4 files changed, 208 insertions, 120 deletions

diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index e9e64e0ff7aa..5a84a1f11231 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -2,7 +2,7 @@
  * Code for replacing ftrace calls with jumps.
  *
  * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
- * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Copyright (C) 2009, 2010 DSLab, Lanzhou University, China
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  *
  * Thanks goes to Steven Rostedt for writing the original x86 version.
@@ -12,18 +12,62 @@
 #include <linux/init.h>
 #include <linux/ftrace.h>
 
-#include <asm/cacheflush.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
+#include <asm/uasm.h>
+
+/*
+ * If the Instruction Pointer is in module space (0xc0000000), return true;
+ * otherwise, it is in kernel space (0x80000000), return false.
+ *
+ * FIXME: This will not work when the kernel space and module space are the
+ * same. If they are the same, we need to modify scripts/recordmcount.pl,
+ * ftrace_make_nop/call() and the other related parts to ensure the
+ * enabling/disabling of the calling site to _mcount is right for both kernel
+ * and module.
+ */
+
+static inline int in_module(unsigned long ip)
+{
+        return ip & 0x40000000;
+}
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #define JAL 0x0c000000          /* jump & link: ip --> ra, jump to target */
 #define ADDR_MASK 0x03ffffff    /*  op_code|addr : 31...26|25 ....0 */
-#define jump_insn_encode(op_code, addr) \
-        ((unsigned int)((op_code) | (((addr) >> 2) & ADDR_MASK)))
 
-static unsigned int ftrace_nop = 0x00000000;
+#define INSN_B_1F_4 0x10000004  /* b 1f; offset = 4 */
+#define INSN_B_1F_5 0x10000005  /* b 1f; offset = 5 */
+#define INSN_NOP 0x00000000     /* nop */
+#define INSN_JAL(addr)  \
+        ((unsigned int)(JAL | (((addr) >> 2) & ADDR_MASK)))
+
+static unsigned int insn_jal_ftrace_caller __read_mostly;
+static unsigned int insn_lui_v1_hi16_mcount __read_mostly;
+static unsigned int insn_j_ftrace_graph_caller __maybe_unused __read_mostly;
+
+static inline void ftrace_dyn_arch_init_insns(void)
+{
+        u32 *buf;
+        unsigned int v1;
+
+        /* lui v1, hi16_mcount */
+        v1 = 3;
+        buf = (u32 *)&insn_lui_v1_hi16_mcount;
+        UASM_i_LA_mostly(&buf, v1, MCOUNT_ADDR);
+
+        /* jal (ftrace_caller + 8), jump over the first two instruction */
+        buf = (u32 *)&insn_jal_ftrace_caller;
+        uasm_i_jal(&buf, (FTRACE_ADDR + 8));
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        /* j ftrace_graph_caller */
+        buf = (u32 *)&insn_j_ftrace_graph_caller;
+        uasm_i_j(&buf, (unsigned long)ftrace_graph_caller);
+#endif
+}
 
 static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
 {
@@ -40,67 +84,56 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
         return 0;
 }
 
-static int lui_v1;
-static int jal_mcount;
-
 int ftrace_make_nop(struct module *mod,
                     struct dyn_ftrace *rec, unsigned long addr)
 {
         unsigned int new;
-        int faulted;
         unsigned long ip = rec->ip;
 
