Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Benjamin Herrenschmidt:
 "Notable highlights:

   - iommu improvements from Anton removing the per-iommu global lock in
     favor of dividing the DMA space into pools, each with its own lock,
     and hashed on the CPU number.  Along with making the locking more
     fine grained, this gives significant improvements in multiqueue
     networking scalability.

   - Still from Anton, we know provide a vdso based variant of getcpu
     which makes sched_getcpu with the appropriate glibc patch something
     like 18 times faster.

   - More anton goodness (he's been busy !) in other areas such as a
     faster __clear_user and copy_page on P7, various perf fixes to
     improve sampling quality, etc...

   - One more step toward removing legacy i2c interfaces by using new
     device-tree based probing of platform devices for the AOA audio
     drivers

   - A nice series of patches from Michael Neuling that helps avoiding
     confusion between register numbers and litterals in assembly code,
     trying to enforce the use of "%rN" register names in gas rather
     than plain numbers.

   - A pile of FSL updates

   - The usual bunch of small fixes, cleanups etc...

  You may spot a change to drivers/char/mem.  The patch got no comment
  or ack from outside, it's a trivial patch to allow the architecture to
  skip creating /dev/port, which we use to disable it on ppc64 that
  don't have a legacy brige.  On those, IO ports 0...64K are not mapped
  in kernel space at all, so accesses to /dev/port cause oopses (and
  yes, distros -still- ship userspace that bangs hard coded ports such
  as kbdrate)."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (106 commits)
  powerpc/mpic: Create a revmap with enough entries for IPIs and timers
  Remove stale .rej file
  powerpc/iommu: Fix iommu pool initialization
  powerpc/eeh: Check handle_eeh_events() return value
  powerpc/85xx: Add phy nodes in SGMII mode for MPC8536/44/72DS & P2020DS
  powerpc/e500: add paravirt QEMU platform
  powerpc/mpc85xx_ds: convert to unified PCI init
  powerpc/fsl-pci: get PCI init out of board files
  powerpc/85xx: Update corenet64_smp_defconfig
  powerpc/85xx: Update corenet32_smp_defconfig
  powerpc/85xx: Rename P1021RDB-PC device trees to be consistent
  powerpc/watchdog: move booke watchdog param related code to setup-common.c
  sound/aoa: Adapt to new i2c probing scheme
  i2c/powermac: Improve detection of devices from device-tree
  powerpc: Disable /dev/port interface on systems without an ISA bridge
  of: Improve prom_update_property() function
  powerpc: Add "memory" attribute for mfmsr()
  powerpc/ftrace: Fix assembly trampoline register usage
  powerpc/hw_breakpoints: Fix incorrect pointer access
  powerpc: Put the gpr save/restore functions in their own section
  ...

1 files changed, 108 insertions, 49 deletions

diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 497db7b23bb..f9ede7c6606 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -19,9 +19,6 @@
  */
 #include <asm/ppc_asm.h>
 
-#define STACKFRAMESIZE	256
-#define STK_REG(i)	(112 + ((i)-14)*8)
-
 	.macro err1
 100:
 	.section __ex_table,"a"
@@ -57,26 +54,26 @@
 
 
 .Ldo_err4:
-	ld	r16,STK_REG(r16)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r14,STK_REG(r14)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	.exit_vmx_copy
+	bl	.exit_vmx_usercopy
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
 	b	.Lexit
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
-	ld	r22,STK_REG(r22)(r1)
-	ld	r21,STK_REG(r21)(r1)
-	ld	r20,STK_REG(r20)(r1)
-	ld	r19,STK_REG(r19)(r1)
-	ld	r18,STK_REG(r18)(r1)
-	ld	r17,STK_REG(r17)(r1)
-	ld	r16,STK_REG(r16)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r14,STK_REG(r14)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
 .Lexit:
 	addi	r1,r1,STACKFRAMESIZE
 .Ldo_err1:
@@ -137,15 +134,15 @@ err1;	stw	r0,0(r3)
 
 	mflr	r0
 	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
-	std	r17,STK_REG(r17)(r1)
-	std	r18,STK_REG(r18)(r1)
-	std	r19,STK_REG(r19)(r1)
-	std	r20,STK_REG(r20)(r1)
-	std	r21,STK_REG(r21)(r1)
-	std	r22,STK_REG(r22)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
 	std	r0,STACKFRAMESIZE+16(r1)
 
 	srdi	r6,r5,7
@@ -192,15 +189,15 @@ err2;	std	r21,120(r3)
 
 	clrldi	r5,r5,(64-7)
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
-	ld	r17,STK_REG(r17)(r1)
-	ld	r18,STK_REG(r18)(r1)
-	ld	r19,STK_REG(r19)(r1)
-	ld	r20,STK_REG(r20)(r1)
-	ld	r21,STK_REG(r21)(r1)
-	ld	r22,STK_REG(r22)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
 	addi	r1,r1,STACKFRAMESIZE
 
 	/* Up to 127B to go */
@@ -290,7 +287,7 @@ err1;	stb	r0,0(r3)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	.enter_vmx_usercopy
 	cmpwi	r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
@@ -298,6 +295,68 @@ err1;	stb	r0,0(r3)
 	ld	r5,STACKFRAMESIZE+64(r1)
 	mtlr	r0
 
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	r7,0x3FF
+	ble	1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r6,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	cr1,r7,0x3FF
+	ble	cr1,1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r6,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
 	beq	.Lunwind_stack_nonvmx_copy
 
 	/*
@@ -378,9 +437,9 @@ err3;	stvx	vr0,r3,r11
 7:	sub	r5,r5,r6
 	srdi	r6,r5,7
 
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 	li	r12,64
 	li	r14,80
@@ -415,9 +474,9 @@ err4;	stvx	vr0,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 
 	/* Up to 127B to go */
 	clrldi	r5,r5,(64-7)
@@ -476,7 +535,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	.exit_vmx_usercopy	/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -563,9 +622,9 @@ err3;	stvx	vr11,r3,r11
 7:	sub	r5,r5,r6
 	srdi	r6,r5,7
 
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 	li	r12,64
 	li	r14,80
@@ -608,9 +667,9 @@ err4;	stvx	vr15,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 
 	/* Up to 127B to go */
 	clrldi	r5,r5,(64-7)
@@ -679,5 +738,5 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	.exit_vmx_usercopy	/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */