Linux 3.0.4

commit be27425dcc upstream.

I ran into a couple of programs which broke with the new Linux 3.0
version.  Some of those were binary only.  I tried to use LD_PRELOAD to
work around it, but it was quite difficult and in one case impossible
because of a mix of 32bit and 64bit executables.

For example, all kind of management software from HP doesnt work, unless
we pretend to run a 2.6 kernel.

  $ uname -a
  Linux svivoipvnx001 3.0.0-08107-g97cd98f #1062 SMP Fri Aug 12 18:11:45 CEST 2011 i686 i686 i386 GNU/Linux

  $ hpacucli ctrl all show

  Error: No controllers detected.

  $ rpm -qf /usr/sbin/hpacucli
  hpacucli-8.75-12.0

Another notable case is that Python now reports "linux3" from
sys.platform(); which in turn can break things that were checking
sys.platform() == "linux2":

  https://bugzilla.mozilla.org/show_bug.cgi?id=664564

It seems pretty clear to me though it's a bug in the apps that are using
'==' instead of .startswith(), but this allows us to unbreak broken
programs.

This patch adds a UNAME26 personality that makes the kernel report a
2.6.40+x version number instead.  The x is the x in 3.x.

I know this is somewhat ugly, but I didn't find a better workaround, and
compatibility to existing programs is important.

Some programs also read /proc/sys/kernel/osrelease.  This can be worked
around in user space with mount --bind (and a mount namespace)

To use:

  wget ftp://ftp.kernel.org/pub/linux/kernel/people/ak/uname26/uname26.c
  gcc -o uname26 uname26.c
  ./uname26 program

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Documentation/virtual/lguest/lguest.c

@@ -2008,6 +2008,9 @@ int main(int argc, char *argv[])
 	/* We use a simple helper to copy the arguments separated by spaces. */
 	concat((char *)(boot + 1), argv+optind+2);
 
+	/* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
+	boot->hdr.kernel_alignment = 0x1000000;
+
 	/* Boot protocol version: 2.07 supports the fields for lguest. */
 	boot->hdr.version = 0x207;
 

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 0
-SUBLEVEL = 0
+SUBLEVEL = 4
 EXTRAVERSION =
 NAME = Sneaky Weasel
 

arch/alpha/kernel/time.c

@@ -91,7 +91,7 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
 #define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
 
-void set_irq_work_pending(void)
+void arch_irq_work_raise(void)
 {
 	set_irq_work_pending_flag();
 }

arch/arm/mach-pxa/cm-x300.c

@@ -161,10 +161,10 @@ static mfp_cfg_t cm_x3xx_mfp_cfg[] __initdata = {
 	GPIO99_GPIO,			/* Ethernet IRQ */
 
 	/* RTC GPIOs */
-	GPIO95_GPIO,			/* RTC CS */
-	GPIO96_GPIO,			/* RTC WR */
-	GPIO97_GPIO,			/* RTC RD */
-	GPIO98_GPIO,			/* RTC IO */
+	GPIO95_GPIO | MFP_LPM_DRIVE_HIGH,	/* RTC CS */
+	GPIO96_GPIO | MFP_LPM_DRIVE_HIGH,	/* RTC WR */
+	GPIO97_GPIO | MFP_LPM_DRIVE_HIGH,	/* RTC RD */
+	GPIO98_GPIO,				/* RTC IO */
 
 	/* Standard I2C */
 	GPIO21_I2C_SCL,

arch/cris/arch-v10/drivers/sync_serial.c

@@ -158,7 +158,7 @@ static int sync_serial_open(struct inode *inode, struct file *file);
 static int sync_serial_release(struct inode *inode, struct file *file);
 static unsigned int sync_serial_poll(struct file *filp, poll_table *wait);
 
-static int sync_serial_ioctl(struct file *file,
+static long sync_serial_ioctl(struct file *file,
 	unsigned int cmd, unsigned long arg);
 static ssize_t sync_serial_write(struct file *file, const char *buf,
 	size_t count, loff_t *ppos);
@@ -625,11 +625,11 @@ static int sync_serial_open(struct inode *inode, struct file *file)
 			*R_IRQ_MASK1_SET = 1 << port->data_avail_bit;
 		DEBUG(printk(KERN_DEBUG "sser%d rec started\n", dev));
 	}
-	ret = 0;
+	err = 0;
 	
 out:
 	mutex_unlock(&sync_serial_mutex);
-	return ret;
+	return err;
 }
 
 static int sync_serial_release(struct inode *inode, struct file *file)

arch/cris/arch-v10/kernel/irq.c

@@ -20,6 +20,9 @@
 #define crisv10_mask_irq(irq_nr) (*R_VECT_MASK_CLR = 1 << (irq_nr));
 #define crisv10_unmask_irq(irq_nr) (*R_VECT_MASK_SET = 1 << (irq_nr));
 
+extern void kgdb_init(void);
+extern void breakpoint(void);
+
 /* don't use set_int_vector, it bypasses the linux interrupt handlers. it is
  * global just so that the kernel gdb can use it.
  */

arch/cris/include/asm/thread_info.h

@@ -11,8 +11,6 @@
 
 #ifdef __KERNEL__
 
-#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 #include <asm/processor.h>
@@ -67,8 +65,10 @@ struct thread_info {
 
 #define init_thread_info	(init_thread_union.thread_info)
 
+#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
 /* thread information allocation */
-#define alloc_thread_info(tsk, node) ((struct thread_info *) __get_free_pages(GFP_KERNEL,1))
+#define alloc_thread_info_node(tsk, node)	\
+	((struct thread_info *) __get_free_pages(GFP_KERNEL, 1))
 #define free_thread_info(ti) free_pages((unsigned long) (ti), 1)
 
 #endif /* !__ASSEMBLY__ */

arch/parisc/include/asm/atomic.h

@@ -259,10 +259,10 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
 
-static __inline__ int
+static __inline__ s64
 __atomic64_add_return(s64 i, atomic64_t *v)
 {
-	int ret;
+	s64 ret;
 	unsigned long flags;
 	_atomic_spin_lock_irqsave(v, flags);
 

arch/parisc/include/asm/futex.h

@@ -5,11 +5,14 @@
 
 #include <linux/futex.h>
 #include <linux/uaccess.h>
+#include <asm/atomic.h>
 #include <asm/errno.h>
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
+	unsigned long int flags;
+	u32 val;
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
@@ -18,21 +21,58 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)))
 		return -EFAULT;
 
 	pagefault_disable();
 
+	_atomic_spin_lock_irqsave(uaddr, flags);
+
 	switch (op) {
 	case FUTEX_OP_SET:
+		/* *(int *)UADDR2 = OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret)
+			ret = put_user(oparg, uaddr);
+		break;
 	case FUTEX_OP_ADD:
+		/* *(int *)UADDR2 += OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval + oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_OR:
+		/* *(int *)UADDR2 |= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval | oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_ANDN:
+		/* *(int *)UADDR2 &= ~OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval & ~oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_XOR:
+		/* *(int *)UADDR2 ^= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval ^ oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	default:
 		ret = -ENOSYS;
 	}
 
+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
 	pagefault_enable();
 
 	if (!ret) {
@@ -54,7 +94,9 @@ static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	int ret;
 	u32 val;
+	unsigned long flags;
 
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@@ -65,12 +107,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	if (get_user(val, uaddr))
-		return -EFAULT;
-	if (val == oldval && put_user(newval, uaddr))
-		return -EFAULT;
+	/* HPPA has no cmpxchg in hardware and therefore the
+	 * best we can do here is use an array of locks. The
+	 * lock selected is based on a hash of the userspace
+	 * address. This should scale to a couple of CPUs.
+	 */
+
+	_atomic_spin_lock_irqsave(uaddr, flags);
+
+	ret = get_user(val, uaddr);
+
+	if (!ret && val == oldval)
+		ret = put_user(newval, uaddr);
+
 	*uval = val;
-	return 0;
+
+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
+	return ret;
 }
 
 #endif /*__KERNEL__*/

arch/parisc/include/asm/unistd.h

@@ -821,8 +821,9 @@
 #define __NR_open_by_handle_at	(__NR_Linux + 326)
 #define __NR_syncfs		(__NR_Linux + 327)
 #define __NR_setns		(__NR_Linux + 328)
+#define __NR_sendmmsg		(__NR_Linux + 329)
 
-#define __NR_Linux_syscalls	(__NR_setns + 1)
+#define __NR_Linux_syscalls	(__NR_sendmmsg + 1)
 
 
 #define __IGNORE_select		/* newselect */

arch/parisc/kernel/syscall_table.S

@@ -427,6 +427,7 @@
 	ENTRY_COMP(open_by_handle_at)
 	ENTRY_SAME(syncfs)
 	ENTRY_SAME(setns)
+	ENTRY_COMP(sendmmsg)
 
 	/* Nothing yet */
 

arch/powerpc/kernel/crash.c

@@ -242,12 +242,8 @@ static void crash_kexec_wait_realmode(int cpu)
 
 		while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) {
 			barrier();
-			if (!cpu_possible(i)) {
+			if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0))
 				break;
-			}
-			if (!cpu_online(i)) {
-				break;
-			}
 			msecs--;
 			mdelay(1);
 		}

arch/powerpc/kernel/prom_init.c

@@ -1020,7 +1020,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
 	}
 	if (addr == 0)
 		return 0;
-	RELOC(alloc_bottom) = addr;
+	RELOC(alloc_bottom) = addr + size;
 
 	prom_debug(" -> %x\n", addr);
 	prom_debug("  alloc_bottom : %x\n", RELOC(alloc_bottom));
@@ -1834,7 +1834,7 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 		chunk = alloc_up(room, 0);
 		if (chunk == 0)
 			prom_panic("No memory for flatten_device_tree (claim failed)");
-		*mem_end = RELOC(alloc_top);
+		*mem_end = chunk + room;
 	}
 
 	ret = (void *)*mem_start;
@@ -2053,7 +2053,7 @@ static void __init flatten_device_tree(void)
 	mem_start = (unsigned long)alloc_up(room, PAGE_SIZE);
 	if (mem_start == 0)
 		prom_panic("Can't allocate initial device-tree chunk\n");
-	mem_end = RELOC(alloc_top);
+	mem_end = mem_start + room;
 
 	/* Get root of tree */
 	root = call_prom("peer", 1, 1, (phandle)0);

arch/powerpc/kernel/time.c

@@ -544,7 +544,7 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 
 #endif /* 32 vs 64 bit */
 
-void set_irq_work_pending(void)
+void arch_irq_work_raise(void)
 {
 	preempt_disable();
 	set_irq_work_pending_flag();

arch/powerpc/platforms/pseries/dtl.c

@@ -181,7 +181,7 @@ static void dtl_stop(struct dtl *dtl)
 
 	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
-	unregister_dtl(hwcpu, __pa(dtl->buf));
+	unregister_dtl(hwcpu);
 }
 
 static u64 dtl_current_index(struct dtl *dtl)

arch/powerpc/platforms/pseries/hvconsole.c

@@ -73,7 +73,7 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
 	if (ret == H_SUCCESS)
 		return count;
 	if (ret == H_BUSY)
-		return 0;
+		return -EAGAIN;
 	return -EIO;
 }
 

arch/powerpc/platforms/pseries/kexec.c

@@ -26,6 +26,17 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 	/* Don't risk a hypervisor call if we're crashing */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
 		unsigned long addr;
+		int ret;
+
+		if (get_lppaca()->dtl_enable_mask) {
+			ret = unregister_dtl(hard_smp_processor_id());
+			if (ret) {
+				pr_err("WARNING: DTL deregistration for cpu "
+				       "%d (hw %d) failed with %d\n",
+				       smp_processor_id(),
+				       hard_smp_processor_id(), ret);
+			}
+		}
 
 		addr = __pa(get_slb_shadow());
 		if (unregister_slb_shadow(hard_smp_processor_id(), addr))

arch/powerpc/platforms/pseries/lpar.c

@@ -395,7 +395,7 @@ static void pSeries_lpar_hptab_clear(void)
 		unsigned long ptel;
 	} ptes[4];
 	long lpar_rc;
-	int i, j;
+	unsigned long i, j;
 
 	/* Read in batches of 4,
 	 * invalidate only valid entries not in the VRMA

arch/powerpc/platforms/pseries/plpar_wrappers.h

@@ -73,9 +73,9 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x3, cpu, vpa);
 }
 
-static inline long unregister_dtl(unsigned long cpu, unsigned long vpa)
+static inline long unregister_dtl(unsigned long cpu)
 {
-	return vpa_call(0x6, cpu, vpa);
+	return vpa_call(0x6, cpu, 0);
 }
 
 static inline long register_dtl(unsigned long cpu, unsigned long vpa)

arch/sparc/include/asm/bitops_64.h

@@ -26,61 +26,28 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()
 
-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #ifdef __KERNEL__
 
+extern int ffs(int x);
+extern unsigned long __ffs(unsigned long);
+
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
 
 /*
  * hweightN: returns the hamming weight (i.e. the number
  * of bits set) of a N-bit word
  */
 
-#ifdef ULTRA_HAS_POPULATION_COUNT
+extern unsigned long __arch_hweight64(__u64 w);
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
 
-static inline unsigned int __arch_hweight64(unsigned long w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w));
-	return res;
-}
-
-static inline unsigned int __arch_hweight32(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff));
-	return res;
-}
-
-static inline unsigned int __arch_hweight16(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff));
-	return res;
-}
-
-static inline unsigned int __arch_hweight8(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff));
-	return res;
-}
-
-#else
-
-#include <asm-generic/bitops/arch_hweight.h>
-
-#endif
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */

arch/sparc/include/asm/elf_64.h

@@ -59,15 +59,33 @@
 #define R_SPARC_6		45
 
 /* Bits present in AT_HWCAP, primarily for Sparc32.  */
+#define HWCAP_SPARC_FLUSH       0x00000001
+#define HWCAP_SPARC_STBAR       0x00000002
+#define HWCAP_SPARC_SWAP        0x00000004
+#define HWCAP_SPARC_MULDIV      0x00000008
+#define HWCAP_SPARC_V9		0x00000010
+#define HWCAP_SPARC_ULTRA3	0x00000020
+#define HWCAP_SPARC_BLKINIT	0x00000040
+#define HWCAP_SPARC_N2		0x00000080
 
