection domains. This is a bitmap - * to know which ones are already in use. - */ -unsigned long *amd_iommu_pd_alloc_bitmap; - -static u32 dev_table_size; /* size of the device table */ -static u32 alias_table_size; /* size of the alias table */ -static u32 rlookup_table_size; /* size if the rlookup table */ - -/* - * This function flushes all internal caches of - * the IOMMU used by this driver. - */ -extern void iommu_flush_all_caches(struct amd_iommu *iommu); - -static inline void update_last_devid(u16 devid) -{ - if (devid > amd_iommu_last_bdf) - amd_iommu_last_bdf = devid; -} - -static inline unsigned long tbl_size(int entry_size) -{ - unsigned shift = PAGE_SHIFT + - get_order(((int)amd_iommu_last_bdf + 1) * entry_size); - - return 1UL << shift; -} - -/* Access to l1 and l2 indexed register spaces */ - -static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address) -{ - u32 val; - - pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); - pci_read_config_dword(iommu->dev, 0xfc, &val); - return val; -} - -static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val) -{ - pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31)); - pci_write_config_dword(iommu->dev, 0xfc, val); - pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); -} - -static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address) -{ - u32 val; - - pci_write_config_dword(iommu->dev, 0xf0, address); - pci_read_config_dword(iommu->dev, 0xf4, &val); - return val; -} - -static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val) -{ - pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8)); - pci_write_config_dword(iommu->dev, 0xf4, val); -} - -/**************************************************************************** - * - * AMD IOMMU MMIO register space handling functions - * - * These functions are used to program the IOMMU device registers in - * MMIO space required for that driver. - * - ****************************************************************************/ - -/* - * This function set the exclusion range in the IOMMU. DMA accesses to the - * exclusion range are passed through untranslated - */ -static void iommu_set_exclusion_range(struct amd_iommu *iommu) -{ - u64 start = iommu->exclusion_start & PAGE_MASK; - u64 limit = (start + iommu->exclusion_length) & PAGE_MASK; - u64 entry; - - if (!iommu->exclusion_start) - return; - - entry = start | MMIO_EXCL_ENABLE_MASK; - memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET, - &entry, sizeof(entry)); - - entry = limit; - memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET, - &entry, sizeof(entry)); -} - -/* Programs the physical address of the device table into the IOMMU hardware */ -static void __init iommu_set_device_table(struct amd_iommu *iommu) -{ - u64 entry; - - BUG_ON(iommu->mmio_base == NULL); - - entry = virt_to_phys(amd_iommu_dev_table); - entry |= (dev_table_size >> 12) - 1; - memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET, - &entry, sizeof(entry)); -} - -/* Generic functions to enable/disable certain features of the IOMMU. */ -static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit) -{ - u32 ctrl; - - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); - ctrl |= (1 << bit); - writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); -} - -static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit) -{ - u32 ctrl; - - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); - ctrl &= ~(1 << bit); - writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); -} - -/* Function to enable the hardware */ -static void iommu_enable(struct amd_iommu *iommu) -{ - static const char * const feat_str[] = { - "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", - "IA", "GA", "HE", "PC", NULL - }; - int i; - - printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx", - dev_name(&iommu->dev->dev), iommu->cap_ptr); - - if (iommu->cap & (1 << IOMMU_CAP_EFR)) { - printk(KERN_CONT " extended features: "); - for (i = 0; feat_str[i]; ++i) - if (iommu_feature(iommu, (1ULL << i))) - printk(KERN_CONT " %s", feat_str[i]); - } - printk(KERN_CONT "\n"); - - iommu_feature_enable(iommu, CONTROL_IOMMU_EN); -} - -static void iommu_disable(struct amd_iommu *iommu) -{ - /* Disable command buffer */ - iommu_feature_disable(iommu, CONTROL_CMDBUF_EN); - - /* Disable event logging and event interrupts */ - iommu_feature_disable(iommu, CONTROL_EVT_INT_EN); - iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); - - /* Disable IOMMU hardware itself */ - iommu_feature_disable(iommu, CONTROL_IOMMU_EN); -} - -/* - * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in - * the system has one. - */ -static u8 * __init iommu_map_mmio_space(u64 address) -{ - u8 *ret; - - if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) { - pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n", - address); - pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n"); - return NULL; - } - - ret = ioremap_nocache(address, MMIO_REGION_LENGTH); - if (ret != NULL) - return ret; - - release_mem_region(address, MMIO_REGION_LENGTH); - - return NULL; -} - -static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu) -{ - if (iommu->mmio_base) - iounmap(iommu->mmio_base); - release_mem_region(iommu->mmio_phys, MMIO_REGION_LENGTH); -} - -/**************************************************************************** - * - * The functions below belong to the first pass of AMD IOMMU ACPI table - * parsing. In this pass we try to find out the highest device id this - * code has to handle. Upon this information the size of the shared data - * structures is determined later. - * - ****************************************************************************/ - -/* - * This function calculates the length of a given IVHD entry - */ -static inline int ivhd_entry_length(u8 *ivhd) -{ - return 0x04 << (*ivhd >> 6); -} - -/* - * This function reads the last device id the IOMMU has to handle from the PCI - * capability header for this IOMMU - */ -static int __init find_last_devid_on_pci(int bus, int dev, int fn, int cap_ptr) -{ - u32 cap; - - cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET); - update_last_devid(calc_devid(MMIO_GET_BUS(cap), MMIO_GET_LD(cap))); - - return 0; -} - -/* - * After reading the highest device id from the IOMMU PCI capability header - * this function looks if there is a higher device id defined in the ACPI table - */ -static int __init find_last_devid_from_ivhd(struct ivhd_header *h) -{ - u8 *p = (void *)h, *end = (void *)h; - struct ivhd_entry *dev; - - p += sizeof(*h); - end += h->length; - - find_last_devid_on_pci(PCI_BUS(h->devid), - PCI_SLOT(h->devid), - PCI_FUNC(h->devid), - h->cap_ptr); - - while (p < end) { - dev = (struct ivhd_entry *)p; - switch (dev->type) { - case IVHD_DEV_SELECT: - case IVHD_DEV_RANGE_END: - case IVHD_DEV_ALIAS: - case IVHD_DEV_EXT_SELECT: - /* all the above subfield types refer to device ids */ - update_last_devid(dev->devid); - break; - default: - break; - } - p += ivhd_entry_length(p); - } - - WARN_ON(p != end); - - return 0; -} - -/* - * Iterate over all IVHD entries in the ACPI table and find the highest device - * id which we need to handle. This is the first of three functions which parse - * the ACPI table. So we check the checksum here. - */ -static int __init find_last_devid_acpi(struct acpi_table_header *table) -{ - int i; - u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table; - struct ivhd_header *h; - - /* - * Validate checksum here so we don't need to do it when - * we actually parse the table - */ - for (i = 0; i < table->length; ++i) - checksum += p[i]; - if (checksum != 0) { - /* ACPI table corrupt */ - amd_iommu_init_err = -ENODEV; - return 0; - } - - p += IVRS_HEADER_LENGTH; - - end += table->length; - while (p < end) { - h = (struct ivhd_header *)p; - switch (h->type) { - case ACPI_IVHD_TYPE: - find_last_devid_from_ivhd(h); - break; - default: - break; - } - p += h->length; - } - WARN_ON(p != end); - - return 0; -} - -/**************************************************************************** - * - * The following functions belong the the code path which parses the ACPI table - * the second time. In this ACPI parsing iteration we allocate IOMMU specific - * data structures, initialize the device/alias/rlookup table and also - * basically initialize the hardware. - * - ****************************************************************************/ - -/* - * Allocates the command buffer. This buffer is per AMD IOMMU. We can - * write commands to that buffer later and the IOMMU will execute them - * asynchronously - */ -static u8 * __init alloc_command_buffer(struct amd_iommu *iommu) -{ - u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(CMD_BUFFER_SIZE)); - - if (cmd_buf == NULL) - return NULL; - - iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED; - - return cmd_buf; -} - -/* - * This function resets the command buffer if the IOMMU stopped fetching - * commands from it. - */ -void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu) -{ - iommu_feature_disable(iommu, CONTROL_CMDBUF_EN); - - writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); - writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); - - iommu_feature_enable(iommu, CONTROL_CMDBUF_EN); -} - -/* - * This function writes the command buffer address to the hardware and - * enables it. - */ -static void iommu_enable_command_buffer(struct amd_iommu *iommu) -{ - u64 entry; - - BUG_ON(iommu->cmd_buf == NULL); - - entry = (u64)virt_to_phys(iommu->cmd_buf); - entry |= MMIO_CMD_SIZE_512; - - memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET, - &entry, sizeof(entry)); - - amd_iommu_reset_cmd_buffer(iommu); - iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED); -} - -static void __init free_command_buffer(struct amd_iommu *iommu) -{ - free_pages((unsigned long)iommu->cmd_buf, - get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED))); -} - -/* allocates the memory where the IOMMU will log its events to */ -static u8 * __init alloc_event_buffer(struct amd_iommu *iommu) -{ - iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(EVT_BUFFER_SIZE)); - - if (iommu->evt_buf == NULL) - return NULL; - - iommu->evt_buf_size = EVT_BUFFER_SIZE; - - return iommu->evt_buf; -} - -static void iommu_enable_event_buffer(struct amd_iommu *iommu) -{ - u64 entry; - - BUG_ON(iommu->evt_buf == NULL); - - entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK; - - memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, - &entry, sizeof(entry)); - - /* set head and tail to zero manually */ - writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); - writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); - - iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); -} - -static void __init free_event_buffer(struct amd_iommu *iommu) -{ - free_pages((unsigned long)iommu->evt_buf, get_order(EVT_BUFFER_SIZE)); -} - -/* sets a specific bit in the device table entry. */ -static void set_dev_entry_bit(u16 devid, u8 bit) -{ - int i = (bit >> 5) & 0x07; - int _bit = bit & 0x1f; - - amd_iommu_dev_table[devid].data[i] |= (1 << _bit); -} - -static int get_dev_entry_bit(u16 devid, u8 bit) -{ - int i = (bit >> 5) & 0x07; - int _bit = bit & 0x1f; - - return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit; -} - - -void amd_iommu_apply_erratum_63(u16 devid) -{ - int sysmgt; - - sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) | - (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1); - - if (sysmgt == 0x01) - set_dev_entry_bit(devid, DEV_ENTRY_IW); -} - -/* Writes the specific IOMMU for a device into the rlookup table */ -static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid) -{ - amd_iommu_rlookup_table[devid] = iommu; -} - -/* - * This function takes the device specific flags read from the ACPI - * table and sets up the device table entry with that information - */ -static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu, - u16 devid, u32 flags, u32 ext_flags) -{ - if (flags & ACPI_DEVFLAG_INITPASS) - set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS); - if (flags & ACPI_DEVFLAG_EXTINT) - set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS); - if (flags & ACPI_DEVFLAG_NMI) - set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS); - if (flags & ACPI_DEVFLAG_SYSMGT1) - set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1); - if (flags & ACPI_DEVFLAG_SYSMGT2) - set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2); - if (flags & ACPI_DEVFLAG_LINT0) - set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS); - if (flags & ACPI_DEVFLAG_LINT1) - set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS); - - amd_iommu_apply_erratum_63(devid); - - set_iommu_for_device(iommu, devid); -} - -/* - * Reads the device exclusion range from ACPI and initialize IOMMU with - * it - */ -static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) -{ - struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; - - if (!(m->flags & IVMD_FLAG_EXCL_RANGE)) - return; - - if (iommu) { - /* - * We only can configure exclusion ranges per IOMMU, not - * per device. But we can enable the exclusion range per - * device. This is done here - */ - set_dev_entry_bit(m->devid, DEV_ENTRY_EX); - iommu->exclusion_start = m->range_start; - iommu->exclusion_length = m->range_length; - } -} - -/* - * This function reads some important data from the IOMMU PCI space and - * initializes the driver data structure with it. It reads the hardware - * capabilities and the first/last device entries - */ -static void __init init_iommu_from_pci(struct amd_iommu *iommu) -{ - int cap_ptr = iommu->cap_ptr; - u32 range, misc, low, high; - int i, j; - - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, - &iommu->cap); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, - &range); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET, - &misc); - - iommu->first_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_FD(range)); - iommu->last_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_LD(range)); - iommu->evt_msi_num = MMIO_MSI_NUM(misc); - - if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) - amd_iommu_iotlb_sup = false; - - /* read extended feature bits */ - low = readl(iommu->mmio_base + MMIO_EXT_FEATURES); - high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4); - - iommu->features = ((u64)high << 32) | low; - - if (!is_rd890_iommu(iommu->dev)) - return; - - /* - * Some rd890 systems may not be fully reconfigured by the BIOS, so - * it's necessary for us to store this information so it can be - * reprogrammed on resume - */ - - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, - &iommu->stored_addr_lo); - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, - &iommu->stored_addr_hi); - - /* Low bit locks writes to configuration space */ - iommu->stored_addr_lo &= ~1; - - for (i = 0; i < 6; i++) - for (j = 0; j < 0x12; j++) - iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); - - for (i = 0; i < 0x83; i++) - iommu->stored_l2[i] = iommu_read_l2(iommu, i); -} - -/* - * Takes a pointer to an AMD IOMMU entry in the ACPI table and - * initializes the hardware and our data structures with it. - */ -static void __init init_iommu_from_acpi(struct amd_iommu *iommu, - struct ivhd_header *h) -{ - u8 *p = (u8 *)h; - u8 *end = p, flags = 0; - u16 dev_i, devid = 0, devid_start = 0, devid_to = 0; - u32 ext_flags = 0; - bool alias = false; - struct ivhd_entry *e; - - /* - * First save the recommended feature enable bits from ACPI - */ - iommu->acpi_flags = h->flags; - - /* - * Done. Now parse the device entries - */ - p += sizeof(struct ivhd_header); - end += h->length; - - - while (p < end) { - e = (struct ivhd_entry *)p; - switch (e->type) { - case IVHD_DEV_ALL: - - DUMP_printk(" DEV_ALL\t\t\t first devid: %02x:%02x.%x" - " last device %02x:%02x.%x flags: %02x\n", - PCI_BUS(iommu->first_device), - PCI_SLOT(iommu->first_device), - PCI_FUNC(iommu->first_device), - PCI_BUS(iommu->last_device), - PCI_SLOT(iommu->last_device), - PCI_FUNC(iommu->last_device), - e->flags); - - for (dev_i = iommu->first_device; - dev_i <= iommu->last_device; ++dev_i) - set_dev_entry_from_acpi(iommu, dev_i, - e->flags, 0); - break; - case IVHD_DEV_SELECT: - - DUMP_printk(" DEV_SELECT\t\t\t devid: %02x:%02x.%x " - "flags: %02x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags); - - devid = e->devid; - set_dev_entry_from_acpi(iommu, devid, e->flags, 0); - break; - case IVHD_DEV_SELECT_RANGE_START: - - DUMP_printk(" DEV_SELECT_RANGE_START\t " - "devid: %02x:%02x.%x flags: %02x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags); - - devid_start = e->devid; - flags = e->flags; - ext_flags = 0; - alias = false; - break; - case IVHD_DEV_ALIAS: - - DUMP_printk(" DEV_ALIAS\t\t\t devid: %02x:%02x.%x " - "flags: %02x devid_to: %02x:%02x.%x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags, - PCI_BUS(e->ext >> 8), - PCI_SLOT(e->ext >> 8), - PCI_FUNC(e->ext >> 8)); - - devid = e->devid; - devid_to = e->ext >> 8; - set_dev_entry_from_acpi(iommu, devid , e->flags, 0); - set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0); - amd_iommu_alias_table[devid] = devid_to; - break; - case IVHD_DEV_ALIAS_RANGE: - - DUMP_printk(" DEV_ALIAS_RANGE\t\t " - "devid: %02x:%02x.%x flags: %02x " - "devid_to: %02x:%02x.%x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags, - PCI_BUS(e->ext >> 8), - PCI_SLOT(e->ext >> 8), - PCI_FUNC(e->ext >> 8)); - - devid_start = e->devid; - flags = e->flags; - devid_to = e->ext >> 8; - ext_flags = 0; - alias = true; - break; - case IVHD_DEV_EXT_SELECT: - - DUMP_printk(" DEV_EXT_SELECT\t\t devid: %02x:%02x.%x " - "flags: %02x ext: %08x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags, e->ext); - - devid = e->devid; - set_dev_entry_from_acpi(iommu, devid, e->flags, - e->ext); - break; - case IVHD_DEV_EXT_SELECT_RANGE: - - DUMP_printk(" DEV_EXT_SELECT_RANGE\t devid: " - "%02x:%02x.%x flags: %02x ext: %08x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid), - e->flags, e->ext); - - devid_start = e->devid; - flags = e->flags; - ext_flags = e->ext; - alias = false; - break; - case IVHD_DEV_RANGE_END: - - DUMP_printk(" DEV_RANGE_END\t\t devid: %02x:%02x.%x\n", - PCI_BUS(e->devid), - PCI_SLOT(e->devid), - PCI_FUNC(e->devid)); - - devid = e->devid; - for (dev_i = devid_start; dev_i <= devid; ++dev_i) { - if (alias) { - amd_iommu_alias_table[dev_i] = devid_to; - set_dev_entry_from_acpi(iommu, - devid_to, flags, ext_flags); - } - set_dev_entry_from_acpi(iommu, dev_i, - flags, ext_flags); - } - break; - default: - break; - } - - p += ivhd_entry_length(p); - } -} - -/* Initializes the device->iommu mapping for the driver */ -static int __init init_iommu_devices(struct amd_iommu *iommu) -{ - u16 i; - - for (i = iommu->first_device; i <= iommu->last_device; ++i) - set_iommu_for_device(iommu, i); - - return 0; -} - -static void __init free_iommu_one(struct amd_iommu *iommu) -{ - free_command_buffer(iommu); - free_event_buffer(iommu); - iommu_unmap_mmio_space(iommu); -} - -static void __init free_iommu_all(void) -{ - struct amd_iommu *iommu, *next; - - for_each_iommu_safe(iommu, next) { - list_del(&iommu->list); - free_iommu_one(iommu); - kfree(iommu); - } -} - -/* - * This function clues the initialization function for one IOMMU - * together and also allocates the command buffer and programs the - * hardware. It does NOT enable the IOMMU. This is done afterwards. - */ -static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) -{ - spin_lock_init(&iommu->lock); - - /* Add IOMMU to internal data structures */ - list_add_tail(&iommu->list, &amd_iommu_list); - iommu->index = amd_iommus_present++; - - if (unlikely(iommu->index >= MAX_IOMMUS)) { - WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n"); - return -ENOSYS; - } - - /* Index is fine - add IOMMU to the array */ - amd_iommus[iommu->index] = iommu; - - /* - * Copy data from ACPI table entry to the iommu struct - */ - iommu->dev = pci_get_bus_and_slot(PCI_BUS(h->devid), h->devid & 0xff); - if (!iommu->dev) - return 1; - - iommu->cap_ptr = h->cap_ptr; - iommu->pci_seg = h->pci_seg; - iommu->mmio_phys = h->mmio_phys; - iommu->mmio_base = iommu_map_mmio_space(h->mmio_phys); - if (!iommu->mmio_base) - return -ENOMEM; - - iommu->cmd_buf = alloc_command_buffer(iommu); - if (!iommu->cmd_buf) - return -ENOMEM; - - iommu->evt_buf = alloc_event_buffer(iommu); - if (!iommu->evt_buf) - return -ENOMEM; - - iommu->int_enabled = false; - - init_iommu_from_pci(iommu); - init_iommu_from_acpi(iommu, h); - init_iommu_devices(iommu); - - if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) - amd_iommu_np_cache = true; - - return pci_enable_device(iommu->dev); -} - -/* - * Iterates over all IOMMU entries in the ACPI table, allocates the - * IOMMU structure and initializes it with init_iommu_one() - */ -static int __init init_iommu_all(struct acpi_table_header *table) -{ - u8 *p = (u8 *)table, *end = (u8 *)table; - struct ivhd_header *h; - struct amd_iommu *iommu; - int ret; - - end += table->length; - p += IVRS_HEADER_LENGTH; - - while (p < end) { - h = (struct ivhd_header *)p; - switch (*p) { - case ACPI_IVHD_TYPE: - - DUMP_printk("device: %02x:%02x.%01x cap: %04x " - "seg: %d flags: %01x info %04x\n", - PCI_BUS(h->devid), PCI_SLOT(h->devid), - PCI_FUNC(h->devid), h->cap_ptr, - h->pci_seg, h->flags, h->info); - DUMP_printk(" mmio-addr: %016llx\n", - h->mmio_phys); - - iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); - if (iommu == NULL) { - amd_iommu_init_err = -ENOMEM; - return 0; - } - - ret = init_iommu_one(iommu, h); - if (ret) { - amd_iommu_init_err = ret; - return 0; - } - break; - default: - break; - } - p += h->length; - - } - WARN_ON(p != end); - - return 0; -} - -/**************************************************************************** - * - * The following functions initialize the MSI interrupts for all IOMMUs - * in the system. Its a bit challenging because there could be multiple - * IOMMUs per PCI BDF but we can call pci_enable_msi(x) only once per - * pci_dev. - * - ****************************************************************************/ - -static int iommu_setup_msi(struct amd_iommu *iommu) -{ - int r; - - if (pci_enable_msi(iommu->dev)) - return 1; - - r = request_threaded_irq(iommu->dev->irq, - amd_iommu_int_handler, - amd_iommu_int_thread, - 0, "AMD-Vi", - iommu->dev); - - if (r) { - pci_disable_msi(iommu->dev); - return 1; - } - - iommu->int_enabled = true; - iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); - - return 0; -} - -static int iommu_init_msi(struct amd_iommu *iommu) -{ - if (iommu->int_enabled) - return 0; - - if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI)) - return iommu_setup_msi(iommu); - - return 1; -} - -/**************************************************************************** - * - * The next functions belong to the third pass of parsing the ACPI - * table. In this last pass the memory mapping requirements are - * gathered (like exclusion and unity mapping reanges). - * - ****************************************************************************/ - -static void __init free_unity_maps(void) -{ - struct unity_map_entry *entry, *next; - - list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) { - list_del(&entry->list); - kfree(entry); - } -} - -/* called when we find an exclusion range definition in ACPI */ -static int __init init_exclusion_range(struct ivmd_header *m) -{ - int i; - - switch (m->type) { - case ACPI_IVMD_TYPE: - set_device_exclusion_range(m->devid, m); - break; - case ACPI_IVMD_TYPE_ALL: - for (i = 0; i <= amd_iommu_last_bdf; ++i) - set_device_exclusion_range(i, m); - break; - case ACPI_IVMD_TYPE_RANGE: - for (i = m->devid; i <= m->aux; ++i) - set_device_exclusion_range(i, m); - break; - default: - break; - } - - return 0; -} - -/* called for unity map ACPI definition */ -static int __init init_unity_map_range(struct ivmd_header *m) -{ - struct unity_map_entry *e = 0; - char *s; - - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (e == NULL) - return -ENOMEM; - - switch (m->type) { - default: - kfree(e); - return 0; - case ACPI_IVMD_TYPE: - s = "IVMD_TYPEi\t\t\t"; - e->devid_start = e->devid_end = m->devid; - break; - case ACPI_IVMD_TYPE_ALL: - s = "IVMD_TYPE_ALL\t\t"; - e->devid_start = 0; - e->devid_end = amd_iommu_last_bdf; - break; - case ACPI_IVMD_TYPE_RANGE: - s = "IVMD_TYPE_RANGE\t\t"; - e->devid_start = m->devid; - e->devid_end = m->aux; - break; - } - e->address_start = PAGE_ALIGN(m->range_start); - e->address_end = e->address_start + PAGE_ALIGN(m->range_length); - e->prot = m->flags >> 1; - - DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x" - " range_start: %016llx range_end: %016llx flags: %x\n", s, - PCI_BUS(e->devid_start), PCI_SLOT(e->devid_start), - PCI_FUNC(e->devid_start), PCI_BUS(e->devid_end), - PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end), - e->address_start, e->address_end, m->flags); - - list_add_tail(&e->list, &amd_iommu_unity_map); - - return 0; -} - -/* iterates over all memory definitions we find in the ACPI table */ -static int __init init_memory_definitions(struct acpi_table_header *table) -{ - u8 *p = (u8 *)table, *end = (u8 *)table; - struct ivmd_header *m; - - end += table->length; - p += IVRS_HEADER_LENGTH; - - while (p < end) { - m = (struct ivmd_header *)p; - if (m->flags & IVMD_FLAG_EXCL_RANGE) - init_exclusion_range(m); - else if (m->flags & IVMD_FLAG_UNITY_MAP) - init_unity_map_range(m); - - p += m->length; - } - - return 0; -} - -/* - * Init the device table to not allow DMA access for devices and - * suppress all page faults - */ -static void init_device_table(void) -{ - u16 devid; - - for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) { - set_dev_entry_bit(devid, DEV_ENTRY_VALID); - set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION); - } -} - -static void iommu_init_flags(struct amd_iommu *iommu) -{ - iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : - iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - - iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - - iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - - iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_ISOC_EN) : - iommu_feature_disable(iommu, CONTROL_ISOC_EN); - - /* - * make IOMMU memory accesses cache coherent - */ - iommu_feature_enable(iommu, CONTROL_COHERENT_EN); -} - -static void iommu_apply_resume_quirks(struct amd_iommu *iommu) -{ - int i, j; - u32 ioc_feature_control; - struct pci_dev *pdev = NULL; - - /* RD890 BIOSes may not have completely reconfigured the iommu */ - if (!is_rd890_iommu(iommu->dev)) - return; - - /* - * First, we need to ensure that the iommu is enabled. This is - * controlled by a register in the northbridge - */ - pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0)); - - if (!pdev) - return; - - /* Select Northbridge indirect register 0x75 and enable writing */ - pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7)); - pci_read_config_dword(pdev, 0x64, &ioc_feature_control); - - /* Enable the iommu */ - if (!