[PATCH] ARM: 2651/3: kernel helpers for NPTL support

Patch from Nicolas Pitre

This patch entirely reworks the kernel assistance for NPTL on ARM.
In particular this provides an efficient way to retrieve the TLS
value and perform atomic operations without any instruction emulation
nor special system call.  This even allows for pre ARMv6 binaries to
be forward compatible with SMP systems without any penalty.
The problematic and performance critical operations are performed
through segment of kernel provided user code reachable from user space
at a fixed address in kernel memory.  Those fixed entry points are
within the vector page so we basically get it for free as no extra
memory page is required and nothing else may be mapped at that
location anyway.
This is different from (but doesn't preclude) a full blown VDSO
implementation, however a VDSO would prevent some assembly tricks with
constants that allows for efficient branching to those code segments.
And since those code segments only use a few cycles before returning to
user code, the overhead of a VDSO far call would add a significant
overhead to such minimalistic operations.
The ARM_NR_set_tls syscall also changed number.  This is done for two
reasons:
1) this patch changes the way the TLS value was previously meant to be
   retrieved, therefore we ensure whatever library using the old way
   gets fixed (they only exist in private tree at the moment since the
   NPTL work is still progressing).
2) the previous number was allocated in a range causing an undefined
   instruction trap on kernels not supporting that syscall and it was
   determined that allocating it in a range returning -ENOSYS would be
   much nicer for libraries trying to determine if the feature is
   present or not.

Signed-off-by: Nicolas Pitre
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

1 files changed, 50 insertions, 8 deletions

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 0078aeb8573..3a001fe5540 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -450,13 +450,17 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 
         case NR(set_tls):
                 thread->tp_value = regs->ARM_r0;
+#ifdef CONFIG_HAS_TLS_REG
+                asm ("mcr p15, 0, %0, c13, c0, 3" : : "r" (regs->ARM_r0) );
+#else
                 /*
-                 * Our user accessible TLS ptr is located at 0xffff0ffc.
-                 * On SMP read access to this address must raise a fault
-                 * and be emulated from the data abort handler.
-                 * m
+                 * User space must never try to access this directly.
+                 * Expect your app to break eventually if you do so.
+                 * The user helper at 0xffff0fe0 must be used instead.
+                 * (see entry-armv.S for details)
                  */
-                *((unsigned long *)0xffff0ffc) = thread->tp_value;
+                *((unsigned int *)0xffff0ff0) = regs->ARM_r0;
+#endif
                 return 0;
 
         default:
@@ -493,6 +497,41 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
         return 0;
 }
 
+#if defined(CONFIG_CPU_32v6) && !defined(CONFIG_HAS_TLS_REG)
+
+/*
+ * We might be running on an ARMv6+ processor which should have the TLS
+ * register, but for some reason we can't use it and have to emulate it.
+ */
+
+static int get_tp_trap(struct pt_regs *regs, unsigned int instr)
+{
+        int reg = (instr >> 12) & 15;
+        if (reg == 15)
+                return 1;
+        regs->uregs[reg] = current_thread_info()->tp_value;
+        regs->ARM_pc += 4;
+        return 0;
+}
+
+static struct undef_hook arm_mrc_hook = {
+        .instr_mask     = 0x0fff0fff,
+        .instr_val      = 0x0e1d0f70,
+        .cpsr_mask      = PSR_T_BIT,
+        .cpsr_val       = 0,
+        .fn             = get_tp_trap,
+};
+
+static int __init arm_mrc_hook_init(void)
+{
+        register_undef_hook(&arm_mrc_hook);
+        return 0;
+}
+
+late_initcall(arm_mrc_hook_init);
+
+#endif
+
 void __bad_xchg(volatile void *ptr, int size)
 {
         printk("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n",
@@ -580,14 +619,17 @@ void __init trap_init(void)
 {
         extern char __stubs_start[], __stubs_end[];
         extern char __vectors_start[], __vectors_end[];
+        extern char __kuser_helper_start[], __kuser_helper_end[];
+        int kuser_sz = __kuser_helper_end - __kuser_helper_start;
 
         /*
-         * Copy the vectors and stubs (in entry-armv.S) into the
-         * vector page, mapped at 0xffff0000, and ensure these are
-         * visible to the instruction stream.
+         * Copy the vectors, stubs and kuser helpers (in entry-armv.S)
+         * into the vector page, mapped at 0xffff0000, and ensure these
+         * are visible to the instruction stream.
          */
         memcpy((void *)0xffff0000, __vectors_start, __vectors_end - __vectors_start);
         memcpy((void *)0xffff0200, __stubs_start, __stubs_end - __stubs_start);
+        memcpy((void *)0xffff1000 - kuser_sz, __kuser_helper_start, kuser_sz);
         flush_icache_range(0xffff0000, 0xffff0000 + PAGE_SIZE);
         modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 }