-#define HWCAP_SPARC_FLUSH       1    /* CPU supports flush instruction. */
-#define HWCAP_SPARC_STBAR       2
-#define HWCAP_SPARC_SWAP        4
-#define HWCAP_SPARC_MULDIV      8
-#define HWCAP_SPARC_V9		16
-#define HWCAP_SPARC_ULTRA3	32
-#define HWCAP_SPARC_BLKINIT	64
-#define HWCAP_SPARC_N2		128
+/* Solaris compatible AT_HWCAP bits. */
+#define AV_SPARC_MUL32		0x00000100 /* 32x32 multiply is efficient */
+#define AV_SPARC_DIV32		0x00000200 /* 32x32 divide is efficient */
+#define AV_SPARC_FSMULD		0x00000400 /* 'fsmuld' is efficient */
+#define AV_SPARC_V8PLUS		0x00000800 /* v9 insn available to 32bit */
+#define AV_SPARC_POPC		0x00001000 /* 'popc' is efficient */
+#define AV_SPARC_VIS		0x00002000 /* VIS insns available */
+#define AV_SPARC_VIS2		0x00004000 /* VIS2 insns available */
+#define AV_SPARC_ASI_BLK_INIT	0x00008000 /* block init ASIs available */
+#define AV_SPARC_FMAF		0x00010000 /* fused multiply-add */
+#define AV_SPARC_VIS3		0x00020000 /* VIS3 insns available */
+#define AV_SPARC_HPC		0x00040000 /* HPC insns available */
+#define AV_SPARC_RANDOM		0x00080000 /* 'random' insn available */
+#define AV_SPARC_TRANS		0x00100000 /* transaction insns available */
+#define AV_SPARC_FJFMAU		0x00200000 /* unfused multiply-add */
+#define AV_SPARC_IMA		0x00400000 /* integer multiply-add */
+#define AV_SPARC_ASI_CACHE_SPARING \
+				0x00800000 /* cache sparing ASIs available */
 
 #define CORE_DUMP_USE_REGSET
 
@@ -162,31 +180,8 @@ typedef struct {
 #define ELF_ET_DYN_BASE		0x0000010000000000UL
 #define COMPAT_ELF_ET_DYN_BASE	0x0000000070000000UL
 
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-/* On Ultra, we support all of the v8 capabilities. */
-static inline unsigned int sparc64_elf_hwcap(void)
-{
-	unsigned int cap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
-			    HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
-			    HWCAP_SPARC_V9);
-
-	if (tlb_type == cheetah || tlb_type == cheetah_plus)
-		cap |= HWCAP_SPARC_ULTRA3;
-	else if (tlb_type == hypervisor) {
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2)
-			cap |= HWCAP_SPARC_BLKINIT;
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2)
-			cap |= HWCAP_SPARC_N2;
-	}
-
-	return cap;
-}
-
-#define ELF_HWCAP	sparc64_elf_hwcap();
+extern unsigned long sparc64_elf_hwcap;
+#define ELF_HWCAP	sparc64_elf_hwcap
 
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in

arch/sparc/include/asm/hypervisor.h

@@ -2927,6 +2927,13 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_FAST_FIRE_GET_PERFREG	0x120
 #define HV_FAST_FIRE_SET_PERFREG	0x121
 
+#define HV_FAST_REBOOT_DATA_SET		0x172
+
+#ifndef __ASSEMBLY__
+extern unsigned long sun4v_reboot_data_set(unsigned long ra,
+					   unsigned long len);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2940,16 +2947,23 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_GRP_CORE			0x0001
 #define HV_GRP_INTR			0x0002
 #define HV_GRP_SOFT_STATE		0x0003
+#define HV_GRP_TM			0x0080
 #define HV_GRP_PCI			0x0100
 #define HV_GRP_LDOM			0x0101
 #define HV_GRP_SVC_CHAN			0x0102
 #define HV_GRP_NCS			0x0103
 #define HV_GRP_RNG			0x0104
+#define HV_GRP_PBOOT			0x0105
+#define HV_GRP_TPM			0x0107
+#define HV_GRP_SDIO			0x0108
+#define HV_GRP_SDIO_ERR			0x0109
+#define HV_GRP_REBOOT_DATA		0x0110
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
 #define HV_GRP_N2_CPU			0x0202
 #define HV_GRP_NIU			0x0204
 #define HV_GRP_VF_CPU			0x0205
+#define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__

arch/sparc/include/asm/spitfire.h

@@ -42,6 +42,7 @@
 #define SUN4V_CHIP_INVALID	0x00
 #define SUN4V_CHIP_NIAGARA1	0x01
 #define SUN4V_CHIP_NIAGARA2	0x02
+#define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_UNKNOWN	0xff
 
 #ifndef __ASSEMBLY__

arch/sparc/include/asm/tsb.h

@@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);
 
-#define KTSB_LOAD_QUAD(TSB, REG) \
-	ldda		[TSB] ASI_NUCLEUS_QUAD_LDD, REG;
-
-#define KTSB_STORE(ADDR, VAL) \
-	stxa		VAL, [ADDR] ASI_N;
-
-#define KTSB_LOCK_TAG(TSB, REG1, REG2)	\
-99:	lduwa	[TSB] ASI_N, REG1;	\
-	sethi	%hi(TSB_TAG_LOCK_HIGH), REG2;\
-	andcc	REG1, REG2, %g0;	\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-	casa	[TSB] ASI_N, REG1, REG2;\
-	cmp	REG1, REG2;		\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-
-#define KTSB_WRITE(TSB, TTE, TAG) \
-	add	TSB, 0x8, TSB;   \
-	stxa	TTE, [TSB] ASI_N;     \
-	sub	TSB, 0x8, TSB;   \
-	stxa	TAG, [TSB] ASI_N;
-
 	/* Do a kernel page table walk.  Leaves physical PTE pointer in
 	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
 	 * VADDR will not be clobbered, but REG2 will.
@@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096
 
+#define KTSB_PHYS_SHIFT		15
+
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_tsb), REG1; \
+661:	sethi		%hi(swapper_tsb), REG1;			\
 	or		REG1, %lo(swapper_tsb), REG1; \
+	.section	.swapper_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;
@@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_4m_tsb), REG1; \
+661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
 	or		REG1, %lo(swapper_4m_tsb), REG1; \
+	.section	.swapper_4m_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;

arch/sparc/include/asm/xor_64.h

@@ -65,6 +65,7 @@ static struct xor_block_template xor_block_niagara = {
 #define XOR_SELECT_TEMPLATE(FASTEST) \
 	((tlb_type == hypervisor && \
 	  (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \
-	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2)) ? \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3)) ? \
 	 &xor_block_niagara : \
 	 &xor_block_VIS)

arch/sparc/kernel/cpu.c

@@ -396,6 +396,7 @@ static int show_cpuinfo(struct seq_file *m, void *__unused)
 		   , cpu_data(0).clock_tick
 #endif
 		);
+	cpucap_info(m);
 #ifdef CONFIG_SMP
 	smp_bogo(m);
 #endif
@@ -474,11 +475,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara2";
 		break;
 
+	case SUN4V_CHIP_NIAGARA3:
+		sparc_cpu_type = "UltraSparc T3 (Niagara3)";
+		sparc_fpu_type = "UltraSparc T3 integrated FPU";
+		sparc_pmu_type = "niagara3";
+		break;
+
 	default:
 		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
 		       prom_cpu_compatible);
 		sparc_cpu_type = "Unknown SUN4V CPU";
 		sparc_fpu_type = "Unknown SUN4V FPU";
+		sparc_pmu_type = "Unknown SUN4V PMU";
 		break;
 	}
 }

arch/sparc/kernel/cpumap.c

@@ -324,6 +324,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_NIAGARA1:
 	case SUN4V_CHIP_NIAGARA2:
+	case SUN4V_CHIP_NIAGARA3:
 		rover_inc_table = niagara_iterate_method;
 		break;
 	default:

arch/sparc/kernel/ds.c

@@ -15,12 +15,15 @@
 #include <linux/reboot.h>
 #include <linux/cpu.h>
 
+#include <asm/hypervisor.h>
 #include <asm/ldc.h>
 #include <asm/vio.h>
 #include <asm/mdesc.h>
 #include <asm/head.h>
 #include <asm/irq.h>
 
+#include "kernel.h"
+
 #define DRV_MODULE_NAME		"ds"
 #define PFX DRV_MODULE_NAME	": "
 #define DRV_MODULE_VERSION	"1.0"
@@ -828,18 +831,32 @@ void ldom_set_var(const char *var, const char *value)
 	}
 }
 
+static char full_boot_str[256] __attribute__((aligned(32)));
+static int reboot_data_supported;
+
 void ldom_reboot(const char *boot_command)
 {
 	/* Don't bother with any of this if the boot_command
 	 * is empty.
 	 */
 	if (boot_command && strlen(boot_command)) {
-		char full_boot_str[256];
+		unsigned long len;
 
 		strcpy(full_boot_str, "boot ");
 		strcpy(full_boot_str + strlen("boot "), boot_command);
+		len = strlen(full_boot_str);
 
-		ldom_set_var("reboot-command", full_boot_str);
+		if (reboot_data_supported) {
+			unsigned long ra = kimage_addr_to_ra(full_boot_str);
+			unsigned long hv_ret;
+
+			hv_ret = sun4v_reboot_data_set(ra, len);
+			if (hv_ret != HV_EOK)
+				pr_err("SUN4V: Unable to set reboot data "
+				       "hv_ret=%lu\n", hv_ret);
+		} else {
+			ldom_set_var("reboot-command", full_boot_str);
+		}
 	}
 	sun4v_mach_sir();
 }
@@ -1237,6 +1254,16 @@ static struct vio_driver ds_driver = {
 
 static int __init ds_init(void)
 {
+	unsigned long hv_ret, major, minor;
+
+	if (tlb_type == hypervisor) {
+		hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
+		if (hv_ret == HV_EOK) {
+			pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
+				major, minor);
+			reboot_data_supported = 1;
+		}
+	}
 	kthread_run(ds_thread, NULL, "kldomd");
 
 	return vio_register_driver(&ds_driver);

arch/sparc/kernel/entry.h

@@ -42,6 +42,20 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+struct popc_3insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[3];
+};
+extern struct popc_3insn_patch_entry __popc_3insn_patch,
+	__popc_3insn_patch_end;
+
+struct popc_6insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[6];
+};
+extern struct popc_6insn_patch_entry __popc_6insn_patch,
+	__popc_6insn_patch_end;
+
 extern void __init per_cpu_patch(void);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);

arch/sparc/kernel/head_64.S

@@ -132,6 +132,8 @@ prom_sun4v_name:
 	.asciz	"sun4v"
 prom_niagara_prefix:
 	.asciz	"SUNW,UltraSPARC-T"
+prom_sparc_prefix:
+	.asciz	"SPARC-T"
 	.align	4
 prom_root_compatible:
 	.skip	64
@@ -379,6 +381,22 @@ sun4v_chip_type:
 	sethi	%hi(prom_niagara_prefix), %g7
 	or	%g7, %lo(prom_niagara_prefix), %g7
 	mov	17, %g3
+90:	ldub	[%g7], %g2
+	ldub	[%g1], %g4
+	cmp	%g2, %g4
+	bne,pn	%icc, 89f
+	 add	%g7, 1, %g7
+	subcc	%g3, 1, %g3
+	bne,pt	%xcc, 90b
+	 add	%g1, 1, %g1
+	ba,pt	%xcc, 91f
+	 nop
+
+89:	sethi	%hi(prom_cpu_compatible), %g1
+	or	%g1, %lo(prom_cpu_compatible), %g1
+	sethi	%hi(prom_sparc_prefix), %g7
+	or	%g7, %lo(prom_sparc_prefix), %g7
+	mov	7, %g3
 90:	ldub	[%g7], %g2
 	ldub	[%g1], %g4
 	cmp	%g2, %g4
@@ -389,6 +407,15 @@ sun4v_chip_type:
 	 add	%g1, 1, %g1
 
 	sethi	%hi(prom_cpu_compatible), %g1
+	or	%g1, %lo(prom_cpu_compatible), %g1
+	ldub	[%g1 + 7], %g2
+	cmp	%g2, '3'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA3, %g4
+	ba,pt	%xcc, 4f
+	 nop
+
+91:	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
 	ldub	[%g1 + 17], %g2
 	cmp	%g2, '1'
@@ -397,6 +424,7 @@ sun4v_chip_type:
 	cmp	%g2, '2'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA2, %g4
+
 4:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
 5:	sethi	%hi(sun4v_chip_type), %g2
@@ -514,6 +542,9 @@ niagara_tlb_fixup:
 	 cmp	%g1, SUN4V_CHIP_NIAGARA2
 	be,pt	%xcc, niagara2_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA3
+	be,pt	%xcc, niagara2_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
@@ -528,7 +559,7 @@ niagara2_patch:
 	 nop
 	call	niagara_patch_bzero
 	 nop
-	call	niagara2_patch_pageops
+	call	niagara_patch_pageops
 	 nop
 
 	ba,a,pt	%xcc, 80f

arch/sparc/kernel/hvapi.c

@@ -28,16 +28,23 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_CORE,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_INTR,					},
 	{ .group = HV_GRP_SOFT_STATE,				},
+	{ .group = HV_GRP_TM,					},
 	{ .group = HV_GRP_PCI,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_LDOM,					},
 	{ .group = HV_GRP_SVC_CHAN,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_NCS,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_RNG,					},
+	{ .group = HV_GRP_PBOOT,				},
+	{ .group = HV_GRP_TPM,					},
+	{ .group = HV_GRP_SDIO,					},
+	{ .group = HV_GRP_SDIO_ERR,				},
+	{ .group = HV_GRP_REBOOT_DATA,				},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},
 	{ .group = HV_GRP_NIU,					},
 	{ .group = HV_GRP_VF_CPU,				},
+	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 

arch/sparc/kernel/hvcalls.S

@@ -798,3 +798,10 @@ ENTRY(sun4v_niagara2_setperf)
 	retl
 	 nop
 ENDPROC(sun4v_niagara2_setperf)
+
+ENTRY(sun4v_reboot_data_set)
+	mov	HV_FAST_REBOOT_DATA_SET, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_reboot_data_set)

arch/sparc/kernel/kernel.h

@@ -4,12 +4,27 @@
 #include <linux/interrupt.h>
 
 #include <asm/traps.h>
+#include <asm/head.h>
+#include <asm/io.h>
 
 /* cpu.c */
 extern const char *sparc_pmu_type;
 extern unsigned int fsr_storage;
 extern int ncpus_probed;
 