(ioc_feature_control & 0x1)) - pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1); - - pci_dev_put(pdev); - - /* Restore the iommu BAR */ - pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, - iommu->stored_addr_lo); - pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8, - iommu->stored_addr_hi); - - /* Restore the l1 indirect regs for each of the 6 l1s */ - for (i = 0; i < 6; i++) - for (j = 0; j < 0x12; j++) - iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]); - - /* Restore the l2 indirect regs */ - for (i = 0; i < 0x83; i++) - iommu_write_l2(iommu, i, iommu->stored_l2[i]); - - /* Lock PCI setup registers */ - pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, - iommu->stored_addr_lo | 1); -} - -/* - * This function finally enables all IOMMUs found in the system after - * they have been initialized - */ -static void enable_iommus(void) -{ - struct amd_iommu *iommu; - - for_each_iommu(iommu) { - iommu_disable(iommu); - iommu_init_flags(iommu); - iommu_set_device_table(iommu); - iommu_enable_command_buffer(iommu); - iommu_enable_event_buffer(iommu); - iommu_set_exclusion_range(iommu); - iommu_init_msi(iommu); - iommu_enable(iommu); - iommu_flush_all_caches(iommu); - } -} - -static void disable_iommus(void) -{ - struct amd_iommu *iommu; - - for_each_iommu(iommu) - iommu_disable(iommu); -} - -/* - * Suspend/Resume support - * disable suspend until real resume implemented - */ - -static void amd_iommu_resume(void) -{ - struct amd_iommu *iommu; - - for_each_iommu(iommu) - iommu_apply_resume_quirks(iommu); - - /* re-load the hardware */ - enable_iommus(); - - /* - * we have to flush after the IOMMUs are enabled because a - * disabled IOMMU will never execute the commands we send - */ - for_each_iommu(iommu) - iommu_flush_all_caches(iommu); -} - -static int amd_iommu_suspend(void) -{ - /* disable IOMMUs to go out of the way for BIOS */ - disable_iommus(); - - return 0; -} - -static struct syscore_ops amd_iommu_syscore_ops = { - .suspend = amd_iommu_suspend, - .resume = amd_iommu_resume, -}; - -/* - * This is the core init function for AMD IOMMU hardware in the system. - * This function is called from the generic x86 DMA layer initialization - * code. - * - * This function basically parses the ACPI table for AMD IOMMU (IVRS) - * three times: - * - * 1 pass) Find the highest PCI device id the driver has to handle. - * Upon this information the size of the data structures is - * determined that needs to be allocated. - * - * 2 pass) Initialize the data structures just allocated with the - * information in the ACPI table about available AMD IOMMUs - * in the system. It also maps the PCI devices in the - * system to specific IOMMUs - * - * 3 pass) After the basic data structures are allocated and - * initialized we update them with information about memory - * remapping requirements parsed out of the ACPI table in - * this last pass. - * - * After that the hardware is initialized and ready to go. In the last - * step we do some Linux specific things like registering the driver in - * the dma_ops interface and initializing the suspend/resume support - * functions. Finally it prints some information about AMD IOMMUs and - * the driver state and enables the hardware. - */ -static int __init amd_iommu_init(void) -{ - int i, ret = 0; - - /* - * First parse ACPI tables to find the largest Bus/Dev/Func - * we need to handle. Upon this information the shared data - * structures for the IOMMUs in the system will be allocated - */ - if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) - return -ENODEV; - - ret = amd_iommu_init_err; - if (ret) - goto out; - - dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE); - alias_table_size = tbl_size(ALIAS_TABLE_ENTRY_SIZE); - rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE); - - ret = -ENOMEM; - - /* Device table - directly used by all IOMMUs */ - amd_iommu_dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(dev_table_size)); - if (amd_iommu_dev_table == NULL) - goto out; - - /* - * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the - * IOMMU see for that device - */ - amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL, - get_order(alias_table_size)); - if (amd_iommu_alias_table == NULL) - goto free; - - /* IOMMU rlookup table - find the IOMMU for a specific device */ - amd_iommu_rlookup_table = (void *)__get_free_pages( - GFP_KERNEL | __GFP_ZERO, - get_order(rlookup_table_size)); - if (amd_iommu_rlookup_table == NULL) - goto free; - - amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages( - GFP_KERNEL | __GFP_ZERO, - get_order(MAX_DOMAIN_ID/8)); - if (amd_iommu_pd_alloc_bitmap == NULL) - goto free; - - /* init the device table */ - init_device_table(); - - /* - * let all alias entries point to itself - */ - for (i = 0; i <= amd_iommu_last_bdf; ++i) - amd_iommu_alias_table[i] = i; - - /* - * never allocate domain 0 because its used as the non-allocated and - * error value placeholder - */ - amd_iommu_pd_alloc_bitmap[0] = 1; - - spin_lock_init(&amd_iommu_pd_lock); - - /* - * now the data structures are allocated and basically initialized - * start the real acpi table scan - */ - ret = -ENODEV; - if (acpi_table_parse("IVRS", init_iommu_all) != 0) - goto free; - - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; - goto free; - } - - if (acpi_table_parse("IVRS", init_memory_definitions) != 0) - goto free; - - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; - goto free; - } - - ret = amd_iommu_init_devices(); - if (ret) - goto free; - - enable_iommus(); - - if (iommu_pass_through) - ret = amd_iommu_init_passthrough(); - else - ret = amd_iommu_init_dma_ops(); - - if (ret) - goto free_disable; - - amd_iommu_init_api(); - - amd_iommu_init_notifier(); - - register_syscore_ops(&amd_iommu_syscore_ops); - - if (iommu_pass_through) - goto out; - - if (amd_iommu_unmap_flush) - printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n"); - else - printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); - - x86_platform.iommu_shutdown = disable_iommus; -out: - return ret; - -free_disable: - disable_iommus(); - -free: - amd_iommu_uninit_devices(); - - free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, - get_order(MAX_DOMAIN_ID/8)); - - free_pages((unsigned long)amd_iommu_rlookup_table, - get_order(rlookup_table_size)); - - free_pages((unsigned long)amd_iommu_alias_table, - get_order(alias_table_size)); - - free_pages((unsigned long)amd_iommu_dev_table, - get_order(dev_table_size)); - - free_iommu_all(); - - free_unity_maps(); - -#ifdef CONFIG_GART_IOMMU - /* - * We failed to initialize the AMD IOMMU - try fallback to GART - * if possible. - */ - gart_iommu_init(); - -#endif - - goto out; -} - -/**************************************************************************** - * - * Early detect code. This code runs at IOMMU detection time in the DMA - * layer. It just looks if there is an IVRS ACPI table to detect AMD - * IOMMUs - * - ****************************************************************************/ -static int __init early_amd_iommu_detect(struct acpi_table_header *table) -{ - return 0; -} - -int __init amd_iommu_detect(void) -{ - if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return -ENODEV; - - if (amd_iommu_disabled) - return -ENODEV; - - if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { - iommu_detected = 1; - amd_iommu_detected = 1; - x86_init.iommu.iommu_init = amd_iommu_init; - - /* Make sure ACS will be enabled */ - pci_request_acs(); - return 1; - } - return -ENODEV; -} - -/**************************************************************************** - * - * Parsing functions for the AMD IOMMU specific kernel command line - * options. - * - ****************************************************************************/ - -static int __init parse_amd_iommu_dump(char *str) -{ - amd_iommu_dump = true; - - return 1; -} - -static int __init parse_amd_iommu_options(char *str) -{ - for (; *str; ++str) { - if (strncmp(str, "fullflush", 9) == 0) - amd_iommu_unmap_flush = true; - if (strncmp(str, "off", 3) == 0) - amd_iommu_disabled = true; - } - - return 1; -} - -__setup("amd_iommu_dump", parse_amd_iommu_dump); -__setup("amd_iommu=", parse_amd_iommu_options); - -IOMMU_INIT_FINISH(amd_iommu_detect, - gart_iommu_hole_init, - 0, - 0); diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 289e928..2b6630d 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -44,6 +44,7 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> #include <asm/mrst.h> +#include <asm/time.h> #define APBT_MASK CLOCKSOURCE_MASK(32) #define APBT_SHIFT 22 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b961af8..9498b84 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -27,6 +27,7 @@ #include <linux/syscore_ops.h> #include <linux/delay.h> #include <linux/timex.h> +#include <linux/i8253.h> #include <linux/dmar.h> #include <linux/init.h> #include <linux/cpu.h> @@ -39,7 +40,6 @@ #include <asm/pgalloc.h> #include <asm/atomic.h> #include <asm/mpspec.h> -#include <asm/i8253.h> #include <asm/i8259.h> #include <asm/proto.h> #include <asm/apic.h> @@ -48,6 +48,7 @@ #include <asm/hpet.h> #include <asm/idle.h> #include <asm/mtrr.h> +#include <asm/time.h> #include <asm/smp.h> #include <asm/mce.h> #include <asm/tsc.h> @@ -390,7 +391,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new) /* * If mask=1, the LVT entry does not generate interrupts while mask=0 - * enables the vector. See also the BKDGs. + * enables the vector. See also the BKDGs. Must be called with + * preemption disabled. */ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask) @@ -1428,7 +1430,7 @@ void enable_x2apic(void) rdmsr(MSR_IA32_APICBASE, msr, msr2); if (!(msr & X2APIC_ENABLE)) { printk_once(KERN_INFO "Enabling x2apic\n"); - wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0); + wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, msr2); } } #endif /* CONFIG_X86_X2APIC */ diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e529339..8eb863e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1295,6 +1295,16 @@ static int setup_ioapic_entry(int apic_id, int irq, * irq handler will do the explicit EOI to the io-apic. */ ir_entry->vector = pin; + + apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: " + "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d " + "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X " + "Avail:%X Vector:%02X Dest:%08X " + "SID:%04X SQ:%X SVT:%X)\n", + apic_id, irte.present, irte.fpd, irte.dst_mode, + irte.redir_hint, irte.trigger_mode, irte.dlvry_mode, + irte.avail, irte.vector, irte.dest_id, + irte.sid, irte.sq, irte.svt); } else { entry->delivery_mode = apic->irq_delivery_mode; entry->dest_mode = apic->irq_dest_mode; @@ -1337,9 +1347,9 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq, apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i)\n", + "IRQ %d Mode:%i Active:%i Dest:%d)\n", apic_id, mpc_ioapic_id(apic_id), pin, cfg->vector, - irq, trigger, polarity); + irq, trigger, polarity, dest); if (setup_ioapic_entry(mpc_ioapic_id(apic_id), irq, &entry, @@ -1522,10 +1532,12 @@ __apicdebuginit(void) print_IO_APIC(void) printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS); printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01); - printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); + printk(KERN_DEBUG "....... : max redirection entries: %02X\n", + reg_01.bits.entries); printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); - printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); + printk(KERN_DEBUG "....... : IO APIC version: %02X\n", + reg_01.bits.version); /* * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02, @@ -1550,31 +1562,60 @@ __apicdebuginit(void) print_IO_APIC(void) printk(KERN_DEBUG ".... IRQ redirection table:\n"); - printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect:\n"); + if (intr_remapping_enabled) { + printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR" + " Pol Stat Indx2 Zero Vect:\n"); + } else { + printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" + " Stat Dmod Deli Vect:\n"); + } for (i = 0; i <= reg_01.bits.entries; i++) { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(apic, i); - - printk(KERN_DEBUG " %02x %03X ", - i, - entry.dest - ); + if (intr_remapping_enabled) { + struct IO_APIC_route_entry entry; + struct IR_IO_APIC_route_entry *ir_entry; + + entry = ioapic_read_entry(apic, i); + ir_entry = (struct IR_IO_APIC_route_entry *) &entry; + printk(KERN_DEBUG " %02x %04X ", + i, + ir_entry->index + ); + printk("%1d %1d %1d %1d %1d " + "%1d %1d %X %02X\n", + ir_entry->format, + ir_entry->mask, + ir_entry->trigger, + ir_entry->irr, + ir_entry->polarity, + ir_entry->delivery_status, + ir_entry->index2, + ir_entry->zero, + ir_entry->vector + ); + } else { + struct IO_APIC_route_entry entry; - printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); + entry = ioapic_read_entry(apic, i); + printk(KERN_DEBUG " %02x %02X ", + i, + entry.dest + ); + printk("%1d %1d %1d %1d %1d " + "%1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector + ); + } } } + printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; @@ -1792,7 +1833,7 @@ __apicdebuginit(int) print_ICs(void) return 0; } -fs_initcall(print_ICs); +late_initcall(print_ICs); /* Where if anywhere is the i8259 connect in external int mode */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f450b68..adc66c3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -91,6 +91,10 @@ static int __init early_get_pnodeid(void) m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR); uv_min_hub_revision_id = node_id.s.revision; + if (node_id.s.part_number == UV2_HUB_PART_NUMBER) + uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; + + uv_hub_info->hub_revision = uv_min_hub_revision_id; pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); return pnode; } @@ -112,17 +116,25 @@ static void __init early_get_apic_pnode_shift(void) */ static void __init uv_set_apicid_hibit(void) { - union uvh_lb_target_physical_apic_id_mask_u apicid_mask; + union uv1h_lb_target_physical_apic_id_mask_u apicid_mask; - apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK); - uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK; + if (is_uv1_hub()) { + apicid_mask.v = + uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK); + uv_apicid_hibits = + apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK; + } } static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int pnodeid; + int pnodeid, is_uv1, is_uv2; - if (!strcmp(oem_id, "SGI")) { + is_uv1 = !strcmp(oem_id, "SGI"); + is_uv2 = !strcmp(oem_id, "SGI2"); + if (is_uv1 || is_uv2) { + uv_hub_info->hub_revision = + is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE; pnodeid = early_get_pnodeid(); early_get_apic_pnode_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; @@ -484,12 +496,19 @@ static __init void map_mmr_high(int max_pnode) static __init void map_mmioh_high(int max_pnode) { union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; - int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + int shift; mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - if (mmioh.s.enable) - map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io, + if (is_uv1_hub() && mmioh.s1.enable) { + shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io, + max_pnode, map_uc); + } + if (is_uv2_hub() && mmioh.s2.enable) { + shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io, max_pnode, map_uc); + } } static __init void map_low_mmrs(void) @@ -613,14 +632,14 @@ late_initcall(uv_init_heartbeat); /* Direct Legacy VGA I/O traffic to designated IOH */ int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n", - pdev->devfn, decode, command_bits, change_bridge); + PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", + pdev->devfn, decode, command_bits, flags); - if (!change_bridge) + if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; if ((command_bits & PCI_COMMAND_IO) == 0) @@ -736,13 +755,14 @@ void __init uv_system_init(void) unsigned long mmr_base, present, paddr; unsigned short pnode_mask, pnode_io_mask; + printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2"); map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - n_io = mmioh.s.n_io; + n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; @@ -811,6 +831,8 @@ void __init uv_system_init(void) */ uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift; + uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision; + pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); lcpu = uv_blade_info[blade].nr_possible_cpus; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 3bfa022..0371c48 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -229,11 +229,11 @@ #include <linux/jiffies.h> #include <linux/acpi.h> #include <linux/syscore_ops.h> +#include <linux/i8253.h> #include <asm/system.h> #include <asm/uaccess.h> #include <asm/desc.h> -#include <asm/i8253.h> #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> @@ -361,6 +361,7 @@ struct apm_user { * idle percentage above which bios idle calls are done */ #ifdef CONFIG_APM_CPU_IDLE +#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012 #define DEFAULT_IDLE_THRESHOLD 95 #else #define DEFAULT_IDLE_THRESHOLD 100 @@ -904,6 +905,7 @@ static void apm_cpu_idle(void) unsigned int jiffies_since_last_check = jiffies - last_jiffies; unsigned int bucket; + WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; @@ -1218,11 +1220,11 @@ static void reinit_timer(void) raw_spin_lock_irqsave(&i8253_lock, flags); /* set the clock to HZ */ - outb_pit(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ + outb_p(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ udelay(10); - outb_pit(LATCH & 0xff, PIT_CH0); /* LSB */ + outb_p(LATCH & 0xff, PIT_CH0); /* LSB */ udelay(10); - outb_pit(LATCH >> 8, PIT_CH0); /* MSB */ + outb_p(LATCH >> 8, PIT_CH0); /* MSB */ udelay(10); raw_spin_unlock_irqrestore(&i8253_lock, flags); #endif diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index c29d631..395a10e 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -63,7 +63,6 @@ void foo(void) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending); - OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir); BLANK(); OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8f5cabb3..b13ed39 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -612,8 +612,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } #endif - /* As a rule processors have APIC timer running in deep C states */ - if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400)) + /* + * Family 0x12 and above processors have APIC timer + * running in deep C states. + */ + if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c39576c..525514c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -19,6 +19,7 @@ static int __init no_halt(char *s) { + WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n"); boot_cpu_data.hlt_works_ok = 0; return 1; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c8b4162..22a073d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -477,13 +477,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) if (smp_num_siblings <= 1) goto out; - if (smp_num_siblings > nr_cpu_ids) { - pr_warning("CPU: Unsupported number of siblings %d", - smp_num_siblings); - smp_num_siblings = 1; - return; - } - index_msb = get_count_order(smp_num_siblings); c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); @@ -909,7 +902,7 @@ static void vgetcpu_set_mode(void) void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); - init_c1e_mask(); + init_amd_e400_c1e_mask(); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3a0338b..4ee3abf 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -22,7 +22,6 @@ #include <linux/sched.h> #include <linux/uaccess.h> #include <linux/slab.h> -#include <linux/highmem.h> #include <linux/cpu.h> #include <linux/bitops.h> @@ -45,38 +44,27 @@ do { \ #endif /* - * best effort, GUP based copy_from_user() that assumes IRQ or NMI context + * | NHM/WSM | SNB | + * register ------------------------------- + * | HT | no HT | HT | no HT | + *----------------------------------------- + * offcore | core | core | cpu | core | + * lbr_sel | core | core | cpu | core | + * ld_lat | cpu | core | cpu | core | + *----------------------------------------- + * + * Given that there is a small number of shared regs, + * we can pre-allocate their slot in the per-cpu + * per-core reg tables. */ -static unsigned long -copy_from_user_nmi(void *to, const void __user *from, unsigned long n) -{ - unsigned long offset, addr = (unsigned long)from; - unsigned long size, len = 0; - struct page *page; - void *map; - int ret; - - do { - ret = __get_user_pages_fast(addr, 1, 0, &page); - if (!ret) - break; - - offset = addr & (PAGE_SIZE - 1); - size = min(PAGE_SIZE - offset, n - len); - - map = kmap_atomic(page); - memcpy(to, map+offset, size); - kunmap_atomic(map); - put_page(page); +enum extra_reg_type { + EXTRA_REG_NONE = -1, /* not used */ - len += size; - to += size; - addr += size; + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ - } while (len < n); - - return len; -} + EXTRA_REG_MAX /* number of entries needed */ +}; struct event_constraint { union { @@ -132,11 +120,10 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; /* - * Intel percore register state. - * Coordinate shared resources between HT threads. + * manage shared (per-core, per-cpu) registers + * used on Intel NHM/WSM/SNB */ - int percore_used; /* Used by this CPU? */ - struct intel_percore *per_core; + struct intel_shared_regs *shared_regs; /* * AMD specific bits @@ -187,26 +174,45 @@ struct cpu_hw_events { for ((e) = (c); (e)->weight; (e)++) /* + * Per register state. + */ +struct er_account { + raw_spinlock_t lock; /* per-core: protect structure */ + u64 config; /* extra MSR config */ + u64 reg; /* extra MSR number */ + atomic_t ref; /* reference count */ +}; + +/* * Extra registers for specific events. + * * Some events need large masks and require external MSRs. - * Define a mapping to these extra registers. + * Those extra MSRs end up being shared for all events on + * a PMU and sometimes between PMU of sibling HT threads. + * In either case, the kernel needs to handle conflicting + * accesses to those extra, shared, regs. The data structure + * to manage those registers is stored in cpu_hw_event. */ struct extra_reg { unsigned int event; unsigned int msr; u64 config_mask; u64 valid_mask; + int idx; /* per_xxx->regs[] reg index */ }; -#define EVENT_EXTRA_REG(e, ms, m, vm) { \ +#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ .event = (e), \ .msr = (ms), \ .config_mask = (m), \ .valid_mask = (vm), \ + .idx = EXTRA_REG_##i \ } -#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \ - EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm) -#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0) + +#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) + +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) union perf_capabilities { struct { @@ -252,7 +258,6 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; - struct event_constraint *percore_constraints; void (*quirks)(void); int perfctr_second_write; @@ -286,8 +291,12 @@ struct x86_pmu { * Extra registers for events */ struct extra_reg *extra_regs; + unsigned int er_flags; }; +#define ERF_NO_HT_SHARING 1 +#define ERF_HAS_RSP_1 2 + static struct x86_pmu x86_pmu __read_mostly; static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { @@ -393,10 +402,10 @@ static inline unsigned int x86_pmu_event_addr(int index) */ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) { + struct hw_perf_event_extra *reg; struct extra_reg *er; - event->hw.extra_reg = 0; - event->hw.extra_config = 0; + reg = &event->hw.extra_reg; if (!x86_pmu.extra_regs) return 0; @@ -406,8 +415,10 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; - event->hw.extra_reg = er->msr; - event->hw.extra_config = event->attr.config1; + + reg->idx = er->idx; + reg->config = event->attr.config1; + reg->reg = er->msr; break; } return 0; @@ -706,6 +717,9 @@ static int __x86_pmu_event_init(struct perf_event *event) event->hw.last_cpu = -1; event->hw.last_tag = ~0ULL; + /* mark unused */ + event->hw.extra_reg.idx = EXTRA_REG_NONE; + return x86_pmu.hw_config(event); } @@ -747,8 +761,8 @@ static void x86_pmu_disable(struct pmu *pmu) static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { - if (hwc->extra_reg) - wrmsrl(hwc->extra_reg, hwc->extra_config); + if (hwc->extra_reg.reg) + wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); wrmsrl(hwc->config_base, hwc->config | enable_mask); } @@ -1332,7 +1346,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1637,6 +1651,40 @@ static int x86_pmu_commit_txn(struct pmu *pmu) perf_pmu_enable(pmu); return 0; } +/* + * a fake_cpuc is used to validate event groups. Due to + * the extra reg logic, we need to also allocate a fake + * per_core and per_cpu structure. Otherwise, group events + * using extra reg may conflict without the kernel being + * able to catch this when the last event gets added to + * the group. + */ +static void free_fake_cpuc(struct cpu_hw_events *cpuc) +{ + kfree(cpuc->shared_regs); + kfree(cpuc); +} + +static struct cpu_hw_events *allocate_fake_cpuc(void) +{ + struct cpu_hw_events *cpuc; + int cpu = raw_smp_processor_id(); + + cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); + if (!cpuc) + return ERR_PTR(-ENOMEM); + + /* only needed, if we have extra_regs */ + if (x86_pmu.extra_regs) { + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) + goto error; + } + return cpuc; +error: + free_fake_cpuc(cpuc); + return ERR_PTR(-ENOMEM); +} /* * validate that we can schedule this event @@ -1647,9 +1695,9 @@ static int validate_event(struct perf_event *event) struct event_constraint *c; int ret = 0; - fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); - if (!fake_cpuc) - return -ENOMEM; + fake_cpuc = allocate_fake_cpuc(); + if (IS_ERR(fake_cpuc)) + return PTR_ERR(fake_cpuc); c = x86_pmu.get_event_constraints(fake_cpuc, event); @@ -1659,7 +1707,7 @@ static int validate_event(struct perf_event *event) if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(fake_cpuc, event); - kfree(fake_cpuc); + free_fake_cpuc(fake_cpuc); return ret; } @@ -1679,36 +1727,32 @@ static int validate_group(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct cpu_hw_events *fake_cpuc; - int ret, n; - - ret = -ENOMEM; - fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); - if (!fake_cpuc) - goto out; + int ret = -ENOSPC, n; + fake_cpuc = allocate_fake_cpuc(); + if (IS_ERR(fake_cpuc)) + return PTR_ERR(fake_cpuc); /* * the event is not yet connected with its * siblings therefore we must first collect * existing siblings, then add the new event * before we can simulate the scheduling */ - ret = -ENOSPC; n = collect_events(fake_cpuc, leader, true); if (n < 0) - goto out_free; + goto out; fake_cpuc->n_events = n; n = collect_events(fake_cpuc, event, false); if (n < 0) - goto out_free; + goto out; fake_cpuc->n_events = n; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); -out_free: - kfree(fake_cpuc); out: + free_fake_cpuc(fake_cpuc); return ret; } diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index fe29c1d..941caa2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -89,6 +89,20 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xb8e9, /* CPU Request to Memory, l+r */ + [ C(RESULT_MISS) ] = 0x98e9, /* CPU Request to Memory, r */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 41178c8..45fbb8f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,25 +1,15 @@ #ifdef CONFIG_CPU_SUP_INTEL -#define MAX_EXTRA_REGS 2 - -/* - * Per register state. - */ -struct er_account { - int ref; /* reference count */ - unsigned int extra_reg; /* extra MSR number */ - u64 extra_config; /* extra MSR config */ -}; - /* - * Per core state - * This used to coordinate shared registers for HT threads. + * Per core/cpu state + * + * Used to coordinate shared registers between HT threads or + * among events on a single PMU. */ -struct intel_percore { - raw_spinlock_t lock; /* protect structure */ - struct er_account regs[MAX_EXTRA_REGS]; - int refcnt; /* number of threads */ - unsigned core_id; +struct intel_shared_regs { + struct er_account regs[EXTRA_REG_MAX]; + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ }; /* @@ -88,16 +78,10 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), EVENT_EXTRA_END }; -static struct event_constraint intel_nehalem_percore_constraints[] __read_mostly = -{ - INTEL_EVENT_CONSTRAINT(0xb7, 0), - EVENT_CONSTRAINT_END -}; - static struct event_constraint intel_westmere_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -116,8 +100,6 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */ - INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ EVENT_CONSTRAINT_END @@ -125,15 +107,13 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), EVENT_EXTRA_END }; -static struct event_constraint intel_westmere_percore_constraints[] __read_mostly = +static struct event_constraint intel_v1_event_constraints[] __read_mostly = { - INTEL_EVENT_CONSTRAINT(0xb7, 0), - INTEL_EVENT_CONSTRAINT(0xbb, 0), EVENT_CONSTRAINT_END }; @@ -145,6 +125,12 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct extra_reg intel_snb_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + EVENT_EXTRA_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -245,6 +231,21 @@ static __initconst const u64 snb_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + }; static __initconst const u64 westmere_hw_cache_event_ids @@ -346,6 +347,20 @@ static __initconst const u64 westmere_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, }; /* @@ -398,7 +413,21 @@ static __initconst const u64 nehalem_hw_cache_extra_regs [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS, [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS, }, - } + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM, + }, + }, }; static __initconst const u64 nehalem_hw_cache_event_ids @@ -500,6 +529,20 @@ static __initconst const u64 nehalem_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, }; static __initconst const u64 core2_hw_cache_event_ids @@ -1003,7 +1046,7 @@ again: data.period = event->hw.last_period; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1037,65 +1080,121 @@ intel_bts_constraints(struct perf_event *event) return NULL; } +static bool intel_try_alt_er(struct perf_event *event, int orig_idx) +{ + if (!