From b332828c39326b1dca617f387dd15d12e81cd5f0 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:43:10 +0530 Subject: hw-breakpoints: prepare the code for Hardware Breakpoint interfaces The generic hardware breakpoint interface provides an abstraction of hardware breakpoints in front of specific arch implementations for both kernel and user side breakpoints. This includes execution breakpoints and read/write breakpoints, also known as "watchpoints". This patch introduces header files containing constants, structure definitions and declaration of functions used by the hardware breakpoint core and x86 specific code. It also introduces an array based storage for the debug-register values in 'struct thread_struct', while modifying all users of debugreg member in the structure. [ Impact: add headers for new hardware breakpoint interface ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/a.out-core.h | 8 +++--- arch/x86/include/asm/debugreg.h | 29 +++++++++++++++++++ arch/x86/include/asm/hw_breakpoint.h | 55 ++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/processor.h | 8 +++--- arch/x86/kernel/process.c | 16 +++++------ arch/x86/kernel/ptrace.c | 16 +++++------ arch/x86/power/cpu_32.c | 8 +++--- arch/x86/power/cpu_64.c | 8 +++--- 8 files changed, 116 insertions(+), 32 deletions(-) create mode 100644 arch/x86/include/asm/hw_breakpoint.h (limited to 'arch') diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h index bb70e397aa8..fc4685dd6e4 100644 --- a/arch/x86/include/asm/a.out-core.h +++ b/arch/x86/include/asm/a.out-core.h @@ -32,10 +32,10 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) >> PAGE_SHIFT; dump->u_dsize -= dump->u_tsize; dump->u_ssize = 0; - dump->u_debugreg[0] = current->thread.debugreg0; - dump->u_debugreg[1] = current->thread.debugreg1; - dump->u_debugreg[2] = current->thread.debugreg2; - dump->u_debugreg[3] = current->thread.debugreg3; + dump->u_debugreg[0] = current->thread.debugreg[0]; + dump->u_debugreg[1] = current->thread.debugreg[1]; + dump->u_debugreg[2] = current->thread.debugreg[2]; + dump->u_debugreg[3] = current->thread.debugreg[3]; dump->u_debugreg[4] = 0; dump->u_debugreg[5] = 0; dump->u_debugreg[6] = current->thread.debugreg6; diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 3ea6f37be9e..23439fbb1d0 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -18,6 +18,7 @@ #define DR_TRAP1 (0x2) /* db1 */ #define DR_TRAP2 (0x4) /* db2 */ #define DR_TRAP3 (0x8) /* db3 */ +#define DR_TRAP_BITS (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3) #define DR_STEP (0x4000) /* single-step */ #define DR_SWITCH (0x8000) /* task switch */ @@ -49,6 +50,8 @@ #define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */ #define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */ +#define DR_LOCAL_ENABLE (0x1) /* Local enable for reg 0 */ +#define DR_GLOBAL_ENABLE (0x2) /* Global enable for reg 0 */ #define DR_ENABLE_SIZE 2 /* 2 enable bits per register */ #define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */ @@ -67,4 +70,30 @@ #define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */ #define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */ +/* + * HW breakpoint additions + */ +#ifdef __KERNEL__ + +/* For process management */ +extern void flush_thread_hw_breakpoint(struct task_struct *tsk); +extern int copy_thread_hw_breakpoint(struct task_struct *tsk, + struct task_struct *child, unsigned long clone_flags); + +/* For CPU management */ +extern void load_debug_registers(void); +static inline void hw_breakpoint_disable(void) +{ + /* Zero the control register for HW Breakpoint */ + set_debugreg(0UL, 7); + + /* Zero-out the individual HW breakpoint address registers */ + set_debugreg(0UL, 0); + set_debugreg(0UL, 1); + set_debugreg(0UL, 2); + set_debugreg(0UL, 3); +} + +#endif /* __KERNEL__ */ + #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h new file mode 100644 index 00000000000..1acb4d45de7 --- /dev/null +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -0,0 +1,55 @@ +#ifndef _I386_HW_BREAKPOINT_H +#define _I386_HW_BREAKPOINT_H + +#ifdef __KERNEL__ +#define __ARCH_HW_BREAKPOINT_H + +struct arch_hw_breakpoint { + char *name; /* Contains name of the symbol to set bkpt */ + unsigned long address; + u8 len; + u8 type; +}; + +#include +#include + +/* Available HW breakpoint length encodings */ +#define HW_BREAKPOINT_LEN_1 0x40 +#define HW_BREAKPOINT_LEN_2 0x44 +#define HW_BREAKPOINT_LEN_4 0x4c +#define HW_BREAKPOINT_LEN_EXECUTE 0x40 + +#ifdef CONFIG_X86_64 +#define HW_BREAKPOINT_LEN_8 0x48 +#endif + +/* Available HW breakpoint type encodings */ + +/* trigger on instruction execute */ +#define HW_BREAKPOINT_EXECUTE 0x80 +/* trigger on memory write */ +#define HW_BREAKPOINT_WRITE 0x81 +/* trigger on memory read or write */ +#define HW_BREAKPOINT_RW 0x83 + +/* Total number of available HW breakpoint registers */ +#define HBP_NUM 4 + +extern struct hw_breakpoint *hbp_kernel[HBP_NUM]; +DECLARE_PER_CPU(struct hw_breakpoint*, this_hbp_kernel[HBP_NUM]); +extern unsigned int hbp_user_refcount[HBP_NUM]; + +extern void arch_install_thread_hw_breakpoint(struct task_struct *tsk); +extern void arch_uninstall_thread_hw_breakpoint(void); +extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len); +extern int arch_validate_hwbkpt_settings(struct hw_breakpoint *bp, + struct task_struct *tsk); +extern void arch_update_user_hw_breakpoint(int pos, struct task_struct *tsk); +extern void arch_flush_thread_hw_breakpoint(struct task_struct *tsk); +extern void arch_update_kernel_hw_breakpoint(void *); +extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data); +#endif /* __KERNEL__ */ +#endif /* _I386_HW_BREAKPOINT_H */ + diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 0b2fab0051e..448b34a8e39 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -29,6 +29,7 @@ struct mm_struct; #include #include +#define HBP_NUM 4 /* * Default implementation of macro that returns current * instruction pointer ("program counter"). @@ -431,12 +432,11 @@ struct thread_struct { unsigned long fs; unsigned long gs; /* Hardware debugging registers: */ - unsigned long debugreg0; - unsigned long debugreg1; - unsigned long debugreg2; - unsigned long debugreg3; + unsigned long debugreg[HBP_NUM]; unsigned long debugreg6; unsigned long debugreg7; + /* Hardware breakpoint info */ + struct hw_breakpoint *hbp[HBP_NUM]; /* Fault info: */ unsigned long cr2; unsigned long trap_no; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index fb5dfb891f0..291527cb438 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -106,10 +106,10 @@ void flush_thread(void) clear_tsk_thread_flag(tsk, TIF_DEBUG); - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; + tsk->thread.debugreg[0] = 0; + tsk->thread.debugreg[1] = 0; + tsk->thread.debugreg[2] = 0; + tsk->thread.debugreg[3] = 0; tsk->thread.debugreg6 = 0; tsk->thread.debugreg7 = 0; memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); @@ -194,10 +194,10 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, update_debugctlmsr(next->debugctlmsr); if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg0, 0); - set_debugreg(next->debugreg1, 1); - set_debugreg(next->debugreg2, 2); - set_debugreg(next->debugreg3, 3); + set_debugreg(next->debugreg[0], 0); + set_debugreg(next->debugreg[1], 1); + set_debugreg(next->debugreg[2], 2); + set_debugreg(next->debugreg[3], 3); /* no 4 and 5 */ set_debugreg(next->debugreg6, 6); set_debugreg(next->debugreg7, 7); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 09ecbde91c1..313be40be55 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -471,10 +471,10 @@ static int genregs_set(struct task_struct *target, static unsigned long ptrace_get_debugreg(struct task_struct *child, int n) { switch (n) { - case 0: return child->thread.debugreg0; - case 1: return child->thread.debugreg1; - case 2: return child->thread.debugreg2; - case 3: return child->thread.debugreg3; + case 0: return child->thread.debugreg[0]; + case 1: return child->thread.debugreg[1]; + case 2: return child->thread.debugreg[2]; + case 3: return child->thread.debugreg[3]; case 6: return child->thread.debugreg6; case 7: return child->thread.debugreg7; } @@ -493,10 +493,10 @@ static int ptrace_set_debugreg(struct task_struct *child, return -EIO; switch (n) { - case 0: child->thread.debugreg0 = data; break; - case 1: child->thread.debugreg1 = data; break; - case 2: child->thread.debugreg2 = data; break; - case 3: child->thread.debugreg3 = data; break; + case 0: child->thread.debugreg[0] = data; break; + case 1: child->thread.debugreg[1] = data; break; + case 2: child->thread.debugreg[2] = data; break; + case 3: child->thread.debugreg[3] = data; break; case 6: if ((data & ~0xffffffffUL) != 0) diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index ce702c5b3a2..51991394800 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -84,10 +84,10 @@ static void fix_processor_context(void) * Now maybe reload the debug registers */ if (current->thread.debugreg7) { - set_debugreg(current->thread.debugreg0, 0); - set_debugreg(current->thread.debugreg1, 1); - set_debugreg(current->thread.debugreg2, 2); - set_debugreg(current->thread.debugreg3, 3); + set_debugreg(current->thread.debugreg[0], 0); + set_debugreg(current->thread.debugreg[1], 1); + set_debugreg(current->thread.debugreg[2], 2); + set_debugreg(current->thread.debugreg[3], 3); /* no 4 and 5 */ set_debugreg(current->thread.debugreg6, 6); set_debugreg(current->thread.debugreg7, 7); diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c index 5343540f260..1e3bdcc959f 100644 --- a/arch/x86/power/cpu_64.c +++ b/arch/x86/power/cpu_64.c @@ -163,10 +163,10 @@ static void fix_processor_context(void) * Now maybe reload the debug registers */ if (current->thread.debugreg7){ - loaddebug(¤t->thread, 0); - loaddebug(¤t->thread, 1); - loaddebug(¤t->thread, 2); - loaddebug(¤t->thread, 3); + set_debugreg(current->thread.debugreg[0], 0); + set_debugreg(current->thread.debugreg[1], 1); + set_debugreg(current->thread.debugreg[2], 2); + set_debugreg(current->thread.debugreg[3], 3); /* no 4 and 5 */ loaddebug(¤t->thread, 6); loaddebug(¤t->thread, 7); -- cgit v1.2.3-70-g09d2 From 62a038d34db26771756cf3689e36de638bedd2c4 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:43:33 +0530 Subject: hw-breakpoints: introducing generic hardware breakpoint handler interfaces This patch introduces the generic Hardware Breakpoint interfaces for both user and kernel space requests. This core Api handles the hardware breakpoints through new helpers. It handles the user-space breakpoints and kernel breakpoints in front of arch implementation. One can choose kernel wide breakpoints using the following helpers and passing them a generic struct hw_breakpoint: - register_kernel_hw_breakpoint() - unregister_kernel_hw_breakpoint() - modify_kernel_hw_breakpoint() On the other side, you can choose per task breakpoints. - register_user_hw_breakpoint() - unregister_user_hw_breakpoint() - modify_user_hw_breakpoint() [ fweisbec@gmail.com: fix conflict against perfcounter ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/Kconfig | 4 + kernel/Makefile | 1 + kernel/hw_breakpoint.c | 378 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 383 insertions(+) create mode 100644 kernel/hw_breakpoint.c (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 78a35e9dc10..1adf2d0e635 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -112,3 +112,7 @@ config HAVE_DMA_API_DEBUG config HAVE_DEFAULT_NO_SPIN_MUTEXES bool + +config HAVE_HW_BREAKPOINT + bool + diff --git a/kernel/Makefile b/kernel/Makefile index a35eee3436d..18ad1110b22 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_X86_DS) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra , the -fno-omit-frame-pointer is diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c new file mode 100644 index 00000000000..c1f64e65a9f --- /dev/null +++ b/kernel/hw_breakpoint.c @@ -0,0 +1,378 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2007 Alan Stern + * Copyright (C) IBM Corporation, 2009 + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + * This file contains the arch-independent routines. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifdef CONFIG_X86 +#include +#endif +/* + * Spinlock that protects all (un)register operations over kernel/user-space + * breakpoint requests + */ +static DEFINE_SPINLOCK(hw_breakpoint_lock); + +/* Array of kernel-space breakpoint structures */ +struct hw_breakpoint *hbp_kernel[HBP_NUM]; + +/* + * Per-processor copy of hbp_kernel[]. Used only when hbp_kernel is being + * modified but we need the older copy to handle any hbp exceptions. It will + * sync with hbp_kernel[] value after updation is done through IPIs. + */ +DEFINE_PER_CPU(struct hw_breakpoint*, this_hbp_kernel[HBP_NUM]); + +/* + * Kernel breakpoints grow downwards, starting from HBP_NUM + * 'hbp_kernel_pos' denotes lowest numbered breakpoint register occupied for + * kernel-space request. We will initialise it here and not in an __init + * routine because load_debug_registers(), which uses this variable can be + * called very early during CPU initialisation. + */ +unsigned int hbp_kernel_pos = HBP_NUM; + +/* + * An array containing refcount of threads using a given bkpt register + * Accesses are synchronised by acquiring hw_breakpoint_lock + */ +unsigned int hbp_user_refcount[HBP_NUM]; + +/* + * Load the debug registers during startup of a CPU. + */ +void load_debug_registers(void) +{ + unsigned long flags; + struct task_struct *tsk = current; + + spin_lock_bh(&hw_breakpoint_lock); + + /* Prevent IPIs for new kernel breakpoint updates */ + local_irq_save(flags); + arch_update_kernel_hw_breakpoint(NULL); + local_irq_restore(flags); + + if (test_tsk_thread_flag(tsk, TIF_DEBUG)) + arch_install_thread_hw_breakpoint(tsk); + + spin_unlock_bh(&hw_breakpoint_lock); +} + +/* + * Erase all the hardware breakpoint info associated with a thread. + * + * If tsk != current then tsk must not be usable (for example, a + * child being cleaned up from a failed fork). + */ +void flush_thread_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *thread = &(tsk->thread); + + spin_lock_bh(&hw_breakpoint_lock); + + /* The thread no longer has any breakpoints associated with it */ + clear_tsk_thread_flag(tsk, TIF_DEBUG); + for (i = 0; i < HBP_NUM; i++) { + if (thread->hbp[i]) { + hbp_user_refcount[i]--; + kfree(thread->hbp[i]); + thread->hbp[i] = NULL; + } + } + + arch_flush_thread_hw_breakpoint(tsk); + + /* Actually uninstall the breakpoints if necessary */ + if (tsk == current) + arch_uninstall_thread_hw_breakpoint(); + spin_unlock_bh(&hw_breakpoint_lock); +} + +/* + * Copy the hardware breakpoint info from a thread to its cloned child. + */ +int copy_thread_hw_breakpoint(struct task_struct *tsk, + struct task_struct *child, unsigned long clone_flags) +{ + /* + * We will assume that breakpoint settings are not inherited + * and the child starts out with no debug registers set. + * But what about CLONE_PTRACE? + */ + clear_tsk_thread_flag(child, TIF_DEBUG); + + /* We will call flush routine since the debugregs are not inherited */ + arch_flush_thread_hw_breakpoint(child); + + return 0; +} + +static int __register_user_hw_breakpoint(int pos, struct task_struct *tsk, + struct hw_breakpoint *bp) +{ + struct thread_struct *thread = &(tsk->thread); + int rc; + + /* Do not overcommit. Fail if kernel has used the hbp registers */ + if (pos >= hbp_kernel_pos) + return -ENOSPC; + + rc = arch_validate_hwbkpt_settings(bp, tsk); + if (rc) + return rc; + + thread->hbp[pos] = bp; + hbp_user_refcount[pos]++; + + arch_update_user_hw_breakpoint(pos, tsk); + /* + * Does it need to be installed right now? + * Otherwise it will get installed the next time tsk runs + */ + if (tsk == current) + arch_install_thread_hw_breakpoint(tsk); + + return rc; +} + +/* + * Modify the address of a hbp register already in use by the task + * Do not invoke this in-lieu of a __unregister_user_hw_breakpoint() + */ +static int __modify_user_hw_breakpoint(int pos, struct task_struct *tsk, + struct hw_breakpoint *bp) +{ + struct thread_struct *thread = &(tsk->thread); + + if ((pos >= hbp_kernel_pos) || (arch_validate_hwbkpt_settings(bp, tsk))) + return -EINVAL; + + if (thread->hbp[pos] == NULL) + return -EINVAL; + + thread->hbp[pos] = bp; + /* + * 'pos' must be that of a hbp register already used by 'tsk' + * Otherwise arch_modify_user_hw_breakpoint() will fail + */ + arch_update_user_hw_breakpoint(pos, tsk); + + if (tsk == current) + arch_install_thread_hw_breakpoint(tsk); + + return 0; +} + +static void __unregister_user_hw_breakpoint(int pos, struct task_struct *tsk) +{ + hbp_user_refcount[pos]--; + tsk->thread.hbp[pos] = NULL; + + arch_update_user_hw_breakpoint(pos, tsk); + + if (tsk == current) + arch_install_thread_hw_breakpoint(tsk); +} + +/** + * register_user_hw_breakpoint - register a hardware breakpoint for user space + * @tsk: pointer to 'task_struct' of the process to which the address belongs + * @bp: the breakpoint structure to register + * + * @bp.info->name or @bp.info->address, @bp.info->len, @bp.info->type and + * @bp->triggered must be set properly before invocation + * + */ +int register_user_hw_breakpoint(struct task_struct *tsk, + struct hw_breakpoint *bp) +{ + struct thread_struct *thread = &(tsk->thread); + int i, rc = -ENOSPC; + + spin_lock_bh(&hw_breakpoint_lock); + + for (i = 0; i < hbp_kernel_pos; i++) { + if (!thread->hbp[i]) { + rc = __register_user_hw_breakpoint(i, tsk, bp); + break; + } + } + if (!rc) + set_tsk_thread_flag(tsk, TIF_DEBUG); + + spin_unlock_bh(&hw_breakpoint_lock); + return rc; +} +EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); + +/** + * modify_user_hw_breakpoint - modify a user-space hardware breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + * @bp: the breakpoint structure to unregister + * + */ +int modify_user_hw_breakpoint(struct task_struct *tsk, struct hw_breakpoint *bp) +{ + struct thread_struct *thread = &(tsk->thread); + int i, ret = -ENOENT; + + spin_lock_bh(&hw_breakpoint_lock); + for (i = 0; i < hbp_kernel_pos; i++) { + if (bp == thread->hbp[i]) { + ret = __modify_user_hw_breakpoint(i, tsk, bp); + break; + } + } + spin_unlock_bh(&hw_breakpoint_lock); + return ret; +} +EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); + +/** + * unregister_user_hw_breakpoint - unregister a user-space hardware breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + * @bp: the breakpoint structure to unregister + * + */ +void unregister_user_hw_breakpoint(struct task_struct *tsk, + struct hw_breakpoint *bp) +{ + struct thread_struct *thread = &(tsk->thread); + int i, pos = -1, hbp_counter = 0; + + spin_lock_bh(&hw_breakpoint_lock); + for (i = 0; i < hbp_kernel_pos; i++) { + if (thread->hbp[i]) + hbp_counter++; + if (bp == thread->hbp[i]) + pos = i; + } + if (pos >= 0) { + __unregister_user_hw_breakpoint(pos, tsk); + hbp_counter--; + } + if (!hbp_counter) + clear_tsk_thread_flag(tsk, TIF_DEBUG); + + spin_unlock_bh(&hw_breakpoint_lock); +} +EXPORT_SYMBOL_GPL(unregister_user_hw_breakpoint); + +/** + * register_kernel_hw_breakpoint - register a hardware breakpoint for kernel space + * @bp: the breakpoint structure to register + * + * @bp.info->name or @bp.info->address, @bp.info->len, @bp.info->type and + * @bp->triggered must be set properly before invocation + * + */ +int register_kernel_hw_breakpoint(struct hw_breakpoint *bp) +{ + int rc; + + rc = arch_validate_hwbkpt_settings(bp, NULL); + if (rc) + return rc; + + spin_lock_bh(&hw_breakpoint_lock); + + rc = -ENOSPC; + /* Check if we are over-committing */ + if ((hbp_kernel_pos > 0) && (!hbp_user_refcount[hbp_kernel_pos-1])) { + hbp_kernel_pos--; + hbp_kernel[hbp_kernel_pos] = bp; + on_each_cpu(arch_update_kernel_hw_breakpoint, NULL, 1); + rc = 0; + } + + spin_unlock_bh(&hw_breakpoint_lock); + return rc; +} +EXPORT_SYMBOL_GPL(register_kernel_hw_breakpoint); + +/** + * unregister_kernel_hw_breakpoint - unregister a HW breakpoint for kernel space + * @bp: the breakpoint structure to unregister + * + * Uninstalls and unregisters @bp. + */ +void unregister_kernel_hw_breakpoint(struct hw_breakpoint *bp) +{ + int i, j; + + spin_lock_bh(&hw_breakpoint_lock); + + /* Find the 'bp' in our list of breakpoints for kernel */ + for (i = hbp_kernel_pos; i < HBP_NUM; i++) + if (bp == hbp_kernel[i]) + break; + + /* Check if we did not find a match for 'bp'. If so return early */ + if (i == HBP_NUM) { + spin_unlock_bh(&hw_breakpoint_lock); + return; + } + + /* + * We'll shift the breakpoints one-level above to compact if + * unregistration creates a hole + */ + for (j = i; j > hbp_kernel_pos; j--) + hbp_kernel[j] = hbp_kernel[j-1]; + + hbp_kernel[hbp_kernel_pos] = NULL; + on_each_cpu(arch_update_kernel_hw_breakpoint, NULL, 1); + hbp_kernel_pos++; + + spin_unlock_bh(&hw_breakpoint_lock); +} +EXPORT_SYMBOL_GPL(unregister_kernel_hw_breakpoint); + +static struct notifier_block hw_breakpoint_exceptions_nb = { + .notifier_call = hw_breakpoint_exceptions_notify, + /* we need to be notified first */ + .priority = 0x7fffffff +}; + +static int __init init_hw_breakpoint(void) +{ + return register_die_notifier(&hw_breakpoint_exceptions_nb); +} + +core_initcall(init_hw_breakpoint); -- cgit v1.2.3-70-g09d2 From 0067f1297241ea567f2b22a455519752d70fcca9 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:43:57 +0530 Subject: hw-breakpoints: x86 architecture implementation of Hardware Breakpoint interfaces This patch introduces the arch-specific implementation of the generic hardware breakpoints in kernel/hw_breakpoint.c inside x86 specific directories. It contains functions which help to validate and serve requests using Hardware Breakpoint registers on x86 processors. [ fweisbec@gmail.com: fix conflict against kmemcheck ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/Kconfig | 1 + arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/hw_breakpoint.c | 382 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 384 insertions(+), 1 deletion(-) create mode 100644 arch/x86/kernel/hw_breakpoint.c (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index df9e885eee1..3033375ed6b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -46,6 +46,7 @@ config X86 select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA + select HAVE_HW_BREAKPOINT config ARCH_DEFCONFIG string diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 77df4d654ff..cbc78182917 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -36,7 +36,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o -obj-y += alternative.o i8253.o pci-nommu.o +obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c new file mode 100644 index 00000000000..4867c9f3b5f --- /dev/null +++ b/arch/x86/kernel/hw_breakpoint.c @@ -0,0 +1,382 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2007 Alan Stern + * Copyright (C) 2009 IBM Corporation + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* Unmasked kernel DR7 value */ +static unsigned long kdr7; + +/* + * Masks for the bits corresponding to registers DR0 - DR3 in DR7 register. + * Used to clear and verify the status of bits corresponding to DR0 - DR3 + */ +static const unsigned long dr7_masks[HBP_NUM] = { + 0x000f0003, /* LEN0, R/W0, G0, L0 */ + 0x00f0000c, /* LEN1, R/W1, G1, L1 */ + 0x0f000030, /* LEN2, R/W2, G2, L2 */ + 0xf00000c0 /* LEN3, R/W3, G3, L3 */ +}; + + +/* + * Encode the length, type, Exact, and Enable bits for a particular breakpoint + * as stored in debug register 7. + */ +static unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type) +{ + unsigned long bp_info; + + bp_info = (len | type) & 0xf; + bp_info <<= (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE); + bp_info |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)) | + DR_GLOBAL_SLOWDOWN; + return bp_info; +} + +void arch_update_kernel_hw_breakpoint(void *unused) +{ + struct hw_breakpoint *bp; + int i, cpu = get_cpu(); + unsigned long temp_kdr7 = 0; + + /* Don't allow debug exceptions while we update the registers */ + set_debugreg(0UL, 7); + + for (i = hbp_kernel_pos; i < HBP_NUM; i++) { + per_cpu(this_hbp_kernel[i], cpu) = bp = hbp_kernel[i]; + if (bp) { + temp_kdr7 |= encode_dr7(i, bp->info.len, bp->info.type); + set_debugreg(bp->info.address, i); + } + } + + /* No need to set DR6. Update the debug registers with kernel-space + * breakpoint values from kdr7 and user-space requests from the + * current process + */ + kdr7 = temp_kdr7; + set_debugreg(kdr7 | current->thread.debugreg7, 7); + put_cpu_no_resched(); +} + +/* + * Install the thread breakpoints in their debug registers. + */ +void arch_install_thread_hw_breakpoint(struct task_struct *tsk) +{ + struct thread_struct *thread = &(tsk->thread); + + switch (hbp_kernel_pos) { + case 4: + set_debugreg(thread->debugreg[3], 3); + case 3: + set_debugreg(thread->debugreg[2], 2); + case 2: + set_debugreg(thread->debugreg[1], 1); + case 1: + set_debugreg(thread->debugreg[0], 0); + default: + break; + } + + /* No need to set DR6 */ + set_debugreg((kdr7 | thread->debugreg7), 7); +} + +/* + * Install the debug register values for just the kernel, no thread. + */ +void arch_uninstall_thread_hw_breakpoint() +{ + /* Clear the user-space portion of debugreg7 by setting only kdr7 */ + set_debugreg(kdr7, 7); + +} + +static int get_hbp_len(u8 hbp_len) +{ + unsigned int len_in_bytes = 0; + + switch (hbp_len) { + case HW_BREAKPOINT_LEN_1: + len_in_bytes = 1; + break; + case HW_BREAKPOINT_LEN_2: + len_in_bytes = 2; + break; + case HW_BREAKPOINT_LEN_4: + len_in_bytes = 4; + break; +#ifdef CONFIG_X86_64 + case HW_BREAKPOINT_LEN_8: + len_in_bytes = 8; + break; +#endif + } + return len_in_bytes; +} + +/* + * Check for virtual address in user space. + */ +int arch_check_va_in_userspace(unsigned long va, u8 hbp_len) +{ + unsigned int len; + + len = get_hbp_len(hbp_len); + + return (va <= TASK_SIZE - len); +} + +/* + * Check for virtual address in kernel space. + */ +int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) +{ + unsigned int len; + + len = get_hbp_len(hbp_len); + + return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); +} + +/* + * Store a breakpoint's encoded address, length, and type. + */ +static int arch_store_info(struct hw_breakpoint *bp, struct task_struct *tsk) +{ + /* + * User-space requests will always have the address field populated + * Symbol names from user-space are rejected + */ + if (tsk && bp->info.name) + return -EINVAL; + /* + * For kernel-addresses, either the address or symbol name can be + * specified. + */ + if (bp->info.name) + bp->info.address = (unsigned long) + kallsyms_lookup_name(bp->info.name); + if (bp->info.address) + return 0; + return -EINVAL; +} + +/* + * Validate the arch-specific HW Breakpoint register settings + */ +int arch_validate_hwbkpt_settings(struct hw_breakpoint *bp, + struct task_struct *tsk) +{ + unsigned int align; + int ret = -EINVAL; + + switch (bp->info.type) { + /* + * Ptrace-refactoring code + * For now, we'll allow instruction breakpoint only for user-space + * addresses + */ + case HW_BREAKPOINT_EXECUTE: + if ((!arch_check_va_in_userspace(bp->info.address, + bp->info.len)) && + bp->info.len != HW_BREAKPOINT_LEN_EXECUTE) + return ret; + break; + case HW_BREAKPOINT_WRITE: + break; + case HW_BREAKPOINT_RW: + break; + default: + return ret; + } + + switch (bp->info.len) { + case HW_BREAKPOINT_LEN_1: + align = 0; + break; + case HW_BREAKPOINT_LEN_2: + align = 1; + break; + case HW_BREAKPOINT_LEN_4: + align = 3; + break; +#ifdef CONFIG_X86_64 + case HW_BREAKPOINT_LEN_8: + align = 7; + break; +#endif + default: + return ret; + } + + if (bp->triggered) + ret = arch_store_info(bp, tsk); + + if (ret < 0) + return ret; + /* + * Check that the low-order bits of the address are appropriate + * for the alignment implied by len. + */ + if (bp->info.address & align) + return -EINVAL; + + /* Check that the virtual address is in the proper range */ + if (tsk) { + if (!arch_check_va_in_userspace(bp->info.address, bp->info.len)) + return -EFAULT; + } else { + if (!arch_check_va_in_kernelspace(bp->info.address, + bp->info.len)) + return -EFAULT; + } + return 0; +} + +void arch_update_user_hw_breakpoint(int pos, struct task_struct *tsk) +{ + struct thread_struct *thread = &(tsk->thread); + struct hw_breakpoint *bp = thread->hbp[pos]; + + thread->debugreg7 &= ~dr7_masks[pos]; + if (bp) { + thread->debugreg[pos] = bp->info.address; + thread->debugreg7 |= encode_dr7(pos, bp->info.len, + bp->info.type); + } else + thread->debugreg[pos] = 0; +} + +void arch_flush_thread_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *thread = &(tsk->thread); + + thread->debugreg7 = 0; + for (i = 0; i < HBP_NUM; i++) + thread->debugreg[i] = 0; +} + +/* + * Handle debug exception notifications. + * + * Return value is either NOTIFY_STOP or NOTIFY_DONE as explained below. + * + * NOTIFY_DONE returned if one of the following conditions is true. + * i) When the causative address is from user-space and the exception + * is a valid one, i.e. not triggered as a result of lazy debug register + * switching + * ii) When there are more bits than trap set in DR6 register (such + * as BD, BS or BT) indicating that more than one debug condition is + * met and requires some more action in do_debug(). + * + * NOTIFY_STOP returned for all other cases + * + */ +int __kprobes hw_breakpoint_handler(struct die_args *args) +{ + int i, cpu, rc = NOTIFY_STOP; + struct hw_breakpoint *bp; + /* The DR6 value is stored in args->err */ + unsigned long dr7, dr6 = args->err; + + /* Do an early return if no trap bits are set in DR6 */ + if ((dr6 & DR_TRAP_BITS) == 0) + return NOTIFY_DONE; + + /* Lazy debug register switching */ + if (!test_tsk_thread_flag(current, TIF_DEBUG)) + arch_uninstall_thread_hw_breakpoint(); + + get_debugreg(dr7, 7); + /* Disable breakpoints during exception handling */ + set_debugreg(0UL, 7); + /* + * Assert that local interrupts are disabled + * Reset the DRn bits in the virtualized register value. + * The ptrace trigger routine will add in whatever is needed. + */ + current->thread.debugreg6 &= ~DR_TRAP_BITS; + cpu = get_cpu(); + + /* Handle all the breakpoints that were triggered */ + for (i = 0; i < HBP_NUM; ++i) { + if (likely(!(dr6 & (DR_TRAP0 << i)))) + continue; + /* + * Find the corresponding hw_breakpoint structure and + * invoke its triggered callback. + */ + if (i >= hbp_kernel_pos) + bp = per_cpu(this_hbp_kernel[i], cpu); + else { + bp = current->thread.hbp[i]; + if (bp) + rc = NOTIFY_DONE; + } + /* + * bp can be NULL due to lazy debug register switching + * or due to the delay between updates of hbp_kernel_pos + * and this_hbp_kernel. + */ + if (!bp) + continue; + + (bp->triggered)(bp, args->regs); + } + if (dr6 & (~DR_TRAP_BITS)) + rc = NOTIFY_DONE; + + set_debugreg(dr7, 7); + put_cpu_no_resched(); + return rc; +} + +/* + * Handle debug exception notifications. + */ +int __kprobes hw_breakpoint_exceptions_notify( + struct notifier_block *unused, unsigned long val, void *data) +{ + if (val != DIE_DEBUG) + return NOTIFY_DONE; + + return hw_breakpoint_handler(data); +} -- cgit v1.2.3-70-g09d2 From 08d68323d1f0c34452e614263b212ca556dae47f Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:44:08 +0530 Subject: hw-breakpoints: modifying generic debug exception to use thread-specific debug registers This patch modifies the breakpoint exception handler code to use the new abstract debug register names. [ fweisbec@gmail.com: fix conflict against kmemcheck ] [ Impact: refactor and cleanup x86 debug exception handler ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/traps.c | 69 +++++++++++++++++-------------------------------- 1 file changed, 24 insertions(+), 45 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a1d288327ff..de9913247dd 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -529,73 +529,52 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - unsigned long condition; + unsigned long dr6; int si_code; - get_debugreg(condition, 6); + get_debugreg(dr6, 6); + /* DR6 may or may not be cleared by the CPU */ + set_debugreg(0, 6); /* * The processor cleared BTF, so don't mark that we need it set. */ clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR); tsk->thread.debugctlmsr = 0; - if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, + /* Store the virtualized DR6 value */ + tsk->thread.debugreg6 = dr6; + + if (notify_die(DIE_DEBUG, "debug", regs, dr6, error_code, SIGTRAP) == NOTIFY_STOP) return; /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); - /* Mask out spurious debug traps due to lazy DR7 setting */ - if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg7) - goto clear_dr7; + if (regs->flags & X86_VM_MASK) { + handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, 1); + return; } -#ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto debug_vm86; -#endif - - /* Save debug status register where ptrace can see it */ - tsk->thread.debugreg6 = condition; - /* - * Single-stepping through TF: make sure we ignore any events in - * kernel space (but re-enable TF when returning to user mode). + * Single-stepping through system calls: ignore any exceptions in + * kernel space, but re-enable TF when returning to user mode. + * + * We already checked v86 mode above, so we can check for kernel mode + * by just checking the CPL of CS. */ - if (condition & DR_STEP) { - if (!user_mode(regs)) - goto clear_TF_reenable; + if ((dr6 & DR_STEP) && !user_mode(regs)) { + tsk->thread.debugreg6 &= ~DR_STEP; + set_tsk_thread_flag(tsk, TIF_SINGLESTEP); + regs->flags &= ~X86_EFLAGS_TF; } - - si_code = get_si_code(condition); - /* Ok, finally something we can handle */ - send_sigtrap(tsk, regs, error_code, si_code); - - /* - * Disable additional traps. They'll be re-enabled when - * the signal is delivered. - */ -clear_dr7: - set_debugreg(0, 7); + si_code = get_si_code(tsk->thread.debugreg6); + if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS)) + send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); - return; -#ifdef CONFIG_X86_32 -debug_vm86: - /* reenable preemption: handle_vm86_trap() might sleep */ - dec_preempt_count(); - handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); - conditional_cli(regs); - return; -#endif - -clear_TF_reenable: - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~X86_EFLAGS_TF; - preempt_conditional_cli(regs); return; } -- cgit v1.2.3-70-g09d2 From 1e3500666f7c5daaadadb8431a2927cdbbdb7dd4 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:44:26 +0530 Subject: hw-breakpoints: use wrapper routines around debug registers in processor related functions This patch enables the use of wrapper routines to access the debug/breakpoint registers on cpu management. The hardcoded debug registers save and restore operations for threads breakpoints are replaced by wrappers. And now that we handle the kernel breakpoints too, we also need to handle them on cpu hotplug operations. [ Impact: adapt new hardware breakpoint api to cpu hotplug ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/smpboot.c | 3 +++ arch/x86/power/cpu_32.c | 13 +++---------- arch/x86/power/cpu_64.c | 12 +++--------- 3 files changed, 9 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 58d24ef917d..2b2652d205c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include @@ -326,6 +327,7 @@ notrace static void __cpuinit start_secondary(void *unused) setup_secondary_clock(); wmb(); + load_debug_registers(); cpu_idle(); } @@ -1250,6 +1252,7 @@ void cpu_disable_common(void) remove_cpu_from_maps(cpu); unlock_vector_lock(); fixup_irqs(); + hw_breakpoint_disable(); } int native_cpu_disable(void) diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index 51991394800..2bc3b016de9 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -13,6 +13,7 @@ #include #include #include +#include static struct saved_context saved_context; @@ -48,6 +49,7 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr2 = read_cr2(); ctxt->cr3 = read_cr3(); ctxt->cr4 = read_cr4_safe(); + hw_breakpoint_disable(); } /* Needed by apm.c */ @@ -83,16 +85,7 @@ static void fix_processor_context(void) /* * Now maybe reload the debug registers */ - if (current->thread.debugreg7) { - set_debugreg(current->thread.debugreg[0], 0); - set_debugreg(current->thread.debugreg[1], 1); - set_debugreg(current->thread.debugreg[2], 2); - set_debugreg(current->thread.debugreg[3], 3); - /* no 4 and 5 */ - set_debugreg(current->thread.debugreg6, 6); - set_debugreg(current->thread.debugreg7, 7); - } - + load_debug_registers(); } static void __restore_processor_state(struct saved_context *ctxt) diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c index 1e3bdcc959f..46866a13a93 100644 --- a/arch/x86/power/cpu_64.c +++ b/arch/x86/power/cpu_64.c @@ -16,6 +16,7 @@ #include #include #include +#include static void fix_processor_context(void); @@ -71,6 +72,7 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr3 = read_cr3(); ctxt->cr4 = read_cr4(); ctxt->cr8 = read_cr8(); + hw_breakpoint_disable(); } void save_processor_state(void) @@ -162,13 +164,5 @@ static void fix_processor_context(void) /* * Now maybe reload the debug registers */ - if (current->thread.debugreg7){ - set_debugreg(current->thread.debugreg[0], 0); - set_debugreg(current->thread.debugreg[1], 1); - set_debugreg(current->thread.debugreg[2], 2); - set_debugreg(current->thread.debugreg[3], 3); - /* no 4 and 5 */ - loaddebug(¤t->thread, 6); - loaddebug(¤t->thread, 7); - } + load_debug_registers(); } -- cgit v1.2.3-70-g09d2 From 66cb5917295958652ff6ba36d83f98f2379c46b4 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:44:55 +0530 Subject: hw-breakpoints: use the new wrapper routines to access debug registers in process/thread code This patch enables the use of abstract debug registers in process-handling routines, according to the new hardware breakpoint Api. [ Impact: adapt thread breakpoints handling code to the new breakpoint Api ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/process.c | 22 ++++++---------------- arch/x86/kernel/process_32.c | 28 ++++++++++++++++++++++++++++ arch/x86/kernel/process_64.c | 31 +++++++++++++++++++++++++++++++ 3 files changed, 65 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 291527cb438..19a686c401b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -15,6 +15,8 @@ #include #include #include +#include +#include unsigned long idle_halt; EXPORT_SYMBOL(idle_halt); @@ -46,6 +48,8 @@ void free_thread_xstate(struct task_struct *tsk) kmem_cache_free(task_xstate_cachep, tsk->thread.xstate); tsk->thread.xstate = NULL; } + if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG))) + flush_thread_hw_breakpoint(tsk); WARN(tsk->thread.ds_ctx, "leaking DS context\n"); } @@ -106,12 +110,8 @@ void flush_thread(void) clear_tsk_thread_flag(tsk, TIF_DEBUG); - tsk->thread.debugreg[0] = 0; - tsk->thread.debugreg[1] = 0; - tsk->thread.debugreg[2] = 0; - tsk->thread.debugreg[3] = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; + if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG))) + flush_thread_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); /* * Forget coprocessor state.. @@ -193,16 +193,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, else if (next->debugctlmsr != prev->debugctlmsr) update_debugctlmsr(next->debugctlmsr); - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg[0], 0); - set_debugreg(next->debugreg[1], 1); - set_debugreg(next->debugreg[2], 2); - set_debugreg(next->debugreg[3], 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg6, 6); - set_debugreg(next->debugreg7, 7); - } - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ test_tsk_thread_flag(next_p, TIF_NOTSC)) { /* prev and next are different */ diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b5e4bfef447..297ffff2ffc 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -61,6 +61,8 @@ #include #include #include +#include +#include asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -265,7 +267,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, task_user_gs(p) = get_user_gs(regs); + p->thread.io_bitmap_ptr = NULL; tsk = current; + err = -ENOMEM; + if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG))) + if (copy_thread_hw_breakpoint(tsk, p, clone_flags)) + goto out; + if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); @@ -285,10 +293,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, err = do_set_thread_area(p, -1, (struct user_desc __user *)childregs->si, 0); +out: if (err && p->thread.io_bitmap_ptr) { kfree(p->thread.io_bitmap_ptr); p->thread.io_bitmap_max = 0; } + if (err) + flush_thread_hw_breakpoint(p); clear_tsk_thread_flag(p, TIF_DS_AREA_MSR); p->thread.ds_ctx = NULL; @@ -427,6 +438,23 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) lazy_load_gs(next->gs); percpu_write(current_task, next_p); + /* + * There's a problem with moving the arch_install_thread_hw_breakpoint() + * call before current is updated. Suppose a kernel breakpoint is + * triggered in between the two, the hw-breakpoint handler will see that + * the 'current' task does not have TIF_DEBUG flag set and will think it + * is leftover from an old task (lazy switching) and will erase it. Then + * until the next context switch, no user-breakpoints will be installed. + * + * The real problem is that it's impossible to update both current and + * physical debug registers at the same instant, so there will always be + * a window in which they disagree and a breakpoint might get triggered. + * Since we use lazy switching, we are forced to assume that a + * disagreement means that current is correct and the exception is due + * to lazy debug register switching. + */ + if (unlikely(test_tsk_thread_flag(next_p, TIF_DEBUG))) + arch_install_thread_hw_breakpoint(next_p); return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 5a1a1de292e..f7b276d4b3f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -55,6 +55,8 @@ #include #include #include +#include +#include asmlinkage extern void ret_from_fork(void); @@ -248,6 +250,8 @@ void release_thread(struct task_struct *dead_task) BUG(); } } + if (unlikely(dead_task->thread.debugreg7)) + flush_thread_hw_breakpoint(dead_task); } static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) @@ -303,12 +307,18 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.fs = me->thread.fs; p->thread.gs = me->thread.gs; + p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); savesegment(fs, p->thread.fsindex); savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); + err = -ENOMEM; + if (unlikely(test_tsk_thread_flag(me, TIF_DEBUG))) + if (copy_thread_hw_breakpoint(me, p, clone_flags)) + goto out; + if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { @@ -347,6 +357,9 @@ out: kfree(p->thread.io_bitmap_ptr); p->thread.io_bitmap_max = 0; } + if (err) + flush_thread_hw_breakpoint(p); + return err; } @@ -492,6 +505,24 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ if (tsk_used_math(next_p) && next_p->fpu_counter > 5) math_state_restore(); + /* + * There's a problem with moving the arch_install_thread_hw_breakpoint() + * call before current is updated. Suppose a kernel breakpoint is + * triggered in between the two, the hw-breakpoint handler will see that + * the 'current' task does not have TIF_DEBUG flag set and will think it + * is leftover from an old task (lazy switching) and will erase it. Then + * until the next context switch, no user-breakpoints will be installed. + * + * The real problem is that it's impossible to update both current and + * physical debug registers at the same instant, so there will always be + * a window in which they disagree and a breakpoint might get triggered. + * Since we use lazy switching, we are forced to assume that a + * disagreement means that current is correct and the exception is due + * to lazy debug register switching. + */ + if (unlikely(test_tsk_thread_flag(next_p, TIF_DEBUG))) + arch_install_thread_hw_breakpoint(next_p); + return prev_p; } -- cgit v1.2.3-70-g09d2 From da0cdc14f5f7e0faee6b2393fefed056cdb17146 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:45:03 +0530 Subject: hw-breakpoints: modify signal handling code to refrain from re-enabling HW Breakpoints This patch disables re-enabling of Hardware Breakpoint registers through the signal handling code. This is now done during from hw_breakpoint_handler(). Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/signal.