-        /* We have compiled module with -mlong-calls, but compiled the kernel
-         * without it, we need to cope with them respectively. */
-        if (ip & 0x40000000) {
-                /* record it for ftrace_make_call */
-                if (lui_v1 == 0) {
-                        /* lui_v1 = *(unsigned int *)ip; */
-                        safe_load_code(lui_v1, ip, faulted);
-
-                        if (unlikely(faulted))
-                                return -EFAULT;
-                }
-
-                /* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
+        /*
+         * We have compiled module with -mlong-calls, but compiled the kernel
+         * without it, we need to cope with them respectively.
+         */
+        if (in_module(ip)) {
+#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
+                /*
+                 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000005)
+                 * addiu v1, v1, low_16bit_of_mcount
+                 * move at, ra
+                 * move $12, ra_address
+                 * jalr v1
+                 *  sub sp, sp, 8
+                 *                                  1: offset = 5 instructions
+                 */
+                new = INSN_B_1F_5;
+#else
+                /*
+                 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
                  * addiu v1, v1, low_16bit_of_mcount
                  * move at, ra
                  * jalr v1
-                 * nop
-                 *                                   1f: (ip + 12)
+                 *  nop | move $12, ra_address | sub sp, sp, 8
+                 *                                  1: offset = 4 instructions
                  */
-                new = 0x10000004;
+                new = INSN_B_1F_4;
+#endif
         } else {
-                /* record/calculate it for ftrace_make_call */
-                if (jal_mcount == 0) {
-                        /* We can record it directly like this:
-                         *     jal_mcount = *(unsigned int *)ip;
-                         * Herein, jump over the first two nop instructions */
-                        jal_mcount = jump_insn_encode(JAL, (MCOUNT_ADDR + 8));
-                }
-
-                /* move at, ra
-                 * jalr v1              --> nop
+                /*
+                 * move at, ra
+                 * jal _mcount          --> nop
                  */
-                new = ftrace_nop;
+                new = INSN_NOP;
         }
         return ftrace_modify_code(ip, new);
 }
 
-static int modified;    /* initialized as 0 by default */
-
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
         unsigned int new;
         unsigned long ip = rec->ip;
 
-        /* We just need to remove the "b ftrace_stub" at the fist time! */
-        if (modified == 0) {
-                modified = 1;
-                ftrace_modify_code(addr, ftrace_nop);
-        }
         /* ip, module: 0xc0000000, kernel: 0x80000000 */
-        new = (ip & 0x40000000) ? lui_v1 : jal_mcount;
+        new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
 
         return ftrace_modify_code(ip, new);
 }
@@ -111,44 +144,48 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 {
         unsigned int new;
 
-        new = jump_insn_encode(JAL, (unsigned long)func);
+        new = INSN_JAL((unsigned long)func);
 
         return ftrace_modify_code(FTRACE_CALL_IP, new);
 }
 
 int __init ftrace_dyn_arch_init(void *data)
 {
+        /* Encode the instructions when booting */
+        ftrace_dyn_arch_init_insns();
+
+        /* Remove "b ftrace_stub" to ensure ftrace_caller() is executed */
+        ftrace_modify_code(MCOUNT_ADDR, INSN_NOP);
+
         /* The return code is retured via data */
         *(unsigned long *)data = 0;
 
         return 0;
 }
-#endif                          /* CONFIG_DYNAMIC_FTRACE */
+#endif  /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 extern void ftrace_graph_call(void);
-#define JMP     0x08000000      /* jump to target directly */
-#define CALL_FTRACE_GRAPH_CALLER \
-        jump_insn_encode(JMP, (unsigned long)(&ftrace_graph_caller))
 #define FTRACE_GRAPH_CALL_IP    ((unsigned long)(&ftrace_graph_call))
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
         return ftrace_modify_code(FTRACE_GRAPH_CALL_IP,
-                                  CALL_FTRACE_GRAPH_CALLER);
+                        insn_j_ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-        return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, ftrace_nop);
+        return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, INSN_NOP);
 }
 
-#endif                          /* !CONFIG_DYNAMIC_FTRACE */
+#endif  /* CONFIG_DYNAMIC_FTRACE */
 
 #ifndef KBUILD_MCOUNT_RA_ADDRESS
+
 #define S_RA_SP (0xafbf << 16)  /* s{d,w} ra, offset(sp) */
 #define S_R_SP  (0xafb0 << 16)  /* s{d,w} R, offset(sp) */
 #define OFFSET_MASK     0xffff  /* stack offset range: 0 ~ PT_SIZE */
@@ -162,17 +199,17 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
         unsigned int code;
         int faulted;
 