(x86_pmu.er_flags & ERF_HAS_RSP_1)) + return false; + + if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) { + event->hw.config &= ~INTEL_ARCH_EVENT_MASK; + event->hw.config |= 0x01bb; + event->hw.extra_reg.idx = EXTRA_REG_RSP_1; + event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1; + } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) { + event->hw.config &= ~INTEL_ARCH_EVENT_MASK; + event->hw.config |= 0x01b7; + event->hw.extra_reg.idx = EXTRA_REG_RSP_0; + event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0; + } + + if (event->hw.extra_reg.idx == orig_idx) + return false; + + return true; +} + +/* + * manage allocation of shared extra msr for certain events + * + * sharing can be: + * per-cpu: to be shared between the various events on a single PMU + * per-core: per-cpu + shared by HT threads + */ static struct event_constraint * -intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; - unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT; - struct event_constraint *c; - struct intel_percore *pc; + struct event_constraint *c = &emptyconstraint; + struct hw_perf_event_extra *reg = &event->hw.extra_reg; struct er_account *era; - int i; - int free_slot; - int found; + unsigned long flags; + int orig_idx = reg->idx; - if (!x86_pmu.percore_constraints || hwc->extra_alloc) - return NULL; + /* already allocated shared msr */ + if (reg->alloc) + return &unconstrained; - for (c = x86_pmu.percore_constraints; c->cmask; c++) { - if (e != c->code) - continue; +again: + era = &cpuc->shared_regs->regs[reg->idx]; + /* + * we use spin_lock_irqsave() to avoid lockdep issues when + * passing a fake cpuc + */ + raw_spin_lock_irqsave(&era->lock, flags); + + if (!atomic_read(&era->ref) || era->config == reg->config) { + + /* lock in msr value */ + era->config = reg->config; + era->reg = reg->reg; + + /* one more user */ + atomic_inc(&era->ref); + + /* no need to reallocate during incremental event scheduling */ + reg->alloc = 1; /* - * Allocate resource per core. + * All events using extra_reg are unconstrained. + * Avoids calling x86_get_event_constraints() + * + * Must revisit if extra_reg controlling events + * ever have constraints. Worst case we go through + * the regular event constraint table. */ - pc = cpuc->per_core; - if (!pc) - break; - c = &emptyconstraint; - raw_spin_lock(&pc->lock); - free_slot = -1; - found = 0; - for (i = 0; i < MAX_EXTRA_REGS; i++) { - era = &pc->regs[i]; - if (era->ref > 0 && hwc->extra_reg == era->extra_reg) { - /* Allow sharing same config */ - if (hwc->extra_config == era->extra_config) { - era->ref++; - cpuc->percore_used = 1; - hwc->extra_alloc = 1; - c = NULL; - } - /* else conflict */ - found = 1; - break; - } else if (era->ref == 0 && free_slot == -1) - free_slot = i; - } - if (!found && free_slot != -1) { - era = &pc->regs[free_slot]; - era->ref = 1; - era->extra_reg = hwc->extra_reg; - era->extra_config = hwc->extra_config; - cpuc->percore_used = 1; - hwc->extra_alloc = 1; - c = NULL; - } - raw_spin_unlock(&pc->lock); - return c; + c = &unconstrained; + } else if (intel_try_alt_er(event, orig_idx)) { + raw_spin_unlock(&era->lock); + goto again; } + raw_spin_unlock_irqrestore(&era->lock, flags); - return NULL; + return c; +} + +static void +__intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc, + struct hw_perf_event_extra *reg) +{ + struct er_account *era; + + /* + * only put constraint if extra reg was actually + * allocated. Also takes care of event which do + * not use an extra shared reg + */ + if (!reg->alloc) + return; + + era = &cpuc->shared_regs->regs[reg->idx]; + + /* one fewer user */ + atomic_dec(&era->ref); + + /* allocate again next time */ + reg->alloc = 0; +} + +static struct event_constraint * +intel_shared_regs_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct event_constraint *c = NULL; + + if (event->hw.extra_reg.idx != EXTRA_REG_NONE) + c = __intel_shared_reg_get_constraints(cpuc, event); + + return c; } static struct event_constraint * @@ -1111,49 +1210,28 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; - c = intel_percore_constraints(cpuc, event); + c = intel_shared_regs_constraints(cpuc, event); if (c) return c; return x86_get_event_constraints(cpuc, event); } -static void intel_put_event_constraints(struct cpu_hw_events *cpuc, +static void +intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct extra_reg *er; - struct intel_percore *pc; - struct er_account *era; - struct hw_perf_event *hwc = &event->hw; - int i, allref; + struct hw_perf_event_extra *reg; - if (!cpuc->percore_used) - return; - - for (er = x86_pmu.extra_regs; er->msr; er++) { - if (er->event != (hwc->config & er->config_mask)) - continue; + reg = &event->hw.extra_reg; + if (reg->idx != EXTRA_REG_NONE) + __intel_shared_reg_put_constraints(cpuc, reg); +} - pc = cpuc->per_core; - raw_spin_lock(&pc->lock); - for (i = 0; i < MAX_EXTRA_REGS; i++) { - era = &pc->regs[i]; - if (era->ref > 0 && - era->extra_config == hwc->extra_config && - era->extra_reg == er->msr) { - era->ref--; - hwc->extra_alloc = 0; - break; - } - } - allref = 0; - for (i = 0; i < MAX_EXTRA_REGS; i++) - allref += pc->regs[i].ref; - if (allref == 0) - cpuc->percore_used = 0; - raw_spin_unlock(&pc->lock); - break; - } +static void intel_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + intel_put_shared_regs_event_constraints(cpuc, event); } static int intel_pmu_hw_config(struct perf_event *event) @@ -1231,20 +1309,36 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; +static struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + struct intel_shared_regs *regs; + int i; + + regs = kzalloc_node(sizeof(struct intel_shared_regs), + GFP_KERNEL, cpu_to_node(cpu)); + if (regs) { + /* + * initialize the locks to keep lockdep happy + */ + for (i = 0; i < EXTRA_REG_MAX; i++) + raw_spin_lock_init(®s->regs[i].lock); + + regs->core_id = -1; + } + return regs; +} + static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!cpu_has_ht_siblings()) + if (!x86_pmu.extra_regs) return NOTIFY_OK; - cpuc->per_core = kzalloc_node(sizeof(struct intel_percore), - GFP_KERNEL, cpu_to_node(cpu)); - if (!cpuc->per_core) + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) return NOTIFY_BAD; - raw_spin_lock_init(&cpuc->per_core->lock); - cpuc->per_core->core_id = -1; return NOTIFY_OK; } @@ -1260,32 +1354,34 @@ static void intel_pmu_cpu_starting(int cpu) */ intel_pmu_lbr_reset(); - if (!cpu_has_ht_siblings()) + if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING)) return; for_each_cpu(i, topology_thread_cpumask(cpu)) { - struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core; + struct intel_shared_regs *pc; + pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->per_core); - cpuc->per_core = pc; + kfree(cpuc->shared_regs); + cpuc->shared_regs = pc; break; } } - cpuc->per_core->core_id = core_id; - cpuc->per_core->refcnt++; + cpuc->shared_regs->core_id = core_id; + cpuc->shared_regs->refcnt++; } static void intel_pmu_cpu_dying(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - struct intel_percore *pc = cpuc->per_core; + struct intel_shared_regs *pc; + pc = cpuc->shared_regs; if (pc) { if (pc->core_id == -1 || --pc->refcnt == 0) kfree(pc); - cpuc->per_core = NULL; + cpuc->shared_regs = NULL; } fini_debug_store_on_cpu(cpu); @@ -1436,7 +1532,6 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_nehalem_event_constraints; x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; - x86_pmu.percore_constraints = intel_nehalem_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; @@ -1481,10 +1576,10 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_westmere_event_constraints; - x86_pmu.percore_constraints = intel_westmere_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; x86_pmu.extra_regs = intel_westmere_extra_regs; + x86_pmu.er_flags |= ERF_HAS_RSP_1; /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; @@ -1502,6 +1597,10 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_events; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; @@ -1512,11 +1611,19 @@ static __init int intel_pmu_init(void) break; default: - /* - * default constraints for v2 and up - */ - x86_pmu.event_constraints = intel_gen_event_constraints; - pr_cont("generic architected perfmon, "); + switch (x86_pmu.version) { + case 1: + x86_pmu.event_constraints = intel_v1_event_constraints; + pr_cont("generic architected perfmon v1, "); + break; + default: + /* + * default constraints for v2 and up + */ + x86_pmu.event_constraints = intel_gen_event_constraints; + pr_cont("generic architected perfmon, "); + break; + } } return 0; } @@ -1528,4 +1635,8 @@ static int intel_pmu_init(void) return 0; } +static struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + return NULL; +} #endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index bab491b..1b1ef3a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -340,7 +340,7 @@ static int intel_pmu_drain_bts_buffer(void) */ perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1)) + if (perf_output_begin(&handle, event, header.size * (top - at))) return 1; for (; at < top; at++) { @@ -616,7 +616,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; - if (perf_event_overflow(event, 1, &data, ®s)) + if (perf_event_overflow(event, &data, ®s)) x86_pmu_stop(event, 0); } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ead584f..7809d2b 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -554,13 +554,102 @@ static __initconst const u64 p4_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; +/* + * Because of Netburst being quite restricted in how many + * identical events may run simultaneously, we introduce event aliases, + * ie the different events which have the same functionality but + * utilize non-intersected resources (ESCR/CCCR/counter registers). + * + * This allow us to relax restrictions a bit and run two or more + * identical events together. + * + * Never set any custom internal bits such as P4_CONFIG_HT, + * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are + * either up to date automatically or not applicable at all. + */ +struct p4_event_alias { + u64 original; + u64 alternative; +} p4_event_aliases[] = { + { + /* + * Non-halted cycles can be substituted with non-sleeping cycles (see + * Intel SDM Vol3b for details). We need this alias to be able + * to run nmi-watchdog and 'perf top' (or any other user space tool + * which is interested in running PERF_COUNT_HW_CPU_CYCLES) + * simultaneously. + */ + .original = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS) | + P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)), + .alternative = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_EXECUTION_EVENT) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)| + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)| + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)| + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)| + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3))| + p4_config_pack_cccr(P4_CCCR_THRESHOLD(15) | P4_CCCR_COMPLEMENT | + P4_CCCR_COMPARE), + }, +}; + +static u64 p4_get_alias_event(u64 config) +{ + u64 config_match; + int i; + + /* + * Only event with special mark is allowed, + * we're to be sure it didn't come as malformed + * RAW event. + */ + if (!(config & P4_CONFIG_ALIASABLE)) + return 0; + + config_match = config & P4_CONFIG_EVENT_ALIAS_MASK; + + for (i = 0; i < ARRAY_SIZE(p4_event_aliases); i++) { + if (config_match == p4_event_aliases[i].original) { + config_match = p4_event_aliases[i].alternative; + break; + } else if (config_match == p4_event_aliases[i].alternative) { + config_match = p4_event_aliases[i].original; + break; + } + } + + if (i >= ARRAY_SIZE(p4_event_aliases)) + return 0; + + return config_match | (config & P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS); +} + static u64 p4_general_events[PERF_COUNT_HW_MAX] = { /* non-halted CPU clocks */ [PERF_COUNT_HW_CPU_CYCLES] = p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS) | - P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)), + P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)) | + P4_CONFIG_ALIASABLE, /* * retired instructions @@ -945,7 +1034,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1120,6 +1209,8 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign struct p4_event_bind *bind; unsigned int i, thread, num; int cntr_idx, escr_idx; + u64 config_alias; + int pass; bitmap_zero(used_mask, X86_PMC_IDX_MAX); bitmap_zero(escr_mask, P4_ESCR_MSR_TABLE_SIZE); @@ -1128,6 +1219,17 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign hwc = &cpuc->event_list[i]->hw; thread = p4_ht_thread(cpu); + pass = 0; + +again: + /* + * It's possible to hit a circular lock + * between original and alternative events + * if both are scheduled already. + */ + if (pass > 2) + goto done; + bind = p4_config_get_bind(hwc->config); escr_idx = p4_get_escr_idx(bind->escr_msr[thread]); if (unlikely(escr_idx == -1)) @@ -1141,8 +1243,17 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign } cntr_idx = p4_next_cntr(thread, used_mask, bind); - if (cntr_idx == -1 || test_bit(escr_idx, escr_mask)) - goto done; + if (cntr_idx == -1 || test_bit(escr_idx, escr_mask)) { + /* + * Check whether an event alias is still available. + */ + config_alias = p4_get_alias_event(hwc->config); + if (!config_alias) + goto done; + hwc->config = config_alias; + pass++; + goto again; + } p4_pmu_swap_config_ts(hwc, cpu); if (assign) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 690bc84..a621f34 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/pci.h> #include <linux/of_pci.h> +#include <linux/initrd.h> #include <asm/hpet.h> #include <asm/irq_controller.h> @@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } +#ifdef CONFIG_BLK_DEV_INITRD +void __init early_init_dt_setup_initrd_arch(unsigned long start, + unsigned long end) +{ + initrd_start = (unsigned long)__va(start); + initrd_end = (unsigned long)__va(end); + initrd_below_start_ok = 1; +} +#endif + void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -123,6 +134,24 @@ static int __init add_bus_probe(void) module_init(add_bus_probe); #ifdef CONFIG_PCI +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct device_node *np; + + for_each_node_by_type(np, "pci") { + const void *prop; + unsigned int bus_min; + + prop = of_get_property(np, "bus-range", NULL); + if (!prop) + continue; + bus_min = be32_to_cpup(prop); + if (bus->number == bus_min) + return np; + } + return NULL; +} + static int x86_of_pci_irq_enable(struct pci_dev *dev) { struct of_irq oirq; @@ -154,50 +183,8 @@ static void x86_of_pci_irq_disable(struct pci_dev *dev) void __cpuinit x86_of_pci_init(void) { - struct device_node *np; - pcibios_enable_irq = x86_of_pci_irq_enable; pcibios_disable_irq = x86_of_pci_irq_disable; - - for_each_node_by_type(np, "pci") { - const void *prop; - struct pci_bus *bus; - unsigned int bus_min; - struct device_node *child; - - prop = of_get_property(np, "bus-range", NULL); - if (!prop) - continue; - bus_min = be32_to_cpup(prop); - - bus = pci_find_bus(0, bus_min); - if (!bus) { - printk(KERN_ERR "Can't find a node for bus %s.\n", - np->full_name); - continue; - } - - if (bus->self) - bus->self->dev.of_node = np; - else - bus->dev.of_node = np; - - for_each_child_of_node(np, child) { - struct pci_dev *dev; - u32 devfn; - - prop = of_get_property(child, "reg", NULL); - if (!prop) - continue; - - devfn = (be32_to_cpup(prop) >> 8) & 0xff; - dev = pci_get_slot(bus, devfn); - if (!dev) - continue; - dev->dev.of_node = child; - pci_dev_put(dev); - } - } } #endif diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index e71c98d..19853ad 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -105,34 +105,6 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack, } /* - * We are returning from the irq stack and go to the previous one. - * If the previous stack is also in the irq stack, then bp in the first - * frame of the irq stack points to the previous, interrupted one. - * Otherwise we have another level of indirection: We first save - * the bp of the previous stack, then we switch the stack to the irq one - * and save a new bp that links to the previous one. - * (See save_args()) - */ -static inline unsigned long -fixup_bp_irq_link(unsigned long bp, unsigned long *stack, - unsigned long *irq_stack, unsigned long *irq_stack_end) -{ -#ifdef CONFIG_FRAME_POINTER - struct stack_frame *frame = (struct stack_frame *)bp; - unsigned long next; - - if (!in_irq_stack(stack, irq_stack, irq_stack_end)) { - if (!probe_kernel_address(&frame->next_frame, next)) - return next; - else - WARN_ONCE(1, "Perf: bad frame pointer = %p in " - "callchain\n", &frame->next_frame); - } -#endif - return bp; -} - -/* * x86-64 can have up to three kernel stacks: * process stack * interrupt stack @@ -155,9 +127,12 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, task = current; if (!stack) { - stack = &dummy; - if (task && task != current) + if (regs) + stack = (unsigned long *)regs->sp; + else if (task && task != current) stack = (unsigned long *)task->thread.sp; + else + stack = &dummy; } if (!bp) @@ -205,8 +180,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * pointer (index -1 to end) in the IRQ stack: */ stack = (unsigned long *) (irq_stack_end[-1]); - bp = fixup_bp_irq_link(bp, stack, irq_stack, - irq_stack_end); irq_stack_end = NULL; ops->stack(data, "EOI"); continue; diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 8a445a0..d130b20 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -297,27 +297,26 @@ ENDPROC(native_usergs_sysret64) .endm /* save partial stack frame */ - .pushsection .kprobes.text, "ax" -ENTRY(save_args) - XCPT_FRAME + .macro SAVE_ARGS_IRQ cld - /* - * start from rbp in pt_regs and jump over - * return address. - */ - movq_cfi rdi, RDI+8-RBP - movq_cfi rsi, RSI+8-RBP - movq_cfi rdx, RDX+8-RBP - movq_cfi rcx, RCX+8-RBP - movq_cfi rax, RAX+8-RBP - movq_cfi r8, R8+8-RBP - movq_cfi r9, R9+8-RBP - movq_cfi r10, R10+8-RBP - movq_cfi r11, R11+8-RBP - - leaq -RBP+8(%rsp),%rdi /* arg1 for handler */ - movq_cfi rbp, 8 /* push %rbp */ - leaq 8(%rsp), %rbp /* mov %rsp, %ebp */ + /* start from rbp in pt_regs and jump over */ + movq_cfi rdi, RDI-RBP + movq_cfi rsi, RSI-RBP + movq_cfi rdx, RDX-RBP + movq_cfi rcx, RCX-RBP + movq_cfi rax, RAX-RBP + movq_cfi r8, R8-RBP + movq_cfi r9, R9-RBP + movq_cfi r10, R10-RBP + movq_cfi r11, R11-RBP + + /* Save rbp so that we can unwind from get_irq_regs() */ + movq_cfi rbp, 0 + + /* Save previous stack value */ + movq %rsp, %rsi + + leaq -RBP(%rsp),%rdi /* arg1 for handler */ testl $3, CS(%rdi) je 1f SWAPGS @@ -329,19 +328,14 @@ ENTRY(save_args) */ 1: incl PER_CPU_VAR(irq_count) jne 2f - popq_cfi %rax /* move return address... */ mov PER_CPU_VAR(irq_stack_ptr),%rsp EMPTY_FRAME 0 - pushq_cfi %rbp /* backlink for unwinder */ - pushq_cfi %rax /* ... to the new stack */ - /* - * We entered an interrupt context - irqs are off: - */ -2: TRACE_IRQS_OFF - ret - CFI_ENDPROC -END(save_args) - .popsection + +2: /* Store previous stack value */ + pushq %rsi + /* We entered an interrupt context - irqs are off: */ + TRACE_IRQS_OFF + .endm ENTRY(save_rest) PARTIAL_FRAME 1 REST_SKIP+8 @@ -473,7 +467,7 @@ ENTRY(system_call_after_swapgs) * and short: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,1 + SAVE_ARGS 8,0 movq %rax,ORIG_RAX-ARGOFFSET(%rsp) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET @@ -508,7 +502,7 @@ sysret_check: TRACE_IRQS_ON movq RIP-ARGOFFSET(%rsp),%rcx CFI_REGISTER rip,rcx - RESTORE_ARGS 0,-ARG_SKIP,1 + RESTORE_ARGS 1,-ARG_SKIP,0 /*CFI_REGISTER rflags,r11*/ movq PER_CPU_VAR(old_rsp), %rsp USERGS_SYSRET64 @@ -791,7 +785,7 @@ END(interrupt) /* reserve pt_regs for scratch regs and rbp */ subq $ORIG_RAX-RBP, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP - call save_args + SAVE_ARGS_IRQ PARTIAL_FRAME 0 call \func .endm @@ -814,15 +808,14 @@ ret_from_intr: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF decl PER_CPU_VAR(irq_count) - leaveq - CFI_RESTORE rbp + /* Restore saved previous stack */ + popq %rsi + leaq 16(%rsi), %rsp + CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET -8 + CFI_ADJUST_CFA_OFFSET -16 - /* we did not save rbx, restore only from ARGOFFSET */ - addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 exit_intr: GET_THREAD_INFO(%rcx) testl $3,CS-ARGOFFSET(%rsp) @@ -858,7 +851,7 @@ retint_restore_args: /* return to kernel space */ */ TRACE_IRQS_IRETQ restore_args: - RESTORE_ARGS 0,8,0 + RESTORE_ARGS 1,8,1 irq_return: INTERRUPT_RETURN diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 0ba15a6..c9a281f 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ static void *mod_code_ip; /* holds the IP to write to */ -static void *mod_code_newcode; /* holds the text to write to the IP */ +static const void *mod_code_newcode; /* holds the text to write to the IP */ static unsigned nmi_wait_count; static atomic_t nmi_update_count = ATOMIC_INIT(0); @@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) } static int -do_ftrace_mod_code(unsigned long ip, void *new_code) +do_ftrace_mod_code(unsigned long ip, const void *new_code) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void) } static int -ftrace_modify_code(unsigned long ip, unsigned char *old_code, - unsigned char *new_code) +ftrace_modify_code(unsigned long ip, unsigned const char *old_code, + unsigned const char *new_code) { unsigned char replaced[MCOUNT_INSN_SIZE]; @@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned char *new, *old; + unsigned const char *new, *old; unsigned long ip = rec->ip; old = ftrace_call_replace(ip, addr); @@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod, int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned char *new, *old; + unsigned const char *new, *old; unsigned long ip = rec->ip; old = ftrace_nop_replace(); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 6781765..0f4b065 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -4,6 +4,7 @@ #include <linux/sysdev.h> #include <linux/delay.h> #include <linux/errno.h> +#include <linux/i8253.h> #include <linux/slab.h> #include <linux/hpet.h> #include <linux/init.h> @@ -12,8 +13,8 @@ #include <linux/io.h> #include <asm/fixmap.h> -#include <asm/i8253.h> #include <asm/hpet.h> +#include <asm/time.h> #define HPET_MASK CLOCKSOURCE_MASK(32) diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index fb66dc9..f2b96de 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -3,113 +3,24 @@ * */ #include <linux/clockchips.h> -#include <linux/interrupt.h> -#include <linux/spinlock.h> -#include <linux/jiffies.h> #include <linux/module.h> #include <linux/timex.