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 14425166b8e..f33d2e0ef09 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -800,15 +800,6 @@ static void do_signal(struct pt_regs *regs) signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { - /* - * Re-enable any watchpoints before delivering the - * signal to user space. The processor register will - * have been cleared if the watchpoint triggered - * inside the kernel. - */ - if (current->thread.debugreg7) - set_debugreg(current->thread.debugreg7, 7); - /* Whee! Actually deliver the signal. */ if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { /* -- cgit v1.2.3-70-g09d2 From 72f674d203cd230426437cdcf7dd6f681dad8b0d Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:45:48 +0530 Subject: hw-breakpoints: modify Ptrace routines to access breakpoint registers This patch modifies the ptrace code to use the new wrapper routines around the debug/breakpoint registers. [ Impact: adapt x86 ptrace to the new breakpoint Api ] Original-patch-by: Alan Stern Signed-off-by: K.Prasad Signed-off-by: Maneesh Soni Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/ptrace.c | 231 +++++++++++++++++++++++++++++------------------ 1 file changed, 141 insertions(+), 90 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 313be40be55..b457f78b7db 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -34,6 +34,7 @@ #include #include #include +#include #include @@ -136,11 +137,6 @@ static int set_segment_reg(struct task_struct *task, return 0; } -static unsigned long debugreg_addr_limit(struct task_struct *task) -{ - return TASK_SIZE - 3; -} - #else /* CONFIG_X86_64 */ #define FLAG_MASK (FLAG_MASK_32 | X86_EFLAGS_NT) @@ -265,15 +261,6 @@ static int set_segment_reg(struct task_struct *task, return 0; } -static unsigned long debugreg_addr_limit(struct task_struct *task) -{ -#ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(task, TIF_IA32)) - return IA32_PAGE_OFFSET - 3; -#endif - return TASK_SIZE_MAX - 7; -} - #endif /* CONFIG_X86_32 */ static unsigned long get_flags(struct task_struct *task) @@ -464,95 +451,159 @@ static int genregs_set(struct task_struct *target, } /* - * This function is trivial and will be inlined by the compiler. - * Having it separates the implementation details of debug - * registers from the interface details of ptrace. + * Decode the length and type bits for a particular breakpoint as + * stored in debug register 7. Return the "enabled" status. */ -static unsigned long ptrace_get_debugreg(struct task_struct *child, int n) +static int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, + unsigned *type) { - switch (n) { - case 0: return child->thread.debugreg[0]; - case 1: return child->thread.debugreg[1]; - case 2: return child->thread.debugreg[2]; - case 3: return child->thread.debugreg[3]; - case 6: return child->thread.debugreg6; - case 7: return child->thread.debugreg7; - } - return 0; + int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE); + + *len = (bp_info & 0xc) | 0x40; + *type = (bp_info & 0x3) | 0x80; + return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3; } -static int ptrace_set_debugreg(struct task_struct *child, - int n, unsigned long data) +static void ptrace_triggered(struct hw_breakpoint *bp, struct pt_regs *regs) { + struct thread_struct *thread = &(current->thread); int i; - if (unlikely(n == 4 || n == 5)) - return -EIO; + /* + * Store in the virtual DR6 register the fact that the breakpoint + * was hit so the thread's debugger will see it. + */ + for (i = 0; i < hbp_kernel_pos; i++) + /* + * We will check bp->info.address against the address stored in + * thread's hbp structure and not debugreg[i]. This is to ensure + * that the corresponding bit for 'i' in DR7 register is enabled + */ + if (bp->info.address == thread->hbp[i]->info.address) + break; - if (n < 4 && unlikely(data >= debugreg_addr_limit(child))) - return -EIO; + thread->debugreg6 |= (DR_TRAP0 << i); +} - switch (n) { - case 0: child->thread.debugreg[0] = data; break; - case 1: child->thread.debugreg[1] = data; break; - case 2: child->thread.debugreg[2] = data; break; - case 3: child->thread.debugreg[3] = data; break; +/* + * Handle ptrace writes to debug register 7. + */ +static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) +{ + struct thread_struct *thread = &(tsk->thread); + unsigned long old_dr7 = thread->debugreg7; + int i, orig_ret = 0, rc = 0; + int enabled, second_pass = 0; + unsigned len, type; + struct hw_breakpoint *bp; + + data &= ~DR_CONTROL_RESERVED; +restore: + /* + * Loop through all the hardware breakpoints, making the + * appropriate changes to each. + */ + for (i = 0; i < HBP_NUM; i++) { + enabled = decode_dr7(data, i, &len, &type); + bp = thread->hbp[i]; + + if (!enabled) { + if (bp) { + /* Don't unregister the breakpoints right-away, + * unless all register_user_hw_breakpoint() + * requests have succeeded. This prevents + * any window of opportunity for debug + * register grabbing by other users. + */ + if (!second_pass) + continue; + unregister_user_hw_breakpoint(tsk, bp); + kfree(bp); + } + continue; + } + if (!bp) { + rc = -ENOMEM; + bp = kzalloc(sizeof(struct hw_breakpoint), GFP_KERNEL); + if (bp) { + bp->info.address = thread->debugreg[i]; + bp->triggered = ptrace_triggered; + bp->info.len = len; + bp->info.type = type; + rc = register_user_hw_breakpoint(tsk, bp); + if (rc) + kfree(bp); + } + } else + rc = modify_user_hw_breakpoint(tsk, bp); + if (rc) + break; + } + /* + * Make a second pass to free the remaining unused breakpoints + * or to restore the original breakpoints if an error occurred. + */ + if (!second_pass) { + second_pass = 1; + if (rc < 0) { + orig_ret = rc; + data = old_dr7; + } + goto restore; + } + return ((orig_ret < 0) ? orig_ret : rc); +} - case 6: - if ((data & ~0xffffffffUL) != 0) - return -EIO; - child->thread.debugreg6 = data; - break; +/* + * Handle PTRACE_PEEKUSR calls for the debug register area. + */ +unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) +{ + struct thread_struct *thread = &(tsk->thread); + unsigned long val = 0; + + if (n < HBP_NUM) + val = thread->debugreg[n]; + else if (n == 6) + val = thread->debugreg6; + else if (n == 7) + val = thread->debugreg7; + return val; +} - case 7: - /* - * Sanity-check data. Take one half-byte at once with - * check = (val >> (16 + 4*i)) & 0xf. It contains the - * R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits - * 2 and 3 are LENi. Given a list of invalid values, - * we do mask |= 1 << invalid_value, so that - * (mask >> check) & 1 is a correct test for invalid - * values. - * - * R/Wi contains the type of the breakpoint / - * watchpoint, LENi contains the length of the watched - * data in the watchpoint case. - * - * The invalid values are: - * - LENi == 0x10 (undefined), so mask |= 0x0f00. [32-bit] - * - R/Wi == 0x10 (break on I/O reads or writes), so - * mask |= 0x4444. - * - R/Wi == 0x00 && LENi != 0x00, so we have mask |= - * 0x1110. - * - * Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54. - * - * See the Intel Manual "System Programming Guide", - * 15.2.4 - * - * Note that LENi == 0x10 is defined on x86_64 in long - * mode (i.e. even for 32-bit userspace software, but - * 64-bit kernel), so the x86_64 mask value is 0x5454. - * See the AMD manual no. 24593 (AMD64 System Programming) - */ -#ifdef CONFIG_X86_32 -#define DR7_MASK 0x5f54 -#else -#define DR7_MASK 0x5554 -#endif - data &= ~DR_CONTROL_RESERVED; - for (i = 0; i < 4; i++) - if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1) - return -EIO; - child->thread.debugreg7 = data; - if (data) - set_tsk_thread_flag(child, TIF_DEBUG); - else - clear_tsk_thread_flag(child, TIF_DEBUG); - break; +/* + * Handle PTRACE_POKEUSR calls for the debug register area. + */ +int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val) +{ + struct thread_struct *thread = &(tsk->thread); + int rc = 0; + + /* There are no DR4 or DR5 registers */ + if (n == 4 || n == 5) + return -EIO; + + if (n == 6) { + tsk->thread.debugreg6 = val; + goto ret_path; } + if (n < HBP_NUM) { + if (thread->hbp[n]) { + if (arch_check_va_in_userspace(val, + thread->hbp[n]->info.len) == 0) { + rc = -EIO; + goto ret_path; + } + thread->hbp[n]->info.address = val; + } + thread->debugreg[n] = val; + } + /* All that's left is DR7 */ + if (n == 7) + rc = ptrace_write_dr7(tsk, val); - return 0; +ret_path: + return rc; } /* -- cgit v1.2.3-70-g09d2 From 17f557e5b5d43a2af66c969f6560ac7105020672 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:46:03 +0530 Subject: hw-breakpoints: cleanup HW Breakpoint registers before kexec This patch disables Hardware breakpoints before doing a 'kexec' on the machine so that the cpu doesn't keep debug registers values which would be out of sync for the new image. Original-patch-by: Alan Stern Signed-off-by: K.Prasad Reviewed-by: Alan Stern Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/machine_kexec_32.c | 2 ++ arch/x86/kernel/machine_kexec_64.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index c1c429d0013..c843f8406da 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -25,6 +25,7 @@ #include #include #include +#include static void set_idt(void *newidt, __u16 limit) { @@ -202,6 +203,7 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + hw_breakpoint_disable(); if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 84c3bf209e9..4a8bb82248a 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -18,6 +18,7 @@ #include #include #include +#include static int init_one_level2_page(struct kimage *image, pgd_t *pgd, unsigned long addr) @@ -282,6 +283,7 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + hw_breakpoint_disable(); if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC -- cgit v1.2.3-70-g09d2 From 62edab9056a6cf0c9207339c8892c923a5217e45 Mon Sep 17 00:00:00 2001 From: "K.Prasad" Date: Mon, 1 Jun 2009 23:47:06 +0530 Subject: hw-breakpoints: reset bits in dr6 after the corresponding exception is handled This patch resets the bit in dr6 after the corresponding exception is handled in code, so that we keep a clean track of the current virtual debug status register. [ Impact: keep track of breakpoints triggering completion ] Signed-off-by: K.Prasad Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/hw_breakpoint.c | 13 +++++++++++-- arch/x86/kernel/kgdb.c | 6 ++++++ arch/x86/kernel/kprobes.c | 9 ++++++++- arch/x86/kernel/traps.c | 4 ++-- arch/x86/mm/kmmio.c | 8 +++++++- 5 files changed, 34 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 4867c9f3b5f..69451473dbd 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -314,8 +314,12 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) { int i, cpu, rc = NOTIFY_STOP; struct hw_breakpoint *bp; - /* The DR6 value is stored in args->err */ - unsigned long dr7, dr6 = args->err; + unsigned long dr7, dr6; + unsigned long *dr6_p; + + /* The DR6 value is pointed by args->err */ + dr6_p = (unsigned long *)ERR_PTR(args->err); + dr6 = *dr6_p; /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) @@ -351,6 +355,11 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (bp) rc = NOTIFY_DONE; } + /* + * Reset the 'i'th TRAP bit in dr6 to denote completion of + * exception handling + */ + (*dr6_p) &= ~(DR_TRAP0 << i); /* * bp can be NULL due to lazy debug register switching * or due to the delay between updates of hbp_kernel_pos diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index b1f4dffb919..f820b73c7f2 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -43,6 +43,7 @@ #include #include +#include #include #include @@ -434,6 +435,11 @@ single_step_cont(struct pt_regs *regs, struct die_args *args) "resuming...\n"); kgdb_arch_handle_exception(args->trapnr, args->signr, args->err, "c", "", regs); + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; return NOTIFY_STOP; } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 7b5169d2b00..b5b1848c533 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -54,6 +54,7 @@ #include #include #include +#include void jprobe_return_end(void); @@ -967,8 +968,14 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; break; case DIE_DEBUG: - if (post_kprobe_handler(args->regs)) + if (post_kprobe_handler(args->regs)) { + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; ret = NOTIFY_STOP; + } break; case DIE_GPF: /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index de9913247dd..124a4d5a95b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -545,8 +545,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; - if (notify_die(DIE_DEBUG, "debug", regs, dr6, error_code, - SIGTRAP) == NOTIFY_STOP) + if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, + SIGTRAP) == NOTIFY_STOP) return; /* It's safe to allow irq's after DR6 has been saved */ diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 16ccbd77917..11a4ad4d625 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -540,8 +540,14 @@ kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args) struct die_args *arg = args; if (val == DIE_DEBUG && (arg->err & DR_STEP)) - if (post_kmmio_handler(arg->err, arg->regs) == 1) + if (post_kmmio_handler(arg->err, arg->regs) == 1) { + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP; return NOTIFY_STOP; + } return NOTIFY_DONE; } -- cgit v1.2.3-70-g09d2 From 4555835b707d5c778ee1c9076670bc99b1eeaf61 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 17 Jun 2009 14:44:19 +0530 Subject: x86: hw_breakpoint.c arch_check_va_in_kernelspace and hw_breakpoint_handler should be static arch_check_va_in_kernelspace() and hw_breakpoint_handler() is used only by same file so it should be static. Also fixed non-ANSI function declaration of function 'arch_uninstall_thread_hw_breakpoint' Fixed following sparse warnings : arch/x86/kernel/hw_breakpoint.c:124:42: warning: non-ANSI function declaration of function 'arch_uninstall_thread_hw_breakpoint' arch/x86/kernel/hw_breakpoint.c:169:5: warning: symbol 'arch_check_va_in_kernelspace' was not declared. Should it be static? arch/x86/kernel/hw_breakpoint.c:313:15: warning: symbol 'hw_breakpoint_handler' was not declared. Should it be static? Signed-off-by: Jaswinder Singh Rajput Cc: Alan Stern Cc: "K.Prasad" Cc: Frederic Weisbecker LKML-Reference: <1245230059.2662.4.camel@ht.satnam> Signed-off-by: Ingo Molnar --- arch/x86/kernel/hw_breakpoint.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 51d959528b1..9316a9de4de 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -121,7 +121,7 @@ void arch_install_thread_hw_breakpoint(struct task_struct *tsk) /* * Install the debug register values for just the kernel, no thread. */ -void arch_uninstall_thread_hw_breakpoint() +void arch_uninstall_thread_hw_breakpoint(void) { /* Clear the user-space portion of debugreg7 by setting only kdr7 */ set_debugreg(kdr7, 7); @@ -166,7 +166,7 @@ int arch_check_va_in_userspace(unsigned long va, u8 hbp_len) /* * Check for virtual address in kernel space. */ -int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) +static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) { unsigned int len; @@ -310,7 +310,7 @@ void arch_flush_thread_hw_breakpoint(struct task_struct *tsk) * NOTIFY_STOP returned for all other cases * */ -int __kprobes hw_breakpoint_handler(struct die_args *args) +static int __kprobes hw_breakpoint_handler(struct die_args *args) { int i, cpu, rc = NOTIFY_STOP; struct hw_breakpoint *bp; -- cgit v1.2.3-70-g09d2 From 9d22b536609abf0d64648f99518676ea58245e3b Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 19:52:30 +0530 Subject: x86: Mark ptrace_get_debugreg() as static This sparse warning: arch/x86/kernel/ptrace.c:560:15: warning: symbol 'ptrace_get_debugreg' was not declared. Should it be static? triggers because ptrace_get_debugreg() is global but is only used in a single .c file. change ptrace_get_debugreg() to static to fix that - this also addresses the sparse warning. Signed-off-by: Jaswinder Singh Rajput Cc: Steven Rostedt LKML-Reference: <1246458150.6940.19.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- arch/x86/kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b457f78b7db..cabdabce3cb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -557,7 +557,7 @@ restore: /* * Handle PTRACE_PEEKUSR calls for the debug register area. */ -unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) +static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) { struct thread_struct *thread = &(tsk->thread); unsigned long val = 0; -- cgit v1.2.3-70-g09d2 From 39fe05e58c5e448601ce46e6b03900d5bf31c4b0 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Aug 2009 11:16:12 +0800 Subject: x86, hpet: Disable per-cpu hpet timer if ARAT is supported If CPU support always running local APIC timer, per-cpu hpet timer could be disabled, which is useless and wasteful in such case. Let's leave the timers to others. The effect is that we reserve less timers. Signed-off-by: Shaohua Li Cc: venkatesh.pallipadi@intel.com LKML-Reference: <20090812031612.GA10062@sli10-desk.sh.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/hpet.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dedc2bddf7a..5969e1078fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -584,6 +584,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return; id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -872,10 +874,8 @@ int __init hpet_enable(void) if (id & HPET_ID_LEGSUP) { hpet_legacy_clockevent_register(); - hpet_msi_capability_lookup(2); return 1; } - hpet_msi_capability_lookup(0); return 0; out_nohpet: @@ -908,9 +908,17 @@ static __init int hpet_late_init(void) if (!hpet_virt_address) return -ENODEV; + if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP) + hpet_msi_capability_lookup(2); + else + hpet_msi_capability_lookup(0); + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (boot_cpu_has(X86_FEATURE_ARAT)) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } -- cgit v1.2.3-70-g09d2 From 50dcfa0234753c32e1c838cc0e6d7952dda73201 Mon Sep 17 00:00:00 2001 From: Andrew Victor Date: Tue, 4 Aug 2009 19:55:56 +0100 Subject: ARM: 5637/1: [KS8695] Don't reference CLOCK_TICK_RATE in drivers Stop referencing CLOCK_TICK_RATE in the KS8695 drivers, rather refer to a KS8695_CLOCK_RATE. Issue pointed out by Russell King on arm-linux-kernel mailing list. Signed-off-by: Andrew Victor Signed-off-by: Russell King --- arch/arm/mach-ks8695/include/mach/hardware.h | 5 +++++ arch/arm/mach-ks8695/include/mach/timex.h | 5 +++-- drivers/serial/serial_ks8695.c | 2 +- drivers/watchdog/ks8695_wdt.c | 4 ++-- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-ks8695/include/mach/hardware.h b/arch/arm/mach-ks8695/include/mach/hardware.h index 1d640d075b7..e0f911d9e02 100644 --- a/arch/arm/mach-ks8695/include/mach/hardware.h +++ b/arch/arm/mach-ks8695/include/mach/hardware.h @@ -16,6 +16,11 @@ #include +/* + * Clocks are derived from MCLK, which is 25Mhz + */ +#define KS8695_CLOCK_RATE 25000000 + /* * Physical RAM address. */ diff --git a/arch/arm/mach-ks8695/include/mach/timex.h b/arch/arm/mach-ks8695/include/mach/timex.h index 4682e350369..10f716371bd 100644 --- a/arch/arm/mach-ks8695/include/mach/timex.h +++ b/arch/arm/mach-ks8695/include/mach/timex.h @@ -14,7 +14,8 @@ #ifndef __ASM_ARCH_TIMEX_H #define __ASM_ARCH_TIMEX_H -/* timers are derived from MCLK, which is 25MHz */ -#define CLOCK_TICK_RATE 25000000 +#include + +#define CLOCK_TICK_RATE KS8695_CLOCK_RATE #endif diff --git a/drivers/serial/serial_ks8695.c b/drivers/serial/serial_ks8695.c index 998e89dc5aa..e0665630e4d 100644 --- a/drivers/serial/serial_ks8695.c +++ b/drivers/serial/serial_ks8695.c @@ -549,7 +549,7 @@ static struct uart_port ks8695uart_ports[SERIAL_KS8695_NR] = { .mapbase = KS8695_UART_VA, .iotype = SERIAL_IO_MEM, .irq = KS8695_IRQ_UART_TX, - .uartclk = CLOCK_TICK_RATE * 16, + .uartclk = KS8695_CLOCK_RATE * 16, .fifosize = 16, .ops = &ks8695uart_pops, .flags = ASYNC_BOOT_AUTOCONF, diff --git a/drivers/watchdog/ks8695_wdt.c b/drivers/watchdog/ks8695_wdt.c index 00b03eb43bf..e1c82769b08 100644 --- a/drivers/watchdog/ks8695_wdt.c +++ b/drivers/watchdog/ks8695_wdt.c @@ -66,7 +66,7 @@ static inline void ks8695_wdt_stop(void) static inline void ks8695_wdt_start(void) { unsigned long tmcon; - unsigned long tval = wdt_time * CLOCK_TICK_RATE; + unsigned long tval = wdt_time * KS8695_CLOCK_RATE; spin_lock(&ks8695_lock); /* disable timer0 */ @@ -103,7 +103,7 @@ static inline void ks8695_wdt_reload(void) static int ks8695_wdt_settimeout(int new_time) { /* - * All counting occurs at SLOW_CLOCK / 128 = 0.256 Hz + * All counting occurs at KS8695_CLOCK_RATE / 128 = 0.256 Hz * * Since WDV is a 16-bit counter, the maximum period is * 65536 / 0.256 = 256 seconds. -- cgit v1.2.3-70-g09d2 From 5946fa3d5cdeb846a647a1900026af9f8b08c8b5 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 19 Aug 2009 08:44:24 +0100 Subject: x86, hpet: Simplify the HPET code On 64-bits, using unsigned long when unsigned int suffices needlessly creates larger code (due to the need for REX prefixes), and most of the logic in hpet.c really doesn't need 64-bit operations. At once this avoids the need for a couple of type casts. Signed-off-by: Jan Beulich Cc: Shaohua Li Cc: Venkatesh Pallipadi LKML-Reference: <4A8BC9780200007800010832@vpn.id2.novell.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/hpet.h | 2 +- arch/x86/kernel/hpet.c | 45 +++++++++++++++++++++++---------------------- 2 files changed, 24 insertions(+), 23 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 1c22cb05ad6..65847c578b7 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -69,7 +69,7 @@ extern int hpet_force_user; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); -extern unsigned long hpet_readl(unsigned long a); +extern unsigned int hpet_readl(unsigned int a); extern void force_hpet_resume(void); extern void hpet_msi_unmask(unsigned int irq); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 5969e1078fc..ba575f0f2e3 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -47,12 +47,12 @@ struct hpet_dev { char name[10]; }; -unsigned long hpet_readl(unsigned long a) +inline unsigned int hpet_readl(unsigned int a) { return readl(hpet_virt_address + a); } -static inline void hpet_writel(unsigned long d, unsigned long a) +static inline void hpet_writel(unsigned int d, unsigned int a) { writel(d, hpet_virt_address + a); } @@ -167,7 +167,7 @@ do { \ static void hpet_reserve_msi_timers(struct hpet_data *hd); -static void hpet_reserve_platform_timers(unsigned long id) +static void hpet_reserve_platform_timers(unsigned int id) { struct hpet __iomem *hpet = hpet_virt_address; struct hpet_timer __iomem *timer = &hpet->hpet_timers[2]; @@ -205,7 +205,7 @@ static void hpet_reserve_platform_timers(unsigned long id) } #else -static void hpet_reserve_platform_timers(unsigned long id) { } +static void hpet_reserve_platform_timers(unsigned int id) { } #endif /* @@ -246,7 +246,7 @@ static void hpet_reset_counter(void) static void hpet_start_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -271,7 +271,7 @@ static void hpet_resume_counter(void) static void hpet_enable_legacy_int(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); @@ -314,7 +314,7 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg, cmp, now; + unsigned int cfg, cmp, now; uint64_t delta; switch (mode) { @@ -323,7 +323,7 @@ static void hpet_set_mode(enum clock_event_mode mode, delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; + cmp = now + (unsigned int) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; @@ -339,7 +339,7 @@ static void hpet_set_mode(enum clock_event_mode mode, * (See AMD-8111 HyperTransport I/O Hub Data Sheet, * Publication # 24674) */ - hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); hpet_start_counter(); hpet_print_config(); break; @@ -387,9 +387,9 @@ static int hpet_next_event(unsigned long delta, * what we wrote hit the chip before we compare it to the * counter. */ - WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); + WARN_ON_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt); - return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; + return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, @@ -415,7 +415,7 @@ static struct hpet_dev *hpet_devs; void hpet_msi_unmask(unsigned int irq) { struct hpet_dev *hdev = get_irq_data(irq); - unsigned long cfg; + unsigned int cfg; /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); @@ -425,7 +425,7 @@ void hpet_msi_unmask(unsigned int irq) void hpet_msi_mask(unsigned int irq) { - unsigned long cfg; + unsigned int cfg; struct hpet_dev *hdev = get_irq_data(irq); /* mask it */ @@ -600,7 +600,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) { struct hpet_dev *hdev = &hpet_devs[num_timers_used]; - unsigned long cfg = hpet_readl(HPET_Tn_CFG(i)); + unsigned int cfg = hpet_readl(HPET_Tn_CFG(i)); /* Only consider HPET timer with MSI support */ if (!(cfg & HPET_TN_FSB_CAP)) @@ -815,7 +815,7 @@ static int hpet_clocksource_register(void) */ int __init hpet_enable(void) { - unsigned long id; + unsigned int id; int i; if (!is_hpet_capable()) @@ -933,7 +933,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { if (is_hpet_capable()) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; @@ -973,8 +973,8 @@ static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static u32 hpet_t1_cmp; -static unsigned long hpet_default_delta; -static unsigned long hpet_pie_delta; +static u32 hpet_default_delta; +static u32 hpet_pie_delta; static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; @@ -1025,7 +1025,8 @@ EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler); */ int hpet_rtc_timer_init(void) { - unsigned long cfg, cnt, delta, flags; + unsigned int cfg, cnt, delta; + unsigned long flags; if (!is_hpet_enabled()) return 0; @@ -1035,7 +1036,7 @@ int hpet_rtc_timer_init(void) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT; - hpet_default_delta = (unsigned long) clc; + hpet_default_delta = clc; } if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit) @@ -1121,7 +1122,7 @@ int hpet_set_periodic_freq(unsigned long freq) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; do_div(clc, freq); clc >>= hpet_clockevent.shift; - hpet_pie_delta = (unsigned long) clc; + hpet_pie_delta = clc; } return 1; } @@ -1135,7 +1136,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); static void hpet_rtc_timer_reinit(void) { - unsigned long cfg, delta; + unsigned int cfg, delta; int lost_ints = -1; if (unlikely(!hpet_rtc_flags)) { -- cgit v1.2.3-70-g09d2 From eb13296cfaf6c699566473669a96a38a90562384 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 13 Aug 2009 16:34:13 -0400 Subject: x86: Instruction decoder API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add x86 instruction decoder to arch-specific libraries. This decoder can decode x86 instructions used in kernel into prefix, opcode, modrm, sib, displacement and immediates. This can also show the length of instructions. This version introduces instruction attributes for decoding instructions. The instruction attribute tables are generated from the opcode map file (x86-opcode-map.txt) by the generator script(gen-insn-attr-x86.awk). Currently, the opcode maps are based on opcode maps in Intel(R) 64 and IA-32 Architectures Software Developers Manual Vol.2: Appendix.A, and consist of below two types of opcode tables. 1-byte/2-bytes/3-bytes opcodes, which has 256 elements, are written as below; Table: table-name Referrer: escaped-name opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] (or) opcode: escape # escaped-name EndTable Group opcodes, which has 8 elements, are written as below; GrpTable: GrpXXX reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] EndTable These opcode maps include a few SSE and FP opcodes (for setup), because those opcodes are used in the kernel. Signed-off-by: Masami Hiramatsu Signed-off-by: Jim Keniston Acked-by: H. Peter Anvin Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: Ingo Molnar Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090813203413.31965.49709.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/inat.h | 188 +++++++++ arch/x86/include/asm/inat_types.h | 29 ++ arch/x86/include/asm/insn.h | 143 +++++++ arch/x86/lib/Makefile | 13 + arch/x86/lib/inat.c | 78 ++++ arch/x86/lib/insn.c | 464 ++++++++++++++++++++++ arch/x86/lib/x86-opcode-map.txt | 719 +++++++++++++++++++++++++++++++++++ arch/x86/tools/gen-insn-attr-x86.awk | 314 +++++++++++++++ 8 files changed, 1948 insertions(+) create mode 100644 arch/x86/include/asm/inat.h create mode 100644 arch/x86/include/asm/inat_types.h create mode 100644 arch/x86/include/asm/insn.h create mode 100644 arch/x86/lib/inat.c create mode 100644 arch/x86/lib/insn.c create mode 100644 arch/x86/lib/x86-opcode-map.txt create mode 100644 arch/x86/tools/gen-insn-attr-x86.awk (limited to 'arch') diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h new file mode 100644 index 00000000000..2866fddd184 --- /dev/null +++ b/arch/x86/include/asm/inat.h @@ -0,0 +1,188 @@ +#ifndef _ASM_X86_INAT_H +#define _ASM_X86_INAT_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ +#include + +/* + * Internal bits. Don't use bitmasks directly, because these bits are + * unstable. You should use checking functions. + */ + +#define INAT_OPCODE_TABLE_SIZE 256 +#define INAT_GROUP_TABLE_SIZE 8 + +/* Legacy instruction prefixes */ +#define INAT_PFX_OPNDSZ 1 /* 0x66 */ /* LPFX1 */ +#define INAT_PFX_REPNE 2 /* 0xF2 */ /* LPFX2 */ +#define INAT_PFX_REPE 3 /* 0xF3 */ /* LPFX3 */ +#define INAT_PFX_LOCK 4 /* 0xF0 */ +#define INAT_PFX_CS 5 /* 0x2E */ +#define INAT_PFX_DS 6 /* 0x3E */ +#define INAT_PFX_ES 7 /* 0x26 */ +#define INAT_PFX_FS 8 /* 0x64 */ +#define INAT_PFX_GS 9 /* 0x65 */ +#define INAT_PFX_SS 10 /* 0x36 */ +#define INAT_PFX_ADDRSZ 11 /* 0x67 */ + +#define INAT_LPREFIX_MAX 3 + +/* Immediate size */ +#define INAT_IMM_BYTE 1 +#define INAT_IMM_WORD 2 +#define INAT_IMM_DWORD 3 +#define INAT_IMM_QWORD 4 +#define INAT_IMM_PTR 5 +#define INAT_IMM_VWORD32 6 +#define INAT_IMM_VWORD 7 + +/* Legacy prefix */ +#define INAT_PFX_OFFS 0 +#define INAT_PFX_BITS 4 +#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) +#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) +/* Escape opcodes */ +#define INAT_ESC_OFFS (INAT_PFX_OFFS + INAT_PFX_BITS) +#define INAT_ESC_BITS 2 +#define INAT_ESC_MAX ((1 << INAT_ESC_BITS) - 1) +#define INAT_ESC_MASK (INAT_ESC_MAX << INAT_ESC_OFFS) +/* Group opcodes (1-16) */ +#define INAT_GRP_OFFS (INAT_ESC_OFFS + INAT_ESC_BITS) +#define INAT_GRP_BITS 5 +#define INAT_GRP_MAX ((1 << INAT_GRP_BITS) - 1) +#define INAT_GRP_MASK (INAT_GRP_MAX << INAT_GRP_OFFS) +/* Immediates */ +#define INAT_IMM_OFFS (INAT_GRP_OFFS + INAT_GRP_BITS) +#define INAT_IMM_BITS 3 +#define INAT_IMM_MASK (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS) +/* Flags */ +#define INAT_FLAG_OFFS (INAT_IMM_OFFS + INAT_IMM_BITS) +#define INAT_REXPFX (1 << INAT_FLAG_OFFS) +#define INAT_MODRM (1 << (INAT_FLAG_OFFS + 1)) +#define INAT_FORCE64 (1 << (INAT_FLAG_OFFS + 2)) +#define INAT_SCNDIMM (1 << (INAT_FLAG_OFFS + 3)) +#define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 4)) +#define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 5)) +/* Attribute making macros for attribute tables */ +#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) +#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) +#define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) +#define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) + +/* Attribute search APIs */ +extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); +extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, + insn_byte_t last_pfx, + insn_attr_t esc_attr); +extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, + insn_byte_t last_pfx, + insn_attr_t esc_attr); + +/* Attribute checking functions */ +static inline int inat_is_prefix(insn_attr_t attr) +{ + return attr & INAT_PFX_MASK; +} + +static inline int inat_is_address_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ; +} + +static inline int inat_is_operand_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ; +} + +static inline int inat_last_prefix_id(insn_attr_t attr) +{ + if ((attr & INAT_PFX_MASK) > INAT_LPREFIX_MAX) + return 0; + else + return attr & INAT_PFX_MASK; +} + +static inline int inat_is_escape(insn_attr_t attr) +{ + return attr & INAT_ESC_MASK; +} + +static inline int inat_escape_id(insn_attr_t attr) +{ + return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS; +} + +static inline int inat_is_group(insn_attr_t attr) +{ + return attr & INAT_GRP_MASK; +} + +static inline int inat_group_id(insn_attr_t attr) +{ + return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS; +} + +static inline int inat_group_common_attribute(insn_attr_t attr) +{ + return attr & ~INAT_GRP_MASK; +} + +static inline int inat_has_immediate(insn_attr_t attr) +{ + return attr & INAT_IMM_MASK; +} + +static inline int inat_immediate_size(insn_attr_t attr) +{ + return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS; +} + +static inline int inat_is_rex_prefix(insn_attr_t attr) +{ + return attr & INAT_REXPFX; +} + +static inline int inat_has_modrm(insn_attr_t attr) +{ + return attr & INAT_MODRM; +} + +static inline int inat_is_force64(insn_attr_t attr) +{ + return attr & INAT_FORCE64; +} + +static inline int inat_has_second_immediate(insn_attr_t attr) +{ + return attr & INAT_SCNDIMM; +} + +static inline int inat_has_moffset(insn_attr_t attr) +{ + return attr & INAT_MOFFSET; +} + +static inline int inat_has_variant(insn_attr_t attr) +{ + return attr & INAT_VARIANT; +} + +#endif diff --git a/arch/x86/include/asm/inat_types.h b/arch/x86/include/asm/inat_types.h new file mode 100644 index 00000000000..cb3c20ce39c --- /dev/null +++ b/arch/x86/include/asm/inat_types.h @@ -0,0 +1,29 @@ +#ifndef _ASM_X86_INAT_TYPES_H +#define _ASM_X86_INAT_TYPES_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +/* Instruction attributes */ +typedef unsigned int insn_attr_t; +typedef unsigned char insn_byte_t; +typedef signed int insn_value_t; + +#endif diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h new file mode 100644 index 00000000000..12b4e3751d3 --- /dev/null +++ b/arch/x86/include/asm/insn.h @@ -0,0 +1,143 @@ +#ifndef _ASM_X86_INSN_H +#define _ASM_X86_INSN_H +/* + * x86 instruction analysis + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2009 + */ + +/* insn_attr_t is defined in inat.h */ +#include + +struct insn_field { + union { + insn_value_t value; + insn_byte_t bytes[4]; + }; + /* !0 if we've run insn_get_xxx() for this field */ + unsigned char got; + unsigned char nbytes; +}; + +struct insn { + struct insn_field prefixes; /* + * Prefixes + * prefixes.bytes[3]: last prefix + */ + struct insn_field rex_prefix; /* REX prefix */ + struct insn_field opcode; /* + * opcode.bytes[0]: opcode1 + * opcode.bytes[1]: opcode2 + * opcode.bytes[2]: opcode3 + */ + struct insn_field modrm; + struct insn_field sib; + struct insn_field displacement; + union { + struct insn_field immediate; + struct insn_field moffset1; /* for 64bit MOV */ + struct insn_field immediate1; /* for 64bit imm or off16/32 */ + }; + union { + struct insn_field moffset2; /* for 64bit MOV */ + struct insn_field immediate2; /* for 64bit imm or seg16 */ + }; + + insn_attr_t attr; + unsigned char opnd_bytes; + unsigned char addr_bytes; + unsigned char length; + unsigned char x86_64; + + const insn_byte_t *kaddr; /* kernel address of insn to analyze */ + const insn_byte_t *next_byte; +}; + +#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) +#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) +#define X86_MODRM_RM(modrm) ((modrm) & 0x07) + +#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6) +#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3) +#define X86_SIB_BASE(sib) ((sib) & 0x07) + +#define X86_REX_W(rex) ((rex) & 8) +#define X86_REX_R(rex) ((rex) & 4) +#define X86_REX_X(rex) ((rex) & 2) +#define X86_REX_B(rex) ((rex) & 1) + +/* The last prefix is needed for two-byte and three-byte opcodes */ +static inline insn_byte_t insn_last_prefix(struct insn *insn) +{ + return insn->prefixes.bytes[3]; +} + +extern void insn_init(struct insn *insn, const void *kaddr, int x86_64); +extern void insn_get_prefixes(struct insn *insn); +extern void insn_get_opcode(struct insn *insn); +extern void insn_get_modrm(struct insn *insn); +extern void insn_get_sib(struct insn *insn); +extern void insn_get_displacement(struct insn *insn); +extern void insn_get_immediate(struct insn *insn); +extern void insn_get_length(struct insn *insn); + +/* Attribute will be determined after getting ModRM (for opcode groups) */ +static inline void insn_get_attribute(struct insn *insn) +{ + insn_get_modrm(insn); +} + +/* Instruction uses RIP-relative addressing */ +extern int insn_rip_relative(struct insn *insn); + +/* Init insn for kernel text */ +static inline void kernel_insn_init(struct insn *insn, const void *kaddr) +{ +#ifdef CONFIG_X86_64 + insn_init(insn, kaddr, 1); +#else /* CONFIG_X86_32 */ + insn_init(insn, kaddr, 0); +#endif +} + +/* Offset of each field from kaddr */ +static inline int insn_offset_rex_prefix(struct insn *insn) +{ + return insn->prefixes.nbytes; +} +static inline int insn_offset_opcode(struct insn *insn) +{ + return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes; +} +static inline int insn_offset_modrm(struct insn *insn) +{ + return insn_offset_opcode(insn) + insn->opcode.nbytes; +} +static inline int insn_offset_sib(struct insn *insn) +{ + return insn_offset_modrm(insn) + insn->modrm.nbytes; +} +static inline int insn_offset_displacement(struct insn *insn) +{ + return insn_offset_sib(insn) + insn->sib.nbytes; +} +static inline int insn_offset_immediate(struct insn *insn) +{ + return insn_offset_displacement(insn) + insn->displacement.nbytes; +} + +#endif /* _ASM_X86_INSN_H */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 07c31899c9c..c77f8a7c531 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -2,12 +2,25 @@ # Makefile for x86 specific library files. # +inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk +inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt +quiet_cmd_inat_tables = GEN $@ + cmd_inat_tables = $(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ + +$(obj)/inat-tables.c: $(inat_tables_script) $(inat_tables_maps) + $(call cmd,inat_tables) + +$(obj)/inat.o: $(obj)/inat-tables.c + +clean-files := inat-tables.c + obj-$(CONFIG_SMP) := msr.o lib-y := delay.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-y += insn.o inat.o ifeq ($(CONFIG_X86_32),y) obj-y += atomic64_32.o diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c new file mode 100644 index 00000000000..054656a01df --- /dev/null +++ b/arch/x86/lib/inat.c @@ -0,0 +1,78 @@ +/* + * x86 instruction attribute tables + * + * Written by Masami Hiramatsu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ +#include + +/* Attribute tables are generated from opcode map */ +#include "inat-tables.c" + +/* Attribute search APIs */ +insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode) +{ + return inat_primary_table[opcode]; +} + +insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx, + insn_attr_t esc_attr) +{ + const insn_attr_t *table; + insn_attr_t lpfx_attr; + int n, m = 0; + + n = inat_escape_id(esc_attr); + if (last_pfx) { + lpfx_attr = inat_get_opcode_attribute(last_pfx); + m = inat_last_prefix_id(lpfx_attr); + } + table = inat_escape_tables[n][0]; + if (!table) + return 0; + if (inat_has_variant(table[opcode]) && m) { + table = inat_escape_tables[n][m]; + if (!table) + return 0; + } + return table[opcode]; +} + +insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx, + insn_attr_t grp_attr) +{ + const insn_attr_t *table; + insn_attr_t lpfx_attr; + int n, m = 0; + + n = inat_group_id(grp_attr); + if (last_pfx) { + lpfx_attr = inat_get_opcode_attribute(last_pfx); + m = inat_last_prefix_id(lpfx_attr); + } + table = inat_group_tables[n][0]; + if (!table) + return inat_group_common_attribute(grp_attr); + if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) { + table = inat_escape_tables[n][m]; + if (!table) + return inat_group_common_attribute(grp_attr); + } + return table[X86_MODRM_REG(modrm)] | + inat_group_common_attribute(grp_attr); +} + diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c new file mode 100644 index 00000000000..dfd56a30053 --- /dev/null +++ b/arch/x86/lib/insn.c @@ -0,0 +1,464 @@ +/* + * x86 instruction analysis + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004, 2009 + */ + +#include +#include +#include + +#define get_next(t, insn) \ + ({t r; r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) + +#define peek_next(t, insn) \ + ({t r; r = *(t*)insn->next_byte; r; }) + +/** + * insn_init() - initialize struct insn + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @x86_64: !0 for 64-bit kernel or 64-bit app + */ +void insn_init(struct insn *insn, const void *kaddr, int x86_64) +{ + memset(insn, 0, sizeof(*insn)); + insn->kaddr = kaddr; + insn->next_byte = kaddr; + insn->x86_64 = x86_64 ? 1 : 0; + insn->opnd_bytes = 4; + if (x86_64) + insn->addr_bytes = 8; + else + insn->addr_bytes = 4; +} + +/** + * insn_get_prefixes - scan x86 instruction prefix bytes + * @insn: &struct insn containing instruction + * + * Populates the @insn->prefixes bitmap, and updates @insn->next_byte + * to point to the (first) opcode. No effect if @insn->prefixes.got + * is already set. + */ +void insn_get_prefixes(struct insn *insn) +{ + struct insn_field *prefixes = &insn->prefixes; + insn_attr_t attr; + insn_byte_t b, lb; + int i, nb; + + if (prefixes->got) + return; + + nb = 0; + lb = 0; + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + while (inat_is_prefix(attr)) { + /* Skip if same prefix */ + for (i = 0; i < nb; i++) + if (prefixes->bytes[i] == b) + goto found; + if (nb == 4) + /* Invalid instruction */ + break; + prefixes->bytes[nb++] = b; + if (inat_is_address_size_prefix(attr)) { + /* address size switches 2/4 or 4/8 */ + if (insn->x86_64) + insn->addr_bytes ^= 12; + else + insn->addr_bytes ^= 6; + } else if (inat_is_operand_size_prefix(attr)) { + /* oprand size switches 2/4 */ + insn->opnd_bytes ^= 6; + } +found: + prefixes->nbytes++; + insn->next_byte++; + lb = b; + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + } + /* Set the last prefix */ + if (lb && lb != insn->prefixes.bytes[3]) { + if (unlikely(insn->prefixes.bytes[3])) { + /* Swap the last prefix */ + b = insn->prefixes.bytes[3]; + for (i = 0; i < nb; i++) + if (prefixes->bytes[i] == lb) + prefixes->bytes[i] = b; + } + insn->prefixes.bytes[3] = lb; + } + + if (insn->x86_64) { + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + if (inat_is_rex_prefix(attr)) { + insn->rex_prefix.value = b; + insn->rex_prefix.nbytes = 1; + insn->next_byte++; + if (X86_REX_W(b)) + /* REX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } + } + insn->rex_prefix.got = 1; + prefixes->got = 1; + return; +} + +/** + * insn_get_opcode - collect opcode(s) + * @insn: &struct insn containing instruction + * + * Populates @insn->opcode, updates @insn->next_byte to point past the + * opcode byte(s), and set @insn->attr (except for groups). + * If necessary, first collects any preceding (prefix) bytes. + * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got + * is already 1. + */ +void insn_get_opcode(struct insn *insn) +{ + struct insn_field *opcode = &insn->opcode; + insn_byte_t op, pfx; + if (opcode->got) + return; + if (!insn->prefixes.got) + insn_get_prefixes(insn); + + /* Get first opcode */ + op = get_next(insn_byte_t, insn); + opcode->bytes[0] = op; + opcode->nbytes = 1; + insn->attr = inat_get_opcode_attribute(op); + while (inat_is_escape(insn->attr)) { + /* Get escaped opcode */ + op = get_next(insn_byte_t, insn); + opcode->bytes[opcode->nbytes++] = op; + pfx = insn_last_prefix(insn); + insn->attr = inat_get_escape_attribute(op, pfx, insn->attr); + } + opcode->got = 1; +} + +/** + * insn_get_modrm - collect ModRM byte, if any + * @insn: &struct insn containing instruction + * + * Populates @insn->modrm and updates @insn->next_byte to point past the + * ModRM byte, if any. If necessary, first collects the preceding bytes + * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + */ +void insn_get_modrm(struct insn *insn) +{ + struct insn_field *modrm = &insn->modrm; + insn_byte_t pfx, mod; + if (modrm->got) + return; + if (!insn->opcode.got) + insn_get_opcode(insn); + + if (inat_has_modrm(insn->attr)) { + mod = get_next(insn_byte_t, insn); + modrm->value = mod; + modrm->nbytes = 1; + if (inat_is_group(insn->attr)) { + pfx = insn_last_prefix(insn); + insn->attr = inat_get_group_attribute(mod, pfx, + insn->attr); + } + } + + if (insn->x86_64 && inat_is_force64(insn->attr)) + insn->opnd_bytes = 8; + modrm->got = 1; +} + + +/** + * insn_rip_relative() - Does instruction use RIP-relative addressing mode? + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * ModRM byte. No effect if @insn->x86_64 is 0. + */ +int insn_rip_relative(struct insn *insn) +{ + struct insn_field *modrm = &insn->modrm; + + if (!insn->x86_64) + return 0; + if (!modrm->got) + insn_get_modrm(insn); + /* + * For rip-relative instructions, the mod field (top 2 bits) + * is zero and the r/m field (bottom 3 bits) is 0x5. + */ + return (modrm->nbytes && (modrm->value & 0xc7) == 0x5); +} + +/** + * insn_get_sib() - Get the SIB byte of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * ModRM byte. + */ +void insn_get_sib(struct insn *insn) +{ + insn_byte_t modrm; + + if (insn->sib.got) + return; + if (!insn->modrm.got) + insn_get_modrm(insn); + if (insn->modrm.nbytes) { + modrm = (insn_byte_t)insn->modrm.value; + if (insn->addr_bytes != 2 && + X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) { + insn->sib.value = get_next(insn_byte_t, insn); + insn->sib.nbytes = 1; + } + } + insn->sib.got = 1; +} + + +/** + * insn_get_displacement() - Get the displacement of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * SIB byte. + * Displacement value is sign-expanded. + */ +void insn_get_displacement(struct insn *insn) +{ + insn_byte_t mod, rm, base; + + if (insn->displacement.got) + return; + if (!insn->sib.got) + insn_get_sib(insn); + if (insn->modrm.nbytes) { + /* + * Interpreting the modrm byte: + * mod = 00 - no displacement fields (exceptions below) + * mod = 01 - 1-byte displacement field + * mod = 10 - displacement field is 4 bytes, or 2 bytes if + * address size = 2 (0x67 prefix in 32-bit mode) + * mod = 11 - no memory operand + * + * If address size = 2... + * mod = 00, r/m = 110 - displacement field is 2 bytes + * + * If address size != 2... + * mod != 11, r/m = 100 - SIB byte exists + * mod = 00, SIB base = 101 - displacement field is 4 bytes + * mod = 00, r/m = 101 - rip-relative addressing, displacement + * field is 4 bytes + */ + mod = X86_MODRM_MOD(insn->modrm.value); + rm = X86_MODRM_RM(insn->modrm.value); + base = X86_SIB_BASE(insn->sib.value); + if (mod == 3) + goto out; + if (mod == 1) { + insn->displacement.value = get_next(char, insn); + insn->displacement.nbytes = 1; + } else if (insn->addr_bytes == 2) { + if ((mod == 0 && rm == 6) || mod == 2) { + insn->displacement.value = + get_next(short, insn); + insn->displacement.nbytes = 2; + } + } else { + if ((mod == 0 && rm == 5) || mod == 2 || + (mod == 0 && base == 5)) { + insn->displacement.value = get_next(int, insn); + insn->displacement.nbytes = 4; + } + } + } +out: + insn->displacement.got = 1; +} + +/* Decode moffset16/32/64 */ +static void __get_moffset(struct insn *insn) +{ + switch (insn->addr_bytes) { + case 2: + insn->moffset1.value = get_next(short, insn); + insn->moffset1.nbytes = 2; + break; + case 4: + insn->moffset1.value = get_next(int, insn); + insn->moffset1.nbytes = 4; + break; + case 8: + insn->moffset1.value = get_next(int, insn); + insn->moffset1.nbytes = 4; + insn->moffset2.value = get_next(int, insn); + insn->moffset2.nbytes = 4; + break; + } + insn->moffset1.got = insn->moffset2.got = 1; +} + +/* Decode imm v32(Iz) */ +static void __get_immv32(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate.value = get_next(short, insn); + insn->immediate.nbytes = 2; + break; + case 4: + case 8: + insn->immediate.value = get_next(int, insn); + insn->immediate.nbytes = 4; + break; + } +} + +/* Decode imm v64(Iv/Ov) */ +static void __get_immv(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate1.value = get_next(short, insn); + insn->immediate1.nbytes = 2; + break; + case 4: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + break; + case 8: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + insn->immediate2.value = get_next(int, insn); + insn->immediate2.nbytes = 4; + break; + } + insn->immediate1.got = insn->immediate2.got = 1; +} + +/* Decode ptr16:16/32(Ap) */ +static void __get_immptr(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate1.value = get_next(short, insn); + insn->immediate1.nbytes = 2; + break; + case 4: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + break; + case 8: + /* ptr16:64 is not exist (no segment) */ + return; + } + insn->immediate2.value = get_next(unsigned short, insn); + insn->immediate2.nbytes = 2; + insn->immediate1.got = insn->immediate2.got = 1; +} + +/** + * insn_get_immediate() - Get the immediates of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * displacement bytes. + * Basically, most