+#ifdef CONFIG_SPARC64
+/* setup_64.c */
+struct seq_file;
+extern void cpucap_info(struct seq_file *);
+
+static inline unsigned long kimage_addr_to_ra(const char *p)
+{
+	unsigned long val = (unsigned long) p;
+
+	return kern_base + (val - KERNBASE);
+}
+#endif
+
 #ifdef CONFIG_SPARC32
 /* cpu.c */
 extern void cpu_probe(void);

arch/sparc/kernel/ktlb.S

@@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss:
 kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
 
@@ -102,9 +102,9 @@ kvmap_itlb_longpath:
 kvmap_itlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	ba,pt		%xcc, kvmap_itlb_load
 	 nop
@@ -112,17 +112,17 @@ kvmap_itlb_obp:
 kvmap_dtlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
 	.align		32
 kvmap_dtlb_tsb4m_load:
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_WRITE(%g1, %g5, %g6)
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
@@ -222,16 +222,16 @@ kvmap_linear_patch:
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
 

arch/sparc/kernel/mdesc.c

@@ -508,6 +508,8 @@ const char *mdesc_node_name(struct mdesc_handle *hp, u64 node)
 }
 EXPORT_SYMBOL(mdesc_node_name);
 
+static u64 max_cpus = 64;
+
 static void __init report_platform_properties(void)
 {
 	struct mdesc_handle *hp = mdesc_grab();
@@ -543,8 +545,10 @@ static void __init report_platform_properties(void)
 	if (v)
 		printk("PLATFORM: watchdog-max-timeout [%llu ms]\n", *v);
 	v = mdesc_get_property(hp, pn, "max-cpus", NULL);
-	if (v)
-		printk("PLATFORM: max-cpus [%llu]\n", *v);
+	if (v) {
+		max_cpus = *v;
+		printk("PLATFORM: max-cpus [%llu]\n", max_cpus);
+	}
 
 #ifdef CONFIG_SMP
 	{
@@ -715,7 +719,7 @@ static void __cpuinit set_proc_ids(struct mdesc_handle *hp)
 }
 
 static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
-					 unsigned char def)
+					 unsigned long def, unsigned long max)
 {
 	u64 val;
 
@@ -726,6 +730,9 @@ static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
 	if (!val || val >= 64)
 		goto use_default;
 
+	if (val > max)
+		val = max;
+
 	*mask = ((1U << val) * 64U) - 1U;
 	return;
 
@@ -736,19 +743,28 @@ use_default:
 static void __cpuinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
 				     struct trap_per_cpu *tb)
 {
+	static int printed;
 	const u64 *val;
 
 	val = mdesc_get_property(hp, mp, "q-cpu-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7, ilog2(max_cpus * 2));
 
 	val = mdesc_get_property(hp, mp, "q-dev-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7, 8);
 
 	val = mdesc_get_property(hp, mp, "q-resumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->resum_qmask, 6);
+	get_one_mondo_bits(val, &tb->resum_qmask, 6, 7);
 
 	val = mdesc_get_property(hp, mp, "q-nonresumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->nonresum_qmask, 2);
+	get_one_mondo_bits(val, &tb->nonresum_qmask, 2, 2);
+	if (!printed++) {
+		pr_info("SUN4V: Mondo queue sizes "
+			"[cpu(%u) dev(%u) r(%u) nr(%u)]\n",
+			tb->cpu_mondo_qmask + 1,
+			tb->dev_mondo_qmask + 1,
+			tb->resum_qmask + 1,
+			tb->nonresum_qmask + 1);
+	}
 }
 
 static void * __cpuinit mdesc_iterate_over_cpus(void *(*func)(struct mdesc_handle *, u64, int, void *), void *arg, cpumask_t *mask)

arch/sparc/kernel/pcr.c

@@ -80,8 +80,11 @@ static void n2_pcr_write(u64 val)
 {
 	unsigned long ret;
 
-	ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
-	if (ret != HV_EOK)
+	if (val & PCR_N2_HTRACE) {
+		ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
+		if (ret != HV_EOK)
+			write_pcr(val);
+	} else
 		write_pcr(val);
 }
 
@@ -106,6 +109,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_N2_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA3:
+			perf_hsvc_group = HV_GRP_KT_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}

arch/sparc/kernel/perf_event.c

@@ -1301,7 +1301,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara1_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara2")) {
+	if (!strcmp(sparc_pmu_type, "niagara2") ||
+	    !strcmp(sparc_pmu_type, "niagara3")) {
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}

arch/sparc/kernel/setup_64.c

@@ -29,6 +29,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/initrd.h>
+#include <linux/module.h>
 
 #include <asm/system.h>
 #include <asm/io.h>
@@ -46,6 +47,8 @@
 #include <asm/mmu.h>
 #include <asm/ns87303.h>
 #include <asm/btext.h>
+#include <asm/elf.h>
+#include <asm/mdesc.h>
 
 #ifdef CONFIG_IP_PNP
 #include <net/ipconfig.h>
@@ -269,6 +272,40 @@ void __init sun4v_patch(void)
 	sun4v_hvapi_init();
 }
 
+static void __init popc_patch(void)
+{
+	struct popc_3insn_patch_entry *p3;
+	struct popc_6insn_patch_entry *p6;
+
+	p3 = &__popc_3insn_patch;
+	while (p3 < &__popc_3insn_patch_end) {
+		unsigned long i, addr = p3->addr;
+
+		for (i = 0; i < 3; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p3->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p3++;
+	}
+
+	p6 = &__popc_6insn_patch;
+	while (p6 < &__popc_6insn_patch_end) {
+		unsigned long i, addr = p6->addr;
+
+		for (i = 0; i < 6; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p6->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p6++;
+	}
+}
+
 #ifdef CONFIG_SMP
 void __init boot_cpu_id_too_large(int cpu)
 {
@@ -278,6 +315,154 @@ void __init boot_cpu_id_too_large(int cpu)
 }
 #endif
 
+/* On Ultra, we support all of the v8 capabilities. */
+unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
+				   HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
+				   HWCAP_SPARC_V9);
+EXPORT_SYMBOL(sparc64_elf_hwcap);
+
+static const char *hwcaps[] = {
+	"flush", "stbar", "swap", "muldiv", "v9",
+	"ultra3", "blkinit", "n2",
+
+	/* These strings are as they appear in the machine description
+	 * 'hwcap-list' property for cpu nodes.
+	 */
+	"mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2",
+	"ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau",
+	"ima", "cspare",
+};
+
+void cpucap_info(struct seq_file *m)
+{
+	unsigned long caps = sparc64_elf_hwcap;
+	int i, printed = 0;
+
+	seq_puts(m, "cpucaps\t\t: ");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			seq_printf(m, "%s%s",
+				   printed ? "," : "", hwcaps[i]);
+			printed++;
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static void __init report_hwcaps(unsigned long caps)
+{
+	int i, printed = 0;
+
+	printk(KERN_INFO "CPU CAPS: [");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			printk(KERN_CONT "%s%s",
+			       printed ? "," : "", hwcaps[i]);
+			if (++printed == 8) {
+				printk(KERN_CONT "]\n");
+				printk(KERN_INFO "CPU CAPS: [");
+				printed = 0;
+			}
+		}
+	}
+	printk(KERN_CONT "]\n");
+}
+
+static unsigned long __init mdesc_cpu_hwcap_list(void)
+{
+	struct mdesc_handle *hp;
+	unsigned long caps = 0;
+	const char *prop;
+	int len;
+	u64 pn;
+
+	hp = mdesc_grab();
+	if (!hp)
+		return 0;
+
+	pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "cpu");
+	if (pn == MDESC_NODE_NULL)
+		goto out;
+
+	prop = mdesc_get_property(hp, pn, "hwcap-list", &len);
+	if (!prop)
+		goto out;
+
+	while (len) {
+		int i, plen;
+
+		for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+			unsigned long bit = 1UL << i;
+
+			if (!strcmp(prop, hwcaps[i])) {
+				caps |= bit;
+				break;
+			}
+		}
+
+		plen = strlen(prop) + 1;
+		prop += plen;
+		len -= plen;
+	}
+
+out:
+	mdesc_release(hp);
+	return caps;
+}
+
+/* This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+static void __init init_sparc64_elf_hwcap(void)
+{
+	unsigned long cap = sparc64_elf_hwcap;
+	unsigned long mdesc_caps;
+
+	if (tlb_type == cheetah || tlb_type == cheetah_plus)
+		cap |= HWCAP_SPARC_ULTRA3;
+	else if (tlb_type == hypervisor) {
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_BLKINIT;
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_N2;
+	}
+
+	cap |= (AV_SPARC_MUL32 | AV_SPARC_DIV32 | AV_SPARC_V8PLUS);
+
+	mdesc_caps = mdesc_cpu_hwcap_list();
+	if (!mdesc_caps) {
+		if (tlb_type == spitfire)
+			cap |= AV_SPARC_VIS;
+		if (tlb_type == cheetah || tlb_type == cheetah_plus)
+			cap |= AV_SPARC_VIS | AV_SPARC_VIS2;
+		if (tlb_type == cheetah_plus)
+			cap |= AV_SPARC_POPC;
+		if (tlb_type == hypervisor) {
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1)
+				cap |= AV_SPARC_ASI_BLK_INIT;
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
+					AV_SPARC_ASI_BLK_INIT |
+					AV_SPARC_POPC);
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
+					AV_SPARC_FMAF);
+		}
+	}
+	sparc64_elf_hwcap = cap | mdesc_caps;
+
+	report_hwcaps(sparc64_elf_hwcap);
+
+	if (sparc64_elf_hwcap & AV_SPARC_POPC)
+		popc_patch();
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
@@ -337,6 +522,7 @@ void __init setup_arch(char **cmdline_p)
 	init_cur_cpu_trap(current_thread_info());
 
 	paging_init();
+	init_sparc64_elf_hwcap();
 }
 
 extern int stop_a_enabled;

arch/sparc/kernel/sparc_ksyms_64.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/bitops.h>
 
 #include <asm/system.h>
 #include <asm/cpudata.h>
@@ -38,5 +39,15 @@ EXPORT_SYMBOL(sun4v_niagara_setperf);
 EXPORT_SYMBOL(sun4v_niagara2_getperf);
 EXPORT_SYMBOL(sun4v_niagara2_setperf);
 
+/* from hweight.S */
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+
+/* from ffs_ffz.S */
+EXPORT_SYMBOL(ffs);
+EXPORT_SYMBOL(__ffs);
+
 /* Exporting a symbol from /init/main.c */
 EXPORT_SYMBOL(saved_command_line);

arch/sparc/kernel/sstate.c

@@ -14,15 +14,10 @@
 #include <asm/head.h>
 #include <asm/io.h>
 
+#include "kernel.h"
+
 static int hv_supports_soft_state;
 
-static unsigned long kimage_addr_to_ra(const char *p)
-{
-	unsigned long val = (unsigned long) p;
-
-	return kern_base + (val - KERNBASE);
-}
-
 static void do_set_sstate(unsigned long state, const char *msg)
 {
 	unsigned long err;

arch/sparc/kernel/unaligned_64.c

@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
 #include <linux/ratelimit.h>
+#include <linux/bitops.h>
 #include <asm/fpumacro.h>
 
 enum direction {
@@ -373,16 +374,11 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 	}
 }
 
-static char popc_helper[] = {
-0, 1, 1, 2, 1, 2, 2, 3,
-1, 2, 2, 3, 2, 3, 3, 4, 
-};
-
 int handle_popc(u32 insn, struct pt_regs *regs)
 {
-	u64 value;
-	int ret, i, rd = ((insn >> 25) & 0x1f);
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	int ret, rd = ((insn >> 25) & 0x1f);
+	u64 value;
 	                        
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
 	if (insn & 0x2000) {
@@ -392,10 +388,7 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 		maybe_flush_windows(0, insn & 0x1f, rd, from_kernel);
 		value = fetch_reg(insn & 0x1f, regs);
 	}
-	for (ret = 0, i = 0; i < 16; i++) {
-		ret += popc_helper[value & 0xf];
-		value >>= 4;
-	}
+	ret = hweight64(value);
 	if (rd < 16) {
 		if (rd)
 			regs->u_regs[rd] = ret;

arch/sparc/kernel/vmlinux.lds.S

@@ -107,7 +107,26 @@ SECTIONS
 		*(.sun4v_2insn_patch)
 		__sun4v_2insn_patch_end = .;
 	}
-
+	.swapper_tsb_phys_patch : {
+		__swapper_tsb_phys_patch = .;
+		*(.swapper_tsb_phys_patch)
+		__swapper_tsb_phys_patch_end = .;
+	}
+	.swapper_4m_tsb_phys_patch : {
+		__swapper_4m_tsb_phys_patch = .;
+		*(.swapper_4m_tsb_phys_patch)
+		__swapper_4m_tsb_phys_patch_end = .;
+	}
+	.popc_3insn_patch : {
+		__popc_3insn_patch = .;
+		*(.popc_3insn_patch)
+		__popc_3insn_patch_end = .;
+	}
+	.popc_6insn_patch : {
+		__popc_6insn_patch = .;
+		*(.popc_6insn_patch)
+		__popc_6insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);

arch/sparc/lib/Makefile

@@ -31,13 +31,13 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o
 lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o
 
 lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
-lib-$(CONFIG_SPARC64) +=  NG2patch.o NG2page.o
+lib-$(CONFIG_SPARC64) +=  NG2patch.o
 