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/io.h> +#include <linux/i8253.h> -#include <asm/i8253.h> #include <asm/hpet.h> +#include <asm/time.h> #include <asm/smp.h> -DEFINE_RAW_SPINLOCK(i8253_lock); -EXPORT_SYMBOL(i8253_lock); - /* * HPET replaces the PIT, when enabled. So we need to know, which of * the two timers is used */ struct clock_event_device *global_clock_event; -/* - * Initialize the PIT timer. - * - * This is also called after resume to bring the PIT into operation again. - */ -static void init_pit_timer(enum clock_event_mode mode, - struct clock_event_device *evt) -{ - raw_spin_lock(&i8253_lock); - - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* binary, mode 2, LSB/MSB, ch 0 */ - outb_pit(0x34, PIT_MODE); - outb_pit(LATCH & 0xff , PIT_CH0); /* LSB */ - outb_pit(LATCH >> 8 , PIT_CH0); /* MSB */ - break; - - case CLOCK_EVT_MODE_SHUTDOWN: - case CLOCK_EVT_MODE_UNUSED: - if (evt->mode == CLOCK_EVT_MODE_PERIODIC || - evt->mode == CLOCK_EVT_MODE_ONESHOT) { - outb_pit(0x30, PIT_MODE); - outb_pit(0, PIT_CH0); - outb_pit(0, PIT_CH0); - } - break; - - case CLOCK_EVT_MODE_ONESHOT: - /* One shot setup */ - outb_pit(0x38, PIT_MODE); - break; - - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here */ - break; - } - raw_spin_unlock(&i8253_lock); -} - -/* - * Program the next event in oneshot mode - * - * Delta is given in PIT ticks - */ -static int pit_next_event(unsigned long delta, struct clock_event_device *evt) -{ - raw_spin_lock(&i8253_lock); - outb_pit(delta & 0xff , PIT_CH0); /* LSB */ - outb_pit(delta >> 8 , PIT_CH0); /* MSB */ - raw_spin_unlock(&i8253_lock); - - return 0; -} - -/* - * On UP the PIT can serve all of the possible timer functions. On SMP systems - * it can be solely used for the global tick. - * - * The profiling and update capabilities are switched off once the local apic is - * registered. This mechanism replaces the previous #ifdef LOCAL_APIC - - * !using_apic_timer decisions in do_timer_interrupt_hook() - */ -static struct clock_event_device pit_ce = { - .name = "pit", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = init_pit_timer, - .set_next_event = pit_next_event, - .irq = 0, -}; - -/* - * Initialize the conversion factor and the min/max deltas of the clock event - * structure and register the clock event source with the framework. - */ void __init setup_pit_timer(void) { - /* - * Start pit with the boot cpu mask and make it global after the - * IO_APIC has been initialized. - */ - pit_ce.cpumask = cpumask_of(smp_processor_id()); - - clockevents_config_and_register(&pit_ce, CLOCK_TICK_RATE, 0xF, 0x7FFF); - global_clock_event = &pit_ce; + clockevent_i8253_init(true); + global_clock_event = &i8253_clockevent; } #ifndef CONFIG_X86_64 @@ -123,7 +34,7 @@ static int __init init_pit_clocksource(void) * - when local APIC timer is active (PIT is switched off) */ if (num_possible_cpus() > 1 || is_hpet_enabled() || - pit_ce.mode != CLOCK_EVT_MODE_PERIODIC) + i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) return 0; return clocksource_i8253_init(); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 5f9ecff..00354d4 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -608,7 +608,7 @@ int kgdb_arch_init(void) return register_die_notifier(&kgdb_notifier); } -static void kgdb_hw_overflow_handler(struct perf_event *event, int nmi, +static void kgdb_hw_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { struct task_struct *tsk = current; @@ -638,7 +638,7 @@ void kgdb_arch_late(void) for (i = 0; i < HBP_NUM; i++) { if (breakinfo[i].pev) continue; - breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); + breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL); if (IS_ERR((void * __force)breakinfo[i].pev)) { printk(KERN_ERR "kgdb: Could not allocate hw" "breakpoints\nDisabling the kernel debugger\n"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 88a90a9..e1ba8cb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -337,7 +337,9 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(pm_idle); +#endif #ifdef CONFIG_X86_32 /* @@ -535,45 +537,45 @@ int mwait_usable(const struct cpuinfo_x86 *c) return (edx & MWAIT_EDX_C1); } -bool c1e_detected; -EXPORT_SYMBOL(c1e_detected); +bool amd_e400_c1e_detected; +EXPORT_SYMBOL(amd_e400_c1e_detected); -static cpumask_var_t c1e_mask; +static cpumask_var_t amd_e400_c1e_mask; -void c1e_remove_cpu(int cpu) +void amd_e400_remove_cpu(int cpu) { - if (c1e_mask != NULL) - cpumask_clear_cpu(cpu, c1e_mask); + if (amd_e400_c1e_mask != NULL) + cpumask_clear_cpu(cpu, amd_e400_c1e_mask); } /* - * C1E aware idle routine. We check for C1E active in the interrupt + * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt * pending message MSR. If we detect C1E, then we handle it the same * way as C3 power states (local apic timer and TSC stop) */ -static void c1e_idle(void) +static void amd_e400_idle(void) { if (need_resched()) return; - if (!c1e_detected) { + if (!amd_e400_c1e_detected) { u32 lo, hi; rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); if (lo & K8_INTP_C1E_ACTIVE_MASK) { - c1e_detected = true; + amd_e400_c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); printk(KERN_INFO "System has AMD C1E enabled\n"); } } - if (c1e_detected) { + if (amd_e400_c1e_detected) { int cpu = smp_processor_id(); - if (!cpumask_test_cpu(cpu, c1e_mask)) { - cpumask_set_cpu(cpu, c1e_mask); + if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) { + cpumask_set_cpu(cpu, amd_e400_c1e_mask); /* * Force broadcast so ACPI can not interfere. */ @@ -616,17 +618,17 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) pm_idle = mwait_idle; } else if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ - printk(KERN_INFO "using C1E aware idle routine\n"); - pm_idle = c1e_idle; + printk(KERN_INFO "using AMD E400 aware idle routine\n"); + pm_idle = amd_e400_idle; } else pm_idle = default_idle; } -void __init init_c1e_mask(void) +void __init init_amd_e400_c1e_mask(void) { - /* If we're using c1e_idle, we need to allocate c1e_mask. */ - if (pm_idle == c1e_idle) - zalloc_cpumask_var(&c1e_mask, GFP_KERNEL); + /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */ + if (pm_idle == amd_e400_idle) + zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL); } static int __init idle_setup(char *str) @@ -640,6 +642,7 @@ static int __init idle_setup(char *str) boot_option_idle_override = IDLE_POLL; } else if (!strcmp(str, "mwait")) { boot_option_idle_override = IDLE_FORCE_MWAIT; + WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n"); } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8d12878..a3d0dc5 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -245,7 +245,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { set_user_gs(regs, 0); regs->fs = 0; - set_fs(USER_DS); regs->ds = __USER_DS; regs->es = __USER_DS; regs->ss = __USER_DS; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6c9dd92..ca6f7ab 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -338,7 +338,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - set_fs(USER_DS); /* * Free the old FP and other extended state */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 807c2a2..8252879 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -528,7 +528,7 @@ static int genregs_set(struct task_struct *target, return ret; } -static void ptrace_triggered(struct perf_event *bp, int nmi, +static void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { @@ -715,7 +715,8 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, attr.bp_type = HW_BREAKPOINT_W; attr.disabled = 1; - bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk); + bp = register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); /* * CHECKME: the previous code returned -EIO if the addr wasn't diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0c016f7..9242436 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -294,6 +294,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), }, }, + { /* Handle reboot issue on Acer Aspire one */ + .callback = set_bios_reboot, + .ident = "Acer Aspire One A110", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), + }, + }, { } }; @@ -411,6 +419,30 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the Latitude E6320. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6320", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"), + }, + }, + { /* Handle problems with rebooting on the Latitude E5420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5420", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"), + }, + }, + { /* Handle problems with rebooting on the Latitude E6420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6420", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a3e5948..afaf384 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -910,6 +910,13 @@ void __init setup_arch(char **cmdline_p) memblock.current_limit = get_max_mapped(); memblock_x86_fill(); + /* + * The EFI specification says that boot service code won't be called + * after ExitBootServices(). This is, in fact, a lie. + */ + if (efi_enabled) + efi_reserve_boot_services(); + /* preallocate 4k for mptable mpc */ early_reserve_e820_mpc_new(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e02653a..9f548cb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); + /* + * Wait until the cpu which brought this one up marked it + * online before enabling interrupts. If we don't do that then + * we can end up waking up the softirq thread before this cpu + * reached the active state, which makes the scheduler unhappy + * and schedule the softirq thread on the wrong cpu. This is + * only observable with forced threaded interrupts, but in + * theory it could also happen w/o them. It's just way harder + * to achieve. + */ + while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) + cpu_relax(); + /* enable local interrupts */ local_irq_enable(); @@ -1307,7 +1320,7 @@ void play_dead_common(void) { idle_task_exit(); reset_lazy_tlbstate(); - c1e_remove_cpu(raw_smp_processor_id()); + amd_e400_remove_cpu(raw_smp_processor_id()); mb(); /* Ack it */ @@ -1332,7 +1345,7 @@ static inline void mwait_play_dead(void) void *mwait_ptr; struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info); - if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)) + if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))) return; if (!this_cpu_has(X86_FEATURE_CLFLSH)) return; diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 55d9bc0..fdd0c64 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -66,7 +66,7 @@ void save_stack_trace(struct stack_trace *trace) } EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs) +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) { dump_trace(current, regs, NULL, 0, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 32cbffb..fbb0a04 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -345,3 +345,4 @@ ENTRY(sys_call_table) .long sys_clock_adjtime .long sys_syncfs .long sys_sendmmsg /* 345 */ + .long sys_setns diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 30ac65d..e07a2fc 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -36,6 +36,7 @@ #include <asm/bootparam.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/swiotlb.h> #include <asm/fixmap.h> #include <asm/proto.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 00cbb27..5a64d05 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -11,13 +11,13 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> +#include <linux/i8253.h> #include <linux/time.h> #include <linux/mca.h> #include <asm/vsyscall.h> #include <asm/x86_init.h> #include <asm/i8259.h> -#include <asm/i8253.h> #include <asm/timer.h> #include <asm/hpet.h> #include <asm/time.h> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d6e2477..adc9867 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -47,38 +47,40 @@ #define DstDI (5<<1) /* Destination is in ES:(E)DI */ #define DstMem64 (6<<1) /* 64bit memory operand */ #define DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */ -#define DstMask (7<<1) +#define DstDX (8<<1) /* Destination is in DX register */ +#define DstMask (0xf<<1) /* Source operand type. */ -#define SrcNone (0<<4) /* No source operand. */ -#define SrcReg (1<<4) /* Register operand. */ -#define SrcMem (2<<4) /* Memory operand. */ -#define SrcMem16 (3<<4) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<4) /* Memory operand (32-bit). */ -#define SrcImm (5<<4) /* Immediate operand. */ -#define SrcImmByte (6<<4) /* 8-bit sign-extended immediate operand. */ -#define SrcOne (7<<4) /* Implied '1' */ -#define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ -#define SrcImmU (9<<4) /* Immediate operand, unsigned */ -#define SrcSI (0xa<<4) /* Source is in the DS:RSI */ -#define SrcImmFAddr (0xb<<4) /* Source is immediate far address */ -#define SrcMemFAddr (0xc<<4) /* Source is far address in memory */ -#define SrcAcc (0xd<<4) /* Source Accumulator */ -#define SrcImmU16 (0xe<<4) /* Immediate operand, unsigned, 16 bits */ -#define SrcMask (0xf<<4) +#define SrcNone (0<<5) /* No source operand. */ +#define SrcReg (1<<5) /* Register operand. */ +#define SrcMem (2<<5) /* Memory operand. */ +#define SrcMem16 (3<<5) /* Memory operand (16-bit). */ +#define SrcMem32 (4<<5) /* Memory operand (32-bit). */ +#define SrcImm (5<<5) /* Immediate operand. */ +#define SrcImmByte (6<<5) /* 8-bit sign-extended immediate operand. */ +#define SrcOne (7<<5) /* Implied '1' */ +#define SrcImmUByte (8<<5) /* 8-bit unsigned immediate operand. */ +#define SrcImmU (9<<5) /* Immediate operand, unsigned */ +#define SrcSI (0xa<<5) /* Source is in the DS:RSI */ +#define SrcImmFAddr (0xb<<5) /* Source is immediate far address */ +#define SrcMemFAddr (0xc<<5) /* Source is far address in memory */ +#define SrcAcc (0xd<<5) /* Source Accumulator */ +#define SrcImmU16 (0xe<<5) /* Immediate operand, unsigned, 16 bits */ +#define SrcDX (0xf<<5) /* Source is in DX register */ +#define SrcMask (0xf<<5) /* Generic ModRM decode. */ -#define ModRM (1<<8) +#define ModRM (1<<9) /* Destination is only written; never read. */ -#define Mov (1<<9) -#define BitOp (1<<10) -#define MemAbs (1<<11) /* Memory operand is absolute displacement */ -#define String (1<<12) /* String instruction (rep capable) */ -#define Stack (1<<13) /* Stack instruction (push/pop) */ -#define GroupMask (7<<14) /* Opcode uses one of the group mechanisms */ -#define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ -#define GroupDual (2<<14) /* Alternate decoding of mod == 3 */ -#define Prefix (3<<14) /* Instruction varies with 66/f2/f3 prefix */ -#define RMExt (4<<14) /* Opcode extension in ModRM r/m if mod == 3 */ -#define Sse (1<<17) /* SSE Vector instruction */ +#define Mov (1<<10) +#define BitOp (1<<11) +#define MemAbs (1<<12) /* Memory operand is absolute displacement */ +#define String (1<<13) /* String instruction (rep capable) */ +#define Stack (1<<14) /* Stack instruction (push/pop) */ +#define GroupMask (7<<15) /* Opcode uses one of the group mechanisms */ +#define Group (1<<15) /* Bits 3:5 of modrm byte extend opcode */ +#define GroupDual (2<<15) /* Alternate decoding of mod == 3 */ +#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ +#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ +#define Sse (1<<18) /* SSE Vector instruction */ /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ @@ -3154,8 +3156,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), - D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */ - D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */ + D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */ + D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ @@ -3212,8 +3214,8 @@ static struct opcode opcode_table[256] = { /* 0xE8 - 0xEF */ D(SrcImm | Stack), D(SrcImm | ImplicitOps), D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps), - D2bvIP(SrcNone | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out), + D2bvIP(SrcDX | DstAcc, in, check_perm_in), + D2bvIP(SrcAcc | DstDX, out, check_perm_out), /* 0xF0 - 0xF7 */ N, DI(ImplicitOps, icebp), N, N, DI(ImplicitOps | Priv, hlt), D(ImplicitOps), @@ -3370,7 +3372,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; struct opcode opcode; - struct operand memop = { .type = OP_NONE }; + struct operand memop = { .type = OP_NONE }, *memopp = NULL; c->eip = ctxt->eip; c->fetch.start = c->eip; @@ -3545,9 +3547,6 @@ done_prefixes: if (memop.type == OP_MEM && c->ad_bytes != 8) memop.addr.mem.ea = (u32)memop.addr.mem.ea; - if (memop.type == OP_MEM && c->rip_relative) - memop.addr.mem.ea += c->eip; - /* * Decode and fetch the source operand: register, memory * or immediate. @@ -3569,6 +3568,7 @@ done_prefixes: c->op_bytes; srcmem_common: c->src = memop; + memopp = &c->src; break; case SrcImmU16: rc = decode_imm(ctxt, &c->src, 2, false); @@ -3613,6 +3613,12 @@ done_prefixes: memop.bytes = c->op_bytes + 2; goto srcmem_common; break; + case SrcDX: + c->src.type = OP_REG; + c->src.bytes = 2; + c->src.addr.reg = &c->regs[VCPU_REGS_RDX]; + fetch_register_operand(&c->src); + break; } if (rc != X86EMUL_CONTINUE) @@ -3659,6 +3665,7 @@ done_prefixes: case DstMem: case DstMem64: c->dst = memop; + memopp = &c->dst; if ((c->d & DstMask) == DstMem64) c->dst.bytes = 8; else @@ -3682,14 +3689,23 @@ done_prefixes: c->dst.addr.mem.seg = VCPU_SREG_ES; c->dst.val = 0; break; + case DstDX: + c->dst.type = OP_REG; + c->dst.bytes = 2; + c->dst.addr.reg = &c->regs[VCPU_REGS_RDX]; + fetch_register_operand(&c->dst); + break; case ImplicitOps: /* Special instructions do their own operand decoding. */ default: c->dst.type = OP_NONE; /* Disable writeback. */ - return 0; + break; } done: + if (memopp && memopp->type == OP_MEM && c->rip_relative) + memopp->addr.mem.ea += c->eip; + return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; } @@ -4027,7 +4043,6 @@ special_insn: break; case 0xec: /* in al,dx */ case 0xed: /* in (e/r)ax,dx */ - c->src.val = c->regs[VCPU_REGS_RDX]; do_io_in: if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, &c->dst.val)) @@ -4035,7 +4050,6 @@ special_insn: break; case 0xee: /* out dx,al */ case 0xef: /* out dx,(e/r)ax */ - c->dst.val = c->regs[VCPU_REGS_RDX]; do_io_out: ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val, &c->src.val, 1); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index bd14bb4..aee3862 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) { - return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); + return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); } static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c4dc01..9d03ad4 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gva_t addr, u32 access) { pt_element_t pte; - pt_element_t __user *ptep_user; + pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4c3fa0f..d48ec60 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { - vmx_decache_cr3(vcpu); + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + vmx_decache_cr3(vcpu); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index e191c09..13ee258 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -71,7 +71,8 @@ #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ -/*G:010 Welcome to the Guest! +/*G:010 + * Welcome to the Guest! * * The Guest in our tale is a simple creature: identical to the Host but * behaving in simplified but equivalent ways. In particular, the Guest is the @@ -190,15 +191,23 @@ static void lazy_hcall4(unsigned long call, #endif /*G:036 - * When lazy mode is turned off reset the per-cpu lazy mode variable and then - * issue the do-nothing hypercall to flush any stored calls. -:*/ + * When lazy mode is turned off, we issue the do-nothing hypercall to + * flush any stored calls, and call the generic helper to reset the + * per-cpu lazy mode variable. + */ static void lguest_leave_lazy_mmu_mode(void) { hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_leave_lazy_mmu(); } +/* + * We also catch the end of context switch; we enter lazy mode for much of + * that too, so again we need to flush here. + * + * (Technically, this is lazy CPU mode, and normally we're in lazy MMU + * mode, but unlike Xen, lguest doesn't care about the difference). + */ static void lguest_end_context_switch(struct task_struct *next) { hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); @@ -391,7 +400,7 @@ static void lguest_load_tr_desc(void) * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. * * This instruction even it has its own Wikipedia entry. The Wikipedia entry - * has been translated into 5 languages. I am not making this up! + * has been translated into 6 languages. I am not making this up! * * We could get funky here and identify ourselves as "GenuineLguest", but * instead we just use the real "cpuid" instruction. Then I pretty much turned @@ -458,7 +467,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, /* * PAE systems can mark pages as non-executable. Linux calls this the * NX bit. Intel calls it XD (eXecute Disable), AMD EVP (Enhanced - * Virus Protection). We just switch turn if off here, since we don't + * Virus Protection). We just switch it off here, since we don't * support it. */ case 0x80000001: @@ -520,17 +529,16 @@ static unsigned long lguest_read_cr2(void) /* See lguest_set_pte() below. */ static bool cr3_changed = false; +static unsigned long current_cr3; /* * cr3 is the current toplevel pagetable page: the principle is the same as - * cr0. Keep a local copy, and tell the Host when it changes. The only - * difference is that our local copy is in lguest_data because the Host needs - * to set it upon our initial hypercall. + * cr0. Keep a local copy, and tell the Host when it changes. */ static void lguest_write_cr3(unsigned long cr3) { - lguest_data.pgdir = cr3; lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); + current_cr3 = cr3; /* These two page tables are simple, linear, and used during boot */ if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table)) @@ -539,7 +547,7 @@ static void lguest_write_cr3(unsigned long cr3) static unsigned long lguest_read_cr3(void) { - return lguest_data.pgdir; + return current_cr3; } /* cr4 is used to enable and disable PGE, but we don't care. */ @@ -641,7 +649,7 @@ static void lguest_write_cr4(unsigned long val) /* * The Guest calls this after it has set a second-level entry (pte), ie. to map - * a page into a process' address space. Wetell the Host the toplevel and + * a page into a process' address space. We tell the Host the toplevel and * address this corresponds to. The Guest uses one pagetable per process, so * we need to tell the Host which one we're changing (mm->pgd). */ @@ -758,7 +766,7 @@ static void lguest_pmd_clear(pmd_t *pmdp) static void lguest_flush_tlb_single(unsigned long addr) { /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); + lazy_hcall3(LHCALL_SET_PTE, current_cr3, addr, 0); } /* @@ -993,6 +1001,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) static void lguest_time_init(void) { /* Set up the timer interrupt (0) to go to our simple timer routine */ + lguest_setup_irq(0); irq_set_handler(0, lguest_time_irq); clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); @@ -1139,7 +1148,7 @@ static struct notifier_block paniced = { static __init char *lguest_memory_setup(void) { /* - *The Linux bootloader header contains an "e820" memory map: the + * The Linux bootloader header contains an "e820" memory map: the * Launcher populated the first entry with our memory limit. */ e820_add_region(boot_params.e820_map[0].addr, diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 4f420c2f..6ddfe4f 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -6,18 +6,22 @@ #include <asm/processor-flags.h> /*G:020 - * Our story starts with the kernel booting into startup_32 in - * arch/x86/kernel/head_32.S. It expects a boot header, which is created by - * the bootloader (the Launcher in our case). + + * Our story starts with the bzImage: booting starts at startup_32 in + * arch/x86/boot/compressed/head_32.S. This merely uncompresses the real + * kernel in place and then jumps into it: startup_32 in + * arch/x86/kernel/head_32.S. Both routines expects a boot header in the %esi + * register, which is created by the bootloader (the Launcher in our case). * * The startup_32 function does very little: it clears the uninitialized global * C variables which we expect to be zero (ie. BSS) and then copies the boot - * header and kernel command line somewhere safe. Finally it checks the - * 'hardware_subarch' field. This was introduced in 2.6.24 for lguest and Xen: - * if it's set to '1' (lguest's assigned number), then it calls us here. + * header and kernel command line somewhere safe, and populates some initial + * page tables. Finally it checks the 'hardware_subarch' field. This was + * introduced in 2.6.24 for lguest and Xen: if it's set to '1' (lguest's + * assigned number), then it calls us here. * * WARNING: be very careful here! We're running at addresses equal to physical - * addesses (around 0), not above PAGE_OFFSET as most code expectes + * addresses (around 0), not above PAGE_OFFSET as most code expects * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any * data without remembering to subtract __PAGE_OFFSET! * @@ -27,13 +31,18 @@ .section .init.text, "ax", @progbits ENTRY(lguest_entry) /* - * We make the "initialization" hypercall now to tell the Host about - * us, and also find out where it put our page tables. + * We make the "initialization" hypercall now to tell the Host where + * our lguest_data struct is. */ movl $LHCALL_LGUEST_INIT, %eax movl $lguest_data - __PAGE_OFFSET, %ebx int $LGUEST_TRAP_ENTRY + /* Now turn our pagetables on; setup by arch/x86/kernel/head_32.S. */ + movl $LHCALL_NEW_PGTABLE, %eax + movl $(initial_page_table - __PAGE_OFFSET), %ebx + int $LGUEST_TRAP_ENTRY + /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp @@ -96,12 +105,8 @@ send_interrupts: */ pushl %eax movl $LHCALL_SEND_INTERRUPTS, %eax - /* - * This is a vmcall instruction (same thing that KVM uses). Older - * assembler versions might not know the "vmcall" instruction, so we - * create one manually here. - */ - .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ + /* This is the actual hypercall trap. */ + int $LGUEST_TRAP_ENTRY /* Put eax back the way we found it. */ popl %eax ret diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2479f1..b00f678 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -18,8 +18,10 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o lib-y += thunk_$(BITS).o -lib-y += usercopy_$(BITS).o getuser.o putuser.o +lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-$(CONFIG_SMP) += rwlock.o +lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o obj-y += msr.o msr-reg.o msr-reg-export.o @@ -29,7 +31,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += atomic64_cx8_32.o lib-y += checksum_32.o lib-y += strstr_32.o - lib-y += semaphore_32.o string_32.o + lib-y += string_32.o lib-y += cmpxchg.o ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o @@ -40,7 +42,6 @@ else lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += thunk_64.o clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o - lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o - lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o + lib-y += copy_user_64.o copy_user_nocache_64.o lib-y += cmpxchg16b_emu.o endif diff --git a/arch/x86/lib/rwlock.S b/arch/x86/lib/rwlock.S new file mode 100644 index 0000000..1cad221 --- /dev/null +++ b/arch/x86/lib/rwlock.S @@ -0,0 +1,44 @@ +/* Slow paths of read/write spinlocks. */ + +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/frame.h> +#include <asm/rwlock.h> + +#ifdef CONFIG_X86_32 +# define __lock_ptr eax +#else +# define __lock_ptr rdi +#endif + +ENTRY(__write_lock_failed) + CFI_STARTPROC + FRAME +0: LOCK_PREFIX + WRITE_LOCK_ADD($RW_LOCK_BIAS) (%__lock_ptr) +1: rep; nop + cmpl $WRITE_LOCK_CMP, (%__lock_ptr) + jne 1b + LOCK_PREFIX + WRITE_LOCK_SUB($RW_LOCK_BIAS) (%__lock_ptr) + jnz 0b + ENDFRAME + ret + CFI_ENDPROC +END(__write_lock_failed) + +ENTRY(__read_lock_failed) + CFI_STARTPROC + FRAME +0: LOCK_PREFIX + READ_LOCK_SIZE(inc) (%__lock_ptr) +1: rep; nop + READ_LOCK_SIZE(cmp) $1, (%__lock_ptr) + js 1b + LOCK_PREFIX + READ_LOCK_SIZE(dec) (%__lock_ptr) + js 0b + ENDFRAME + ret + CFI_ENDPROC +END(__read_lock_failed) diff --git a/arch/x86/lib/rwlock_64.S b/arch/x86/lib/rwlock_64.S deleted file mode 100644 index 05ea55f..0000000 --- a/arch/x86/lib/rwlock_64.S +++ /dev/null @@ -1,38 +0,0 @@ -/* Slow paths of read/write spinlocks. */ - -#include <linux/linkage.h> -#include <asm/rwlock.h> -#include <asm/alternative-asm.h> -#include <asm/dwarf2.h> - -/* rdi: pointer to rwlock_t */ -ENTRY(__write_lock_failed) - CFI_STARTPROC - LOCK_PREFIX - addl $RW_LOCK_BIAS,(%rdi) -1: rep - nop - cmpl $RW_LOCK_BIAS,(%rdi) - jne 1b - LOCK_PREFIX - subl $RW_LOCK_BIAS,(%rdi) - jnz __write_lock_failed - ret - CFI_ENDPROC -END(__write_lock_failed) - -/* rdi: pointer to rwlock_t */ -ENTRY(__read_lock_failed) - CFI_STARTPROC - LOCK_PREFIX - incl (%rdi) -1: rep - nop - cmpl $1,(%rdi) - js 1b - LOCK_PREFIX - decl (%rdi) - js __read_lock_failed - ret - CFI_ENDPROC -END(__read_lock_failed) diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem.S index 6774397..5dff5f0 100644 --- a/arch/x86/lib/rwsem_64.S +++ b/arch/x86/lib/rwsem.S @@ -1,4 +1,51 @@ /* + * x86 semaphore implementation. + * + * (C) Copyright 1999 Linus Torvalds + * + * Portions Copyright 1999 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> + */ + +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/dwarf2.h> + +#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) +#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) + +#ifdef CONFIG_X86_32 + +/* + * The semaphore operations have a special calling sequence that + * allow us to do a simpler in-line version of them. These routines + * need to convert that sequence back into the C sequence when + * there is contention on the semaphore. + * + * %eax contains the semaphore pointer on entry. Save the C-clobbered + * registers (%eax, %edx and %ecx) except %eax whish is either a return + * value or just clobbered.. + */ + +#define save_common_regs \ + pushl_cfi %ecx; CFI_REL_OFFSET ecx, 0 + +#define restore_common_regs \ + popl_cfi %ecx; CFI_RESTORE ecx + + /* Avoid uglifying the argument copying x86-64 needs to do. */ + .macro movq src, dst + .endm + +#else + +/* * x86-64 rwsem wrappers * * This interfaces the inline asm code to the slow-path @@ -16,12 +63,6 @@ * but %rdi, %rsi, %rcx, %r8-r11 always need saving. */ -#include <linux/linkage.h> -#include <asm/rwlock.