-        /* in module or kernel? */
-        if (self_addr & 0x40000000) {
-                /* module: move to the instruction "lui v1, HI_16BIT_OF_MCOUNT" */
-                ip = self_addr - 20;
-        } else {
-                /* kernel: move to the instruction "move ra, at" */
-                ip = self_addr - 12;
-        }
+        /*
+         * For module, move the ip from calling site of mcount to the
+         * instruction "lui v1, hi_16bit_of_mcount"(offset is 20), but for
+         * kernel, move to the instruction "move ra, at"(offset is 12)
+         */
+        ip = self_addr - (in_module(self_addr) ? 20 : 12);
 
-        /* search the text until finding the non-store instruction or "s{d,w}
-         * ra, offset(sp)" instruction */
+        /*
+         * search the text until finding the non-store instruction or "s{d,w}
+         * ra, offset(sp)" instruction
+         */
         do {
                 ip -= 4;
 
@@ -181,10 +218,11 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
 
                 if (unlikely(faulted))
                         return 0;
-
-                /* If we hit the non-store instruction before finding where the
+                /*
+                 * If we hit the non-store instruction before finding where the
                  * ra is stored, then this is a leaf function and it does not
-                 * store the ra on the stack. */
+                 * store the ra on the stack
+                 */
                 if ((code & S_R_SP) != S_R_SP)
                         return parent_addr;
 
@@ -202,7 +240,7 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
         return 0;
 }
 
-#endif
+#endif  /* !KBUILD_MCOUNT_RA_ADDRESS */
 
 /*
  * Hook the return address and push it in the stack of return addrs
@@ -220,7 +258,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
         if (unlikely(atomic_read(&current->tracing_graph_pause)))
                 return;
 
-        /* "parent" is the stack address saved the return address of the caller
+        /*
+         * "parent" is the stack address saved the return address of the caller
          * of _mcount.
          *
          * if the gcc < 4.5, a leaf function does not save the return address
@@ -242,10 +281,11 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
                 goto out;
 #ifndef KBUILD_MCOUNT_RA_ADDRESS
         parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
-                                                         (unsigned long)parent,
-                                                         fp);
-        /* If fails when getting the stack address of the non-leaf function's
-         * ra, stop function graph tracer and return */
+                        (unsigned long)parent, fp);
+        /*
+         * If fails when getting the stack address of the non-leaf function's
+         * ra, stop function graph tracer and return
+         */
         if (parent == 0)
                 goto out;
 #endif
@@ -272,4 +312,4 @@ out:
         ftrace_graph_stop();
         WARN_ON(1);
 }
-#endif                          /* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif  /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 6851fc97a511..6bfcb7a00ec6 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -6,6 +6,7 @@
  * more details.
  *
  * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Copyright (C) 2010 DSLab, Lanzhou University, China
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  */
 
@@ -45,8 +46,6 @@
         PTR_L   a5, PT_R9(sp)
         PTR_L   a6, PT_R10(sp)
         PTR_L   a7, PT_R11(sp)
-#endif
-#ifdef CONFIG_64BIT
         PTR_ADDIU       sp, PT_SIZE
 #else
         PTR_ADDIU       sp, (PT_SIZE + 8)
@@ -58,6 +57,12 @@
          move ra, AT
         .endm
 
+/*
+ * The -mmcount-ra-address option of gcc 4.5 uses register $12 to pass
+ * the location of the parent's return address.
+ */
+#define MCOUNT_RA_ADDRESS_REG   $12
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 NESTED(ftrace_caller, PT_SIZE, ra)
@@ -71,14 +76,14 @@ _mcount:
 
         MCOUNT_SAVE_REGS
 #ifdef KBUILD_MCOUNT_RA_ADDRESS
-        PTR_S   t0, PT_R12(sp)  /* t0 saved the location of the return address(at) by -mmcount-ra-address */
+        PTR_S   MCOUNT_RA_ADDRESS_REG, PT_R12(sp)
 #endif
 