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 
 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
-lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
 obj-y                 += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o

arch/sparc/lib/NG2page.S

@@ -1,61 +0,0 @@
-/* NG2page.S: Niagara-2 optimized clear and copy page.
- *
- * Copyright (C) 2007 (davem@davemloft.net)
- */
-
-#include <asm/asi.h>
-#include <asm/page.h>
-#include <asm/visasm.h>
-
-	.text
-	.align	32
-
-	/* This is heavily simplified from the sun4u variants
-	 * because Niagara-2 does not have any D-cache aliasing issues.
-	 */
-NG2copy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	prefetch	[%o1 + 0x40], #one_read
-	VISEntryHalf
-	set		PAGE_SIZE, %g7
-	sub		%o0, %o1, %g3
-1:	stxa		%g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
-	ldda		[%o1] ASI_BLK_P, %f0
-	stda		%f0, [%o1 + %g3] ASI_BLK_P
-	add		%o1, 64, %o1
-	bne,pt		%xcc, 1b
-	 prefetch	[%o1 + 0x40], #one_read
-	membar		#Sync
-	VISExitHalf
-	retl
-	 nop
-
-#define BRANCH_ALWAYS	0x10680000
-#define NOP		0x01000000
-#define NG_DO_PATCH(OLD, NEW)	\
-	sethi	%hi(NEW), %g1; \
-	or	%g1, %lo(NEW), %g1; \
-	sethi	%hi(OLD), %g2; \
-	or	%g2, %lo(OLD), %g2; \
-	sub	%g1, %g2, %g1; \
-	sethi	%hi(BRANCH_ALWAYS), %g3; \
-	sll	%g1, 11, %g1; \
-	srl	%g1, 11 + 2, %g1; \
-	or	%g3, %lo(BRANCH_ALWAYS), %g3; \
-	or	%g3, %g1, %g3; \
-	stw	%g3, [%g2]; \
-	sethi	%hi(NOP), %g3; \
-	or	%g3, %lo(NOP), %g3; \
-	stw	%g3, [%g2 + 0x4]; \
-	flush	%g2;
-
-	.globl	niagara2_patch_pageops
-	.type	niagara2_patch_pageops,#function
-niagara2_patch_pageops:
-	NG_DO_PATCH(copy_user_page, NG2copy_user_page)
-	NG_DO_PATCH(_clear_page, NGclear_page)
-	NG_DO_PATCH(clear_user_page, NGclear_user_page)
-	retl
-	 nop
-	.size	niagara2_patch_pageops,.-niagara2_patch_pageops

arch/sparc/lib/NGpage.S

@@ -16,55 +16,91 @@
 	 */
 
 NGcopy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	save		%sp, -192, %sp
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7
+	prefetch	[%i1 + 0x00], #one_read
+	prefetch	[%i1 + 0x40], #one_read
 
-1:	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	prefetch	[%o1 + 0x40], #one_read
-	add		%o1, 32, %o1
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	add		%o1, 32, %o1
-	add		%o0, 32, %o0
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	prefetch	[%i1 + 0x80], #one_read
+	prefetch	[%i1 + 0xc0], #one_read
+	ldda		[%i1 + 0x00] %asi, %o2
+	ldda		[%i1 + 0x10] %asi, %o4
+	ldda		[%i1 + 0x20] %asi, %l2
+	ldda		[%i1 + 0x30] %asi, %l4
+	stxa		%o2, [%i0 + 0x00] %asi
+	stxa		%o3, [%i0 + 0x08] %asi
+	stxa		%o4, [%i0 + 0x10] %asi
+	stxa		%o5, [%i0 + 0x18] %asi
+	stxa		%l2, [%i0 + 0x20] %asi
+	stxa		%l3, [%i0 + 0x28] %asi
+	stxa		%l4, [%i0 + 0x30] %asi
+	stxa		%l5, [%i0 + 0x38] %asi
+	ldda		[%i1 + 0x40] %asi, %o2
+	ldda		[%i1 + 0x50] %asi, %o4
+	ldda		[%i1 + 0x60] %asi, %l2
+	ldda		[%i1 + 0x70] %asi, %l4
+	stxa		%o2, [%i0 + 0x40] %asi
+	stxa		%o3, [%i0 + 0x48] %asi
+	stxa		%o4, [%i0 + 0x50] %asi
+	stxa		%o5, [%i0 + 0x58] %asi
+	stxa		%l2, [%i0 + 0x60] %asi
+	stxa		%l3, [%i0 + 0x68] %asi
+	stxa		%l4, [%i0 + 0x70] %asi
+	stxa		%l5, [%i0 + 0x78] %asi
+	add		%i1, 128, %i1
+	subcc		%g7, 128, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%i0, 128, %i0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
-	retl
-	 nop
+	ret
+	 restore
 
-	.globl		NGclear_page, NGclear_user_page
+	.align		32
 NGclear_page:		/* %o0=dest */
 NGclear_user_page:	/* %o0=dest, %o1=vaddr */
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7
 
-1:	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	add		%o0, 32, %o0
-	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	stxa		%g0, [%o0 + 0x00] %asi
+	stxa		%g0, [%o0 + 0x08] %asi
+	stxa		%g0, [%o0 + 0x10] %asi
+	stxa		%g0, [%o0 + 0x18] %asi
+	stxa		%g0, [%o0 + 0x20] %asi
+	stxa		%g0, [%o0 + 0x28] %asi
+	stxa		%g0, [%o0 + 0x30] %asi
+	stxa		%g0, [%o0 + 0x38] %asi
+	stxa		%g0, [%o0 + 0x40] %asi
+	stxa		%g0, [%o0 + 0x48] %asi
+	stxa		%g0, [%o0 + 0x50] %asi
+	stxa		%g0, [%o0 + 0x58] %asi
+	stxa		%g0, [%o0 + 0x60] %asi
+	stxa		%g0, [%o0 + 0x68] %asi
+	stxa		%g0, [%o0 + 0x70] %asi
+	stxa		%g0, [%o0 + 0x78] %asi
+	stxa		%g0, [%o0 + 0x80] %asi
+	stxa		%g0, [%o0 + 0x88] %asi
+	stxa		%g0, [%o0 + 0x90] %asi
+	stxa		%g0, [%o0 + 0x98] %asi
+	stxa		%g0, [%o0 + 0xa0] %asi
+	stxa		%g0, [%o0 + 0xa8] %asi
+	stxa		%g0, [%o0 + 0xb0] %asi
+	stxa		%g0, [%o0 + 0xb8] %asi
+	stxa		%g0, [%o0 + 0xc0] %asi
+	stxa		%g0, [%o0 + 0xc8] %asi
+	stxa		%g0, [%o0 + 0xd0] %asi
+	stxa		%g0, [%o0 + 0xd8] %asi
+	stxa		%g0, [%o0 + 0xe0] %asi
+	stxa		%g0, [%o0 + 0xe8] %asi
+	stxa		%g0, [%o0 + 0xf0] %asi
+	stxa		%g0, [%o0 + 0xf8] %asi
+	subcc		%g7, 256, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%o0, 256, %o0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
 	retl
 	 nop

arch/sparc/lib/ffs.S

@@ -0,0 +1,84 @@
+#include <linux/linkage.h>
+
+	.register	%g2,#scratch
+
+	.text
+	.align	32
+
+ENTRY(ffs)
+	brnz,pt	%o0, 1f
+	 mov	1, %o1
+	retl
+	 clr	%o0
+	nop
+	nop
+ENTRY(__ffs)
+	sllx	%o0, 32, %g1		/* 1  */
+	srlx	%o0, 32, %g2
+
+	clr	%o1			/* 2  */
+	movrz	%g1, %g2, %o0
+
+	movrz	%g1, 32, %o1		/* 3  */
+1:	clr	%o2
+
+	sllx	%o0, (64 - 16), %g1	/* 4  */
+	srlx	%o0, 16, %g2
+
+	movrz	%g1, %g2, %o0		/* 5  */
+	clr	%o3
+
+	movrz	%g1, 16, %o2		/* 6  */
+	clr	%o4
+
+	and	%o0, 0xff, %g1		/* 7  */
+	srlx	%o0, 8, %g2
+
+	movrz	%g1, %g2, %o0		/* 8  */
+	clr	%o5
+
+	movrz	%g1, 8, %o3		/* 9  */
+	add	%o2, %o1, %o2
+
+	and	%o0, 0xf, %g1		/* 10 */
+	srlx	%o0, 4, %g2
+
+	movrz	%g1, %g2, %o0		/* 11 */
+	add	%o2, %o3, %o2
+
+	movrz	%g1, 4, %o4		/* 12 */
+
+	and	%o0, 0x3, %g1		/* 13 */
+	srlx	%o0, 2, %g2
+
+	movrz	%g1, %g2, %o0		/* 14 */
+	add	%o2, %o4, %o2
+
+	movrz	%g1, 2, %o5		/* 15 */
+
+	and	%o0, 0x1, %g1		/* 16 */
+
+	add	%o2, %o5, %o2		/* 17 */
+	xor	%g1, 0x1, %g1
+
+	retl				/* 18 */
+	 add	%o2, %g1, %o0
+ENDPROC(ffs)
+ENDPROC(__ffs)
+
+	.section	.popc_6insn_patch, "ax"
+	.word		ffs
+	brz,pn	%o0, 98f
+	 neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+98:	retl
+	 nop
+	.word		__ffs
+	neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+	retl
+	 sub	%o0, 1, %o0
+	nop
+	.previous

arch/sparc/lib/hweight.S

@@ -0,0 +1,51 @@
+#include <linux/linkage.h>
+
+	.text
+	.align	32
+ENTRY(__arch_hweight8)
+	ba,pt	%xcc, __sw_hweight8
+	 nop
+	nop
+ENDPROC(__arch_hweight8)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight8
+	sllx		%o0, 64-8, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight16)
+	ba,pt	%xcc, __sw_hweight16
+	 nop
+	nop
+ENDPROC(__arch_hweight16)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight16
+	sllx		%o0, 64-16, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight32)
+	ba,pt	%xcc, __sw_hweight32
+	 nop
+	nop
+ENDPROC(__arch_hweight32)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight32
+	sllx		%o0, 64-32, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight64)
+	ba,pt	%xcc, __sw_hweight64
+	 nop
+	nop
+ENDPROC(__arch_hweight64)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight64
+	retl
+	 popc		%o0, %o0
+	nop
+	.previous

arch/sparc/mm/init_64.c

@@ -1597,6 +1597,44 @@ static void __init tsb_phys_patch(void)
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
+static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
+{
+	pa >>= KTSB_PHYS_SHIFT;
+
+	while (start < end) {
+		unsigned int *ia = (unsigned int *)(unsigned long)*start;
+
+		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		__asm__ __volatile__("flush	%0" : : "r" (ia));
+
+		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
+
+		start++;
+	}
+}
+
+static void ktsb_phys_patch(void)
+{
+	extern unsigned int __swapper_tsb_phys_patch;
+	extern unsigned int __swapper_tsb_phys_patch_end;
+	unsigned long ktsb_pa;
+
+	ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+	patch_one_ktsb_phys(&__swapper_tsb_phys_patch,
+			    &__swapper_tsb_phys_patch_end, ktsb_pa);
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	{
+	extern unsigned int __swapper_4m_tsb_phys_patch;
+	extern unsigned int __swapper_4m_tsb_phys_patch_end;
+	ktsb_pa = (kern_base +
+		   ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+	patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch,
+			    &__swapper_4m_tsb_phys_patch_end, ktsb_pa);
+	}
+#endif
+}
+
 static void __init sun4v_ktsb_init(void)
 {
 	unsigned long ktsb_pa;
@@ -1716,8 +1754,10 @@ void __init paging_init(void)
 		sun4u_pgprot_init();
 
 	if (tlb_type == cheetah_plus ||
-	    tlb_type == hypervisor)
+	    tlb_type == hypervisor) {
 		tsb_phys_patch();
+		ktsb_phys_patch();
+	}
 
 	if (tlb_type == hypervisor) {
 		sun4v_patch_tlb_handlers();

arch/x86/include/asm/msr-index.h

@@ -259,6 +259,9 @@
 #define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
 
 #define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
+#define ENERGY_PERF_BIAS_PERFORMANCE	0
+#define ENERGY_PERF_BIAS_NORMAL		6
+#define ENERGY_PERF_BIAS_POWERSWAVE	15
 
 #define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
 

arch/x86/include/asm/xen/page.h

@@ -39,7 +39,7 @@ typedef struct xpaddr {
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
 extern unsigned long *machine_to_phys_mapping;
-extern unsigned int   machine_to_phys_order;
+extern unsigned long  machine_to_phys_nr;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -87,7 +87,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+	if (unlikely(mfn >= machine_to_phys_nr)) {
 		pfn = ~0;
 		goto try_override;
 	}

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -207,7 +207,6 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
-	mdelay(10);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |

arch/x86/kernel/cpu/intel.c

@@ -456,6 +456,24 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_VMX))
 		detect_vmx_virtcap(c);
+
+	/*
+	 * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not.
+	 * x86_energy_perf_policy(8) is available to change it at run-time
+	 */
+	if (cpu_has(c, X86_FEATURE_EPB)) {
+		u64 epb;
+
+		rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+		if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) {
+			printk_once(KERN_WARNING "ENERGY_PERF_BIAS:"
+				" Set to 'normal', was 'performance'\n"
+				"ENERGY_PERF_BIAS: View and update with"
+				" x86_energy_perf_policy(8)\n");
+			epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
+			wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+		}
+	}
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/cpu/mtrr/main.c

@@ -248,6 +248,25 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	unsigned long flags;
 	int cpu;
 
