Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

[linux-2.6] / arch / i386 / kernel / process.c

diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 5f8cfa6b794085b9fb224e229398369bc0f4c64a..b45cbf93d4391b49411cfdaecf7c1e084e184c33 100644 (file)
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -164,7 +164,7 @@ static inline void play_dead(void)
         */
        local_irq_disable();
        while (1)
-               __asm__ __volatile__("hlt":::"memory");
+               halt();
 }
 #else
 static inline void play_dead(void)
@@ -313,16 +313,12 @@ void show_regs(struct pt_regs * regs)
        printk(" DS: %04x ES: %04x\n",
                0xffff & regs->xds,0xffff & regs->xes);
 
-       __asm__("movl %%cr0, %0": "=r" (cr0));
-       __asm__("movl %%cr2, %0": "=r" (cr2));
-       __asm__("movl %%cr3, %0": "=r" (cr3));
-       /* This could fault if %cr4 does not exist */
-       __asm__("1: movl %%cr4, %0              \n"
-               "2:                             \n"
-               ".section __ex_table,\"a\"      \n"
-               ".long 1b,2b                    \n"
-               ".previous                      \n"
-               : "=r" (cr4): "0" (0));
+       cr0 = read_cr0();
+       cr2 = read_cr2();
+       cr3 = read_cr3();
+       if (current_cpu_data.x86 > 4) {
+               cr4 = read_cr4();
+       }
        printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
        show_trace(NULL, &regs->esp);
 }
@@ -616,6 +612,33 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss)
        tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
 }
 
+/*
+ * This function selects if the context switch from prev to next
+ * has to tweak the TSC disable bit in the cr4.
+ */
+static inline void disable_tsc(struct task_struct *prev_p,
+                              struct task_struct *next_p)
+{
+       struct thread_info *prev, *next;
+
+       /*
+        * gcc should eliminate the ->thread_info dereference if
+        * has_secure_computing returns 0 at compile time (SECCOMP=n).
+        */
+       prev = prev_p->thread_info;
+       next = next_p->thread_info;
+
+       if (has_secure_computing(prev) || has_secure_computing(next)) {
+               /* slow path here */
+               if (has_secure_computing(prev) &&
+                   !has_secure_computing(next)) {
+                       write_cr4(read_cr4() & ~X86_CR4_TSD);
+               } else if (!has_secure_computing(prev) &&
+                          has_secure_computing(next))
+                       write_cr4(read_cr4() | X86_CR4_TSD);
+       }
+}
+
 /*
  *     switch_to(x,yn) should switch tasks from x to y.
  *
@@ -655,46 +678,63 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
        __unlazy_fpu(prev_p);
 
        /*
-        * Reload esp0, LDT and the page table pointer:
+        * Reload esp0.
         */
        load_esp0(tss, next);
 
        /*
-        * Load the per-thread Thread-Local Storage descriptor.
+        * Save away %fs and %gs. No need to save %es and %ds, as
+        * those are always kernel segments while inside the kernel.
+        * Doing this before setting the new TLS descriptors avoids
+        * the situation where we temporarily have non-reloadable
+        * segments in %fs and %gs.  This could be an issue if the
+        * NMI handler ever used %fs or %gs (it does not today), or
+        * if the kernel is running inside of a hypervisor layer.
         */
-       load_TLS(next, cpu);
+       savesegment(fs, prev->fs);
+       savesegment(gs, prev->gs);
 
        /*
-        * Save away %fs and %gs. No need to save %es and %ds, as
-        * those are always kernel segments while inside the kernel.
+        * Load the per-thread Thread-Local Storage descriptor.
         */
-       asm volatile("mov %%fs,%0":"=m" (prev->fs));
-       asm volatile("mov %%gs,%0":"=m" (prev->gs));
+       load_TLS(next, cpu);
 
        /*
         * Restore %fs and %gs if needed.
+        *
+        * Glibc normally makes %fs be zero, and %gs is one of
+        * the TLS segments.
         */
-       if (unlikely(prev->fs | prev->gs | next->fs | next->gs)) {
+       if (unlikely(prev->fs | next->fs))
                loadsegment(fs, next->fs);
+
+       if (prev->gs | next->gs)
                loadsegment(gs, next->gs);
-       }
+
+       /*
+        * Restore IOPL if needed.
+        */
+       if (unlikely(prev->iopl != next->iopl))
+               set_iopl_mask(next->iopl);
 
        /*
         * Now maybe reload the debug registers
         */
        if (unlikely(next->debugreg[7])) {
-               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);
+               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(current->thread.debugreg[6], 6);
-               set_debugreg(current->thread.debugreg[7], 7);
+               set_debugreg(next->debugreg[6], 6);
+               set_debugreg(next->debugreg[7], 7);
        }
 
        if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr))
                handle_io_bitmap(next, tss);
 
+       disable_tsc(prev_p, next_p);
+
        return prev_p;
 }
 
@@ -884,6 +924,8 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
        if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
                return -EINVAL;
 
+       memset(&info, 0, sizeof(info));
+
        desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
 
        info.entry_number = idx;