of immediates are sign-expanded. Unsigned-value can be + * get by bit masking with ((1 << (nbytes * 8)) - 1) + */ +void insn_get_immediate(struct insn *insn) +{ + if (insn->immediate.got) + return; + if (!insn->displacement.got) + insn_get_displacement(insn); + + if (inat_has_moffset(insn->attr)) { + __get_moffset(insn); + goto done; + } + + if (!inat_has_immediate(insn->attr)) + /* no immediates */ + goto done; + + switch (inat_immediate_size(insn->attr)) { + case INAT_IMM_BYTE: + insn->immediate.value = get_next(char, insn); + insn->immediate.nbytes = 1; + break; + case INAT_IMM_WORD: + insn->immediate.value = get_next(short, insn); + insn->immediate.nbytes = 2; + break; + case INAT_IMM_DWORD: + insn->immediate.value = get_next(int, insn); + insn->immediate.nbytes = 4; + break; + case INAT_IMM_QWORD: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + insn->immediate2.value = get_next(int, insn); + insn->immediate2.nbytes = 4; + break; + case INAT_IMM_PTR: + __get_immptr(insn); + break; + case INAT_IMM_VWORD32: + __get_immv32(insn); + break; + case INAT_IMM_VWORD: + __get_immv(insn); + break; + default: + break; + } + if (inat_has_second_immediate(insn->attr)) { + insn->immediate2.value = get_next(char, insn); + insn->immediate2.nbytes = 1; + } +done: + insn->immediate.got = 1; +} + +/** + * insn_get_length() - Get the length of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * immediates bytes. + */ +void insn_get_length(struct insn *insn) +{ + if (insn->length) + return; + if (!insn->immediate.got) + insn_get_immediate(insn); + insn->length = (unsigned char)((unsigned long)insn->next_byte + - (unsigned long)insn->kaddr); +} diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt new file mode 100644 index 00000000000..083dd59dd74 --- /dev/null +++ b/arch/x86/lib/x86-opcode-map.txt @@ -0,0 +1,719 @@ +# x86 Opcode Maps +# +# +# Table: table-name +# Referrer: escaped-name +# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] +# (or) +# opcode: escape # escaped-name +# EndTable +# +# +# GrpTable: GrpXXX +# reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] +# EndTable +# + +Table: one byte opcode +Referrer: +# 0x00 - 0x0f +00: ADD Eb,Gb +01: ADD Ev,Gv +02: ADD Gb,Eb +03: ADD Gv,Ev +04: ADD AL,Ib +05: ADD rAX,Iz +06: PUSH ES (i64) +07: POP ES (i64) +08: OR Eb,Gb +09: OR Ev,Gv +0a: OR Gb,Eb +0b: OR Gv,Ev +0c: OR AL,Ib +0d: OR rAX,Iz +0e: PUSH CS (i64) +0f: escape # 2-byte escape +# 0x10 - 0x1f +10: ADC Eb,Gb +11: ADC Ev,Gv +12: ADC Gb,Eb +13: ADC Gv,Ev +14: ADC AL,Ib +15: ADC rAX,Iz +16: PUSH SS (i64) +17: POP SS (i64) +18: SBB Eb,Gb +19: SBB Ev,Gv +1a: SBB Gb,Eb +1b: SBB Gv,Ev +1c: SBB AL,Ib +1d: SBB rAX,Iz +1e: PUSH DS (i64) +1f: POP DS (i64) +# 0x20 - 0x2f +20: AND Eb,Gb +21: AND Ev,Gv +22: AND Gb,Eb +23: AND Gv,Ev +24: AND AL,Ib +25: AND rAx,Iz +26: SEG=ES (Prefix) +27: DAA (i64) +28: SUB Eb,Gb +29: SUB Ev,Gv +2a: SUB Gb,Eb +2b: SUB Gv,Ev +2c: SUB AL,Ib +2d: SUB rAX,Iz +2e: SEG=CS (Prefix) +2f: DAS (i64) +# 0x30 - 0x3f +30: XOR Eb,Gb +31: XOR Ev,Gv +32: XOR Gb,Eb +33: XOR Gv,Ev +34: XOR AL,Ib +35: XOR rAX,Iz +36: SEG=SS (Prefix) +37: AAA (i64) +38: CMP Eb,Gb +39: CMP Ev,Gv +3a: CMP Gb,Eb +3b: CMP Gv,Ev +3c: CMP AL,Ib +3d: CMP rAX,Iz +3e: SEG=DS (Prefix) +3f: AAS (i64) +# 0x40 - 0x4f +40: INC eAX (i64) | REX (o64) +41: INC eCX (i64) | REX.B (o64) +42: INC eDX (i64) | REX.X (o64) +43: INC eBX (i64) | REX.XB (o64) +44: INC eSP (i64) | REX.R (o64) +45: INC eBP (i64) | REX.RB (o64) +46: INC eSI (i64) | REX.RX (o64) +47: INC eDI (i64) | REX.RXB (o64) +48: DEC eAX (i64) | REX.W (o64) +49: DEC eCX (i64) | REX.WB (o64) +4a: DEC eDX (i64) | REX.WX (o64) +4b: DEC eBX (i64) | REX.WXB (o64) +4c: DEC eSP (i64) | REX.WR (o64) +4d: DEC eBP (i64) | REX.WRB (o64) +4e: DEC eSI (i64) | REX.WRX (o64) +4f: DEC eDI (i64) | REX.WRXB (o64) +# 0x50 - 0x5f +50: PUSH rAX/r8 (d64) +51: PUSH rCX/r9 (d64) +52: PUSH rDX/r10 (d64) +53: PUSH rBX/r11 (d64) +54: PUSH rSP/r12 (d64) +55: PUSH rBP/r13 (d64) +56: PUSH rSI/r14 (d64) +57: PUSH rDI/r15 (d64) +58: POP rAX/r8 (d64) +59: POP rCX/r9 (d64) +5a: POP rDX/r10 (d64) +5b: POP rBX/r11 (d64) +5c: POP rSP/r12 (d64) +5d: POP rBP/r13 (d64) +5e: POP rSI/r14 (d64) +5f: POP rDI/r15 (d64) +# 0x60 - 0x6f +60: PUSHA/PUSHAD (i64) +61: POPA/POPAD (i64) +62: BOUND Gv,Ma (i64) +63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) +64: SEG=FS (Prefix) +65: SEG=GS (Prefix) +66: Operand-Size (Prefix) +67: Address-Size (Prefix) +68: PUSH Iz (d64) +69: IMUL Gv,Ev,Iz +6a: PUSH Ib (d64) +6b: IMUL Gv,Ev,Ib +6c: INS/INSB Yb,DX +6d: INS/INSW/INSD Yz,DX +6e: OUTS/OUTSB DX,Xb +6f: OUTS/OUTSW/OUTSD DX,Xz +# 0x70 - 0x7f +70: JO Jb +71: JNO Jb +72: JB/JNAE/JC Jb +73: JNB/JAE/JNC Jb +74: JZ/JE Jb +75: JNZ/JNE Jb +76: JBE/JNA Jb +77: JNBE/JA Jb +78: JS Jb +79: JNS Jb +7a: JP/JPE Jb +7b: JNP/JPO Jb +7c: JL/JNGE Jb +7d: JNL/JGE Jb +7e: JLE/JNG Jb +7f: JNLE/JG Jb +# 0x80 - 0x8f +80: Grp1 Eb,Ib (1A) +81: Grp1 Ev,Iz (1A) +82: Grp1 Eb,Ib (1A),(i64) +83: Grp1 Ev,Ib (1A) +84: TEST Eb,Gb +85: TEST Ev,Gv +86: XCHG Eb,Gb +87: XCHG Ev,Gv +88: MOV Eb,Gb +89: MOV Ev,Gv +8a: MOV Gb,Eb +8b: MOV Gv,Ev +8c: MOV Ev,Sw +8d: LEA Gv,M +8e: MOV Sw,Ew +8f: Grp1A (1A) | POP Ev (d64) +# 0x90 - 0x9f +90: NOP | PAUSE (F3) | XCHG r8,rAX +91: XCHG rCX/r9,rAX +92: XCHG rDX/r10,rAX +93: XCHG rBX/r11,rAX +94: XCHG rSP/r12,rAX +95: XCHG rBP/r13,rAX +96: XCHG rSI/r14,rAX +97: XCHG rDI/r15,rAX +98: CBW/CWDE/CDQE +99: CWD/CDQ/CQO +9a: CALLF Ap (i64) +9b: FWAIT/WAIT +9c: PUSHF/D/Q Fv (d64) +9d: POPF/D/Q Fv (d64) +9e: SAHF +9f: LAHF +# 0xa0 - 0xaf +a0: MOV AL,Ob +a1: MOV rAX,Ov +a2: MOV Ob,AL +a3: MOV Ov,rAX +a4: MOVS/B Xb,Yb +a5: MOVS/W/D/Q Xv,Yv +a6: CMPS/B Xb,Yb +a7: CMPS/W/D Xv,Yv +a8: TEST AL,Ib +a9: TEST rAX,Iz +aa: STOS/B Yb,AL +ab: STOS/W/D/Q Yv,rAX +ac: LODS/B AL,Xb +ad: LODS/W/D/Q rAX,Xv +ae: SCAS/B AL,Yb +af: SCAS/W/D/Q rAX,Xv +# 0xb0 - 0xbf +b0: MOV AL/R8L,Ib +b1: MOV CL/R9L,Ib +b2: MOV DL/R10L,Ib +b3: MOV BL/R11L,Ib +b4: MOV AH/R12L,Ib +b5: MOV CH/R13L,Ib +b6: MOV DH/R14L,Ib +b7: MOV BH/R15L,Ib +b8: MOV rAX/r8,Iv +b9: MOV rCX/r9,Iv +ba: MOV rDX/r10,Iv +bb: MOV rBX/r11,Iv +bc: MOV rSP/r12,Iv +bd: MOV rBP/r13,Iv +be: MOV rSI/r14,Iv +bf: MOV rDI/r15,Iv +# 0xc0 - 0xcf +c0: Grp2 Eb,Ib (1A) +c1: Grp2 Ev,Ib (1A) +c2: RETN Iw (f64) +c3: RETN +c4: LES Gz,Mp (i64) +c5: LDS Gz,Mp (i64) +c6: Grp11 Eb,Ib (1A) +c7: Grp11 Ev,Iz (1A) +c8: ENTER Iw,Ib +c9: LEAVE (d64) +ca: RETF Iw +cb: RETF +cc: INT3 +cd: INT Ib +ce: INTO (i64) +cf: IRET/D/Q +# 0xd0 - 0xdf +d0: Grp2 Eb,1 (1A) +d1: Grp2 Ev,1 (1A) +d2: Grp2 Eb,CL (1A) +d3: Grp2 Ev,CL (1A) +d4: AAM Ib (i64) +d5: AAD Ib (i64) +d6: +d7: XLAT/XLATB +d8: ESC +d9: ESC +da: ESC +db: ESC +dc: ESC +dd: ESC +de: ESC +df: ESC +# 0xe0 - 0xef +e0: LOOPNE/LOOPNZ Jb (f64) +e1: LOOPE/LOOPZ Jb (f64) +e2: LOOP Jb (f64) +e3: JrCXZ Jb (f64) +e4: IN AL,Ib +e5: IN eAX,Ib +e6: OUT Ib,AL +e7: OUT Ib,eAX +e8: CALL Jz (f64) +e9: JMP-near Jz (f64) +ea: JMP-far Ap (i64) +eb: JMP-short Jb (f64) +ec: IN AL,DX +ed: IN eAX,DX +ee: OUT DX,AL +ef: OUT DX,eAX +# 0xf0 - 0xff +f0: LOCK (Prefix) +f1: +f2: REPNE (Prefix) +f3: REP/REPE (Prefix) +f4: HLT +f5: CMC +f6: Grp3_1 Eb (1A) +f7: Grp3_2 Ev (1A) +f8: CLC +f9: STC +fa: CLI +fb: STI +fc: CLD +fd: STD +fe: Grp4 (1A) +ff: Grp5 (1A) +EndTable + +Table: 2-byte opcode # First Byte is 0x0f +Referrer: 2-byte escape +# 0x0f 0x00-0x0f +00: Grp6 (1A) +01: Grp7 (1A) +02: LAR Gv,Ew +03: LSL Gv,Ew +04: +05: SYSCALL (o64) +06: CLTS +07: SYSRET (o64) +08: INVD +09: WBINVD +0a: +0b: UD2 (1B) +0c: +0d: NOP Ev +0e: +0f: +# 0x0f 0x10-0x1f +10: +11: +12: +13: +14: +15: +16: +17: +18: Grp16 (1A) +19: +1a: +1b: +1c: +1d: +1e: +1f: NOP Ev +# 0x0f 0x20-0x2f +20: MOV Rd,Cd +21: MOV Rd,Dd +22: MOV Cd,Rd +23: MOV Dd,Rd +24: +25: +26: +27: +28: movaps Vps,Wps | movapd Vpd,Wpd (66) +29: movaps Wps,Vps | movapd Wpd,Vpd (66) +2a: +2b: +2c: +2d: +2e: +2f: +# 0x0f 0x30-0x3f +30: WRMSR +31: RDTSC +32: RDMSR +33: RDPMC +34: SYSENTER +35: SYSEXIT +36: +37: GETSEC +38: escape # 3-byte escape 1 +39: +3a: escape # 3-byte escape 2 +3b: +3c: +3d: +3e: +3f: +# 0x0f 0x40-0x4f +40: CMOVO Gv,Ev +41: CMOVNO Gv,Ev +42: CMOVB/C/NAE Gv,Ev +43: CMOVAE/NB/NC Gv,Ev +44: CMOVE/Z Gv,Ev +45: CMOVNE/NZ Gv,Ev +46: CMOVBE/NA Gv,Ev +47: CMOVA/NBE Gv,Ev +48: CMOVS Gv,Ev +49: CMOVNS Gv,Ev +4a: CMOVP/PE Gv,Ev +4b: CMOVNP/PO Gv,Ev +4c: CMOVL/NGE Gv,Ev +4d: CMOVNL/GE Gv,Ev +4e: CMOVLE/NG Gv,Ev +4f: CMOVNLE/G Gv,Ev +# 0x0f 0x50-0x5f +50: +51: +52: +53: +54: +55: +56: +57: +58: +59: +5a: +5b: +5c: +5d: +5e: +5f: +# 0x0f 0x60-0x6f +60: +61: +62: +63: +64: +65: +66: +67: +68: +69: +6a: +6b: +6c: +6d: +6e: +6f: +# 0x0f 0x70-0x7f +70: +71: Grp12 (1A) +72: Grp13 (1A) +73: Grp14 (1A) +74: +75: +76: +77: +78: VMREAD Ed/q,Gd/q +79: VMWRITE Gd/q,Ed/q +7a: +7b: +7c: +7d: +7e: +7f: +# 0x0f 0x80-0x8f +80: JO Jz (f64) +81: JNO Jz (f64) +82: JB/JNAE/JC Jz (f64) +83: JNB/JAE/JNC Jz (f64) +84: JZ/JE Jz (f64) +85: JNZ/JNE Jz (f64) +86: JBE/JNA Jz (f64) +87: JNBE/JA Jz (f64) +88: JS Jz (f64) +89: JNS Jz (f64) +8a: JP/JPE Jz (f64) +8b: JNP/JPO Jz (f64) +8c: JL/JNGE Jz (f64) +8d: JNL/JGE Jz (f64) +8e: JLE/JNG Jz (f64) +8f: JNLE/JG Jz (f64) +# 0x0f 0x90-0x9f +90: SETO Eb +91: SETNO Eb +92: SETB/C/NAE Eb +93: SETAE/NB/NC Eb +94: SETE/Z Eb +95: SETNE/NZ Eb +96: SETBE/NA Eb +97: SETA/NBE Eb +98: SETS Eb +99: SETNS Eb +9a: SETP/PE Eb +9b: SETNP/PO Eb +9c: SETL/NGE Eb +9d: SETNL/GE Eb +9e: SETLE/NG Eb +9f: SETNLE/G Eb +# 0x0f 0xa0-0xaf +a0: PUSH FS (d64) +a1: POP FS (d64) +a2: CPUID +a3: BT Ev,Gv +a4: SHLD Ev,Gv,Ib +a5: SHLD Ev,Gv,CL +a6: +a7: GrpRNG +a8: PUSH GS (d64) +a9: POP GS (d64) +aa: RSM +ab: BTS Ev,Gv +ac: SHRD Ev,Gv,Ib +ad: SHRD Ev,Gv,CL +ae: Grp15 (1A),(1C) +af: IMUL Gv,Ev +# 0x0f 0xb0-0xbf +b0: CMPXCHG Eb,Gb +b1: CMPXCHG Ev,Gv +b2: LSS Gv,Mp +b3: BTR Ev,Gv +b4: LFS Gv,Mp +b5: LGS Gv,Mp +b6: MOVZX Gv,Eb +b7: MOVZX Gv,Ew +b8: JMPE | POPCNT Gv,Ev (F3) +b9: Grp10 (1A) +ba: Grp8 Ev,Ib (1A) +bb: BTC Ev,Gv +bc: BSF Gv,Ev +bd: BSR Gv,Ev +be: MOVSX Gv,Eb +bf: MOVSX Gv,Ew +# 0x0f 0xc0-0xcf +c0: XADD Eb,Gb +c1: XADD Ev,Gv +c2: +c3: movnti Md/q,Gd/q +c4: +c5: +c6: +c7: Grp9 (1A) +c8: BSWAP RAX/EAX/R8/R8D +c9: BSWAP RCX/ECX/R9/R9D +ca: BSWAP RDX/EDX/R10/R10D +cb: BSWAP RBX/EBX/R11/R11D +cc: BSWAP RSP/ESP/R12/R12D +cd: BSWAP RBP/EBP/R13/R13D +ce: BSWAP RSI/ESI/R14/R14D +cf: BSWAP RDI/EDI/R15/R15D +# 0x0f 0xd0-0xdf +d0: +d1: +d2: +d3: +d4: +d5: +d6: +d7: +d8: +d9: +da: +db: +dc: +dd: +de: +df: +# 0x0f 0xe0-0xef +e0: +e1: +e2: +e3: +e4: +e5: +e6: +e7: +e8: +e9: +ea: +eb: +ec: +ed: +ee: +ef: +# 0x0f 0xf0-0xff +f0: +f1: +f2: +f3: +f4: +f5: +f6: +f7: +f8: +f9: +fa: +fb: +fc: +fd: +fe: +ff: +EndTable + +Table: 3-byte opcode 1 +Referrer: 3-byte escape 1 +80: INVEPT Gd/q,Mdq (66) +81: INVPID Gd/q,Mdq (66) +f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2) +f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2) +EndTable + +Table: 3-byte opcode 2 +Referrer: 3-byte escape 2 +# all opcode is for SSE +EndTable + +GrpTable: Grp1 +0: ADD +1: OR +2: ADC +3: SBB +4: AND +5: SUB +6: XOR +7: CMP +EndTable + +GrpTable: Grp1A +0: POP +EndTable + +GrpTable: Grp2 +0: ROL +1: ROR +2: RCL +3: RCR +4: SHL/SAL +5: SHR +6: +7: SAR +EndTable + +GrpTable: Grp3_1 +0: TEST Eb,Ib +1: +2: NOT Eb +3: NEG Eb +4: MUL AL,Eb +5: IMUL AL,Eb +6: DIV AL,Eb +7: IDIV AL,Eb +EndTable + +GrpTable: Grp3_2 +0: TEST Ev,Iz +1: +2: NOT Ev +3: NEG Ev +4: MUL rAX,Ev +5: IMUL rAX,Ev +6: DIV rAX,Ev +7: IDIV rAX,Ev +EndTable + +GrpTable: Grp4 +0: INC Eb +1: DEC Eb +EndTable + +GrpTable: Grp5 +0: INC Ev +1: DEC Ev +2: CALLN Ev (f64) +3: CALLF Ep +4: JMPN Ev (f64) +5: JMPF Ep +6: PUSH Ev (d64) +7: +EndTable + +GrpTable: Grp6 +0: SLDT Rv/Mw +1: STR Rv/Mw +2: LLDT Ew +3: LTR Ew +4: VERR Ew +5: VERW Ew +EndTable + +GrpTable: Grp7 +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) +3: LIDT Ms +4: SMSW Mw/Rv +5: +6: LMSW Ew +7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) +EndTable + +GrpTable: Grp8 +4: BT +5: BTS +6: BTR +7: BTC +EndTable + +GrpTable: Grp9 +1: CMPXCHG8B/16B Mq/Mdq +6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) +7: VMPTRST Mq +EndTable + +GrpTable: Grp10 +EndTable + +GrpTable: Grp11 +0: MOV +EndTable + +GrpTable: Grp12 +EndTable + +GrpTable: Grp13 +EndTable + +GrpTable: Grp14 +EndTable + +GrpTable: Grp15 +0: fxsave +1: fxstor +2: ldmxcsr +3: stmxcsr +4: XSAVE +5: XRSTOR | lfence (11B) +6: mfence (11B) +7: clflush | sfence (11B) +EndTable + +GrpTable: Grp16 +0: prefetch NTA +1: prefetch T0 +2: prefetch T1 +3: prefetch T2 +EndTable + +GrpTable: GrpRNG +0: xstore-rng +1: xcrypt-ecb +2: xcrypt-cbc +4: xcrypt-cfb +5: xcrypt-ofb +EndTable diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk new file mode 100644 index 00000000000..93b62c92d04 --- /dev/null +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -0,0 +1,314 @@ +#!/bin/awk -f +# gen-insn-attr-x86.awk: Instruction attribute table generator +# Written by Masami Hiramatsu +# +# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c + +BEGIN { + print "/* x86 opcode map generated from x86-opcode-map.txt */" + print "/* Do not change this code. */" + ggid = 1 + geid = 1 + + opnd_expr = "^[[:alpha:]]" + ext_expr = "^\\(" + sep_expr = "^\\|$" + group_expr = "^Grp[[:alnum:]]+" + + imm_expr = "^[IJAO][[:lower:]]" + imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" + imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" + imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)" + imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)" + imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)" + imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)" + imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" + imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" + imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)" + imm_flag["Ob"] = "INAT_MOFFSET" + imm_flag["Ov"] = "INAT_MOFFSET" + + modrm_expr = "^([CDEGMNPQRSUVW][[:lower:]]+|NTA|T[012])" + force64_expr = "\\([df]64\\)" + rex_expr = "^REX(\\.[XRWB]+)*" + fpu_expr = "^ESC" # TODO + + lprefix1_expr = "\\(66\\)" + delete lptable1 + lprefix2_expr = "\\(F2\\)" + delete lptable2 + lprefix3_expr = "\\(F3\\)" + delete lptable3 + max_lprefix = 4 + + prefix_expr = "\\(Prefix\\)" + prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" + prefix_num["REPNE"] = "INAT_PFX_REPNE" + prefix_num["REP/REPE"] = "INAT_PFX_REPE" + prefix_num["LOCK"] = "INAT_PFX_LOCK" + prefix_num["SEG=CS"] = "INAT_PFX_CS" + prefix_num["SEG=DS"] = "INAT_PFX_DS" + prefix_num["SEG=ES"] = "INAT_PFX_ES" + prefix_num["SEG=FS"] = "INAT_PFX_FS" + prefix_num["SEG=GS"] = "INAT_PFX_GS" + prefix_num["SEG=SS"] = "INAT_PFX_SS" + prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" + + delete table + delete etable + delete gtable + eid = -1 + gid = -1 +} + +function semantic_error(msg) { + print "Semantic error at " NR ": " msg > "/dev/stderr" + exit 1 +} + +function debug(msg) { + print "DEBUG: " msg +} + +function array_size(arr, i,c) { + c = 0 + for (i in arr) + c++ + return c +} + +/^Table:/ { + print "/* " $0 " */" +} + +/^Referrer:/ { + if (NF == 1) { + # primary opcode table + tname = "inat_primary_table" + eid = -1 + } else { + # escape opcode table + ref = "" + for (i = 2; i <= NF; i++) + ref = ref $i + eid = escape[ref] + tname = sprintf("inat_escape_table_%d", eid) + } +} + +/^GrpTable:/ { + print "/* " $0 " */" + if (!($2 in group)) + semantic_error("No group: " $2 ) + gid = group[$2] + tname = "inat_group_table_" gid +} + +function print_table(tbl,name,fmt,n) +{ + print "const insn_attr_t " name " = {" + for (i = 0; i < n; i++) { + id = sprintf(fmt, i) + if (tbl[id]) + print " [" id "] = " tbl[id] "," + } + print "};" +} + +/^EndTable/ { + if (gid != -1) { + # print group tables + if (array_size(table) != 0) { + print_table(table, tname "[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,0] = tname + } + if (array_size(lptable1) != 0) { + print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,1] = tname "_1" + } + if (array_size(lptable2) != 0) { + print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,2] = tname "_2" + } + if (array_size(lptable3) != 0) { + print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,3] = tname "_3" + } + } else { + # print primary/escaped tables + if (array_size(table) != 0) { + print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,0] = tname + } + if (array_size(lptable1) != 0) { + print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,1] = tname "_1" + } + if (array_size(lptable2) != 0) { + print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,2] = tname "_2" + } + if (array_size(lptable3) != 0) { + print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,3] = tname "_3" + } + } + print "" + delete table + delete lptable1 + delete lptable2 + delete lptable3 + gid = -1 + eid = -1 +} + +function add_flags(old,new) { + if (old && new) + return old " | " new + else if (old) + return old + else + return new +} + +# convert operands to flags. +function convert_operands(opnd, i,imm,mod) +{ + imm = null + mod = null + for (i in opnd) { + i = opnd[i] + if (match(i, imm_expr) == 1) { + if (!imm_flag[i]) + semantic_error("Unknown imm opnd: " i) + if (imm) { + if (i != "Ib") + semantic_error("Second IMM error") + imm = add_flags(imm, "INAT_SCNDIMM") + } else + imm = imm_flag[i] + } else if (match(i, modrm_expr)) + mod = "INAT_MODRM" + } + return add_flags(imm, mod) +} + +/^[0-9a-f]+\:/ { + if (NR == 1) + next + # get index + idx = "0x" substr($1, 1, index($1,":") - 1) + if (idx in table) + semantic_error("Redefine " idx " in " tname) + + # check if escaped opcode + if ("escape" == $2) { + if ($3 != "#") + semantic_error("No escaped name") + ref = "" + for (i = 4; i <= NF; i++) + ref = ref $i + if (ref in escape) + semantic_error("Redefine escape (" ref ")") + escape[ref] = geid + geid++ + table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")" + next + } + + variant = null + # converts + i = 2 + while (i <= NF) { + opcode = $(i++) + delete opnds + ext = null + flags = null + opnd = null + # parse one opcode + if (match($i, opnd_expr)) { + opnd = $i + split($(i++), opnds, ",") + flags = convert_operands(opnds) + } + if (match($i, ext_expr)) + ext = $(i++) + if (match($i, sep_expr)) + i++ + else if (i < NF) + semantic_error($i " is not a separator") + + # check if group opcode + if (match(opcode, group_expr)) { + if (!(opcode in group)) { + group[opcode] = ggid + ggid++ + } + flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")") + } + # check force(or default) 64bit + if (match(ext, force64_expr)) + flags = add_flags(flags, "INAT_FORCE64") + + # check REX prefix + if (match(opcode, rex_expr)) + flags = add_flags(flags, "INAT_REXPFX") + + # check coprocessor escape : TODO + if (match(opcode, fpu_expr)) + flags = add_flags(flags, "INAT_MODRM") + + # check prefixes + if (match(ext, prefix_expr)) { + if (!prefix_num[opcode]) + semantic_error("Unknown prefix: " opcode) + flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")") + } + if (length(flags) == 0) + continue + # check if last prefix + if (match(ext, lprefix1_expr)) { + lptable1[idx] = add_flags(lptable1[idx],flags) + variant = "INAT_VARIANT" + } else if (match(ext, lprefix2_expr)) { + lptable2[idx] = add_flags(lptable2[idx],flags) + variant = "INAT_VARIANT" + } else if (match(ext, lprefix3_expr)) { + lptable3[idx] = add_flags(lptable3[idx],flags) + variant = "INAT_VARIANT" + } else { + table[idx] = add_flags(table[idx],flags) + } + } + if (variant) + table[idx] = add_flags(table[idx],variant) +} + +END { + # print escape opcode map's array + print "/* Escape opcode map array */" + print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LPREFIX_MAX + 1] = {" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print " ["i"]["j"] = "etable[i,j]"," + print "};\n" + # print group opcode map's array + print "/* Group opcode map array */" + print "const insn_attr_t const *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LPREFIX_MAX + 1] = {" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print " ["i"]["j"] = "gtable[i,j]"," + print "};" +} -- cgit v1.2.3-70-g09d2 From ca0e9badd1a39fecdd235f4bf1481b9da756e27b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 13 Aug 2009 16:34:21 -0400 Subject: x86: X86 instruction decoder build-time selftest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a user-space selftest of x86 instruction decoder at kernel build time. When CONFIG_X86_DECODER_SELFTEST=y, Kbuild builds a test harness of x86 instruction decoder and performs it after building vmlinux. The test compares the results of objdump and x86 instruction decoder code and check there are no differences. Signed-off-by: Masami Hiramatsu Signed-off-by: Jim Keniston Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090813203421.31965.29006.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/Kconfig.debug | 9 ++++ arch/x86/Makefile | 3 ++ arch/x86/tools/Makefile | 15 ++++++ arch/x86/tools/distill.awk | 42 ++++++++++++++++ arch/x86/tools/test_get_len.c | 113 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 182 insertions(+) create mode 100644 arch/x86/tools/Makefile create mode 100644 arch/x86/tools/distill.awk create mode 100644 arch/x86/tools/test_get_len.c (limited to 'arch') diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d105f29bb6b..7d0b681a132 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -186,6 +186,15 @@ config X86_DS_SELFTEST config HAVE_MMIOTRACE_SUPPORT def_bool y +config X86_DECODER_SELFTEST + bool "x86 instruction decoder selftest" + depends on DEBUG_KERNEL + ---help--- + Perform x86 instruction decoder selftests at build time. + This option is useful for checking the sanity of x86 instruction + decoder code. + If unsure, say "N". + # # IO delay types: # diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1b68659c41b..5fe16bfd15a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -154,6 +154,9 @@ all: bzImage KBUILD_IMAGE := $(boot)/bzImage bzImage: vmlinux +ifeq ($(CONFIG_X86_DECODER_SELFTEST),y) + $(Q)$(MAKE) $(build)=arch/x86/tools posttest +endif $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE) $(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@ diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile new file mode 100644 index 00000000000..3dd626b99dc --- /dev/null +++ b/arch/x86/tools/Makefile @@ -0,0 +1,15 @@ +PHONY += posttest +quiet_cmd_posttest = TEST $@ + cmd_posttest = $(OBJDUMP) -d $(objtree)/vmlinux | awk -f $(srctree)/arch/x86/tools/distill.awk | $(obj)/test_get_len + +posttest: $(obj)/test_get_len vmlinux + $(call cmd,posttest) + +hostprogs-y := test_get_len + +# -I needed for generated C source and C source which in the kernel tree. +HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ + +# Dependancies are also needed. +$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c + diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/distill.awk new file mode 100644 index 00000000000..d433619bb86 --- /dev/null +++ b/arch/x86/tools/distill.awk @@ -0,0 +1,42 @@ +#!/bin/awk -f +# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len +# Distills the disassembly as follows: +# - Removes all lines except the disassembled instructions. +# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes +# into a single line. +# - Remove bad(or prefix only) instructions + +BEGIN { + prev_addr = "" + prev_hex = "" + prev_mnemonic = "" + bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))" + fwait_expr = "^9b " + fwait_str="9b\tfwait" +} + +/^ *[0-9a-f]+:/ { + if (split($0, field, "\t") < 3) { + # This is a continuation of the same insn. + prev_hex = prev_hex field[2] + } else { + # Skip bad instructions + if (match(prev_mnemonic, bad_expr)) + prev_addr = "" + # Split fwait from other f* instructions + if (match(prev_hex, fwait_expr) && prev_mnemonic != "fwait") { + printf "%s\t%s\n", prev_addr, fwait_str + sub(fwait_expr, "", prev_hex) + } + if (prev_addr != "") + printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic + prev_addr = field[1] + prev_hex = field[2] + prev_mnemonic = field[3] + } +} + +END { + if (prev_addr != "") + printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic +} diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c new file mode 100644 index 00000000000..1e81adb2d8a --- /dev/null +++ b/arch/x86/tools/test_get_len.c @@ -0,0 +1,113 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2009 + */ + +#include +#include +#include +#include + +#ifdef __x86_64__ +#define CONFIG_X86_64 +#else +#define CONFIG_X86_32 +#endif +#define unlikely(cond) (cond) + +#include +#include +#include + +/* + * Test of instruction analysis in general and insn_get_length() in + * particular. See if insn_get_length() and the disassembler agree + * on the length of each instruction in an elf disassembly. + * + * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len + */ + +const char *prog; + +static void usage(void) +{ + fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |" + " ./test_get_len\n"); + exit(1); +} + +static void malformed_line(const char *line, int line_nr) +{ + fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line); + exit(3); +} + +#define BUFSIZE 256 + +int main(int argc, char **argv) +{ + char line[BUFSIZE]; + unsigned char insn_buf[16]; + struct insn insn; + int insns = 0; + + prog = argv[0]; + if (argc > 1) + usage(); + + while (fgets(line, BUFSIZE, stdin)) { + char copy[BUFSIZE], *s, *tab1, *tab2; + int nb = 0; + unsigned int b; + + insns++; + memset(insn_buf, 0, 16); + strcpy(copy, line); + tab1 = strchr(copy, '\t'); + if (!tab1) + malformed_line(line, insns); + s = tab1 + 1; + s += strspn(s, " "); + tab2 = strchr(s, '\t'); + if (!tab2) + malformed_line(line, insns); + *tab2 = '\0'; /* Characters beyond tab2 aren't examined */ + while (s < tab2) { + if (sscanf(s, "%x", &b) == 1) { + insn_buf[nb++] = (unsigned char) b; + s += 3; + } else + break; + } + /* Decode an instruction */ +#ifdef __x86_64__ + insn_init(&insn, insn_buf, 1); +#else + insn_init(&insn, insn_buf, 0); +#endif + insn_get_length(&insn); + if (insn.length != nb) { + fprintf(stderr, "Error: %s", line); + fprintf(stderr, "Error: objdump says %d bytes, but " + "insn_get_length() says %d (attr:%x)\n", nb, + insn.length, insn.attr); + exit(2); + } + } + fprintf(stderr, "Succeed: decoded and checked %d instructions\n", + insns); + return 0; +} -- cgit v1.2.3-70-g09d2 From b46b3d70c9c017d7c4ec49f7f3ffd0af5a622277 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 13 Aug 2009 16:34:28 -0400 Subject: kprobes: Checks probe address is instruction boudary on x86 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Ensure safeness of inserting kprobes by checking whether the specified address is at the first byte of an instruction on x86. This is done by decoding probed function from its head to the probe point. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Jason Baron Cc: Jim Keniston Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090813203428.31965.21939.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/kprobes.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 7b5169d2b00..aa15f3e1f64 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -48,12 +48,14 @@ #include #include #include +#include #include #include #include #include #include +#include void jprobe_return_end(void); @@ -244,6 +246,75 @@ retry: } } +/* Recover the probed instruction at addr for further analysis. */ +static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + struct kprobe *kp; + kp = get_kprobe((void *)addr); + if (!kp) + return -EINVAL; + + /* + * Basically, kp->ainsn.insn has an original instruction. + * However, RIP-relative instruction can not do single-stepping + * at different place, fix_riprel() tweaks the displacement of + * that instruction. In that case, we can't recover the instruction + * from the kp->ainsn.insn. + * + * On the other hand, kp->opcode has a copy of the first byte of + * the probed instruction, which is overwritten by int3. And + * the instruction at kp->addr is not modified by kprobes except + * for the first byte, we can recover the original instruction + * from it and kp->opcode. + */ + memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + buf[0] = kp->opcode; + return 0; +} + +/* Dummy buffers for kallsyms_lookup */ +static char __dummy_buf[KSYM_NAME_LEN]; + +/* Check if paddr is at an instruction boundary */ +static int __kprobes can_probe(unsigned long paddr) +{ + int ret; + unsigned long addr, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf)) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + kernel_insn_init(&insn, (void *)addr); + insn_get_opcode(&insn); + + /* + * Check if the instruction has been modified by another + * kprobe, in which case we replace the breakpoint by the + * original instruction in our buffer. + */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, addr); + if (ret) + /* + * Another debugging subsystem might insert + * this breakpoint. In that case, we can't + * recover it. + */ + return 0; + kernel_insn_init(&insn, buf); + } + insn_get_length(&insn); + addr += insn.length; + } + + return (addr == paddr); +} + /* * Returns non-zero if opcode modifies the interrupt flag. */ @@ -359,6 +430,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) int __kprobes arch_prepare_kprobe(struct kprobe *p) { + if (!can_probe((unsigned long)p->addr)) + return -EILSEQ; /* insn: must be on special executable page on x86. */ p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) -- cgit v1.2.3-70-g09d2 From 89ae465b0ee470f7d3f8a1c61353445c3acbbe2a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 13 Aug 2009 16:34:36 -0400 Subject: kprobes: Cleanup fix_riprel() using insn decoder on x86 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cleanup fix_riprel() in arch/x86/kernel/kprobes.c by using the new x86 instruction decoder instead of using comparisons with raw ad hoc numeric opcodes. Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Jason Baron Cc: Jim Keniston Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090813203436.31965.34374.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/kprobes.c | 128 +++++++++------------------------------------- 1 file changed, 23 insertions(+), 105 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index aa15f3e1f64..16ae9610f6f 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -108,50 +108,6 @@ static const u32 twobyte_is_boostable[256 / 32] = { /* ----------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; -static const u32 onebyte_has_modrm[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ----------------------------------------------- */ - W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 00 */ - W(0x10, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 10 */ - W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 20 */ - W(0x30, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 30 */ - W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */ - W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */ - W(0x60, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0) | /* 60 */ - W(0x70, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 70 */ - W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ - W(0x90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 90 */ - W(0xa0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* a0 */ - W(0xb0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* b0 */ - W(0xc0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* c0 */ - W(0xd0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ - W(0xe0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* e0 */ - W(0xf0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) /* f0 */ - /* ----------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; -static const u32 twobyte_has_modrm[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ----------------------------------------------- */ - W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1) | /* 0f */ - W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0) , /* 1f */ - W(0x20, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 2f */ - W(0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 3f */ - W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 4f */ - W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 5f */ - W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 6f */ - W(0x70, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1) , /* 7f */ - W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 8f */ - W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 9f */ - W(0xa0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) | /* af */ - W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1) , /* bf */ - W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* cf */ - W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* df */ - W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* ef */ - W(0xf0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0) /* ff */ - /* ----------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; #undef W struct kretprobe_blackpoint kretprobe_blacklist[] = { @@ -348,68 +304,30 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) static void __kprobes fix_riprel(struct kprobe *p) { #ifdef CONFIG_X86_64 - u8 *insn = p->ainsn.insn; - s64 disp; - int need_modrm; - - /* Skip legacy instruction prefixes. */ - while (1) { - switch (*insn) { - case 0x66: - case 0x67: - case 0x2e: - case 0x3e: - case 0x26: - case 0x64: - case 0x65: - case 0x36: - case 0xf0: - case 0xf3: - case 0xf2: - ++insn; - continue; - } - break; - } + struct insn insn; + kernel_insn_init(&insn, p->ainsn.insn); - /* Skip REX instruction prefix. */ - if (is_REX_prefix(insn)) - ++insn; - - if (*insn == 0x0f) { - /* Two-byte opcode. */ - ++insn; - need_modrm = test_bit(*insn, - (unsigned long *)twobyte_has_modrm); - } else - /* One-byte opcode. */ - need_modrm = test_bit(*insn, - (unsigned long *)onebyte_has_modrm); - - if (need_modrm) { - u8 modrm = *++insn; - if ((modrm & 0xc7) == 0x05) { - /* %rip+disp32 addressing mode */ - /* Displacement follows ModRM byte. */ - ++insn; - /* - * The copied instruction uses the %rip-relative - * addressing mode. Adjust the displacement for the - * difference between the original location of this - * instruction and the location of the copy that will - * actually be run. The tricky bit here is making sure - * that the sign extension happens correctly in this - * calculation, since we need a signed 32-bit result to - * be sign-extended to 64 bits when it's added to the - * %rip value and yield the same 64-bit result that the - * sign-extension of the original signed 32-bit - * displacement would have given. - */ - disp = (u8 *) p->addr + *((s32 *) insn) - - (u8 *) p->ainsn.insn; - BUG_ON((s64) (s32) disp != disp); /* Sanity check. */ - *(s32 *)insn = (s32) disp; - } + if (insn_rip_relative(&insn)) { + s64 newdisp; + u8 *disp; + insn_get_displacement(&insn); + /* + * The copied instruction uses the %rip-relative addressing + * mode. Adjust the displacement for the difference between + * the original location of this instruction and the location + * of the copy that will actually be run. The tricky bit here + * is making sure that the sign extension happens correctly in + * this calculation, since we need a signed 32-bit result to + * be sign-extended to 64 bits when it's added to the %rip + * value and yield the same 64-bit result that the sign- + * extension of the original signed 32-bit displacement would + * have given. + */ + newdisp = (u8 *) p->addr + (s64) insn.displacement.value - + (u8 *) p->ainsn.insn; + BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ + disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn); + *(s32 *) disp = (s32) newdisp; } #endif } -- cgit v1.2.3-70-g09d2 From b1cf540f0e5278ecfe8532557e547d833ed269d7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 13 Aug 2009 16:34:44 -0400 Subject: x86: Add pt_regs register and stack access APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add following APIs for accessing registers and stack entries from pt_regs. These APIs are required by kprobes-based event tracer on ftrace. Some other debugging tools might be able to use it too. - regs_query_register_offset(const char *name) Query the offset of "name" register. - regs_query_register_name(unsigned int offset) Query the name of register by its offset. - regs_get_register(struct pt_regs *regs, unsigned int offset) Get the value of a register by its offset. - regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) Check the address is in the kernel stack. - regs_get_kernel_stack_nth(struct pt_regs *reg, unsigned int nth) Get Nth entry of the kernel stack. (N >= 0) - regs_get_argument_nth(struct pt_regs *reg, unsigned int nth) Get Nth argument at function call. (N >= 0) Signed-off-by: Masami Hiramatsu Cc: linux-arch@vger.kernel.org Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Jason Baron Cc: Jim Keniston Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090813203444.31965.26374.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/ptrace.h | 62 +++++++++++++++++++++++ arch/x86/kernel/ptrace.c | 112 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 174 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 0f0d908349a..a3d49dd7d26 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -7,6 +7,7 @@ #ifdef __KERNEL__ #include +#include #endif #ifndef __ASSEMBLY__ @@ -216,6 +217,67 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) return regs->sp; } +/* Query offset/name of register from its name/offset */ +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); +#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten. + * @offset: offset number of the register. + * + * regs_get_register returns the value of a register whose offset from @regs + * is @offset. The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + return *(unsigned long *)((unsigned long)regs + offset); +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kenel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static inline int regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specifined by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + +/* Get Nth argument at function call */ +extern unsigned long regs_get_argument_nth(struct pt_regs *regs, + unsigned int n); + /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 8d7d5c9c1be..a33a17d5d5c 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -49,6 +49,118 @@ enum x86_regset { REGSET_IOPERM32, }; +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { +#ifdef CONFIG_X86_64 + REG_OFFSET_NAME(r15), + REG_OFFSET_NAME(r14), + REG_OFFSET_NAME(r13), + REG_OFFSET_NAME(r12), + REG_OFFSET_NAME(r11), + REG_OFFSET_NAME(r10), + REG_OFFSET_NAME(r9), + REG_OFFSET_NAME(r8), +#endif + REG_OFFSET_NAME(bx), + REG_OFFSET_NAME(cx), + REG_OFFSET_NAME(dx), + REG_OFFSET_NAME(si), + REG_OFFSET_NAME(di), + REG_OFFSET_NAME(bp), + REG_OFFSET_NAME(ax), +#ifdef CONFIG_X86_32 + REG_OFFSET_NAME(ds), + REG_OFFSET_NAME(es), + REG_OFFSET_NAME(fs), + REG_OFFSET_NAME(gs), +#endif + REG_OFFSET_NAME(orig_ax), + REG_OFFSET_NAME(ip), + REG_OFFSET_NAME(cs), + REG_OFFSET_NAME(flags), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(ss), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} + +static const int arg_offs_table[] = { +#ifdef CONFIG_X86_32 + [0] = offsetof(struct pt_regs, ax), + [1] = offsetof(struct pt_regs, dx), + [2] = offsetof(struct pt_regs, cx) +#else /* CONFIG_X86_64 */ + [0] = offsetof(struct pt_regs, di), + [1] = offsetof(struct pt_regs, si), + [2] = offsetof(struct pt_regs, dx), + [3] = offsetof(struct pt_regs, cx), + [4] = offsetof(struct pt_regs, r8), + [5] = offsetof(struct pt_regs, r9) +#endif +}; + +/** + * regs_get_argument_nth() - get Nth argument at function call + * @regs: pt_regs which contains registers at function entry. + * @n: argument number. + * + * regs_get_argument_nth() returns @n th argument of a function call. + * Since usually the kernel stack will be changed right after function entry, + * you must use this at function entry. If the @n th entry is NOT in the + * kernel stack or pt_regs, this returns 0. + */ +unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n) +{ + if (n < ARRAY_SIZE(arg_offs_table)) + return *((unsigned long *)regs + arg_offs_table[n]); + else { + /* + * The typical case: arg n is on the stack. + * (Note: stack[0] = return address, so skip it) + */ + n -= ARRAY_SIZE(arg_offs_table); + return regs_get_kernel_stack_nth(regs, 1 + n); + } +} + /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. -- cgit v1.2.3-70-g09d2 From 8d7d14fb27818eb08ebedf9f4a6e286970fe9977 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 21 Aug 2009 15:43:07 -0400 Subject: x86: Fix x86 instruction decoder selftest to check only .text MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix x86 instruction decoder selftest to check only .text because other sections (e.g. .notes) will have random bytes which don't need to be checked. Signed-off-by: Masami Hiramatsu Cc: Jim Keniston Cc: H. Peter Anvin Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: Ingo Molnar Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090821194307.12478.76938.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/tools/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 3dd626b99dc..95e9cc4bcd9 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -1,6 +1,6 @@ PHONY += posttest quiet_cmd_posttest = TEST $@ - cmd_posttest = $(OBJDUMP) -d $(objtree)/vmlinux | awk -f $(srctree)/arch/x86/tools/distill.awk | $(obj)/test_get_len + cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | awk -f $(srctree)/arch/x86/tools/distill.awk | $(obj)/test_get_len posttest: $(obj)/test_get_len vmlinux $(call cmd,posttest) -- cgit v1.2.3-70-g09d2 From 69d991f32152283cbc373136fa45bbb152b32048 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 21 Aug 2009 15:43:16 -0400 Subject: x86: Check awk features before generating inat-tables.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Check some awk mandatory features to generate inat-tables.c that old mawk doesn't support. Signed-off-by: Masami Hiramatsu Cc: Jim Keniston Cc: H. Peter Anvin Cc: Ananth N Mavinakayanahalli Cc: Avi Kivity Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: Ingo Molnar Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Przemysław Pawełczyk Cc: Roland McGrath Cc: Sam Ravnborg Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vegard Nossum LKML-Reference: <20090821194316.12478.57394.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/tools/gen-insn-attr-x86.awk | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'arch') diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index 93b62c92d04..19ba096b7dd 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -4,7 +4,25 @@ # # Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c +# Awk implementation sanity check +function check_awk_implement() { + if (!match("abc", "[[:lower:]]+")) + return "Your awk doesn't support charactor-class." + if (sprintf("%x", 0) != "0") + return "Your awk has a printf-format problem." + return "" +} + BEGIN { + # Implementation error checking + awkchecked = check_awk_implement() + if (awkchecked != "") { + print "Error: " awkchecked > "/dev/stderr" + print "Please try to use gawk." > "/dev/stderr" + exit 1 + } + + # Setup generating tables print "/* x86 opcode map generated from x86-opcode-map.txt */" print "/* Do not change this code. */" ggid = 1 @@ -293,6 +311,8 @@ function convert_operands(opnd, i,imm,mod) } END { + if (awkchecked != "") + exit 1 # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \ -- cgit v1.2.3-70-g09d2 From 24851d2447830e6cba4c4b641cb73e713f312373 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 26 Aug 2009 23:38:30 +0200 Subject: tracing/kprobes: Dump the culprit kprobe in case of kprobe recursion Kprobes can enter into a probing recursion, ie: a kprobe that does an endless loop because one of its core mechanism function used during probing is also probed itself. This patch helps pinpointing the kprobe that raised such recursion by dumping it and raising a BUG instead of a warning (we also disarm the kprobe to try avoiding recursion in BUG itself). Having a BUG instead of a warning stops the stacktrace in the right place and doesn't pollute the logs with hundreds of traces that eventually end up in a stack overflow. Signed-off-by: Frederic Weisbecker Cc: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli --- arch/x86/kernel/kprobes.c | 8 ++++++-- include/linux/kprobes.h | 2 ++ kernel/kprobes.c | 7 +++++++ 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 16ae9610f6f..ecee3d23fef 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -490,9 +490,13 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, /* A probe has been hit in the codepath leading up * to, or just after, single-stepping of a probed * instruction. This entire codepath should strictly - * reside in .kprobes.text section. Raise a warning - * to highlight this peculiar case. + * reside in .kprobes.text section. + * Raise a BUG or we'll continue in an endless + * reentering loop and eventually a stack overflow. */ + arch_disarm_kprobe(p); + dump_kprobe(p); + BUG(); } default: /* impossible cases */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index bcd9c07848b..87eb79c9dd6 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -296,6 +296,8 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); +void dump_kprobe(struct kprobe *kp); + #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ef177d653b2..f72e96c25a3 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1141,6 +1141,13 @@ static void __kprobes kill_kprobe(struct kprobe *p) arch_remove_kprobe(p); } +void __kprobes dump_kprobe(struct kprobe *kp) +{ + printk(KERN_WARNING "Dumping kprobe:\n"); + printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", + kp->symbol_name, kp->addr, kp->offset); +} + /* Module notifier call back, checking kprobes on the module */ static int __kprobes kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) -- cgit v1.2.3-70-g09d2 From 3fe6ad6c39834350d74145de855fbffdde02ace4 Mon Sep 17 00:00:00 2001 From: Peter Ma Date: Mon, 24 Aug 2009 14:13:29 -0700 Subject: avr32: re-instate MCI WP/CD pin assignments for ATNGW100 The MRMT1 patch mistakenly reverted commit fe272b5bd13d3522f9d1ed35425f1c7af4d8343f. This new patch is intended to correct this, so that both daughtercards should be able to assign GPIO PC25 and PE0 to the MCI driver. Signed-off-by: Peter Ma Signed-off-by: Haavard Skinnemoen --- arch/avr32/boards/atngw100/setup.