Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

17 files changed, 143 insertions, 103 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index c40f0ae96552..6680ec44779e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3561,6 +3561,8 @@ P:	Christoph Lameter
 M:      clameter@sgi.com
 P:      Pekka Enberg
 M:      penberg@cs.helsinki.fi
+P:      Matt Mackall
+M:      mpm@selenic.com
 L:      linux-mm@kvack.org
 S:      Maintained
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 2d4fcd01bc91..dff9edfc7465 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -232,7 +232,14 @@ config PGTABLE_4
 
 endchoice
 
+if IA64_HP_SIM
+config HZ
+        default 32
+endif
+
+if !IA64_HP_SIM
 source kernel/Kconfig.hz
+endif
 
 config IA64_BRL_EMU
         bool
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index ed8201600354..75f1b109aae8 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -40,7 +40,6 @@ struct split_state {
 static int print_split(struct split_state *s)
 {
         long i, expected, missed = 0;
-        int printed = 0;
         int err = 0;
 
         s->lpg = s->gpg = s->spg = s->exec = 0;
@@ -53,12 +52,6 @@ static int print_split(struct split_state *s)
 
                 pte = lookup_address(addr, &level);
                 if (!pte) {
-                        if (!printed) {
-                                dump_pagetable(addr);
-                                printk(KERN_INFO "CPA %lx no pte level %d\n",
-                                        addr, level);
-                                printed = 1;
-                        }
                         missed++;
                         i++;
                         continue;
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index d28dda574700..f385a4b4a484 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -7,7 +7,7 @@ VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)         := y
 
 vdso-install-$(VDSO64-y)        += vdso.so
-vdso-install-$(VDSO32-y)        += $(vdso32-y:=.so)
+vdso-install-$(VDSO32-y)        += $(vdso32-images)
 
 
 # files to link into the vdso
@@ -63,6 +63,8 @@ vdso32.so-$(CONFIG_X86_32)	+= int80
 vdso32.so-$(CONFIG_COMPAT)      += syscall
 vdso32.so-$(VDSO32-y)           += sysenter
 
+vdso32-images                   = $(vdso32.so-y:%=vdso32-%.so)
+
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1
 
@@ -71,21 +73,21 @@ VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1
 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
 
 targets += vdso32/vdso32.lds
-targets += $(vdso32.so-y:%=vdso32-%.so.dbg) $(vdso32.so-y:%=vdso32-%.so)
+targets += $(vdso32-images) $(vdso32-images:=.dbg)
 targets += vdso32/note.o $(vdso32.so-y:%=vdso32/%.o)
 
-extra-y += $(vdso32.so-y:%=vdso32-%.so)
+extra-y += $(vdso32-images)
 
-$(obj)/vdso32.o: $(vdso32.so-y:%=$(obj)/vdso32-%.so)
+$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
 
 KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
-$(vdso32.so-y:%=$(obj)/vdso32-%.so.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
-$(vdso32.so-y:%=$(obj)/vdso32-%.so.dbg): asflags-$(CONFIG_X86_64) += -m32
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
 
-$(vdso32.so-y:%=$(obj)/vdso32-%.so.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
-                                         $(obj)/vdso32/vdso32.lds \
-                                         $(obj)/vdso32/note.o \
-                                         $(obj)/vdso32/%.o
+$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
+                                 $(obj)/vdso32/vdso32.lds \
+                                 $(obj)/vdso32/note.o \
+                                 $(obj)/vdso32/%.o
         $(call if_changed,vdso)
 
 # Make vdso32-*-syms.lds from each image, and then make sure they match.
diff --git a/drivers/acpi/wmi.c b/drivers/acpi/wmi.c
index 36b84ab418dd..457ed3d3f51c 100644
--- a/drivers/acpi/wmi.c
+++ b/drivers/acpi/wmi.c
@@ -673,11 +673,11 @@ static int __init acpi_wmi_init(void)
 {
         acpi_status result;
 
+        INIT_LIST_HEAD(&wmi_blocks.list);
+
         if (acpi_disabled)
                 return -ENODEV;
 