-        move    a0, ra          /* arg1: next ip, selfaddr */
+        move    a0, ra          /* arg1: self return address */
         .globl ftrace_call
 ftrace_call:
         nop     /* a placeholder for the call to a real tracing function */
-         move   a1, AT          /* arg2: the caller's next ip, parent */
+         move   a1, AT          /* arg2: parent's return address */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         .globl ftrace_graph_call
@@ -119,9 +124,9 @@ NESTED(_mcount, PT_SIZE, ra)
 static_trace:
         MCOUNT_SAVE_REGS
 
-        move    a0, ra          /* arg1: next ip, selfaddr */
+        move    a0, ra          /* arg1: self return address */
         jalr    t2              /* (1) call *ftrace_trace_function */
-         move   a1, AT          /* arg2: the caller's next ip, parent */
+         move   a1, AT          /* arg2: parent's return address */
 
         MCOUNT_RESTORE_REGS
         .globl ftrace_stub
@@ -134,28 +139,34 @@ ftrace_stub:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 NESTED(ftrace_graph_caller, PT_SIZE, ra)
-#ifdef CONFIG_DYNAMIC_FTRACE
-        PTR_L   a1, PT_R31(sp)  /* load the original ra from the stack */
-#ifdef KBUILD_MCOUNT_RA_ADDRESS
-        PTR_L   t0, PT_R12(sp)  /* load the original t0 from the stack */
-#endif
-#else
+#ifndef CONFIG_DYNAMIC_FTRACE
         MCOUNT_SAVE_REGS
-        move    a1, ra          /* arg2: next ip, selfaddr */
 #endif
 
+        /* arg1: Get the location of the parent's return address */
 #ifdef KBUILD_MCOUNT_RA_ADDRESS
-        bnez    t0, 1f          /* non-leaf func: t0 saved the location of the return address */
+#ifdef CONFIG_DYNAMIC_FTRACE
+        PTR_L   a0, PT_R12(sp)
+#else
+        move    a0, MCOUNT_RA_ADDRESS_REG
+#endif
+        bnez    a0, 1f  /* non-leaf func: stored in MCOUNT_RA_ADDRESS_REG */
          nop
-        PTR_LA  t0, PT_R1(sp)   /* leaf func: get the location of at(old ra) from our own stack */
-1:      move    a0, t0          /* arg1: the location of the return address */
+#endif
+        PTR_LA  a0, PT_R1(sp)   /* leaf func: the location in current stack */
+1:
+
+        /* arg2: Get self return address */
+#ifdef CONFIG_DYNAMIC_FTRACE
+        PTR_L   a1, PT_R31(sp)
 #else
-        PTR_LA  a0, PT_R1(sp)   /* arg1: &AT -> a0 */
+        move    a1, ra
 #endif
-        jal     prepare_ftrace_return
+
+        /* arg3: Get frame pointer of current stack */
 #ifdef CONFIG_FRAME_POINTER
-         move   a2, fp          /* arg3: frame pointer */
-#else
+         move   a2, fp
+#else /* ! CONFIG_FRAME_POINTER */
 #ifdef CONFIG_64BIT
          PTR_LA a2, PT_SIZE(sp)
 #else
@@ -163,6 +174,8 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra)
 #endif
 #endif
 
+        jal     prepare_ftrace_return
+         nop
         MCOUNT_RESTORE_REGS
         RETURN_BACK
         END(ftrace_graph_caller)
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index f5981c499109..2340f11dc29c 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2005 Mips Technologies, Inc
  */
 #include <linux/cpu.h>
+#include <linux/cpuset.h>
 #include <linux/cpumask.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
@@ -39,6 +40,21 @@ static inline struct task_struct *find_process_by_pid(pid_t pid)
         return pid ? find_task_by_vpid(pid) : current;
 }
 
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+        const struct cred *cred = current_cred(), *pcred;
+        bool match;
+
+        rcu_read_lock();
+        pcred = __task_cred(p);
+        match = (cred->euid == pcred->euid ||
+                 cred->euid == pcred->uid);
+        rcu_read_unlock();
+        return match;
+}
 
