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

Pull powerpc updates from Benjamin Herrenschmidt:
 "The bulk of this is LE updates.  One should now be able to build an LE
  kernel and even run some things in it.

  I'm still sitting on a handful of patches to enable the new ABI that I
  *might* still send this merge window around, but due to the
  incertainty (they are pretty fresh) I want to keep them separate.

  Other notable changes are some infrastructure bits to better handle
  PCI pass-through under KVM, some bits and pieces added to the new
  PowerNV platform support such as access to the CPU SCOM bus via sysfs,
  and support for EEH error handling on PHB3 (Power8 PCIe).

  We also grew arch_get_random_long() for both pseries and powernv when
  running on P7+ and P8, exploiting the HW rng.

  And finally various embedded updates from freescale"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (154 commits)
  powerpc: Fix fatal SLB miss when restoring PPR
  powerpc/powernv: Reserve the correct PE number
  powerpc/powernv: Add PE to its own PELTV
  powerpc/powernv: Add support for indirect XSCOM via debugfs
  powerpc/scom: Improve debugfs interface
  powerpc/scom: Enable 64-bit addresses
  powerpc/boot: Properly handle the base "of" boot wrapper
  powerpc/bpf: Support MOD operation
  powerpc/bpf: Fix DIVWU instruction opcode
  of: Move definition of of_find_next_cache_node into common code.
  powerpc: Remove big endianness assumption in of_find_next_cache_node
  powerpc/tm: Remove interrupt disable in __switch_to()
  powerpc: word-at-a-time optimization for 64-bit Little Endian
  powerpc/bpf: BPF JIT compiler for 64-bit Little Endian
  powerpc: Only save/restore SDR1 if in hypervisor mode
  powerpc/pmu: Fix ADB_PMU_LED_IDE dependencies
  powerpc/nvram: Fix endian issue when using the partition length
  powerpc/nvram: Fix endian issue when reading the NVRAM size
  powerpc/nvram: Scan partitions only once
  powerpc/mpc512x: remove unnecessary #if
  ...

1 files changed, 112 insertions, 61 deletions

diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index a27ccd5dc6b9..de91f3ae631e 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -54,8 +54,6 @@ struct aligninfo {
 /* DSISR bits reported for a DCBZ instruction: */
 #define DCBZ	0x5f	/* 8xx/82xx dcbz faults when cache not enabled */
 
-#define SWAP(a, b)	(t = (a), (a) = (b), (b) = t)
-
 /*
  * The PowerPC stores certain bits of the instruction that caused the
  * alignment exception in the DSISR register.  This array maps those
@@ -256,11 +254,17 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
  * bottom 4 bytes of each register, and the loads clear the
  * top 4 bytes of the affected register.
  */
+#ifdef __BIG_ENDIAN__
 #ifdef CONFIG_PPC64
 #define REG_BYTE(rp, i)		*((u8 *)((rp) + ((i) >> 2)) + ((i) & 3) + 4)
 #else
 #define REG_BYTE(rp, i)		*((u8 *)(rp) + (i))
 #endif
+#endif
+
+#ifdef __LITTLE_ENDIAN__
+#define REG_BYTE(rp, i)		(*(((u8 *)((rp) + ((i)>>2)) + ((i)&3))))
+#endif
 
 #define SWIZ_PTR(p)		((unsigned char __user *)((p) ^ swiz))
 
@@ -305,6 +309,15 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 			nb0 = nb + reg * 4 - 128;
 			nb = 128 - reg * 4;
 		}
+#ifdef __LITTLE_ENDIAN__
+		/*
+		 *  String instructions are endian neutral but the code
+		 *  below is not.  Force byte swapping on so that the
+		 *  effects of swizzling are undone in the load/store
+		 *  loops below.
+		 */
+		flags ^= SW;
+#endif
 	} else {
 		/* lwm, stmw */
 		nb = (32 - reg) * 4;
@@ -458,7 +471,7 @@ static struct aligninfo spe_aligninfo[32] = {
 static int emulate_spe(struct pt_regs *regs, unsigned int reg,
 		       unsigned int instr)
 {
-	int t, ret;
+	int ret;
 	union {
 		u64 ll;
 		u32 w[2];
@@ -581,24 +594,18 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
 	if (flags & SW) {
 		switch (flags & 0xf0) {
 		case E8:
-			SWAP(data.v[0], data.v[7]);
-			SWAP(data.v[1], data.v[6]);
-			SWAP(data.v[2], data.v[5]);
-			SWAP(data.v[3], data.v[4]);
+			data.ll = swab64(data.ll);
 			break;
 		case E4:
-
-			SWAP(data.v[0], data.v[3]);
-			SWAP(data.v[1], data.v[2]);
-			SWAP(data.v[4], data.v[7]);
-			SWAP(data.v[5], data.v[6]);
+			data.w[0] = swab32(data.w[0]);
+			data.w[1] = swab32(data.w[1]);
 			break;
 		/* Its half word endian */
 		default:
-			SWAP(data.v[0], data.v[1]);
-			SWAP(data.v[2], data.v[3]);
-			SWAP(data.v[4], data.v[5]);
-			SWAP(data.v[6], data.v[7]);
+			data.h[0] = swab16(data.h[0]);
+			data.h[1] = swab16(data.h[1]);
+			data.h[2] = swab16(data.h[2]);
+			data.h[3] = swab16(data.h[3]);
 			break;
 		}
 	}
@@ -658,14 +665,31 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	flush_vsx_to_thread(current);
 