-        INIT_LIST_HEAD(&wmi_blocks.list);
-
         result = acpi_bus_register_driver(&acpi_wmi_driver);
 
         if (result < 0) {
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 3011919f3ec8..004dae4ea5bc 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3048,6 +3048,8 @@ int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel)
 static int ata_dev_set_mode(struct ata_device *dev)
 {
         struct ata_eh_context *ehc = &dev->link->eh_context;
+        const char *dev_err_whine = "";
+        int ign_dev_err = 0;
         unsigned int err_mask;
         int rc;
 
@@ -3057,41 +3059,57 @@ static int ata_dev_set_mode(struct ata_device *dev)
 
         err_mask = ata_dev_set_xfermode(dev);
 
+        if (err_mask & ~AC_ERR_DEV)
+                goto fail;
+
+        /* revalidate */
+        ehc->i.flags |= ATA_EHI_POST_SETMODE;
+        rc = ata_dev_revalidate(dev, ATA_DEV_UNKNOWN, 0);
+        ehc->i.flags &= ~ATA_EHI_POST_SETMODE;
+        if (rc)
+                return rc;
+
         /* Old CFA may refuse this command, which is just fine */
         if (dev->xfer_shift == ATA_SHIFT_PIO && ata_id_is_cfa(dev->id))
-                err_mask &= ~AC_ERR_DEV;
+                ign_dev_err = 1;
 
         /* Some very old devices and some bad newer ones fail any kind of
            SET_XFERMODE request but support PIO0-2 timings and no IORDY */
         if (dev->xfer_shift == ATA_SHIFT_PIO && !ata_id_has_iordy(dev->id) &&
                         dev->pio_mode <= XFER_PIO_2)
-                err_mask &= ~AC_ERR_DEV;
+                ign_dev_err = 1;
 
         /* Early MWDMA devices do DMA but don't allow DMA mode setting.
            Don't fail an MWDMA0 set IFF the device indicates it is in MWDMA0 */
         if (dev->xfer_shift == ATA_SHIFT_MWDMA &&
             dev->dma_mode == XFER_MW_DMA_0 &&
             (dev->id[63] >> 8) & 1)
-                err_mask &= ~AC_ERR_DEV;
+                ign_dev_err = 1;
 
-        if (err_mask) {
-                ata_dev_printk(dev, KERN_ERR, "failed to set xfermode "
-                               "(err_mask=0x%x)\n", err_mask);
-                return -EIO;
-        }
+        /* if the device is actually configured correctly, ignore dev err */
+        if (dev->xfer_mode == ata_xfer_mask2mode(ata_id_xfermask(dev->id)))
+                ign_dev_err = 1;
 
-        ehc->i.flags |= ATA_EHI_POST_SETMODE;
-        rc = ata_dev_revalidate(dev, ATA_DEV_UNKNOWN, 0);
-        ehc->i.flags &= ~ATA_EHI_POST_SETMODE;
-        if (rc)
-                return rc;
+        if (err_mask & AC_ERR_DEV) {
+                if (!ign_dev_err)
+                        goto fail;
+                else
+                        dev_err_whine = " (device error ignored)";
+        }
 
         DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n",
                 dev->xfer_shift, (int)dev->xfer_mode);
 
-        ata_dev_printk(dev, KERN_INFO, "configured for %s\n",
-                       ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)));
+        ata_dev_printk(dev, KERN_INFO, "configured for %s%s\n",
+                       ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)),
+                       dev_err_whine);
+
         return 0;
+
+ fail:
+        ata_dev_printk(dev, KERN_ERR, "failed to set xfermode "
+                       "(err_mask=0x%x)\n", err_mask);
+        return -EIO;
 }
 
 /**
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index 761a66608d7b..ea567e2b1703 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -772,7 +772,7 @@ static void __exit amd_exit(void)
 }
 