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch') diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c index bc299fbbeb4..5b022aad4bd 100644 --- a/arch/avr32/boards/atngw100/setup.c +++ b/arch/avr32/boards/atngw100/setup.c @@ -56,13 +56,8 @@ static struct spi_board_info spi0_board_info[] __initdata = { static struct mci_platform_data __initdata mci0_data = { .slot[0] = { .bus_width = 4, -#if defined(CONFIG_BOARD_ATNGW100_EVKLCD10X) || defined(CONFIG_BOARD_ATNGW100_MRMT1) - .detect_pin = GPIO_PIN_NONE, - .wp_pin = GPIO_PIN_NONE, -#else .detect_pin = GPIO_PIN_PC(25), .wp_pin = GPIO_PIN_PE(0), -#endif }, }; -- cgit v1.2.3-70-g09d2 From 0708420370db7350b75cbf64b1eb80ad1b2a89df Mon Sep 17 00:00:00 2001 From: Peter Ma Date: Thu, 27 Aug 2009 00:31:47 -0700 Subject: avr32: function for independently setting up SPI slaves at32ap_spi_setup_slaves() is exposed to allow the addition of SPI slaves to a SPI bus that has already been registered. This is especially useful for add-on cards, which have their own board setup function. at32ap_spi_add_device() has been slightly re-organized, but should be transparent to existing users. So to add a SPI slave, after a SPI bus has already been registered: /* Configure the list of slaves on SPI controller "id" */ at32_spi_setup_slaves(id,spi_board_info,ARRAY_SIZE(spi_board_info)); /* Register the list of slaves */ spi_register_board_info(spi_board_info,ARRAY_SIZE(spi_board_info)); Signed-off-by: Peter Ma [haavard.skinnemoen@atmel.com: trivial whitespace fix] Signed-off-by: Haavard Skinnemoen --- arch/avr32/mach-at32ap/at32ap700x.c | 35 ++++++++++++++++------------- arch/avr32/mach-at32ap/include/mach/board.h | 1 + 2 files changed, 20 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index eb9d4dc2e86..a47592e2fc3 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1181,19 +1181,32 @@ static struct resource atmel_spi1_resource[] = { DEFINE_DEV(atmel_spi, 1); DEV_CLK(spi_clk, atmel_spi1, pba, 1); -static void __init -at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, - unsigned int n, const u8 *pins) +void __init +at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n) { + /* + * Manage the chipselects as GPIOs, normally using the same pins + * the SPI controller expects; but boards can use other pins. + */ + static u8 __initdata spi_pins[][4] = { + { GPIO_PIN_PA(3), GPIO_PIN_PA(4), + GPIO_PIN_PA(5), GPIO_PIN_PA(20) }, + { GPIO_PIN_PB(2), GPIO_PIN_PB(3), + GPIO_PIN_PB(4), GPIO_PIN_PA(27) }, + }; unsigned int pin, mode; + /* There are only 2 SPI controllers */ + if (bus_num > 1) + return; + for (; n; n--, b++) { b->bus_num = bus_num; if (b->chip_select >= 4) continue; pin = (unsigned)b->controller_data; if (!pin) { - pin = pins[b->chip_select]; + pin = spi_pins[bus_num][b->chip_select]; b->controller_data = (void *)pin; } mode = AT32_GPIOF_OUTPUT; @@ -1206,16 +1219,6 @@ at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, struct platform_device *__init at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n) { - /* - * Manage the chipselects as GPIOs, normally using the same pins - * the SPI controller expects; but boards can use other pins. - */ - static u8 __initdata spi0_pins[] = - { GPIO_PIN_PA(3), GPIO_PIN_PA(4), - GPIO_PIN_PA(5), GPIO_PIN_PA(20), }; - static u8 __initdata spi1_pins[] = - { GPIO_PIN_PB(2), GPIO_PIN_PB(3), - GPIO_PIN_PB(4), GPIO_PIN_PA(27), }; struct platform_device *pdev; u32 pin_mask; @@ -1228,7 +1231,7 @@ at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n) select_peripheral(PIOA, (1 << 0), PERIPH_A, AT32_GPIOF_PULLUP); select_peripheral(PIOA, pin_mask, PERIPH_A, 0); - at32_spi_setup_slaves(0, b, n, spi0_pins); + at32_spi_setup_slaves(0, b, n); break; case 1: @@ -1239,7 +1242,7 @@ at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n) select_peripheral(PIOB, (1 << 0), PERIPH_B, AT32_GPIOF_PULLUP); select_peripheral(PIOB, pin_mask, PERIPH_B, 0); - at32_spi_setup_slaves(1, b, n, spi1_pins); + at32_spi_setup_slaves(1, b, n); break; default: diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h index ddedb471f33..c7f25bb1d06 100644 --- a/arch/avr32/mach-at32ap/include/mach/board.h +++ b/arch/avr32/mach-at32ap/include/mach/board.h @@ -49,6 +49,7 @@ at32_add_device_eth(unsigned int id, struct eth_platform_data *data); struct spi_board_info; struct platform_device * at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n); +void at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n); struct atmel_lcdfb_info; struct platform_device * -- cgit v1.2.3-70-g09d2 From d55651168a20078a94597a297d5cdfd807bf07b6 Mon Sep 17 00:00:00 2001 From: Peter Ma Date: Thu, 27 Aug 2009 00:56:43 -0700 Subject: avr32: MRMT: correct setup of SPI slaves For MRMT1/2 add-on card to Atmel ATNGW100. This patch implements the SPI slave setup method created by patch: <> Signed-off-by: Peter Ma Signed-off-by: Haavard Skinnemoen --- arch/avr32/boards/atngw100/mrmt.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c index bf78e516a85..7919be311f4 100644 --- a/arch/avr32/boards/atngw100/mrmt.c +++ b/arch/avr32/boards/atngw100/mrmt.c @@ -302,6 +302,7 @@ static int __init mrmt1_init(void) at32_select_periph( GPIO_PIOB_BASE, 1 << (PB_EXTINT_BASE+TS_IRQ), GPIO_PERIPH_A, AT32_GPIOF_DEGLITCH); set_irq_type( AT32_EXTINT(TS_IRQ), IRQ_TYPE_EDGE_FALLING ); + at32_spi_setup_slaves(0,spi01_board_info,ARRAY_SIZE(spi01_board_info)); spi_register_board_info(spi01_board_info,ARRAY_SIZE(spi01_board_info)); #endif -- cgit v1.2.3-70-g09d2 From c8bc6f3c806f1fcbfdbf0b1ff6c52dba59192d3b Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 4 Aug 2009 12:07:09 -0700 Subject: x86: arch specific support for remapping HPET MSIs x86 arch support for remapping HPET MSI's by associating the HPET timer block with the interrupt-remapping HW unit and setting up appropriate irq_chip Signed-off-by: Suresh Siddha Cc: Venkatesh Pallipadi Cc: David Woodhouse Cc: Jesse Barnes Cc: Jay Fenlason LKML-Reference: <20090804190729.630510000@intel.com> Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/hpet.h | 5 +++-- arch/x86/kernel/acpi/boot.c | 1 + arch/x86/kernel/apic/io_apic.c | 49 +++++++++++++++++++++++++++++++++++------- arch/x86/kernel/hpet.c | 3 ++- 4 files changed, 47 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 65847c578b7..5d89fd2a369 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -65,6 +65,7 @@ /* hpet memory map physical address */ extern unsigned long hpet_address; extern unsigned long force_hpet_address; +extern u8 hpet_blockid; extern int hpet_force_user; extern int is_hpet_enabled(void); extern int hpet_enable(void); @@ -78,9 +79,9 @@ extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg); extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg); #ifdef CONFIG_PCI_MSI -extern int arch_setup_hpet_msi(unsigned int irq); +extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id); #else -static inline int arch_setup_hpet_msi(unsigned int irq) +static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { return -EINVAL; } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6b8ca3a0285..eae642b0f34 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -624,6 +624,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) } hpet_address = hpet_tbl->address.address; + hpet_blockid = hpet_tbl->sequence; /* * Some broken BIOSes advertise HPET at 0x0. We really do not diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d2ed6c5ddc8..d9c6f14d3b3 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3254,7 +3254,8 @@ void destroy_irq(unsigned int irq) * MSI message composition */ #ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) { struct irq_cfg *cfg; int err; @@ -3288,7 +3289,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms irte.dest_id = IRTE_DEST(dest); /* Set source-id of interrupt request */ - set_msi_sid(&irte, pdev); + if (pdev) + set_msi_sid(&irte, pdev); + else + set_hpet_sid(&irte, hpet_id); modify_irte(irq, &irte); @@ -3453,7 +3457,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(dev, irq, &msg); + ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; @@ -3586,7 +3590,7 @@ int arch_setup_dmar_msi(unsigned int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(NULL, irq, &msg); + ret = msi_compose_msg(NULL, irq, &msg, -1); if (ret < 0) return ret; dmar_msi_write(irq, &msg); @@ -3626,6 +3630,19 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) #endif /* CONFIG_SMP */ +static struct irq_chip ir_hpet_msi_type = { + .name = "IR-HPET_MSI", + .unmask = hpet_msi_unmask, + .mask = hpet_msi_mask, +#ifdef CONFIG_INTR_REMAP + .ack = ir_ack_apic_edge, +#ifdef CONFIG_SMP + .set_affinity = ir_set_msi_irq_affinity, +#endif +#endif + .retrigger = ioapic_retrigger_irq, +}; + static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .unmask = hpet_msi_unmask, @@ -3637,20 +3654,36 @@ static struct irq_chip hpet_msi_type = { .retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq) +int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { int ret; struct msi_msg msg; struct irq_desc *desc = irq_to_desc(irq); - ret = msi_compose_msg(NULL, irq, &msg); + if (intr_remapping_enabled) { + struct intel_iommu *iommu = map_hpet_to_ir(id); + int index; + + if (!iommu) + return -1; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) + return -1; + } + + ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq, &msg); desc->status |= IRQ_MOVE_PCNTXT; - set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, - "edge"); + if (irq_remapped(irq)) + set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type, + handle_edge_irq, "edge"); + else + set_irq_chip_and_handler_name(irq, &hpet_msi_type, + handle_edge_irq, "edge"); return 0; } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ba575f0f2e3..7f024ff47d1 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -33,6 +33,7 @@ * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; +u8 hpet_blockid; /* OS timer block num */ #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -467,7 +468,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq)) { + if (arch_setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } -- cgit v1.2.3-70-g09d2 From e9afe9e1b3fdbd56cca53959a2519e70db9c8095 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 27 Aug 2009 13:22:58 -0400 Subject: kprobes/x86: Call BUG() when reentering probe into KPROBES_HIT_SS Call BUG() when a probe have been hit on the way of kprobe processing path, because that kind of probes are currently unrecoverable (recovering it will cause an infinite loop and stack overflow). The original code seems to assume that it's caused by an int3 which another subsystem inserted on out-of-line singlestep buffer if the hitting probe is same as current probe. However, in that case, int3-hitting-address is on the out-of-line buffer and should be different from first (current) int3 address. Thus, I decided to remove the code. I also removes arch_disarm_kprobe() because it will involve other stuffs in text_poke(). Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Ingo Molnar LKML-Reference: <20090827172258.8246.61889.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/kprobes.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index ecee3d23fef..e0fb615ba1e 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -482,22 +482,16 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, kcb->kprobe_status = KPROBE_REENTER; break; case KPROBE_HIT_SS: - if (p == kprobe_running()) { - regs->flags &= ~X86_EFLAGS_TF; - regs->flags |= kcb->kprobe_saved_flags; - return 0; - } else { - /* A probe has been hit in the codepath leading up - * to, or just after, single-stepping of a probed - * instruction. This entire codepath should strictly - * reside in .kprobes.text section. - * Raise a BUG or we'll continue in an endless - * reentering loop and eventually a stack overflow. - */ - arch_disarm_kprobe(p); - dump_kprobe(p); - BUG(); - } + /* A probe has been hit in the codepath leading up to, or just + * after, single-stepping of a probed instruction. This entire + * codepath should strictly reside in .kprobes.text section. + * Raise a BUG or we'll continue in an endless reentering loop + * and eventually a stack overflow. + */ + printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", + p->addr); + dump_kprobe(p); + BUG(); default: /* impossible cases */ WARN_ON(1); -- cgit v1.2.3-70-g09d2 From f5ad31158d60946b9fd18c8a79c283a6bc432430 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 27 Aug 2009 13:23:04 -0400 Subject: kprobes/x86-64: Allow to reenter probe on post_handler Allow to reenter probe on the post_handler of another probe on x86-64, because x86-64 already allows reentering int3. In that case, reentered probe just increases kp.nmissed and returns. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Ingo Molnar LKML-Reference: <20090827172304.8246.4822.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/kprobes.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e0fb615ba1e..c5f1f117e0c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -463,17 +463,6 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: -#ifdef CONFIG_X86_64 - /* TODO: Provide re-entrancy from post_kprobes_handler() and - * avoid exception stack corruption while single-stepping on - * the instruction of the new probe. - */ - arch_disarm_kprobe(p); - regs->ip = (unsigned long)p->addr; - reset_current_kprobe(); - preempt_enable_no_resched(); - break; -#endif case KPROBE_HIT_ACTIVE: save_previous_kprobe(kcb); set_current_kprobe(p, regs, kcb); -- cgit v1.2.3-70-g09d2 From 62c9295f9dd250ea1bb2c8078642a275a9ce82f8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 27 Aug 2009 13:23:11 -0400 Subject: kprobes/x86: Fix to add __kprobes to in-kernel fault handing functions Add __kprobes to the functions which handle in-kernel fixable page faults. Since kprobes can cause those in-kernel page faults by accessing kprobe data structures, probing those fault functions will cause fault-int3-loop (do_page_fault has already been marked as __kprobes). Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Ingo Molnar LKML-Reference: <20090827172311.8246.92725.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/mm/fault.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index bfae139182f..c322e59f2d1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -38,7 +38,8 @@ enum x86_pf_error_code { * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ -static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) +static inline int __kprobes +kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) @@ -46,7 +47,7 @@ static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int notify_page_fault(struct pt_regs *regs) +static inline int __kprobes notify_page_fault(struct pt_regs *regs) { int ret = 0; @@ -239,7 +240,7 @@ void vmalloc_sync_all(void) * * Handle a fault on the vmalloc or module mapping area */ -static noinline int vmalloc_fault(unsigned long address) +static noinline __kprobes int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; @@ -361,7 +362,7 @@ void vmalloc_sync_all(void) * * This assumes no large pages in there. */ -static noinline int vmalloc_fault(unsigned long address) +static noinline __kprobes int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; pud_t *pud, *pud_ref; @@ -858,7 +859,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static noinline int +static noinline __kprobes int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; -- cgit v1.2.3-70-g09d2 From 8222d718b3ad3ae49c48f69ae4b6a1128c9a92cf Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 27 Aug 2009 13:23:25 -0400 Subject: kprobes/x86-64: Fix to move common_interrupt to .kprobes.text Since nmi, debug and int3 returns to irq_return inside common_interrupt, probing this function will cause int3-loop, so it should be marked as __kprobes. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Ingo Molnar LKML-Reference: <20090827172325.8246.40000.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/entry_64.S | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index c251be74510..36e2ef5cc83 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -809,6 +809,10 @@ END(interrupt) call \func .endm +/* + * Interrupt entry/exit should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -947,6 +951,10 @@ ENTRY(retint_kernel) CFI_ENDPROC END(common_interrupt) +/* + * End of kprobes section + */ + .popsection /* * APIC interrupts. -- cgit v1.2.3-70-g09d2 From 50a482fbd96943516b7a2783900e8fe61a6425e7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 28 Aug 2009 18:13:19 -0400 Subject: x86: Allow x86-32 instruction decoder selftest on x86-64 Pass $(CONFIG_64BIT) to the x86 insn decoder selftest in case we are decoding 32bit code on x86-64, which will happen when building kernel with ARCH=i386 on x86-64. Signed-off-by: Masami Hiramatsu Cc: Jim Keniston Cc: Ingo Molnar LKML-Reference: <20090828221319.8778.88508.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/tools/Makefile | 2 +- arch/x86/tools/test_get_len.c | 14 +++++++------- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 95e9cc4bcd9..1bd006c8156 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -1,6 +1,6 @@ PHONY += posttest quiet_cmd_posttest = TEST $@ - cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | awk -f $(srctree)/arch/x86/tools/distill.awk | $(obj)/test_get_len + cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | awk -f $(srctree)/arch/x86/tools/distill.awk | $(obj)/test_get_len $(CONFIG_64BIT) posttest: $(obj)/test_get_len vmlinux $(call cmd,posttest) diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c index 1e81adb2d8a..a3273f4244d 100644 --- a/arch/x86/tools/test_get_len.c +++ b/arch/x86/tools/test_get_len.c @@ -45,7 +45,7 @@ const char *prog; static void usage(void) { fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |" - " ./test_get_len\n"); + " %s [y|n](64bit flag)\n", prog); exit(1); } @@ -63,11 +63,15 @@ int main(int argc, char **argv) unsigned char insn_buf[16]; struct insn insn; int insns = 0; + int x86_64 = 0; prog = argv[0]; - if (argc > 1) + if (argc > 2) usage(); + if (argc == 2 && argv[1][0] == 'y') + x86_64 = 1; + while (fgets(line, BUFSIZE, stdin)) { char copy[BUFSIZE], *s, *tab1, *tab2; int nb = 0; @@ -93,11 +97,7 @@ int main(int argc, char **argv) break; } /* Decode an instruction */ -#ifdef __x86_64__ - insn_init(&insn, insn_buf, 1); -#else - insn_init(&insn, insn_buf, 0); -#endif + insn_init(&insn, insn_buf, x86_64); insn_get_length(&insn); if (insn.length != nb) { fprintf(stderr, "Error: %s", line); -- cgit v1.2.3-70-g09d2 From 70069577323e6f72b845166724f34b9858134437 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 28 Aug 2009 18:13:26 -0400 Subject: x86: Remove unused config macros from instruction decoder selftest Remove dummy definitions of CONFIG_X86_64 and CONFIG_X86_32 because those macros are not used in the instruction decoder anymore. Signed-off-by: Masami Hiramatsu Cc: Jim Keniston Cc: Ingo Molnar LKML-Reference: <20090828221326.8778.70723.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker --- arch/x86/tools/test_get_len.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c index a3273f4244d..376d3385219 100644 --- a/arch/x86/tools/test_get_len.c +++ b/arch/x86/tools/test_get_len.c @@ -21,11 +21,6 @@ #include #include -#ifdef __x86_64__ -#define CONFIG_X86_64 -#else -#define CONFIG_X86_32 -#endif #define unlikely(cond) (cond) #include -- cgit v1.2.3-70-g09d2 From 654d364e26c797e8a5f9e2a1393607e6ca0106eb Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 14:04:06 +0900 Subject: sh: sh4_flush_cache_mm() optimizations. The i-cache flush in the case of VM_EXEC was added way back when as a sanity measure, and in practice we only care about evicting aliases from the d-cache. As a result, it's possible to drop the i-cache flush completely here. After careful profiling it's also come up that all of the work associated with hunting down aliases and doing ranged flushing ends up generating more overhead than simply blasting away the entire dcache, particularly if there are many mm's that need to be iterated over. As a result of that, just move back to flush_dcache_all() in these cases, which restores the old behaviour, and vastly simplifies the path. Additionally, on platforms without aliases at all, this can simply be nopped out. Presently we have the alias check in the SH-4 specific version, but this is true for all of the platforms, so move the check up to a generic location. This cuts down quite a bit on superfluous cacheop IPIs. Signed-off-by: Paul Mundt --- arch/sh/mm/cache-sh4.c | 124 ++----------------------------------------------- arch/sh/mm/cache.c | 6 +++ 2 files changed, 10 insertions(+), 120 deletions(-) (limited to 'arch') diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index b2453bbef4c..a5c339bca8a 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -170,89 +170,13 @@ static void sh4_flush_cache_all(void *unused) flush_icache_all(); } -static void __flush_cache_mm(struct mm_struct *mm, unsigned long start, - unsigned long end) -{ - unsigned long d = 0, p = start & PAGE_MASK; - unsigned long alias_mask = boot_cpu_data.dcache.alias_mask; - unsigned long n_aliases = boot_cpu_data.dcache.n_aliases; - unsigned long select_bit; - unsigned long all_aliases_mask; - unsigned long addr_offset; - pgd_t *dir; - pmd_t *pmd; - pud_t *pud; - pte_t *pte; - int i; - - dir = pgd_offset(mm, p); - pud = pud_offset(dir, p); - pmd = pmd_offset(pud, p); - end = PAGE_ALIGN(end); - - all_aliases_mask = (1 << n_aliases) - 1; - - do { - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) { - p &= PMD_MASK; - p += PMD_SIZE; - pmd++; - - continue; - } - - pte = pte_offset_kernel(pmd, p); - - do { - unsigned long phys; - pte_t entry = *pte; - - if (!(pte_val(entry) & _PAGE_PRESENT)) { - pte++; - p += PAGE_SIZE; - continue; - } - - phys = pte_val(entry) & PTE_PHYS_MASK; - - if ((p ^ phys) & alias_mask) { - d |= 1 << ((p & alias_mask) >> PAGE_SHIFT); - d |= 1 << ((phys & alias_mask) >> PAGE_SHIFT); - - if (d == all_aliases_mask) - goto loop_exit; - } - - pte++; - p += PAGE_SIZE; - } while (p < end && ((unsigned long)pte & ~PAGE_MASK)); - pmd++; - } while (p < end); - -loop_exit: - addr_offset = 0; - select_bit = 1; - - for (i = 0; i < n_aliases; i++) { - if (d & select_bit) { - (*__flush_dcache_segment_fn)(addr_offset, PAGE_SIZE); - wmb(); - } - - select_bit <<= 1; - addr_offset += PAGE_SIZE; - } -} - /* * Note : (RPC) since the caches are physically tagged, the only point * of flush_cache_mm for SH-4 is to get rid of aliases from the * D-cache. The assumption elsewhere, e.g. flush_cache_range, is that * lines can stay resident so long as the virtual address they were * accessed with (hence cache set) is in accord with the physical - * address (i.e. tag). It's no different here. So I reckon we don't - * need to flush the I-cache, since aliases don't matter for that. We - * should try that. + * address (i.e. tag). It's no different here. * * Caller takes mm->mmap_sem. */ @@ -263,33 +187,7 @@ static void sh4_flush_cache_mm(void *arg) if (cpu_context(smp_processor_id(), mm) == NO_CONTEXT) return; - /* - * If cache is only 4k-per-way, there are never any 'aliases'. Since - * the cache is physically tagged, the data can just be left in there. - */ - if (boot_cpu_data.dcache.n_aliases == 0) - return; - - /* - * Don't bother groveling around the dcache for the VMA ranges - * if there are too many PTEs to make it worthwhile. - */ - if (mm->nr_ptes >= MAX_DCACHE_PAGES) - flush_dcache_all(); - else { - struct vm_area_struct *vma; - - /* - * In this case there are reasonably sized ranges to flush, - * iterate through the VMA list and take care of any aliases. - */ - for (vma = mm->mmap; vma; vma = vma->vm_next) - __flush_cache_mm(mm, vma->vm_start, vma->vm_end); - } - - /* Only touch the icache if one of the VMAs has VM_EXEC set. */ - if (mm->exec_vm) - flush_icache_all(); + flush_dcache_all(); } /* @@ -372,24 +270,10 @@ static void sh4_flush_cache_range(void *args) if (boot_cpu_data.dcache.n_aliases == 0) return; - /* - * Don't bother with the lookup and alias check if we have a - * wide range to cover, just blow away the dcache in its - * entirety instead. -- PFM. - */ - if (((end - start) >> PAGE_SHIFT) >= MAX_DCACHE_PAGES) - flush_dcache_all(); - else - __flush_cache_mm(vma->vm_mm, start, end); + flush_dcache_all(); - if (vma->vm_flags & VM_EXEC) { - /* - * TODO: Is this required??? Need to look at how I-cache - * coherency is assured when new programs are loaded to see if - * this matters. - */ + if (vma->vm_flags & VM_EXEC) flush_icache_all(); - } } /** diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 35c37b7f717..4aa92605453 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -164,11 +164,17 @@ void flush_cache_all(void) void flush_cache_mm(struct mm_struct *mm) { + if (boot_cpu_data.dcache.n_aliases == 0) + return; + cacheop_on_each_cpu(local_flush_cache_mm, mm, 1); } void flush_cache_dup_mm(struct mm_struct *mm) { + if (boot_cpu_data.dcache.n_aliases == 0) + return; + cacheop_on_each_cpu(local_flush_cache_dup_mm, mm, 1); } -- cgit v1.2.3-70-g09d2 From 31c9efde786252112cc3d04a1ed3513b6ec63a7b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 14:10:28 +0900 Subject: sh: Kill off broken PHYSADDR() usage in sh4_flush_dcache_page(). PHYSADDR() runs in to issues in 32-bit mode when we do not have the legacy P1/P2 areas mapped, as such, we need to use page_to_phys() directly, which also happens to do the right thing in legacy 29-bit mode. Signed-off-by: Paul Mundt --- arch/sh/mm/cache-sh4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index a5c339bca8a..f0999606686 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -123,12 +123,12 @@ static void sh4_flush_dcache_page(void *arg) else #endif { - unsigned long phys = PHYSADDR(page_address(page)); + unsigned long phys = page_to_phys(page); unsigned long addr = CACHE_OC_ADDRESS_ARRAY; int i, n; /* Loop all the D-cache */ - n = boot_cpu_data.dcache.n_aliases; + n = boot_cpu_data.dcache.way_incr >> 12; for (i = 0; i < n; i++, addr += 4096) flush_cache_4096(addr, phys); } -- cgit v1.2.3-70-g09d2 From bd6df57481b329dfeeb4889068848ee4f4761561 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 14:22:15 +0900 Subject: sh: Kill off segment-based d-cache flushing on SH-4. This kills off the unrolled segment based flushers on SH-4 and switches over to a generic unrolled approach derived from the writethrough segment flusher. Signed-off-by: Paul Mundt --- arch/sh/mm/cache-sh4.c | 291 ++++--------------------------------------------- 1 file changed, 20 insertions(+), 271 deletions(-) (limited to 'arch') diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index f0999606686..92b7d947db9 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -29,14 +29,6 @@ static void __flush_cache_4096(unsigned long addr, unsigned long phys, unsigned long exec_offset); -/* - * This is initialised here to ensure that it is not placed in the BSS. If - * that were to happen, note that cache_init gets called before the BSS is - * cleared, so this would get nulled out which would be hopeless. - */ -static void (*__flush_dcache_segment_fn)(unsigned long, unsigned long) = - (void (*)(unsigned long, unsigned long))0xdeadbeef; - /* * Write back the range of D-cache, and purge the I-cache. * @@ -158,10 +150,27 @@ static void __uses_jump_to_uncached flush_icache_all(void) local_irq_restore(flags); } -static inline void flush_dcache_all(void) +static void flush_dcache_all(void) { - (*__flush_dcache_segment_fn)(0UL, boot_cpu_data.dcache.way_size); - wmb(); + unsigned long addr, end_addr, entry_offset; + + end_addr = CACHE_OC_ADDRESS_ARRAY + + (current_cpu_data.dcache.sets << + current_cpu_data.dcache.entry_shift) * + current_cpu_data.dcache.ways; + + entry_offset = 1 << current_cpu_data.dcache.entry_shift; + + for (addr = CACHE_OC_ADDRESS_ARRAY; addr < end_addr; ) { + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + __raw_writel(0, addr); addr += entry_offset; + } } static void sh4_flush_cache_all(void *unused) @@ -347,245 +356,6 @@ static void __flush_cache_4096(unsigned long addr, unsigned long phys, } while (--way_count != 0); } -/* - * Break the 1, 2 and 4 way variants of this out into separate functions to - * avoid nearly all the overhead of having the conditional stuff in the function - * bodies (+ the 1 and 2 way cases avoid saving any registers too). - * - * We want to eliminate unnecessary bus transactions, so this code uses - * a non-obvious technique. - * - * Loop over a cache way sized block of, one cache line at a time. For each - * line, use movca.a to cause the current cache line contents to be written - * back, but without reading anything from main memory. However this has the - * side effect that the cache is now caching that memory location. So follow - * this with a cache invalidate to mark the cache line invalid. And do all - * this with interrupts disabled, to avoid the cache line being accidently - * evicted while it is holding garbage. - * - * This also breaks in a number of circumstances: - * - if there are modifications to the region of memory just above - * empty_zero_page (for example because a breakpoint has been placed - * there), then these can be lost. - * - * This is because the the memory address which the cache temporarily - * caches in the above description is empty_zero_page. So the - * movca.l hits the cache (it is assumed that it misses, or at least - * isn't dirty), modifies the line and then invalidates it, losing the - * required change. - * - * - If caches are disabled or configured in write-through mode, then - * the movca.l writes garbage directly into memory. - */ -static void __flush_dcache_segment_writethrough(unsigned long start, - unsigned long extent_per_way) -{ - unsigned long addr; - int i; - - addr = CACHE_OC_ADDRESS_ARRAY | (start & cpu_data->dcache.entry_mask); - - while (extent_per_way) { - for (i = 0; i < cpu_data->dcache.ways; i++) - __raw_writel(0, addr + cpu_data->dcache.way_incr * i); - - addr += cpu_data->dcache.linesz; - extent_per_way -= cpu_data->dcache.linesz; - } -} - -static void __flush_dcache_segment_1way(unsigned long start, - unsigned long extent_per_way) -{ - unsigned long orig_sr, sr_with_bl; - unsigned long base_addr; - unsigned long way_incr, linesz, way_size; - struct cache_info *dcache; - register unsigned long a0, a0e; - - asm volatile("stc sr, %0" : "=r" (orig_sr)); - sr_with_bl = orig_sr | (1<<28); - base_addr = ((unsigned long)&empty_zero_page[0]); - - /* - * The previous code aligned base_addr to 16k, i.e. the way_size of all - * existing SH-4 D-caches. Whilst I don't see a need to have this - * aligned to any better than the cache line size (which it will be - * anyway by construction), let's align it to at least the way_size of - * any existing or conceivable SH-4 D-cache. -- RPC - */ - base_addr = ((base_addr >> 16) << 16); - base_addr |= start; - - dcache = &boot_cpu_data.dcache; - linesz = dcache->linesz; - way_incr = dcache->way_incr; - way_size = dcache->way_size; - - a0 = base_addr; - a0e = base_addr + extent_per_way; - do { - asm volatile("ldc %0, sr" : : "r" (sr_with_bl)); - asm volatile("movca.l r0, @%0\n\t" - "ocbi @%0" : : "r" (a0)); - a0 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "ocbi @%0" : : "r" (a0)); - a0 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "ocbi @%0" : : "r" (a0)); - a0 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "ocbi @%0" : : "r" (a0)); - asm volatile("ldc %0, sr" : : "r" (orig_sr)); - a0 += linesz; - } while (a0 < a0e); -} - -static void __flush_dcache_segment_2way(unsigned long start, - unsigned long extent_per_way) -{ - unsigned long orig_sr, sr_with_bl; - unsigned long base_addr; - unsigned long way_incr, linesz, way_size; - struct cache_info *dcache; - register unsigned long a0, a1, a0e; - - asm volatile("stc sr, %0" : "=r" (orig_sr)); - sr_with_bl = orig_sr | (1<<28); - base_addr = ((unsigned long)&empty_zero_page[0]); - - /* See comment under 1-way above */ - base_addr = ((base_addr >> 16) << 16); - base_addr |= start; - - dcache = &boot_cpu_data.dcache; - linesz = dcache->linesz; - way_incr = dcache->way_incr; - way_size = dcache->way_size; - - a0 = base_addr; - a1 = a0 + way_incr; - a0e = base_addr + extent_per_way; - do { - asm volatile("ldc %0, sr" : : "r" (sr_with_bl)); - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "ocbi @%0\n\t" - "ocbi @%1" : : - "r" (a0), "r" (a1)); - a0 += linesz; - a1 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "ocbi @%0\n\t" - "ocbi @%1" : : - "r" (a0), "r" (a1)); - a0 += linesz; - a1 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "ocbi @%0\n\t" - "ocbi @%1" : : - "r" (a0), "r" (a1)); - a0 += linesz; - a1 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "ocbi @%0\n\t" - "ocbi @%1" : : - "r" (a0), "r" (a1)); - asm volatile("ldc %0, sr" : : "r" (orig_sr)); - a0 += linesz; - a1 += linesz; - } while (a0 < a0e); -} - -static void __flush_dcache_segment_4way(unsigned long start, - unsigned long extent_per_way) -{ - unsigned long orig_sr, sr_with_bl; - unsigned long base_addr; - unsigned long way_incr, linesz, way_size; - struct cache_info *dcache; - register unsigned long a0, a1, a2, a3, a0e; - - asm volatile("stc sr, %0" : "=r" (orig_sr)); - sr_with_bl = orig_sr | (1<<28); - base_addr = ((unsigned long)&empty_zero_page[0]); - - /* See comment under 1-way above */ - base_addr = ((base_addr >> 16) << 16); - base_addr |= start; - - dcache = &boot_cpu_data.dcache; - linesz = dcache->linesz; - way_incr = dcache->way_incr; - way_size = dcache->way_size; - - a0 = base_addr; - a1 = a0 + way_incr; - a2 = a1 + way_incr; - a3 = a2 + way_incr; - a0e = base_addr + extent_per_way; - do { - asm volatile("ldc %0, sr" : : "r" (sr_with_bl)); - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "movca.l r0, @%2\n\t" - "movca.l r0, @%3\n\t" - "ocbi @%0\n\t" - "ocbi @%1\n\t" - "ocbi @%2\n\t" - "ocbi @%3\n\t" : : - "r" (a0), "r" (a1), "r" (a2), "r" (a3)); - a0 += linesz; - a1 += linesz; - a2 += linesz; - a3 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "movca.l r0, @%2\n\t" - "movca.l r0, @%3\n\t" - "ocbi @%0\n\t" - "ocbi @%1\n\t" - "ocbi @%2\n\t" - "ocbi @%3\n\t" : : - "r" (a0), "r" (a1), "r" (a2), "r" (a3)); - a0 += linesz; - a1 += linesz; - a2 += linesz; - a3 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "movca.l r0, @%2\n\t" - "movca.l r0, @%3\n\t" - "ocbi @%0\n\t" - "ocbi @%1\n\t" - "ocbi @%2\n\t" - "ocbi @%3\n\t" : : - "r" (a0), "r" (a1), "r" (a2), "r" (a3)); - a0 += linesz; - a1 += linesz; - a2 += linesz; - a3 += linesz; - asm volatile("movca.l r0, @%0\n\t" - "movca.l r0, @%1\n\t" - "movca.l r0, @%2\n\t" - "movca.l r0, @%3\n\t" - "ocbi @%0\n\t" - "ocbi @%1\n\t" - "ocbi @%2\n\t" - "ocbi @%3\n\t" : : - "r" (a0), "r" (a1), "r" (a2), "r" (a3)); - asm volatile("ldc %0, sr" : : "r" (orig_sr)); - a0 += linesz; - a1 += linesz; - a2 += linesz; - a3 += linesz; - } while (a0 < a0e); -} - extern void __weak sh4__flush_region_init(void); /* @@ -593,32 +363,11 @@ extern void __weak sh4__flush_region_init(void); */ void __init sh4_cache_init(void) { - unsigned int wt_enabled = !!(__raw_readl(CCR) & CCR_CACHE_WT); - printk("PVR=%08x CVR=%08x PRR=%08x\n", ctrl_inl(CCN_PVR), ctrl_inl(CCN_CVR), ctrl_inl(CCN_PRR)); - if (wt_enabled) - __flush_dcache_segment_fn = __flush_dcache_segment_writethrough; - else { - switch (boot_cpu_data.dcache.ways) { - case 1: - __flush_dcache_segment_fn = __flush_dcache_segment_1way; - break; - case 2: - __flush_dcache_segment_fn = __flush_dcache_segment_2way; - break; - case 4: - __flush_dcache_segment_fn = __flush_dcache_segment_4way; - break; - default: - panic("unknown number of cache ways\n"); - break; - } - } - local_flush_icache_range = sh4_flush_icache_range; local_flush_dcache_page = sh4_flush_dcache_page; local_flush_cache_all = sh4_flush_cache_all; -- cgit v1.2.3-70-g09d2 From deaef20e9789d93c06d2d3b5ffc99939814802ca Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 16:06:39 +0900 Subject: sh: Rework sh4_flush_cache_page() for coherent kmap mapping. This builds on top of the MIPS r4k code that does roughly the same thing. This permits the use of kmap_coherent() for mapped pages with dirty dcache lines and falls back on kmap_atomic() otherwise. This also fixes up a problem with the alias check and defers to shm_align_mask directly. Signed-off-by: Paul Mundt --- arch/sh/mm/cache-sh4.c | 75 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 48 insertions(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 92b7d947db9..e3fbd99b323 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -2,7 +2,7 @@ * arch/sh/mm/cache-sh4.c * * Copyright (C) 1999, 2000, 2002 Niibe Yutaka - * Copyright (C) 2001 - 2007 Paul Mundt + * Copyright (C) 2001 - 2009 Paul Mundt * Copyright (C) 2003 Richard Curnow * Copyright (c) 2007 STMicroelectronics (R&D) Ltd. * @@ -15,6 +15,8 @@ #include #include #include +#include +#include #include #include @@ -23,7 +25,6 @@ * flushing. Anything exceeding this will simply flush the dcache in its * entirety. */ -#define MAX_DCACHE_PAGES 64 /* XXX: Tune for ways */ #define MAX_ICACHE_PAGES 32 static void __flush_cache_4096(unsigned long addr, unsigned long phys, @@ -209,44 +210,64 @@ static void sh4_flush_cache_page(void *args) { struct flusher_data *data = args; struct vm_area_struct *vma; + struct page *page; unsigned long address, pfn, phys; - unsigned int alias_mask; + int map_coherent = 0; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + void *vaddr; vma = data->vma; address = data->addr1; pfn = data->addr2; phys = pfn << PAGE_SHIFT; + page = pfn_to_page(pfn); if (cpu_context(smp_processor_id(), vma->vm_mm) == NO_CONTEXT) return; - alias_mask = boot_cpu_data.dcache.alias_mask; - - /* We only need to flush D-cache when we have alias */ - if ((address^phys) & alias_mask) { - /* Loop 4K of the D-cache */ - flush_cache_4096( - CACHE_OC_ADDRESS_ARRAY | (address & alias_mask), - phys); - /* Loop another 4K of the D-cache */ - flush_cache_4096( - CACHE_OC_ADDRESS_ARRAY | (phys & alias_mask), - phys); - } + address &= PAGE_MASK; + pgd = pgd_offset(vma->vm_mm, address); + pud = pud_offset(pgd, address); + pmd = pmd_offset(pud, address); + pte = pte_offset_kernel(pmd, address); + + /* If the page isn't present, there is nothing to do here. */ + if (!(pte_val(*pte) & _PAGE_PRESENT)) + return; - alias_mask = boot_cpu_data.icache.alias_mask; - if (vma->vm_flags & VM_EXEC) { + if ((vma->vm_mm == current->active_mm)) + vaddr = NULL; + else { /* - * Evict entries from the portion of the cache from which code - * may have been executed at this address (virtual). There's - * no need to evict from the portion corresponding to the - * physical address as for the D-cache, because we know the - * kernel has never executed the code through its identity - * translation. + * Use kmap_coherent or kmap_atomic to do flushes for + * another ASID than the current one. */ - flush_cache_4096( - CACHE_IC_ADDRESS_ARRAY | (address & alias_mask), - phys); + map_coherent = (current_cpu_data.dcache.n_aliases && + !test_bit(PG_dcache_dirty, &page->flags) && + page_mapped(page)); + if (map_coherent) + vaddr = kmap_coherent(page, address); + else + vaddr = kmap_atomic(page, KM_USER0); + + address = (unsigned long)vaddr; + } + + if (pages_do_alias(address, phys)) + flush_cache_4096(CACHE_OC_ADDRESS_ARRAY | + (address & shm_align_mask), phys); + + if (vma->vm_flags & VM_EXEC) + flush_icache_all(); + + if (vaddr) { + if (map_coherent) + kunmap_coherent(vaddr); + else + kunmap_atomic(vaddr, KM_USER0); } } -- cgit v1.2.3-70-g09d2 From c4845a4b2288a9e5d96a0558e474809028c8aff3 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 17:13:07 +0900 Subject: sh: Fix up redundant cache flushing for PAGE_SIZE > 4k. If PAGE_SIZE is presently over 4k we do a lot of extra flushing given that we purge the cache 4k at a time. Make it explicitly 4k per iteration, rather than iterating for PAGE_SIZE before looping over again. Signed-off-by: Paul Mundt --- arch/sh/mm/cache-sh4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index e3fbd99b323..8362d312ad9 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -357,7 +357,7 @@ static void __flush_cache_4096(unsigned long addr, unsigned long phys, * pointless nead-of-loop check for 0 iterations. */ do { - ea = base_addr + PAGE_SIZE; + ea = base_addr + 4096; a = base_addr; p = phys; -- cgit v1.2.3-70-g09d2 From f9e2bdfdbb4c9da13422b349227be8c7b41dbd44 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 9 Sep 2009 17:14:19 +0900 Subject: sh: Factor in cpu id for selection of cache colour fixmap. In the SMP VIPT case the page copy/clear ops still perform colouring, care needs to be taken that CPUs don't end up stepping on each other, so we give them a bit of room to work with. At the same time, we reduce the worst-case colouring given that these pages are always consumed. Signed-off-by: Paul Mundt --- arch/sh/include/asm/fixmap.h | 6 +++--- arch/sh/mm/kmap.c | 4 +++- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/sh/include/asm/fixmap.h b/arch/sh/include/asm/fixmap.h index 721fcc4d5e9..76c5a3099cb 100644 --- a/arch/sh/include/asm/fixmap.h +++ b/arch/sh/include/asm/fixmap.h @@ -14,9 +14,9 @@ #define _ASM_FIXMAP_H #include +#include #include #ifdef CONFIG_HIGHMEM -#include #include #endif @@ -46,9 +46,9 @@ * fix-mapped? */ enum fixed_addresses { -#define FIX_N_COLOURS 16 +#define FIX_N_COLOURS 8 FIX_CMAP_BEGIN, - FIX_CMAP_END = FIX_CMAP_BEGIN + FIX_N_COLOURS, + FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS), FIX_UNCACHED, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c index 16e01b5fed0..15d74ea4209 100644 --- a/arch/sh/mm/kmap.c +++ b/arch/sh/mm/kmap.c @@ -39,7 +39,9 @@ void *kmap_coherent(struct page *page, unsigned long addr) pagefault_disable(); idx = FIX_CMAP_END - - ((addr & current_cpu_data.dcache.alias_mask) >> PAGE_SHIFT); + (((addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1)) + + (FIX_N_COLOURS * smp_processor_id())); + vaddr = __fix_to_virt(idx); BUG_ON(!pte_none(*(kmap_coherent_pte - idx))); -- cgit v1.2.3-70-g09d2 From f12b4f546b4e327d5620a544a2bddab68de66027 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 8 Sep 2009 12:32:46 -0400 Subject: x86: Add MMX support for instruction decoder Add MMX/SSE instructions to x86 opcode maps, since some of those instructions are used in the kernel. This also fixes failures in the x86 instruction decoder seftest. Signed-off-by: Masami Hiramatsu Cc: Jim Keniston Cc: H. Peter Anvin Cc: Sam Ravnborg Cc: Frederic Weisbecker Cc: Ingo Molnar LKML-Reference: <20090908163246.23516.78835.