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> -#include <asm/dwarf2.h> - #define save_common_regs \ pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \ pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \ @@ -40,16 +81,18 @@ popq_cfi %rsi; CFI_RESTORE rsi; \ popq_cfi %rdi; CFI_RESTORE rdi +#endif + /* Fix up special calling conventions */ ENTRY(call_rwsem_down_read_failed) CFI_STARTPROC save_common_regs - pushq_cfi %rdx - CFI_REL_OFFSET rdx, 0 + __ASM_SIZE(push,_cfi) %__ASM_REG(dx) + CFI_REL_OFFSET __ASM_REG(dx), 0 movq %rax,%rdi call rwsem_down_read_failed - popq_cfi %rdx - CFI_RESTORE rdx + __ASM_SIZE(pop,_cfi) %__ASM_REG(dx) + CFI_RESTORE __ASM_REG(dx) restore_common_regs ret CFI_ENDPROC @@ -67,7 +110,8 @@ ENDPROC(call_rwsem_down_write_failed) ENTRY(call_rwsem_wake) CFI_STARTPROC - decl %edx /* do nothing if still outstanding active readers */ + /* do nothing if still outstanding active readers */ + __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) jnz 1f save_common_regs movq %rax,%rdi @@ -77,16 +121,15 @@ ENTRY(call_rwsem_wake) CFI_ENDPROC ENDPROC(call_rwsem_wake) -/* Fix up special calling conventions */ ENTRY(call_rwsem_downgrade_wake) CFI_STARTPROC save_common_regs - pushq_cfi %rdx - CFI_REL_OFFSET rdx, 0 + __ASM_SIZE(push,_cfi) %__ASM_REG(dx) + CFI_REL_OFFSET __ASM_REG(dx), 0 movq %rax,%rdi call rwsem_downgrade_wake - popq_cfi %rdx - CFI_RESTORE rdx + __ASM_SIZE(pop,_cfi) %__ASM_REG(dx) + CFI_RESTORE __ASM_REG(dx) restore_common_regs ret CFI_ENDPROC diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S deleted file mode 100644 index 06691da..0000000 --- a/arch/x86/lib/semaphore_32.S +++ /dev/null @@ -1,124 +0,0 @@ -/* - * i386 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> - */ - -#include <linux/linkage.h> -#include <asm/rwlock.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> -#include <asm/dwarf2.h> - -/* - * The semaphore operations have a special calling sequence that - * allow us to do a simpler in-line version of them. These routines - * need to convert that sequence back into the C sequence when - * there is contention on the semaphore. - * - * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax whish is either a return - * value or just clobbered.. - */ - .section .sched.text, "ax" - -/* - * rw spinlock fallbacks - */ -#ifdef CONFIG_SMP -ENTRY(__write_lock_failed) - CFI_STARTPROC - FRAME -2: LOCK_PREFIX - addl $ RW_LOCK_BIAS,(%eax) -1: rep; nop - cmpl $ RW_LOCK_BIAS,(%eax) - jne 1b - LOCK_PREFIX - subl $ RW_LOCK_BIAS,(%eax) - jnz 2b - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__write_lock_failed) - -ENTRY(__read_lock_failed) - CFI_STARTPROC - FRAME -2: LOCK_PREFIX - incl (%eax) -1: rep; nop - cmpl $1,(%eax) - js 1b - LOCK_PREFIX - decl (%eax) - js 2b - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__read_lock_failed) - -#endif - -#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM - -/* Fix up special calling conventions */ -ENTRY(call_rwsem_down_read_failed) - CFI_STARTPROC - pushl_cfi %ecx - CFI_REL_OFFSET ecx,0 - pushl_cfi %edx - CFI_REL_OFFSET edx,0 - call rwsem_down_read_failed - popl_cfi %edx - popl_cfi %ecx - ret - CFI_ENDPROC - ENDPROC(call_rwsem_down_read_failed) - -ENTRY(call_rwsem_down_write_failed) - CFI_STARTPROC - pushl_cfi %ecx - CFI_REL_OFFSET ecx,0 - calll rwsem_down_write_failed - popl_cfi %ecx - ret - CFI_ENDPROC - ENDPROC(call_rwsem_down_write_failed) - -ENTRY(call_rwsem_wake) - CFI_STARTPROC - decw %dx /* do nothing if still outstanding active readers */ - jnz 1f - pushl_cfi %ecx - CFI_REL_OFFSET ecx,0 - call rwsem_wake - popl_cfi %ecx -1: ret - CFI_ENDPROC - ENDPROC(call_rwsem_wake) - -/* Fix up special calling conventions */ -ENTRY(call_rwsem_downgrade_wake) - CFI_STARTPROC - pushl_cfi %ecx - CFI_REL_OFFSET ecx,0 - pushl_cfi %edx - CFI_REL_OFFSET edx,0 - call rwsem_downgrade_wake - popl_cfi %edx - popl_cfi %ecx - ret - CFI_ENDPROC - ENDPROC(call_rwsem_downgrade_wake) - -#endif diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index 782b082..a63efd6 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -5,50 +5,41 @@ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc. * Subject to the GNU public license, v.2. No warranty of any kind. */ +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/calling.h> - #include <linux/linkage.h> - #include <asm/dwarf2.h> - #include <asm/calling.h> - #include <asm/rwlock.h> - - /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro thunk name,func - .globl \name -\name: - CFI_STARTPROC - SAVE_ARGS - call \func - jmp restore - CFI_ENDPROC - .endm - -#ifdef CONFIG_TRACE_IRQFLAGS - /* put return address in rdi (arg1) */ - .macro thunk_ra name,func + /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ + .macro THUNK name, func, put_ret_addr_in_rdi=0 .globl \name \name: CFI_STARTPROC + + /* this one pushes 9 elems, the next one would be %rIP */ SAVE_ARGS - /* SAVE_ARGS pushs 9 elements */ - /* the next element would be the rip */ - movq 9*8(%rsp), %rdi + + .if \put_ret_addr_in_rdi + movq_cfi_restore 9*8, rdi + .endif + call \func jmp restore CFI_ENDPROC .endm - thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller - thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller +#ifdef CONFIG_TRACE_IRQFLAGS + THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1 + THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC - thunk lockdep_sys_exit_thunk,lockdep_sys_exit + THUNK lockdep_sys_exit_thunk,lockdep_sys_exit #endif - + /* SAVE_ARGS below is used only for the .cfi directives it contains. */ CFI_STARTPROC SAVE_ARGS restore: RESTORE_ARGS - ret + ret CFI_ENDPROC diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c new file mode 100644 index 0000000..97be9cb --- /dev/null +++ b/arch/x86/lib/usercopy.c @@ -0,0 +1,43 @@ +/* + * User address space access functions. + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/highmem.h> +#include <linux/module.h> + +/* + * best effort, GUP based copy_from_user() that is NMI-safe + */ +unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n) +{ + unsigned long offset, addr = (unsigned long)from; + unsigned long size, len = 0; + struct page *page; + void *map; + int ret; + + do { + ret = __get_user_pages_fast(addr, 1, 0, &page); + if (!ret) + break; + + offset = addr & (PAGE_SIZE - 1); + size = min(PAGE_SIZE - offset, n - len); + + map = kmap_atomic(page); + memcpy(to, map+offset, size); + kunmap_atomic(map); + put_page(page); + + len += size; + to += size; + addr += size; + + } while (len < n); + + return len; +} +EXPORT_SYMBOL_GPL(copy_from_user_nmi); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f7a2a05..4d09df0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -823,16 +823,30 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, force_sig_info_fault(SIGBUS, code, address, tsk, fault); } -static noinline void +static noinline int mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { + /* + * Pagefault was interrupted by SIGKILL. We have no reason to + * continue pagefault. + */ + if (fatal_signal_pending(current)) { + if (!(fault & VM_FAULT_RETRY)) + up_read(¤t->mm->mmap_sem); + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); + return 1; + } + if (!(fault & VM_FAULT_ERROR)) + return 0; + if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address); - return; + return 1; } out_of_memory(regs, error_code, address); @@ -843,6 +857,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, else BUG(); } + return 1; } static int spurious_fault_check(unsigned long error_code, pte_t *pte) @@ -1044,7 +1059,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* * If we're in an interrupt, have no user context or are running @@ -1133,19 +1148,9 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); - if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, fault); - return; - } - - /* - * Pagefault was interrupted by SIGKILL. We have no reason to - * continue pagefault. - */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { - if (!(error_code & PF_USER)) - no_context(regs, error_code, address); - return; + if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (mm_fault_error(regs, error_code, address, fault)) + return; } /* @@ -1156,11 +1161,11 @@ good_area: if (flags & FAULT_FLAG_ALLOW_RETRY) { if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } if (fault & VM_FAULT_RETRY) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d865c4a..bbaaa00 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -28,6 +28,7 @@ #include <linux/poison.h> #include <linux/dma-mapping.h> #include <linux/module.h> +#include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/nmi.h> #include <linux/gfp.h> @@ -895,8 +896,6 @@ const char *arch_vma_name(struct vm_area_struct *vma) } #ifdef CONFIG_X86_UV -#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) - unsigned long memory_block_size_bytes(void) { if (is_uv_system()) { diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index 704a37c..dab4187 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state, e->trace.entries = e->trace_entries; e->trace.max_entries = ARRAY_SIZE(e->trace_entries); e->trace.skip = 0; - save_stack_trace_regs(&e->trace, regs); + save_stack_trace_regs(regs, &e->trace); /* Round address down to nearest 16 bytes */ shadow_copy = kmemcheck_shadow_lookup(address diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c index aa11693..992da5e 100644 --- a/arch/x86/mm/memblock.c +++ b/arch/x86/mm/memblock.c @@ -8,7 +8,7 @@ #include <linux/range.h> /* Check for already reserved areas */ -static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align) +bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) { struct memblock_region *r; u64 addr = *addrp, last; @@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) if (addr >= ei_last) continue; *sizep = ei_last - addr; - while (check_with_memblock_reserved_size(&addr, sizep, align)) + while (memblock_x86_check_reserved_size(&addr, sizep, align)) ; if (*sizep) diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index a5b64ab..bff89df 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -11,10 +11,11 @@ #include <linux/oprofile.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/compat.h> +#include <linux/uaccess.h> + #include <asm/ptrace.h> -#include <asm/uaccess.h> #include <asm/stacktrace.h> -#include <linux/compat.h> static int backtrace_stack(void *data, char *name) { @@ -40,13 +41,13 @@ static struct stacktrace_ops backtrace_ops = { static struct stack_frame_ia32 * dump_user_backtrace_32(struct stack_frame_ia32 *head) { + /* Also check accessibility of one struct frame_head beyond: */ struct stack_frame_ia32 bufhead[2]; struct stack_frame_ia32 *fp; + unsigned long bytes; - /* Also check accessibility of one struct frame_head beyond */ - if (!access_ok(VERIFY_READ, head, sizeof(bufhead))) - return NULL; - if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead))) + bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); + if (bytes != sizeof(bufhead)) return NULL; fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame); @@ -87,12 +88,12 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) static struct stack_frame *dump_user_backtrace(struct stack_frame *head) { + /* Also check accessibility of one struct frame_head beyond: */ struct stack_frame bufhead[2]; + unsigned long bytes; - /* Also check accessibility of one struct stack_frame beyond */ - if (!access_ok(VERIFY_READ, head, sizeof(bufhead))) - return NULL; - if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead))) + bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); + if (bytes != sizeof(bufhead)) return NULL; oprofile_add_trace(bufhead[0].return_address); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cf97500..68894fd 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy) static int nmi_start(void) { get_online_cpus(); - on_each_cpu(nmi_cpu_start, NULL, 1); ctr_running = 1; + /* make ctr_running visible to the nmi handler: */ + smp_mb(); + on_each_cpu(nmi_cpu_start, NULL, 1); put_online_cpus(); return 0; } @@ -504,15 +506,18 @@ static int nmi_setup(void) nmi_enabled = 0; ctr_running = 0; - barrier(); + /* make variables visible to the nmi handler: */ + smp_mb(); err = register_die_notifier(&profile_exceptions_nb); if (err) goto fail; get_online_cpus(); register_cpu_notifier(&oprofile_cpu_nb); - on_each_cpu(nmi_cpu_setup, NULL, 1); nmi_enabled = 1; + /* make nmi_enabled visible to the nmi handler: */ + smp_mb(); + on_each_cpu(nmi_cpu_setup, NULL, 1); put_online_cpus(); return 0; @@ -531,7 +536,8 @@ static void nmi_shutdown(void) nmi_enabled = 0; ctr_running = 0; put_online_cpus(); - barrier(); + /* make variables visible to the nmi handler: */ + smp_mb(); unregister_die_notifier(&profile_exceptions_nb); msrs = &get_cpu_var(cpu_msrs); model->shutdown(msrs); diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index c3b8e24..9cbb710 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void) wrmsrl(MSR_AMD64_IBSOPCTL, 0); } -static inline int eilvt_is_available(int offset) +static inline int get_eilvt(int offset) { - /* check if we may assign a vector */ return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1); } +static inline int put_eilvt(int offset) +{ + return !setup_APIC_eilvt(offset, 0, 0, 1); +} + static inline int ibs_eilvt_valid(void) { int offset; u64 val; + int valid = 0; + + preempt_disable(); rdmsrl(MSR_AMD64_IBSCTL, val); offset = val & IBSCTL_LVT_OFFSET_MASK; @@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void) if (!(val & IBSCTL_LVT_OFFSET_VALID)) { pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n", smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - return 0; + goto out; } - if (!eilvt_is_available(offset)) { + if (!get_eilvt(offset)) { pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n", smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - return 0; + goto out; } - return 1; + valid = 1; +out: + preempt_enable(); + + return valid; } static inline int get_ibs_offset(void) @@ -598,69 +609,76 @@ static int setup_ibs_ctl(int ibs_eilvt_off) return 0; } +/* + * This runs only on the current cpu. We try to find an LVT offset and + * setup the local APIC. For this we must disable preemption. On + * success we initialize all nodes with this offset. This updates then + * the offset in the IBS_CTL per-node msr. The per-core APIC setup of + * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_- + * amd_cpu_shutdown() using the new offset. + */ static int force_ibs_eilvt_setup(void) { - int i; + int offset; int ret; - /* find the next free available EILVT entry */ - for (i = 1; i < 4; i++) { - if (!eilvt_is_available(i)) - continue; - ret = setup_ibs_ctl(i); - if (ret) - return ret; - pr_err(FW_BUG "using offset %d for IBS interrupts\n", i); - return 0; + preempt_disable(); + /* find the next free available EILVT entry, skip offset 0 */ + for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) { + if (get_eilvt(offset)) + break; } + preempt_enable(); - printk(KERN_DEBUG "No EILVT entry available\n"); - - return -EBUSY; -} - -static int __init_ibs_nmi(void) -{ - int ret; - - if (ibs_eilvt_valid()) - return 0; + if (offset == APIC_EILVT_NR_MAX) { + printk(KERN_DEBUG "No EILVT entry available\n"); + return -EBUSY; + } - ret = force_ibs_eilvt_setup(); + ret = setup_ibs_ctl(offset); if (ret) - return ret; + goto out; - if (!ibs_eilvt_valid()) - return -EFAULT; + if (!ibs_eilvt_valid()) { + ret = -EFAULT; + goto out; + } + pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset); pr_err(FW_BUG "workaround enabled for IBS LVT offset\n"); return 0; +out: + preempt_disable(); + put_eilvt(offset); + preempt_enable(); + return ret; } /* * check and reserve APIC extended interrupt LVT offset for IBS if * available - * - * init_ibs() preforms implicitly cpu-local operations, so pin this - * thread to its current CPU */ static void init_ibs(void) { - preempt_disable(); - ibs_caps = get_ibs_caps(); + if (!ibs_caps) + return; + + if (ibs_eilvt_valid()) goto out; - if (__init_ibs_nmi() < 0) - ibs_caps = 0; - else - printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); + if (!force_ibs_eilvt_setup()) + goto out; + + /* Failed to setup ibs */ + ibs_caps = 0; + return; out: - preempt_enable(); + printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); } static int (*create_arch_files)(struct super_block *sb, struct dentry *root); diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0972315..68c3c13 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point) return false; } -static void coalesce_windows(struct pci_root_info *info, int type) +static void coalesce_windows(struct pci_root_info *info, unsigned long type) { int i, j; struct resource *res1, *res2; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 8214724..1017c7b 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -1,8 +1,13 @@ /* - * Xen PCI Frontend Stub - puts some "dummy" functions in to the Linux - * x86 PCI core to support the Xen PCI Frontend + * Xen PCI - handle PCI (INTx) and MSI infrastructure calls for PV, HVM and + * initial domain support. We also handle the DSDT _PRT callbacks for GSI's + * used in HVM and initial domain mode (PV does not parse ACPI, so it has no + * concept of GSIs). Under PV we hook under the pnbbios API for IRQs and + * 0xcf8 PCI configuration read/write. * * Author: Ryan Wilson <hap9@epoch.ncsc.mil> + * Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> + * Stefano Stabellini <stefano.stabellini@eu.citrix.com> */ #include <linux/module.h> #include <linux/init.h> @@ -19,22 +24,53 @@ #include <xen/events.h> #include <asm/xen/pci.h> +static int xen_pcifront_enable_irq(struct pci_dev *dev) +{ + int rc; + int share = 1; + int pirq; + u8 gsi; + + rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", + rc); + return rc; + } + /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ + pirq = gsi; + + if (gsi < NR_IRQS_LEGACY) + share = 0; + + rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n", + gsi, pirq, rc); + return rc; + } + + dev->irq = rc; + dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); + return 0; +} + #ifdef CONFIG_ACPI -static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, - int trigger, int polarity) +static int xen_register_pirq(u32 gsi, int gsi_override, int triggering, + bool set_pirq) { - int rc, irq; + int rc, pirq = -1, irq = -1; struct physdev_map_pirq map_irq; int shareable = 0; char *name; - if (!xen_hvm_domain()) - return -1; + if (set_pirq) + pirq = gsi; map_irq.domid = DOMID_SELF; map_irq.type = MAP_PIRQ_TYPE_GSI; map_irq.index = gsi; - map_irq.pirq = -1; + map_irq.pirq = pirq; rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); if (rc) { @@ -42,7 +78,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, return -1; } - if (trigger == ACPI_EDGE_SENSITIVE) { + if (triggering == ACPI_EDGE_SENSITIVE) { shareable = 0; name = "ioapic-edge"; } else { @@ -50,12 +86,63 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, name = "ioapic-level"; } + if (gsi_override >= 0) + gsi = gsi_override; + irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name); + if (irq < 0) + goto out; - printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq); + printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d (gsi=%d)\n", map_irq.pirq, irq, gsi); +out: + return irq; +} + +static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, + int trigger, int polarity) +{ + if (!xen_hvm_domain()) + return -1; + + return xen_register_pirq(gsi, -1 /* no GSI override */, trigger, + false /* no mapping of GSI to PIRQ */); +} + +#ifdef CONFIG_XEN_DOM0 +static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polarity) +{ + int rc, irq; + struct physdev_setup_gsi setup_gsi; + + if (!xen_pv_domain()) + return -1; + + printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n", + gsi, triggering, polarity); + + irq = xen_register_pirq(gsi, gsi_override, triggering, true); + + setup_gsi.gsi = gsi; + setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1); + setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + + rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); + if (rc == -EEXIST) + printk(KERN_INFO "Already setup the GSI :%d\n", gsi); + else if (rc) { + printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n", + gsi, rc); + } return irq; } + +static int acpi_register_gsi_xen(struct device *dev, u32 gsi, + int trigger, int polarity) +{ + return xen_register_gsi(gsi, -1 /* no GSI override */, trigger, polarity); +} +#endif #endif #if defined(CONFIG_PCI_MSI) @@ -65,6 +152,43 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); +static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + int irq, ret, i; + struct msi_desc *msidesc; + int *v; + + v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL); + if (!v) + return -ENOMEM; + + if (type == PCI_CAP_ID_MSIX) + ret = xen_pci_frontend_enable_msix(dev, v, nvec); + else + ret = xen_pci_frontend_enable_msi(dev, v); + if (ret) + goto error; + i = 0; + list_for_each_entry(msidesc, &dev->msi_list, list) { + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + (type == PCI_CAP_ID_MSIX) ? + "pcifront-msi-x" : + "pcifront-msi", + DOMID_SELF); + if (irq < 0) + goto free; + i++; + } + kfree(v); + return 0; + +error: + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); +free: + kfree(v); + return ret; +} + #define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \ MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0)) @@ -123,67 +247,6 @@ error: return -ENODEV; } -/* - * For MSI interrupts we have to use drivers/xen/event.s functions to - * allocate an irq_desc and setup the right */ - - -static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - int irq, ret, i; - struct msi_desc *msidesc; - int *v; - - v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL); - if (!v) - return -ENOMEM; - - if (type == PCI_CAP_ID_MSIX) - ret = xen_pci_frontend_enable_msix(dev, v, nvec); - else - ret = xen_pci_frontend_enable_msi(dev, v); - if (ret) - goto error; - i = 0; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, - (type == PCI_CAP_ID_MSIX) ? - "pcifront-msi-x" : - "pcifront-msi", - DOMID_SELF); - if (irq < 0) - goto free; - i++; - } - kfree(v); - return 0; - -error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); -free: - kfree(v); - return ret; -} - -static void xen_teardown_msi_irqs(struct pci_dev *dev) -{ - struct msi_desc *msidesc; - - msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); - if (msidesc->msi_attrib.is_msix) - xen_pci_frontend_disable_msix(dev); - else - xen_pci_frontend_disable_msi(dev); - - /* Free the IRQ's and the msidesc using the generic code. */ - default_teardown_msi_irqs(dev); -} - -static void xen_teardown_msi_irq(unsigned int irq) -{ - xen_destroy_irq(irq); -} - #ifdef CONFIG_XEN_DOM0 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { @@ -242,45 +305,28 @@ out: return ret; } #endif -#endif -static int xen_pcifront_enable_irq(struct pci_dev *dev) +static void xen_teardown_msi_irqs(struct pci_dev *dev) { - int rc; - int share = 1; - int pirq; - u8 gsi; - - rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", - rc); - return rc; - } - - rc = xen_allocate_pirq_gsi(gsi); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to allocate a PIRQ for GSI%d: %d\n", - gsi, rc); - return rc; - } - pirq = rc; + struct msi_desc *msidesc; - if (gsi < NR_IRQS_LEGACY) - share = 0; + msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + if (msidesc->msi_attrib.is_msix) + xen_pci_frontend_disable_msix(dev); + else + xen_pci_frontend_disable_msi(dev); - rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n", - gsi, pirq, rc); - return rc; - } + /* Free the IRQ's and the msidesc using the generic code. */ + default_teardown_msi_irqs(dev); +} - dev->irq = rc; - dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); - return 0; +static void xen_teardown_msi_irq(unsigned int irq) +{ + xen_destroy_irq(irq); } +#endif + int __init pci_xen_init(void) { if (!xen_pv_domain() || xen_initial_domain()) @@ -327,82 +373,13 @@ int __init pci_xen_hvm_init(void) } #ifdef CONFIG_XEN_DOM0 -static int xen_register_pirq(u32 gsi, int triggering) -{ - int rc, pirq, irq = -1; - struct physdev_map_pirq map_irq; - int shareable = 0; - char *name; - - if (!xen_pv_domain()) - return -1; - - if (triggering == ACPI_EDGE_SENSITIVE) { - shareable = 0; - name = "ioapic-edge"; - } else { - shareable = 1; - name = "ioapic-level"; - } - - pirq = xen_allocate_pirq_gsi(gsi); - if (pirq < 0) - goto out; - - irq = xen_bind_pirq_gsi_to_irq(gsi, pirq, shareable, name); - if (irq < 0) - goto out; - - printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d\n", pirq, irq); - - map_irq.domid = DOMID_SELF; - map_irq.type = MAP_PIRQ_TYPE_GSI; - map_irq.index = gsi; - map_irq.pirq = pirq; - - rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); - if (rc) { - printk(KERN_WARNING "xen map irq failed %d\n", rc); - return -1; - } - -out: - return irq; -} - -static int xen_register_gsi(u32 gsi, int triggering, int polarity) -{ - int rc, irq; - struct physdev_setup_gsi setup_gsi; - - if (!xen_pv_domain()) - return -1; - - printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n", - gsi, triggering, polarity); - - irq = xen_register_pirq(gsi, triggering); - - setup_gsi.gsi = gsi; - setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1); - setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - - rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); - if (rc == -EEXIST) - printk(KERN_INFO "Already setup the GSI :%d\n", gsi); - else if (rc) { - printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n", - gsi, rc); - } - - return irq; -} - static __init void xen_setup_acpi_sci(void) { int rc; int trigger, polarity; int gsi = acpi_sci_override_gsi; + int irq = -1; + int gsi_override = -1; if (!gsi) return; @@ -415,51 +392,43 @@ static __init void xen_setup_acpi_sci(void) } trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; - + printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d " "polarity=%d\n", gsi, trigger, polarity); - gsi = xen_register_gsi(gsi, trigger, polarity); + /* Before we bind the GSI to a Linux IRQ, check whether + * we need to override it with bus_irq (IRQ) value. Usually for + * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so: + * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level) + * but there are oddballs where the IRQ != GSI: + * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level) + * which ends up being: gsi_to_irq[9] == 20 + * (which is what acpi_gsi_to_irq ends up calling when