 MODULE_AUTHOR("Alan Cox");
-MODULE_DESCRIPTION("low-level driver for AMD PATA IDE");
+MODULE_DESCRIPTION("low-level driver for AMD and Nvidia PATA IDE");
 MODULE_LICENSE("GPL");
 MODULE_DEVICE_TABLE(pci, amd);
 MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index 333dc15f8ccf..6c59969fd50b 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -127,7 +127,7 @@ static int opti82c611a;		/* Opti82c611A on primary 1, sec 2, both 3 */
 static int opti82c46x;          /* Opti 82c465MV present(pri/sec autodetect) */
 static int qdi;                 /* Set to probe QDI controllers */
 static int winbond;             /* Set to probe Winbond controllers,
-                                        give I/O port if non stdanard */
+                                        give I/O port if non standard */
 static int autospeed;           /* Chip present which snoops speed changes */
 static int pio_mask = 0x1F;     /* PIO range for autospeed devices */
 static int iordy_mask = 0xFFFFFFFF;     /* Use iordy if available */
diff --git a/drivers/ata/pata_ninja32.c b/drivers/ata/pata_ninja32.c
index 1c1b83541d13..15dd649f89ee 100644
--- a/drivers/ata/pata_ninja32.c
+++ b/drivers/ata/pata_ninja32.c
@@ -17,6 +17,7 @@
  *      Base + 0x00 IRQ Status
  *      Base + 0x01 IRQ control
  *      Base + 0x02 Chipset control
+ *      Base + 0x03 Unknown
  *      Base + 0x04 VDMA and reset control + wait bits
  *      Base + 0x08 BMIMBA
  *      Base + 0x0C DMA Length
@@ -174,8 +175,12 @@ static int ninja32_init_one(struct pci_dev *dev, const struct pci_device_id *id)
         ata_std_ports(&ap->ioaddr);
 
         iowrite8(0x05, base + 0x01);    /* Enable interrupt lines */
-        iowrite8(0xB3, base + 0x02);    /* Burst, ?? setup */
-        iowrite8(0x00, base + 0x04);    /* WAIT0 ? */
+        iowrite8(0xBE, base + 0x02);    /* Burst, ?? setup */
+        iowrite8(0x01, base + 0x03);    /* Unknown */
+        iowrite8(0x20, base + 0x04);    /* WAIT0 */
+        iowrite8(0x8f, base + 0x05);    /* Unknown */
+        iowrite8(0xa4, base + 0x1c);    /* Unknown */
+        iowrite8(0x83, base + 0x1d);    /* BMDMA control: WAIT0 */
         /* FIXME: Should we disable them at remove ? */
         return ata_host_activate(host, dev->irq, ata_interrupt,
                                  IRQF_SHARED, &ninja32_sht);
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 39627ab684bf..d119a68c388f 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -84,6 +84,7 @@ enum {
         VIA_BAD_ID      = 0x100, /* Has wrong vendor ID (0x1107) */
         VIA_BAD_AST     = 0x200, /* Don't touch Address Setup Timing */
         VIA_NO_ENABLES  = 0x400, /* Has no enablebits */
+        VIA_SATA_PATA   = 0x800, /* SATA/PATA combined configuration */
 };
 
 /*
@@ -100,7 +101,7 @@ static const struct via_isa_bridge {
         { "vx800",      PCI_DEVICE_ID_VIA_VX800,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
         { "vt8237s",    PCI_DEVICE_ID_VIA_8237S,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
         { "vt8251",     PCI_DEVICE_ID_VIA_8251,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
-        { "cx700",      PCI_DEVICE_ID_VIA_CX700,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
+        { "cx700",      PCI_DEVICE_ID_VIA_CX700,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_SATA_PATA },
         { "vt6410",     PCI_DEVICE_ID_VIA_6410,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_NO_ENABLES},
         { "vt8237a",    PCI_DEVICE_ID_VIA_8237A,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
         { "vt8237",     PCI_DEVICE_ID_VIA_8237,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
@@ -172,6 +173,9 @@ static int via_cable_detect(struct ata_port *ap) {
         if (via_cable_override(pdev))
                 return ATA_CBL_PATA40_SHORT;
 
+        if ((config->flags & VIA_SATA_PATA) && ap->port_no == 0)
+                return ATA_CBL_SATA;
+
         /* Early chips are 40 wire */
         if ((config->flags & VIA_UDMA) < VIA_UDMA_66)
                 return ATA_CBL_PATA40;
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 080b8362f8d6..04b571764aff 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -1716,14 +1716,16 @@ static void mv_host_intr(struct ata_host *host, u32 relevant, unsigned int hc)
         VPRINTK("ENTER, hc%u relevant=0x%08x HC IRQ cause=0x%08x\n",
                 hc, relevant, hc_irq_cause);
 