 /*
  * mipsmt_sys_sched_setaffinity - set the cpu affinity of a process
@@ -46,12 +62,10 @@ static inline struct task_struct *find_process_by_pid(pid_t pid)
 asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
                                       unsigned long __user *user_mask_ptr)
 {
-        cpumask_t new_mask;
-        cpumask_t effective_mask;
-        int retval;
-        struct task_struct *p;
+        cpumask_var_t cpus_allowed, new_mask, effective_mask;
         struct thread_info *ti;
-        uid_t euid;
+        struct task_struct *p;
+        int retval;
 
         if (len < sizeof(new_mask))
                 return -EINVAL;
@@ -60,53 +74,74 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
                 return -EFAULT;
 
         get_online_cpus();
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
 
         p = find_process_by_pid(pid);
         if (!p) {
-                read_unlock(&tasklist_lock);
+                rcu_read_unlock();
                 put_online_cpus();
                 return -ESRCH;
         }
 
-        /*
-         * It is not safe to call set_cpus_allowed with the
-         * tasklist_lock held.  We will bump the task_struct's
-         * usage count and drop tasklist_lock before invoking
-         * set_cpus_allowed.
-         */
+        /* Prevent p going away */
         get_task_struct(p);
+        rcu_read_unlock();
 
-        euid = current_euid();
+        if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+                retval = -ENOMEM;
+                goto out_put_task;
+        }
+        if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+                retval = -ENOMEM;
+                goto out_free_cpus_allowed;
+        }
+        if (!alloc_cpumask_var(&effective_mask, GFP_KERNEL)) {
+                retval = -ENOMEM;
+                goto out_free_new_mask;
+        }
         retval = -EPERM;
-        if (euid != p->cred->euid && euid != p->cred->uid &&
-            !capable(CAP_SYS_NICE)) {
-                read_unlock(&tasklist_lock);
+        if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                 goto out_unlock;
-        }
 
         retval = security_task_setscheduler(p, 0, NULL);
         if (retval)
                 goto out_unlock;
 
         /* Record new user-specified CPU set for future reference */
-        p->thread.user_cpus_allowed = new_mask;
-
-        /* Unlock the task list */
-        read_unlock(&tasklist_lock);
+        cpumask_copy(&p->thread.user_cpus_allowed, new_mask);
 
+ again:
         /* Compute new global allowed CPU set if necessary */
         ti = task_thread_info(p);
         if (test_ti_thread_flag(ti, TIF_FPUBOUND) &&
-            cpus_intersects(new_mask, mt_fpu_cpumask)) {
-                cpus_and(effective_mask, new_mask, mt_fpu_cpumask);
-                retval = set_cpus_allowed_ptr(p, &effective_mask);
+            cpus_intersects(*new_mask, mt_fpu_cpumask)) {
+                cpus_and(*effective_mask, *new_mask, mt_fpu_cpumask);
+                retval = set_cpus_allowed_ptr(p, effective_mask);
         } else {
+                cpumask_copy(effective_mask, new_mask);
                 clear_ti_thread_flag(ti, TIF_FPUBOUND);
-                retval = set_cpus_allowed_ptr(p, &new_mask);
+                retval = set_cpus_allowed_ptr(p, new_mask);
         }
 
+        if (!retval) {
+                cpuset_cpus_allowed(p, cpus_allowed);
+                if (!cpumask_subset(effective_mask, cpus_allowed)) {
+                        /*
+                         * We must have raced with a concurrent cpuset
+                         * update. Just reset the cpus_allowed to the
+                         * cpuset's cpus_allowed
+                         */
+                        cpumask_copy(new_mask, cpus_allowed);
+                        goto again;
+                }
+        }
 out_unlock:
+        free_cpumask_var(effective_mask);
+out_free_new_mask:
+        free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+        free_cpumask_var(cpus_allowed);
+out_put_task:
         put_task_struct(p);
         put_online_cpus();
         return retval;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 8bdd6a663c7f..852780868fb4 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -976,7 +976,7 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 
         case 2:
                 raw_notifier_call_chain(&cu2_chain, CU2_EXCEPTION, regs);
-                break;
+                return;
 
         case 3:
                 break;