starting the + * the ACPI interpreter and keels over since IRQ 9 has not been + * setup as we had setup IRQ 20 for it). + */ + if (acpi_gsi_to_irq(gsi, &irq) == 0) { + /* Use the provided value if it's valid. */ + if (irq >= 0) + gsi_override = irq; + } + + gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity); printk(KERN_INFO "xen: acpi sci %d\n", gsi); return; } -static int acpi_register_gsi_xen(struct device *dev, u32 gsi, - int trigger, int polarity) +int __init pci_xen_initial_domain(void) { - return xen_register_gsi(gsi, trigger, polarity); -} + int irq; -static int __init pci_xen_initial_domain(void) -{ #ifdef CONFIG_PCI_MSI x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; - - return 0; -} - -void __init xen_setup_pirqs(void) -{ - int pirq, irq; - - pci_xen_initial_domain(); - - if (0 == nr_ioapics) { - for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { - pirq = xen_allocate_pirq_gsi(irq); - if (WARN(pirq < 0, - "Could not allocate PIRQ for legacy interrupt\n")) - break; - irq = xen_bind_pirq_gsi_to_irq(irq, pirq, 0, "xt-pic"); - } - return; - } - /* Pre-allocate legacy irqs */ for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { int trigger, polarity; @@ -467,13 +436,17 @@ void __init xen_setup_pirqs(void) if (acpi_get_override_irq(irq, &trigger, &polarity) == -1) continue; - xen_register_pirq(irq, - trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE); + xen_register_pirq(irq, -1 /* no GSI override */, + trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE, + true /* Map GSI to PIRQ */); } + if (0 == nr_ioapics) { + for (irq = 0; irq < NR_IRQS_LEGACY; irq++) + xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic"); + } + return 0; } -#endif -#ifdef CONFIG_XEN_DOM0 struct xen_device_domain_owner { domid_t domain; struct pci_dev *dev; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index b30aa26..cfc588c 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -79,26 +79,50 @@ early_param("add_efi_memmap", setup_add_efi_memmap); static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { - return efi_call_virt2(get_time, tm, tc); + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt2(get_time, tm, tc); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; } static efi_status_t virt_efi_set_time(efi_time_t *tm) { - return efi_call_virt1(set_time, tm); + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt1(set_time, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; } static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm) { - return efi_call_virt3(get_wakeup_time, - enabled, pending, tm); + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt3(get_wakeup_time, + enabled, pending, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; } static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { - return efi_call_virt2(set_wakeup_time, - enabled, tm); + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + status = efi_call_virt2(set_wakeup_time, + enabled, tm); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; } static efi_status_t virt_efi_get_variable(efi_char16_t *name, @@ -164,11 +188,14 @@ static efi_status_t __init phys_efi_set_virtual_address_map( static efi_status_t __init phys_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { + unsigned long flags; efi_status_t status; + spin_lock_irqsave(&rtc_lock, flags); efi_call_phys_prelog(); status = efi_call_phys2(efi_phys.get_time, tm, tc); efi_call_phys_epilog(); + spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -304,6 +331,61 @@ static void __init print_efi_memmap(void) } #endif /* EFI_DEBUG */ +void __init efi_reserve_boot_services(void) +{ + void *p; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + u64 start = md->phys_addr; + u64 size = md->num_pages << EFI_PAGE_SHIFT; + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + /* Only reserve where possible: + * - Not within any already allocated areas + * - Not over any memory area (really needed, if above?) + * - Not within any part of the kernel + * - Not the bios reserved area + */ + if ((start+size >= virt_to_phys(_text) + && start <= virt_to_phys(_end)) || + !e820_all_mapped(start, start+size, E820_RAM) || + memblock_x86_check_reserved_size(&start, &size, + 1<<EFI_PAGE_SHIFT)) { + /* Could not reserve, skip it */ + md->num_pages = 0; + memblock_dbg(PFX "Could not reserve boot range " + "[0x%010llx-0x%010llx]\n", + start, start+size-1); + } else + memblock_x86_reserve_range(start, start+size, + "EFI Boot"); + } +} + +static void __init efi_free_boot_services(void) +{ + void *p; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + unsigned long long start = md->phys_addr; + unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + + /* Could not reserve boot area */ + if (!size) + continue; + + free_bootmem_late(start, size); + } +} + void __init efi_init(void) { efi_config_table_t *config_tables; @@ -449,9 +531,6 @@ void __init efi_init(void) x86_platform.set_wallclock = efi_set_rtc_mmss; #endif - /* Setup for EFI runtime service */ - reboot_type = BOOT_EFI; - #if EFI_DEBUG print_efi_memmap(); #endif @@ -536,7 +615,9 @@ void __init efi_enter_virtual_mode(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME)) + if (!(md->attribute & EFI_MEMORY_RUNTIME) && + md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) continue; size = md->num_pages << EFI_PAGE_SHIFT; @@ -593,6 +674,13 @@ void __init efi_enter_virtual_mode(void) } /* + * Thankfully, it does seem that no runtime services other than + * SetVirtualAddressMap() will touch boot services code, so we can + * get rid of it all at this point + */ + efi_free_boot_services(); + + /* * Now that EFI is in virtual mode, update the function * pointers in the runtime service table to the new virtual addresses. * diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2649426..ac3aa54 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -49,10 +49,11 @@ static void __init early_code_mapping_set_exec(int executable) if (!(__supported_pte_mask & _PAGE_NX)) return; - /* Make EFI runtime service code area executable */ + /* Make EFI service code area executable */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (md->type == EFI_RUNTIME_SERVICES_CODE) + if (md->type == EFI_RUNTIME_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_CODE) efi_set_executable(md, executable); } } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index c58e0ea..68e467f 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1,7 +1,7 @@ /* * SGI UltraViolet TLB flush routines. * - * (c) 2008-2010 Cliff Wickman <cpw@sgi.com>, SGI. + * (c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI. * * This code is released under the GNU General Public License version 2 or * later. @@ -35,6 +35,7 @@ static int timeout_base_ns[] = { 5242880, 167772160 }; + static int timeout_us; static int nobau; static int baudisabled; @@ -42,20 +43,70 @@ static spinlock_t disable_lock; static cycles_t congested_cycles; /* tunables: */ -static int max_bau_concurrent = MAX_BAU_CONCURRENT; -static int max_bau_concurrent_constant = MAX_BAU_CONCURRENT; -static int plugged_delay = PLUGGED_DELAY; -static int plugsb4reset = PLUGSB4RESET; -static int timeoutsb4reset = TIMEOUTSB4RESET; -static int ipi_reset_limit = IPI_RESET_LIMIT; -static int complete_threshold = COMPLETE_THRESHOLD; -static int congested_response_us = CONGESTED_RESPONSE_US; -static int congested_reps = CONGESTED_REPS; -static int congested_period = CONGESTED_PERIOD; +static int max_concurr = MAX_BAU_CONCURRENT; +static int max_concurr_const = MAX_BAU_CONCURRENT; +static int plugged_delay = PLUGGED_DELAY; +static int plugsb4reset = PLUGSB4RESET; +static int timeoutsb4reset = TIMEOUTSB4RESET; +static int ipi_reset_limit = IPI_RESET_LIMIT; +static int complete_threshold = COMPLETE_THRESHOLD; +static int congested_respns_us = CONGESTED_RESPONSE_US; +static int congested_reps = CONGESTED_REPS; +static int congested_period = CONGESTED_PERIOD; + +static struct tunables tunables[] = { + {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */ + {&plugged_delay, PLUGGED_DELAY}, + {&plugsb4reset, PLUGSB4RESET}, + {&timeoutsb4reset, TIMEOUTSB4RESET}, + {&ipi_reset_limit, IPI_RESET_LIMIT}, + {&complete_threshold, COMPLETE_THRESHOLD}, + {&congested_respns_us, CONGESTED_RESPONSE_US}, + {&congested_reps, CONGESTED_REPS}, + {&congested_period, CONGESTED_PERIOD} +}; + static struct dentry *tunables_dir; static struct dentry *tunables_file; -static int __init setup_nobau(char *arg) +/* these correspond to the statistics printed by ptc_seq_show() */ +static char *stat_description[] = { + "sent: number of shootdown messages sent", + "stime: time spent sending messages", + "numuvhubs: number of hubs targeted with shootdown", + "numuvhubs16: number times 16 or more hubs targeted", + "numuvhubs8: number times 8 or more hubs targeted", + "numuvhubs4: number times 4 or more hubs targeted", + "numuvhubs2: number times 2 or more hubs targeted", + "numuvhubs1: number times 1 hub targeted", + "numcpus: number of cpus targeted with shootdown", + "dto: number of destination timeouts", + "retries: destination timeout retries sent", + "rok: : destination timeouts successfully retried", + "resetp: ipi-style resource resets for plugs", + "resett: ipi-style resource resets for timeouts", + "giveup: fall-backs to ipi-style shootdowns", + "sto: number of source timeouts", + "bz: number of stay-busy's", + "throt: number times spun in throttle", + "swack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE", + "recv: shootdown messages received", + "rtime: time spent processing messages", + "all: shootdown all-tlb messages", + "one: shootdown one-tlb messages", + "mult: interrupts that found multiple messages", + "none: interrupts that found no messages", + "retry: number of retry messages processed", + "canc: number messages canceled by retries", + "nocan: number retries that found nothing to cancel", + "reset: number of ipi-style reset requests processed", + "rcan: number messages canceled by reset requests", + "disable: number times use of the BAU was disabled", + "enable: number times use of the BAU was re-enabled" +}; + +static int __init +setup_nobau(char *arg) { nobau = 1; return 0; @@ -63,7 +114,7 @@ static int __init setup_nobau(char *arg) early_param("nobau", setup_nobau); /* base pnode in this partition */ -static int uv_partition_base_pnode __read_mostly; +static int uv_base_pnode __read_mostly; /* position of pnode (which is nasid>>1): */ static int uv_nshift __read_mostly; static unsigned long uv_mmask __read_mostly; @@ -109,60 +160,52 @@ static int __init uvhub_to_first_apicid(int uvhub) * clear of the Timeout bit (as well) will free the resource. No reply will * be sent (the hardware will only do one reply per message). */ -static inline void uv_reply_to_message(struct msg_desc *mdp, - struct bau_control *bcp) +static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp) { unsigned long dw; - struct bau_payload_queue_entry *msg; + struct bau_pq_entry *msg; msg = mdp->msg; if (!msg->canceled) { - dw = (msg->sw_ack_vector << UV_SW_ACK_NPENDING) | - msg->sw_ack_vector; - uv_write_local_mmr( - UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw); + dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec; + write_mmr_sw_ack(dw); } msg->replied_to = 1; - msg->sw_ack_vector = 0; + msg->swack_vec = 0; } /* * Process the receipt of a RETRY message */ -static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, - struct bau_control *bcp) +static void bau_process_retry_msg(struct msg_desc *mdp, + struct bau_control *bcp) { int i; int cancel_count = 0; - int slot2; unsigned long msg_res; unsigned long mmr = 0; - struct bau_payload_queue_entry *msg; - struct bau_payload_queue_entry *msg2; - struct ptc_stats *stat; + struct bau_pq_entry *msg = mdp->msg; + struct bau_pq_entry *msg2; + struct ptc_stats *stat = bcp->statp; - msg = mdp->msg; - stat = bcp->statp; stat->d_retries++; /* * cancel any message from msg+1 to the retry itself */ for (msg2 = msg+1, i = 0; i < DEST_Q_SIZE; msg2++, i++) { - if (msg2 > mdp->va_queue_last) - msg2 = mdp->va_queue_first; + if (msg2 > mdp->queue_last) + msg2 = mdp->queue_first; if (msg2 == msg) break; - /* same conditions for cancellation as uv_do_reset */ + /* same conditions for cancellation as do_reset */ if ((msg2->replied_to == 0) && (msg2->canceled == 0) && - (msg2->sw_ack_vector) && ((msg2->sw_ack_vector & - msg->sw_ack_vector) == 0) && + (msg2->swack_vec) && ((msg2->swack_vec & + msg->swack_vec) == 0) && (msg2->sending_cpu == msg->sending_cpu) && (msg2->msg_type != MSG_NOOP)) { - slot2 = msg2 - mdp->va_queue_first; - mmr = uv_read_local_mmr - (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); - msg_res = msg2->sw_ack_vector; + mmr = read_mmr_sw_ack(); + msg_res = msg2->swack_vec; /* * This is a message retry; clear the resources held * by the previous message only if they timed out. @@ -170,6 +213,7 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, * situation to report. */ if (mmr & (msg_res << UV_SW_ACK_NPENDING)) { + unsigned long mr; /* * is the resource timed out? * make everyone ignore the cancelled message. @@ -177,10 +221,8 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, msg2->canceled = 1; stat->d_canceled++; cancel_count++; - uv_write_local_mmr( - UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, - (msg_res << UV_SW_ACK_NPENDING) | - msg_res); + mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res; + write_mmr_sw_ack(mr); } } } @@ -192,20 +234,19 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, * Do all the things a cpu should do for a TLB shootdown message. * Other cpu's may come here at the same time for this message. */ -static void uv_bau_process_message(struct msg_desc *mdp, - struct bau_control *bcp) +static void bau_process_message(struct msg_desc *mdp, + struct bau_control *bcp) { - int msg_ack_count; short socket_ack_count = 0; - struct ptc_stats *stat; - struct bau_payload_queue_entry *msg; + short *sp; + struct atomic_short *asp; + struct ptc_stats *stat = bcp->statp; + struct bau_pq_entry *msg = mdp->msg; struct bau_control *smaster = bcp->socket_master; /* * This must be a normal message, or retry of a normal message */ - msg = mdp->msg; - stat = bcp->statp; if (msg->address == TLB_FLUSH_ALL) { local_flush_tlb(); stat->d_alltlb++; @@ -222,30 +263,32 @@ static void uv_bau_process_message(struct msg_desc *mdp, * cpu number. */ if (msg->msg_type == MSG_RETRY && bcp == bcp->uvhub_master) - uv_bau_process_retry_msg(mdp, bcp); + bau_process_retry_msg(mdp, bcp); /* - * This is a sw_ack message, so we have to reply to it. + * This is a swack message, so we have to reply to it. * Count each responding cpu on the socket. This avoids * pinging the count's cache line back and forth between * the sockets. */ - socket_ack_count = atomic_add_short_return(1, (struct atomic_short *) - &smaster->socket_acknowledge_count[mdp->msg_slot]); + sp = &smaster->socket_acknowledge_count[mdp->msg_slot]; + asp = (struct atomic_short *)sp; + socket_ack_count = atom_asr(1, asp); if (socket_ack_count == bcp->cpus_in_socket) { + int msg_ack_count; /* * Both sockets dump their completed count total into * the message's count. */ smaster->socket_acknowledge_count[mdp->msg_slot] = 0; - msg_ack_count = atomic_add_short_return(socket_ack_count, - (struct atomic_short *)&msg->acknowledge_count); + asp = (struct atomic_short *)&msg->acknowledge_count; + msg_ack_count = atom_asr(socket_ack_count, asp); if (msg_ack_count == bcp->cpus_in_uvhub) { /* * All cpus in uvhub saw it; reply */ - uv_reply_to_message(mdp, bcp); + reply_to_message(mdp, bcp); } } @@ -268,62 +311,51 @@ static int uvhub_to_first_cpu(int uvhub) * Last resort when we get a large number of destination timeouts is * to clear resources held by a given cpu. * Do this with IPI so that all messages in the BAU message queue - * can be identified by their nonzero sw_ack_vector field. + * can be identified by their nonzero swack_vec field. * * This is entered for a single cpu on the uvhub. * The sender want's this uvhub to free a specific message's - * sw_ack resources. + * swack resources. */ -static void -uv_do_reset(void *ptr) +static void do_reset(void *ptr) { int i; - int slot; - int count = 0; - unsigned long mmr; - unsigned long msg_res; - struct bau_control *bcp; - struct reset_args *rap; - struct bau_payload_queue_entry *msg; - struct ptc_stats *stat; + struct bau_control *bcp = &per_cpu(bau_control, smp_processor_id()); + struct reset_args *rap = (struct reset_args *)ptr; + struct bau_pq_entry *msg; + struct ptc_stats *stat = bcp->statp; - bcp = &per_cpu(bau_control, smp_processor_id()); - rap = (struct reset_args *)ptr; - stat = bcp->statp; stat->d_resets++; - /* * We're looking for the given sender, and - * will free its sw_ack resource. + * will free its swack resource. * If all cpu's finally responded after the timeout, its * message 'replied_to' was set. */ - for (msg = bcp->va_queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) { - /* uv_do_reset: same conditions for cancellation as - uv_bau_process_retry_msg() */ + for (msg = bcp->queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) { + unsigned long msg_res; + /* do_reset: same conditions for cancellation as + bau_process_retry_msg() */ if ((msg->replied_to == 0) && (msg->canceled == 0) && (msg->sending_cpu == rap->sender) && - (msg->sw_ack_vector) && + (msg->swack_vec) && (msg->msg_type != MSG_NOOP)) { + unsigned long mmr; + unsigned long mr; /* * make everyone else ignore this message */ msg->canceled = 1; - slot = msg - bcp->va_queue_first; - count++; /* * only reset the resource if it is still pending */ - mmr = uv_read_local_mmr - (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); - msg_res = msg->sw_ack_vector; + mmr = read_mmr_sw_ack(); + msg_res = msg->swack_vec; + mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res; if (mmr & msg_res) { stat->d_rcanceled++; - uv_write_local_mmr( - UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, - (msg_res << UV_SW_ACK_NPENDING) | - msg_res); + write_mmr_sw_ack(mr); } } } @@ -334,39 +366,38 @@ uv_do_reset(void *ptr) * Use IPI to get all target uvhubs to release resources held by * a given sending cpu number. */ -static void uv_reset_with_ipi(struct bau_target_uvhubmask *distribution, - int sender) +static void reset_with_ipi(struct bau_targ_hubmask *distribution, int sender) { int uvhub; - int cpu; + int maskbits; cpumask_t mask; struct reset_args reset_args; reset_args.sender = sender; - cpus_clear(mask); /* find a single cpu for each uvhub in this distribution mask */ - for (uvhub = 0; - uvhub < sizeof(struct bau_target_uvhubmask) * BITSPERBYTE; - uvhub++) { + maskbits = sizeof(struct bau_targ_hubmask) * BITSPERBYTE; + for (uvhub = 0; uvhub < maskbits; uvhub++) { + int cpu; if (!bau_uvhub_isset(uvhub, distribution)) continue; /* find a cpu for this uvhub */ cpu = uvhub_to_first_cpu(uvhub); cpu_set(cpu, mask); } - /* IPI all cpus; Preemption is already disabled */ - smp_call_function_many(&mask, uv_do_reset, (void *)&reset_args, 1); + + /* IPI all cpus; preemption is already disabled */ + smp_call_function_many(&mask, do_reset, (void *)&reset_args, 1); return; } -static inline unsigned long -cycles_2_us(unsigned long long cyc) +static inline unsigned long cycles_2_us(unsigned long long cyc) { unsigned long long ns; unsigned long us; - ns = (cyc * per_cpu(cyc2ns, smp_processor_id())) - >> CYC2NS_SCALE_FACTOR; + int cpu = smp_processor_id(); + + ns = (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR; us = ns / 1000; return us; } @@ -376,56 +407,56 @@ cycles_2_us(unsigned long long cyc) * leaves uvhub_quiesce set so that no new broadcasts are started by * bau_flush_send_and_wait() */ -static inline void -quiesce_local_uvhub(struct bau_control *hmaster) +static inline void quiesce_local_uvhub(struct bau_control *hmaster) { - atomic_add_short_return(1, (struct atomic_short *) - &hmaster->uvhub_quiesce); + atom_asr(1, (struct atomic_short *)&hmaster->uvhub_quiesce); } /* * mark this quiet-requestor as done */ -static inline void -end_uvhub_quiesce(struct bau_control *hmaster) +static inline void end_uvhub_quiesce(struct bau_control *hmaster) { - atomic_add_short_return(-1, (struct atomic_short *) - &hmaster->uvhub_quiesce); + atom_asr(-1, (struct atomic_short *)&hmaster->uvhub_quiesce); +} + +static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift) +{ + unsigned long descriptor_status; + + descriptor_status = uv_read_local_mmr(mmr_offset); + descriptor_status >>= right_shift; + descriptor_status &= UV_ACT_STATUS_MASK; + return descriptor_status; } /* * Wait for completion of a broadcast software ack message * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP */ -static int uv_wait_completion(struct bau_desc *bau_desc, - unsigned long mmr_offset, int right_shift, int this_cpu, - struct bau_control *bcp, struct bau_control *smaster, long try) +static int uv1_wait_completion(struct bau_desc *bau_desc, + unsigned long mmr_offset, int right_shift, + struct bau_control *bcp, long try) { unsigned long descriptor_status; - cycles_t ttime; + cycles_t ttm; struct ptc_stats *stat = bcp->statp; - struct bau_control *hmaster; - - hmaster = bcp->uvhub_master; + descriptor_status = uv1_read_status(mmr_offset, right_shift); /* spin on the status MMR, waiting for it to go idle */ - while ((descriptor_status = (((unsigned long) - uv_read_local_mmr(mmr_offset) >> - right_shift) & UV_ACT_STATUS_MASK)) != - DESC_STATUS_IDLE) { + while ((descriptor_status != DS_IDLE)) { /* - * Our software ack messages may be blocked because there are - * no swack resources available. As long as none of them - * has timed out hardware will NACK our message and its - * state will stay IDLE. + * Our software ack messages may be blocked because + * there are no swack resources available. As long + * as none of them has timed out hardware will NACK + * our message and its state will stay IDLE. */ - if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) { + if (descriptor_status == DS_SOURCE_TIMEOUT) { stat->s_stimeout++; return FLUSH_GIVEUP; - } else if (descriptor_status == - DESC_STATUS_DESTINATION_TIMEOUT) { + } else if (descriptor_status == DS_DESTINATION_TIMEOUT) { stat->s_dtimeout++; - ttime = get_cycles(); + ttm = get_cycles(); /* * Our retries may be blocked by all destination @@ -433,8 +464,7 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * pending. In that case hardware returns the * ERROR that looks like a destination timeout. */ - if (cycles_2_us(ttime - bcp->send_message) < - timeout_us) { + if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { bcp->conseccompletes = 0; return FLUSH_RETRY_PLUGGED; } @@ -447,80 +477,160 @@ static int uv_wait_completion(struct bau_desc *bau_desc, */ cpu_relax(); } + descriptor_status = uv1_read_status(mmr_offset, right_shift); } bcp->conseccompletes++; return FLUSH_COMPLETE; } -static inline cycles_t -sec_2_cycles(unsigned long sec) +/* + * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register. + */ +static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu) { - unsigned long ns; - cycles_t cyc; + unsigned long descriptor_status; + unsigned long descriptor_status2; - ns = sec * 1000000000; - cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); - return cyc; + descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK); + descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL; + descriptor_status = (descriptor_status << 1) | descriptor_status2; + return descriptor_status; +} + +static int uv2_wait_completion(struct bau_desc *bau_desc, + unsigned long mmr_offset, int right_shift, + struct bau_control *bcp, long try) +{ + unsigned long descriptor_stat; + cycles_t ttm; + int cpu = bcp->uvhub_cpu; + struct ptc_stats *stat = bcp->statp; + + descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + + /* spin on the status MMR, waiting for it to go idle */ + while (descriptor_stat != UV2H_DESC_IDLE) { + /* + * Our software ack messages may be blocked because + * there are no swack resources available. As long + * as none of them has timed out hardware will NACK + * our message and its state will stay IDLE. + */ + if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) || + (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) || + (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) { + stat->s_stimeout++; + return FLUSH_GIVEUP; + } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) { + stat->s_dtimeout++; + ttm = get_cycles(); + /* + * Our retries may be blocked by all destination + * swack resources being consumed, and a timeout + * pending. In that case hardware returns the + * ERROR that looks like a destination timeout. + */ + if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { + bcp->conseccompletes = 0; + return FLUSH_RETRY_PLUGGED; + } + bcp->conseccompletes = 0; + return FLUSH_RETRY_TIMEOUT; + } else { + /* + * descriptor_stat is still BUSY + */ + cpu_relax(); + } + descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + } + bcp->conseccompletes++; + return FLUSH_COMPLETE; } /* - * conditionally add 1 to *v, unless *v is >= u - * return 0 if we cannot add 1 to *v because it is >= u - * return 1 if we can add 1 to *v because it is < u - * the add is atomic - * - * This is close to atomic_add_unless(), but this allows the 'u' value - * to be lowered below the current 'v'. atomic_add_unless can only stop - * on equal. + * There are 2 status registers; each and array[32] of 2 bits. Set up for + * which register to read and position in that register based on cpu in + * current hub. */ -static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) +static int wait_completion(struct bau_desc *bau_desc, + struct bau_control *bcp, long try) { - spin_lock(lock); - if (atomic_read(v) >= u) { - spin_unlock(lock); - return 0; + int right_shift; + unsigned long mmr_offset; + int cpu = bcp->uvhub_cpu; + + if (cpu < UV_CPUS_PER_AS) { + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; + right_shift = cpu * UV_ACT_STATUS_SIZE; + } else { + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; + right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); } - atomic_inc(v); - spin_unlock(lock); - return 1; + + if (is_uv1_hub()) + return uv1_wait_completion(bau_desc, mmr_offset, right_shift, + bcp, try); + else + return uv2_wait_completion(bau_desc, mmr_offset, right_shift, + bcp, try); +} + +static inline cycles_t sec_2_cycles(unsigned long sec) +{ + unsigned long ns; + cycles_t cyc; + + ns = sec * 1000000000; + cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); + return cyc; } /* - * Our retries are blocked by all destination swack resources being + * Our retries are blocked by all destination sw ack resources being * in use, and a timeout is pending. In that case hardware immediately * returns the ERROR that looks like a destination timeout. */ -static void -destination_plugged(struct bau_desc *bau_desc, struct bau_control *bcp, +static void destination_plugged(struct bau_desc *bau_desc, + struct bau_control *bcp, struct bau_control *hmaster, struct ptc_stats *stat) { udelay(bcp->plugged_delay); bcp->plugged_tries++; + if (bcp->plugged_tries >= bcp->plugsb4reset) { bcp->plugged_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); - uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu); + reset_with_ipi(&bau_desc->distribution, bcp->cpu); spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; stat->s_resets_plug++; } } -static