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker --- arch/x86/lib/x86-opcode-map.txt | 307 ++++++++++++++++++++++++++-------------- 1 file changed, 200 insertions(+), 107 deletions(-) (limited to 'arch') diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 083dd59dd74..59e20d5c2a5 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -310,14 +310,14 @@ Referrer: 2-byte escape 0e: 0f: # 0x0f 0x10-0x1f -10: -11: -12: -13: -14: -15: -16: -17: +10: movups Vps,Wps | movss Vss,Wss (F3) | movupd Vpd,Wpd (66) | movsd Vsd,Wsd (F2) +11: movups Wps,Vps | movss Wss,Vss (F3) | movupd Wpd,Vpd (66) | movsd Wsd,Vsd (F2) +12: movlps Vq,Mq | movlpd Vq,Mq (66) | movhlps Vq,Uq | movddup Vq,Wq (F2) | movsldup Vq,Wq (F3) +13: mpvlps Mq,Vq | movlpd Mq,Vq (66) +14: unpcklps Vps,Wq | unpcklpd Vpd,Wq (66) +15: unpckhps Vps,Wq | unpckhpd Vpd,Wq (66) +16: movhps Vq,Mq | movhpd Vq,Mq (66) | movlsps Vq,Uq | movshdup Vq,Wq (F3) +17: movhps Mq,Vq | movhpd Mq,Vq (66) 18: Grp16 (1A) 19: 1a: @@ -337,12 +337,12 @@ Referrer: 2-byte escape 27: 28: movaps Vps,Wps | movapd Vpd,Wpd (66) 29: movaps Wps,Vps | movapd Wpd,Vpd (66) -2a: -2b: -2c: -2d: -2e: -2f: +2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2) +2b: movntps Mps,Vps | movntpd Mpd,Vpd (66) +2c: cvttps2pi Ppi,Wps | cvttss2si Gd/q,Wss (F3) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2) +2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2) +2e: ucomiss Vss,Wss | ucomisd Vsd,Wsd (66) +2f: comiss Vss,Wss | comisd Vsd,Wsd (66) # 0x0f 0x30-0x3f 30: WRMSR 31: RDTSC @@ -378,56 +378,56 @@ Referrer: 2-byte escape 4e: CMOVLE/NG Gv,Ev 4f: CMOVNLE/G Gv,Ev # 0x0f 0x50-0x5f -50: -51: -52: -53: -54: -55: -56: -57: -58: -59: -5a: -5b: -5c: -5d: -5e: -5f: +50: movmskps Gd/q,Ups | movmskpd Gd/q,Upd (66) +51: sqrtps Vps,Wps | sqrtss Vss,Wss (F3) | sqrtpd Vpd,Wpd (66) | sqrtsd Vsd,Wsd (F2) +52: rsqrtps Vps,Wps | rsqrtss Vss,Wss (F3) +53: rcpps Vps,Wps | rcpss Vss,Wss (F3) +54: andps Vps,Wps | andpd Vpd,Wpd (66) +55: andnps Vps,Wps | andnpd Vpd,Wpd (66) +56: orps Vps,Wps | orpd Vpd,Wpd (66) +57: xorps Vps,Wps | xorpd Vpd,Wpd (66) +58: addps Vps,Wps | addss Vss,Wss (F3) | addpd Vpd,Wpd (66) | addsd Vsd,Wsd (F2) +59: mulps Vps,Wps | mulss Vss,Wss (F3) | mulpd Vpd,Wpd (66) | mulsd Vsd,Wsd (F2) +5a: cvtps2pd Vpd,Wps | cvtss2sd Vsd,Wss (F3) | cvtpd2ps Vps,Wpd (66) | cvtsd2ss Vsd,Wsd (F2) +5b: cvtdq2ps Vps,Wdq | cvtps2dq Vdq,Wps (66) | cvttps2dq Vdq,Wps (F3) +5c: subps Vps,Wps | subss Vss,Wss (F3) | subpd Vpd,Wpd (66) | subsd Vsd,Wsd (F2) +5d: minps Vps,Wps | minss Vss,Wss (F3) | minpd Vpd,Wpd (66) | minsd Vsd,Wsd (F2) +5e: divps Vps,Wps | divss Vss,Wss (F3) | divpd Vpd,Wpd (66) | divsd Vsd,Wsd (F2) +5f: maxps Vps,Wps | maxss Vss,Wss (F3) | maxpd Vpd,Wpd (66) | maxsd Vsd,Wsd (F2) # 0x0f 0x60-0x6f -60: -61: -62: -63: -64: -65: -66: -67: -68: -69: -6a: -6b: -6c: -6d: -6e: -6f: +60: punpcklbw Pq,Qd | punpcklbw Vdq,Wdq (66) +61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66) +62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66) +63: packsswb Pq,Qq | packsswb Vdq,Wdq (66) +64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66) +65: pcmpgtw Pq,Qq | pcmpgtw(66) Vdq,Wdq +66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66) +67: packuswb Pq,Qq | packuswb(66) Vdq,Wdq +68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66) +69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66) +6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66) +6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66) +6c: punpcklqdq Vdq,Wdq (66) +6d: punpckhqdq Vdq,Wdq (66) +6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66) +6f: movq Pq,Qq | movdqa Vdq,Wdq (66) | movdqu Vdq,Wdq (F3) # 0x0f 0x70-0x7f -70: +70: pshufw Pq,Qq,Ib | pshufd Vdq,Wdq,Ib (66) | pshufhw Vdq,Wdq,Ib (F3) | pshuflw VdqWdq,Ib (F2) 71: Grp12 (1A) 72: Grp13 (1A) 73: Grp14 (1A) -74: -75: -76: -77: +74: pcmpeqb Pq,Qq | pcmpeqb Vdq,Wdq (66) +75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66) +76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66) +77: emms 78: VMREAD Ed/q,Gd/q 79: VMWRITE Gd/q,Ed/q 7a: 7b: -7c: -7d: -7e: -7f: +7c: haddps(F2) Vps,Wps | haddpd(66) Vpd,Wpd +7d: hsubps(F2) Vps,Wps | hsubpd(66) Vpd,Wpd +7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66) | movq Vq,Wq (F3) +7f: movq Qq,Pq | movdqa Wdq,Vdq (66) | movdqu Wdq,Vdq (F3) # 0x0f 0x80-0x8f 80: JO Jz (f64) 81: JNO Jz (f64) @@ -499,11 +499,11 @@ bf: MOVSX Gv,Ew # 0x0f 0xc0-0xcf c0: XADD Eb,Gb c1: XADD Ev,Gv -c2: +c2: cmpps Vps,Wps,Ib | cmpss Vss,Wss,Ib (F3) | cmppd Vpd,Wpd,Ib (66) | cmpsd Vsd,Wsd,Ib (F2) c3: movnti Md/q,Gd/q -c4: -c5: -c6: +c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66) +c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66) +c6: shufps Vps,Wps,Ib | shufpd Vpd,Wpd,Ib (66) c7: Grp9 (1A) c8: BSWAP RAX/EAX/R8/R8D c9: BSWAP RCX/ECX/R9/R9D @@ -514,60 +514,131 @@ cd: BSWAP RBP/EBP/R13/R13D ce: BSWAP RSI/ESI/R14/R14D cf: BSWAP RDI/EDI/R15/R15D # 0x0f 0xd0-0xdf -d0: -d1: -d2: -d3: -d4: -d5: -d6: -d7: -d8: -d9: -da: -db: -dc: -dd: -de: -df: +d0: addsubps Vps,Wps (F2) | addsubpd Vpd,Wpd (66) +d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66) +d2: psrld Pq,Qq | psrld Vdq,Wdq (66) +d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66) +d4: paddq Pq,Qq | paddq Vdq,Wdq (66) +d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66) +d6: movq Wq,Vq (66) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2) +d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66) +d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66) +d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66) +da: pminub Pq,Qq | pminub Vdq,Wdq (66) +db: pand Pq,Qq | pand Vdq,Wdq (66) +dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66) +dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66) +de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66) +df: pandn Pq,Qq | pandn Vdq,Wdq (66) # 0x0f 0xe0-0xef -e0: -e1: -e2: -e3: -e4: -e5: -e6: -e7: -e8: -e9: -ea: -eb: -ec: -ed: -ee: -ef: +e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66) +e1: psraw Pq,Qq | psraw Vdq,Wdq (66) +e2: psrad Pq,Qq | psrad Vdq,Wdq (66) +e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66) +e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66) +e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66) +e6: cvtpd2dq Vdq,Wpd (F2) | cvttpd2dq Vdq,Wpd (66) | cvtdq2pd Vpd,Wdq (F3) +e7: movntq Mq,Pq | movntdq Mdq,Vdq (66) +e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66) +e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66) +ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66) +eb: por Pq,Qq | por Vdq,Wdq (66) +ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66) +ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66) +ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66) +ef: pxor Pq,Qq | pxor Vdq,Wdq (66) # 0x0f 0xf0-0xff -f0: -f1: -f2: -f3: -f4: -f5: -f6: -f7: -f8: -f9: -fa: -fb: -fc: -fd: -fe: +f0: lddqu Vdq,Mdq (F2) +f1: psllw Pq,Qq | psllw Vdq,Wdq (66) +f2: pslld Pq,Qq | pslld Vdq,Wdq (66) +f3: psllq Pq,Qq | psllq Vdq,Wdq (66) +f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66) +f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66) +f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66) +f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66) +f8: psubb Pq,Qq | psubb Vdq,Wdq (66) +f9: psubw Pq,Qq | psubw Vdq,Wdq (66) +fa: psubd Pq,Qq | psubd Vdq,Wdq (66) +fb: psubq Pq,Qq | psubq Vdq,Wdq (66) +fc: paddb Pq,Qq | paddb Vdq,Wdq (66) +fd: paddw Pq,Qq | paddw Vdq,Wdq (66) +fe: paddd Pq,Qq | paddd Vdq,Wdq (66) ff: EndTable Table: 3-byte opcode 1 Referrer: 3-byte escape 1 +# 0x0f 0x38 0x00-0x0f +00: pshufb Pq,Qq | pshufb Vdq,Wdq (66) +01: phaddw Pq,Qq | phaddw Vdq,Wdq (66) +02: phaddd Pq,Qq | phaddd Vdq,Wdq (66) +03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66) +04: pmaddubsw Pq,Qq | pmaddubsw (66)Vdq,Wdq +05: phsubw Pq,Qq | phsubw Vdq,Wdq (66) +06: phsubd Pq,Qq | phsubd Vdq,Wdq (66) +07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66) +08: psignb Pq,Qq | psignb Vdq,Wdq (66) +09: psignw Pq,Qq | psignw Vdq,Wdq (66) +0a: psignd Pq,Qq | psignd Vdq,Wdq (66) +0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66) +0c: +0d: +0e: +0f: +# 0x0f 0x38 0x10-0x1f +10: pblendvb Vdq,Wdq (66) +11: +12: +13: +14: blendvps Vdq,Wdq (66) +15: blendvpd Vdq,Wdq (66) +16: +17: ptest Vdq,Wdq (66) +18: +19: +1a: +1b: +1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66) +1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66) +1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66) +1f: +# 0x0f 0x38 0x20-0x2f +20: pmovsxbw Vdq,Udq/Mq (66) +21: pmovsxbd Vdq,Udq/Md (66) +22: pmovsxbq Vdq,Udq/Mw (66) +23: pmovsxwd Vdq,Udq/Mq (66) +24: pmovsxwq Vdq,Udq/Md (66) +25: pmovsxdq Vdq,Udq/Mq (66) +26: +27: +28: pmuldq Vdq,Wdq (66) +29: pcmpeqq Vdq,Wdq (66) +2a: movntdqa Vdq,Mdq (66) +2b: packusdw Vdq,Wdq (66) +2c: +2d: +2e: +2f: +# 0x0f 0x38 0x30-0x3f +30: pmovzxbw Vdq,Udq/Mq (66) +31: pmovzxbd Vdq,Udq/Md (66) +32: pmovzxbq Vdq,Udq/Mw (66) +33: pmovzxwd Vdq,Udq/Mq (66) +34: pmovzxwq Vdq,Udq/Md (66) +35: pmovzxdq Vdq,Udq/Mq (66) +36: +37: pcmpgtq Vdq,Wdq (66) +38: pminsb Vdq,Wdq (66) +39: pminsd Vdq,Wdq (66) +3a: pminuw Vdq,Wdq (66) +3b: pminud Vdq,Wdq (66) +3c: pmaxsb Vdq,Wdq (66) +3d: pmaxsd Vdq,Wdq (66) +3e: pmaxuw Vdq,Wdq (66) +3f: pmaxud Vdq,Wdq (66) +# 0x0f 0x38 0x4f-0xff +40: pmulld Vdq,Wdq (66) +41: phminposuw Vdq,Wdq (66) 80: INVEPT Gd/q,Mdq (66) 81: INVPID Gd/q,Mdq (66) f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2) @@ -576,7 +647,29 @@ EndTable Table: 3-byte opcode 2 Referrer: 3-byte escape 2 -# all opcode is for SSE +# 0x0f 0x3a 0x00-0xff +08: roundps Vdq,Wdq,Ib (66) +09: roundpd Vdq,Wdq,Ib (66) +0a: roundss Vss,Wss,Ib (66) +0b: roundsd Vsd,Wsd,Ib (66) +0c: blendps Vdq,Wdq,Ib (66) +0d: blendpd Vdq,Wdq,Ib (66) +0e: pblendw Vdq,Wdq,Ib (66) +0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66) +14: pextrb Rd/Mb,Vdq,Ib (66) +15: pextrw Rd/Mw,Vdq,Ib (66) +16: pextrd/pextrq Ed/q,Vdq,Ib (66) +17: extractps Ed,Vdq,Ib (66) +20: pinsrb Vdq,Rd/q/Mb,Ib (66) +21: insertps Vdq,Udq/Md,Ib (66) +22: pinsrd/pinsrq Vdq,Ed/q,Ib (66) +40: dpps Vdq,Wdq,Ib (66) +41: dppd Vdq,Wdq,Ib (66) +42: mpsadbw Vdq,Wdq,Ib (66) +60: pcmpestrm Vdq,Wdq,Ib (66) +61: pcmpestri Vdq,Wdq,Ib (66) +62: pcmpistrm Vdq,Wdq,Ib (66) +63: pcmpistri Vdq,Wdq,Ib (66) EndTable GrpTable: Grp1 -- cgit v1.2.3-70-g09d2 From a00e817f42663941ea0aa5f85a9d1c4f8b212839 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 8 Sep 2009 12:47:55 -0400 Subject: kprobes/x86-32: Move irq-exit functions to kprobes section Move irq-exit functions to .kprobes.text section to protect against kprobes recursion. When I ran kprobe stress test on x86-32, I found below symbols cause unrecoverable recursive probing: ret_from_exception ret_from_intr check_userspace restore_all restore_all_notrace restore_nocheck irq_return And also, I found some interrupt/exception entry points that cause similar problems. This patch moves those symbols (including their container functions) to .kprobes.text section to prevent any kprobes probing. Signed-off-by: Masami Hiramatsu Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Ingo Molnar LKML-Reference: <20090908164755.24050.81182.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/entry_32.S | 24 ++++++++++++++++++++++++ kernel/kprobes.c | 2 ++ 2 files changed, 26 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c097e7d607c..beb30da203d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -333,6 +333,10 @@ ENTRY(ret_from_fork) CFI_ENDPROC END(ret_from_fork) +/* + * Interrupt exit functions should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" /* * Return to user mode is not as complex as all this looks, * but we want the default path for a system call return to @@ -383,6 +387,10 @@ need_resched: END(resume_kernel) #endif CFI_ENDPROC +/* + * End of kprobes section + */ + .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -513,6 +521,10 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) +/* + * syscall stub including irq exit should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway @@ -705,6 +717,10 @@ syscall_badsys: jmp resume_userspace END(syscall_badsys) CFI_ENDPROC +/* + * End of kprobes section + */ + .popsection /* * System calls that need a pt_regs pointer. @@ -814,6 +830,10 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC +/* + * Irq entries should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ @@ -980,6 +1000,10 @@ ENTRY(spurious_interrupt_bug) jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) +/* + * End of kprobes section + */ + .popsection ENTRY(kernel_thread_helper) pushl $0 # fake return address for unwinder diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 3267d90bc9d..00d01b0f9fe 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -91,6 +91,8 @@ static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) static struct kprobe_blackpoint kprobe_blacklist[] = { {"preempt_schedule",}, {"native_get_debugreg",}, + {"irq_entries_start",}, + {"common_interrupt",}, {NULL} /* Terminator */ }; -- cgit v1.2.3-70-g09d2 From ad5cafcdb09c57008c990edd309c0a563b09f238 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 10 Sep 2009 19:53:06 -0400 Subject: x86/ptrace: Fix regs_get_argument_nth() to add correct offset Fix regs_get_argument_nth() to add correct offset bytes. Because offset_of() returns offset in byte, the offset should be added to char * instead of unsigned long *. Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Cc: Jim Keniston Cc: Ananth N Mavinakayanahalli Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Steven Rostedt Cc: Tom Zanussi LKML-Reference: <20090910235306.22412.31613.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index a33a17d5d5c..caffb680945 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -150,7 +150,7 @@ static const int arg_offs_table[] = { unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n) { if (n < ARRAY_SIZE(arg_offs_table)) - return *((unsigned long *)regs + arg_offs_table[n]); + return *(unsigned long *)((char *)regs + arg_offs_table[n]); else { /* * The typical case: arg n is on the stack. -- cgit v1.2.3-70-g09d2 From b8a4754147d61f5359a765a3afd3eb03012aa052 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 30 Jul 2009 11:10:02 +0200 Subject: x86, msr: Unify rdmsr_on_cpus/wrmsr_on_cpus Since rdmsr_on_cpus and wrmsr_on_cpus are almost identical, unify them into a common __rwmsr_on_cpus helper thus avoiding code duplication. While at it, convert cpumask_t's to const struct cpumask *. Signed-off-by: Borislav Petkov Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- arch/x86/include/asm/msr.h | 4 ++-- arch/x86/lib/msr.c | 46 +++++++++++++++++++--------------------------- 2 files changed, 21 insertions(+), 29 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7e2b6ba962f..9a00219b331 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -247,8 +247,8 @@ do { \ #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 33a1e3ca22d..41628b104b9 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -71,14 +71,9 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); -/* rdmsr on a bunch of CPUs - * - * @mask: which CPUs - * @msr_no: which MSR - * @msrs: array of MSR values - * - */ -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, + struct msr *msrs, + void (*msr_func) (void *info)) { struct msr_info rv; int this_cpu; @@ -92,11 +87,23 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) this_cpu = get_cpu(); if (cpumask_test_cpu(this_cpu, mask)) - __rdmsr_on_cpu(&rv); + msr_func(&rv); - smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1); + smp_call_function_many(mask, msr_func, &rv, 1); put_cpu(); } + +/* rdmsr on a bunch of CPUs + * + * @mask: which CPUs + * @msr_no: which MSR + * @msrs: array of MSR values + * + */ +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +{ + __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); +} EXPORT_SYMBOL(rdmsr_on_cpus); /* @@ -107,24 +114,9 @@ EXPORT_SYMBOL(rdmsr_on_cpus); * @msrs: array of MSR values * */ -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) { - struct msr_info rv; - int this_cpu; - - memset(&rv, 0, sizeof(rv)); - - rv.off = cpumask_first(mask); - rv.msrs = msrs; - rv.msr_no = msr_no; - - this_cpu = get_cpu(); - - if (cpumask_test_cpu(this_cpu, mask)) - __wrmsr_on_cpu(&rv); - - smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1); - put_cpu(); + __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } EXPORT_SYMBOL(wrmsr_on_cpus); -- cgit v1.2.3-70-g09d2 From 8bb014895547eeeb9aa61a654f24e41e15919304 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 16 Sep 2009 19:38:53 +0100 Subject: ASoC: Add S3C64xx IIS CDCLK source selection CDCLK can either be an output generated by the CPU, intended for use as the CODEC master clock, or an input (probably from the CODEC) providing a master clock for the IIS block. Signed-off-by: Mark Brown --- arch/arm/plat-s3c/include/plat/regs-s3c2412-iis.h | 2 ++ sound/soc/s3c24xx/s3c64xx-i2s.c | 13 +++++++++++++ sound/soc/s3c24xx/s3c64xx-i2s.h | 1 + 3 files changed, 16 insertions(+) (limited to 'arch') diff --git a/arch/arm/plat-s3c/include/plat/regs-s3c2412-iis.h b/arch/arm/plat-s3c/include/plat/regs-s3c2412-iis.h index 07659dad174..abf2fbc2eb2 100644 --- a/arch/arm/plat-s3c/include/plat/regs-s3c2412-iis.h +++ b/arch/arm/plat-s3c/include/plat/regs-s3c2412-iis.h @@ -67,6 +67,8 @@ #define S3C2412_IISMOD_BCLK_MASK (3 << 1) #define S3C2412_IISMOD_8BIT (1 << 0) +#define S3C64XX_IISMOD_CDCLKCON (1 << 12) + #define S3C2412_IISPSR_PSREN (1 << 15) #define S3C2412_IISFIC_TXFLUSH (1 << 15) diff --git a/sound/soc/s3c24xx/s3c64xx-i2s.c b/sound/soc/s3c24xx/s3c64xx-i2s.c index 3c06c401d0f..aaf452096be 100644 --- a/sound/soc/s3c24xx/s3c64xx-i2s.c +++ b/sound/soc/s3c24xx/s3c64xx-i2s.c @@ -99,6 +99,19 @@ static int s3c64xx_i2s_set_sysclk(struct snd_soc_dai *cpu_dai, iismod |= S3C64XX_IISMOD_IMS_SYSMUX; break; + case S3C64XX_CLKSRC_CDCLK: + switch (dir) { + case SND_SOC_CLOCK_IN: + iismod |= S3C64XX_IISMOD_CDCLKCON; + break; + case SND_SOC_CLOCK_OUT: + iismod &= ~S3C64XX_IISMOD_CDCLKCON; + break; + default: + return -EINVAL; + } + break; + default: return -EINVAL; } diff --git a/sound/soc/s3c24xx/s3c64xx-i2s.h b/sound/soc/s3c24xx/s3c64xx-i2s.h index 02148cee261..abe7253b55f 100644 --- a/sound/soc/s3c24xx/s3c64xx-i2s.h +++ b/sound/soc/s3c24xx/s3c64xx-i2s.h @@ -25,6 +25,7 @@ struct clk; #define S3C64XX_CLKSRC_PCLK (0) #define S3C64XX_CLKSRC_MUX (1) +#define S3C64XX_CLKSRC_CDCLK (2) extern struct snd_soc_dai s3c64xx_i2s_dai[]; -- cgit v1.2.3-70-g09d2 From c1558b55c55620f54f0f78cb8295947a2a3f6de2 Mon Sep 17 00:00:00 2001 From: Alessandro Rubini Date: Sun, 20 Sep 2009 23:28:24 +0200 Subject: ARM Nomadik: use new OneNand name and pdata This enables the onenand with the new platform device name. Moreover, it fixes a related typo that doesn't deserve a separate patch. Signed-off-by: Alessandro Rubini Acked-by: Andrea Gallo Signed-off-by: David Woodhouse --- arch/arm/mach-nomadik/board-nhk8815.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c index 6bfd537d5af..781b915819c 100644 --- a/arch/arm/mach-nomadik/board-nhk8815.c +++ b/arch/arm/mach-nomadik/board-nhk8815.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -142,7 +143,7 @@ static struct mtd_partition nhk8815_onenand_partitions[] = { } }; -static struct flash_platform_data nhk8815_onenand_data = { +static struct onenand_platform_data nhk8815_onenand_data = { .parts = nhk8815_onenand_partitions, .nr_parts = ARRAY_SIZE(nhk8815_onenand_partitions), }; @@ -156,7 +157,7 @@ static struct resource nhk8815_onenand_resource[] = { }; static struct platform_device nhk8815_onenand_device = { - .name = "onenand", + .name = "onenand-flash", .id = -1, .dev = { .platform_data = &nhk8815_onenand_data, @@ -167,10 +168,10 @@ static struct platform_device nhk8815_onenand_device = { static void __init nhk8815_onenand_init(void) { -#ifdef CONFIG_ONENAND +#ifdef CONFIG_MTD_ONENAND /* Set up SMCS0 for OneNand */ - writel(0x000030db, FSMC_BCR0); - writel(0x02100551, FSMC_BTR0); + writel(0x000030db, FSMC_BCR(0)); + writel(0x02100551, FSMC_BTR(0)); #endif } -- cgit v1.2.3-70-g09d2 From 9f0cf4adb6aa0bfccf675c938124e68f7f06349d Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sat, 26 Sep 2009 14:33:01 +0200 Subject: x86: Use __builtin_object_size() to validate the buffer size for copy_from_user() gcc (4.x) supports the __builtin_object_size() builtin, which reports the size of an object that a pointer point to, when known at compile time. If the buffer size is not known at compile time, a constant -1 is returned. This patch uses this feature to add a sanity check to copy_from_user(); if the target buffer is known to be smaller than the copy size, the copy is aborted and a WARNing is emitted in memory debug mode. These extra checks compile away when the object size is not known, or if both the buffer size and the copy length are constants. Signed-off-by: Arjan van de Ven LKML-Reference: <20090926143301.2c396b94@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/uaccess_32.h | 19 ++++++++++++++++++- arch/x86/include/asm/uaccess_64.h | 19 ++++++++++++++++++- arch/x86/kernel/x8664_ksyms_64.c | 2 +- arch/x86/lib/copy_user_64.S | 4 ++-- arch/x86/lib/usercopy_32.c | 4 ++-- include/linux/compiler-gcc4.h | 2 ++ include/linux/compiler.h | 4 ++++ 7 files changed, 47 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 632fb44b4cb..582d6aef741 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -187,9 +187,26 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n); -unsigned long __must_check copy_from_user(void *to, +unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long n); + +static inline unsigned long __must_check copy_from_user(void *to, + const void __user *from, + unsigned long n) +{ + int sz = __compiletime_object_size(to); + int ret = -EFAULT; + + if (likely(sz == -1 || sz >= n)) + ret = _copy_from_user(to, from, n); +#ifdef CONFIG_DEBUG_VM + else + WARN(1, "Buffer overflow detected!\n"); +#endif + return ret; +} + long __must_check strncpy_from_user(char *dst, const char __user *src, long count); long __must_check __strncpy_from_user(char *dst, diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index db24b215fc5..ce6fec7ce38 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -21,10 +21,27 @@ copy_user_generic(void *to, const void *from, unsigned len); __must_check unsigned long copy_to_user(void __user *to, const void *from, unsigned len); __must_check unsigned long -copy_from_user(void *to, const void __user *from, unsigned len); +_copy_from_user(void *to, const void __user *from, unsigned len); __must_check unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len); +static inline unsigned long __must_check copy_from_user(void *to, + const void __user *from, + unsigned long n) +{ + int sz = __compiletime_object_size(to); + int ret = -EFAULT; + + if (likely(sz == -1 || sz >= n)) + ret = _copy_from_user(to, from, n); +#ifdef CONFIG_DEBUG_VM + else + WARN(1, "Buffer overflow detected!\n"); +#endif + return ret; +} + + static __always_inline __must_check int __copy_from_user(void *dst, const void __user *src, unsigned size) { diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 3909e3ba5ce..a0cdd8cc1d6 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(copy_user_generic); EXPORT_SYMBOL(__copy_user_nocache); -EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(copy_to_user); EXPORT_SYMBOL(__copy_from_user_inatomic); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 6ba0f7bb85e..4be3c415b3e 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -78,7 +78,7 @@ ENTRY(copy_to_user) ENDPROC(copy_to_user) /* Standard copy_from_user with segment limit checking */ -ENTRY(copy_from_user) +ENTRY(_copy_from_user) CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx @@ -88,7 +88,7 @@ ENTRY(copy_from_user) jae bad_from_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENDPROC(copy_from_user) +ENDPROC(_copy_from_user) ENTRY(copy_user_generic) CFI_STARTPROC diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1f118d462ac..8498684e45b 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -874,7 +874,7 @@ EXPORT_SYMBOL(copy_to_user); * data to the requested size using zero bytes. */ unsigned long -copy_from_user(void *to, const void __user *from, unsigned long n) +_copy_from_user(void *to, const void __user *from, unsigned long n) { if (access_ok(VERIFY_READ, from, n)) n = __copy_from_user(to, from, n); @@ -882,4 +882,4 @@ copy_from_user(void *to, const void __user *from, unsigned long n) memset(to, 0, n); return n; } -EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(_copy_from_user); diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 450fa597c94..a3aef5d55db 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -37,3 +37,5 @@ #define __cold __attribute__((__cold__)) #endif + +#define __compiletime_object_size(obj) __builtin_object_size(obj, 0) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 04fb5135b4e..8e54108688f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -266,6 +266,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) #endif +/* Compile time object size, -1 for unknown */ +#ifndef __compiletime_object_size +# define __compiletime_object_size(obj) -1 +#endif /* * Prevent the compiler from merging or refetching accesses. The compiler * is also forbidden from reordering successive instances of ACCESS_ONCE(), -- cgit v1.2.3-70-g09d2 From ff60fab71bb3b4fdbf8caf57ff3739ffd0887396 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 28 Sep 2009 14:21:22 +0200 Subject: x86: Use __builtin_memset and __builtin_memcpy for memset/memcpy GCC provides reasonable memset/memcpy functions itself, with __builtin_memset and __builtin_memcpy. For the "unknown" cases, it'll fall back to our current existing functions, but for fixed size versions it'll inline something smart. Quite often that will be the same as we have now, but sometimes it can do something smarter (for example, if the code then sets the first member of a struct, it can do a shorter memset). In addition, and this is more important, gcc knows which registers and such are not clobbered (while for our asm version it pretty much acts like a compiler barrier), so for various cases it can avoid reloading values. The effect on codesize is shown below on my typical laptop .config: text data bss dec hex filename 5605675 2041100 6525148 14171923 d83f13 vmlinux.before 5595849 2041668 6525148 14162665 d81ae9 vmlinux.after Due to some not-so-good behavior in the gcc 3.x series, this change is only done for GCC 4.x and above. Signed-off-by: Arjan van de Ven LKML-Reference: <20090928142122.6fc57e9c@infradead.org> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/string_32.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index ae907e61718..3d3e8353ee5 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -177,10 +177,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) */ #ifndef CONFIG_KMEMCHECK + +#if (__GNUC__ >= 4) +#define memcpy(t, f, n) __builtin_memcpy(t, f, n) +#else #define memcpy(t, f, n) \ (__builtin_constant_p((n)) \ ? __constant_memcpy((t), (f), (n)) \ : __memcpy((t), (f), (n))) +#endif #else /* * kmemcheck becomes very happy if we use the REP instructions unconditionally, @@ -316,11 +321,15 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, : __memset_generic((s), (c), (count))) #define __HAVE_ARCH_MEMSET +#if (__GNUC__ >= 4) +#define memset(s, c, count) __builtin_memset(s, c, count) +#else #define memset(s, c, count) \ (__builtin_constant_p(c) \ ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ (count)) \ : __memset((s), (c), (count))) +#endif /* * find the first occurrence of byte 'c', or 1 past the area if none -- cgit v1.2.3-70-g09d2 From 4a3127693001c61a21d1ce680db6340623f52e93 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 30 Sep 2009 13:05:23 +0200 Subject: x86: Turn the copy_from_user check into an (optional) compile time warning A previous patch added the buffer size check to copy_from_user(). One of the things learned from analyzing the result of the previous patch is that in general, gcc is really good at proving that the code contains sufficient security checks to not need to do a runtime check. But that for those cases where gcc could not prove this, there was a relatively high percentage of real security issues. This patch turns the case of "gcc cannot prove" into a compile time warning, as long as a sufficiently new gcc is in use that supports this. The objective is that these warnings will trigger developers checking new cases out before a security hole enters a linux kernel release. Signed-off-by: Arjan van de Ven Cc: Linus Torvalds Cc: "David S. Miller" Cc: James Morris Cc: Jan Beulich LKML-Reference: <20090930130523.348ae6c4@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/uaccess_32.h | 12 +++++++++--- arch/x86/lib/usercopy_32.c | 6 ++++++ include/linux/compiler-gcc4.h | 3 +++ include/linux/compiler.h | 4 ++++ 4 files changed, 22 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 582d6aef741..952f9e793c3 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -191,6 +191,13 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long n); + +extern void copy_from_user_overflow(void) +#ifdef CONFIG_DEBUG_STACKOVERFLOW + __compiletime_warning("copy_from_user() buffer size is not provably correct") +#endif +; + static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) @@ -200,10 +207,9 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) ret = _copy_from_user(to, from, n); -#ifdef CONFIG_DEBUG_VM else - WARN(1, "Buffer overflow detected!\n"); -#endif + copy_from_user_overflow(); + return ret; } diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 8498684e45b..e218d5df85f 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -883,3 +883,9 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } EXPORT_SYMBOL(_copy_from_user); + +void copy_from_user_overflow(void) +{ + WARN(1, "Buffer overflow detected!\n"); +} +EXPORT_SYMBOL(copy_from_user_overflow); diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index a3aef5d55db..f1709c1f9ea 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -39,3 +39,6 @@ #endif #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#if __GNUC_MINOR__ >= 4 +#define __compiletime_warning(message) __attribute__((warning(message))) +#endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8e54108688f..950356311f1 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -270,6 +270,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 #endif +#ifndef __compiletime_warning +# define __compiletime_warning(message) +#endif + /* * Prevent the compiler from merging or refetching accesses. The compiler * is also forbidden from reordering successive instances of ACCESS_ONCE(), -- cgit v1.2.3-70-g09d2 From 7c68af6e32c73992bad24107311f3433c89016e2 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sat, 19 Sep 2009 09:40:22 +0300 Subject: core, x86: Add user return notifiers Add a general per-cpu notifier that is called whenever the kernel is about to return to userspace. The notifier uses a thread_info flag and existing checks, so there is no impact on user return or context switch fast paths. This will be used initially to speed up KVM task switching by lazily updating MSRs. Signed-off-by: Avi Kivity LKML-Reference: <1253342422-13811-1-git-send-email-avi@redhat.com> Signed-off-by: H. Peter Anvin --- arch/Kconfig | 10 ++++++++ arch/x86/Kconfig | 1 + arch/x86/include/asm/thread_info.h | 7 ++++-- arch/x86/kernel/process.c | 2 ++ arch/x86/kernel/signal.c | 3 +++ include/linux/user-return-notifier.h | 42 ++++++++++++++++++++++++++++++++ kernel/user-return-notifier.c | 46 ++++++++++++++++++++++++++++++++++++ 7 files changed, 109 insertions(+), 2 deletions(-) create mode 100644 include/linux/user-return-notifier.h create mode 100644 kernel/user-return-notifier.c (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 7f418bbc261..4e312fffbfd 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -83,6 +83,13 @@ config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES +config USER_RETURN_NOTIFIER + bool + depends on HAVE_USER_RETURN_NOTIFIER + help + Provide a kernel-internal notification when a cpu is about to + switch to user mode. + config HAVE_IOREMAP_PROT bool @@ -126,4 +133,7 @@ config HAVE_DMA_API_DEBUG config HAVE_DEFAULT_NO_SPIN_MUTEXES bool +config HAVE_USER_RETURN_NOTIFIER + bool + source "kernel/gcov/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8da93745c08..1df175d15aa 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -50,6 +50,7 @@ config X86 select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA select HAVE_ARCH_KMEMCHECK + select HAVE_USER_RETURN_NOTIFIER config OUTPUT_FORMAT string diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d27d0a2fec4..375c917c37d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ +#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ @@ -107,6 +108,7 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) +#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) @@ -142,13 +144,14 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME) + (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ + _TIF_USER_RETURN_NOTIFY) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) -#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW +#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) #define PREEMPT_ACTIVE 0x10000000 diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5284cd2b577..e51b056fc88 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -224,6 +225,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } + propagate_user_return_notify(prev_p, next_p); } int sys_fork(struct pt_regs *regs) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6a44a76055a..c49f90f7957 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -872,6 +873,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (current->replacement_session_keyring) key_replace_session_keyring(); } + if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); diff --git a/include/linux/user-return-notifier.h b/include/linux/user-return-notifier.h new file mode 100644 index 00000000000..b6ac056291d --- /dev/null +++ b/include/linux/user-return-notifier.h @@ -0,0 +1,42 @@ +#ifndef _LINUX_USER_RETURN_NOTIFIER_H +#define _LINUX_USER_RETURN_NOTIFIER_H + +#ifdef CONFIG_USER_RETURN_NOTIFIER + +#include +#include + +struct user_return_notifier { + void (*on_user_return)(struct user_return_notifier *urn); + struct hlist_node link; +}; + + +void user_return_notifier_register(struct user_return_notifier *urn); +void user_return_notifier_unregister(struct user_return_notifier *urn); + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ + if (test_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY)) { + clear_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY); + set_tsk_thread_flag(next, TIF_USER_RETURN_NOTIFY); + } +} + +void fire_user_return_notifiers(void); + +#else + +struct user_return_notifier {}; + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ +} + +static inline void fire_user_return_notifiers(void) {} + +#endif + +#endif diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c new file mode 100644 index 00000000000..530ccb81651 --- /dev/null +++ b/kernel/user-return-notifier.c @@ -0,0 +1,46 @@ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct hlist_head, return_notifier_list); + +#define URN_LIST_HEAD per_cpu(return_notifier_list, raw_smp_processor_id()) + +/* + * Request a notification when the current cpu returns to userspace. Must be + * called in atomic context. The notifier will also be called in atomic + * context. + */ +void user_return_notifier_register(struct user_return_notifier *urn) +{ + set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); + hlist_add_head(&urn->link, &URN_LIST_HEAD); +} +EXPORT_SYMBOL_GPL(user_return_notifier_register); + +/* + * Removes a registered user return notifier. Must be called from atomic + * context, and from the same cpu registration occured in. + */ +void user_return_notifier_unregister(struct user_return_notifier *urn) +{ + hlist_del(&urn->link); + if (hlist_empty(&URN_LIST_HEAD)) + clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); +} +EXPORT_SYMBOL_GPL(user_return_notifier_unregister); + +/* Calls registered user return notifiers */ +void fire_user_return_notifiers(void) +{ + struct user_return_notifier *urn; + struct hlist_node *tmp1, *tmp2; + struct hlist_head *head; + + head = &get_cpu_var(return_notifier_list); + hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) + urn->on_user_return(urn); + put_cpu_var(); +} -- cgit v1.2.3-70-g09d2 From 126b3fcdecd350cad9700908d0ad845084e26a31 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Oct 2009 13:28:55 +0900 Subject: ia64: don't alias VMALLOC_END to vmalloc_end If CONFIG_VIRTUAL_MEM_MAP is enabled, ia64 defines macro VMALLOC_END as unsigned long variable vmalloc_end which is adjusted to prepare room for vmemmap. This becomes probnlematic if a local variables vmalloc_end is defined in some function (not very unlikely) and VMALLOC_END is used in the function - the function thinks its referencing the global VMALLOC_END value but would be referencing its own local vmalloc_end variable. There's no reason VMALLOC_END should be a macro. Just define it as an unsigned long variable if CONFIG_VIRTUAL_MEM_MAP is set to avoid nasty surprises. Signed-off-by: Tejun Heo Acked-by: Tony Luck Cc: Fenghua Yu Cc: linux-ia64 Cc: Christoph Lameter --- arch/ia64/include/asm/meminit.h | 2 +- arch/ia64/include/asm/pgtable.h | 3 +-- arch/ia64/mm/contig.c | 4 ++-- arch/ia64/mm/discontig.c | 4 ++-- arch/ia64/mm/init.c | 4 ++-- 5 files changed, 8 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h index 688a812c017..61c7b1750b1 100644 --- a/arch/ia64/include/asm/meminit.h +++ b/arch/ia64/include/asm/meminit.h @@ -61,7 +61,7 @@ extern int register_active_ranges(u64 start, u64 len, int nid); #ifdef CONFIG_VIRTUAL_MEM_MAP # define LARGE_GAP 0x40000000 /* Use virtual mem map if hole is > than this */ - extern unsigned long vmalloc_end; + extern unsigned long VMALLOC_END; extern struct page *vmem_map; extern int find_largest_hole(u64 start, u64 end, void *arg); extern int create_mem_map_page_table(u64 start, u64 end, void *arg); diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 8840a690d1e..69bf13857a9 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -228,8 +228,7 @@ ia64_phys_addr_valid (unsigned long addr) #define VMALLOC_START (RGN_BASE(RGN_GATE) + 0x200000000UL) #ifdef CONFIG_VIRTUAL_MEM_MAP # define VMALLOC_END_INIT (RGN_BASE(RGN_GATE) + (1UL << (4*PAGE_SHIFT - 9))) -# define VMALLOC_END vmalloc_end - extern unsigned long vmalloc_end; +extern unsigned long VMALLOC_END; #else #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_SPARSEMEM_VMEMMAP) /* SPARSEMEM_VMEMMAP uses half of vmalloc... */ diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 2f724d2bf29..1341437c1b2 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -270,8 +270,8 @@ paging_init (void) map_size = PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * sizeof(struct page)); - vmalloc_end -= map_size; - vmem_map = (struct page *) vmalloc_end; + VMALLOC_END -= map_size; + vmem_map = (struct page *) VMALLOC_END; efi_memmap_walk(create_mem_map_page_table, NULL); /* diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index d85ba98d900..9f24b3c6dc7 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -666,9 +666,9 @@ void __init paging_init(void) sparse_init(); #ifdef CONFIG_VIRTUAL_MEM_MAP - vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * + VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * sizeof(struct page)); - vmem_map = (struct page *) vmalloc_end; + vmem_map = (struct page *) VMALLOC_END; efi_memmap_walk(create_mem_map_page_table, NULL); printk("Virtual mem_map starts at 0x%p\n", vmem_map); #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 1857766a63c..b9609c69343 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -44,8 +44,8 @@ extern void ia64_tlb_init (void); unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL; #ifdef CONFIG_VIRTUAL_MEM_MAP -unsigned long vmalloc_end = VMALLOC_END_INIT; -EXPORT_SYMBOL(vmalloc_end); +unsigned long VMALLOC_END = VMALLOC_END_INIT; +EXPORT_SYMBOL(VMALLOC_END); struct page *vmem_map; EXPORT_SYMBOL(vmem_map); #endif -- cgit v1.2.3-70-g09d2 From 12cda817779ce5381a9a4ba8d464abe17c50a9e2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Oct 2009 13:28:56 +0900 Subject: ia64: initialize cpu maps early All information necessary to initialize cpu possible and present maps are available once early_acpi_boot_init() is complete. Reorganize setup_arch() and acpi init functions such that, * CPU information is printed after LAPIC entries are parsed in early_acpi_boot_init(). * smp_build_cpu_map() is called by setup_arch() instead of acpi functions. * smp_build_cpu_map() is called once all CPU related information is available before memory is initialized. This is primarily to allow find_memory() to use cpu maps but is also a general cleanup. Please note that with this change, the somewhat ad-hoc early_cpu_possible_map defined and used for NUMA configurations is probably unnecessary. Something to clean up another day. Signed-off-by: Tejun Heo Acked-by: Tony Luck Cc: Fenghua Yu Cc: linux-ia64 --- arch/ia64/kernel/acpi.c | 33 +++++++++++++++------------------ arch/ia64/kernel/setup.c | 11 +++++------ 2 files changed, 20 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index baec6f00f7f..40574ae1140 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -702,11 +702,23 @@ int __init early_acpi_boot_init(void) printk(KERN_ERR PREFIX "Error parsing MADT - no LAPIC entries\n"); +#ifdef CONFIG_SMP + if (available_cpus == 0) { + printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n"); + printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id()); + smp_boot_data.cpu_phys_id[available_cpus] = + hard_smp_processor_id(); + available_cpus = 1; /* We've got at least one of these, no? */ + } + smp_boot_data.cpu_count = available_cpus; +#endif + /* Make boot-up look pretty */ + printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus, + total_cpus); + return 0; } - - int __init acpi_boot_init(void) { @@ -769,18 +781,8 @@ int __init acpi_boot_init(void) if (acpi_table_parse(ACPI_SIG_FADT, acpi_parse_fadt)) printk(KERN_ERR PREFIX "Can't find FADT\n"); +#ifdef CONFIG_ACPI_NUMA #ifdef CONFIG_SMP - if (available_cpus == 0) { - printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n"); - printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id()); - smp_boot_data.cpu_phys_id[available_cpus] = - hard_smp_processor_id(); - available_cpus = 1; /* We've got at least one of these, no? */ - } - smp_boot_data.cpu_count = available_cpus; - - smp_build_cpu_map(); -# ifdef CONFIG_ACPI_NUMA if (srat_num_cpus == 0) { int cpu, i = 1; for (cpu = 0; cpu < smp_boot_data.cpu_count; cpu++) @@ -789,14 +791,9 @@ int __init acpi_boot_init(void) node_cpuid[i++].phys_id = smp_boot_data.cpu_phys_id[cpu]; } -# endif #endif -#ifdef CONFIG_ACPI_NUMA build_cpu_to_node_map(); #endif - /* Make boot-up look pretty */ - printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus, - total_cpus); return 0; } diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 1de86c96801..5d77c1e1c0c 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -566,19 +566,18 @@ setup_arch (char **cmdline_p) early_acpi_boot_init(); # ifdef CONFIG_ACPI_NUMA acpi_numa_init(); -#ifdef CONFIG_ACPI_HOTPLUG_CPU +# ifdef CONFIG_ACPI_HOTPLUG_CPU prefill_possible_map(); -#endif +# endif per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ? 32 : cpus_weight(early_cpu_possible_map)), additional_cpus > 0 ? additional_cpus : 0); # endif -#else -# ifdef CONFIG_SMP - smp_build_cpu_map(); /* happens, e.g., with the Ski simulator */ -# endif #endif /* CONFIG_APCI_BOOT */ +#ifdef CONFIG_SMP + smp_build_cpu_map(); +#endif find_memory(); /* process SAL system table: */ -- cgit v1.2.3-70-g09d2 From 36886478f59ec0fdc24a8877c572b92f8d416aba Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Oct 2009 13:28:56 +0900 Subject: ia64: allocate percpu area for cpu0 like percpu areas for other cpus cpu0 used special percpu area reserved by the linker, __cpu0_per_cpu, which is set up early in boot by head.S. However, this doesn't guarantee that the area will be on the same node as cpu0 and the percpu area for cpu0 ends up very far away from percpu areas for other cpus which cause problems for congruent percpu allocator. This patch makes percpu area initialization allocate percpu area for cpu0 like any other cpus and copy it from __cpu0_per_cpu which now resides in the __init area. This means that for cpu0, percpu area is first setup at __cpu0_per_cpu early by head.S and then moved to an area in the linear mapping during memory initialization and it's not allowed to take a pointer to percpu variables between head.S and memory initialization. Signed-off-by: Tejun Heo Acked-by: Tony Luck Cc: Fenghua Yu Cc: linux-ia64 --- arch/ia64/kernel/vmlinux.lds.S | 11 ++++++----- arch/ia64/mm/contig.c | 41 +++++++++++++++++++++++++++-------------- arch/ia64/mm/discontig.c | 35 ++++++++++++++++++++++++----------- 3 files changed, 57 insertions(+), 30 deletions(-) (limited to 'arch') diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 0a0c77b2c98..1295ba327f6 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -166,6 +166,12 @@ SECTIONS } #endif +#ifdef CONFIG_SMP + . = ALIGN(PERCPU_PAGE_SIZE); + __cpu0_per_cpu = .; + . = . + PERCPU_PAGE_SIZE; /* cpu0 per-cpu space */ +#endif + . = ALIGN(PAGE_SIZE); __init_end = .; @@ -198,11 +204,6 @@ SECTIONS data : { } :data .data : AT(ADDR(.data) - LOAD_OFFSET) { -#ifdef CONFIG_SMP - . = ALIGN(PERCPU_PAGE_SIZE); - __cpu0_per_cpu = .; - . = . + PERCPU_PAGE_SIZE; /* cpu0 per-cpu space */ -#endif INIT_TASK_DATA(PAGE_SIZE) CACHELINE_ALIGNED_DATA(SMP_CACHE_BYTES) READ_MOSTLY_DATA(SMP_CACHE_BYTES) diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 1341437c1b2..351da0a06cd 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -154,36 +154,49 @@ static void *cpu_data; void * __cpuinit per_cpu_init (void) { - int cpu; - static int first_time=1; + static bool first_time = true; + void *cpu0_data = __cpu0_per_cpu; + unsigned int cpu; + + if (!first_time) + goto skip; + first_time = false; /* * get_free_pages() cannot be used before cpu_init() done. BSP * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls * get_zeroed_page(). */ - if (first_time) { - void *cpu0_data = __cpu0_per_cpu; + for (cpu = 0; cpu < NR_CPUS; cpu++) { + void *src = cpu == 0 ? cpu0_data : __phys_per_cpu_start; - first_time=0; + memcpy(cpu_data, src, __per_cpu_end - __per_cpu_start); + __per_cpu_offset[cpu] = (char *)cpu_data - __per_cpu_start; + per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu]; - __per_cpu_offset[0] = (char *) cpu0_data - __per_cpu_start; - per_cpu(local_per_cpu_offset, 0) = __per_cpu_offset[0]; + /* + * percpu area for cpu0 is moved from the __init area + * which is setup by head.S and used till this point. + * Update ar.k3. This move is ensures that percpu + * area for cpu0 is on the correct node and its + * virtual address isn't insanely far from other + * percpu areas which is important for congruent + * percpu allocator. + */ + if (cpu == 0) + ia64_set_kr(IA64_KR_PER_CPU_DATA, __pa(cpu_data) - + (unsigned long)__per_cpu_start); - for (cpu = 1; cpu < NR_CPUS; cpu++) { - memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start); - __per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start; - cpu_data += PERCPU_PAGE_SIZE; - per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu]; - } + cpu_data += PERCPU_PAGE_SIZE; } +skip: return __per_cpu_start + __per_cpu_offset[smp_processor_id()]; } static inline void alloc_per_cpu_data(void) { - cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS-1, + cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS, PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); } #else diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 9f24b3c6dc7..200282b9298 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -143,17 +143,30 @@ static void *per_cpu_node_setup(void *cpu_data, int node) int cpu; for_each_possible_early_cpu(cpu) { - if (cpu == 0) { - void *cpu0_data = __cpu0_per_cpu; - __per_cpu_offset[cpu] = (char*)cpu0_data - - __per_cpu_start; - } else if (node == node_cpuid[cpu].nid) { - memcpy(__va(cpu_data), __phys_per_cpu_start, - __per_cpu_end - __per_cpu_start); - __per_cpu_offset[cpu] = (char*)__va(cpu_data) - - __per_cpu_start; - cpu_data += PERCPU_PAGE_SIZE; - } + void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start; + + if (node != node_cpuid[cpu].nid) + continue; + + memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start); + __per_cpu_offset[cpu] = (char *)__va(cpu_data) - + __per_cpu_start; + + /* + * percpu area for cpu0 is moved from the __init area + * which is setup by head.S and used till this point. + * Update ar.k3. This move is ensures that percpu + * area for cpu0 is on the correct node and its + * virtual address isn't insanely far from other + * percpu areas which is important for congruent + * percpu allocator. + */ + if (cpu == 0) + ia64_set_kr(IA64_KR_PER_CPU_DATA, + (unsigned long)cpu_data - + (unsigned long)__per_cpu_start); + + cpu_data += PERCPU_PAGE_SIZE; } #endif return cpu_data; -- cgit v1.2.3-70-g09d2 From 52594762a39dfb6338c9d0906ca21dd9ae9453be Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Oct 2009 13:28:56 +0900 Subject: ia64: convert to dynamic percpu allocator Unlike other archs, ia64 reserves space for percpu areas during early memory initialization. These areas occupy a contiguous region indexed by cpu number on contiguous memory model or are grouped by node on discontiguous memory model. As allocation and initialization are done by the arch code, all that setup_per_cpu_areas() needs to do is communicating the determined layout to the percpu allocator. This patch implements setup_per_cpu_areas() for both contig and discontig memory models and drops HAVE_LEGACY_PER_CPU_AREA. Please note that for contig model, the allocation itself is modified only to allocate for possible cpus instead of NR_CPUS. As dynamic percpu allocator can handle non-direct mapping, there's no reason to allocate memory for cpus which aren't possible. Signed-off-by: Tejun Heo Acked-by: Tony Luck Cc: Fenghua Yu Cc: linux-ia64 --- arch/ia64/Kconfig | 3 -- arch/ia64/kernel/setup.c | 12 ------- arch/ia64/mm/contig.c | 58 ++++++++++++++++++++++++++++++--- arch/ia64/mm/discontig.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 138 insertions(+), 20 deletions(-) (limited to 'arch') diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 1ee596cd942..2d7f56a98e0 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -87,9 +87,6 @@ config GENERIC_TIME_VSYSCALL bool default y -config HAVE_LEGACY_PER_CPU_AREA - def_bool y - config HAVE_SETUP_PER_CPU_AREA def_bool y diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 5d77c1e1c0c..bc1ef4ae828 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -854,18 +854,6 @@ identify_cpu (struct cpuinfo_ia64 *c) c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1)); } -/* - * In UP configuration, setup_per_cpu_areas() is defined in - * include/linux/percpu.h - */ -#ifdef CONFIG_SMP -void __init -setup_per_cpu_areas (void) -{ - /* start_kernel() requires this... */ -} -#endif - /* * Do the following calculations: * diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 351da0a06cd..54bf5405981 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -163,11 +163,11 @@ per_cpu_init (void) first_time = false; /* - * get_free_pages() cannot be used before cpu_init() done. BSP - * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls - * get_zeroed_page(). + * get_free_pages() cannot be used before cpu_init() done. + * BSP allocates PERCPU_PAGE_SIZE bytes for all possible CPUs + * to avoid that AP calls get_zeroed_page(). */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { + for_each_possible_cpu(cpu) { void *src = cpu == 0 ? cpu0_data : __phys_per_cpu_start; memcpy(cpu_data, src, __per_cpu_end - __per_cpu_start); @@ -196,9 +196,57 @@ skip: static inline void alloc_per_cpu_data(void) { - cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS, + cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * num_possible_cpus(), PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); } + +/** + * setup_per_cpu_areas - setup percpu areas + * + * Arch code has already allocated and initialized percpu areas. All + * this function has to do is to teach the determined layout to the + * dynamic percpu allocator, which happens to be more complex than + * creating whole new ones using helpers. + */ +void __init +setup_per_cpu_areas(void) +{ + struct pcpu_alloc_info *ai; + struct pcpu_group_info *gi; + unsigned int cpu; + ssize_t static_size, reserved_size, dyn_size; + int rc; + + ai = pcpu_alloc_alloc_info(1, num_possible_cpus()); + if (!ai) + panic("failed to allocate pcpu_alloc_info"); + gi = &ai->groups[0]; + + /* units are assigned consecutively to possible cpus */ + for_each_possible_cpu(cpu) + gi->cpu_map[gi->nr_units++] = cpu; + + /* set parameters */ + static_size = __per_cpu_end - __per_cpu_start; + reserved_size = PERCPU_MODULE_RESERVE; + dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size; + if (dyn_size < 0) + panic("percpu area overflow static=%zd reserved=%zd\n", + static_size, reserved_size); + + ai->static_size = static_size; + ai->reserved_size = reserved_size; + ai->dyn_size = dyn_size; + ai->unit_size = PERCPU_PAGE_SIZE; + ai->atom_size = PAGE_SIZE; + ai->alloc_size = PERCPU_PAGE_SIZE; + + rc = pcpu_setup_first_chunk(ai, __per_cpu_start + __per_cpu_offset[0]); + if (rc) + panic("failed to setup percpu area (err=%d)", rc); + + pcpu_free_alloc_info(ai); +} #else #define alloc_per_cpu_data() do { } while (0) #endif /* CONFIG_SMP */ diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 200282b9298..40e4c1fbf76 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -172,6 +172,91 @@ static void *per_cpu_node_setup(void *cpu_data, int node) return cpu_data; } +#ifdef CONFIG_SMP +/** + * setup_per_cpu_areas - setup percpu areas + * + * Arch code has already allocated and initialized percpu areas. All + * this function has to do is to teach the determined layout to the + * dynamic percpu allocator, which happens to be more complex than + * creating whole new ones using helpers. + */ +void __init setup_per_cpu_areas(void) +{ + struct pcpu_alloc_info *ai; + struct pcpu_group_info *uninitialized_var(gi); + unsigned int *cpu_map; + void *base; + unsigned long base_offset; + unsigned int cpu; + ssize_t static_size, reserved_size, dyn_size; + int node, prev_node, unit, nr_units, rc; + + ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids); + if (!ai) + panic("failed to allocate pcpu_alloc_info"); + cpu_map = ai->groups[0].cpu_map; + + /* determine base */ + base = (void *)ULONG_MAX; + for_each_possible_cpu(cpu) + base = min(base, + (void *)(__per_cpu_offset[cpu] + __per_cpu_start)); + base_offset = (void *)__per_cpu_start - base; + + /* build cpu_map, units are grouped by node */ + unit = 0; + for_each_node(node) + for_each_possible_cpu(cpu) + if (node == node_cpuid[cpu].nid) + cpu_map[unit++] = cpu; + nr_units = unit; + + /* set basic parameters */ + static_size = __per_cpu_end - __per_cpu_start; + reserved_size = PERCPU_MODULE_RESERVE; + dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size; + if (dyn_size < 0) + panic("percpu area overflow static=%zd reserved=%zd\n", + static_size, reserved_size); + + ai->static_size = static_size; + ai->reserved_size = reserved_size; + ai->dyn_size = dyn_size; + ai->unit_size = PERCPU_PAGE_SIZE; + ai->atom_size = PAGE_SIZE; + ai->alloc_size = PERCPU_PAGE_SIZE; + + /* + * CPUs are put into groups according to node. Walk cpu_map + * and create new groups at node boundaries. + */ + prev_node = -1; + ai->nr_groups = 0; + for (unit = 0; unit < nr_units; unit++) { + cpu = cpu_map[unit]; + node = node_cpuid[cpu].nid; + + if (node == prev_node) { + gi->nr_units++; + continue; + } + prev_node = node; + + gi = &ai->groups[ai->nr_groups++]; + gi->nr_units = 1; + gi->base_offset = __per_cpu_offset[cpu] + base_offset; + gi->cpu_map = &cpu_map[unit]; + } + + rc = pcpu_setup_first_chunk(ai, base); + if (rc) + panic("failed to setup percpu area (err=%d)", rc); + + pcpu_free_alloc_info(ai); +} +#endif + /** * fill_pernode - initialize pernode data. * @node: the node id. -- cgit v1.2.3-70-g09d2 From 63312b6a6faae3f2e5577f2b001e3b504f10a2aa Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 2 Oct 2009 07:50:50 -0700 Subject: x86: Add a Kconfig option to turn the copy_from_user warnings into errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For automated testing it is useful to have the option to turn the warnings on copy_from_user() etc checks into errors: In function ‘copy_from_user’, inlined from ‘fd_copyin’ at drivers/block/floppy.c:3080, inlined from ‘fd_ioctl’ at drivers/block/floppy.c:3503: linux/arch/x86/include/asm/uaccess_32.h:213: error: call to ‘copy_from_user_overflow’ declared with attribute error: copy_from_user buffer size is not provably correct Signed-off-by: Arjan van de Ven Cc: Linus Torvalds Cc: Andrew Morton LKML-Reference: <20091002075050.4e9f7641@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.debug | 14 ++++++++++++++ arch/x86/include/asm/uaccess_32.h | 4 +++- include/linux/compiler-gcc4.h | 1 + include/linux/compiler.h | 3 +++ 4 files changed, 21 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d105f29bb6b..1bd2e36f153 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -287,4 +287,18 @@ config OPTIMIZE_INLINING If unsure, say N. +config DEBUG_STRICT_USER_COPY_CHECKS + bool "Strict copy size checks" + depends on DEBUG_KERNEL + ---help--- + Enabling this option turns a certain set of sanity checks for user + copy operations into compile time failures. + + The copy_from_user() etc checks are there to help test if there + are sufficient security checks on the length argument of + the copy operation, by having gcc prove that the argument is + within bounds. + + If unsure, or if you run an older (pre 4.4) gcc, say N. + endmenu diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 952f9e793c3..0c9825e97f3 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -193,7 +193,9 @@ unsigned long __must_check _copy_from_user(void *to, extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STACKOVERFLOW +#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS + __compiletime_error("copy_from_user() buffer size is not provably correct") +#else __compiletime_warning("copy_from_user() buffer size is not provably correct") #endif ; diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index f1709c1f9ea..77542c57e20 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -41,4 +41,5 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #if __GNUC_MINOR__ >= 4 #define __compiletime_warning(message) __attribute__((warning(message))) +#define __compiletime_error(message) __attribute__((error(message))) #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 950356311f1..88fd4b673cb 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -273,6 +273,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #ifndef __compiletime_warning # define __compiletime_warning(message) #endif +#ifndef __compiletime_error +# define __compiletime_error(message) +#endif /* * Prevent the compiler from merging or refetching accesses. The compiler -- cgit v1.2.3-70-g09d2 From 98059e3463383b18fd79181179cd539b74846b47 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 1 Oct 2009 17:11:10 +0200 Subject: x86: AMD Geode LX optimizations Add CPU optimizations for AMD Geode LX. Signed-off-by: Matteo Croce LKML-Reference: <40101cc30910010811v5d15ff4cx9dd57c9cc9b4b045@mail.gmail.com> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig.cpu | 2 +- arch/x86/Makefile_32.cpu | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 527519b8a9f..979de294710 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -406,7 +406,7 @@ config X86_CMPXCHG64 # generates cmov. config X86_CMOV def_bool y - depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM) + depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) config X86_MINIMUM_CPU_FAMILY int diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 30e9a264f69..cbf0776dbec 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -41,7 +41,7 @@ cflags-$(CONFIG_X86_ELAN) += -march=i486 # Geode GX1 support cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx - +cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx) # add at the end to overwrite eventual tuning options from earlier # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) -- cgit v1.2.3-70-g09d2 From c0b11d3af164947c71e2491912c5b8418900dafb Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 25 Sep 2009 11:20:38 -0700 Subject: x86: Add VIA processor instructions in opcodes decoder Add VIA processor's Padlock instructions(MONTMUL, XSHA1, XSHA256) as parts of the kernel may use them. This fixes the following crash in opcodes decoder selftests: make[2]: `scripts/unifdef' is up to date. TEST posttest Error: c145cf71: f3 0f a6 d0 repz xsha256 Error: objdump says 4 bytes, but insn_get_length() says 3 (attr:0) make[1]: *** [posttest] Error 2 make: *** [bzImage] Error 2 Reported-by: Ingo Molnar Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Acked-by: Ingo Molnar Cc: Jim Keniston Cc: Ananth N Mavinakayanahalli Cc: Andi Kleen Cc: Christoph Hellwig Cc: Frank Ch. Eigler Cc: H. Peter Anvin Cc: Jason Baron Cc: K.Prasad Cc: Lai Jiangshan Cc: Li Zefan Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Tom Zanussi LKML-Reference: <20090925182037.10157.3180.stgit@omoto> Signed-off-by: Frederic Weisbecker --- arch/x86/lib/x86-opcode-map.txt | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 59e20d5c2a5..78a0daf12e1 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -469,7 +469,7 @@ a2: CPUID a3: BT Ev,Gv a4: SHLD Ev,Gv,Ib a5: SHLD Ev,Gv,CL -a6: +a6: GrpPDLK a7: GrpRNG a8: PUSH GS (d64) a9: POP GS (d64) @@ -803,6 +803,12 @@ GrpTable: Grp16 3: prefetch T2 EndTable +GrpTable: GrpPDLK +0: MONTMUL +1: XSHA1 +2: XSHA2 +EndTable + GrpTable: GrpRNG 0: xstore-rng 1: xcrypt-ecb -- cgit v1.2.3-70-g09d2 From 30ed1a79f5bf271d33e782afee3323582dcc621e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sat, 3 Oct 2009 19:48:22 +0900 Subject: this_cpu: Implement X86 optimized this_cpu operations Basically the existing percpu ops can be used for this_cpu variants that allow operations also on dynamically allocated percpu data. However, we do not pass a reference to a percpu variable in. Instead a dynamically or statically allocated percpu variable is provided. Preempt, the non preempt and the irqsafe operations generate the same code. It will always be possible to have the requires per cpu atomicness in a single RMW instruction with segment override on x86. 64 bit this_cpu operations are not supported on 32 bit. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- arch/x86/include/asm/percpu.h | 78 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index b65a36defeb..8b5ec19bdef 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -153,6 +153,84 @@ do { \ #define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val) #define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, 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)) +#define __this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) + +#define __this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) +#define __this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) +#define __this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) +#define __this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) +#define __this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) +#define __this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) +#define __this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) +#define __this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) +#define __this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) +#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) + +#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)) +#define this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) +#define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) +#define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) +#define this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) +#define this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) +#define this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) +#define this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) +#define this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) +#define this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) +#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) + +#define irqsafe_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) +#define irqsafe_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) +#define irqsafe_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) +#define irqsafe_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) +#define irqsafe_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) +#define irqsafe_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) +#define irqsafe_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) +#define irqsafe_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) +#define irqsafe_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) + +/* + * Per cpu atomic 64 bit operations are only available under 64 bit. + * 32 bit must fall back to generic operations. + */ +#ifdef CONFIG_X86_64 +#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) +#define __this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) +#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_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) +#define this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) +#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 irqsafe_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val) +#define irqsafe_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) +#define irqsafe_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) +#define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) + +#endif + /* This is not atomic against other CPUs -- CPU preemption needs to be off */ #define x86_test_and_clear_bit_percpu(bit, var) \ ({ \ -- cgit v1.2.3-70-g09d2 From 209205801caf24ba0d54cc607800ee20c7d5132a Mon Sep 17 00:00:00 2001 From: Nelson Elhage Date: Wed, 16 Sep 2009 12:40:47 -0400 Subject: avr32: clean up linker script using standard macros. As a side effect, this patch changes the .init.ramfs data to be PAGE_SIZE-aligned, instead of 32-byte aligned. Also, the init data is moved into its own output sections rather than the .init output section. There should be no other changes to the resulting vmlinux as a result of this patch. Signed-off-by: Nelson Elhage Signed-off-by: Tim Abbott Cc: Haavard Skinnemoen Signed-off-by: Haavard Skinnemoen --- arch/avr32/kernel/vmlinux.lds.S | 64 ++++++----------------------------------- 1 file changed, 9 insertions(+), 55 deletions(-) (limited to 'arch') diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S index c4b56654349..9cd2bd91d64 100644 --- a/arch/avr32/kernel/vmlinux.lds.S +++ b/arch/avr32/kernel/vmlinux.lds.S @@ -39,30 +39,10 @@ SECTIONS __tagtable_begin = .; *(.taglist.init) __tagtable_end = .; - INIT_DATA - . = ALIGN(16); - __setup_start = .; - *(.init.setup) - __setup_end = .; - . = ALIGN(4); - __initcall_start = .; - INITCALLS - __initcall_end = .; - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - __security_initcall_start = .; - *(.security_initcall.init) - __security_initcall_end = .; -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(32); - __initramfs_start = .; - *(.init.ramfs) - __initramfs_end = .; -#endif - . = ALIGN(PAGE_SIZE); - __init_end = .; } + INIT_DATA_SECTION(16) + . = ALIGN(PAGE_SIZE); + __init_end = .; .text : AT(ADDR(.text) - LOAD_OFFSET) { _evba = .; @@ -78,34 +58,16 @@ SECTIONS _etext = .; } = 0xd703d703 - . = ALIGN(4); - __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } - + EXCEPTION_TABLE(4) RODATA - . = ALIGN(THREAD_SIZE); - .data : AT(ADDR(.data) - LOAD_OFFSET) { _data = .; _sdata = .; - /* - * First, the init task union, aligned to an 8K boundary. - */ - *(.data.init_task) - /* Then, the page-aligned data */ - . = ALIGN(PAGE_SIZE); - *(.data.page_aligned) - - /* Then, the cacheline aligned data */ - . = ALIGN(L1_CACHE_BYTES); - *(.data.cacheline_aligned) - - /* And the rest... */ + INIT_TASK_DATA(THREAD_SIZE) + PAGE_ALIGNED_DATA(PAGE_SIZE); + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) *(.data.rel*) DATA_DATA CONSTRUCTORS @@ -113,16 +75,8 @@ SECTIONS _edata = .; } - - . = ALIGN(8); - .bss : AT(ADDR(.bss) - LOAD_OFFSET) { - __bss_start = .; - *(.bss) - *(COMMON) - . = ALIGN(8); - __bss_stop = .; - _end = .; - } + BSS_SECTION(0, 8, 8) + _end = .; DWARF_DEBUG -- cgit v1.2.3-70-g09d2 From 5416bf33f92a4104dbcd6062bf377c8421ca3cfd Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Mon, 6 Jul 2009 12:15:12 +0200 Subject: avr32: add two new at91 to cpu.h definition Somme common drivers will need those at91 cpu_is_xxx() definitions. As at91sam9g10 and at91sam9g45 are on the way to linus' tree, here is the patch that adds those chips to cpu.h in AVR32 architecture. Signed-off-by: Nicolas Ferre Signed-off-by: Haavard Skinnemoen --- arch/avr32/mach-at32ap/include/mach/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/avr32/mach-at32ap/include/mach/cpu.h b/arch/avr32/mach-at32ap/include/mach/cpu.h index 44d0bfa1f40..c253e9bb561 100644 --- a/arch/avr32/mach-at32ap/include/mach/cpu.h +++ b/arch/avr32/mach-at32ap/include/mach/cpu.h @@ -31,5 +31,7 @@ #define cpu_is_at91sam9263() (0) #define cpu_is_at91sam9rl() (0) #define cpu_is_at91cap9() (0) +#define cpu_is_at91sam9g10() (0) +#define cpu_is_at91sam9g45() (0) #endif /* __ASM_ARCH_CPU_H */ -- cgit v1.2.3-70-g09d2 From d6c304055b3cecd4ca865769ac7cea97a320727b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 7 Oct 2009 21:43:22 +0200 Subject: x86, msr: Remove the bkl from msr_open() Remove the big kernel lock from msr_open() as it doesn't protect anything there. The only racy event that can happen here is a concurrent cpu shutdown. So let's look at what could be racy during/after the above event: - The cpu_online() check is racy, but the bkl doesn't help about that anyway it disables preemption but we may be chcking another cpu than the current one. Also the cpu can still become offlined between open and read calls. - The cpu_data(cpu) returns a safe pointer too. It won't be released on cpu offlining. But some fields can be changed from arch/x86/kernel/smpboot.c:remove_siblinginfo() : - phys_proc_id - cpu_core_id Those are not read from msr_open(). What we are checking is the x86_capability that is left untouched on offlining. So this removal looks safe. Signed-off-by: Frederic Weisbecker Cc: John Kacur Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Sven-Thorsten Dietrich LKML-Reference: <1254944602-7382-1-git-send-email-fweisbec@gmail.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/msr.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 7dd95009417..c0061096323 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -174,21 +174,17 @@ static int msr_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); struct cpuinfo_x86 *c = &cpu_data(cpu); - int ret = 0; - lock_kernel(); cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { - ret = -ENXIO; /* No such CPU */ - goto out; - } + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + return -ENXIO; /* No such CPU */ + c = &cpu_data(cpu); if (!cpu_has(c, X86_FEATURE_MSR)) - ret = -EIO; /* MSR not supported */ -out: - unlock_kernel(); - return ret; + return -EIO; /* MSR not supported */ + + return 0; } /* -- cgit v1.2.3-70-g09d2 From d8723ae2a416473f8e974baadcb6acb7f8b0b485 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 05:49:53 +0100 Subject: OMAP7XX: Serial: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/serial.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/serial.c b/arch/arm/mach-omap1/serial.c index d496e50fec4..49381e271be 100644 --- a/arch/arm/mach-omap1/serial.c +++ b/arch/arm/mach-omap1/serial.c @@ -110,20 +110,13 @@ void __init omap_serial_init(void) { int i; - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { serial_platform_data[0].regshift = 0; serial_platform_data[1].regshift = 0; serial_platform_data[0].irq = INT_730_UART_MODEM_1; serial_platform_data[1].irq = INT_730_UART_MODEM_IRDA_2; } - if (cpu_is_omap850()) { - serial_platform_data[0].regshift = 0; - serial_platform_data[1].regshift = 0; - serial_platform_data[0].irq = INT_850_UART_MODEM_1; - serial_platform_data[1].irq = INT_850_UART_MODEM_IRDA_2; - } - if (cpu_is_omap15xx()) { serial_platform_data[0].uartclk = OMAP1510_BASE_BAUD * 16; serial_platform_data[1].uartclk = OMAP1510_BASE_BAUD * 16; -- cgit v1.2.3-70-g09d2 From b718aa810b50e0d988d8b83f1011865b19b17491 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Wed, 23 Sep 2009 18:56:19 +0100 Subject: OMAP7XX: GPIO: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/plat-omap/gpio.c | 133 +++++----------------------------------------- 1 file changed, 14 insertions(+), 119 deletions(-) (limited to 'arch') diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c index 71ebd7fcfea..665ca050183 100644 --- a/arch/arm/plat-omap/gpio.c +++ b/arch/arm/plat-omap/gpio.c @@ -83,22 +83,6 @@ #define OMAP730_GPIO_INT_MASK 0x10 #define OMAP730_GPIO_INT_STATUS 0x14 -/* - * OMAP850 specific GPIO registers - */ -#define OMAP850_GPIO1_BASE OMAP1_IO_ADDRESS(0xfffbc000) -#define OMAP850_GPIO2_BASE OMAP1_IO_ADDRESS(0xfffbc800) -#define OMAP850_GPIO3_BASE OMAP1_IO_ADDRESS(0xfffbd000) -#define OMAP850_GPIO4_BASE OMAP1_IO_ADDRESS(0xfffbd800) -#define OMAP850_GPIO5_BASE OMAP1_IO_ADDRESS(0xfffbe000) -#define OMAP850_GPIO6_BASE OMAP1_IO_ADDRESS(0xfffbe800) -#define OMAP850_GPIO_DATA_INPUT 0x00 -#define OMAP850_GPIO_DATA_OUTPUT 0x04 -#define OMAP850_GPIO_DIR_CONTROL 0x08 -#define OMAP850_GPIO_INT_CONTROL 0x0c -#define OMAP850_GPIO_INT_MASK 0x10 -#define OMAP850_GPIO_INT_STATUS 0x14 - #define OMAP1_MPUIO_VBASE OMAP1_IO_ADDRESS(OMAP1_MPUIO_BASE) /* @@ -216,7 +200,6 @@ struct gpio_bank { #define METHOD_GPIO_1510 1 #define METHOD_GPIO_1610 2 #define METHOD_GPIO_730 3 -#define METHOD_GPIO_850 4 #define METHOD_GPIO_24XX 5 #ifdef CONFIG_ARCH_OMAP16XX @@ -236,7 +219,7 @@ static struct gpio_bank gpio_bank_1510[2] = { }; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) static struct gpio_bank gpio_bank_730[7] = { { OMAP1_MPUIO_VBASE, INT_730_MPUIO, IH_MPUIO_BASE, METHOD_MPUIO }, { OMAP730_GPIO1_BASE, INT_730_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_730 }, @@ -248,19 +231,6 @@ static struct gpio_bank gpio_bank_730[7] = { }; #endif -#ifdef CONFIG_ARCH_OMAP850 -static struct gpio_bank gpio_bank_850[7] = { - { OMAP1_MPUIO_VBASE, INT_850_MPUIO, IH_MPUIO_BASE, METHOD_MPUIO }, - { OMAP850_GPIO1_BASE, INT_850_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_850 }, - { OMAP850_GPIO2_BASE, INT_850_GPIO_BANK2, IH_GPIO_BASE + 32, METHOD_GPIO_850 }, - { OMAP850_GPIO3_BASE, INT_850_GPIO_BANK3, IH_GPIO_BASE + 64, METHOD_GPIO_850 }, - { OMAP850_GPIO4_BASE, INT_850_GPIO_BANK4, IH_GPIO_BASE + 96, METHOD_GPIO_850 }, - { OMAP850_GPIO5_BASE, INT_850_GPIO_BANK5, IH_GPIO_BASE + 128, METHOD_GPIO_850 }, - { OMAP850_GPIO6_BASE, INT_850_GPIO_BANK6, IH_GPIO_BASE + 160, METHOD_GPIO_850 }, -}; -#endif - - #ifdef CONFIG_ARCH_OMAP24XX static struct gpio_bank gpio_bank_242x[4] = { @@ -402,16 +372,11 @@ static void _set_gpio_direction(struct gpio_bank *bank, int gpio, int is_input) reg += OMAP1610_GPIO_DIRECTION; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_DIR_CONTROL; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_DIR_CONTROL; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_OE; @@ -469,7 +434,7 @@ static void _set_gpio_dataout(struct gpio_bank *bank, int gpio, int enable) l = 1 << gpio; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_DATA_OUTPUT; l = __raw_readl(reg); @@ -479,16 +444,6 @@ static void _set_gpio_dataout(struct gpio_bank *bank, int gpio, int enable) l &= ~(1 << gpio); break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_DATA_OUTPUT; - l = __raw_readl(reg); - if (enable) - l |= 1 << gpio; - else - l &= ~(1 << gpio); - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: if (enable) @@ -537,16 +492,11 @@ static int _get_gpio_datain(struct gpio_bank *bank, int gpio) reg += OMAP1610_GPIO_DATAIN; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_DATA_INPUT; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_DATA_INPUT; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_DATAIN; @@ -588,16 +538,11 @@ static int _get_gpio_dataout(struct gpio_bank *bank, int gpio) reg += OMAP1610_GPIO_DATAOUT; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_DATA_OUTPUT; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_DATA_OUTPUT; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) || \ defined(CONFIG_ARCH_OMAP4) case METHOD_GPIO_24XX: @@ -797,7 +742,7 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger) __raw_writel(1 << gpio, bank->base + OMAP1610_GPIO_CLEAR_WAKEUPENA); break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_INT_CONTROL; l = __raw_readl(reg); @@ -809,18 +754,6 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger) goto bad; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_INT_CONTROL; - l = __raw_readl(reg); - if (trigger & IRQ_TYPE_EDGE_RISING) - l |= 1 << gpio; - else if (trigger & IRQ_TYPE_EDGE_FALLING) - l &= ~(1 << gpio); - else - goto bad; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) || \ defined(CONFIG_ARCH_OMAP4) case METHOD_GPIO_24XX: @@ -897,16 +830,11 @@ static void _clear_gpio_irqbank(struct gpio_bank *bank, int gpio_mask) reg += OMAP1610_GPIO_IRQSTATUS1; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_INT_STATUS; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_INT_STATUS; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_IRQSTATUS1; @@ -971,20 +899,13 @@ static u32 _get_gpio_irqbank_mask(struct gpio_bank *bank) mask = 0xffff; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_INT_MASK; mask = 0xffffffff; inv = 1; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_INT_MASK; - mask = 0xffffffff; - inv = 1; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_IRQENABLE1; @@ -1044,7 +965,7 @@ static void _enable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask, int enab l = gpio_mask; break; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) case METHOD_GPIO_730: reg += OMAP730_GPIO_INT_MASK; l = __raw_readl(reg); @@ -1054,16 +975,6 @@ static void _enable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask, int enab l |= gpio_mask; break; #endif -#ifdef CONFIG_ARCH_OMAP850 - case METHOD_GPIO_850: - reg += OMAP850_GPIO_INT_MASK; - l = __raw_readl(reg); - if (enable) - l &= ~(gpio_mask); - else - l |= gpio_mask; - break; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) case METHOD_GPIO_24XX: if (enable) @@ -1249,14 +1160,10 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc) if (bank->method == METHOD_GPIO_1610) isr_reg = bank->base + OMAP1610_GPIO_IRQSTATUS1; #endif -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) if (bank->method == METHOD_GPIO_730) isr_reg = bank->base + OMAP730_GPIO_INT_STATUS; #endif -#ifdef CONFIG_ARCH_OMAP850 - if (bank->method == METHOD_GPIO_850) - isr_reg = bank->base + OMAP850_GPIO_INT_STATUS; -#endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) if (bank->method == METHOD_GPIO_24XX) isr_reg = bank->base + OMAP24XX_GPIO_IRQSTATUS1; @@ -1527,9 +1434,6 @@ static int gpio_is_input(struct gpio_bank *bank, int mask) case METHOD_GPIO_730: reg += OMAP730_GPIO_DIR_CONTROL; break; - case METHOD_GPIO_850: - reg += OMAP850_GPIO_DIR_CONTROL; - break; case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_OE; break; @@ -1695,21 +1599,13 @@ static int __init _omap_gpio_init(void) (rev >> 4) & 0x0f, rev & 0x0f); } #endif -#ifdef CONFIG_ARCH_OMAP730 - if (cpu_is_omap730()) { - printk(KERN_INFO "OMAP730 GPIO hardware\n"); +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) + if (cpu_is_omap7xx()) { + printk(KERN_INFO "OMAP7XX GPIO hardware\n"); gpio_bank_count = 7; gpio_bank = gpio_bank_730; } #endif -#ifdef CONFIG_ARCH_OMAP850 - if (cpu_is_omap850()) { - printk(KERN_INFO "OMAP850 GPIO hardware\n"); - gpio_bank_count = 7; - gpio_bank = gpio_bank_850; - } -#endif - #ifdef CONFIG_ARCH_OMAP24XX if (cpu_is_omap242x()) { int rev; @@ -2160,8 +2056,7 @@ static int dbg_gpio_show(struct seq_file *s, void *unused) if (bank_is_mpuio(bank)) gpio = OMAP_MPUIO(0); - else if (cpu_class_is_omap2() || cpu_is_omap730() || - cpu_is_omap850()) + else if (cpu_class_is_omap2() || cpu_is_omap7xx()) bankwidth = 32; for (j = 0; j < bankwidth; j++, gpio++, mask <<= 1) { -- cgit v1.2.3-70-g09d2 From ab49df737d28c67eb6a5cb5be40dbab43fd7582c Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 05:58:08 +0100 Subject: OMAP7XX: IO: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/io.c | 29 +++-------------------------- arch/arm/plat-omap/io.c | 2 +- 2 files changed, 4 insertions(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c index 7030f9281ea..19de57f74e8 100644 --- a/arch/arm/mach-omap1/io.c +++ b/arch/arm/mach-omap1/io.c @@ -36,7 +36,7 @@ static struct map_desc omap_io_desc[] __initdata = { } }; -#ifdef CONFIG_ARCH_OMAP730 +#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) static struct map_desc omap730_io_desc[] __initdata = { { .virtual = OMAP730_DSP_BASE, @@ -52,22 +52,6 @@ static struct map_desc omap730_io_desc[] __initdata = { }; #endif -#ifdef CONFIG_ARCH_OMAP850 -static struct map_desc omap850_io_desc[] __initdata = { - { - .virtual = OMAP850_DSP_BASE, - .pfn = __phys_to_pfn(OMAP850_DSP_START), - .length = OMAP850_DSP_SIZE, - .type = MT_DEVICE - }, { - .virtual = OMAP850_DSPREG_BASE, - .pfn = __phys_to_pfn(OMAP850_DSPREG_START), - .length = OMAP850_DSPREG_SIZE, - .type = MT_DEVICE - } -}; -#endif - #ifdef CONFIG_ARCH_OMAP15XX static struct map_desc omap1510_io_desc[] __initdata = { { @@ -120,18 +104,11 @@ void __init omap1_map_common_io(void) */ omap_check_revision(); -#ifdef CONFIG_ARCH_OMAP730 - if (cpu_is_omap730()) { +#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) + if (cpu_is_omap7xx()) { iotable_init(omap730_io_desc, ARRAY_SIZE(omap730_io_desc)); } #endif - -#ifdef CONFIG_ARCH_OMAP850 - if (cpu_is_omap850()) { - iotable_init(omap850_io_desc, ARRAY_SIZE(omap850_io_desc)); - } -#endif - #ifdef CONFIG_ARCH_OMAP15XX if (cpu_is_omap15xx()) { iotable_init(omap1510_io_desc, ARRAY_SIZE(omap1510_io_desc)); diff --git a/arch/arm/plat-omap/io.c b/arch/arm/plat-omap/io.c index b6defa23e77..388fd949093 100644 --- a/arch/arm/plat-omap/io.c +++ b/arch/arm/plat-omap/io.c @@ -33,7 +33,7 @@ void __iomem *omap_ioremap(unsigned long p, size_t size, unsigned int type) if (BETWEEN(p, OMAP1_IO_PHYS, OMAP1_IO_SIZE)) return XLATE(p, OMAP1_IO_PHYS, OMAP1_IO_VIRT); } - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { if (BETWEEN(p, OMAP730_DSP_BASE, OMAP730_DSP_SIZE)) return XLATE(p, OMAP730_DSP_BASE, OMAP730_DSP_START); -- cgit v1.2.3-70-g09d2 From 190215f963551405cc97ed220003bb7524219131 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 05:58:54 +0100 Subject: OMAP7XX: Mux: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/mux.c | 28 ++------------------ arch/arm/plat-omap/include/mach/mux.h | 50 ----------------------------------- 2 files changed, 2 insertions(+), 76 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/mux.c b/arch/arm/mach-omap1/mux.c index 721e0d9d8b1..f9d45a3bf4f 100644 --- a/arch/arm/mach-omap1/mux.c +++ b/arch/arm/mach-omap1/mux.c @@ -35,7 +35,7 @@ static struct omap_mux_cfg arch_mux_cfg; -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) static struct pin_config __initdata_or_module omap730_pins[] = { MUX_CFG_730("E2_730_KBR0", 12, 21, 0, 20, 1, 0) MUX_CFG_730("J7_730_KBR1", 12, 25, 0, 24, 1, 0) @@ -58,25 +58,6 @@ MUX_CFG_730("W17_730_USB_VBUSI", 2, 29, 0, 28, 0, 0) #define OMAP730_PINS_SZ 0 #endif /* CONFIG_ARCH_OMAP730 */ -#ifdef CONFIG_ARCH_OMAP850 -struct pin_config __initdata_or_module omap850_pins[] = { -MUX_CFG_850("E2_850_KBR0", 12, 21, 0, 20, 1, 0) -MUX_CFG_850("J7_850_KBR1", 12, 25, 0, 24, 1, 0) -MUX_CFG_850("E1_850_KBR2", 12, 29, 0, 28, 1, 0) -MUX_CFG_850("F3_850_KBR3", 13, 1, 0, 0, 1, 0) -MUX_CFG_850("D2_850_KBR4", 13, 5, 0, 4, 1, 0) -MUX_CFG_850("C2_850_KBC0", 13, 9, 0, 8, 1, 0) -MUX_CFG_850("D3_850_KBC1", 13, 13, 0, 12, 1, 0) -MUX_CFG_850("E4_850_KBC2", 13, 17, 0, 16, 1, 0) -MUX_CFG_850("F4_850_KBC3", 13, 21, 0, 20, 1, 0) -MUX_CFG_850("E3_850_KBC4", 13, 25, 0, 24, 1, 0) - -MUX_CFG_850("AA17_850_USB_DM", 2, 21, 0, 20, 0, 0) -MUX_CFG_850("W16_850_USB_PU_EN", 2, 25, 0, 24, 0, 0) -MUX_CFG_850("W17_850_USB_VBUSI", 2, 29, 0, 28, 0, 0) -}; -#endif - #if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX) static struct pin_config __initdata_or_module omap1xxx_pins[] = { /* @@ -438,11 +419,6 @@ int __init_or_module omap1_cfg_reg(const struct pin_config *cfg) printk(" %s (0x%08x) = 0x%08x -> 0x%08x\n", cfg->pull_name, cfg->pull_reg, pull_orig, pull); } - -#ifdef CONFIG_ARCH_OMAP850 - omap_mux_register(omap850_pins, ARRAY_SIZE(omap850_pins)); -#endif - #endif #ifdef CONFIG_OMAP_MUX_ERRORS @@ -454,7 +430,7 @@ int __init_or_module omap1_cfg_reg(const struct pin_config *cfg) int __init omap1_mux_init(void) { - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { arch_mux_cfg.pins = omap730_pins; arch_mux_cfg.size = OMAP730_PINS_SZ; arch_mux_cfg.cfg_reg = omap1_cfg_reg; diff --git a/arch/arm/plat-omap/include/mach/mux.h b/arch/arm/plat-omap/include/mach/mux.h index 0f49d2d563d..587fb63d232 100644 --- a/arch/arm/plat-omap/include/mach/mux.h +++ b/arch/arm/plat-omap/include/mach/mux.h @@ -61,16 +61,6 @@ .pull_bit = bit, \ .pull_val = status, -#define MUX_REG_850(reg, mode_offset, mode) .mux_reg_name = "OMAP850_IO_CONF_"#reg, \ - .mux_reg = OMAP850_IO_CONF_##reg, \ - .mask_offset = mode_offset, \ - .mask = mode, - -#define PULL_REG_850(reg, bit, status) .pull_name = "OMAP850_IO_CONF_"#reg, \ - .pull_reg = OMAP850_IO_CONF_##reg, \ - .pull_bit = bit, \ - .pull_val = status, - #else #define MUX_REG(reg, mode_offset, mode) .mux_reg = FUNC_MUX_CTRL_##reg, \ @@ -93,15 +83,6 @@ .pull_bit = bit, \ .pull_val = status, -#define MUX_REG_850(reg, mode_offset, mode) \ - .mux_reg = OMAP850_IO_CONF_##reg, \ - .mask_offset = mode_offset, \ - .mask = mode, - -#define PULL_REG_850(reg, bit, status) .pull_reg = OMAP850_IO_CONF_##reg, \ - .pull_bit = bit, \ - .pull_val = status, - #endif /* CONFIG_OMAP_MUX_DEBUG */ #define MUX_CFG(desc, mux_reg, mode_offset, mode, \ @@ -133,17 +114,6 @@ PU_PD_REG(NA, 0) \ }, -#define MUX_CFG_850(desc, mux_reg, mode_offset, mode, \ - pull_bit, pull_status, debug_status)\ -{ \ - .name = desc, \ - .debug = debug_status, \ - MUX_REG_850(mux_reg, mode_offset, mode) \ - PULL_REG_850(mux_reg, pull_bit, pull_status) \ - PU_PD_REG(NA, 0) \ -}, - - #define MUX_CFG_24XX(desc, reg_offset, mode, \ pull_en, pull_mode, dbg) \ { \ @@ -251,26 +221,6 @@ enum omap730_index { W17_730_USB_VBUSI, }; -enum omap850_index { - /* OMAP 850 keyboard */ - E2_850_KBR0, - J7_850_KBR1, - E1_850_KBR2, - F3_850_KBR3, - D2_850_KBR4, - C2_850_KBC0, - D3_850_KBC1, - E4_850_KBC2, - F4_850_KBC3, - E3_850_KBC4, - - /* USB */ - AA17_850_USB_DM, - W16_850_USB_PU_EN, - W17_850_USB_VBUSI, -}; - - enum omap1xxx_index { /* UART1 (BT_UART_GATING)*/ UART1_TX = 0, -- cgit v1.2.3-70-g09d2 From 207b0e9cfef296c469cce84f74455f97f8ab2227 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 06:01:08 +0100 Subject: OMAP7XX: USB: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/plat-omap/usb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/plat-omap/usb.c b/arch/arm/plat-omap/usb.c index 509f2ed99e2..980d2eb68a2 100644 --- a/arch/arm/plat-omap/usb.c +++ b/arch/arm/plat-omap/usb.c @@ -614,7 +614,7 @@ omap_otg_init(struct omap_usb_config *config) if (config->otg || config->register_host) { syscon &= ~HST_IDLE_EN; ohci_device.dev.platform_data = config; - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) ohci_resources[1].start = INT_730_USB_HHC_1; status = platform_device_register(&ohci_device); if (status) @@ -626,7 +626,7 @@ omap_otg_init(struct omap_usb_config *config) if (config->otg) { syscon &= ~OTG_IDLE_EN; otg_device.dev.platform_data = config; - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) otg_resources[1].start = INT_730_USB_OTG; status = platform_device_register(&otg_device); if (status) @@ -731,7 +731,7 @@ static inline void omap_1510_usb_init(struct omap_usb_config *config) {} void __init omap_usb_init(struct omap_usb_config *pdata) { - if (cpu_is_omap730() || cpu_is_omap16xx() || cpu_is_omap24xx()) + if (cpu_is_omap7xx() || cpu_is_omap16xx() || cpu_is_omap24xx()) omap_otg_init(pdata); else if (cpu_is_omap15xx()) omap_1510_usb_init(pdata); -- cgit v1.2.3-70-g09d2 From 559663b980c8293b3624b4d91d08efc71f6fae82 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 06:33:04 +0100 Subject: OMAP7XX: IRQ: Remove duplicate omap850 code This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. This fixes a bug which prevents IRQs from being enabled on omap850 due to a missing check in entry-macro.S, which was found by Cory Maccarrone. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/irq.c | 24 ++------ arch/arm/plat-omap/include/mach/entry-macro.S | 6 +- arch/arm/plat-omap/include/mach/irqs.h | 81 --------------------------- 3 files changed, 7 insertions(+), 104 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c index de03c844899..c05999c4116 100644 --- a/arch/arm/mach-omap1/irq.c +++ b/arch/arm/mach-omap1/irq.c @@ -137,7 +137,7 @@ static void omap_irq_set_cfg(int irq, int fiq, int priority, int trigger) irq_bank_writel(val, bank, offset); } -#ifdef CONFIG_ARCH_OMAP730 +#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) static struct omap_irq_bank omap730_irq_banks[] = { { .base_reg = OMAP_IH1_BASE, .trigger_map = 0xb3f8e22f }, { .base_reg = OMAP_IH2_BASE, .trigger_map = 0xfdb9c1f2 }, @@ -145,14 +145,6 @@ static struct omap_irq_bank omap730_irq_banks[] = { }; #endif -#ifdef CONFIG_ARCH_OMAP850 -static struct omap_irq_bank omap850_irq_banks[] = { - { .base_reg = OMAP_IH1_BASE, .trigger_map = 0xb3f8e22f }, - { .base_reg = OMAP_IH2_BASE, .trigger_map = 0xfdb9c1f2 }, - { .base_reg = OMAP_IH2_BASE + 0x100, .trigger_map = 0x800040f3 }, -}; -#endif - #ifdef CONFIG_ARCH_OMAP15XX static struct omap_irq_bank omap1510_irq_banks[] = { { .base_reg = OMAP_IH1_BASE, .trigger_map = 0xb3febfff }, @@ -186,18 +178,12 @@ void __init omap_init_irq(void) { int i, j; -#ifdef CONFIG_ARCH_OMAP730 - if (cpu_is_omap730()) { +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) + if (cpu_is_omap7xx()) { irq_banks = omap730_irq_banks; irq_bank_count = ARRAY_SIZE(omap730_irq_banks); } #endif -#ifdef CONFIG_ARCH_OMAP850 - if (cpu_is_omap850()) { - irq_banks = omap850_irq_banks; - irq_bank_count = ARRAY_SIZE(omap850_irq_banks); - } -#endif #ifdef CONFIG_ARCH_OMAP15XX if (cpu_is_omap1510()) { irq_banks = omap1510_irq_banks; @@ -247,10 +233,8 @@ void __init omap_init_irq(void) /* Unmask level 2 handler */ - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_unmask_irq(INT_730_IH2_IRQ); - else if (cpu_is_omap850()) - omap_unmask_irq(INT_850_IH2_IRQ); else if (cpu_is_omap15xx()) omap_unmask_irq(INT_1510_IH2_IRQ); else if (cpu_is_omap16xx()) diff --git a/arch/arm/plat-omap/include/mach/entry-macro.S b/arch/arm/plat-omap/include/mach/entry-macro.S index a5592991634..bcf71585665 100644 --- a/arch/arm/plat-omap/include/mach/entry-macro.S +++ b/arch/arm/plat-omap/include/mach/entry-macro.S @@ -17,10 +17,10 @@ #if defined(CONFIG_ARCH_OMAP1) -#if defined(CONFIG_ARCH_OMAP730) && \ +#if (defined(CONFIG_ARCH_OMAP730)||defined(CONFIG_ARCH_OMAP850)) && \ (defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX)) -#error "FIXME: OMAP730 doesn't support multiple-OMAP" -#elif defined(CONFIG_ARCH_OMAP730) +#error "FIXME: OMAP7XX doesn't support multiple-OMAP" +#elif defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) #define INT_IH2_IRQ INT_730_IH2_IRQ #elif defined(CONFIG_ARCH_OMAP15XX) #define INT_IH2_IRQ INT_1510_IH2_IRQ diff --git a/arch/arm/plat-omap/include/mach/irqs.h b/arch/arm/plat-omap/include/mach/irqs.h index 28a165058b6..7f338f0c745 100644 --- a/arch/arm/plat-omap/include/mach/irqs.h +++ b/arch/arm/plat-omap/include/mach/irqs.h @@ -107,29 +107,6 @@ #define INT_730_GPIO_BANK6 18 #define INT_730_SPGIO_WR 29 -/* - * OMAP-850 specific IRQ numbers for interrupt handler 1 - */ -#define INT_850_IH2_FIQ 0 -#define INT_850_IH2_IRQ 1 -#define INT_850_USB_NON_ISO 2 -#define INT_850_USB_ISO 3 -#define INT_850_ICR 4 -#define INT_850_EAC 5 -#define INT_850_GPIO_BANK1 6 -#define INT_850_GPIO_BANK2 7 -#define INT_850_GPIO_BANK3 8 -#define INT_850_McBSP2TX 10 -#define INT_850_McBSP2RX 11 -#define INT_850_McBSP2RX_OVF 12 -#define INT_850_LCD_LINE 14 -#define INT_850_GSM_PROTECT 15 -#define INT_850_TIMER3 16 -#define INT_850_GPIO_BANK5 17 -#define INT_850_GPIO_BANK6 18 -#define INT_850_SPGIO_WR 29 - - /* * IRQ numbers for interrupt handler 2 * @@ -263,64 +240,6 @@ #define INT_730_DMA_CH15 (62 + IH2_BASE) #define INT_730_NAND (63 + IH2_BASE) -/* - * OMAP-850 specific IRQ numbers for interrupt handler 2 - */ -#define INT_850_HW_ERRORS (0 + IH2_BASE) -#define INT_850_NFIQ_PWR_FAIL (1 + IH2_BASE) -#define INT_850_CFCD (2 + IH2_BASE) -#define INT_850_CFIREQ (3 + IH2_BASE) -#define INT_850_I2C (4 + IH2_BASE) -#define INT_850_PCC (5 + IH2_BASE) -#define INT_850_MPU_EXT_NIRQ (6 + IH2_BASE) -#define INT_850_SPI_100K_1 (7 + IH2_BASE) -#define INT_850_SYREN_SPI (8 + IH2_BASE) -#define INT_850_VLYNQ (9 + IH2_BASE) -#define INT_850_GPIO_BANK4 (10 + IH2_BASE) -#define INT_850_McBSP1TX (11 + IH2_BASE) -#define INT_850_McBSP1RX (12 + IH2_BASE) -#define INT_850_McBSP1RX_OF (13 + IH2_BASE) -#define INT_850_UART_MODEM_IRDA_2 (14 + IH2_BASE) -#define INT_850_UART_MODEM_1 (15 + IH2_BASE) -#define INT_850_MCSI (16 + IH2_BASE) -#define INT_850_uWireTX (17 + IH2_BASE) -#define INT_850_uWireRX (18 + IH2_BASE) -#define INT_850_SMC_CD (19 + IH2_BASE) -#define INT_850_SMC_IREQ (20 + IH2_BASE) -#define INT_850_HDQ_1WIRE (21 + IH2_BASE) -#define INT_850_TIMER32K (22 + IH2_BASE) -#define INT_850_MMC_SDIO (23 + IH2_BASE) -#define INT_850_UPLD (24 + IH2_BASE) -#define INT_850_USB_HHC_1 (27 + IH2_BASE) -#define INT_850_USB_HHC_2 (28 + IH2_BASE) -#define INT_850_USB_GENI (29 + IH2_BASE) -#define INT_850_USB_OTG (30 + IH2_BASE) -#define INT_850_CAMERA_IF (31 + IH2_BASE) -#define INT_850_RNG (32 + IH2_BASE) -#define INT_850_DUAL_MODE_TIMER (33 + IH2_BASE) -#define INT_850_DBB_RF_EN (34 + IH2_BASE) -#define INT_850_MPUIO_KEYPAD (35 + IH2_BASE) -#define INT_850_SHA1_MD5 (36 + IH2_BASE) -#define INT_850_SPI_100K_2 (37 + IH2_BASE) -#define INT_850_RNG_IDLE (38 + IH2_BASE) -#define INT_850_MPUIO (39 + IH2_BASE) -#define INT_850_LLPC_LCD_CTRL_CAN_BE_OFF (40 + IH2_BASE) -#define INT_850_LLPC_OE_FALLING (41 + IH2_BASE) -#define INT_850_LLPC_OE_RISING (42 + IH2_BASE) -#define INT_850_LLPC_VSYNC (43 + IH2_BASE) -#define INT_850_WAKE_UP_REQ (46 + IH2_BASE) -#define INT_850_DMA_CH6 (53 + IH2_BASE) -#define INT_850_DMA_CH7 (54 + IH2_BASE) -#define INT_850_DMA_CH8 (55 + IH2_BASE) -#define INT_850_DMA_CH9 (56 + IH2_BASE) -#define INT_850_DMA_CH10 (57 + IH2_BASE) -#define INT_850_DMA_CH11 (58 + IH2_BASE) -#define INT_850_DMA_CH12 (59 + IH2_BASE) -#define INT_850_DMA_CH13 (60 + IH2_BASE) -#define INT_850_DMA_CH14 (61 + IH2_BASE) -#define INT_850_DMA_CH15 (62 + IH2_BASE) -#define INT_850_NAND (63 + IH2_BASE) - #define INT_24XX_SYS_NIRQ 7 #define INT_24XX_SDMA_IRQ0 12 #define INT_24XX_SDMA_IRQ1 13 -- cgit v1.2.3-70-g09d2 From 4b9100dde2820296003940ffd81e006c33c9bf5d Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 06:41:09 +0100 Subject: OMAP7XX: PM: Add omap850 support This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. This file had no omap850 specific code. Original omap850 support in Linwizard was done by cloning the omap730 code. That work was done by Zebediah C. McClure. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/pm.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 5218943c91c..12f246e3cdc 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -183,7 +183,7 @@ static void omap_pm_wakeup_setup(void) * drivers must still separately call omap_set_gpio_wakeup() to * wake up to a GPIO interrupt. */ - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) level1_wake = OMAP_IRQ_BIT(INT_730_GPIO_BANK1) | OMAP_IRQ_BIT(INT_730_IH2_IRQ); else if (cpu_is_omap15xx()) @@ -195,7 +195,7 @@ static void omap_pm_wakeup_setup(void) omap_writel(~level1_wake, OMAP_IH1_MIR); - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { omap_writel(~level2_wake, OMAP_IH2_0_MIR); omap_writel(~(OMAP_IRQ_BIT(INT_730_WAKE_UP_REQ) | OMAP_IRQ_BIT(INT_730_MPUIO_KEYPAD)), @@ -253,7 +253,7 @@ void omap1_pm_suspend(void) * Save interrupt, MPUI, ARM and UPLD control registers. */ - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { MPUI730_SAVE(OMAP_IH1_MIR); MPUI730_SAVE(OMAP_IH2_0_MIR); MPUI730_SAVE(OMAP_IH2_1_MIR); @@ -306,7 +306,7 @@ void omap1_pm_suspend(void) omap_writew(omap_readw(ARM_RSTCT1) & ~(1 << DSP_EN), ARM_RSTCT1); /* shut down dsp_ck */ - if (!cpu_is_omap730()) + if (!cpu_is_omap7xx()) omap_writew(omap_readw(ARM_CKCTL) & ~(1 << EN_DSPCK), ARM_CKCTL); /* temporarily enabling api_ck to access DSP registers */ @@ -383,7 +383,7 @@ void omap1_pm_suspend(void) ULPD_RESTORE(ULPD_CLOCK_CTRL); ULPD_RESTORE(ULPD_STATUS_REQ); - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { MPUI730_RESTORE(EMIFS_CONFIG); MPUI730_RESTORE(EMIFF_SDRAM_CONFIG); MPUI730_RESTORE(OMAP_IH1_MIR); @@ -461,7 +461,7 @@ static int omap_pm_read_proc( ULPD_SAVE(ULPD_DPLL_CTRL); ULPD_SAVE(ULPD_POWER_CTRL); - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { MPUI730_SAVE(MPUI_CTRL); MPUI730_SAVE(MPUI_DSP_STATUS); MPUI730_SAVE(MPUI_DSP_BOOT_CONFIG); @@ -517,7 +517,7 @@ static int omap_pm_read_proc( ULPD_SHOW(ULPD_STATUS_REQ), ULPD_SHOW(ULPD_POWER_CTRL)); - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { my_buffer_offset += sprintf(my_base + my_buffer_offset, "MPUI730_CTRL_REG 0x%-8x \n" "MPUI730_DSP_STATUS_REG: 0x%-8x \n" @@ -668,7 +668,7 @@ static int __init omap_pm_init(void) * These routines need to be in SRAM as that's the only * memory the MPU can see when it wakes up. */ - if (cpu_is_omap730()) { + if (cpu_is_omap7xx()) { omap_sram_suspend = omap_sram_push(omap730_cpu_suspend, omap730_cpu_suspend_sz); } else if (cpu_is_omap15xx()) { @@ -686,7 +686,7 @@ static int __init omap_pm_init(void) pm_idle = omap1_pm_idle; - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) setup_irq(INT_730_WAKE_UP_REQ, &omap_wakeup_irq); else if (cpu_is_omap16xx()) setup_irq(INT_1610_WAKE_UP_REQ, &omap_wakeup_irq); @@ -700,7 +700,7 @@ static int __init omap_pm_init(void) omap_writew(ULPD_POWER_CTRL_REG_VAL, ULPD_POWER_CTRL); /* Configure IDLECT3 */ - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_writel(OMAP730_IDLECT3_VAL, OMAP730_IDLECT3); else if (cpu_is_omap16xx()) omap_writel(OMAP1610_IDLECT3_VAL, OMAP1610_IDLECT3); -- cgit v1.2.3-70-g09d2 From 39a8b08610a10f3456ef9f4a38986d0407f1c57e Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 06:47:14 +0100 Subject: OMAP7XX: Clocks: Add omap850 support This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. This file had no omap850 specific code. Initial clock support was done in the Linwizard tree by Zebediah C. McClure. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/clock.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index 436eed22801..fcbea61cb8c 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -398,7 +398,7 @@ static int omap1_select_table_rate(struct clk * clk, unsigned long rate) * Reprogramming the DPLL is tricky, it must be done from SRAM. * (on 730, bit 13 must always be 1) */ - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_sram_reprogram_clock(ptr->dpllctl_val, ptr->ckctl_val | 0x2000); else omap_sram_reprogram_clock(ptr->dpllctl_val, ptr->ckctl_val); @@ -783,7 +783,7 @@ int __init omap1_clk_init(void) cpu_mask |= CK_16XX; if (cpu_is_omap1510()) cpu_mask |= CK_1510; - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) cpu_mask |= CK_730; if (cpu_is_omap310()) cpu_mask |= CK_310; @@ -800,7 +800,7 @@ int __init omap1_clk_init(void) crystal_type = info->system_clock_type; } -#if defined(CONFIG_ARCH_OMAP730) +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) ck_ref.rate = 13000000; #elif defined(CONFIG_ARCH_OMAP16XX) if (crystal_type == 2) @@ -847,7 +847,7 @@ int __init omap1_clk_init(void) printk(KERN_ERR "System frequencies not set. Check your config.\n"); /* Guess sane values (60MHz) */ omap_writew(0x2290, DPLL_CTL); - omap_writew(cpu_is_omap730() ? 0x3005 : 0x1005, ARM_CKCTL); + omap_writew(cpu_is_omap7xx() ? 0x3005 : 0x1005, ARM_CKCTL); ck_dpll1.rate = 60000000; } #endif @@ -873,7 +873,7 @@ int __init omap1_clk_init(void) /* Turn off DSP and ARM_TIMXO. Make sure ARM_INTHCK is not divided */ /* (on 730, bit 13 must not be cleared) */ - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_writew(omap_readw(ARM_CKCTL) & 0x2fff, ARM_CKCTL); else omap_writew(omap_readw(ARM_CKCTL) & 0x0fff, ARM_CKCTL); -- cgit v1.2.3-70-g09d2 From bf1cb7eb4fe35e50798f03e00d3900db0474f7d0 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 06:49:35 +0100 Subject: OMAP7XX: McBSP: Add omap850 support This patch is part of a series which unifies all duplicated code between omap730 and omap850. All cpu checks are converted to cpu_is_omap7xx() and CONFIG_ARCH_OMAP850 is added to all CONFIG_ARCH_OMAP730 checks. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/mcbsp.c | 6 +++--- arch/arm/plat-omap/include/mach/mcbsp.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index 505d98cfe50..06f380bf221 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -79,7 +79,7 @@ static struct omap_mcbsp_ops omap1_mcbsp_ops = { .free = omap1_mcbsp_free, }; -#ifdef CONFIG_ARCH_OMAP730 +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) static struct omap_mcbsp_platform_data omap730_mcbsp_pdata[] = { { .phys_base = OMAP730_MCBSP1_BASE, @@ -172,7 +172,7 @@ static struct omap_mcbsp_platform_data omap16xx_mcbsp_pdata[] = { int __init omap1_mcbsp_init(void) { - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_mcbsp_count = OMAP730_MCBSP_PDATA_SZ; if (cpu_is_omap15xx()) omap_mcbsp_count = OMAP15XX_MCBSP_PDATA_SZ; @@ -184,7 +184,7 @@ int __init omap1_mcbsp_init(void) if (!mcbsp_ptr) return -ENOMEM; - if (cpu_is_omap730()) + if (cpu_is_omap7xx()) omap_mcbsp_register_board_cfg(omap730_mcbsp_pdata, OMAP730_MCBSP_PDATA_SZ); diff --git a/arch/arm/plat-omap/include/mach/mcbsp.h b/arch/arm/plat-omap/include/mach/mcbsp.h index e0d6eca222c..0b476b909aa 100644 --- a/arch/arm/plat-omap/include/mach/mcbsp.h +++ b/arch/arm/plat-omap/include/mach/mcbsp.h @@ -58,7 +58,7 @@ #define OMAP44XX_MCBSP3_BASE 0x49026000 #define OMAP44XX_MCBSP4_BASE 0x48074000 -#if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP730) +#if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) #define OMAP_MCBSP_REG_DRR2 0x00 #define OMAP_MCBSP_REG_DRR1 0x02 -- cgit v1.2.3-70-g09d2 From e6684f7132c6e6333e96407b06910bebaa4c1935 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 07:22:56 +0100 Subject: OMAP7XX: Create omap7xx.h This patch is part of a series which removes references to omap730 in code which is shared with omap850, replacing them with references to omap7xx. This include file is intended to replace omap730.h and omap850.h All values defined herein are identical to those in both the old files. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/plat-omap/include/mach/omap7xx.h | 104 ++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 arch/arm/plat-omap/include/mach/omap7xx.h (limited to 'arch') diff --git a/arch/arm/plat-omap/include/mach/omap7xx.h b/arch/arm/plat-omap/include/mach/omap7xx.h new file mode 100644 index 00000000000..53f52414b0e --- /dev/null +++ b/arch/arm/plat-omap/include/mach/omap7xx.h @@ -0,0 +1,104 @@ +/* arch/arm/plat-omap/include/mach/omap7xx.h + * + * Hardware definitions for TI OMAP7XX processor. + * + * Cleanup for Linux-2.6 by Dirk Behme + * Adapted for omap850 by Zebediah C. McClure + * Adapted for omap7xx by Alistair Buxton + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN + * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF + * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * 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., + * 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef __ASM_ARCH_OMAP7XX_H +#define __ASM_ARCH_OMAP7XX_H + +/* + * ---------------------------------------------------------------------------- + * Base addresses + * ---------------------------------------------------------------------------- + */ + +/* Syntax: XX_BASE = Virtual base address, XX_START = Physical base address */ + +#define OMAP7XX_DSP_BASE 0xE0000000 +#define OMAP7XX_DSP_SIZE 0x50000 +#define OMAP7XX_DSP_START 0xE0000000 + +#define OMAP7XX_DSPREG_BASE 0xE1000000 +#define OMAP7XX_DSPREG_SIZE SZ_128K +#define OMAP7XX_DSPREG_START 0xE1000000 + +/* + * ---------------------------------------------------------------------------- + * OMAP7XX specific configuration registers + * ---------------------------------------------------------------------------- + */ +#define OMAP7XX_CONFIG_BASE 0xfffe1000 +#define OMAP7XX_IO_CONF_0 0xfffe1070 +#define OMAP7XX_IO_CONF_1 0xfffe1074 +#define OMAP7XX_IO_CONF_2 0xfffe1078 +#define OMAP7XX_IO_CONF_3 0xfffe107c +#define OMAP7XX_IO_CONF_4 0xfffe1080 +#define OMAP7XX_IO_CONF_5 0xfffe1084 +#define OMAP7XX_IO_CONF_6 0xfffe1088 +#define OMAP7XX_IO_CONF_7 0xfffe108c +#define OMAP7XX_IO_CONF_8 0xfffe1090 +#define OMAP7XX_IO_CONF_9 0xfffe1094 +#define OMAP7XX_IO_CONF_10 0xfffe1098 +#define OMAP7XX_IO_CONF_11 0xfffe109c +#define OMAP7XX_IO_CONF_12 0xfffe10a0 +#define OMAP7XX_IO_CONF_13 0xfffe10a4 + +#define OMAP7XX_MODE_1 0xfffe1010 +#define OMAP7XX_MODE_2 0xfffe1014 + +/* CSMI specials: in terms of base + offset */ +#define OMAP7XX_MODE2_OFFSET 0x14 + +/* + * ---------------------------------------------------------------------------- + * OMAP7XX traffic controller configuration registers + * ---------------------------------------------------------------------------- + */ +#define OMAP7XX_FLASH_CFG_0 0xfffecc10 +#define OMAP7XX_FLASH_ACFG_0 0xfffecc50 +#define OMAP7XX_FLASH_CFG_1 0xfffecc14 +#define OMAP7XX_FLASH_ACFG_1 0xfffecc54 + +/* + * ---------------------------------------------------------------------------- + * OMAP7XX DSP control registers + * ---------------------------------------------------------------------------- + */ +#define OMAP7XX_ICR_BASE 0xfffbb800 +#define OMAP7XX_DSP_M_CTL 0xfffbb804 +#define OMAP7XX_DSP_MMU_BASE 0xfffed200 + +/* + * ---------------------------------------------------------------------------- + * OMAP7XX PCC_UPLD configuration registers + * ---------------------------------------------------------------------------- + */ +#define OMAP7XX_PCC_UPLD_CTRL_BASE (0xfffe0900) +#define OMAP7XX_PCC_UPLD_CTRL (OMAP7XX_PCC_UPLD_CTRL_BASE + 0x00) + +#endif /* __ASM_ARCH_OMAP7XX_H */ + -- cgit v1.2.3-70-g09d2 From b51988db94faec47d6e7c69c8e691cfc194f66db Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 07:34:13 +0100 Subject: OMAP7XX: Update core omap1 files to use omap7xx.h This patch is part of a series which removes references to omap730 in code which is shared with omap850, replacing them with references to omap7xx. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/board-fsample.c | 12 ++++++------ arch/arm/mach-omap1/board-perseus2.c | 12 ++++++------ arch/arm/mach-omap1/clock.c | 2 +- arch/arm/mach-omap1/io.c | 12 ++++++------ arch/arm/plat-omap/include/mach/hardware.h | 2 +- arch/arm/plat-omap/include/mach/mux.h | 14 +++++++------- arch/arm/plat-omap/io.c | 12 ++++++------ 7 files changed, 33 insertions(+), 33 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/board-fsample.c b/arch/arm/mach-omap1/board-fsample.c index a7ead1b9322..e53f7748ac1 100644 --- a/arch/arm/mach-omap1/board-fsample.c +++ b/arch/arm/mach-omap1/board-fsample.c @@ -309,7 +309,7 @@ static void __init omap_fsample_map_io(void) /* * Hold GSM Reset until needed */ - omap_writew(omap_readw(OMAP730_DSP_M_CTL) & ~1, OMAP730_DSP_M_CTL); + omap_writew(omap_readw(OMAP7XX_DSP_M_CTL) & ~1, OMAP7XX_DSP_M_CTL); /* * UARTs -> done automagically by 8250 driver @@ -320,21 +320,21 @@ static void __init omap_fsample_map_io(void) */ /* Flash: CS0 timings setup */ - omap_writel(0x0000fff3, OMAP730_FLASH_CFG_0); - omap_writel(0x00000088, OMAP730_FLASH_ACFG_0); + omap_writel(0x0000fff3, OMAP7XX_FLASH_CFG_0); + omap_writel(0x00000088, OMAP7XX_FLASH_ACFG_0); /* * Ethernet support through the debug board * CS1 timings setup */ - omap_writel(0x0000fff3, OMAP730_FLASH_CFG_1); - omap_writel(0x00000000, OMAP730_FLASH_ACFG_1); + omap_writel(0x0000fff3, OMAP7XX_FLASH_CFG_1); + omap_writel(0x00000000, OMAP7XX_FLASH_ACFG_1); /* * Configure MPU_EXT_NIRQ IO in IO_CONF9 register, * It is used as the Ethernet controller interrupt */ - omap_writel(omap_readl(OMAP730_IO_CONF_9) & 0x1FFFFFFF, OMAP730_IO_CONF_9); + omap_writel(omap_readl(OMAP7XX_IO_CONF_9) & 0x1FFFFFFF, OMAP7XX_IO_CONF_9); } MACHINE_START(OMAP_FSAMPLE, "OMAP730 F-Sample") diff --git a/arch/arm/mach-omap1/board-perseus2.c b/arch/arm/mach-omap1/board-perseus2.c index 83406699f31..ec22838e8e7 100644 --- a/arch/arm/mach-omap1/board-perseus2.c +++ b/arch/arm/mach-omap1/board-perseus2.c @@ -270,7 +270,7 @@ static void __init omap_perseus2_map_io(void) /* * Hold GSM Reset until needed */ - omap_writew(omap_readw(OMAP730_DSP_M_CTL) & ~1, OMAP730_DSP_M_CTL); + omap_writew(omap_readw(OMAP7XX_DSP_M_CTL) & ~1, OMAP7XX_DSP_M_CTL); /* * UARTs -> done automagically by 8250 driver @@ -281,21 +281,21 @@ static void __init omap_perseus2_map_io(void) */ /* Flash: CS0 timings setup */ - omap_writel(0x0000fff3, OMAP730_FLASH_CFG_0); - omap_writel(0x00000088, OMAP730_FLASH_ACFG_0); + omap_writel(0x0000fff3, OMAP7XX_FLASH_CFG_0); + omap_writel(0x00000088, OMAP7XX_FLASH_ACFG_0); /* * Ethernet support through the debug board * CS1 timings setup */ - omap_writel(0x0000fff3, OMAP730_FLASH_CFG_1); - omap_writel(0x00000000, OMAP730_FLASH_ACFG_1); + omap_writel(0x0000fff3, OMAP7XX_FLASH_CFG_1); + omap_writel(0x00000000, OMAP7XX_FLASH_ACFG_1); /* * Configure MPU_EXT_NIRQ IO in IO_CONF9 register, * It is used as the Ethernet controller interrupt */ - omap_writel(omap_readl(OMAP730_IO_CONF_9) & 0x1FFFFFFF, OMAP730_IO_CONF_9); + omap_writel(omap_readl(OMAP7XX_IO_CONF_9) & 0x1FFFFFFF, OMAP7XX_IO_CONF_9); } MACHINE_START(OMAP_PERSEUS2, "OMAP730 Perseus2") diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index fcbea61cb8c..c24cc28238f 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -862,7 +862,7 @@ int __init omap1_clk_init(void) #if defined(CONFIG_MACH_OMAP_PERSEUS2) || defined(CONFIG_MACH_OMAP_FSAMPLE) /* Select slicer output as OMAP input clock */ - omap_writew(omap_readw(OMAP730_PCC_UPLD_CTRL) & ~0x1, OMAP730_PCC_UPLD_CTRL); + omap_writew(omap_readw(OMAP7XX_PCC_UPLD_CTRL) & ~0x1, OMAP7XX_PCC_UPLD_CTRL); #endif /* Amstrad Delta wants BCLK high when inactive */ diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c index 19de57f74e8..157d5082ffe 100644 --- a/arch/arm/mach-omap1/io.c +++ b/arch/arm/mach-omap1/io.c @@ -39,14 +39,14 @@ static struct map_desc omap_io_desc[] __initdata = { #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) static struct map_desc omap730_io_desc[] __initdata = { { - .virtual = OMAP730_DSP_BASE, - .pfn = __phys_to_pfn(OMAP730_DSP_START), - .length = OMAP730_DSP_SIZE, + .virtual = OMAP7XX_DSP_BASE, + .pfn = __phys_to_pfn(OMAP7XX_DSP_START), + .length = OMAP7XX_DSP_SIZE, .type = MT_DEVICE }, { - .virtual = OMAP730_DSPREG_BASE, - .pfn = __phys_to_pfn(OMAP730_DSPREG_START), - .length = OMAP730_DSPREG_SIZE, + .virtual = OMAP7XX_DSPREG_BASE, + .pfn = __phys_to_pfn(OMAP7XX_DSPREG_START), + .length = OMAP7XX_DSPREG_SIZE, .type = MT_DEVICE } }; diff --git a/arch/arm/plat-omap/include/mach/hardware.h b/arch/arm/plat-omap/include/mach/hardware.h index 26c1fbff08a..99c42412c0a 100644 --- a/arch/arm/plat-omap/include/mach/hardware.h +++ b/arch/arm/plat-omap/include/mach/hardware.h @@ -280,7 +280,7 @@ * --------------------------------------------------------------------------- */ -#include "omap730.h" +#include "omap7xx.h" #include "omap1510.h" #include "omap16xx.h" #include "omap24xx.h" diff --git a/arch/arm/plat-omap/include/mach/mux.h b/arch/arm/plat-omap/include/mach/mux.h index 587fb63d232..66ae302f0c0 100644 --- a/arch/arm/plat-omap/include/mach/mux.h +++ b/arch/arm/plat-omap/include/mach/mux.h @@ -51,13 +51,13 @@ .pu_pd_reg = PU_PD_SEL_##reg, \ .pu_pd_val = status, -#define MUX_REG_730(reg, mode_offset, mode) .mux_reg_name = "OMAP730_IO_CONF_"#reg, \ - .mux_reg = OMAP730_IO_CONF_##reg, \ +#define MUX_REG_730(reg, mode_offset, mode) .mux_reg_name = "OMAP7XX_IO_CONF_"#reg, \ + .mux_reg = OMAP7XX_IO_CONF_##reg, \ .mask_offset = mode_offset, \ .mask = mode, -#define PULL_REG_730(reg, bit, status) .pull_name = "OMAP730_IO_CONF_"#reg, \ - .pull_reg = OMAP730_IO_CONF_##reg, \ +#define PULL_REG_730(reg, bit, status) .pull_name = "OMAP7XX_IO_CONF_"#reg, \ + .pull_reg = OMAP7XX_IO_CONF_##reg, \ .pull_bit = bit, \ .pull_val = status, @@ -75,11 +75,11 @@ .pu_pd_val = status, #define MUX_REG_730(reg, mode_offset, mode) \ - .mux_reg = OMAP730_IO_CONF_##reg, \ + .mux_reg = OMAP7XX_IO_CONF_##reg, \ .mask_offset = mode_offset, \ .mask = mode, -#define PULL_REG_730(reg, bit, status) .pull_reg = OMAP730_IO_CONF_##reg, \ +#define PULL_REG_730(reg, bit, status) .pull_reg = OMAP7XX_IO_CONF_##reg, \ .pull_bit = bit, \ .pull_val = status, @@ -99,7 +99,7 @@ /* * OMAP730/850 has a slightly different config for the pin mux. - * - config regs are the OMAP730_IO_CONF_x regs (see omap730.h) regs and + * - config regs are the OMAP7XX_IO_CONF_x regs (see omap730.h) regs and * not the FUNC_MUX_CTRL_x regs from hardware.h * - for pull-up/down, only has one enable bit which is is in the same register * as mux config diff --git a/arch/arm/plat-omap/io.c b/arch/arm/plat-omap/io.c index 388fd949093..23a205f4a2b 100644 --- a/arch/arm/plat-omap/io.c +++ b/arch/arm/plat-omap/io.c @@ -13,7 +13,7 @@ #include #include -#include +#include #include #include #include @@ -34,12 +34,12 @@ void __iomem *omap_ioremap(unsigned long p, size_t size, unsigned int type) return XLATE(p, OMAP1_IO_PHYS, OMAP1_IO_VIRT); } if (cpu_is_omap7xx()) { - if (BETWEEN(p, OMAP730_DSP_BASE, OMAP730_DSP_SIZE)) - return XLATE(p, OMAP730_DSP_BASE, OMAP730_DSP_START); + if (BETWEEN(p, OMAP7XX_DSP_BASE, OMAP7XX_DSP_SIZE)) + return XLATE(p, OMAP7XX_DSP_BASE, OMAP7XX_DSP_START); - if (BETWEEN(p, OMAP730_DSPREG_BASE, OMAP730_DSPREG_SIZE)) - return XLATE(p, OMAP730_DSPREG_BASE, - OMAP730_DSPREG_START); + if (BETWEEN(p, OMAP7XX_DSPREG_BASE, OMAP7XX_DSPREG_SIZE)) + return XLATE(p, OMAP7XX_DSPREG_BASE, + OMAP7XX_DSPREG_START); } if (cpu_is_omap15xx()) { if (BETWEEN(p, OMAP1510_DSP_BASE, OMAP1510_DSP_SIZE)) -- cgit v1.2.3-70-g09d2 From 372b1c32e7e7d7aa5f44e0eaed4ad8ae21e4e9da Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Fri, 18 Sep 2009 04:09:39 +0100 Subject: OMAP7XX: Replace omap730 references in irqs.h and all users This patch is part of a series which removes references to omap730 in code which is shared with omap850, replacing them with references to omap7xx. Turns INT_730_* to INT_7XX_* for definitions in irqs.h and all users. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/board-fsample.c | 6 +- arch/arm/mach-omap1/board-perseus2.c | 6 +- arch/arm/mach-omap1/irq.c | 2 +- arch/arm/mach-omap1/mcbsp.c | 8 +- arch/arm/mach-omap1/pm.c | 10 +- arch/arm/mach-omap1/serial.c | 4 +- arch/arm/plat-omap/gpio.c | 14 +-- arch/arm/plat-omap/include/mach/entry-macro.S | 2 +- arch/arm/plat-omap/include/mach/irqs.h | 148 +++++++++++++------------- arch/arm/plat-omap/usb.c | 4 +- 10 files changed, 102 insertions(+), 102 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/board-fsample.c b/arch/arm/mach-omap1/board-fsample.c index e53f7748ac1..74720e65f11 100644 --- a/arch/arm/mach-omap1/board-fsample.c +++ b/arch/arm/mach-omap1/board-fsample.c @@ -107,7 +107,7 @@ static struct resource smc91x_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = INT_730_MPU_EXT_NIRQ, + .start = INT_7XX_MPU_EXT_NIRQ, .end = 0, .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, }, @@ -196,8 +196,8 @@ static struct platform_device smc91x_device = { static struct resource kp_resources[] = { [0] = { - .start = INT_730_MPUIO_KEYPAD, - .end = INT_730_MPUIO_KEYPAD, + .start = INT_7XX_MPUIO_KEYPAD, + .end = INT_7XX_MPUIO_KEYPAD, .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mach-omap1/board-perseus2.c b/arch/arm/mach-omap1/board-perseus2.c index ec22838e8e7..2f897cf2350 100644 --- a/arch/arm/mach-omap1/board-perseus2.c +++ b/arch/arm/mach-omap1/board-perseus2.c @@ -74,7 +74,7 @@ static struct resource smc91x_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = INT_730_MPU_EXT_NIRQ, + .start = INT_7XX_MPU_EXT_NIRQ, .end = 0, .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, }, @@ -163,8 +163,8 @@ static struct platform_device smc91x_device = { static struct resource kp_resources[] = { [0] = { - .start = INT_730_MPUIO_KEYPAD, - .end = INT_730_MPUIO_KEYPAD, + .start = INT_7XX_MPUIO_KEYPAD, + .end = INT_7XX_MPUIO_KEYPAD, .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c index c05999c4116..704a80c2972 100644 --- a/arch/arm/mach-omap1/irq.c +++ b/arch/arm/mach-omap1/irq.c @@ -234,7 +234,7 @@ void __init omap_init_irq(void) /* Unmask level 2 handler */ if (cpu_is_omap7xx()) - omap_unmask_irq(INT_730_IH2_IRQ); + omap_unmask_irq(INT_7XX_IH2_IRQ); else if (cpu_is_omap15xx()) omap_unmask_irq(INT_1510_IH2_IRQ); else if (cpu_is_omap16xx()) diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index 06f380bf221..7ccca0069dc 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -85,16 +85,16 @@ static struct omap_mcbsp_platform_data omap730_mcbsp_pdata[] = { .phys_base = OMAP730_MCBSP1_BASE, .dma_rx_sync = OMAP_DMA_MCBSP1_RX, .dma_tx_sync = OMAP_DMA_MCBSP1_TX, - .rx_irq = INT_730_McBSP1RX, - .tx_irq = INT_730_McBSP1TX, + .rx_irq = INT_7XX_McBSP1RX, + .tx_irq = INT_7XX_McBSP1TX, .ops = &omap1_mcbsp_ops, }, { .phys_base = OMAP730_MCBSP2_BASE, .dma_rx_sync = OMAP_DMA_MCBSP3_RX, .dma_tx_sync = OMAP_DMA_MCBSP3_TX, - .rx_irq = INT_730_McBSP2RX, - .tx_irq = INT_730_McBSP2TX, + .rx_irq = INT_7XX_McBSP2RX, + .tx_irq = INT_7XX_McBSP2TX, .ops = &omap1_mcbsp_ops, }, }; diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 12f246e3cdc..58479c75cac 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -184,8 +184,8 @@ static void omap_pm_wakeup_setup(void) * wake up to a GPIO interrupt. */ if (cpu_is_omap7xx()) - level1_wake = OMAP_IRQ_BIT(INT_730_GPIO_BANK1) | - OMAP_IRQ_BIT(INT_730_IH2_IRQ); + level1_wake = OMAP_IRQ_BIT(INT_7XX_GPIO_BANK1) | + OMAP_IRQ_BIT(INT_7XX_IH2_IRQ); else if (cpu_is_omap15xx()) level1_wake = OMAP_IRQ_BIT(INT_GPIO_BANK1) | OMAP_IRQ_BIT(INT_1510_IH2_IRQ); @@ -197,8 +197,8 @@ static void omap_pm_wakeup_setup(void) if (cpu_is_omap7xx()) { omap_writel(~level2_wake, OMAP_IH2_0_MIR); - omap_writel(~(OMAP_IRQ_BIT(INT_730_WAKE_UP_REQ) | - OMAP_IRQ_BIT(INT_730_MPUIO_KEYPAD)), + omap_writel(~(OMAP_IRQ_BIT(INT_7XX_WAKE_UP_REQ) | + OMAP_IRQ_BIT(INT_7XX_MPUIO_KEYPAD)), OMAP_IH2_1_MIR); } else if (cpu_is_omap15xx()) { level2_wake |= OMAP_IRQ_BIT(INT_KEYBOARD); @@ -687,7 +687,7 @@ static int __init omap_pm_init(void) pm_idle = omap1_pm_idle; if (cpu_is_omap7xx()) - setup_irq(INT_730_WAKE_UP_REQ, &omap_wakeup_irq); + setup_irq(INT_7XX_WAKE_UP_REQ, &omap_wakeup_irq); else if (cpu_is_omap16xx()) setup_irq(INT_1610_WAKE_UP_REQ, &omap_wakeup_irq); diff --git a/arch/arm/mach-omap1/serial.c b/arch/arm/mach-omap1/serial.c index 49381e271be..ed07af109f0 100644 --- a/arch/arm/mach-omap1/serial.c +++ b/arch/arm/mach-omap1/serial.c @@ -113,8 +113,8 @@ void __init omap_serial_init(void) if (cpu_is_omap7xx()) { serial_platform_data[0].regshift = 0; serial_platform_data[1].regshift = 0; - serial_platform_data[0].irq = INT_730_UART_MODEM_1; - serial_platform_data[1].irq = INT_730_UART_MODEM_IRDA_2; + serial_platform_data[0].irq = INT_7XX_UART_MODEM_1; + serial_platform_data[1].irq = INT_7XX_UART_MODEM_IRDA_2; } if (cpu_is_omap15xx()) { diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c index 665ca050183..22f6e689f5c 100644 --- a/arch/arm/plat-omap/gpio.c +++ b/arch/arm/plat-omap/gpio.c @@ -221,13 +221,13 @@ static struct gpio_bank gpio_bank_1510[2] = { #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) static struct gpio_bank gpio_bank_730[7] = { - { OMAP1_MPUIO_VBASE, INT_730_MPUIO, IH_MPUIO_BASE, METHOD_MPUIO }, - { OMAP730_GPIO1_BASE, INT_730_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_730 }, - { OMAP730_GPIO2_BASE, INT_730_GPIO_BANK2, IH_GPIO_BASE + 32, METHOD_GPIO_730 }, - { OMAP730_GPIO3_BASE, INT_730_GPIO_BANK3, IH_GPIO_BASE + 64, METHOD_GPIO_730 }, - { OMAP730_GPIO4_BASE, INT_730_GPIO_BANK4, IH_GPIO_BASE + 96, METHOD_GPIO_730 }, - { OMAP730_GPIO5_BASE, INT_730_GPIO_BANK5, IH_GPIO_BASE + 128, METHOD_GPIO_730 }, - { OMAP730_GPIO6_BASE, INT_730_GPIO_BANK6, IH_GPIO_BASE + 160, METHOD_GPIO_730 }, + { OMAP1_MPUIO_VBASE, INT_7XX_MPUIO, IH_MPUIO_BASE, METHOD_MPUIO }, + { OMAP730_GPIO1_BASE, INT_7XX_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_730 }, + { OMAP730_GPIO2_BASE, INT_7XX_GPIO_BANK2, IH_GPIO_BASE + 32, METHOD_GPIO_730 }, + { OMAP730_GPIO3_BASE, INT_7XX_GPIO_BANK3, IH_GPIO_BASE + 64, METHOD_GPIO_730 }, + { OMAP730_GPIO4_BASE, INT_7XX_GPIO_BANK4, IH_GPIO_BASE + 96, METHOD_GPIO_730 }, + { OMAP730_GPIO5_BASE, INT_7XX_GPIO_BANK5, IH_GPIO_BASE + 128, METHOD_GPIO_730 }, + { OMAP730_GPIO6_BASE, INT_7XX_GPIO_BANK6, IH_GPIO_BASE + 160, METHOD_GPIO_730 }, }; #endif diff --git a/arch/arm/plat-omap/include/mach/entry-macro.S b/arch/arm/plat-omap/include/mach/entry-macro.S index bcf71585665..abe086416e1 100644 --- a/arch/arm/plat-omap/include/mach/entry-macro.S +++ b/arch/arm/plat-omap/include/mach/entry-macro.S @@ -21,7 +21,7 @@ (defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX)) #error "FIXME: OMAP7XX doesn't support multiple-OMAP" #elif defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) -#define INT_IH2_IRQ INT_730_IH2_IRQ +#define INT_IH2_IRQ INT_7XX_IH2_IRQ #elif defined(CONFIG_ARCH_OMAP15XX) #define INT_IH2_IRQ INT_1510_IH2_IRQ #elif defined(CONFIG_ARCH_OMAP16XX) diff --git a/arch/arm/plat-omap/include/mach/irqs.h b/arch/arm/plat-omap/include/mach/irqs.h index 7f338f0c745..6a6d0281e1d 100644 --- a/arch/arm/plat-omap/include/mach/irqs.h +++ b/arch/arm/plat-omap/include/mach/irqs.h @@ -86,26 +86,26 @@ #define INT_1610_SSR_FIFO_0 29 /* - * OMAP-730 specific IRQ numbers for interrupt handler 1 + * OMAP-7xx specific IRQ numbers for interrupt handler 1 */ -#define INT_730_IH2_FIQ 0 -#define INT_730_IH2_IRQ 1 -#define INT_730_USB_NON_ISO 2 -#define INT_730_USB_ISO 3 -#define INT_730_ICR 4 -#define INT_730_EAC 5 -#define INT_730_GPIO_BANK1 6 -#define INT_730_GPIO_BANK2 7 -#define INT_730_GPIO_BANK3 8 -#define INT_730_McBSP2TX 10 -#define INT_730_McBSP2RX 11 -#define INT_730_McBSP2RX_OVF 12 -#define INT_730_LCD_LINE 14 -#define INT_730_GSM_PROTECT 15 -#define INT_730_TIMER3 16 -#define INT_730_GPIO_BANK5 17 -#define INT_730_GPIO_BANK6 18 -#define INT_730_SPGIO_WR 29 +#define INT_7XX_IH2_FIQ 0 +#define INT_7XX_IH2_IRQ 1 +#define INT_7XX_USB_NON_ISO 2 +#define INT_7XX_USB_ISO 3 +#define INT_7XX_ICR 4 +#define INT_7XX_EAC 5 +#define INT_7XX_GPIO_BANK1 6 +#define INT_7XX_GPIO_BANK2 7 +#define INT_7XX_GPIO_BANK3 8 +#define INT_7XX_McBSP2TX 10 +#define INT_7XX_McBSP2RX 11 +#define INT_7XX_McBSP2RX_OVF 12 +#define INT_7XX_LCD_LINE 14 +#define INT_7XX_GSM_PROTECT 15 +#define INT_7XX_TIMER3 16 +#define INT_7XX_GPIO_BANK5 17 +#define INT_7XX_GPIO_BANK6 18 +#define INT_7XX_SPGIO_WR 29 /* * IRQ numbers for interrupt handler 2 @@ -183,62 +183,62 @@ #define INT_1610_SHA1MD5 (91 + IH2_BASE) /* - * OMAP-730 specific IRQ numbers for interrupt handler 2 + * OMAP-7xx specific IRQ numbers for interrupt handler 2 */ -#define INT_730_HW_ERRORS (0 + IH2_BASE) -#define INT_730_NFIQ_PWR_FAIL (1 + IH2_BASE) -#define INT_730_CFCD (2 + IH2_BASE) -#define INT_730_CFIREQ (3 + IH2_BASE) -#define INT_730_I2C (4 + IH2_BASE) -#define INT_730_PCC (5 + IH2_BASE) -#define INT_730_MPU_EXT_NIRQ (6 + IH2_BASE) -#define INT_730_SPI_100K_1 (7 + IH2_BASE) -#define INT_730_SYREN_SPI (8 + IH2_BASE) -#define INT_730_VLYNQ (9 + IH2_BASE) -#define INT_730_GPIO_BANK4 (10 + IH2_BASE) -#define INT_730_McBSP1TX (11 + IH2_BASE) -#define INT_730_McBSP1RX (12 + IH2_BASE) -#define INT_730_McBSP1RX_OF (13 + IH2_BASE) -#define INT_730_UART_MODEM_IRDA_2 (14 + IH2_BASE) -#define INT_730_UART_MODEM_1 (15 + IH2_BASE) -#define INT_730_MCSI (16 + IH2_BASE) -#define INT_730_uWireTX (17 + IH2_BASE) -#define INT_730_uWireRX (18 + IH2_BASE) -#define INT_730_SMC_CD (19 + IH2_BASE) -#define INT_730_SMC_IREQ (20 + IH2_BASE) -#define INT_730_HDQ_1WIRE (21 + IH2_BASE) -#define INT_730_TIMER32K (22 + IH2_BASE) -#define INT_730_MMC_SDIO (23 + IH2_BASE) -#define INT_730_UPLD (24 + IH2_BASE) -#define INT_730_USB_HHC_1 (27 + IH2_BASE) -#define INT_730_USB_HHC_2 (28 + IH2_BASE) -#define INT_730_USB_GENI (29 + IH2_BASE) -#define INT_730_USB_OTG (30 + IH2_BASE) -#define INT_730_CAMERA_IF (31 + IH2_BASE) -#define INT_730_RNG (32 + IH2_BASE) -#define INT_730_DUAL_MODE_TIMER (33 + IH2_BASE) -#define INT_730_DBB_RF_EN (34 + IH2_BASE) -#define INT_730_MPUIO_KEYPAD (35 + IH2_BASE) -#define INT_730_SHA1_MD5 (36 + IH2_BASE) -#define INT_730_SPI_100K_2 (37 + IH2_BASE) -#define INT_730_RNG_IDLE (38 + IH2_BASE) -#define INT_730_MPUIO (39 + IH2_BASE) -#define INT_730_LLPC_LCD_CTRL_CAN_BE_OFF (40 + IH2_BASE) -#define INT_730_LLPC_OE_FALLING (41 + IH2_BASE) -#define INT_730_LLPC_OE_RISING (42 + IH2_BASE) -#define INT_730_LLPC_VSYNC (43 + IH2_BASE) -#define INT_730_WAKE_UP_REQ (46 + IH2_BASE) -#define INT_730_DMA_CH6 (53 + IH2_BASE) -#define INT_730_DMA_CH7 (54 + IH2_BASE) -#define INT_730_DMA_CH8 (55 + IH2_BASE) -#define INT_730_DMA_CH9 (56 + IH2_BASE) -#define INT_730_DMA_CH10 (57 + IH2_BASE) -#define INT_730_DMA_CH11 (58 + IH2_BASE) -#define INT_730_DMA_CH12 (59 + IH2_BASE) -#define INT_730_DMA_CH13 (60 + IH2_BASE) -#define INT_730_DMA_CH14 (61 + IH2_BASE) -#define INT_730_DMA_CH15 (62 + IH2_BASE) -#define INT_730_NAND (63 + IH2_BASE) +#define INT_7XX_HW_ERRORS (0 + IH2_BASE) +#define INT_7XX_NFIQ_PWR_FAIL (1 + IH2_BASE) +#define INT_7XX_CFCD (2 + IH2_BASE) +#define INT_7XX_CFIREQ (3 + IH2_BASE) +#define INT_7XX_I2C (4 + IH2_BASE) +#define INT_7XX_PCC (5 + IH2_BASE) +#define INT_7XX_MPU_EXT_NIRQ (6 + IH2_BASE) +#define INT_7XX_SPI_100K_1 (7 + IH2_BASE) +#define INT_7XX_SYREN_SPI (8 + IH2_BASE) +#define INT_7XX_VLYNQ (9 + IH2_BASE) +#define INT_7XX_GPIO_BANK4 (10 + IH2_BASE) +#define INT_7XX_McBSP1TX (11 + IH2_BASE) +#define INT_7XX_McBSP1RX (12 + IH2_BASE) +#define INT_7XX_McBSP1RX_OF (13 + IH2_BASE) +#define INT_7XX_UART_MODEM_IRDA_2 (14 + IH2_BASE) +#define INT_7XX_UART_MODEM_1 (15 + IH2_BASE) +#define INT_7XX_MCSI (16 + IH2_BASE) +#define INT_7XX_uWireTX (17 + IH2_BASE) +#define INT_7XX_uWireRX (18 + IH2_BASE) +#define INT_7XX_SMC_CD (19 + IH2_BASE) +#define INT_7XX_SMC_IREQ (20 + IH2_BASE) +#define INT_7XX_HDQ_1WIRE (21 + IH2_BASE) +#define INT_7XX_TIMER32K (22 + IH2_BASE) +#define INT_7XX_MMC_SDIO (23 + IH2_BASE) +#define INT_7XX_UPLD (24 + IH2_BASE) +#define INT_7XX_USB_HHC_1 (27 + IH2_BASE) +#define INT_7XX_USB_HHC_2 (28 + IH2_BASE) +#define INT_7XX_USB_GENI (29 + IH2_BASE) +#define INT_7XX_USB_OTG (30 + IH2_BASE) +#define INT_7XX_CAMERA_IF (31 + IH2_BASE) +#define INT_7XX_RNG (32 + IH2_BASE) +#define INT_7XX_DUAL_MODE_TIMER (33 + IH2_BASE) +#define INT_7XX_DBB_RF_EN (34 + IH2_BASE) +#define INT_7XX_MPUIO_KEYPAD (35 + IH2_BASE) +#define INT_7XX_SHA1_MD5 (36 + IH2_BASE) +#define INT_7XX_SPI_100K_2 (37 + IH2_BASE) +#define INT_7XX_RNG_IDLE (38 + IH2_BASE) +#define INT_7XX_MPUIO (39 + IH2_BASE) +#define INT_7XX_LLPC_LCD_CTRL_CAN_BE_OFF (40 + IH2_BASE) +#define INT_7XX_LLPC_OE_FALLING (41 + IH2_BASE) +#define INT_7XX_LLPC_OE_RISING (42 + IH2_BASE) +#define INT_7XX_LLPC_VSYNC (43 + IH2_BASE) +#define INT_7XX_WAKE_UP_REQ (46 + IH2_BASE) +#define INT_7XX_DMA_CH6 (53 + IH2_BASE) +#define INT_7XX_DMA_CH7 (54 + IH2_BASE) +#define INT_7XX_DMA_CH8 (55 + IH2_BASE) +#define INT_7XX_DMA_CH9 (56 + IH2_BASE) +#define INT_7XX_DMA_CH10 (57 + IH2_BASE) +#define INT_7XX_DMA_CH11 (58 + IH2_BASE) +#define INT_7XX_DMA_CH12 (59 + IH2_BASE) +#define INT_7XX_DMA_CH13 (60 + IH2_BASE) +#define INT_7XX_DMA_CH14 (61 + IH2_BASE) +#define INT_7XX_DMA_CH15 (62 + IH2_BASE) +#define INT_7XX_NAND (63 + IH2_BASE) #define INT_24XX_SYS_NIRQ 7 #define INT_24XX_SDMA_IRQ0 12 diff --git a/arch/arm/plat-omap/usb.c b/arch/arm/plat-omap/usb.c index 980d2eb68a2..3c40b8525df 100644 --- a/arch/arm/plat-omap/usb.c +++ b/arch/arm/plat-omap/usb.c @@ -615,7 +615,7 @@ omap_otg_init(struct omap_usb_config *config) syscon &= ~HST_IDLE_EN; ohci_device.dev.platform_data = config; if (cpu_is_omap7xx()) - ohci_resources[1].start = INT_730_USB_HHC_1; + ohci_resources[1].start = INT_7XX_USB_HHC_1; status = platform_device_register(&ohci_device); if (status) pr_debug("can't register OHCI device, %d\n", status); @@ -627,7 +627,7 @@ omap_otg_init(struct omap_usb_config *config) syscon &= ~OTG_IDLE_EN; otg_device.dev.platform_data = config; if (cpu_is_omap7xx()) - otg_resources[1].start = INT_730_USB_OTG; + otg_resources[1].start = INT_7XX_USB_OTG; status = platform_device_register(&otg_device); if (status) pr_debug("can't register OTG device, %d\n", status); -- cgit v1.2.3-70-g09d2 From 7c0069264017fdac8ef017b8893f0f0d7a13851a Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 10:02:58 +0100 Subject: OMAP7XX: Rename all the rest of the omap730 references in omap1 core This patch is part of a series which removes references to omap730 in code which is shared with omap850, replacing them with references to omap7xx. This updates all the remaining omap730 references in miscellaneous local variables, macros and similar. Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/clock.c | 8 +-- arch/arm/mach-omap1/io.c | 4 +- arch/arm/mach-omap1/irq.c | 6 +-- arch/arm/mach-omap1/mcbsp.c | 18 +++---- arch/arm/mach-omap1/mux.c | 42 +++++++-------- arch/arm/mach-omap1/pm.c | 70 ++++++++++++------------- arch/arm/mach-omap1/pm.h | 52 +++++++++---------- arch/arm/mach-omap1/sleep.S | 22 ++++---- arch/arm/plat-omap/devices.c | 22 ++++---- arch/arm/plat-omap/gpio.c | 92 ++++++++++++++++----------------- arch/arm/plat-omap/include/mach/mcbsp.h | 4 +- arch/arm/plat-omap/include/mach/mux.h | 42 +++++++-------- 12 files changed, 191 insertions(+), 191 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index c24cc28238f..d2b00a56393 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -69,7 +69,7 @@ struct omap_clk { } #define CK_310 (1 << 0) -#define CK_730 (1 << 1) +#define CK_7XX (1 << 1) #define CK_1510 (1 << 2) #define CK_16XX (1 << 3) @@ -97,7 +97,7 @@ static struct omap_clk omap_clks[] = { CLK(NULL, "dspxor_ck", &dspxor_ck, CK_16XX | CK_1510 | CK_310), CLK(NULL, "dsptim_ck", &dsptim_ck, CK_16XX | CK_1510 | CK_310), /* CK_GEN3 clocks */ - CLK(NULL, "tc_ck", &tc_ck.clk, CK_16XX | CK_1510 | CK_310 | CK_730), + CLK(NULL, "tc_ck", &tc_ck.clk, CK_16XX | CK_1510 | CK_310 | CK_7XX), CLK(NULL, "tipb_ck", &tipb_ck, CK_1510 | CK_310), CLK(NULL, "l3_ocpi_ck", &l3_ocpi_ck, CK_16XX), CLK(NULL, "tc1_ck", &tc1_ck, CK_16XX), @@ -108,7 +108,7 @@ static struct omap_clk omap_clks[] = { CLK(NULL, "lb_ck", &lb_ck.clk, CK_1510 | CK_310), CLK(NULL, "rhea1_ck", &rhea1_ck, CK_16XX), CLK(NULL, "rhea2_ck", &rhea2_ck, CK_16XX), - CLK(NULL, "lcd_ck", &lcd_ck_16xx, CK_16XX | CK_730), + CLK(NULL, "lcd_ck", &lcd_ck_16xx, CK_16XX | CK_7XX), CLK(NULL, "lcd_ck", &lcd_ck_1510.clk, CK_1510 | CK_310), /* ULPD clocks */ CLK(NULL, "uart1_ck", &uart1_1510, CK_1510 | CK_310), @@ -784,7 +784,7 @@ int __init omap1_clk_init(void) if (cpu_is_omap1510()) cpu_mask |= CK_1510; if (cpu_is_omap7xx()) - cpu_mask |= CK_730; + cpu_mask |= CK_7XX; if (cpu_is_omap310()) cpu_mask |= CK_310; diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c index 157d5082ffe..a27df2c14ac 100644 --- a/arch/arm/mach-omap1/io.c +++ b/arch/arm/mach-omap1/io.c @@ -37,7 +37,7 @@ static struct map_desc omap_io_desc[] __initdata = { }; #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) -static struct map_desc omap730_io_desc[] __initdata = { +static struct map_desc omap7xx_io_desc[] __initdata = { { .virtual = OMAP7XX_DSP_BASE, .pfn = __phys_to_pfn(OMAP7XX_DSP_START), @@ -106,7 +106,7 @@ void __init omap1_map_common_io(void) #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) if (cpu_is_omap7xx()) { - iotable_init(omap730_io_desc, ARRAY_SIZE(omap730_io_desc)); + iotable_init(omap7xx_io_desc, ARRAY_SIZE(omap7xx_io_desc)); } #endif #ifdef CONFIG_ARCH_OMAP15XX diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c index 704a80c2972..8f98b58575d 100644 --- a/arch/arm/mach-omap1/irq.c +++ b/arch/arm/mach-omap1/irq.c @@ -138,7 +138,7 @@ static void omap_irq_set_cfg(int irq, int fiq, int priority, int trigger) } #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) -static struct omap_irq_bank omap730_irq_banks[] = { +static struct omap_irq_bank omap7xx_irq_banks[] = { { .base_reg = OMAP_IH1_BASE, .trigger_map = 0xb3f8e22f }, { .base_reg = OMAP_IH2_BASE, .trigger_map = 0xfdb9c1f2 }, { .base_reg = OMAP_IH2_BASE + 0x100, .trigger_map = 0x800040f3 }, @@ -180,8 +180,8 @@ void __init omap_init_irq(void) #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) if (cpu_is_omap7xx()) { - irq_banks = omap730_irq_banks; - irq_bank_count = ARRAY_SIZE(omap730_irq_banks); + irq_banks = omap7xx_irq_banks; + irq_bank_count = ARRAY_SIZE(omap7xx_irq_banks); } #endif #ifdef CONFIG_ARCH_OMAP15XX diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index 7ccca0069dc..3a51cb210de 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -80,9 +80,9 @@ static struct omap_mcbsp_ops omap1_mcbsp_ops = { }; #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) -static struct omap_mcbsp_platform_data omap730_mcbsp_pdata[] = { +static struct omap_mcbsp_platform_data omap7xx_mcbsp_pdata[] = { { - .phys_base = OMAP730_MCBSP1_BASE, + .phys_base = OMAP7XX_MCBSP1_BASE, .dma_rx_sync = OMAP_DMA_MCBSP1_RX, .dma_tx_sync = OMAP_DMA_MCBSP1_TX, .rx_irq = INT_7XX_McBSP1RX, @@ -90,7 +90,7 @@ static struct omap_mcbsp_platform_data omap730_mcbsp_pdata[] = { .ops = &omap1_mcbsp_ops, }, { - .phys_base = OMAP730_MCBSP2_BASE, + .phys_base = OMAP7XX_MCBSP2_BASE, .dma_rx_sync = OMAP_DMA_MCBSP3_RX, .dma_tx_sync = OMAP_DMA_MCBSP3_TX, .rx_irq = INT_7XX_McBSP2RX, @@ -98,10 +98,10 @@ static struct omap_mcbsp_platform_data omap730_mcbsp_pdata[] = { .ops = &omap1_mcbsp_ops, }, }; -#define OMAP730_MCBSP_PDATA_SZ ARRAY_SIZE(omap730_mcbsp_pdata) +#define OMAP7XX_MCBSP_PDATA_SZ ARRAY_SIZE(omap7xx_mcbsp_pdata) #else -#define omap730_mcbsp_pdata NULL -#define OMAP730_MCBSP_PDATA_SZ 0 +#define omap7xx_mcbsp_pdata NULL +#define OMAP7XX_MCBSP_PDATA_SZ 0 #endif #ifdef CONFIG_ARCH_OMAP15XX @@ -173,7 +173,7 @@ static struct omap_mcbsp_platform_data omap16xx_mcbsp_pdata[] = { int __init omap1_mcbsp_init(void) { if (cpu_is_omap7xx()) - omap_mcbsp_count = OMAP730_MCBSP_PDATA_SZ; + omap_mcbsp_count = OMAP7XX_MCBSP_PDATA_SZ; if (cpu_is_omap15xx()) omap_mcbsp_count = OMAP15XX_MCBSP_PDATA_SZ; if (cpu_is_omap16xx()) @@ -185,8 +185,8 @@ int __init omap1_mcbsp_init(void) return -ENOMEM; if (cpu_is_omap7xx()) - omap_mcbsp_register_board_cfg(omap730_mcbsp_pdata, - OMAP730_MCBSP_PDATA_SZ); + omap_mcbsp_register_board_cfg(omap7xx_mcbsp_pdata, + OMAP7XX_MCBSP_PDATA_SZ); if (cpu_is_omap15xx()) omap_mcbsp_register_board_cfg(omap15xx_mcbsp_pdata, diff --git a/arch/arm/mach-omap1/mux.c b/arch/arm/mach-omap1/mux.c index f9d45a3bf4f..d59899d6a7f 100644 --- a/arch/arm/mach-omap1/mux.c +++ b/arch/arm/mach-omap1/mux.c @@ -36,27 +36,27 @@ static struct omap_mux_cfg arch_mux_cfg; #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) -static struct pin_config __initdata_or_module omap730_pins[] = { -MUX_CFG_730("E2_730_KBR0", 12, 21, 0, 20, 1, 0) -MUX_CFG_730("J7_730_KBR1", 12, 25, 0, 24, 1, 0) -MUX_CFG_730("E1_730_KBR2", 12, 29, 0, 28, 1, 0) -MUX_CFG_730("F3_730_KBR3", 13, 1, 0, 0, 1, 0) -MUX_CFG_730("D2_730_KBR4", 13, 5, 0, 4, 1, 0) -MUX_CFG_730("C2_730_KBC0", 13, 9, 0, 8, 1, 0) -MUX_CFG_730("D3_730_KBC1", 13, 13, 0, 12, 1, 0) -MUX_CFG_730("E4_730_KBC2", 13, 17, 0, 16, 1, 0) -MUX_CFG_730("F4_730_KBC3", 13, 21, 0, 20, 1, 0) -MUX_CFG_730("E3_730_KBC4", 13, 25, 0, 24, 1, 0) - -MUX_CFG_730("AA17_730_USB_DM", 2, 21, 0, 20, 0, 0) -MUX_CFG_730("W16_730_USB_PU_EN", 2, 25, 0, 24, 0, 0) -MUX_CFG_730("W17_730_USB_VBUSI", 2, 29, 0, 28, 0, 0) +static struct pin_config __initdata_or_module omap7xx_pins[] = { +MUX_CFG_7XX("E2_7XX_KBR0", 12, 21, 0, 20, 1, 0) +MUX_CFG_7XX("J7_7XX_KBR1", 12, 25, 0, 24, 1, 0) +MUX_CFG_7XX("E1_7XX_KBR2", 12, 29, 0, 28, 1, 0) +MUX_CFG_7XX("F3_7XX_KBR3", 13, 1, 0, 0, 1, 0) +MUX_CFG_7XX("D2_7XX_KBR4", 13, 5, 0, 4, 1, 0) +MUX_CFG_7XX("C2_7XX_KBC0", 13, 9, 0, 8, 1, 0) +MUX_CFG_7XX("D3_7XX_KBC1", 13, 13, 0, 12, 1, 0) +MUX_CFG_7XX("E4_7XX_KBC2", 13, 17, 0, 16, 1, 0) +MUX_CFG_7XX("F4_7XX_KBC3", 13, 21, 0, 20, 1, 0) +MUX_CFG_7XX("E3_7XX_KBC4", 13, 25, 0, 24, 1, 0) + +MUX_CFG_7XX("AA17_7XX_USB_DM", 2, 21, 0, 20, 0, 0) +MUX_CFG_7XX("W16_7XX_USB_PU_EN", 2, 25, 0, 24, 0, 0) +MUX_CFG_7XX("W17_7XX_USB_VBUSI", 2, 29, 0, 28, 0, 0) }; -#define OMAP730_PINS_SZ ARRAY_SIZE(omap730_pins) +#define OMAP7XX_PINS_SZ ARRAY_SIZE(omap7xx_pins) #else -#define omap730_pins NULL -#define OMAP730_PINS_SZ 0 -#endif /* CONFIG_ARCH_OMAP730 */ +#define omap7xx_pins NULL +#define OMAP7XX_PINS_SZ 0 +#endif /* CONFIG_ARCH_OMAP730 || CONFIG_ARCH_OMAP850 */ #if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX) static struct pin_config __initdata_or_module omap1xxx_pins[] = { @@ -431,8 +431,8 @@ int __init_or_module omap1_cfg_reg(const struct pin_config *cfg) int __init omap1_mux_init(void) { if (cpu_is_omap7xx()) { - arch_mux_cfg.pins = omap730_pins; - arch_mux_cfg.size = OMAP730_PINS_SZ; + arch_mux_cfg.pins = omap7xx_pins; + arch_mux_cfg.size = OMAP7XX_PINS_SZ; arch_mux_cfg.cfg_reg = omap1_cfg_reg; } diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 58479c75cac..10f4e4adca1 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -62,7 +62,7 @@ static unsigned int arm_sleep_save[ARM_SLEEP_SAVE_SIZE]; static unsigned short dsp_sleep_save[DSP_SLEEP_SAVE_SIZE]; static unsigned short ulpd_sleep_save[ULPD_SLEEP_SAVE_SIZE]; -static unsigned int mpui730_sleep_save[MPUI730_SLEEP_SAVE_SIZE]; +static unsigned int mpui7xx_sleep_save[MPUI7XX_SLEEP_SAVE_SIZE]; static unsigned int mpui1510_sleep_save[MPUI1510_SLEEP_SAVE_SIZE]; static unsigned int mpui1610_sleep_save[MPUI1610_SLEEP_SAVE_SIZE]; @@ -254,14 +254,14 @@ void omap1_pm_suspend(void) */ if (cpu_is_omap7xx()) { - MPUI730_SAVE(OMAP_IH1_MIR); - MPUI730_SAVE(OMAP_IH2_0_MIR); - MPUI730_SAVE(OMAP_IH2_1_MIR); - MPUI730_SAVE(MPUI_CTRL); - MPUI730_SAVE(MPUI_DSP_BOOT_CONFIG); - MPUI730_SAVE(MPUI_DSP_API_CONFIG); - MPUI730_SAVE(EMIFS_CONFIG); - MPUI730_SAVE(EMIFF_SDRAM_CONFIG); + MPUI7XX_SAVE(OMAP_IH1_MIR); + MPUI7XX_SAVE(OMAP_IH2_0_MIR); + MPUI7XX_SAVE(OMAP_IH2_1_MIR); + MPUI7XX_SAVE(MPUI_CTRL); + MPUI7XX_SAVE(MPUI_DSP_BOOT_CONFIG); + MPUI7XX_SAVE(MPUI_DSP_API_CONFIG); + MPUI7XX_SAVE(EMIFS_CONFIG); + MPUI7XX_SAVE(EMIFF_SDRAM_CONFIG); } else if (cpu_is_omap15xx()) { MPUI1510_SAVE(OMAP_IH1_MIR); @@ -384,11 +384,11 @@ void omap1_pm_suspend(void) ULPD_RESTORE(ULPD_STATUS_REQ); if (cpu_is_omap7xx()) { - MPUI730_RESTORE(EMIFS_CONFIG); - MPUI730_RESTORE(EMIFF_SDRAM_CONFIG); - MPUI730_RESTORE(OMAP_IH1_MIR); - MPUI730_RESTORE(OMAP_IH2_0_MIR); - MPUI730_RESTORE(OMAP_IH2_1_MIR); + MPUI7XX_RESTORE(EMIFS_CONFIG); + MPUI7XX_RESTORE(EMIFF_SDRAM_CONFIG); + MPUI7XX_RESTORE(OMAP_IH1_MIR); + MPUI7XX_RESTORE(OMAP_IH2_0_MIR); + MPUI7XX_RESTORE(OMAP_IH2_1_MIR); } else if (cpu_is_omap15xx()) { MPUI1510_RESTORE(MPUI_CTRL); MPUI1510_RESTORE(MPUI_DSP_BOOT_CONFIG); @@ -462,12 +462,12 @@ static int omap_pm_read_proc( ULPD_SAVE(ULPD_POWER_CTRL); if (cpu_is_omap7xx()) { - MPUI730_SAVE(MPUI_CTRL); - MPUI730_SAVE(MPUI_DSP_STATUS); - MPUI730_SAVE(MPUI_DSP_BOOT_CONFIG); - MPUI730_SAVE(MPUI_DSP_API_CONFIG); - MPUI730_SAVE(EMIFF_SDRAM_CONFIG); - MPUI730_SAVE(EMIFS_CONFIG); + MPUI7XX_SAVE(MPUI_CTRL); + MPUI7XX_SAVE(MPUI_DSP_STATUS); + MPUI7XX_SAVE(MPUI_DSP_BOOT_CONFIG); + MPUI7XX_SAVE(MPUI_DSP_API_CONFIG); + MPUI7XX_SAVE(EMIFF_SDRAM_CONFIG); + MPUI7XX_SAVE(EMIFS_CONFIG); } else if (cpu_is_omap15xx()) { MPUI1510_SAVE(MPUI_CTRL); MPUI1510_SAVE(MPUI_DSP_STATUS); @@ -519,18 +519,18 @@ static int omap_pm_read_proc( if (cpu_is_omap7xx()) { my_buffer_offset += sprintf(my_base + my_buffer_offset, - "MPUI730_CTRL_REG 0x%-8x \n" - "MPUI730_DSP_STATUS_REG: 0x%-8x \n" - "MPUI730_DSP_BOOT_CONFIG_REG: 0x%-8x \n" - "MPUI730_DSP_API_CONFIG_REG: 0x%-8x \n" - "MPUI730_SDRAM_CONFIG_REG: 0x%-8x \n" - "MPUI730_EMIFS_CONFIG_REG: 0x%-8x \n", - MPUI730_SHOW(MPUI_CTRL), - MPUI730_SHOW(MPUI_DSP_STATUS), - MPUI730_SHOW(MPUI_DSP_BOOT_CONFIG), - MPUI730_SHOW(MPUI_DSP_API_CONFIG), - MPUI730_SHOW(EMIFF_SDRAM_CONFIG), - MPUI730_SHOW(EMIFS_CONFIG)); + "MPUI7XX_CTRL_REG 0x%-8x \n" + "MPUI7XX_DSP_STATUS_REG: 0x%-8x \n" + "MPUI7XX_DSP_BOOT_CONFIG_REG: 0x%-8x \n" + "MPUI7XX_DSP_API_CONFIG_REG: 0x%-8x \n" + "MPUI7XX_SDRAM_CONFIG_REG: 0x%-8x \n" + "MPUI7XX_EMIFS_CONFIG_REG: 0x%-8x \n", + MPUI7XX_SHOW(MPUI_CTRL), + MPUI7XX_SHOW(MPUI_DSP_STATUS), + MPUI7XX_SHOW(MPUI_DSP_BOOT_CONFIG), + MPUI7XX_SHOW(MPUI_DSP_API_CONFIG), + MPUI7XX_SHOW(EMIFF_SDRAM_CONFIG), + MPUI7XX_SHOW(EMIFS_CONFIG)); } else if (cpu_is_omap15xx()) { my_buffer_offset += sprintf(my_base + my_buffer_offset, "MPUI1510_CTRL_REG 0x%-8x \n" @@ -669,8 +669,8 @@ static int __init omap_pm_init(void) * memory the MPU can see when it wakes up. */ if (cpu_is_omap7xx()) { - omap_sram_suspend = omap_sram_push(omap730_cpu_suspend, - omap730_cpu_suspend_sz); + omap_sram_suspend = omap_sram_push(omap7xx_cpu_suspend, + omap7xx_cpu_suspend_sz); } else if (cpu_is_omap15xx()) { omap_sram_suspend = omap_sram_push(omap1510_cpu_suspend, omap1510_cpu_suspend_sz); @@ -701,7 +701,7 @@ static int __init omap_pm_init(void) /* Configure IDLECT3 */ if (cpu_is_omap7xx()) - omap_writel(OMAP730_IDLECT3_VAL, OMAP730_IDLECT3); + omap_writel(OMAP7XX_IDLECT3_VAL, OMAP7XX_IDLECT3); else if (cpu_is_omap16xx()) omap_writel(OMAP1610_IDLECT3_VAL, OMAP1610_IDLECT3); diff --git a/arch/arm/mach-omap1/pm.h b/arch/arm/mach-omap1/pm.h index c4f05bdcf8a..0f20aedd63f 100644 --- a/arch/arm/mach-omap1/pm.h +++ b/arch/arm/mach-omap1/pm.h @@ -98,11 +98,11 @@ #define OMAP1610_IDLECT3 0xfffece24 #define OMAP1610_IDLE_LOOP_REQUEST 0x0400 -#define OMAP730_IDLECT1_SLEEP_VAL 0x16c7 -#define OMAP730_IDLECT2_SLEEP_VAL 0x09c7 -#define OMAP730_IDLECT3_VAL 0x3f -#define OMAP730_IDLECT3 0xfffece24 -#define OMAP730_IDLE_LOOP_REQUEST 0x0C00 +#define OMAP7XX_IDLECT1_SLEEP_VAL 0x16c7 +#define OMAP7XX_IDLECT2_SLEEP_VAL 0x09c7 +#define OMAP7XX_IDLECT3_VAL 0x3f +#define OMAP7XX_IDLECT3 0xfffece24 +#define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00 #if !defined(CONFIG_ARCH_OMAP730) && \ !defined(CONFIG_ARCH_OMAP15XX) && \ @@ -122,17 +122,17 @@ extern void allow_idle_sleep(void); extern void omap1_pm_idle(void); extern void omap1_pm_suspend(void); -extern void omap730_cpu_suspend(unsigned short, unsigned short); +extern void omap7xx_cpu_suspend(unsigned short, unsigned short); extern void omap1510_cpu_suspend(unsigned short, unsigned short); extern void omap1610_cpu_suspend(unsigned short, unsigned short); -extern void omap730_idle_loop_suspend(void); +extern void omap7xx_idle_loop_suspend(void); extern void omap1510_idle_loop_suspend(void); extern void omap1610_idle_loop_suspend(void); -extern unsigned int omap730_cpu_suspend_sz; +extern unsigned int omap7xx_cpu_suspend_sz; extern unsigned int omap1510_cpu_suspend_sz; extern unsigned int omap1610_cpu_suspend_sz; -extern unsigned int omap730_idle_loop_suspend_sz; +extern unsigned int omap7xx_idle_loop_suspend_sz; extern unsigned int omap1510_idle_loop_suspend_sz; extern unsigned int omap1610_idle_loop_suspend_sz; @@ -155,9 +155,9 @@ extern void omap_serial_wake_trigger(int enable); #define ULPD_RESTORE(x) omap_writew((ulpd_sleep_save[ULPD_SLEEP_SAVE_##x]), (x)) #define ULPD_SHOW(x) ulpd_sleep_save[ULPD_SLEEP_SAVE_##x] -#define MPUI730_SAVE(x) mpui730_sleep_save[MPUI730_SLEEP_SAVE_##x] = omap_readl(x) -#define MPUI730_RESTORE(x) omap_writel((mpui730_sleep_save[MPUI730_SLEEP_SAVE_##x]), (x)) -#define MPUI730_SHOW(x) mpui730_sleep_save[MPUI730_SLEEP_SAVE_##x] +#define MPUI7XX_SAVE(x) mpui7xx_sleep_save[MPUI7XX_SLEEP_SAVE_##x] = omap_readl(x) +#define MPUI7XX_RESTORE(x) omap_writel((mpui7xx_sleep_save[MPUI7XX_SLEEP_SAVE_##x]), (x)) +#define MPUI7XX_SHOW(x) mpui7xx_sleep_save[MPUI7XX_SLEEP_SAVE_##x] #define MPUI1510_SAVE(x) mpui1510_sleep_save[MPUI1510_SLEEP_SAVE_##x] = omap_readl(x) #define MPUI1510_RESTORE(x) omap_writel((mpui1510_sleep_save[MPUI1510_SLEEP_SAVE_##x]), (x)) @@ -232,24 +232,24 @@ enum mpui1510_save_state { #endif }; -enum mpui730_save_state { - MPUI730_SLEEP_SAVE_START = 0, +enum mpui7xx_save_state { + MPUI7XX_SLEEP_SAVE_START = 0, /* * MPUI registers 32 bits */ - MPUI730_SLEEP_SAVE_MPUI_CTRL, - MPUI730_SLEEP_SAVE_MPUI_DSP_BOOT_CONFIG, - MPUI730_SLEEP_SAVE_MPUI_DSP_API_CONFIG, - MPUI730_SLEEP_SAVE_MPUI_DSP_STATUS, - MPUI730_SLEEP_SAVE_EMIFF_SDRAM_CONFIG, - MPUI730_SLEEP_SAVE_EMIFS_CONFIG, - MPUI730_SLEEP_SAVE_OMAP_IH1_MIR, - MPUI730_SLEEP_SAVE_OMAP_IH2_0_MIR, - MPUI730_SLEEP_SAVE_OMAP_IH2_1_MIR, -#if defined(CONFIG_ARCH_OMAP730) - MPUI730_SLEEP_SAVE_SIZE + MPUI7XX_SLEEP_SAVE_MPUI_CTRL, + MPUI7XX_SLEEP_SAVE_MPUI_DSP_BOOT_CONFIG, + MPUI7XX_SLEEP_SAVE_MPUI_DSP_API_CONFIG, + MPUI7XX_SLEEP_SAVE_MPUI_DSP_STATUS, + MPUI7XX_SLEEP_SAVE_EMIFF_SDRAM_CONFIG, + MPUI7XX_SLEEP_SAVE_EMIFS_CONFIG, + MPUI7XX_SLEEP_SAVE_OMAP_IH1_MIR, + MPUI7XX_SLEEP_SAVE_OMAP_IH2_0_MIR, + MPUI7XX_SLEEP_SAVE_OMAP_IH2_1_MIR, +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) + MPUI7XX_SLEEP_SAVE_SIZE #else - MPUI730_SLEEP_SAVE_SIZE = 0 + MPUI7XX_SLEEP_SAVE_SIZE = 0 #endif }; diff --git a/arch/arm/mach-omap1/sleep.S b/arch/arm/mach-omap1/sleep.S index 22e8568339b..ef771ce8b03 100644 --- a/arch/arm/mach-omap1/sleep.S +++ b/arch/arm/mach-omap1/sleep.S @@ -1,7 +1,7 @@ /* * linux/arch/arm/mach-omap1/sleep.S * - * Low-level OMAP730/1510/1610 sleep/wakeUp support + * Low-level OMAP7XX/1510/1610 sleep/wakeUp support * * Initial SA1110 code: * Copyright (c) 2001 Cliff Brake @@ -57,8 +57,8 @@ * */ -#if defined(CONFIG_ARCH_OMAP730) -ENTRY(omap730_cpu_suspend) +#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) +ENTRY(omap7xx_cpu_suspend) @ save registers on stack stmfd sp!, {r0 - r12, lr} @@ -91,13 +91,13 @@ ENTRY(omap730_cpu_suspend) @ turn off clock domains @ do not disable PERCK (0x04) - mov r5, #OMAP730_IDLECT2_SLEEP_VAL & 0xff - orr r5, r5, #OMAP730_IDLECT2_SLEEP_VAL & 0xff00 + mov r5, #OMAP7XX_IDLECT2_SLEEP_VAL & 0xff + orr r5, r5, #OMAP7XX_IDLECT2_SLEEP_VAL & 0xff00 strh r5, [r4, #ARM_IDLECT2_ASM_OFFSET & 0xff] @ request ARM idle - mov r3, #OMAP730_IDLECT1_SLEEP_VAL & 0xff - orr r3, r3, #OMAP730_IDLECT1_SLEEP_VAL & 0xff00 + mov r3, #OMAP7XX_IDLECT1_SLEEP_VAL & 0xff + orr r3, r3, #OMAP7XX_IDLECT1_SLEEP_VAL & 0xff00 strh r3, [r4, #ARM_IDLECT1_ASM_OFFSET & 0xff] @ disable instruction cache @@ -113,7 +113,7 @@ ENTRY(omap730_cpu_suspend) mov r2, #0 mcr p15, 0, r2, c7, c0, 4 @ wait for interrupt /* - * omap730_cpu_suspend()'s resume point. + * omap7xx_cpu_suspend()'s resume point. * * It will just start executing here, so we'll restore stuff from the * stack. @@ -132,9 +132,9 @@ ENTRY(omap730_cpu_suspend) @ restore regs and return ldmfd sp!, {r0 - r12, pc} -ENTRY(omap730_cpu_suspend_sz) - .word . - omap730_cpu_suspend -#endif /* CONFIG_ARCH_OMAP730 */ +ENTRY(omap7xx_cpu_suspend_sz) + .word . - omap7xx_cpu_suspend +#endif /* CONFIG_ARCH_OMAP730 || CONFIG_ARCH_OMAP850 */ #ifdef CONFIG_ARCH_OMAP15XX ENTRY(omap1510_cpu_suspend) diff --git a/arch/arm/plat-omap/devices.c b/arch/arm/plat-omap/devices.c index a64b692a1bf..d2f54753b01 100644 --- a/arch/arm/plat-omap/devices.c +++ b/arch/arm/plat-omap/devices.c @@ -113,17 +113,17 @@ static void omap_init_kp(void) omap_cfg_reg(E19_1610_KBR4); omap_cfg_reg(N19_1610_KBR5); } else if (machine_is_omap_perseus2() || machine_is_omap_fsample()) { - omap_cfg_reg(E2_730_KBR0); - omap_cfg_reg(J7_730_KBR1); - omap_cfg_reg(E1_730_KBR2); - omap_cfg_reg(F3_730_KBR3); - omap_cfg_reg(D2_730_KBR4); - - omap_cfg_reg(C2_730_KBC0); - omap_cfg_reg(D3_730_KBC1); - omap_cfg_reg(E4_730_KBC2); - omap_cfg_reg(F4_730_KBC3); - omap_cfg_reg(E3_730_KBC4); + omap_cfg_reg(E2_7XX_KBR0); + omap_cfg_reg(J7_7XX_KBR1); + omap_cfg_reg(E1_7XX_KBR2); + omap_cfg_reg(F3_7XX_KBR3); + omap_cfg_reg(D2_7XX_KBR4); + + omap_cfg_reg(C2_7XX_KBC0); + omap_cfg_reg(D3_7XX_KBC1); + omap_cfg_reg(E4_7XX_KBC2); + omap_cfg_reg(F4_7XX_KBC3); + omap_cfg_reg(E3_7XX_KBC4); } else if (machine_is_omap_h4()) { omap_cfg_reg(T19_24XX_KBR0); omap_cfg_reg(R19_24XX_KBR1); diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c index 22f6e689f5c..b0c73613a4e 100644 --- a/arch/arm/plat-omap/gpio.c +++ b/arch/arm/plat-omap/gpio.c @@ -68,20 +68,20 @@ #define OMAP1610_GPIO_SET_DATAOUT 0x00f0 /* - * OMAP730 specific GPIO registers + * OMAP7XX specific GPIO registers */ -#define OMAP730_GPIO1_BASE OMAP1_IO_ADDRESS(0xfffbc000) -#define OMAP730_GPIO2_BASE OMAP1_IO_ADDRESS(0xfffbc800) -#define OMAP730_GPIO3_BASE OMAP1_IO_ADDRESS(0xfffbd000) -#define OMAP730_GPIO4_BASE OMAP1_IO_ADDRESS(0xfffbd800) -#define OMAP730_GPIO5_BASE OMAP1_IO_ADDRESS(0xfffbe000) -#define OMAP730_GPIO6_BASE OMAP1_IO_ADDRESS(0xfffbe800) -#define OMAP730_GPIO_DATA_INPUT 0x00 -#define OMAP730_GPIO_DATA_OUTPUT 0x04 -#define OMAP730_GPIO_DIR_CONTROL 0x08 -#define OMAP730_GPIO_INT_CONTROL 0x0c -#define OMAP730_GPIO_INT_MASK 0x10 -#define OMAP730_GPIO_INT_STATUS 0x14 +#define OMAP7XX_GPIO1_BASE OMAP1_IO_ADDRESS(0xfffbc000) +#define OMAP7XX_GPIO2_BASE OMAP1_IO_ADDRESS(0xfffbc800) +#define OMAP7XX_GPIO3_BASE OMAP1_IO_ADDRESS(0xfffbd000) +#define OMAP7XX_GPIO4_BASE OMAP1_IO_ADDRESS(0xfffbd800) +#define OMAP7XX_GPIO5_BASE OMAP1_IO_ADDRESS(0xfffbe000) +#define OMAP7XX_GPIO6_BASE OMAP1_IO_ADDRESS(0xfffbe800) +#define OMAP7XX_GPIO_DATA_INPUT 0x00 +#define OMAP7XX_GPIO_DATA_OUTPUT 0x04 +#define OMAP7XX_GPIO_DIR_CONTROL 0x08 +#define OMAP7XX_GPIO_INT_CONTROL 0x0c +#define OMAP7XX_GPIO_INT_MASK 0x10 +#define OMAP7XX_GPIO_INT_STATUS 0x14 #define OMAP1_MPUIO_VBASE OMAP1_IO_ADDRESS(OMAP1_MPUIO_BASE) @@ -199,7 +199,7 @@ struct gpio_bank { #define METHOD_MPUIO 0 #define METHOD_GPIO_1510 1 #define METHOD_GPIO_1610 2 -#define METHOD_GPIO_730 3 +#define METHOD_GPIO_7XX 3 #define METHOD_GPIO_24XX 5 #ifdef CONFIG_ARCH_OMAP16XX @@ -220,14 +220,14 @@ static struct gpio_bank gpio_bank_1510[2] = { #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) -static struct gpio_bank gpio_bank_730[7] = { +static struct gpio_bank gpio_bank_7xx[7] = { { OMAP1_MPUIO_VBASE, INT_7XX_MPUIO, IH_MPUIO_BASE, METHOD_MPUIO }, - { OMAP730_GPIO1_BASE, INT_7XX_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_730 }, - { OMAP730_GPIO2_BASE, INT_7XX_GPIO_BANK2, IH_GPIO_BASE + 32, METHOD_GPIO_730 }, - { OMAP730_GPIO3_BASE, INT_7XX_GPIO_BANK3, IH_GPIO_BASE + 64, METHOD_GPIO_730 }, - { OMAP730_GPIO4_BASE, INT_7XX_GPIO_BANK4, IH_GPIO_BASE + 96, METHOD_GPIO_730 }, - { OMAP730_GPIO5_BASE, INT_7XX_GPIO_BANK5, IH_GPIO_BASE + 128, METHOD_GPIO_730 }, - { OMAP730_GPIO6_BASE, INT_7XX_GPIO_BANK6, IH_GPIO_BASE + 160, METHOD_GPIO_730 }, + { OMAP7XX_GPIO1_BASE, INT_7XX_GPIO_BANK1, IH_GPIO_BASE, METHOD_GPIO_7XX }, + { OMAP7XX_GPIO2_BASE, INT_7XX_GPIO_BANK2, IH_GPIO_BASE + 32, METHOD_GPIO_7XX }, + { OMAP7XX_GPIO3_BASE, INT_7XX_GPIO_BANK3, IH_GPIO_BASE + 64, METHOD_GPIO_7XX }, + { OMAP7XX_GPIO4_BASE, INT_7XX_GPIO_BANK4, IH_GPIO_BASE + 96, METHOD_GPIO_7XX }, + { OMAP7XX_GPIO5_BASE, INT_7XX_GPIO_BANK5, IH_GPIO_BASE + 128, METHOD_GPIO_7XX }, + { OMAP7XX_GPIO6_BASE, INT_7XX_GPIO_BANK6, IH_GPIO_BASE + 160, METHOD_GPIO_7XX }, }; #endif @@ -373,8 +373,8 @@ static void _set_gpio_direction(struct gpio_bank *bank, int gpio, int is_input) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_DIR_CONTROL; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_DIR_CONTROL; break; #endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) @@ -435,8 +435,8 @@ static void _set_gpio_dataout(struct gpio_bank *bank, int gpio, int enable) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_DATA_OUTPUT; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_DATA_OUTPUT; l = __raw_readl(reg); if (enable) l |= 1 << gpio; @@ -493,8 +493,8 @@ static int _get_gpio_datain(struct gpio_bank *bank, int gpio) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_DATA_INPUT; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_DATA_INPUT; break; #endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) @@ -539,8 +539,8 @@ static int _get_gpio_dataout(struct gpio_bank *bank, int gpio) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_DATA_OUTPUT; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_DATA_OUTPUT; break; #endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) || \ @@ -743,8 +743,8 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_INT_CONTROL; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_INT_CONTROL; l = __raw_readl(reg); if (trigger & IRQ_TYPE_EDGE_RISING) l |= 1 << gpio; @@ -831,8 +831,8 @@ static void _clear_gpio_irqbank(struct gpio_bank *bank, int gpio_mask) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_INT_STATUS; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_INT_STATUS; break; #endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) @@ -900,8 +900,8 @@ static u32 _get_gpio_irqbank_mask(struct gpio_bank *bank) break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_INT_MASK; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_INT_MASK; mask = 0xffffffff; inv = 1; break; @@ -966,8 +966,8 @@ static void _enable_gpio_irqbank(struct gpio_bank *bank, int gpio_mask, int enab break; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - case METHOD_GPIO_730: - reg += OMAP730_GPIO_INT_MASK; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_INT_MASK; l = __raw_readl(reg); if (enable) l &= ~(gpio_mask); @@ -1161,8 +1161,8 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc) isr_reg = bank->base + OMAP1610_GPIO_IRQSTATUS1; #endif #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) - if (bank->method == METHOD_GPIO_730) - isr_reg = bank->base + OMAP730_GPIO_INT_STATUS; + if (bank->method == METHOD_GPIO_7XX) + isr_reg = bank->base + OMAP7XX_GPIO_INT_STATUS; #endif #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) if (bank->method == METHOD_GPIO_24XX) @@ -1431,8 +1431,8 @@ static int gpio_is_input(struct gpio_bank *bank, int mask) case METHOD_GPIO_1610: reg += OMAP1610_GPIO_DIRECTION; break; - case METHOD_GPIO_730: - reg += OMAP730_GPIO_DIR_CONTROL; + case METHOD_GPIO_7XX: + reg += OMAP7XX_GPIO_DIR_CONTROL; break; case METHOD_GPIO_24XX: reg += OMAP24XX_GPIO_OE; @@ -1603,7 +1603,7 @@ static int __init _omap_gpio_init(void) if (cpu_is_omap7xx()) { printk(KERN_INFO "OMAP7XX GPIO hardware\n"); gpio_bank_count = 7; - gpio_bank = gpio_bank_730; + gpio_bank = gpio_bank_7xx; } #endif #ifdef CONFIG_ARCH_OMAP24XX @@ -1664,11 +1664,11 @@ static int __init _omap_gpio_init(void) __raw_writew(0xffff, bank->base + OMAP1610_GPIO_IRQSTATUS1); __raw_writew(0x0014, bank->base + OMAP1610_GPIO_SYSCONFIG); } - if (cpu_is_omap7xx() && bank->method == METHOD_GPIO_730) { - __raw_writel(0xffffffff, bank->base + OMAP730_GPIO_INT_MASK); - __raw_writel(0x00000000, bank->base + OMAP730_GPIO_INT_STATUS); + if (cpu_is_omap7xx() && bank->method == METHOD_GPIO_7XX) { + __raw_writel(0xffffffff, bank->base + OMAP7XX_GPIO_INT_MASK); + __raw_writel(0x00000000, bank->base + OMAP7XX_GPIO_INT_STATUS); - gpio_count = 32; /* 730 has 32-bit GPIOs */ + gpio_count = 32; /* 7xx has 32-bit GPIOs */ } #if defined(CONFIG_ARCH_OMAP24XX) || defined(CONFIG_ARCH_OMAP34XX) || \ diff --git a/arch/arm/plat-omap/include/mach/mcbsp.h b/arch/arm/plat-omap/include/mach/mcbsp.h index 0b476b909aa..7e9cae3e3d1 100644 --- a/arch/arm/plat-omap/include/mach/mcbsp.h +++ b/arch/arm/plat-omap/include/mach/mcbsp.h @@ -30,8 +30,8 @@ #include #include -#define OMAP730_MCBSP1_BASE 0xfffb1000 -#define OMAP730_MCBSP2_BASE 0xfffb1800 +#define OMAP7XX_MCBSP1_BASE 0xfffb1000 +#define OMAP7XX_MCBSP2_BASE 0xfffb1800 #define OMAP1510_MCBSP1_BASE 0xe1011800 #define OMAP1510_MCBSP2_BASE 0xfffb1000 diff --git a/arch/arm/plat-omap/include/mach/mux.h b/arch/arm/plat-omap/include/mach/mux.h index 66ae302f0c0..f3c1d8a9045 100644 --- a/arch/arm/plat-omap/include/mach/mux.h +++ b/arch/arm/plat-omap/include/mach/mux.h @@ -51,12 +51,12 @@ .pu_pd_reg = PU_PD_SEL_##reg, \ .pu_pd_val = status, -#define MUX_REG_730(reg, mode_offset, mode) .mux_reg_name = "OMAP7XX_IO_CONF_"#reg, \ +#define MUX_REG_7XX(reg, mode_offset, mode) .mux_reg_name = "OMAP7XX_IO_CONF_"#reg, \ .mux_reg = OMAP7XX_IO_CONF_##reg, \ .mask_offset = mode_offset, \ .mask = mode, -#define PULL_REG_730(reg, bit, status) .pull_name = "OMAP7XX_IO_CONF_"#reg, \ +#define PULL_REG_7XX(reg, bit, status) .pull_name = "OMAP7XX_IO_CONF_"#reg, \ .pull_reg = OMAP7XX_IO_CONF_##reg, \ .pull_bit = bit, \ .pull_val = status, @@ -74,12 +74,12 @@ #define PU_PD_REG(reg, status) .pu_pd_reg = PU_PD_SEL_##reg, \ .pu_pd_val = status, -#define MUX_REG_730(reg, mode_offset, mode) \ +#define MUX_REG_7XX(reg, mode_offset, mode) \ .mux_reg = OMAP7XX_IO_CONF_##reg, \ .mask_offset = mode_offset, \ .mask = mode, -#define PULL_REG_730(reg, bit, status) .pull_reg = OMAP7XX_IO_CONF_##reg, \ +#define PULL_REG_7XX(reg, bit, status) .pull_reg = OMAP7XX_IO_CONF_##reg, \ .pull_bit = bit, \ .pull_val = status, @@ -104,13 +104,13 @@ * - for pull-up/down, only has one enable bit which is is in the same register * as mux config */ -#define MUX_CFG_730(desc, mux_reg, mode_offset, mode, \ +#define MUX_CFG_7XX(desc, mux_reg, mode_offset, mode, \ pull_bit, pull_status, debug_status)\ { \ .name = desc, \ .debug = debug_status, \ - MUX_REG_730(mux_reg, mode_offset, mode) \ - PULL_REG_730(mux_reg, pull_bit, pull_status) \ + MUX_REG_7XX(mux_reg, mode_offset, mode) \ + PULL_REG_7XX(mux_reg, pull_bit, pull_status) \ PU_PD_REG(NA, 0) \ }, @@ -202,23 +202,23 @@ struct pin_config { }; -enum omap730_index { +enum omap7xx_index { /* OMAP 730 keyboard */ - E2_730_KBR0, - J7_730_KBR1, - E1_730_KBR2, - F3_730_KBR3, - D2_730_KBR4, - C2_730_KBC0, - D3_730_KBC1, - E4_730_KBC2, - F4_730_KBC3, - E3_730_KBC4, + E2_7XX_KBR0, + J7_7XX_KBR1, + E1_7XX_KBR2, + F3_7XX_KBR3, + D2_7XX_KBR4, + C2_7XX_KBC0, + D3_7XX_KBC1, + E4_7XX_KBC2, + F4_7XX_KBC3, + E3_7XX_KBC4, /* USB */ - AA17_730_USB_DM, - W16_730_USB_PU_EN, - W17_730_USB_VBUSI, + AA17_7XX_USB_DM, + W16_7XX_USB_PU_EN, + W17_7XX_USB_VBUSI, }; enum omap1xxx_index { -- cgit v1.2.3-70-g09d2 From ab985ff471048479b475f973358ccc6af8e42bc4 Mon Sep 17 00:00:00 2001 From: Angelo Arrifano Date: Fri, 4 Sep 2009 23:41:49 +0100 Subject: OMAP7XX: Clocks: Add ck_ref and armxor These clocks are required for booting. Signed-off-by: Angelo Arrifano Signed-off-by: Alistair Buxton Reviewed-by: Zebediah C. McClure --- arch/arm/mach-omap1/clock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index d2b00a56393..5f77b8355b4 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -75,7 +75,7 @@ struct omap_clk { static struct omap_clk omap_clks[] = { /* non-ULPD clocks */ - CLK(NULL, "ck_ref", &ck_ref, CK_16XX | CK_1510 | CK_310), + CLK(NULL, "ck_ref", &ck_ref, CK_16XX | CK_1510 | CK_310 | CK_7XX), CLK(NULL, "ck_dpll1", &ck_dpll1, CK_16XX | CK_1510 | CK_310), /* CK_GEN1 clocks */ CLK(NULL, "ck_dpll1out", &ck_dpll1out.clk, CK_16XX), @@ -83,7 +83,7 @@ static struct omap_clk omap_clks[] = { CLK(NULL, "arm_ck", &arm_ck, CK_16XX | CK_1510 | CK_310), CLK(NULL, "armper_ck", &armper_ck.clk, CK_16XX | CK_1510 | CK_310), CLK(NULL, "arm_gpio_ck", &arm_gpio_ck, CK_1510 | CK_310), - CLK(NULL, "armxor_ck", &armxor_ck.clk, CK_16XX | CK_1510 | CK_310), + CLK(NULL, "armxor_ck", &armxor_ck.clk, CK_16XX | CK_1510 | CK_310 | CK_7XX), CLK(NULL, "armtim_ck", &armtim_ck.clk, CK_16XX | CK_1510 | CK_310), CLK("omap_wdt", "fck", &armwdt_ck.clk, CK_16XX | CK_1510 | CK_310), CLK("omap_wdt", "ick", &armper_ck.clk, CK_16XX), -- cgit v1.2.3-70-g09d2 From 1f73b4de93e06d18c28cb282761c8507bc476489 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Fri, 18 Sep 2009 20:53:04 +0100 Subject: OMAP850: PM: Add an ARCH_OMAP850 check This just makes the same warning be printed on omap850 and omap730. Signed-off-by: Alistair Buxton --- arch/arm/mach-omap1/pm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm/mach-omap1/pm.h b/arch/arm/mach-omap1/pm.h index 0f20aedd63f..56a647986ae 100644 --- a/arch/arm/mach-omap1/pm.h +++ b/arch/arm/mach-omap1/pm.h @@ -105,6 +105,7 @@ #define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00 #if !defined(CONFIG_ARCH_OMAP730) && \ + !defined(CONFIG_ARCH_OMAP850) && \ !defined(CONFIG_ARCH_OMAP15XX) && \ !defined(CONFIG_ARCH_OMAP16XX) #warning "Power management for this processor not implemented yet" -- cgit v1.2.3-70-g09d2 From f8631e7bba34d46d6ccea4cd90f7a0482770ff70 Mon Sep 17 00:00:00 2001 From: Alistair Buxton Date: Tue, 22 Sep 2009 10:05:30 +0100 Subject: OMAP850: Fix zImage booting This adds the OMAP850 JTAG ID to the IDs checked by OMAP uncompress.h putc. Without this putc hangs up trying to check the uarts and zImage crashes. Signed-off-by: Alistair Buxton --- arch/arm/plat-omap/include/mach/uncompress.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/plat-omap/include/mach/uncompress.h b/arch/arm/plat-omap/include/mach/uncompress.h index 0814c5f210c..ddf7b88dec4 100644 --- a/arch/arm/plat-omap/include/mach/uncompress.h +++ b/arch/arm/plat-omap/include/mach/uncompress.h @@ -25,6 +25,7 @@ unsigned int system_rev; #define UART_OMAP_MDR1 0x08 /* mode definition register */ #define OMAP_ID_730 0x355F +#define OMAP_ID_850 0x362C #define ID_MASK 0x7fff #define check_port(base, shift) ((base[UART_OMAP_MDR1 << shift] & 7) == 0) #define omap_get_id() ((*(volatile unsigned int *)(0xfffed404)) >> 12) & ID_MASK @@ -53,7 +54,7 @@ static void putc(int c) /* MMU is not on, so cpu_is_omapXXXX() won't work here */ unsigned int omap_id = omap_get_id(); - if (omap_id == OMAP_ID_730) + if (omap_id == OMAP_ID_730 || omap_id == OMAP_ID_850) shift = 0; if (check_port(uart, shift)) -- cgit v1.2.3-70-g09d2 From 170a0bc3808909d8ea0f3f9c725c6565efe7f9c4 Mon Sep 17 00:00:00 2001 From: John Kacur Date: Wed, 7 Oct 2009 20:19:32 +0200 Subject: x86, cpuid: Remove the bkl from cpuid_open() Most of the variables are local to the function. It IS possible that for struct cpuinfo_x86 *c c could point to the same area. However, this is used read only. Signed-off-by: John Kacur LKML-Reference: Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpuid.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index b07af886124..ef6928418c8 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -118,8 +118,6 @@ static int cpuid_open(struct inode *inode, struct file *file) struct cpuinfo_x86 *c; int ret = 0; - lock_kernel(); - cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { ret = -ENXIO; /* No such CPU */ @@ -129,7 +127,6 @@ static int cpuid_open(struct inode *inode, struct file *file) if (c->cpuid_level < 0) ret = -EIO; /* CPUID not supported */ out: - unlock_kernel(); return ret; } -- cgit v1.2.3-70-g09d2 From 5a943617ef52e9f79cd7cf437aad8870be27aabb Mon Sep 17 00:00:00 2001 From: John Kacur Date: Thu, 8 Oct 2009 17:20:15 +0200 Subject: x86, cpuid: Simplify the code in cpuid_open Peter picked up my patch for tip/x86/cpu that removes the bkl in cpuid_open. Ingo subsequently merged that into tip/master. This patch folds back in tglx's 55968ede164ae523692f00717f50cd926f1382a0 to my patch that removed the bkl. This simplifies the code, and makes it consistent with the changes to kill the bkl in msr.c as well. Originally-by: Thomas Gleixner Signed-off-by: John Kacur Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpuid.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index ef6928418c8..48e8e6558b2 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -116,18 +116,16 @@ static int cpuid_open(struct inode *inode, struct file *file) { unsigned int cpu; struct cpuinfo_x86 *c; - int ret = 0; cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { - ret = -ENXIO; /* No such CPU */ - goto out; - } + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + return -ENXIO; /* No such CPU */ + c = &cpu_data(cpu); if (c->cpuid_level < 0) - ret = -EIO; /* CPUID not supported */ -out: - return ret; + return -EIO; /* CPUID not supported */ + + return 0; } /* -- cgit v1.2.3-70-g09d2 From 04a705df47d1ea27ca2b066f24b1951c51792d0d Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 6 Oct 2009 16:42:08 +0200 Subject: perf_events: Check for filters on fixed counter events Intel fixed counters do not support all the filters possible with a generic counter. Thus, if a fixed counter event is passed but with certain filters set, then the fixed_mode_idx() function must fail and the event must be measured in a generic counter instead. Reject filters are: inv, edge, cnt-mask. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra LKML-Reference: <1254840129-6198-2-git-send-email-eranian@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event.h | 13 ++++++++++++- arch/x86/kernel/cpu/perf_event.c | 6 ++++++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index ad7ce3fd506..8d9f8548a87 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -28,9 +28,20 @@ */ #define ARCH_PERFMON_EVENT_MASK 0xffff +/* + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ +#define ARCH_PERFMON_EVENT_FILTER_MASK 0xff840000 + #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) -#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \ (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX)) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b5801c31184..1d16bd69551 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1349,6 +1349,12 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) if (!x86_pmu.num_events_fixed) return -1; + /* + * fixed counters do not take all possible filters + */ + if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK) + return -1; + if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS))) return X86_PMC_IDX_FIXED_INSTRUCTIONS; if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES))) -- cgit v1.2.3-70-g09d2 From b690081d4d3f6a23541493f1682835c3cd5c54a1 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 6 Oct 2009 16:42:09 +0200 Subject: perf_events: Add event constraints support for Intel processors On some Intel processors, not all events can be measured in all counters. Some events can only be measured in one particular counter, for instance. Assigning an event to the wrong counter does not crash the machine but this yields bogus counts, i.e., silent error. This patch changes the event to counter assignment logic to take into account event constraints for Intel P6, Core and Nehalem processors. There is no contraints on Intel Atom. There are constraints on Intel Yonah (Core Duo) but they are not provided in this patch given that this processor is not yet supported by perf_events. As a result of the constraints, it is possible for some event groups to never actually be loaded onto the PMU if they contain two events which can only be measured on a single counter. That situation can be detected with the scaling information extracted with read(). Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra LKML-Reference: <1254840129-6198-3-git-send-email-eranian@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 109 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 105 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1d16bd69551..9c758548a0e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -77,6 +77,18 @@ struct cpu_hw_events { struct debug_store *ds; }; +struct event_constraint { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int code; +}; + +#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) } +#define EVENT_CONSTRAINT_END { .code = 0, .idxmsk[0] = 0 } + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->idxmsk[0]; (e)++) + + /* * struct x86_pmu - generic x86 pmu */ @@ -102,6 +114,7 @@ struct x86_pmu { u64 intel_ctrl; void (*enable_bts)(u64 config); void (*disable_bts)(void); + int (*get_event_idx)(struct hw_perf_event *hwc); }; static struct x86_pmu x86_pmu __read_mostly; @@ -110,6 +123,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; +static const struct event_constraint *event_constraint; + /* * Not sure about some of these */ @@ -155,6 +170,16 @@ static u64 p6_pmu_raw_event(u64 hw_event) return hw_event & P6_EVNTSEL_MASK; } +static const struct event_constraint intel_p6_event_constraints[] = +{ + EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ + EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ + EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + EVENT_CONSTRAINT_END +}; /* * Intel PerfMon v3. Used on Core2 and later. @@ -170,6 +195,35 @@ static const u64 intel_perfmon_event_map[] = [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, }; +static const struct event_constraint intel_core_event_constraints[] = +{ + EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ + EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */ + EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ + EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */ + EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */ + EVENT_CONSTRAINT_END +}; + +static const struct event_constraint intel_nehalem_event_constraints[] = +{ + EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ + EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ + EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ + EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */ + EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */ + EVENT_CONSTRAINT(0x4c, 0x3), /* LOAD_HIT_PRE */ + EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ + EVENT_CONSTRAINT(0x52, 0x3), /* L1D_CACHE_PREFETCH_LOCK_FB_HIT */ + EVENT_CONSTRAINT(0x53, 0x3), /* L1D_CACHE_LOCK_FB_HIT */ + EVENT_CONSTRAINT(0xc5, 0x3), /* CACHE_LOCK_CYCLES */ + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -932,6 +986,8 @@ static int __hw_perf_event_init(struct perf_event *event) */ hwc->config = ARCH_PERFMON_EVENTSEL_INT; + hwc->idx = -1; + /* * Count user and OS events unless requested not to. */ @@ -1365,6 +1421,45 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) return -1; } +/* + * generic counter allocator: get next free counter + */ +static int gen_get_event_idx(struct hw_perf_event *hwc) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events); + return idx == x86_pmu.num_events ? -1 : idx; +} + +/* + * intel-specific counter allocator: check event constraints + */ +static int intel_get_event_idx(struct hw_perf_event *hwc) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + const struct event_constraint *event_constraint; + int i, code; + + if (!event_constraint) + goto skip; + + code = hwc->config & 0xff; + + for_each_event_constraint(event_constraint, event_constraint) { + if (code == event_constraint->code) { + for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) { + if (!test_and_set_bit(i, cpuc->used_mask)) + return i; + } + return -1; + } + } +skip: + return gen_get_event_idx(hwc); +} + /* * Find a PMC slot for the freshly enabled / scheduled in event: */ @@ -1402,11 +1497,10 @@ static int x86_pmu_enable(struct perf_event *event) } else { idx = hwc->idx; /* Try to get the previous generic event again */ - if (test_and_set_bit(idx, cpuc->used_mask)) { + if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) { try_generic: - idx = find_first_zero_bit(cpuc->used_mask, - x86_pmu.num_events); - if (idx == x86_pmu.num_events) + idx = x86_pmu.get_event_idx(hwc); + if (idx == -1) return -EAGAIN; set_bit(idx, cpuc->used_mask); @@ -1883,6 +1977,7 @@ static struct x86_pmu p6_pmu = { */ .event_bits = 32, .event_mask = (1ULL << 32) - 1, + .get_event_idx = intel_get_event_idx, }; static struct x86_pmu intel_pmu = { @@ -1906,6 +2001,7 @@ static struct x86_pmu intel_pmu = { .max_period = (1ULL << 31) - 1, .enable_bts = intel_pmu_enable_bts, .disable_bts = intel_pmu_disable_bts, + .get_event_idx = intel_get_event_idx, }; static struct x86_pmu amd_pmu = { @@ -1926,6 +2022,7 @@ static struct x86_pmu amd_pmu = { .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, + .get_event_idx = gen_get_event_idx, }; static int p6_pmu_init(void) @@ -1938,10 +2035,12 @@ static int p6_pmu_init(void) case 7: case 8: case 11: /* Pentium III */ + event_constraint = intel_p6_event_constraints; break; case 9: case 13: /* Pentium M */ + event_constraint = intel_p6_event_constraints; break; default: pr_cont("unsupported p6 CPU model %d ", @@ -2013,12 +2112,14 @@ static int intel_pmu_init(void) sizeof(hw_cache_event_ids)); pr_cont("Core2 events, "); + event_constraint = intel_core_event_constraints; break; default: case 26: memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + event_constraint = intel_nehalem_event_constraints; pr_cont("Nehalem/Corei7 events, "); break; case 28: -- cgit v1.2.3-70-g09d2 From fe9081cc9bdabb0be953a39ad977cea14e35bce5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 8 Oct 2009 11:56:07 +0200 Subject: perf, x86: Add simple group validation Refuse to add events when the group wouldn't fit onto the PMU anymore. Naive implementation. Signed-off-by: Peter Zijlstra Cc: Stephane Eranian LKML-Reference: <1254911461.26976.239.camel@twins> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 90 ++++++++++++++++++++++++++++++---------- 1 file changed, 69 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9c758548a0e..9961d845719 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -114,7 +114,8 @@ struct x86_pmu { u64 intel_ctrl; void (*enable_bts)(u64 config); void (*disable_bts)(void); - int (*get_event_idx)(struct hw_perf_event *hwc); + int (*get_event_idx)(struct cpu_hw_events *cpuc, + struct hw_perf_event *hwc); }; static struct x86_pmu x86_pmu __read_mostly; @@ -523,7 +524,7 @@ static u64 intel_pmu_raw_event(u64 hw_event) #define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL #define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL #define CORE_EVNTSEL_INV_MASK 0x00800000ULL -#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL +#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL #define CORE_EVNTSEL_MASK \ (CORE_EVNTSEL_EVENT_MASK | \ @@ -1390,8 +1391,7 @@ static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx) x86_pmu_enable_event(hwc, idx); } -static int -fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) +static int fixed_mode_idx(struct hw_perf_event *hwc) { unsigned int hw_event; @@ -1424,9 +1424,9 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) /* * generic counter allocator: get next free counter */ -static int gen_get_event_idx(struct hw_perf_event *hwc) +static int +gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events); @@ -1436,16 +1436,16 @@ static int gen_get_event_idx(struct hw_perf_event *hwc) /* * intel-specific counter allocator: check event constraints */ -static int intel_get_event_idx(struct hw_perf_event *hwc) +static int +intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); const struct event_constraint *event_constraint; int i, code; if (!event_constraint) goto skip; - code = hwc->config & 0xff; + code = hwc->config & CORE_EVNTSEL_EVENT_MASK; for_each_event_constraint(event_constraint, event_constraint) { if (code == event_constraint->code) { @@ -1457,26 +1457,22 @@ static int intel_get_event_idx(struct hw_perf_event *hwc) } } skip: - return gen_get_event_idx(hwc); + return gen_get_event_idx(cpuc, hwc); } -/* - * Find a PMC slot for the freshly enabled / scheduled in event: - */ -static int x86_pmu_enable(struct perf_event *event) +static int +x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; int idx; - idx = fixed_mode_idx(event, hwc); + idx = fixed_mode_idx(hwc); if (idx == X86_PMC_IDX_FIXED_BTS) { /* BTS is already occupied. */ if (test_and_set_bit(idx, cpuc->used_mask)) return -EAGAIN; hwc->config_base = 0; - hwc->event_base = 0; + hwc->event_base = 0; hwc->idx = idx; } else if (idx >= 0) { /* @@ -1499,17 +1495,33 @@ static int x86_pmu_enable(struct perf_event *event) /* Try to get the previous generic event again */ if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) { try_generic: - idx = x86_pmu.get_event_idx(hwc); + idx = x86_pmu.get_event_idx(cpuc, hwc); if (idx == -1) return -EAGAIN; set_bit(idx, cpuc->used_mask); hwc->idx = idx; } - hwc->config_base = x86_pmu.eventsel; - hwc->event_base = x86_pmu.perfctr; + hwc->config_base = x86_pmu.eventsel; + hwc->event_base = x86_pmu.perfctr; } + return idx; +} + +/* + * Find a PMC slot for the freshly enabled / scheduled in event: + */ +static int x86_pmu_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx; + + idx = x86_schedule_event(cpuc, hwc); + if (idx < 0) + return idx; + perf_events_lapic_init(); x86_pmu.disable(hwc, idx); @@ -2212,11 +2224,47 @@ static const struct pmu pmu = { .unthrottle = x86_pmu_unthrottle, }; +static int +validate_event(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event fake_event = event->hw; + + if (event->pmu != &pmu) + return 0; + + return x86_schedule_event(cpuc, &fake_event); +} + +static int validate_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct cpu_hw_events fake_pmu; + + memset(&fake_pmu, 0, sizeof(fake_pmu)); + + if (!validate_event(&fake_pmu, leader)) + return -ENOSPC; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (!validate_event(&fake_pmu, sibling)) + return -ENOSPC; + } + + if (!validate_event(&fake_pmu, event)) + return -ENOSPC; + + return 0; +} + const struct pmu *hw_perf_event_init(struct perf_event *event) { int err; err = __hw_perf_event_init(event); + if (!err) { + if (event->group_leader != event) + err = validate_group(event); + } if (err) { if (event->destroy) event->destroy(event); -- cgit v1.2.3-70-g09d2 From f3834b9ef68067199486740b31f691afb14dbdf5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 9 Oct 2009 10:12:46 +0200 Subject: x86: Generate cmpxchg build failures Rework the x86 cmpxchg() implementation to generate build failures when used on improper types. Signed-off-by: Peter Zijlstra Acked-by: Linus Torvalds LKML-Reference: <1254771187.21044.22.camel@laptop> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cmpxchg_32.h | 218 ++++++++++++++--------------------- arch/x86/include/asm/cmpxchg_64.h | 234 +++++++++++++++----------------------- 2 files changed, 177 insertions(+), 275 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 82ceb788a98..5371174cf5d 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -8,14 +8,50 @@ * you need to test for the feature in boot_cpu_data. */ -#define xchg(ptr, v) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), sizeof(*(ptr)))) +extern void __xchg_wrong_size(void); + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway + * Note 2: xchg has side effect, so that attribute volatile is necessary, + * but generally the primitive is invalid, *ptr is output argument. --ANK + */ struct __xchg_dummy { unsigned long a[100]; }; #define __xg(x) ((struct __xchg_dummy *)(x)) +#define __xchg(x, ptr, size) \ +({ \ + __typeof(*(ptr)) __x = (x); \ + switch (size) { \ + case 1: \ + asm volatile("xchgb %b0,%1" \ + : "=q" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("xchgw %w0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + default: \ + __xchg_wrong_size(); \ + } \ + __x; \ +}) + +#define xchg(ptr, v) \ + __xchg((v), (ptr), sizeof(*ptr)) + /* * The semantics of XCHGCMP8B are a bit strange, this is why * there is a loop and the loading of %%eax and %%edx has to @@ -71,57 +107,63 @@ static inline void __set_64bit_var(unsigned long long *ptr, (unsigned int)((value) >> 32)) \ : __set_64bit(ptr, ll_low((value)), ll_high((value)))) -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK - */ -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) -{ - switch (size) { - case 1: - asm volatile("xchgb %b0,%1" - : "=q" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 2: - asm volatile("xchgw %w0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 4: - asm volatile("xchgl %0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - } - return x; -} +extern void __cmpxchg_wrong_size(void); /* * Atomic compare and exchange. Compare OLD with MEM, if identical, * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case 1: \ + asm volatile(lock "cmpxchgb %b1,%2" \ + : "=a"(__ret) \ + : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile(lock "cmpxchgw %w1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile(lock "cmpxchgl %1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") + +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") #ifdef CONFIG_X86_CMPXCHG #define __HAVE_ARCH_CMPXCHG 1 -#define cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define sync_cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) + +#define cmpxchg(ptr, old, new) \ + __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define cmpxchg_local(ptr, old, new) \ + __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) #endif #ifdef CONFIG_X86_CMPXCHG64 @@ -133,94 +175,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, (unsigned long long)(n))) #endif -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile(LOCK_PREFIX "cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -/* - * Always use locked operations when touching memory shared with a - * hypervisor, since the system may be SMP even if the guest kernel - * isn't. - */ -static inline unsigned long __sync_cmpxchg(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("lock; cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("lock; cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("lock; cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -static inline unsigned long __cmpxchg_local(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old, unsigned long long new) diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 52de72e0de8..485ae415fae 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,9 +3,6 @@ #include /* Provides LOCK_PREFIX */ -#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), \ - (ptr), sizeof(*(ptr)))) - #define __xg(x) ((volatile long *)(x)) static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) @@ -15,167 +12,118 @@ static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) #define _set_64bit set_64bit +extern void __xchg_wrong_size(void); +extern void __cmpxchg_wrong_size(void); + /* * Note: no "lock" prefix even on SMP: xchg always implies lock anyway * Note 2: xchg has side effect, so that attribute volatile is necessary, * but generally the primitive is invalid, *ptr is output argument. --ANK */ -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) -{ - switch (size) { - case 1: - asm volatile("xchgb %b0,%1" - : "=q" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 2: - asm volatile("xchgw %w0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 4: - asm volatile("xchgl %k0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 8: - asm volatile("xchgq %0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - } - return x; -} +#define __xchg(x, ptr, size) \ +({ \ + __typeof(*(ptr)) __x = (x); \ + switch (size) { \ + case 1: \ + asm volatile("xchgb %b0,%1" \ + : "=q" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("xchgw %w0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("xchgl %k0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile("xchgq %0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + default: \ + __xchg_wrong_size(); \ + } \ + __x; \ +}) + +#define xchg(ptr, v) \ + __xchg((v), (ptr), sizeof(*ptr)) + +#define __HAVE_ARCH_CMPXCHG 1 /* * Atomic compare and exchange. Compare OLD with MEM, if identical, * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case 1: \ + asm volatile(lock "cmpxchgb %b1,%2" \ + : "=a"(__ret) \ + : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile(lock "cmpxchgw %w1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile(lock "cmpxchgl %k1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile(lock "cmpxchgq %1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) -#define __HAVE_ARCH_CMPXCHG 1 +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile(LOCK_PREFIX "cmpxchgl %k1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 8: - asm volatile(LOCK_PREFIX "cmpxchgq %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") -/* - * Always use locked operations when touching memory shared with a - * hypervisor, since the system may be SMP even if the guest kernel - * isn't. - */ -static inline unsigned long __sync_cmpxchg(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("lock; cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("lock; cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("lock; cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") -static inline unsigned long __cmpxchg_local(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("cmpxchgl %k1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 8: - asm volatile("cmpxchgq %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define cmpxchg(ptr, old, new) \ + __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define cmpxchg_local(ptr, old, new) \ + __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) -#define cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr)))) #define cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg((ptr), (o), (n)); \ }) -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define sync_cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) + #define cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ -- cgit v1.2.3-70-g09d2 From a6f05a6a0a1713d5b019f096799d49226807d3df Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 8 Oct 2009 18:02:54 -0700 Subject: x86-64: make compat_start_thread() match start_thread() For no real good reason, compat_start_thread() was embedded inline in whereas the native start_thread() lives in process_*.c. Move compat_start_thread() to process_64.c, remove gratuitious differences, and fix a few items which mostly look like bit rot. In particular, compat_start_thread() didn't do free_thread_xstate(), which means it was hanging on to the xstate store area even when it was not needed. It was also not setting old_rsp, but it looks like that generally shouldn't matter for a 32-bit process. Note: compat_start_thread *has* to be a macro, since it is tested with start_thread_ia32() as the out of line function name. Signed-off-by: H. Peter Anvin Acked-by: Suresh Siddha --- arch/x86/include/asm/elf.h | 20 ++------------------ arch/x86/kernel/process_64.c | 23 ++++++++++++++++++++++- 2 files changed, 24 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 456a304b817..8a024babe5e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -157,19 +157,6 @@ do { \ #define compat_elf_check_arch(x) elf_check_arch_ia32(x) -static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp) -{ - loadsegment(fs, 0); - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); - load_gs_index(0); - regs->ip = ip; - regs->sp = sp; - regs->flags = X86_EFLAGS_IF; - regs->cs = __USER32_CS; - regs->ss = __USER32_DS; -} - static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { @@ -191,11 +178,8 @@ do { \ #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) -#define compat_start_thread(regs, ip, sp) \ -do { \ - start_ia32_thread(regs, ip, sp); \ - set_fs(USER_DS); \ -} while (0) +void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); +#define compat_start_thread start_thread_ia32 #define COMPAT_SET_PERSONALITY(ex) \ do { \ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ad535b68317..7cf0a6b6d4b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -356,7 +356,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) percpu_write(old_rsp, new_sp); regs->cs = __USER_CS; regs->ss = __USER_DS; - regs->flags = 0x200; + regs->flags = X86_EFLAGS_IF; set_fs(USER_DS); /* * Free the old FP and other extended state @@ -365,6 +365,27 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); +#ifdef CONFIG_IA32_EMULATION +void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +{ + loadsegment(fs, 0); + loadsegment(ds, __USER32_DS); + loadsegment(es, __USER32_DS); + load_gs_index(0); + regs->ip = new_ip; + regs->sp = new_sp; + percpu_write(old_rsp, new_sp); + regs->cs = __USER32_CS; + regs->ss = __USER32_DS; + regs->flags = X86_EFLAGS_IF; + set_fs(USER_DS); + /* + * Free the old FP and other extended state + */ + free_thread_xstate(current); +} +#endif + /* * switch_to(x,y) should switch tasks from x to y. * -- cgit v1.2.3-70-g09d2 From e634d8fc792c66c3d4ff45518c04848c1e28f221 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 9 Oct 2009 15:56:53 -0700 Subject: x86-64: merge the standard and compat start_thread() functions The only thing left that differs between the standard and compat start_thread functions is the actual segment numbers and the prototype, so have a single common function which contains the guts and two very small wrappers. Signed-off-by: H. Peter Anvin Acked-by: Suresh Siddha --- arch/x86/kernel/process_64.c | 39 +++++++++++++++++---------------------- 1 file changed, 17 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 7cf0a6b6d4b..eb261c582a4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -344,18 +344,20 @@ out: return err; } -void -start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +static void +start_thread_common(struct pt_regs *regs, unsigned long new_ip, + unsigned long new_sp, + unsigned int _cs, unsigned int _ss, unsigned int _ds) { loadsegment(fs, 0); - loadsegment(es, 0); - loadsegment(ds, 0); + loadsegment(es, _ds); + loadsegment(ds, _ds); load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; percpu_write(old_rsp, new_sp); - regs->cs = __USER_CS; - regs->ss = __USER_DS; + regs->cs = _cs; + regs->ss = _ss; regs->flags = X86_EFLAGS_IF; set_fs(USER_DS); /* @@ -363,26 +365,19 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) */ free_thread_xstate(current); } -EXPORT_SYMBOL_GPL(start_thread); + +void +start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +{ + start_thread_common(regs, new_ip, new_sp, + __USER_CS, __USER_DS, 0); +} #ifdef CONFIG_IA32_EMULATION void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) { - loadsegment(fs, 0); - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); - load_gs_index(0); - regs->ip = new_ip; - regs->sp = new_sp; - percpu_write(old_rsp, new_sp); - regs->cs = __USER32_CS; - regs->ss = __USER32_DS; - regs->flags = X86_EFLAGS_IF; - set_fs(USER_DS); - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); + start_thread_common(regs, new_ip, new_sp, + __USER32_CS, __USER32_DS, __USER32_DS); } #endif -- cgit v1.2.3-70-g09d2 From a469f627c15de2af392be23508e6094d7268e2b7 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Sat, 3 Oct 2009 11:21:30 +0000 Subject: SH: add support for the RJ54N1CB0C camera for the kfr2r09 platform Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- arch/sh/boards/mach-kfr2r09/setup.c | 139 ++++++++++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) (limited to 'arch') diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index c08d33fe210..ce01d6a953b 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include