+#ifdef CONFIG_SMP
+	/*
+	 * If this cpu is not yet active, we are in the cpu online path. There
+	 * can be no stop_machine() in parallel, as stop machine ensures this
+	 * by using get_online_cpus(). We can skip taking the stop_cpus_mutex,
+	 * as we don't need it and also we can't afford to block while waiting
+	 * for the mutex.
+	 *
+	 * If this cpu is active, we need to prevent stop_machine() happening
+	 * in parallel by taking the stop cpus mutex.
+	 *
+	 * Also, this is called in the context of cpu online path or in the
+	 * context where cpu hotplug is prevented. So checking the active status
+	 * of the raw_smp_processor_id() is safe.
+	 */
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_lock(&stop_cpus_mutex);
+#endif
+
 	preempt_disable();
 
 	data.smp_reg = reg;
@@ -330,6 +349,10 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
 	local_irq_restore(flags);
 	preempt_enable();
+#ifdef CONFIG_SMP
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_unlock(&stop_cpus_mutex);
+#endif
 }
 
 /**

arch/x86/kernel/relocate_kernel_32.S

@@ -97,6 +97,8 @@ relocate_kernel:
 	ret
 
 identity_mapped:
+	/* set return address to 0 if not preserving context */
+	pushl	$0
 	/* store the start address on the stack */
 	pushl   %edx
 

arch/x86/kernel/relocate_kernel_64.S

@@ -100,6 +100,8 @@ relocate_kernel:
 	ret
 
 identity_mapped:
+	/* set return address to 0 if not preserving context */
+	pushq	$0
 	/* store the start address on the stack */
 	pushq   %rdx
 

arch/x86/oprofile/backtrace.c

@@ -11,10 +11,12 @@
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/compat.h>
+#include <linux/highmem.h>
+
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
-#include <linux/compat.h>
 
 static int backtrace_stack(void *data, char *name)
 {
@@ -36,17 +38,53 @@ static struct stacktrace_ops backtrace_ops = {
 	.walk_stack	= print_context_stack,
 };
 
+/* from arch/x86/kernel/cpu/perf_event.c: */
+
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
+
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
+
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
+
+		map = kmap_atomic(page);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map);
+		put_page(page);
+
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
+
 #ifdef CONFIG_COMPAT
 static struct stack_frame_ia32 *
 dump_user_backtrace_32(struct stack_frame_ia32 *head)
 {
+	/* Also check accessibility of one struct frame_head beyond: */
 	struct stack_frame_ia32 bufhead[2];
 	struct stack_frame_ia32 *fp;
+	unsigned long bytes;
 
-	/* Also check accessibility of one struct frame_head beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+	if (bytes != sizeof(bufhead))
 		return NULL;
 
 	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
@@ -87,12 +125,12 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
 
 static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
 {
+	/* Also check accessibility of one struct frame_head beyond: */
 	struct stack_frame bufhead[2];
+	unsigned long bytes;
 
-	/* Also check accessibility of one struct stack_frame beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+	if (bytes != sizeof(bufhead))
 		return NULL;
 
 	oprofile_add_trace(bufhead[0].return_address);

arch/x86/platform/olpc/olpc.c

@@ -157,13 +157,13 @@ restart:
 	if (inbuf && inlen) {
 		/* write data to EC */
 		for (i = 0; i < inlen; i++) {
+			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
+			outb(inbuf[i], 0x68);
 			if (wait_on_ibf(0x6c, 0)) {
 				printk(KERN_ERR "olpc-ec:  timeout waiting for"
 						" EC accept data!\n");
 				goto err;
 			}
-			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
-			outb(inbuf[i], 0x68);
 		}
 	}
 	if (outbuf && outlen) {

arch/x86/vdso/vdso32/sysenter.S

@@ -43,7 +43,7 @@ __kernel_vsyscall:
 	.space 7,0x90
 
 	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
-	jmp .Lenter_kernel
+	int $0x80
 	/* 16: System call normal return point is here! */
 VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
 	pop %ebp

arch/x86/xen/Makefile

@@ -18,5 +18,5 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o

arch/x86/xen/enlighten.c

@@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type);
 
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int   machine_to_phys_order;
-EXPORT_SYMBOL(machine_to_phys_order);
+unsigned long  machine_to_phys_nr;
+EXPORT_SYMBOL(machine_to_phys_nr);
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -1248,6 +1248,14 @@ asmlinkage void __init xen_start_kernel(void)
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
+		const struct dom0_vga_console_info *info =
+			(void *)((char *)xen_start_info +
+				 xen_start_info->console.dom0.info_off);
+
+		xen_init_vga(info, xen_start_info->console.dom0.info_size);
+		xen_start_info->console.domU.mfn = 0;
+		xen_start_info->console.domU.evtchn = 0;
+
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}

arch/x86/xen/mmu.c

@@ -1626,15 +1626,19 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
-	unsigned long machine_to_phys_nr_ents;
 
 	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
 		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+		machine_to_phys_nr = mapping.max_mfn + 1;
 	} else {
-		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
 	}
-	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+	if ((machine_to_phys_mapping + machine_to_phys_nr)
+	    < machine_to_phys_mapping)
+		machine_to_phys_nr = (unsigned long *)NULL
+				     - machine_to_phys_mapping;
+#endif
 }
 
 #ifdef CONFIG_X86_64

arch/x86/xen/smp.c

@@ -521,8 +521,6 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	native_smp_prepare_cpus(max_cpus);
 	WARN_ON(xen_smp_intr_init(0));
 
-	if (!xen_have_vector_callback)
-		return;
 	xen_init_lock_cpu(0);
 	xen_init_spinlocks();
 }
@@ -546,6 +544,8 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
+	if (!xen_have_vector_callback)
+		return;
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.cpu_up = xen_hvm_cpu_up;

arch/x86/xen/vga.c

@@ -0,0 +1,67 @@
+#include <linux/screen_info.h>
+#include <linux/init.h>
+
+#include <asm/bootparam.h>
+#include <asm/setup.h>
+
+#include <xen/interface/xen.h>
+
+#include "xen-ops.h"
+
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+{
+	struct screen_info *screen_info = &boot_params.screen_info;
+
+	/* This is drawn from a dump from vgacon:startup in
+	 * standard Linux. */
+	screen_info->orig_video_mode = 3;
+	screen_info->orig_video_isVGA = 1;
+	screen_info->orig_video_lines = 25;
+	screen_info->orig_video_cols = 80;
+	screen_info->orig_video_ega_bx = 3;
+	screen_info->orig_video_points = 16;
+	screen_info->orig_y = screen_info->orig_video_lines - 1;
+
+	switch (info->video_type) {
+	case XEN_VGATYPE_TEXT_MODE_3:
+		if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3)
+		    + sizeof(info->u.text_mode_3))
+			break;
+		screen_info->orig_video_lines = info->u.text_mode_3.rows;
+		screen_info->orig_video_cols = info->u.text_mode_3.columns;
+		screen_info->orig_x = info->u.text_mode_3.cursor_x;
+		screen_info->orig_y = info->u.text_mode_3.cursor_y;
+		screen_info->orig_video_points =
+			info->u.text_mode_3.font_height;
+		break;
+
+	case XEN_VGATYPE_VESA_LFB:
+		if (size < offsetof(struct dom0_vga_console_info,
+				    u.vesa_lfb.gbl_caps))
+			break;
+		screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB;
+		screen_info->lfb_width = info->u.vesa_lfb.width;
+		screen_info->lfb_height = info->u.vesa_lfb.height;
+		screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel;
+		screen_info->lfb_base = info->u.vesa_lfb.lfb_base;
+		screen_info->lfb_size = info->u.vesa_lfb.lfb_size;
+		screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line;
+		screen_info->red_size = info->u.vesa_lfb.red_size;
+		screen_info->red_pos = info->u.vesa_lfb.red_pos;
+		screen_info->green_size = info->u.vesa_lfb.green_size;
+		screen_info->green_pos = info->u.vesa_lfb.green_pos;
+		screen_info->blue_size = info->u.vesa_lfb.blue_size;
+		screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
+		screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
+		screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.gbl_caps)
+		    + sizeof(info->u.vesa_lfb.gbl_caps))
+			screen_info->capabilities = info->u.vesa_lfb.gbl_caps;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.mode_attrs)
+		    + sizeof(info->u.vesa_lfb.mode_attrs))
+			screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs;
+		break;
+	}
+}

arch/x86/xen/xen-ops.h

@@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu)
 }
 #endif
 
+struct dom0_vga_console_info;
+
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#else
+static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
+				       size_t size)
+{
+}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\

arch/xtensa/kernel/ptrace.c

@@ -147,6 +147,9 @@ int ptrace_setxregs(struct task_struct *child, void __user *uregs)
 	elf_xtregs_t *xtregs = uregs;
 	int ret = 0;
 
+	if (!access_ok(VERIFY_READ, uregs, sizeof(elf_xtregs_t)))
+		return -EFAULT;
+
 #if XTENSA_HAVE_COPROCESSORS
 	/* Flush all coprocessors before we overwrite them. */
 	coprocessor_flush_all(ti);

block/blk-core.c

@@ -839,6 +839,9 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	struct request *rq;
 
+	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
+		return NULL;
+
 	BUG_ON(rw != READ && rw != WRITE);
 
 	spin_lock_irq(q->queue_lock);

block/blk-exec.c

@@ -50,6 +50,13 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 {
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
+	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+		rq->errors = -ENXIO;
+		if (rq->end_io)
+			rq->end_io(rq, rq->errors);
+		return;
+	}
+
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 	WARN_ON(irqs_disabled());

crypto/md5.c

@@ -21,99 +21,9 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/cryptohash.h>
 #include <asm/byteorder.h>
 
-#define F1(x, y, z)	(z ^ (x & (y ^ z)))
-#define F2(x, y, z)	F1(z, x, y)
-#define F3(x, y, z)	(x ^ y ^ z)
-#define F4(x, y, z)	(y ^ (x | ~z))
-
-#define MD5STEP(f, w, x, y, z, in, s) \
-	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
-
-static void md5_transform(u32 *hash, u32 const *in)
-{
-	u32 a, b, c, d;
-
-	a = hash[0];
-	b = hash[1];
-	c = hash[2];
-	d = hash[3];
-
-	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
-	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
-	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
-	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
-	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
-	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
-	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
-	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
-	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
-	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
-	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
-	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
-	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
-	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
-	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
-	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
-	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
-	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
-	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
-	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
-	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
-	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
-	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
-	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
-	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
-	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
-	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
-	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
-	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
-	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
-	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
-	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
-	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
-	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
-	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
-	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
-	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
-	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
-	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
-	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
-	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
-	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
-	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
-	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
-	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
-	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
-	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
-	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
-	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
-	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
-	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
-	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
-	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
-	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
-	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
-	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
-	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
-	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
-	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
-	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
-	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
-	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
-	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
-	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
-	hash[0] += a;
-	hash[1] += b;
-	hash[2] += c;
-	hash[3] += d;
-}
-
 /* XXX: this stuff can be optimized */
 static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
 {

drivers/block/cciss.h

@@ -223,7 +223,7 @@ static void SA5_submit_command( ctlr_info_t *h, CommandList_struct *c)
 			h->ctlr, c->busaddr);
 #endif /* CCISS_DEBUG */
          writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
-	readl(h->vaddr + SA5_REQUEST_PORT_OFFSET);
+	readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
 	 h->commands_outstanding++;
 	 if ( h->commands_outstanding > h->max_outstanding)
 		h->max_outstanding = h->commands_outstanding;

drivers/block/loop.c

@@ -750,10 +750,10 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 	ssize_t ret;
 	char *p = NULL;
 
-	mutex_lock(&lo->lo_ctl_mutex);
+	spin_lock_irq(&lo->lo_lock);
 	if (lo->lo_backing_file)
 		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
-	mutex_unlock(&lo->lo_ctl_mutex);
+	spin_unlock_irq(&lo->lo_lock);
 
 	if (IS_ERR_OR_NULL(p))
 		ret = PTR_ERR(p);
@@ -1007,7 +1007,9 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 
 	kthread_stop(lo->lo_thread);
 
+	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
+	spin_unlock_irq(&lo->lo_lock);
 
 	loop_release_xfer(lo);
 	lo->transfer = NULL;

drivers/block/xen-blkfront.c

@@ -123,8 +123,8 @@ static DEFINE_SPINLOCK(minor_lock);
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
 #define EMULATED_HD_DISK_MINOR_OFFSET (0)
 #define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
-#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
-#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
+#define EMULATED_SD_DISK_MINOR_OFFSET (0)
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256)
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
@@ -529,7 +529,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
 		offset = minor / nr_parts;
-		if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+		if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4)
 			printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
 					"emulated IDE disks,\n\t choose an xvd device name"
 					"from xvde on\n", info->vdevice);

drivers/char/random.c

@@ -1300,330 +1300,14 @@ ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-/********************************************************************
- *
- * Random functions for networking
- *
- ********************************************************************/
+static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-/*
- * TCP initial sequence number picking.  This uses the random number
- * generator to pick an initial secret value.  This value is hashed
- * along with the TCP endpoint information to provide a unique
- * starting point for each pair of TCP endpoints.  This defeats
- * attacks which rely on guessing the initial TCP sequence number.
- * This algorithm was suggested by Steve Bellovin.
- *
- * Using a very strong hash was taking an appreciable amount of the total
- * TCP connection establishment time, so this is a weaker hash,
- * compensated for by changing the secret periodically.
- */
-
-/* F, G and H are basic MD4 functions: selection, majority, parity */
-#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
-#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
-#define H(x, y, z) ((x) ^ (y) ^ (z))
-
-/*
- * The generic round function.  The application is so specific that
- * we don't bother protecting all the arguments with parens, as is generally
- * good macro practice, in favor of extra legibility.
- * Rotation is separate from addition to prevent recomputation
- */
-#define ROUND(f, a, b, c, d, x, s)	\
-	(a += f(b, c, d) + x, a = (a << s) | (a >> (32 - s)))
-#define K1 0
-#define K2 013240474631UL
-#define K3 015666365641UL
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-
-static __u32 twothirdsMD4Transform(__u32 const buf[4], __u32 const in[12])
+static int __init random_int_secret_init(void)
 {
-	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
-
-	/* Round 1 */
-	ROUND(F, a, b, c, d, in[ 0] + K1,  3);
-	ROUND(F, d, a, b, c, in[ 1] + K1,  7);
-	ROUND(F, c, d, a, b, in[ 2] + K1, 11);
-	ROUND(F, b, c, d, a, in[ 3] + K1, 19);
-	ROUND(F, a, b, c, d, in[ 4] + K1,  3);
-	ROUND(F, d, a, b, c, in[ 5] + K1,  7);
-	ROUND(F, c, d, a, b, in[ 6] + K1, 11);
-	ROUND(F, b, c, d, a, in[ 7] + K1, 19);
-	ROUND(F, a, b, c, d, in[ 8] + K1,  3);
-	ROUND(F, d, a, b, c, in[ 9] + K1,  7);
-	ROUND(F, c, d, a, b, in[10] + K1, 11);
-	ROUND(F, b, c, d, a, in[11] + K1, 19);
-
-	/* Round 2 */
-	ROUND(G, a, b, c, d, in[ 1] + K2,  3);
-	ROUND(G, d, a, b, c, in[ 3] + K2,  5);
-	ROUND(G, c, d, a, b, in[ 5] + K2,  9);
-	ROUND(G, b, c, d, a, in[ 7] + K2, 13);
-	ROUND(G, a, b, c, d, in[ 9] + K2,  3);
-	ROUND(G, d, a, b, c, in[11] + K2,  5);
-	ROUND(G, c, d, a, b, in[ 0] + K2,  9);
-	ROUND(G, b, c, d, a, in[ 2] + K2, 13);
-	ROUND(G, a, b, c, d, in[ 4] + K2,  3);
-	ROUND(G, d, a, b, c, in[ 6] + K2,  5);
-	ROUND(G, c, d, a, b, in[ 8] + K2,  9);
-	ROUND(G, b, c, d, a, in[10] + K2, 13);
-
-	/* Round 3 */
-	ROUND(H, a, b, c, d, in[ 3] + K3,  3);
-	ROUND(H, d, a, b, c, in[ 7] + K3,  9);
-	ROUND(H, c, d, a, b, in[11] + K3, 11);
-	ROUND(H, b, c, d, a, in[ 2] + K3, 15);
-	ROUND(H, a, b, c, d, in[ 6] + K3,  3);
-	ROUND(H, d, a, b, c, in[10] + K3,  9);
-	ROUND(H, c, d, a, b, in[ 1] + K3, 11);
-	ROUND(H, b, c, d, a, in[ 5] + K3, 15);
-	ROUND(H, a, b, c, d, in[ 9] + K3,  3);
-	ROUND(H, d, a, b, c, in[ 0] + K3,  9);
-	ROUND(H, c, d, a, b, in[ 4] + K3, 11);
-	ROUND(H, b, c, d, a, in[ 8] + K3, 15);
-
-	return buf[1] + b; /* "most hashed" word */
-	/* Alternative: return sum of all words? */
-}
-#endif
-
-#undef ROUND
-#undef F
-#undef G
-#undef H
-#undef K1
-#undef K2
-#undef K3
-
-/* This should not be decreased so low that ISNs wrap too fast. */
-#define REKEY_INTERVAL (300 * HZ)
-/*
- * Bit layout of the tcp sequence numbers (before adding current time):
- * bit 24-31: increased after every key exchange
- * bit 0-23: hash(source,dest)
- *
- * The implementation is similar to the algorithm described
- * in the Appendix of RFC 1185, except that
- * - it uses a 1 MHz clock instead of a 250 kHz clock
- * - it performs a rekey every 5 minutes, which is equivalent
- * 	to a (source,dest) tulple dependent forward jump of the
- * 	clock by 0..2^(HASH_BITS+1)
- *
- * Thus the average ISN wraparound time is 68 minutes instead of
- * 4.55 hours.
- *
- * SMP cleanup and lock avoidance with poor man's RCU.
- * 			Manfred Spraul <manfred@colorfullife.com>
- *
- */
-#define COUNT_BITS 8
-#define COUNT_MASK ((1 << COUNT_BITS) - 1)
-#define HASH_BITS 24
-#define HASH_MASK ((1 << HASH_BITS) - 1)
-
-static struct keydata {
-	__u32 count; /* already shifted to the final position */
-	__u32 secret[12];
-} ____cacheline_aligned ip_keydata[2];
-
-static unsigned int ip_cnt;
-
-static void rekey_seq_generator(struct work_struct *work);
-
-static DECLARE_DELAYED_WORK(rekey_work, rekey_seq_generator);
-
-/*
- * Lock avoidance:
- * The ISN generation runs lockless - it's just a hash over random data.
- * State changes happen every 5 minutes when the random key is replaced.
- * Synchronization is performed by having two copies of the hash function
- * state and rekey_seq_generator always updates the inactive copy.
- * The copy is then activated by updating ip_cnt.
- * The implementation breaks down if someone blocks the thread
- * that processes SYN requests for more than 5 minutes. Should never
- * happen, and even if that happens only a not perfectly compliant
- * ISN is generated, nothing fatal.
- */
-static void rekey_seq_generator(struct work_struct *work)
-{
-	struct keydata *keyptr = &ip_keydata[1 ^ (ip_cnt & 1)];
-
-	get_random_bytes(keyptr->secret, sizeof(keyptr->secret));
-	keyptr->count = (ip_cnt & COUNT_MASK) << HASH_BITS;
-	smp_wmb();
-	ip_cnt++;
-	schedule_delayed_work(&rekey_work,
-			      round_jiffies_relative(REKEY_INTERVAL));
-}
-
-static inline struct keydata *get_keyptr(void)
-{
-	struct keydata *keyptr = &ip_keydata[ip_cnt & 1];
-
-	smp_rmb();
-
-	return keyptr;
-}
-
-static __init int seqgen_init(void)
-{
-	rekey_seq_generator(NULL);
+	get_random_bytes(random_int_secret, sizeof(random_int_secret));
 	return 0;
 }
-late_initcall(seqgen_init);
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr,
-				   __be16 sport, __be16 dport)
-{
-	__u32 seq;
-	__u32 hash[12];
-	struct keydata *keyptr = get_keyptr();
-
-	/* The procedure is the same as for IPv4, but addresses are longer.
-	 * Thus we must use twothirdsMD4Transform.
-	 */
-
-	memcpy(hash, saddr, 16);
-	hash[4] = ((__force u16)sport << 16) + (__force u16)dport;
-	memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7);
-
-	seq = twothirdsMD4Transform((const __u32 *)daddr, hash) & HASH_MASK;
-	seq += keyptr->count;
-
-	seq += ktime_to_ns(ktime_get_real());
-
-	return seq;
-}
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
-#endif
-
-/*  The code below is shamelessly stolen from secure_tcp_sequence_number().
- *  All blames to Andrey V. Savochkin <saw@msu.ru>.
- */
-__u32 secure_ip_id(__be32 daddr)
-{
-	struct keydata *keyptr;
-	__u32 hash[4];
-
-	keyptr = get_keyptr();
-
-	/*
-	 *  Pick a unique starting offset for each IP destination.
-	 *  The dest ip address is placed in the starting vector,
-	 *  which is then hashed with random data.
-	 */
-	hash[0] = (__force __u32)daddr;
-	hash[1] = keyptr->secret[9];
-	hash[2] = keyptr->secret[10];
-	hash[3] = keyptr->secret[11];
-
-	return half_md4_transform(hash, keyptr->secret);
-}
-
-#ifdef CONFIG_INET
-
-__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-				 __be16 sport, __be16 dport)
-{
-	__u32 seq;
-	__u32 hash[4];
-	struct keydata *keyptr = get_keyptr();
-
-	/*
-	 *  Pick a unique starting offset for each TCP connection endpoints
-	 *  (saddr, daddr, sport, dport).
-	 *  Note that the words are placed into the starting vector, which is
-	 *  then mixed with a partial MD4 over random data.
-	 */
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = keyptr->secret[11];
-
-	seq = half_md4_transform(hash, keyptr->secret) & HASH_MASK;
-	seq += keyptr->count;
-	/*
-	 *	As close as possible to RFC 793, which
-	 *	suggests using a 250 kHz clock.
-	 *	Further reading shows this assumes 2 Mb/s networks.
-	 *	For 10 Mb/s Ethernet, a 1 MHz clock is appropriate.
-	 *	For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but
-	 *	we also need to limit the resolution so that the u32 seq
-	 *	overlaps less than one time per MSL (2 minutes).
-	 *	Choosing a clock of 64 ns period is OK. (period of 274 s)
-	 */
-	seq += ktime_to_ns(ktime_get_real()) >> 6;
-
-	return seq;
-}
-
-/* Generate secure starting point for ephemeral IPV4 transport port search */
-u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
-{
-	struct keydata *keyptr = get_keyptr();
-	u32 hash[4];
-
-	/*
-	 *  Pick a unique starting offset for each ephemeral port search
-	 *  (saddr, daddr, dport) and 48bits of random data.
-	 */
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = (__force u32)dport ^ keyptr->secret[10];
-	hash[3] = keyptr->secret[11];
-
-	return half_md4_transform(hash, keyptr->secret);
-}
-EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
-			       __be16 dport)
-{
-	struct keydata *keyptr = get_keyptr();
-	u32 hash[12];
-
-	memcpy(hash, saddr, 16);
-	hash[4] = (__force u32)dport;
-	memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7);
-
-	return twothirdsMD4Transform((const __u32 *)daddr, hash);
-}
-#endif
-
-#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
-/* Similar to secure_tcp_sequence_number but generate a 48 bit value
- * bit's 32-47 increase every key exchange
- *       0-31  hash(source, dest)
- */
-u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
-				__be16 sport, __be16 dport)
-{
-	u64 seq;
-	__u32 hash[4];
-	struct keydata *keyptr = get_keyptr();
-
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = keyptr->secret[11];
-
-	seq = half_md4_transform(hash, keyptr->secret);
-	seq |= ((u64)keyptr->count) << (32 - HASH_BITS);
-
-	seq += ktime_to_ns(ktime_get_real());
-	seq &= (1ull << 48) - 1;
-
-	return seq;
-}
-EXPORT_SYMBOL(secure_dccp_sequence_number);
-#endif
-
-#endif /* CONFIG_INET */
-
+late_initcall(random_int_secret_init);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -1631,17 +1315,15 @@ EXPORT_SYMBOL(secure_dccp_sequence_number);
  * value is not cryptographically secure but for several uses the cost of
  * depleting entropy is too high
  */
-DEFINE_PER_CPU(__u32 [4], get_random_int_hash);
+DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
 unsigned int get_random_int(void)
 {
-	struct keydata *keyptr;
 	__u32 *hash = get_cpu_var(get_random_int_hash);
-	int ret;
+	unsigned int ret;
 
-	keyptr = get_keyptr();
 	hash[0] += current->pid + jiffies + get_cycles();
-
-	ret = half_md4_transform(hash, keyptr->secret);
+	md5_transform(hash, random_int_secret);
+	ret = hash[0];
 	put_cpu_var(get_random_int_hash);
 
 	return ret;

drivers/edac/i7core_edac.c

@@ -1670,7 +1670,7 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci,
 	char *type, *optype, *err, *msg;
 	unsigned long error = m->status & 0x1ff0000l;
 	u32 optypenum = (m->status >> 4) & 0x07;
-	u32 core_err_cnt = (m->status >> 38) && 0x7fff;
+	u32 core_err_cnt = (m->status >> 38) & 0x7fff;
 	u32 dimm = (m->misc >> 16) & 0x3;
 	u32 channel = (m->misc >> 18) & 0x3;
 	u32 syndrome = m->misc >> 32;

drivers/firewire/core-cdev.c

@@ -253,14 +253,11 @@ static int fw_device_op_open(struct inode *inode, struct file *file)
 	init_waitqueue_head(&client->wait);
 	init_waitqueue_head(&client->tx_flush_wait);
 	INIT_LIST_HEAD(&client->phy_receiver_link);
+	INIT_LIST_HEAD(&client->link);
 	kref_init(&client->kref);
 
 	file->private_data = client;
 
-	mutex_lock(&device->client_list_mutex);
-	list_add_tail(&client->link, &device->client_list);
-	mutex_unlock(&device->client_list_mutex);
-
 	return nonseekable_open(inode, file);
 }
 
@@ -451,15 +448,20 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg)
 	if (ret != 0)
 		return -EFAULT;
 
+	mutex_lock(&client->device->client_list_mutex);
+
 	client->bus_reset_closure = a->bus_reset_closure;
 	if (a->bus_reset != 0) {
 		fill_bus_reset_event(&bus_reset, client);
-		if (copy_to_user(u64_to_uptr(a->bus_reset),
-				 &bus_reset, sizeof(bus_reset)))
-			return -EFAULT;
+		ret = copy_to_user(u64_to_uptr(a->bus_reset),
+				   &bus_reset, sizeof(bus_reset));
 	}
+	if (ret == 0 && list_empty(&client->link))
+		list_add_tail(&client->link, &client->device->client_list);
 
-	return 0;
+	mutex_unlock(&client->device->client_list_mutex);
+
+	return ret ? -EFAULT : 0;
 }
 
 static int add_client_resource(struct client *client,
@@ -1583,7 +1585,7 @@ static int dispatch_ioctl(struct client *client,
 	if (_IOC_TYPE(cmd) != '#' ||
 	    _IOC_NR(cmd) >= ARRAY_SIZE(ioctl_handlers) ||
 	    _IOC_SIZE(cmd) > sizeof(buffer))
-		return -EINVAL;
+		return -ENOTTY;
 
 	if (_IOC_DIR(cmd) == _IOC_READ)
 		memset(&buffer, 0, _IOC_SIZE(cmd));

drivers/firmware/sigma.c

@@ -11,6 +11,7 @@
 #include <linux/firmware.h>
 #include <linux/kernel.h>
 #include <linux/i2c.h>
+#include <linux/module.h>
 #include <linux/sigma.h>
 
 /* Return: 0==OK, <0==error, =1 ==no more actions */
@@ -113,3 +114,5 @@ int process_sigma_firmware(struct i2c_client *client, const char *name)
 	return ret;
 }
 EXPORT_SYMBOL(process_sigma_firmware);
+
+MODULE_LICENSE("GPL");

drivers/gpu/drm/drm_edid.c

@@ -127,6 +127,23 @@ static const u8 edid_header[] = {
 	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00
 };
 