void -destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp, - struct bau_control *hmaster, struct ptc_stats *stat) +static void destination_timeout(struct bau_desc *bau_desc, + struct bau_control *bcp, struct bau_control *hmaster, + struct ptc_stats *stat) { - hmaster->max_bau_concurrent = 1; + hmaster->max_concurr = 1; bcp->timeout_tries++; if (bcp->timeout_tries >= bcp->timeoutsb4reset) { bcp->timeout_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); - uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu); + reset_with_ipi(&bau_desc->distribution, bcp->cpu); spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; stat->s_resets_timeout++; } @@ -530,34 +640,104 @@ destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp, * Completions are taking a very long time due to a congested numalink * network. */ -static void -disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat) +static void disable_for_congestion(struct bau_control *bcp, + struct ptc_stats *stat) { - int tcpu; - struct bau_control *tbcp; - /* let only one cpu do this disabling */ spin_lock(&disable_lock); + if (!baudisabled && bcp->period_requests && ((bcp->period_time / bcp->period_requests) > congested_cycles)) { + int tcpu; + struct bau_control *tbcp; /* it becomes this cpu's job to turn on the use of the BAU again */ baudisabled = 1; bcp->set_bau_off = 1; - bcp->set_bau_on_time = get_cycles() + - sec_2_cycles(bcp->congested_period); + bcp->set_bau_on_time = get_cycles(); + bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period); stat->s_bau_disabled++; for_each_present_cpu(tcpu) { tbcp = &per_cpu(bau_control, tcpu); - tbcp->baudisabled = 1; + tbcp->baudisabled = 1; } } + spin_unlock(&disable_lock); } -/** - * uv_flush_send_and_wait - * +static void count_max_concurr(int stat, struct bau_control *bcp, + struct bau_control *hmaster) +{ + bcp->plugged_tries = 0; + bcp->timeout_tries = 0; + if (stat != FLUSH_COMPLETE) + return; + if (bcp->conseccompletes <= bcp->complete_threshold) + return; + if (hmaster->max_concurr >= hmaster->max_concurr_const) + return; + hmaster->max_concurr++; +} + +static void record_send_stats(cycles_t time1, cycles_t time2, + struct bau_control *bcp, struct ptc_stats *stat, + int completion_status, int try) +{ + cycles_t elapsed; + + if (time2 > time1) { + elapsed = time2 - time1; + stat->s_time += elapsed; + + if ((completion_status == FLUSH_COMPLETE) && (try == 1)) { + bcp->period_requests++; + bcp->period_time += elapsed; + if ((elapsed > congested_cycles) && + (bcp->period_requests > bcp->cong_reps)) + disable_for_congestion(bcp, stat); + } + } else + stat->s_requestor--; + + if (completion_status == FLUSH_COMPLETE && try > 1) + stat->s_retriesok++; + else if (completion_status == FLUSH_GIVEUP) + stat->s_giveup++; +} + +/* + * Because of a uv1 hardware bug only a limited number of concurrent + * requests can be made. + */ +static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat) +{ + spinlock_t *lock = &hmaster->uvhub_lock; + atomic_t *v; + + v = &hmaster->active_descriptor_count; + if (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr)) { + stat->s_throttles++; + do { + cpu_relax(); + } while (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr)); + } +} + +/* + * Handle the completion status of a message send. + */ +static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, + struct bau_control *bcp, struct bau_control *hmaster, + struct ptc_stats *stat) +{ + if (completion_status == FLUSH_RETRY_PLUGGED) + destination_plugged(bau_desc, bcp, hmaster, stat); + else if (completion_status == FLUSH_RETRY_TIMEOUT) + destination_timeout(bau_desc, bcp, hmaster, stat); +} + +/* * Send a broadcast and wait for it to complete. * * The flush_mask contains the cpus the broadcast is to be sent to including @@ -568,44 +748,23 @@ disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat) * returned to the kernel. */ int uv_flush_send_and_wait(struct bau_desc *bau_desc, - struct cpumask *flush_mask, struct bau_control *bcp) + struct cpumask *flush_mask, struct bau_control *bcp) { - int right_shift; - int completion_status = 0; int seq_number = 0; + int completion_stat = 0; long try = 0; - int cpu = bcp->uvhub_cpu; - int this_cpu = bcp->cpu; - unsigned long mmr_offset; unsigned long index; cycles_t time1; cycles_t time2; - cycles_t elapsed; struct ptc_stats *stat = bcp->statp; - struct bau_control *smaster = bcp->socket_master; struct bau_control *hmaster = bcp->uvhub_master; - if (!atomic_inc_unless_ge(&hmaster->uvhub_lock, - &hmaster->active_descriptor_count, - hmaster->max_bau_concurrent)) { - stat->s_throttles++; - do { - cpu_relax(); - } while (!atomic_inc_unless_ge(&hmaster->uvhub_lock, - &hmaster->active_descriptor_count, - hmaster->max_bau_concurrent)); - } + if (is_uv1_hub()) + uv1_throttle(hmaster, stat); + while (hmaster->uvhub_quiesce) cpu_relax(); - if (cpu < UV_CPUS_PER_ACT_STATUS) { - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; - right_shift = cpu * UV_ACT_STATUS_SIZE; - } else { - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - right_shift = - ((cpu - UV_CPUS_PER_ACT_STATUS) * UV_ACT_STATUS_SIZE); - } time1 = get_cycles(); do { if (try == 0) { @@ -615,64 +774,134 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, bau_desc->header.msg_type = MSG_RETRY; stat->s_retry_messages++; } + bau_desc->header.sequence = seq_number; - index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) | - bcp->uvhub_cpu; + index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; bcp->send_message = get_cycles(); - uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index); + + write_mmr_activation(index); + try++; - completion_status = uv_wait_completion(bau_desc, mmr_offset, - right_shift, this_cpu, bcp, smaster, try); + completion_stat = wait_completion(bau_desc, bcp, try); + + handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); - if (completion_status == FLUSH_RETRY_PLUGGED) { - destination_plugged(bau_desc, bcp, hmaster, stat); - } else if (completion_status == FLUSH_RETRY_TIMEOUT) { - destination_timeout(bau_desc, bcp, hmaster, stat); - } if (bcp->ipi_attempts >= bcp->ipi_reset_limit) { bcp->ipi_attempts = 0; - completion_status = FLUSH_GIVEUP; + completion_stat = FLUSH_GIVEUP; break; } cpu_relax(); - } while ((completion_status == FLUSH_RETRY_PLUGGED) || - (completion_status == FLUSH_RETRY_TIMEOUT)); + } while ((completion_stat == FLUSH_RETRY_PLUGGED) || + (completion_stat == FLUSH_RETRY_TIMEOUT)); + time2 = get_cycles(); - bcp->plugged_tries = 0; - bcp->timeout_tries = 0; - if ((completion_status == FLUSH_COMPLETE) && - (bcp->conseccompletes > bcp->complete_threshold) && - (hmaster->max_bau_concurrent < - hmaster->max_bau_concurrent_constant)) - hmaster->max_bau_concurrent++; + + count_max_concurr(completion_stat, bcp, hmaster); + while (hmaster->uvhub_quiesce) cpu_relax(); + atomic_dec(&hmaster->active_descriptor_count); - if (time2 > time1) { - elapsed = time2 - time1; - stat->s_time += elapsed; - if ((completion_status == FLUSH_COMPLETE) && (try == 1)) { - bcp->period_requests++; - bcp->period_time += elapsed; - if ((elapsed > congested_cycles) && - (bcp->period_requests > bcp->congested_reps)) { - disable_for_congestion(bcp, stat); + + record_send_stats(time1, time2, bcp, stat, completion_stat, try); + + if (completion_stat == FLUSH_GIVEUP) + return 1; + return 0; +} + +/* + * The BAU is disabled. When the disabled time period has expired, the cpu + * that disabled it must re-enable it. + * Return 0 if it is re-enabled for all cpus. + */ +static int check_enable(struct bau_control *bcp, struct ptc_stats *stat) +{ + int tcpu; + struct bau_control *tbcp; + + if (bcp->set_bau_off) { + if (get_cycles() >= bcp->set_bau_on_time) { + stat->s_bau_reenabled++; + baudisabled = 0; + for_each_present_cpu(tcpu) { + tbcp = &per_cpu(bau_control, tcpu); + tbcp->baudisabled = 0; + tbcp->period_requests = 0; + tbcp->period_time = 0; } + return 0; } + } + return -1; +} + +static void record_send_statistics(struct ptc_stats *stat, int locals, int hubs, + int remotes, struct bau_desc *bau_desc) +{ + stat->s_requestor++; + stat->s_ntargcpu += remotes + locals; + stat->s_ntargremotes += remotes; + stat->s_ntarglocals += locals; + + /* uvhub statistics */ + hubs = bau_uvhub_weight(&bau_desc->distribution); + if (locals) { + stat->s_ntarglocaluvhub++; + stat->s_ntargremoteuvhub += (hubs - 1); } else - stat->s_requestor--; - if (completion_status == FLUSH_COMPLETE && try > 1) - stat->s_retriesok++; - else if (completion_status == FLUSH_GIVEUP) { - stat->s_giveup++; - return 1; + stat->s_ntargremoteuvhub += hubs; + + stat->s_ntarguvhub += hubs; + + if (hubs >= 16) + stat->s_ntarguvhub16++; + else if (hubs >= 8) + stat->s_ntarguvhub8++; + else if (hubs >= 4) + stat->s_ntarguvhub4++; + else if (hubs >= 2) + stat->s_ntarguvhub2++; + else + stat->s_ntarguvhub1++; +} + +/* + * Translate a cpu mask to the uvhub distribution mask in the BAU + * activation descriptor. + */ +static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, + struct bau_desc *bau_desc, int *localsp, int *remotesp) +{ + int cpu; + int pnode; + int cnt = 0; + struct hub_and_pnode *hpp; + + for_each_cpu(cpu, flush_mask) { + /* + * The distribution vector is a bit map of pnodes, relative + * to the partition base pnode (and the partition base nasid + * in the header). + * Translate cpu to pnode and hub using a local memory array. + */ + hpp = &bcp->socket_master->thp[cpu]; + pnode = hpp->pnode - bcp->partition_base_pnode; + bau_uvhub_set(pnode, &bau_desc->distribution); + cnt++; + if (hpp->uvhub == bcp->uvhub) + (*localsp)++; + else + (*remotesp)++; } + if (!cnt) + return 1; return 0; } -/** - * uv_flush_tlb_others - globally purge translation cache of a virtual - * address or all TLB's +/* + * globally purge translation cache of a virtual address or all TLB's * @cpumask: mask of all cpu's in which the address is to be removed * @mm: mm_struct containing virtual address range * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu) @@ -696,20 +925,16 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, * done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long va, unsigned int cpu) + struct mm_struct *mm, unsigned long va, + unsigned int cpu) { int locals = 0; int remotes = 0; int hubs = 0; - int tcpu; - int tpnode; struct bau_desc *bau_desc; struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; - struct bau_control *tbcp; - struct hub_and_pnode *hpp; /* kernel was booted 'nobau' */ if (nobau) @@ -720,20 +945,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, /* bau was disabled due to slow response */ if (bcp->baudisabled) { - /* the cpu that disabled it must re-enable it */ - if (bcp->set_bau_off) { - if (get_cycles() >= bcp->set_bau_on_time) { - stat->s_bau_reenabled++; - baudisabled = 0; - for_each_present_cpu(tcpu) { - tbcp = &per_cpu(bau_control, tcpu); - tbcp->baudisabled = 0; - tbcp->period_requests = 0; - tbcp->period_time = 0; - } - } - } - return cpumask; + if (check_enable(bcp, stat)) + return cpumask; } /* @@ -744,59 +957,20 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, flush_mask = (struct cpumask *)per_cpu(uv_flush_tlb_mask, cpu); /* don't actually do a shootdown of the local cpu */ cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); + if (cpu_isset(cpu, *cpumask)) stat->s_ntargself++; bau_desc = bcp->descriptor_base; - bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu; + bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu; bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); - - for_each_cpu(tcpu, flush_mask) { - /* - * The distribution vector is a bit map of pnodes, relative - * to the partition base pnode (and the partition base nasid - * in the header). - * Translate cpu to pnode and hub using an array stored - * in local memory. - */ - hpp = &bcp->socket_master->target_hub_and_pnode[tcpu]; - tpnode = hpp->pnode - bcp->partition_base_pnode; - bau_uvhub_set(tpnode, &bau_desc->distribution); - if (hpp->uvhub == bcp->uvhub) - locals++; - else - remotes++; - } - if ((locals + remotes) == 0) + if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes)) return NULL; - stat->s_requestor++; - stat->s_ntargcpu += remotes + locals; - stat->s_ntargremotes += remotes; - stat->s_ntarglocals += locals; - remotes = bau_uvhub_weight(&bau_desc->distribution); - /* uvhub statistics */ - hubs = bau_uvhub_weight(&bau_desc->distribution); - if (locals) { - stat->s_ntarglocaluvhub++; - stat->s_ntargremoteuvhub += (hubs - 1); - } else - stat->s_ntargremoteuvhub += hubs; - stat->s_ntarguvhub += hubs; - if (hubs >= 16) - stat->s_ntarguvhub16++; - else if (hubs >= 8) - stat->s_ntarguvhub8++; - else if (hubs >= 4) - stat->s_ntarguvhub4++; - else if (hubs >= 2) - stat->s_ntarguvhub2++; - else - stat->s_ntarguvhub1++; + record_send_statistics(stat, locals, hubs, remotes, bau_desc); bau_desc->payload.address = va; bau_desc->payload.sending_cpu = cpu; - /* * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. @@ -825,26 +999,31 @@ void uv_bau_message_interrupt(struct pt_regs *regs) { int count = 0; cycles_t time_start; - struct bau_payload_queue_entry *msg; + struct bau_pq_entry *msg; struct bau_control *bcp; struct ptc_stats *stat; struct msg_desc msgdesc; time_start = get_cycles(); + bcp = &per_cpu(bau_control, smp_processor_id()); stat = bcp->statp; - msgdesc.va_queue_first = bcp->va_queue_first; - msgdesc.va_queue_last = bcp->va_queue_last; + + msgdesc.queue_first = bcp->queue_first; + msgdesc.queue_last = bcp->queue_last; + msg = bcp->bau_msg_head; - while (msg->sw_ack_vector) { + while (msg->swack_vec) { count++; - msgdesc.msg_slot = msg - msgdesc.va_queue_first; - msgdesc.sw_ack_slot = ffs(msg->sw_ack_vector) - 1; + + msgdesc.msg_slot = msg - msgdesc.queue_first; + msgdesc.swack_slot = ffs(msg->swack_vec) - 1; msgdesc.msg = msg; - uv_bau_process_message(&msgdesc, bcp); + bau_process_message(&msgdesc, bcp); + msg++; - if (msg > msgdesc.va_queue_last) - msg = msgdesc.va_queue_first; + if (msg > msgdesc.queue_last) + msg = msgdesc.queue_first; bcp->bau_msg_head = msg; } stat->d_time += (get_cycles() - time_start); @@ -852,18 +1031,17 @@ void uv_bau_message_interrupt(struct pt_regs *regs) stat->d_nomsg++; else if (count > 1) stat->d_multmsg++; + ack_APIC_irq(); } /* - * uv_enable_timeouts - * - * Each target uvhub (i.e. a uvhub that has no cpu's) needs to have + * Each target uvhub (i.e. a uvhub that has cpu's) needs to have * shootdown message timeouts enabled. The timeout does not cause * an interrupt, but causes an error message to be returned to * the sender. */ -static void __init uv_enable_timeouts(void) +static void __init enable_timeouts(void) { int uvhub; int nuvhubs; @@ -877,47 +1055,44 @@ static void __init uv_enable_timeouts(void) continue; pnode = uv_blade_to_pnode(uvhub); - mmr_image = - uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL); + mmr_image = read_mmr_misc_control(pnode); /* * Set the timeout period and then lock it in, in three * steps; captures and locks in the period. * * To program the period, the SOFT_ACK_MODE must be off. */ - mmr_image &= ~((unsigned long)1 << - UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT); - uv_write_global_mmr64 - (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + mmr_image &= ~(1L << SOFTACK_MSHIFT); + write_mmr_misc_control(pnode, mmr_image); /* * Set the 4-bit period. */ - mmr_image &= ~((unsigned long)0xf << - UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT); - mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD << - UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT); - uv_write_global_mmr64 - (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + mmr_image &= ~((unsigned long)0xf << SOFTACK_PSHIFT); + mmr_image |= (SOFTACK_TIMEOUT_PERIOD << SOFTACK_PSHIFT); + write_mmr_misc_control(pnode, mmr_image); /* + * UV1: * Subsequent reversals of the timebase bit (3) cause an * immediate timeout of one or all INTD resources as * indicated in bits 2:0 (7 causes all of them to timeout). */ - mmr_image |= ((unsigned long)1 << - UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT); - uv_write_global_mmr64 - (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + mmr_image |= (1L << SOFTACK_MSHIFT); + if (is_uv2_hub()) { + mmr_image |= (1L << UV2_LEG_SHFT); + mmr_image |= (1L << UV2_EXT_SHFT); + } + write_mmr_misc_control(pnode, mmr_image); } } -static void *uv_ptc_seq_start(struct seq_file *file, loff_t *offset) +static void *ptc_seq_start(struct seq_file *file, loff_t *offset) { if (*offset < num_possible_cpus()) return offset; return NULL; } -static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset) +static void *ptc_seq_next(struct seq_file *file, void *data, loff_t *offset) { (*offset)++; if (*offset < num_possible_cpus()) @@ -925,12 +1100,11 @@ static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset) return NULL; } -static void uv_ptc_seq_stop(struct seq_file *file, void *data) +static void ptc_seq_stop(struct seq_file *file, void *data) { } -static inline unsigned long long -microsec_2_cycles(unsigned long microsec) +static inline unsigned long long usec_2_cycles(unsigned long microsec) { unsigned long ns; unsigned long long cyc; @@ -941,29 +1115,27 @@ microsec_2_cycles(unsigned long microsec) } /* - * Display the statistics thru /proc. + * Display the statistics thru /proc/sgi_uv/ptc_statistics * 'data' points to the cpu number + * Note: see the descriptions in stat_description[]. */ -static int uv_ptc_seq_show(struct seq_file *file, void *data) +static int ptc_seq_show(struct seq_file *file, void *data) { struct ptc_stats *stat; int cpu; cpu = *(loff_t *)data; - if (!cpu) { seq_printf(file, "# cpu sent stime self locals remotes ncpus localhub "); seq_printf(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto "); - seq_printf(file, - "retries rok resetp resett giveup sto bz throt "); + "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok "); seq_printf(file, - "sw_ack recv rtime all "); + "resetp resett giveup sto bz throt swack recv rtime "); seq_printf(file, - "one mult none retry canc nocan reset rcan "); + "all one mult none retry canc nocan reset rcan "); seq_printf(file, "disable enable\n"); } @@ -990,8 +1162,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) /* destination side statistics */ seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", - uv_read_global_mmr64(uv_cpu_to_pnode(cpu), - UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), + read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)), stat->d_requestee, cycles_2_us(stat->d_time), stat->d_alltlb, stat->d_onetlb, stat->d_multmsg, stat->d_nomsg, stat->d_retries, stat->d_canceled, @@ -1000,7 +1171,6 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) seq_printf(file, "%ld %ld\n", stat->s_bau_disabled, stat->s_bau_reenabled); } - return 0; } @@ -1008,18 +1178,18 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) * Display the tunables thru debugfs */ static ssize_t tunables_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos) { char *buf; int ret; buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n", - "max_bau_concurrent plugged_delay plugsb4reset", + "max_concur plugged_delay plugsb4reset", "timeoutsb4reset ipi_reset_limit complete_threshold", "congested_response_us congested_reps congested_period", - max_bau_concurrent, plugged_delay, plugsb4reset, + max_concurr, plugged_delay, plugsb4reset, timeoutsb4reset, ipi_reset_limit, complete_threshold, - congested_response_us, congested_reps, congested_period); + congested_respns_us, congested_reps, congested_period); if (!buf) return -ENOMEM; @@ -1030,13 +1200,16 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf, } /* - * -1: resetf the statistics + * handle a write to /proc/sgi_uv/ptc_statistics + * -1: reset the statistics * 0: display meaning of the statistics */ -static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, - size_t count, loff_t *data) +static ssize_t ptc_proc_write(struct file *file, const char __user *user, + size_t count, loff_t *data) { int cpu; + int i; + int elements; long input_arg; char optstr[64]; struct ptc_stats *stat; @@ -1046,79 +1219,18 @@ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, if (copy_from_user(optstr, user, count)) return -EFAULT; optstr[count - 1] = '\0'; + if (strict_strtol(optstr, 10, &input_arg) < 0) { printk(KERN_DEBUG "%s is invalid\n", optstr); return -EINVAL; } if (input_arg == 0) { + elements = sizeof(stat_description)/sizeof(*stat_description); printk(KERN_DEBUG "# cpu: cpu number\n"); printk(KERN_DEBUG "Sender statistics:\n"); - printk(KERN_DEBUG - "sent: number of shootdown messages sent\n"); - printk(KERN_DEBUG - "stime: time spent sending messages\n"); - printk(KERN_DEBUG - "numuvhubs: number of hubs targeted with shootdown\n"); - printk(KERN_DEBUG - "numuvhubs16: number times 16 or more hubs targeted\n"); - printk(KERN_DEBUG - "numuvhubs8: number times 8 or more hubs targeted\n"); - printk(KERN_DEBUG - "numuvhubs4: number times 4 or more hubs targeted\n"); - printk(KERN_DEBUG - "numuvhubs2: number times 2 or more hubs targeted\n"); - printk(KERN_DEBUG - "numuvhubs1: number times 1 hub targeted\n"); - printk(KERN_DEBUG - "numcpus: number of cpus targeted with shootdown\n"); - printk(KERN_DEBUG - "dto: number of destination timeouts\n"); - printk(KERN_DEBUG - "retries: destination timeout retries sent\n"); - printk(KERN_DEBUG - "rok: : destination timeouts successfully retried\n"); - printk(KERN_DEBUG - "resetp: ipi-style resource resets for plugs\n"); - printk(KERN_DEBUG - "resett: ipi-style resource resets for timeouts\n"); - printk(KERN_DEBUG - "giveup: fall-backs to ipi-style shootdowns\n"); - printk(KERN_DEBUG - "sto: number of source timeouts\n"); - printk(KERN_DEBUG - "bz: number of stay-busy's\n"); - printk(KERN_DEBUG - "throt: number times spun in throttle\n"); - printk(KERN_DEBUG "Destination side statistics:\n"); - printk(KERN_DEBUG - "sw_ack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n"); - printk(KERN_DEBUG - "recv: shootdown messages received\n"); - printk(KERN_DEBUG - "rtime: time spent processing messages\n"); - printk(KERN_DEBUG - "all: shootdown all-tlb messages\n"); - printk(KERN_DEBUG - "one: shootdown one-tlb messages\n"); - printk(KERN_DEBUG - "mult: interrupts that found multiple messages\n"); - printk(KERN_DEBUG - "none: interrupts that found no messages\n"); - printk(KERN_DEBUG - "retry: number of retry messages processed\n"); - printk(KERN_DEBUG - "canc: number messages canceled by retries\n"); - printk(KERN_DEBUG - "nocan: number retries that found nothing to cancel\n"); - printk(KERN_DEBUG - "reset: number of ipi-style reset requests processed\n"); - printk(KERN_DEBUG - "rcan: number messages canceled by reset requests\n"); - printk(KERN_DEBUG - "disable: number times use of the BAU was disabled\n"); - printk(KERN_DEBUG - "enable: number times use of the BAU was re-enabled\n"); + for (i = 0; i < elements; i++) + printk(KERN_DEBUG "%s\n", stat_description[i]); } else if (input_arg == -1) { for_each_present_cpu(cpu) { stat = &per_cpu(ptcstats, cpu); @@ -1145,27 +1257,18 @@ static int local_atoi(const char *name) } /* - * set the tunables - * 0 values reset them to defaults + * Parse the values written to /sys/kernel/debug/sgi_uv/bau_tunables. + * Zero values reset them to defaults. */ -static ssize_t tunables_write(struct file *file, const char __user *user, - size_t count, loff_t *data) +static int parse_tunables_write(struct bau_control *bcp, char *instr, + int count) { - int cpu; - int cnt = 0; - int val; char *p; char *q; - char instr[64]; - struct bau_control *bcp; - - if (count == 0 || count > sizeof(instr)-1) - return -EINVAL; - if (copy_from_user(instr, user, count)) - return -EFAULT; + int cnt = 0; + int val; + int e = sizeof(tunables) / sizeof(*tunables); - instr[count] = '\0'; - /* count the fields */ p = instr + strspn(instr, WHITESPACE); q = p; for (; *p; p = q + strspn(q, WHITESPACE)) { @@ -1174,8 +1277,8 @@ static ssize_t tunables_write(struct file *file, const char __user *user, if (q == p) break; } - if (cnt != 9) { - printk(KERN_INFO "bau tunable error: should be 9 numbers\n"); + if (cnt != e) { + printk(KERN_INFO "bau tunable error: should be %d values\n", e); return -EINVAL; } @@ -1187,97 +1290,80 @@ static ssize_t tunables_write(struct file *file, const char __user *user, switch (cnt) { case 0: if (val == 0) { - max_bau_concurrent = MAX_BAU_CONCURRENT; - max_bau_concurrent_constant = - MAX_BAU_CONCURRENT; + max_concurr = MAX_BAU_CONCURRENT; + max_concurr_const = MAX_BAU_CONCURRENT; continue; } - bcp = &per_cpu(bau_control, smp_processor_id()); if (val < 1 || val > bcp->cpus_in_uvhub) { printk(KERN_DEBUG "Error: BAU max concurrent %d is invalid\n", val); return -EINVAL; } - max_bau_concurrent = val; - max_bau_concurrent_constant = val; - continue; - case 1: - if (val == 0) - plugged_delay = PLUGGED_DELAY; - else - plugged_delay = val; - continue; - case 2: - if (val == 0) - plugsb4reset = PLUGSB4RESET; - else - plugsb4reset = val; - continue; - case 3: - if (val == 0) - timeoutsb4reset = TIMEOUTSB4RESET; - else - timeoutsb4reset = val; - continue; - case 4: - if (val == 0) - ipi_reset_limit = IPI_RESET_LIMIT; - else - ipi_reset_limit = val; - continue; - case 5: - if (val == 0) - complete_threshold = COMPLETE_THRESHOLD; - else - complete_threshold = val; - continue; - case 6: - if (val == 0) - congested_response_us = CONGESTED_RESPONSE_US; - else - congested_response_us = val; - continue; - case 7: - if (val == 0) - congested_reps = CONGESTED_REPS; - else - congested_reps = val; + max_concurr = val; + max_concurr_const = val; continue; - case 8: + default: if (val == 0) - congested_period = CONGESTED_PERIOD; + *tunables[cnt].tunp = tunables[cnt].deflt; else - congested_period = val; + *tunables[cnt].tunp = val; continue; } if (q == p) break; } + return 0; +} + +/* + * Handle a write to debugfs. (/sys/kernel/debug/sgi_uv/bau_tunables) + */ +static ssize_t tunables_write(struct file *file, const char __user *user, + size_t count, loff_t *data) +{ + int cpu; + int ret; + char instr[100]; + struct bau_control *bcp; + + if (count == 0 || count > sizeof(instr)-1) + return -EINVAL; + if (copy_from_user(instr, user, count)) + return -EFAULT; + + instr[count] = '\0'; + + bcp = &per_cpu(bau_control, smp_processor_id()); + + ret = parse_tunables_write(bcp, instr, count); + if (ret) + return ret; + for_each_present_cpu(cpu) { bcp = &per_cpu(bau_control, cpu); - bcp->max_bau_concurrent = max_bau_concurrent; - bcp->max_bau_concurrent_constant = max_bau_concurrent; - bcp->plugged_delay = plugged_delay; - bcp->plugsb4reset = plugsb4reset; - bcp->timeoutsb4reset = timeoutsb4reset; - bcp->ipi_reset_limit = ipi_reset_limit; - bcp->complete_threshold = complete_threshold; - bcp->congested_response_us = congested_response_us; - bcp->congested_reps = congested_reps; - bcp->congested_period = congested_period; + bcp->max_concurr = max_concurr; + bcp->max_concurr_const = max_concurr; + bcp->plugged_delay = plugged_delay; + bcp->plugsb4reset = plugsb4reset; + bcp->timeoutsb4reset = timeoutsb4reset; + bcp->ipi_reset_limit = ipi_reset_limit; + bcp->complete_threshold = complete_threshold; + bcp->cong_response_us = congested_respns_us; + bcp->cong_reps = congested_reps; + bcp->cong_period = congested_period; } return count; } static const struct seq_operations uv_ptc_seq_ops = { - .start = uv_ptc_seq_start, - .next = uv_ptc_seq_next, - .stop = uv_ptc_seq_stop, - .show = uv_ptc_seq_show + .start = ptc_seq_start, + .next = ptc_seq_next, + .stop = ptc_seq_stop, + .show = ptc_seq_show }; -static int uv_ptc_proc_open(struct inode *inode, struct file *file) +static int ptc_proc_open(struct inode *inode, struct file *file) { return seq_open(file, &uv_ptc_seq_ops); } @@ -1288,9 +1374,9 @@ static int tunables_open(struct inode *inode, struct file *file) } static const struct file_operations proc_uv_ptc_operations = { - .open = uv_ptc_proc_open, + .open = ptc_proc_open, .read = seq_read, - .write = uv_ptc_proc_write, + .write = ptc_proc_write, .llseek = seq_lseek, .release = seq_release, }; @@ -1324,7 +1410,7 @@ static int __init uv_ptc_init(void) return -EINVAL; } tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600, - tunables_dir, NULL, &tunables_fops); + tunables_dir, NULL, &tunables_fops); if (!tunables_file) { printk(KERN_ERR "unable to create debugfs file %s\n", UV_BAU_TUNABLES_FILE); @@ -1336,24 +1422,24 @@ static int __init uv_ptc_init(void) /* * Initialize the sending side's sending buffers. */ -static void -uv_activation_descriptor_init(int node, int pnode, int base_pnode) +static void activation_descriptor_init(int node, int pnode, int base_pnode) { int i; int cpu; unsigned long pa; unsigned long m; unsigned long n; + size_t dsize; struct bau_desc *bau_desc; struct bau_desc *bd2; struct bau_control *bcp; /* - * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR) - * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE) + * each bau_desc is 64 bytes; there are 8 (ITEMS_PER_DESC) + * per cpu; and one per cpu on the uvhub (ADP_SZ) */ - bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE - * UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node); + dsize = sizeof(struct bau_desc) * ADP_SZ * ITEMS_PER_DESC; + bau_desc = kmalloc_node(dsize, GFP_KERNEL, node); BUG_ON(!bau_desc); pa = uv_gpa(bau_desc); /* need the real nasid*/ @@ -1361,27 +1447,25 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode) m = pa & uv_mmask; /* the 14-bit pnode */ - uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, - (n << UV_DESC_BASE_PNODE_SHIFT | m)); + write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m)); /* - * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each + * Initializing all 8 (ITEMS_PER_DESC) descriptors for each * cpu even though we only use the first one; one descriptor can * describe a broadcast to 256 uv hubs. */ - for (i = 0, bd2 = bau_desc; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR); - i++, bd2++) { + for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) { memset(bd2, 0, sizeof(struct bau_desc)); - bd2->header.sw_ack_flag = 1; + bd2->header.swack_flag = 1; /* * The base_dest_nasid set in the message header is the nasid * of the first uvhub in the partition. The bit map will * indicate destination pnode numbers relative to that base. * They may not be consecutive if nasid striding is being used. */ - bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); - bd2->header.dest_subnodeid = UV_LB_SUBNODEID; - bd2->header.command = UV_NET_ENDPOINT_INTD; - bd2->header.int_both = 1; + bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); + bd2->header.dest_subnodeid = UV_LB_SUBNODEID; + bd2->header.command = UV_NET_ENDPOINT_INTD; + bd2->header.int_both = 1; /* * all others need to be set to zero: * fairness chaining multilevel count replied_to @@ -1401,57 +1485,55 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode) * - node is first node (kernel memory notion) on the uvhub * - pnode is the uvhub's physical identifier */ -static void -uv_payload_queue_init(int node, int pnode) +static void pq_init(int node, int pnode) { - int pn; int cpu; + size_t plsize; char *cp; - unsigned long pa; - struct bau_payload_queue_entry *pqp; - struct bau_payload_queue_entry *pqp_malloc; + void *vp; + unsigned long pn; + unsigned long first; + unsigned long pn_first; + unsigned long last; + struct bau_pq_entry *pqp; struct bau_control *bcp; - pqp = kmalloc_node((DEST_Q_SIZE + 1) - * sizeof(struct bau_payload_queue_entry), - GFP_KERNEL, node); + plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry); + vp = kmalloc_node(plsize, GFP_KERNEL, node); + pqp = (struct bau_pq_entry *)vp; BUG_ON(!pqp); - pqp_malloc = pqp; cp = (char *)pqp + 31; - pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); + pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5); for_each_present_cpu(cpu) { if (pnode != uv_cpu_to_pnode(cpu)) continue; /* for every cpu on this pnode: */ bcp = &per_cpu(bau_control, cpu); - bcp->va_queue_first = pqp; - bcp->bau_msg_head = pqp; - bcp->va_queue_last = pqp + (DEST_Q_SIZE - 1); + bcp->queue_first = pqp; + bcp->bau_msg_head = pqp; + bcp->queue_last = pqp + (DEST_Q_SIZE - 1); } /* * need the pnode of where the memory was really allocated */ - pa = uv_gpa(pqp); - pn = pa >> uv_nshift; - uv_write_global_mmr64(pnode, - UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, - ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | - uv_physnodeaddr(pqp)); - uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, - uv_physnodeaddr(pqp)); - uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, - (unsigned long) - uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1))); + pn = uv_gpa(pqp) >> uv_nshift; + first = uv_physnodeaddr(pqp); + pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first; + last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1)); + write_mmr_payload_first(pnode, pn_first); + write_mmr_payload_tail(pnode, first); + write_mmr_payload_last(pnode, last); + /* in effect, all msg_type's are set to MSG_NOOP */ - memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * DEST_Q_SIZE); + memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); } /* * Initialization of each UV hub's structures */ -static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode) +static void __init init_uvhub(int uvhub, int vector, int base_pnode) { int node; int pnode; @@ -1459,24 +1541,24 @@ static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode) node = uvhub_to_first_node(uvhub); pnode = uv_blade_to_pnode(uvhub); - uv_activation_descriptor_init(node, pnode, base_pnode); - uv_payload_queue_init(node, pnode); + + activation_descriptor_init(node, pnode, base_pnode); + + pq_init(node, pnode); /* * The below initialization can't be in firmware because the * messaging IRQ will be determined by the OS. */ apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits; - uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, - ((apicid << 32) | vector)); + write_mmr_data_config(pnode, ((apicid << 32) | vector)); } /* * We will set BAU_MISC_CONTROL with a timeout period. * But the BIOS has set UVH_AGING_PRESCALE_SEL and UVH_TRANSACTION_TIMEOUT. - * So the destination timeout period has be be calculated from them. + * So the destination timeout period has to be calculated from them. */ -static int -calculate_destination_timeout(void) +static int calculate_destination_timeout(void) { unsigned long mmr_image; int mult1; @@ -1486,73 +1568,92 @@ calculate_destination_timeout(void) int ret; unsigned long ts_ns; - mult1 = UV_INTD_SOFT_ACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK; - mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); - index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK; - mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT); - mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK; - base = timeout_base_ns[index]; - ts_ns = base * mult1 * mult2; - ret = ts_ns / 1000; + if (is_uv1_hub()) { + mult1 = SOFTACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK; + mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK; + mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT); + mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK; + base = timeout_base_ns[index]; + ts_ns = base * mult1 * mult2; + ret = ts_ns / 1000; + } else { + /* 4 bits 0/1 for 10/80us, 3 bits of multiplier */ + mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT; + if (mmr_image & (1L << UV2_ACK_UNITS_SHFT)) + mult1 = 80; + else + mult1 = 10; + base = mmr_image & UV2_ACK_MASK; + ret = mult1 * base; + } return ret; } +static void __init init_per_cpu_tunables(void) +{ + int cpu; + struct bau_control *bcp; + + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->baudisabled = 0; + bcp->statp = &per_cpu(ptcstats, cpu); + /* time interval to catch a hardware stay-busy bug */ + bcp->timeout_interval = usec_2_cycles(2*timeout_us); + bcp->max_concurr = max_concurr; + bcp->max_concurr_const = max_concurr; + bcp->plugged_delay = plugged_delay; + bcp->plugsb4reset = plugsb4reset; + bcp->timeoutsb4reset = timeoutsb4reset; + bcp->ipi_reset_limit = ipi_reset_limit; + bcp->complete_threshold = complete_threshold; + bcp->cong_response_us = congested_respns_us; + bcp->cong_reps = congested_reps; + bcp->cong_period = congested_period; + } +} + /* - * initialize the bau_control structure for each cpu + * Scan all cpus to collect blade and socket summaries. */ -static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode) +static int __init get_cpu_topology(int base_pnode, + struct uvhub_desc *uvhub_descs, + unsigned char *uvhub_mask) { - int i; int cpu; - int tcpu; int pnode; int uvhub; - int have_hmaster; - short socket = 0; - unsigned short socket_mask; - unsigned char *uvhub_mask; + int socket; struct bau_control *bcp; struct uvhub_desc *bdp; struct socket_desc *sdp; - struct bau_control *hmaster = NULL; - struct bau_control *smaster = NULL; - struct socket_desc { - short num_cpus; - short cpu_number[MAX_CPUS_PER_SOCKET]; - }; - struct uvhub_desc { - unsigned short socket_mask; - short num_cpus; - short uvhub; - short pnode; - struct socket_desc socket[2]; - }; - struct uvhub_desc *uvhub_descs; - - timeout_us = calculate_destination_timeout(); - uvhub_descs = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL); - memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc)); - uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL); for_each_present_cpu(cpu) { bcp = &per_cpu(bau_control, cpu); + memset(bcp, 0, sizeof(struct bau_control)); + pnode = uv_cpu_hub_info(cpu)->pnode; - if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) { + if ((pnode - base_pnode) >= UV_DISTRIBUTION_SIZE) { printk(KERN_EMERG "cpu %d pnode %d-%d beyond %d; BAU disabled\n", - cpu, pnode, base_part_pnode, - UV_DISTRIBUTION_SIZE); + cpu, pnode, base_pnode, UV_DISTRIBUTION_SIZE); return 1; } + bcp->osnode = cpu_to_node(cpu); - bcp->partition_base_pnode = uv_partition_base_pnode; + bcp->partition_base_pnode = base_pnode; + uvhub = uv_cpu_hub_info(cpu)->numa_blade_id; *(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8)); bdp = &uvhub_descs[uvhub]; + bdp->num_cpus++; bdp->uvhub = uvhub; bdp->pnode = pnode; + /* kludge: 'assuming' one node per socket, and assuming that disabling a socket just leaves a gap in node numbers */ socket = bcp->osnode & 1; @@ -1561,84 +1662,129 @@ static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode) sdp->cpu_number[sdp->num_cpus] = cpu; sdp->num_cpus++; if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) { - printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus); + printk(KERN_EMERG "%d cpus per socket invalid\n", + sdp->num_cpus); return 1; } } + return 0; +} + +/* + * Each socket is to get a local array of pnodes/hubs. + */ +static void make_per_cpu_thp(struct bau_control *smaster) +{ + int cpu; + size_t hpsz = sizeof(struct hub_and_pnode) * num_possible_cpus(); + + smaster->thp = kmalloc_node(hpsz, GFP_KERNEL, smaster->osnode); + memset(smaster->thp, 0, hpsz); + for_each_present_cpu(cpu) { + smaster->thp[cpu].pnode = uv_cpu_hub_info(cpu)->pnode; + smaster->thp[cpu].uvhub = uv_cpu_hub_info(cpu)->numa_blade_id; + } +} + +/* + * Initialize all the per_cpu information for the cpu's on a given socket, + * given what has been gathered into the socket_desc struct. + * And reports the chosen hub and socket masters back to the caller. + */ +static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, + struct bau_control **smasterp, + struct bau_control **hmasterp) +{ + int i; + int cpu; + struct bau_control *bcp; + + for (i = 0; i < sdp->num_cpus; i++) { + cpu = sdp->cpu_number[i]; + bcp = &per_cpu(bau_control, cpu); + bcp->cpu = cpu; + if (i == 0) { + *smasterp = bcp; + if (!(*hmasterp)) + *hmasterp = bcp; + } + bcp->cpus_in_uvhub = bdp->num_cpus; + bcp->cpus_in_socket = sdp->num_cpus; + bcp->socket_master = *smasterp; + bcp->uvhub = bdp->uvhub; + bcp->uvhub_master = *hmasterp; + bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id; + if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { + printk(KERN_EMERG "%d cpus per uvhub invalid\n", + bcp->uvhub_cpu); + return 1; + } + } + return 0; +} + +/* + * Summarize the blade and socket topology into the per_cpu structures. + */ +static int __init summarize_uvhub_sockets(int nuvhubs, + struct uvhub_desc *uvhub_descs, + unsigned char *uvhub_mask) +{ + int socket; + int uvhub; + unsigned short socket_mask; + for (uvhub = 0; uvhub < nuvhubs; uvhub++) { + struct uvhub_desc *bdp; + struct bau_control *smaster = NULL; + struct bau_control *hmaster = NULL; + if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8)))) continue; - have_hmaster = 0; + bdp = &uvhub_descs[uvhub]; socket_mask = bdp->socket_mask; socket = 0; while (socket_mask) { - if (!(socket_mask & 1)) - goto nextsocket; - sdp = &bdp->socket[socket]; - for (i = 0; i < sdp->num_cpus; i++) { - cpu = sdp->cpu_number[i]; - bcp = &per_cpu(bau_control, cpu); - bcp->cpu = cpu; - if (i == 0) { - smaster = bcp; - if (!have_hmaster) { - have_hmaster++; - hmaster = bcp; - } - } - bcp->cpus_in_uvhub = bdp->num_cpus; - bcp->cpus_in_socket = sdp->num_cpus; - bcp->socket_master = smaster; - bcp->uvhub = bdp->uvhub; - bcp->uvhub_master = hmaster; - bcp->uvhub_cpu = uv_cpu_hub_info(cpu)-> - blade_processor_id; - if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { - printk(KERN_EMERG - "%d cpus per uvhub invalid\n", - bcp->uvhub_cpu); + struct socket_desc *sdp; + if ((socket_mask & 1)) { + sdp = &bdp->socket[socket]; + if (scan_sock(sdp, bdp, &smaster, &hmaster)) return 1; - } } -nextsocket: socket++; socket_mask = (socket_mask >> 1); - /* each socket gets a local array of pnodes/hubs */ - bcp = smaster; - bcp->target_hub_and_pnode = kmalloc_node( - sizeof(struct hub_and_pnode) * - num_possible_cpus(), GFP_KERNEL, bcp->osnode); - memset(bcp->target_hub_and_pnode, 0, - sizeof(struct hub_and_pnode) * - num_possible_cpus()); - for_each_present_cpu(tcpu) { - bcp->target_hub_and_pnode[tcpu].pnode = - uv_cpu_hub_info(tcpu)->pnode; - bcp->target_hub_and_pnode[tcpu].uvhub = - uv_cpu_hub_info(tcpu)->numa_blade_id; - } + make_per_cpu_thp(smaster); } } + return 0; +} + +/* + * initialize the bau_control structure for each cpu + */ +static int __init init_per_cpu(int nuvhubs, int base_part_pnode) +{ + unsigned char *uvhub_mask; + void *vp; + struct uvhub_desc *uvhub_descs; + + timeout_us = calculate_destination_timeout(); + + vp = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL); + uvhub_descs = (struct uvhub_desc *)vp; + memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc)); + uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL); + + if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask)) + return 1; + + if (summarize_uvhub_sockets(nuvhubs, uvhub_descs, uvhub_mask)) + return 1; + kfree(uvhub_descs); kfree(uvhub_mask); - for_each_present_cpu(cpu) { - bcp = &per_cpu(bau_control, cpu); - bcp->baudisabled = 0; - bcp->statp = &per_cpu(ptcstats, cpu); - /* time interval to catch a hardware stay-busy bug */ - bcp->timeout_interval = microsec_2_cycles(2*timeout_us); - bcp->max_bau_concurrent = max_bau_concurrent; - bcp->max_bau_concurrent_constant = max_bau_concurrent; - bcp->plugged_delay = plugged_delay; - bcp->plugsb4reset = plugsb4reset; - bcp->timeoutsb4reset = timeoutsb4reset; - bcp->ipi_reset_limit = ipi_reset_limit; - bcp->complete_threshold = complete_threshold; - bcp->congested_response_us = congested_response_us; - bcp->congested_reps = congested_reps; - bcp->congested_period = congested_period; - } + init_per_cpu_tunables(); return 0; } @@ -1651,8 +1797,9 @@ static int __init uv_bau_init(void) int pnode; int nuvhubs; int cur_cpu; + int cpus; int vector; - unsigned long mmr; + cpumask_var_t *mask; if (!is_uv_system()) return 0; @@ -1660,24 +1807,25 @@ static int __init uv_bau_init(void) if (nobau) return 0; - for_each_possible_cpu(cur_cpu) - zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), - GFP_KERNEL, cpu_to_node(cur_cpu)); + for_each_possible_cpu(cur_cpu) { + mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); + zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); + } uv_nshift = uv_hub_info->m_val; uv_mmask = (1UL << uv_hub_info->m_val) - 1; nuvhubs = uv_num_possible_blades(); spin_lock_init(&disable_lock); - congested_cycles = microsec_2_cycles(congested_response_us); + congested_cycles = usec_2_cycles(congested_respns_us); - uv_partition_base_pnode = 0x7fffffff; + uv_base_pnode = 0x7fffffff; for (uvhub = 0; uvhub < nuvhubs; uvhub++) { - if (uv_blade_nr_possible_cpus(uvhub) && - (uv_blade_to_pnode(uvhub) < uv_partition_base_pnode)) - uv_partition_base_pnode = uv_blade_to_pnode(uvhub); + cpus = uv_blade_nr_possible_cpus(uvhub); + if (cpus && (uv_blade_to_pnode(uvhub) < uv_base_pnode)) + uv_base_pnode = uv_blade_to_pnode(uvhub); } - if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) { + if (init_per_cpu(nuvhubs, uv_base_pnode)) { nobau = 1; return 0; } @@ -1685,21 +1833,21 @@ static int __init uv_bau_init(void) vector = UV_BAU_MESSAGE; for_each_possible_blade(uvhub) if (uv_blade_nr_possible_cpus(uvhub)) - uv_init_uvhub(uvhub, vector, uv_partition_base_pnode); + init_uvhub(uvhub, vector, uv_base_pnode); - uv_enable_timeouts(); + enable_timeouts(); alloc_intr_gate(vector, uv_bau_message_intr1); for_each_possible_blade(uvhub) { if (uv_blade_nr_possible_cpus(uvhub)) { + unsigned long val; + unsigned long mmr; pnode = uv_blade_to_pnode(uvhub); /* INIT the bau */ - uv_write_global_mmr64(pnode, - UVH_LB_BAU_SB_ACTIVATION_CONTROL, - ((unsigned long)1 << 63)); + val = 1L << 63; + write_gmmr_activation(pnode, val); mmr = 1; /* should be 1 to broadcast to both sockets */ - uv_write_global_mmr64(pnode, UVH_BAU_DATA_BROADCAST, - mmr); + write_mmr_data_broadcast(pnode, mmr); } } diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 0eb9018..9f29a01 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -99,8 +99,12 @@ static void uv_rtc_send_IPI(int cpu) /* Check for an RTC interrupt pending */ static int uv_intr_pending(int pnode) { - return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) & - UVH_EVENT_OCCURRED0_RTC1_MASK; + if (is_uv1_hub()) + return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) & + UV1H_EVENT_OCCURRED0_RTC1_MASK; + else + return uv_read_global_mmr64(pnode, UV2H_EVENT_OCCURRED2) & + UV2H_EVENT_OCCURRED2_RTC_1_MASK; } /* Setup interrupt and return non-zero if early expiration occurred. */ @@ -114,8 +118,12 @@ static int uv_setup_intr(int cpu, u64 expires) UVH_RTC1_INT_CONFIG_M_MASK); uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L); - uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, - UVH_EVENT_OCCURRED0_RTC1_MASK); + if (is_uv1_hub()) + uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, + UV1H_EVENT_OCCURRED0_RTC1_MASK); + else + uv_write_global_mmr64(pnode, UV2H_EVENT_OCCURRED2_ALIAS, + UV2H_EVENT_OCCURRED2_RTC_1_MASK); val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | ((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 17c565d..a6575b9 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -18,5 +18,5 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o - +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index dd7b88f..5325742 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1033,6 +1033,13 @@ static void xen_machine_halt(void) xen_reboot(SHUTDOWN_poweroff); } +static void xen_machine_power_off(void) +{ + if (pm_power_off) + pm_power_off(); + xen_reboot(SHUTDOWN_poweroff); +} + static void xen_crash_shutdown(struct pt_regs *regs) { xen_reboot(SHUTDOWN_crash); @@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void) static const struct machine_ops xen_machine_ops __initconst = { .restart = xen_restart, .halt = xen_machine_halt, - .power_off = xen_machine_halt, + .power_off = xen_machine_power_off, .shutdown = xen_machine_halt, .crash_shutdown = xen_crash_shutdown, .emergency_restart = xen_emergency_restart, @@ -1241,6 +1248,14 @@ asmlinkage void __init xen_start_kernel(void) if (pci_xen) x86_init.pci.arch_init = pci_xen_init; } else { + const struct dom0_vga_console_info *info = + (void *)((char *)xen_start_info + + xen_start_info->console.dom0.info_off); + + xen_init_vga(info, xen_start_info->console.dom0.info_size); + xen_start_info->console.domU.mfn = 0; + xen_start_info->console.domU.evtchn = 0; + /* Make sure ACS will be enabled */ pci_request_acs(); } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dc708dc..0ccccb6 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -59,6 +59,7 @@ #include <asm/page.h> #include <asm/init.h> #include <asm/pat.h> +#include <asm/smp.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -1231,7 +1232,11 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; +#ifdef CONFIG_SMP + DECLARE_BITMAP(mask, num_processors); +#else DECLARE_BITMAP(mask, NR_CPUS); +#endif } *args; struct multicall_space mcs; @@ -1599,6 +1604,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; +#ifdef CONFIG_X86_32 + if (pfn > max_pfn_mapped) + max_pfn_mapped = pfn; +#endif + if (!pte_none(pte_page[pteidx])) continue; @@ -1766,7 +1776,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 8bff7e7..1b2b73f 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args) unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == MC_BATCH || - (argidx + args) > MC_ARGS) { + (argidx + args) >= MC_ARGS) { mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS); xen_mc_flush(); argidx = roundup(b->argidx, sizeof(u64)); @@ -206,7 +206,7 @@ struct multicall_space __xen_mc_entry(size_t args) ret.args = &b->args[argidx]; b->argidx = argidx + args; - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); return ret; } @@ -216,7 +216,7 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) struct multicall_space ret = { NULL, NULL }; BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == 0) return ret; @@ -224,14 +224,14 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) if (b->entries[b->mcidx - 1].op != op) return ret; - if ((b->argidx + size) > MC_ARGS) + if ((b->argidx + size) >= MC_ARGS) return ret; ret.mc = &b->entries[b->mcidx - 1]; ret.args = &b->args[b->argidx]; b->argidx += size; - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); return ret; } diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 25c52f9..ffcf261 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); #ifdef CONFIG_XEN_PVHVM static int xen_emul_unplug; -static int __init check_platform_magic(void) +static int check_platform_magic(void) { short magic; char protocol; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index be1a464..60aeeb5 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -227,11 +227,7 @@ char * __init xen_memory_setup(void) memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; -#ifdef CONFIG_X86_32 xen_extra_mem_start = mem_end; -#else - xen_extra_mem_start = max((1ULL << 32), mem_end); -#endif for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end; @@ -266,6 +262,12 @@ char * __init xen_memory_setup(void) if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } + /* Align the balloon area so that max_low_pfn does not get set + * to be at the _end_ of the PCI gap at the far end (fee01000). + * Note that xen_extra_mem_start gets set in the loop above to be + * past the last E820 region. */ + if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) + xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 41038c0..b4533a8 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void) static void __init xen_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; + unsigned int i; xen_init_lock_cpu(0); smp_store_cpu_info(0); cpu_data(0).x86_max_cores = 1; + + for_each_possible_cpu(i) { + zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); + } set_cpu_sibling_map(0); if (xen_smp_intr_init(0)) diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c new file mode 100644 index 0000000..1cd7f4d --- /dev/null +++ b/arch/x86/xen/vga.c @@ -0,0 +1,67 @@ +#include <linux/screen_info.h> +#include <linux/init.h> + +#include <asm/bootparam.h> +#include <asm/setup.h> + +#include <xen/interface/xen.h> + +#include "xen-ops.h" + +void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) +{ + struct screen_info *screen_info = &boot_params.screen_info; + + /* This is drawn from a dump from vgacon:startup in + * standard Linux. */ + screen_info->orig_video_mode = 3; + screen_info->orig_video_isVGA = 1; + screen_info->orig_video_lines = 25; + screen_info->orig_video_cols = 80; + screen_info->orig_video_ega_bx = 3; + screen_info->orig_video_points = 16; + screen_info->orig_y = screen_info->orig_video_lines - 1; + + switch (info->video_type) { + case XEN_VGATYPE_TEXT_MODE_3: + if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3) + + sizeof(info->u.text_mode_3)) + break; + screen_info->orig_video_lines = info->u.text_mode_3.rows; + screen_info->orig_video_cols = info->u.text_mode_3.columns; + screen_info->orig_x = info->u.text_mode_3.cursor_x; + screen_info->orig_y = info->u.text_mode_3.cursor_y; + screen_info->orig_video_points = + info->u.text_mode_3.font_height; + break; + + case XEN_VGATYPE_VESA_LFB: + if (size < offsetof(struct dom0_vga_console_info, + u.vesa_lfb.gbl_caps)) + break; + screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB; + screen_info->lfb_width = info->u.vesa_lfb.width; + screen_info->lfb_height = info->u.vesa_lfb.height; + screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel; + screen_info->lfb_base = info->u.vesa_lfb.lfb_base; + screen_info->lfb_size = info->u.vesa_lfb.lfb_size; + screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line; + screen_info->red_size = info->u.vesa_lfb.red_size; + screen_info->red_pos = info->u.vesa_lfb.red_pos; + screen_info->green_size = info->u.vesa_lfb.green_size; + screen_info->green_pos = info->u.vesa_lfb.green_pos; + screen_info->blue_size = info->u.vesa_lfb.blue_size; + screen_info->blue_pos = info->u.vesa_lfb.blue_pos; + screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size; + screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos; + if (size >= offsetof(struct dom0_vga_console_info, + u.vesa_lfb.gbl_caps) + + sizeof(info->u.vesa_lfb.gbl_caps)) + screen_info->capabilities = info->u.vesa_lfb.gbl_caps; + if (size >= offsetof(struct dom0_vga_console_info, + u.vesa_lfb.mode_attrs) + + sizeof(info->u.vesa_lfb.mode_attrs)) + screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs; + break; + } +} diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 97dfdc8..b095739 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu) } #endif +struct dom0_vga_console_info; + +#ifdef CONFIG_XEN_DOM0 +void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); +#else +static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, + size_t size) +{ +} +#endif + /* Declare an asm function, along with symbols needed to make it inlineable */ #define DECL_ASM(ret, name, ...) \ |