Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS update from Ralf Baechle:
 "This is the MIPS update for 3.7.

  A fair chunk of them are platform updates to the Cavium Octeon SOC
  (which involves machine generated header files of considerable size),
  Atheros ATH79xx, RMI aka Netlogic aka Broadcom XLP, Broadcom BCM63xx
  platforms.

  Support for the commercial MIPS simulator MIPSsim has been removed as
  MIPS Technologies is shifting away from this product and Qemu is
  offering various more powerful platforms.  The generic MIPS code can
  now also probe for no-execute / write-only TLB features implemented
  without the full SmartMIPS extension as permitted by the latest MIPS
  processor architecture.  Lots of small changes to generic code."

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (78 commits)
  MIPS: ath79: Fix CPU/DDR frequency calculation for SRIF PLLs
  MIPS: ath79: use correct fractional dividers for {CPU,DDR}_PLL on AR934x
  MIPS: BCM63XX: Properly handle mac address octet overflow
  MIPS: Kconfig: Avoid build errors by hiding USE_OF from the user.
  MIPS: Replace `-' in defconfig filename wth `_' for consistency.
  MIPS: Wire kcmp syscall.
  MIPS: MIPSsim: Remove the MIPSsim platform.
  MIPS: NOTIFY_RESUME is not needed in TIF masks
  MIPS: Merge the identical "return from syscall" per-ABI code
  MIPS: Unobfuscate _TIF..._MASK
  MIPS: Prevent hitting do_notify_resume() with !user_mode(regs).
  MIPS: Replace 'kernel_uses_smartmips_rixi' with 'cpu_has_rixi'.
  MIPS: Add base architecture support for RI and XI.
  MIPS: Optimise TLB handlers for MIPS32/64 R2 cores.
  MIPS: uasm: Add INS and EXT instructions.
  MIPS: Avoid pipeline stalls on some MIPS32R2 cores.
  MIPS: Make VPE count to be one-based.
  MIPS: Add new end of interrupt functionality for GIC.
  MIPS: Add EIC support for GIC.
  MIPS: Code clean-ups for the GIC.
  ...

1 files changed, 63 insertions, 30 deletions

diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index ce6483a..0219395 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -4,7 +4,7 @@
  * for more details.
  *
  * Copyright (C) 2007 by Ralf Baechle
- * Copyright (C) 2009, 2010 Cavium Networks, Inc.
+ * Copyright (C) 2009, 2012 Cavium, Inc.
  */
 #include <linux/clocksource.h>
 #include <linux/export.h>
@@ -18,6 +18,33 @@
 #include <asm/octeon/cvmx-ipd-defs.h>
 #include <asm/octeon/cvmx-mio-defs.h>
 
+
+static u64 f;
+static u64 rdiv;
+static u64 sdiv;
+static u64 octeon_udelay_factor;
+static u64 octeon_ndelay_factor;
+
+void __init octeon_setup_delays(void)
+{
+	octeon_udelay_factor = octeon_get_clock_rate() / 1000000;
+	/*
+	 * For __ndelay we divide by 2^16, so the factor is multiplied
+	 * by the same amount.
+	 */
+	octeon_ndelay_factor = (octeon_udelay_factor * 0x10000ull) / 1000ull;
+
+	preset_lpj = octeon_get_clock_rate() / HZ;
+
+	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
+		union cvmx_mio_rst_boot rst_boot;
+		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
+		rdiv = rst_boot.s.c_mul;	/* CPU clock */
+		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
+		f = (0x8000000000000000ull / sdiv) * 2;
+	}
+}
+
 /*
  * Set the current core's cvmcount counter to the value of the
  * IPD_CLK_COUNT.  We do this on all cores as they are brought
@@ -30,17 +57,6 @@ void octeon_init_cvmcount(void)
 {
 	unsigned long flags;
 	unsigned loops = 2;
-	u64 f = 0;
-	u64 rdiv = 0;
-	u64 sdiv = 0;
-	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
-		union cvmx_mio_rst_boot rst_boot;
-		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
-		rdiv = rst_boot.s.c_mul;	/* CPU clock */
-		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
-		f = (0x8000000000000000ull / sdiv) * 2;
-	}
-
 
 	/* Clobber loops so GCC will not unroll the following while loop. */
 	asm("" : "+r" (loops));
@@ -57,9 +73,9 @@ void octeon_init_cvmcount(void)
 			if (f != 0) {
 				asm("dmultu\t%[cnt],%[f]\n\t"
 				    "mfhi\t%[cnt]"
-				    : [cnt] "+r" (ipd_clk_count),
-				      [f] "=r" (f)
-				    : : "hi", "lo");
+				    : [cnt] "+r" (ipd_clk_count)
+				    : [f] "r" (f)
+				    : "hi", "lo");
 			}
 		}
 		write_c0_cvmcount(ipd_clk_count);
@@ -109,21 +125,6 @@ void __init plat_time_init(void)
 	clocksource_register_hz(&clocksource_mips, octeon_get_clock_rate());
 }
 
-static u64 octeon_udelay_factor;
-static u64 octeon_ndelay_factor;
-
-void __init octeon_setup_delays(void)
-{
-	octeon_udelay_factor = octeon_get_clock_rate() / 1000000;
-	/*
-	 * For __ndelay we divide by 2^16, so the factor is multiplied
-	 * by the same amount.
-	 */
-	octeon_ndelay_factor = (octeon_udelay_factor * 0x10000ull) / 1000ull;
-
-	preset_lpj = octeon_get_clock_rate() / HZ;
-}
-
 void __udelay(unsigned long us)
 {
 	u64 cur, end, inc;
@@ -163,3 +164,35 @@ void __delay(unsigned long loops)
 		cur = read_c0_cvmcount();
 }
 EXPORT_SYMBOL(__delay);
+
+
+/**
+ * octeon_io_clk_delay - wait for a given number of io clock cycles to pass.
+ *
+ * We scale the wait by the clock ratio, and then wait for the
+ * corresponding number of core clocks.
+ *
+ * @count: The number of clocks to wait.
+ */
+void octeon_io_clk_delay(unsigned long count)
+{
+	u64 cur, end;
+
+	cur = read_c0_cvmcount();
+	if (rdiv != 0) {
+		end = count * rdiv;
+		if (f != 0) {
+			asm("dmultu\t%[cnt],%[f]\n\t"
+				"mfhi\t%[cnt]"
+				: [cnt] "+r" (end)
+				: [f] "r" (f)
+				: "hi", "lo");
+		}
+		end = cur + end;
+	} else {
+		end = cur + count;
+	}
+	while (end > cur)
+		cur = read_c0_cvmcount();
+}
+EXPORT_SYMBOL(octeon_io_clk_delay);