 	if (reg < 32)
-		ptr = (char *) &current->thread.TS_FPR(reg);
+		ptr = (char *) &current->thread.fp_state.fpr[reg][0];
 	else
-		ptr = (char *) &current->thread.vr[reg - 32];
+		ptr = (char *) &current->thread.vr_state.vr[reg - 32];
 
 	lptr = (unsigned long *) ptr;
 
+#ifdef __LITTLE_ENDIAN__
+	if (flags & SW) {
+		elsize = length;
+		sw = length-1;
+	} else {
+		/*
+		 * The elements are BE ordered, even in LE mode, so process
+		 * them in reverse order.
+		 */
+		addr += length - elsize;
+
+		/* 8 byte memory accesses go in the top 8 bytes of the VR */
+		if (length == 8)
+			ptr += 8;
+	}
+#else
 	if (flags & SW)
 		sw = elsize-1;
+#endif
 
 	for (j = 0; j < length; j += elsize) {
 		for (i = 0; i < elsize; ++i) {
@@ -675,19 +699,31 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 				ret |= __get_user(ptr[i^sw], addr + i);
 		}
 		ptr  += elsize;
+#ifdef __LITTLE_ENDIAN__
+		addr -= elsize;
+#else
 		addr += elsize;
+#endif
 	}
 
+#ifdef __BIG_ENDIAN__
+#define VSX_HI 0
+#define VSX_LO 1
+#else
+#define VSX_HI 1
+#define VSX_LO 0
+#endif
+
 	if (!ret) {
 		if (flags & U)
 			regs->gpr[areg] = regs->dar;
 
 		/* Splat load copies the same data to top and bottom 8 bytes */
 		if (flags & SPLT)
-			lptr[1] = lptr[0];
-		/* For 8 byte loads, zero the top 8 bytes */
+			lptr[VSX_LO] = lptr[VSX_HI];
+		/* For 8 byte loads, zero the low 8 bytes */
 		else if (!(flags & ST) && (8 == length))
-			lptr[1] = 0;
+			lptr[VSX_LO] = 0;
 	} else
 		return -EFAULT;
 
@@ -710,18 +746,28 @@ int fix_alignment(struct pt_regs *regs)
 	unsigned int dsisr;
 	unsigned char __user *addr;
 	unsigned long p, swiz;
-	int ret, t;
-	union {
+	int ret, i;
+	union data {
 		u64 ll;
 		double dd;
 		unsigned char v[8];
 		struct {
+#ifdef __LITTLE_ENDIAN__
+			int	 low32;
+			unsigned hi32;
+#else
 			unsigned hi32;
 			int	 low32;
+#endif
 		} x32;
 		struct {
+#ifdef __LITTLE_ENDIAN__
+			short	      low16;
+			unsigned char hi48[6];
+#else
 			unsigned char hi48[6];
 			short	      low16;
+#endif
 		} x16;
 	} data;
 
@@ -780,8 +826,9 @@ int fix_alignment(struct pt_regs *regs)
 
 	/* Byteswap little endian loads and stores */
 	swiz = 0;
-	if (regs->msr & MSR_LE) {
+	if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
 		flags ^= SW;
+#ifdef __BIG_ENDIAN__
 		/*
 		 * So-called "PowerPC little endian" mode works by
 		 * swizzling addresses rather than by actually doing
@@ -794,6 +841,7 @@ int fix_alignment(struct pt_regs *regs)
 		 */
 		if (cpu_has_feature(CPU_FTR_PPC_LE))
 			swiz = 7;
+#endif
 	}
 
 	/* DAR has the operand effective address */
@@ -818,7 +866,7 @@ int fix_alignment(struct pt_regs *regs)
 			elsize = 8;
 
 		flags = 0;
-		if (regs->msr & MSR_LE)
+		if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE))
 			flags |= SW;
 		if (instruction & 0x100)
 			flags |= ST;
@@ -878,32 +926,36 @@ int fix_alignment(struct pt_regs *regs)
 	 * get it from register values
 	 */
 	if (!(flags & ST)) {
-		data.ll = 0;
-		ret = 0;
-		p = (unsigned long) addr;
+		unsigned int start = 0;
+
 		switch (nb) {
-		case 8:
-			ret |= __get_user_inatomic(data.v[0], SWIZ_PTR(p++));
-			ret |= __get_user_inatomic(data.v[1], SWIZ_PTR(p++));
-			ret |= __get_user_inatomic(data.v[2], SWIZ_PTR(p++));
-			ret |= __get_user_inatomic(data.v[3], SWIZ_PTR(p++));
 		case 4:
-			ret |= __get_user_inatomic(data.v[4], SWIZ_PTR(p++));
-			ret |= __get_user_inatomic(data.v[5], SWIZ_PTR(p++));
+			start = offsetof(union data, x32.low32);
+			break;
 		case 2:
-			ret |= __get_user_inatomic(data.v[6], SWIZ_PTR(p++));
-			ret |= __get_user_inatomic(data.v[7], SWIZ_PTR(p++));
-			if (unlikely(ret))
-				return -EFAULT;
+			start = offsetof(union data, x16.low16);
+			break;
 		}
+
+		data.ll = 0;
+		ret = 0;
+		p = (unsigned long)addr;
+
+		for (i = 0; i < nb; i++)
+			ret |= __get_user_inatomic(data.v[start + i],
+						   SWIZ_PTR(p++));
+
+		if (unlikely(ret))
+			return -EFAULT;
+
 	} else if (flags & F) {
-		data.dd = current->thread.TS_FPR(reg);
+		data.ll = current->thread.TS_FPR(reg);
 		if (flags & S) {
 			/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
 			preempt_disable();
 			enable_kernel_fp();
-			cvt_df(&data.dd, (float *)&data.v[4]);
+			cvt_df(&data.dd, (float *)&data.x32.low32);
 			preempt_enable();
 #else
 			return 0;
@@ -915,17 +967,13 @@ int fix_alignment(struct pt_regs *regs)
 	if (flags & SW) {
 		switch (nb) {
 		case 8:
-			SWAP(data.v[0], data.v[7]);
-			SWAP(data.v[1], data.v[6]);
-			SWAP(data.v[2], data.v[5]);
-			SWAP(data.v[3], data.v[4]);
+			data.ll = swab64(data.ll);
 			break;
 		case 4:
-			SWAP(data.v[4], data.v[7]);
-			SWAP(data.v[5], data.v[6]);
+			data.x32.low32 = swab32(data.x32.low32);
 			break;
 		case 2:
-			SWAP(data.v[6], data.v[7]);
+			data.x16.low16 = swab16(data.x16.low16);
 			break;
 		}
 	}
@@ -947,7 +995,7 @@ int fix_alignment(struct pt_regs *regs)
 #ifdef CONFIG_PPC_FPU
 		preempt_disable();
 		enable_kernel_fp();
-		cvt_fd((float *)&data.v[4], &data.dd);
+		cvt_fd((float *)&data.x32.low32, &data.dd);
 		preempt_enable();
 #else
 		return 0;
@@ -957,25 +1005,28 @@ int fix_alignment(struct pt_regs *regs)
 
 	/* Store result to memory or update registers */
 	if (flags & ST) {
-		ret = 0;
-		p = (unsigned long) addr;
+		unsigned int start = 0;
+
 		switch (nb) {
-		case 8:
-			ret |= __put_user_inatomic(data.v[0], SWIZ_PTR(p++));
-			ret |= __put_user_inatomic(data.v[1], SWIZ_PTR(p++));
-			ret |= __put_user_inatomic(data.v[2], SWIZ_PTR(p++));
-			ret |= __put_user_inatomic(data.v[3], SWIZ_PTR(p++));
 		case 4:
-			ret |= __put_user_inatomic(data.v[4], SWIZ_PTR(p++));
-			ret |= __put_user_inatomic(data.v[5], SWIZ_PTR(p++));
+			start = offsetof(union data, x32.low32);
+			break;
 		case 2:
-			ret |= __put_user_inatomic(data.v[6], SWIZ_PTR(p++));
-			ret |= __put_user_inatomic(data.v[7], SWIZ_PTR(p++));
+			start = offsetof(union data, x16.low16);
+			break;
 		}
+
+		ret = 0;
+		p = (unsigned long)addr;
+
+		for (i = 0; i < nb; i++)
+			ret |= __put_user_inatomic(data.v[start + i],
+						   SWIZ_PTR(p++));
+
 		if (unlikely(ret))
 			return -EFAULT;
 	} else if (flags & F)
-		current->thread.TS_FPR(reg) = data.dd;
+		current->thread.TS_FPR(reg) = data.ll;
 	else
 		regs->gpr[reg] = data.ll;