+ /*
+ * Sanity check the header of the base EDID block.  Return 8 if the header
+ * is perfect, down to 0 if it's totally wrong.
+ */
+int drm_edid_header_is_valid(const u8 *raw_edid)
+{
+	int i, score = 0;
+
+	for (i = 0; i < sizeof(edid_header); i++)
+		if (raw_edid[i] == edid_header[i])
+			score++;
+
+	return score;
+}
+EXPORT_SYMBOL(drm_edid_header_is_valid);
+
+
 /*
  * Sanity check the EDID block (base or extension).  Return 0 if the block
  * doesn't check out, or 1 if it's valid.
@@ -139,12 +156,7 @@ drm_edid_block_valid(u8 *raw_edid)
 	struct edid *edid = (struct edid *)raw_edid;
 
 	if (raw_edid[0] == 0x00) {
-		int score = 0;
-
-		for (i = 0; i < sizeof(edid_header); i++)
-			if (raw_edid[i] == edid_header[i])
-				score++;
-
+		int score = drm_edid_header_is_valid(raw_edid);
 		if (score == 8) ;
 		else if (score >= 6) {
 			DRM_DEBUG("Fixing EDID header, your hardware may be failing\n");

drivers/gpu/drm/i915/i915_dma.c

@@ -61,7 +61,6 @@ static void i915_write_hws_pga(struct drm_device *dev)
 static int i915_init_phys_hws(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = LP_RING(dev_priv);
 
 	/* Program Hardware Status Page */
 	dev_priv->status_page_dmah =
@@ -71,10 +70,9 @@ static int i915_init_phys_hws(struct drm_device *dev)
 		DRM_ERROR("Can not allocate hardware status page\n");
 		return -ENOMEM;
 	}
-	ring->status_page.page_addr =
-		(void __force __iomem *)dev_priv->status_page_dmah->vaddr;
 
-	memset_io(ring->status_page.page_addr, 0, PAGE_SIZE);
+	memset_io((void __force __iomem *)dev_priv->status_page_dmah->vaddr,
+		  0, PAGE_SIZE);
 
 	i915_write_hws_pga(dev);
 

drivers/gpu/drm/i915/i915_irq.c

@@ -306,12 +306,15 @@ static void i915_hotplug_work_func(struct work_struct *work)
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *encoder;
 
+	mutex_lock(&mode_config->mutex);
 	DRM_DEBUG_KMS("running encoder hotplug functions\n");
 
 	list_for_each_entry(encoder, &mode_config->encoder_list, base.head)
 		if (encoder->hot_plug)
 			encoder->hot_plug(encoder);
 
+	mutex_unlock(&mode_config->mutex);
+
 	/* Just fire off a uevent and let userspace tell us what to do */
 	drm_helper_hpd_irq_event(dev);
 }

drivers/gpu/drm/i915/intel_display.c

@@ -2699,14 +2699,18 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 		I915_WRITE(PF_WIN_SZ(pipe), dev_priv->pch_pf_size);
 	}
 
+	/*
+	 * On ILK+ LUT must be loaded before the pipe is running but with
+	 * clocks enabled
+	 */
+	intel_crtc_load_lut(crtc);
+
 	intel_enable_pipe(dev_priv, pipe, is_pch_port);
 	intel_enable_plane(dev_priv, plane, pipe);
 
 	if (is_pch_port)
 		ironlake_pch_enable(crtc);
 
-	intel_crtc_load_lut(crtc);
-
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
 	mutex_unlock(&dev->struct_mutex);

drivers/gpu/drm/i915/intel_panel.c

@@ -83,11 +83,15 @@ intel_pch_panel_fitting(struct drm_device *dev,
 			u32 scaled_height = mode->hdisplay * adjusted_mode->vdisplay;
 			if (scaled_width > scaled_height) { /* pillar */
 				width = scaled_height / mode->vdisplay;
+				if (width & 1)
+				    	width++;
 				x = (adjusted_mode->hdisplay - width + 1) / 2;
 				y = 0;
 				height = adjusted_mode->vdisplay;
 			} else if (scaled_width < scaled_height) { /* letter */
 				height = scaled_width / mode->hdisplay;
+				if (height & 1)
+				    height++;
 				y = (adjusted_mode->vdisplay - height + 1) / 2;
 				x = 0;
 				width = adjusted_mode->hdisplay;

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -1319,6 +1319,9 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 		ring->get_seqno = pc_render_get_seqno;
 	}
 
+	if (!I915_NEED_GFX_HWS(dev))
+		ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
+
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);

drivers/gpu/drm/radeon/atombios_dp.c

@@ -613,6 +613,18 @@ static bool radeon_dp_get_link_status(struct radeon_connector *radeon_connector,
 	return true;
 }
 
+bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector)
+{
+	u8 link_status[DP_LINK_STATUS_SIZE];
+	struct radeon_connector_atom_dig *dig = radeon_connector->con_priv;
+
+	if (!radeon_dp_get_link_status(radeon_connector, link_status))
+		return false;
+	if (dp_channel_eq_ok(link_status, dig->dp_lane_count))
+		return false;
+	return true;
+}
+
 struct radeon_dp_link_train_info {
 	struct radeon_device *rdev;
 	struct drm_encoder *encoder;
@@ -627,6 +639,7 @@ struct radeon_dp_link_train_info {
 	u8 train_set[4];
 	u8 link_status[DP_LINK_STATUS_SIZE];
 	u8 tries;
+	bool use_dpencoder;
 };
 
 static void radeon_dp_update_vs_emph(struct radeon_dp_link_train_info *dp_info)
@@ -646,7 +659,7 @@ static void radeon_dp_set_tp(struct radeon_dp_link_train_info *dp_info, int tp)
 	int rtp = 0;
 
 	/* set training pattern on the source */
-	if (ASIC_IS_DCE4(dp_info->rdev)) {
+	if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder) {
 		switch (tp) {
 		case DP_TRAINING_PATTERN_1:
 			rtp = ATOM_ENCODER_CMD_DP_LINK_TRAINING_PATTERN1;
@@ -706,7 +719,7 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 	radeon_write_dpcd_reg(dp_info->radeon_connector, DP_LINK_BW_SET, tmp);
 
 	/* start training on the source */
-	if (ASIC_IS_DCE4(dp_info->rdev))
+	if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder)
 		atombios_dig_encoder_setup(dp_info->encoder,
 					   ATOM_ENCODER_CMD_DP_LINK_TRAINING_START, 0);
 	else
@@ -731,7 +744,7 @@ static int radeon_dp_link_train_finish(struct radeon_dp_link_train_info *dp_info
 			      DP_TRAINING_PATTERN_DISABLE);
 
 	/* disable the training pattern on the source */
-	if (ASIC_IS_DCE4(dp_info->rdev))
+	if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder)
 		atombios_dig_encoder_setup(dp_info->encoder,
 					   ATOM_ENCODER_CMD_DP_LINK_TRAINING_COMPLETE, 0);
 	else
@@ -869,7 +882,8 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
 	struct radeon_connector *radeon_connector;
 	struct radeon_connector_atom_dig *dig_connector;
 	struct radeon_dp_link_train_info dp_info;
- 	u8 tmp;
+	int index;
+	u8 tmp, frev, crev;
 
 	if (!radeon_encoder->enc_priv)
 		return;
@@ -884,6 +898,18 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
 	    (dig_connector->dp_sink_type != CONNECTOR_OBJECT_ID_eDP))
 		return;
 
+	/* DPEncoderService newer than 1.1 can't program properly the
+	 * training pattern. When facing such version use the
+	 * DIGXEncoderControl (X== 1 | 2)
+	 */
+	dp_info.use_dpencoder = true;
+	index = GetIndexIntoMasterTable(COMMAND, DPEncoderService);
+	if (atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) {
+		if (crev > 1) {
+			dp_info.use_dpencoder = false;
+		}
+	}
+
 	dp_info.enc_id = 0;
 	if (dig->dig_encoder)
 		dp_info.enc_id |= ATOM_DP_CONFIG_DIG2_ENCODER;

drivers/gpu/drm/radeon/radeon_combios.c

@@ -779,7 +779,8 @@ void radeon_combios_i2c_init(struct radeon_device *rdev)
 				}
 			}
 		}
-	} else if (rdev->family >= CHIP_R200) {
+	} else if ((rdev->family == CHIP_R200) ||
+		   (rdev->family >= CHIP_R300)) {
 		/* 0x68 */
 		i2c = combios_setup_i2c_bus(rdev, DDC_MONID, 0, 0);
 		rdev->i2c_bus[3] = radeon_i2c_create(dev, &i2c, "MONID");

drivers/gpu/drm/radeon/radeon_connectors.c

@@ -60,18 +60,20 @@ void radeon_connector_hotplug(struct drm_connector *connector)
 
 	radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 
-	/* powering up/down the eDP panel generates hpd events which
-	 * can interfere with modesetting.
-	 */
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+	/* if the connector is already off, don't turn it back on */
+	if (connector->dpms != DRM_MODE_DPMS_ON)
 		return;
 
-	/* pre-r600 did not always have the hpd pins mapped accurately to connectors */
-	if (rdev->family >= CHIP_R600) {
-		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
+	/* just deal with DP (not eDP) here. */
+	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		int saved_dpms = connector->dpms;
+
+		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) &&
+		    radeon_dp_needs_link_train(radeon_connector))
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		else
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+		connector->dpms = saved_dpms;
 	}
 }
 
@@ -430,6 +432,55 @@ int radeon_connector_set_property(struct drm_connector *connector, struct drm_pr
 	return 0;
 }
 
+/*
+ * Some integrated ATI Radeon chipset implementations (e. g.
+ * Asus M2A-VM HDMI) may indicate the availability of a DDC,
+ * even when there's no monitor connected. For these connectors
+ * following DDC probe extension will be applied: check also for the
+ * availability of EDID with at least a correct EDID header. Only then,
+ * DDC is assumed to be available. This prevents drm_get_edid() and
+ * drm_edid_block_valid() from periodically dumping data and kernel
+ * errors into the logs and onto the terminal.
+ */
+static bool radeon_connector_needs_extended_probe(struct radeon_device *dev,
+				     uint32_t supported_device,
+				     int connector_type)
+{
+	/* Asus M2A-VM HDMI board sends data to i2c bus even,
+	 * if HDMI add-on card is not plugged in or HDMI is disabled in
+	 * BIOS. Valid DDC can only be assumed, if also a valid EDID header
+	 * can be retrieved via i2c bus during DDC probe */
+	if ((dev->pdev->device == 0x791e) &&
+	    (dev->pdev->subsystem_vendor == 0x1043) &&
+	    (dev->pdev->subsystem_device == 0x826d)) {
+		if ((connector_type == DRM_MODE_CONNECTOR_HDMIA) &&
+		    (supported_device == ATOM_DEVICE_DFP2_SUPPORT))
+			return true;
+	}
+	/* ECS A740GM-M with ATI RADEON 2100 sends data to i2c bus
+	 * for a DVI connector that is not implemented */
+	if ((dev->pdev->device == 0x796e) &&
+	    (dev->pdev->subsystem_vendor == 0x1019) &&
+	    (dev->pdev->subsystem_device == 0x2615)) {
+		if ((connector_type == DRM_MODE_CONNECTOR_DVID) &&
+		    (supported_device == ATOM_DEVICE_DFP2_SUPPORT))
+			return true;
+	}
+	/* TOSHIBA Satellite L300D with ATI Mobility Radeon x1100
+	 * (RS690M) sends data to i2c bus for a HDMI connector that
+	 * is not implemented */
+	if ((dev->pdev->device == 0x791f) &&
+	    (dev->pdev->subsystem_vendor == 0x1179) &&
+	    (dev->pdev->subsystem_device == 0xff68)) {
+		if ((connector_type == DRM_MODE_CONNECTOR_HDMIA) &&
+		    (supported_device == ATOM_DEVICE_DFP2_SUPPORT))
+			return true;
+	}
+
+	/* Default: no EDID header probe required for DDC probing */
+	return false;
+}
+
 static void radeon_fixup_lvds_native_mode(struct drm_encoder *encoder,
 					  struct drm_connector *connector)
 {
@@ -661,7 +712,8 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 		ret = connector_status_disconnected;
 
 	if (radeon_connector->ddc_bus)
-		dret = radeon_ddc_probe(radeon_connector);
+		dret = radeon_ddc_probe(radeon_connector,
+					radeon_connector->requires_extended_probe);
 	if (dret) {
 		if (radeon_connector->edid) {
 			kfree(radeon_connector->edid);
@@ -833,7 +885,8 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	bool dret = false;
 
 	if (radeon_connector->ddc_bus)
-		dret = radeon_ddc_probe(radeon_connector);
+		dret = radeon_ddc_probe(radeon_connector,
+					radeon_connector->requires_extended_probe);
 	if (dret) {
 		if (radeon_connector->edid) {
 			kfree(radeon_connector->edid);
@@ -1251,7 +1304,8 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 				if (radeon_dp_getdpcd(radeon_connector))
 					ret = connector_status_connected;
 			} else {
-				if (radeon_ddc_probe(radeon_connector))
+				if (radeon_ddc_probe(radeon_connector,
+						     radeon_connector->requires_extended_probe))
 					ret = connector_status_connected;
 			}
 		}
@@ -1406,6 +1460,9 @@ radeon_add_atom_connector(struct drm_device *dev,
 	radeon_connector->shared_ddc = shared_ddc;
 	radeon_connector->connector_object_id = connector_object_id;
 	radeon_connector->hpd = *hpd;
+	radeon_connector->requires_extended_probe =
+		radeon_connector_needs_extended_probe(rdev, supported_device,
+							connector_type);
 	radeon_connector->router = *router;
 	if (router->ddc_valid || router->cd_valid) {
 		radeon_connector->router_bus = radeon_i2c_lookup(rdev, &router->i2c_info);
@@ -1752,6 +1809,9 @@ radeon_add_legacy_connector(struct drm_device *dev,
 	radeon_connector->devices = supported_device;
 	radeon_connector->connector_object_id = connector_object_id;
 	radeon_connector->hpd = *hpd;
+	radeon_connector->requires_extended_probe =
+		radeon_connector_needs_extended_probe(rdev, supported_device,
+							connector_type);
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_VGA:
 		drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type);

drivers/gpu/drm/radeon/radeon_device.c

@@ -704,8 +704,9 @@ int radeon_device_init(struct radeon_device *rdev,
 	rdev->gpu_lockup = false;
 	rdev->accel_working = false;
 
-	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X).\n",
-		radeon_family_name[rdev->family], pdev->vendor, pdev->device);
+	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X).\n",
+		radeon_family_name[rdev->family], pdev->vendor, pdev->device,
+		pdev->subsystem_vendor, pdev->subsystem_device);
 
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */

drivers/gpu/drm/radeon/radeon_display.c

@@ -777,8 +777,17 @@ static int radeon_ddc_dump(struct drm_connector *connector)
 	if (!radeon_connector->ddc_bus)
 		return -1;
 	edid = drm_get_edid(connector, &radeon_connector->ddc_bus->adapter);
+	/* Log EDID retrieval status here. In particular with regard to
+	 * connectors with requires_extended_probe flag set, that will prevent
+	 * function radeon_dvi_detect() to fetch EDID on this connector,
+	 * as long as there is no valid EDID header found */
 	if (edid) {
+		DRM_INFO("Radeon display connector %s: Found valid EDID",
+				drm_get_connector_name(connector));
 		kfree(edid);
+	} else {
+		DRM_INFO("Radeon display connector %s: No monitor connected or invalid EDID",
+				drm_get_connector_name(connector));
 	}
 	return ret;
 }

drivers/gpu/drm/radeon/radeon_encoders.c

@@ -2323,6 +2323,9 @@ radeon_add_atom_encoder(struct drm_device *dev,
 	default:
 		encoder->possible_crtcs = 0x3;
 		break;
+	case 4:
+		encoder->possible_crtcs = 0xf;
+		break;
 	case 6:
 		encoder->possible_crtcs = 0x3f;
 		break;

drivers/gpu/drm/radeon/radeon_i2c.c

@@ -32,17 +32,17 @@
  * radeon_ddc_probe
  *
  */
-bool radeon_ddc_probe(struct radeon_connector *radeon_connector)
+bool radeon_ddc_probe(struct radeon_connector *radeon_connector, bool requires_extended_probe)
 {
-	u8 out_buf[] = { 0x0, 0x0};
-	u8 buf[2];
+	u8 out = 0x0;
+	u8 buf[8];
 	int ret;
 	struct i2c_msg msgs[] = {
 		{
 			.addr = 0x50,
 			.flags = 0,
 			.len = 1,
-			.buf = out_buf,
+			.buf = &out,
 		},
 		{
 			.addr = 0x50,
@@ -52,15 +52,31 @@ bool radeon_ddc_probe(struct radeon_connector *radeon_connector)
 		}
 	};
 
+	/* Read 8 bytes from i2c for extended probe of EDID header */
+	if (requires_extended_probe)
+		msgs[1].len = 8;
+
 	/* on hw with routers, select right port */
 	if (radeon_connector->router.ddc_valid)
 		radeon_router_select_ddc_port(radeon_connector);
 
 	ret = i2c_transfer(&radeon_connector->ddc_bus->adapter, msgs, 2);
-	if (ret == 2)
-		return true;
-
-	return false;
+	if (ret != 2)
+		/* Couldn't find an accessible DDC on this connector */
+		return false;
+	if (requires_extended_probe) {
+		/* Probe also for valid EDID header
+		 * EDID header starts with:
+		 * 0x00,0xFF,0xFF,0xFF,0xFF,0xFF,0xFF,0x00.
+		 * Only the first 6 bytes must be valid as
+		 * drm_edid_block_valid() can fix the last 2 bytes */
+		if (drm_edid_header_is_valid(buf) < 6) {
+			/* Couldn't find an accessible EDID on this
+			 * connector */
+			return false;
+		}
+	}
+	return true;
 }
 
 /* bit banging i2c */

drivers/gpu/drm/radeon/radeon_mode.h

@@ -438,6 +438,9 @@ struct radeon_connector {
 	struct radeon_i2c_chan *ddc_bus;
 	/* some systems have an hdmi and vga port with a shared ddc line */
 	bool shared_ddc;
+	/* for some Radeon chip families we apply an additional EDID header
+	   check as part of the DDC probe */
+	bool requires_extended_probe;
 	bool use_digital;
 	/* we need to mind the EDID between detect
 	   and get modes due to analog/digital/tvencoder */
@@ -476,6 +479,7 @@ extern void radeon_dp_set_link_config(struct drm_connector *connector,
 				      struct drm_display_mode *mode);
 extern void radeon_dp_link_train(struct drm_encoder *encoder,
 				 struct drm_connector *connector);
+extern bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector);
 extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector);
 extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector);
 extern void atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mode);
@@ -514,7 +518,8 @@ extern void radeon_i2c_put_byte(struct radeon_i2c_chan *i2c,
 				u8 val);
 extern void radeon_router_select_ddc_port(struct radeon_connector *radeon_connector);
 extern void radeon_router_select_cd_port(struct radeon_connector *radeon_connector);
-extern bool radeon_ddc_probe(struct radeon_connector *radeon_connector);
+extern bool radeon_ddc_probe(struct radeon_connector *radeon_connector,
+			bool requires_extended_probe);
 extern int radeon_ddc_get_modes(struct radeon_connector *radeon_connector);
 
 extern struct drm_encoder *radeon_best_encoder(struct drm_connector *connector);

drivers/gpu/drm/radeon/radeon_pm.c

@@ -594,6 +594,9 @@ int radeon_pm_init(struct radeon_device *rdev)
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
 							SET_VOLTAGE_TYPE_ASIC_VDDC);
+			if (rdev->pm.default_vddci)
+				radeon_atom_set_voltage(rdev, rdev->pm.default_vddci,
+							SET_VOLTAGE_TYPE_ASIC_VDDCI);
 			if (rdev->pm.default_sclk)
 				radeon_set_engine_clock(rdev, rdev->pm.default_sclk);
 			if (rdev->pm.default_mclk)

drivers/gpu/drm/ttm/ttm_bo.c

@@ -353,8 +353,10 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 
 		ret = ttm_tt_set_user(bo->ttm, current,
 				      bo->buffer_start, bo->num_pages);
-		if (unlikely(ret != 0))
+		if (unlikely(ret != 0)) {
 			ttm_tt_destroy(bo->ttm);
+			bo->ttm = NULL;
+		}
 		break;
 	default:
 		printk(KERN_ERR TTM_PFX "Illegal buffer object type\n");

drivers/hwmon/ibmaem.c

@@ -432,13 +432,15 @@ static int aem_read_sensor(struct aem_data *data, u8 elt, u8 reg,
 	aem_send_message(ipmi);
 
 	res = wait_for_completion_timeout(&ipmi->read_complete, IPMI_TIMEOUT);
-	if (!res)
-		return -ETIMEDOUT;
+	if (!res) {
+		res = -ETIMEDOUT;
+		goto out;
+	}
 
 	if (ipmi->rx_result || ipmi->rx_msg_len != rs_size ||
 	    memcmp(&rs_resp->id, &system_x_id, sizeof(system_x_id))) {
-		kfree(rs_resp);
-		return -ENOENT;
+		res = -ENOENT;
+		goto out;
 	}
 
 	switch (size) {
@@ -463,8 +465,11 @@ static int aem_read_sensor(struct aem_data *data, u8 elt, u8 reg,
 		break;
 	}
 	}
+	res = 0;
 
-	return 0;
+out:
+	kfree(rs_resp);
+	return res;
 }
 
 /* Update AEM energy registers */

drivers/infiniband/ulp/srp/ib_srp.c

@@ -2127,6 +2127,8 @@ static ssize_t srp_create_target(struct device *dev,
 		return -ENOMEM;
 
 	target_host->transportt  = ib_srp_transport_template;
+	target_host->max_channel = 0;
+	target_host->max_id      = 1;
 	target_host->max_lun     = SRP_MAX_LUN;
 	target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb;
 

drivers/isdn/i4l/isdn_net.c

@@ -2531,6 +2531,9 @@ static void _isdn_setup(struct net_device *dev)
 
 	/* Setup the generic properties */
 	dev->flags = IFF_NOARP|IFF_POINTOPOINT;
+
+	/* isdn prepends a header in the tx path, can't share skbs */
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->header_ops = NULL;
 	dev->netdev_ops = &isdn_netdev_ops;
 

drivers/md/dm-io.c

@@ -38,6 +38,8 @@ struct io {
 	struct dm_io_client *client;
 	io_notify_fn callback;
 	void *context;
+	void *vma_invalidate_address;
+	unsigned long vma_invalidate_size;
 } __attribute__((aligned(DM_IO_MAX_REGIONS)));
 
 static struct kmem_cache *_dm_io_cache;
@@ -116,6 +118,10 @@ static void dec_count(struct io *io, unsigned int region, int error)
 		set_bit(region, &io->error_bits);
 
 	if (atomic_dec_and_test(&io->count)) {
+		if (io->vma_invalidate_size)
+			invalidate_kernel_vmap_range(io->vma_invalidate_address,
+						     io->vma_invalidate_size);
+
 		if (io->sleeper)
 			wake_up_process(io->sleeper);
 
@@ -159,6 +165,9 @@ struct dpages {
 
 	unsigned context_u;
 	void *context_ptr;
+
+	void *vma_invalidate_address;
+	unsigned long vma_invalidate_size;
 };
 
 /*
@@ -377,6 +386,9 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	io->sleeper = current;
 	io->client = client;
 
+	io->vma_invalidate_address = dp->vma_invalidate_address;
+	io->vma_invalidate_size = dp->vma_invalidate_size;
+
 	dispatch_io(rw, num_regions, where, dp, io, 1);
 
 	while (1) {
@@ -415,13 +427,21 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io->callback = fn;
 	io->context = context;
 
+	io->vma_invalidate_address = dp->vma_invalidate_address;
+	io->vma_invalidate_size = dp->vma_invalidate_size;
+
 	dispatch_io(rw, num_regions, where, dp, io, 0);
 	return 0;
 }
 
-static int dp_init(struct dm_io_request *io_req, struct dpages *dp)
+static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
+		   unsigned long size)
 {
 	/* Set up dpages based on memory type */
+
+	dp->vma_invalidate_address = NULL;
+	dp->vma_invalidate_size = 0;
+
 	switch (io_req->mem.type) {
 	case DM_IO_PAGE_LIST:
 		list_dp_init(dp, io_req->mem.ptr.pl, io_req->mem.offset);
@@ -432,6 +452,11 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp)
 		break;
 
 	case DM_IO_VMA:
+		flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
+		if ((io_req->bi_rw & RW_MASK) == READ) {
+			dp->vma_invalidate_address = io_req->mem.ptr.vma;
+			dp->vma_invalidate_size = size;
+		}
 		vm_dp_init(dp, io_req->mem.ptr.vma);
 		break;
 
@@ -460,7 +485,7 @@ int dm_io(struct dm_io_request *io_req, unsigned num_regions,
 	int r;
 	struct dpages dp;
 
-	r = dp_init(io_req, &dp);
+	r = dp_init(io_req, &dp, (unsigned long)where->count << SECTOR_SHIFT);
 	if (r)
 		return r;
 

drivers/md/dm-mpath.c

@@ -807,6 +807,11 @@ static int parse_features(struct arg_set *as, struct multipath *m)
 	if (!argc)
 		return 0;
 
+	if (argc > as->argc) {
+		ti->error = "not enough arguments for features";
+		return -EINVAL;
+	}
+
 	do {
 		param_name = shift(as);
 		argc--;

drivers/md/dm-snap-persistent.c

@@ -753,7 +753,7 @@ static int persistent_commit_merge(struct dm_exception_store *store,
 	for (i = 0; i < nr_merged; i++)
 		clear_exception(ps, ps->current_committed - 1 - i);
 
-	r = area_io(ps, WRITE);
+	r = area_io(ps, WRITE_FLUSH_FUA);
 	if (r < 0)
 		return r;
 

drivers/md/dm.c

@@ -37,6 +37,8 @@ static const char *_name = DM_NAME;
 static unsigned int major = 0;
 static unsigned int _major = 0;
 
+static DEFINE_IDR(_minor_idr);
+
 static DEFINE_SPINLOCK(_minor_lock);
 /*
  * For bio-based dm.
@@ -313,6 +315,12 @@ static void __exit dm_exit(void)
 
 	while (i--)
 		_exits[i]();
+
+	/*
+	 * Should be empty by this point.
+	 */
+	idr_remove_all(&_minor_idr);
+	idr_destroy(&_minor_idr);
 }
 
 /*
@@ -1705,8 +1713,6 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 /*-----------------------------------------------------------------
  * An IDR is used to keep track of allocated minor numbers.
  *---------------------------------------------------------------*/
-static DEFINE_IDR(_minor_idr);
-
 static void free_minor(int minor)
 {
 	spin_lock(&_minor_lock);

drivers/misc/Kconfig

@@ -245,8 +245,7 @@ config SGI_XP
 
 config CS5535_MFGPT
 	tristate "CS5535/CS5536 Geode Multi-Function General Purpose Timer (MFGPT) support"
-	depends on PCI
-	depends on X86
+	depends on PCI && X86 && MFD_CS5535
 	default n
 	help
 	  This driver provides access to MFGPT functionality for other

drivers/mmc/host/sdhci-esdhc-imx.c

@@ -74,7 +74,7 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 		if (boarddata && gpio_is_valid(boarddata->cd_gpio)
 				&& gpio_get_value(boarddata->cd_gpio))
 			/* no card, if a valid gpio says so... */
-			val &= SDHCI_CARD_PRESENT;
+			val &= ~SDHCI_CARD_PRESENT;
 		else
 			/* ... in all other cases assume card is present */
 			val |= SDHCI_CARD_PRESENT;