-        for (port = port0; port < port0 + last_port; port++) {
+        for (port = port0; port < last_port; port++) {
                 struct ata_port *ap = host->ports[port];
-                struct mv_port_priv *pp = ap->private_data;
+                struct mv_port_priv *pp;
                 int have_err_bits, hard_port, shift;
 
                 if ((!ap) || (ap->flags & ATA_FLAG_DISABLED))
                         continue;
 
+                pp = ap->private_data;
+
                 shift = port << 1;              /* (port * 2) */
                 if (port >= MV_PORTS_PER_HC) {
                         shift++;        /* skip bit 8 in the HC Main IRQ reg */
@@ -2879,6 +2881,26 @@ done:
         return rc;
 }
 
+static int mv_create_dma_pools(struct mv_host_priv *hpriv, struct device *dev)
+{
+        hpriv->crqb_pool   = dmam_pool_create("crqb_q", dev, MV_CRQB_Q_SZ,
+                                                             MV_CRQB_Q_SZ, 0);
+        if (!hpriv->crqb_pool)
+                return -ENOMEM;
+
+        hpriv->crpb_pool   = dmam_pool_create("crpb_q", dev, MV_CRPB_Q_SZ,
+                                                             MV_CRPB_Q_SZ, 0);
+        if (!hpriv->crpb_pool)
+                return -ENOMEM;
+
+        hpriv->sg_tbl_pool = dmam_pool_create("sg_tbl", dev, MV_SG_TBL_SZ,
+                                                             MV_SG_TBL_SZ, 0);
+        if (!hpriv->sg_tbl_pool)
+                return -ENOMEM;
+
+        return 0;
+}
+
 /**
  *      mv_platform_probe - handle a positive probe of an soc Marvell
  *      host
@@ -2932,6 +2954,10 @@ static int mv_platform_probe(struct platform_device *pdev)
         hpriv->base = ioremap(res->start, res->end - res->start + 1);
         hpriv->base -= MV_SATAHC0_REG_BASE;
 
+        rc = mv_create_dma_pools(hpriv, &pdev->dev);
+        if (rc)
+                return rc;
+
         /* initialize adapter */
         rc = mv_init_host(host, chip_soc);
         if (rc)
@@ -3068,26 +3094,6 @@ static void mv_print_info(struct ata_host *host)
                scc_s, (MV_HP_FLAG_MSI & hpriv->hp_flags) ? "MSI" : "INTx");
 }
 
-static int mv_create_dma_pools(struct mv_host_priv *hpriv, struct device *dev)
-{
-        hpriv->crqb_pool   = dmam_pool_create("crqb_q", dev, MV_CRQB_Q_SZ,
-                                                             MV_CRQB_Q_SZ, 0);
-        if (!hpriv->crqb_pool)
-                return -ENOMEM;
-
-        hpriv->crpb_pool   = dmam_pool_create("crpb_q", dev, MV_CRPB_Q_SZ,
-                                                             MV_CRPB_Q_SZ, 0);
-        if (!hpriv->crpb_pool)
-                return -ENOMEM;
-
-        hpriv->sg_tbl_pool = dmam_pool_create("sg_tbl", dev, MV_SG_TBL_SZ,
-                                                             MV_SG_TBL_SZ, 0);
-        if (!hpriv->sg_tbl_pool)
-                return -ENOMEM;
-
-        return 0;
-}
-
 /**
  *      mv_pci_init_one - handle a positive probe of a PCI Marvell host
  *      @pdev: PCI device found
diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index 521dc0322ee4..75ef9d0d974d 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/bitmap.h>
 #include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
 
 #include "mlx4.h"
 
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 5d9d70cd17fc..342a2a0105c4 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -30,19 +30,19 @@
 /* Other architectures wishing to use this simple topology API should fill
    in the below functions as appropriate in their own <asm/topology.h> file. */
 #ifndef cpu_to_node
-#define cpu_to_node(cpu)        (0)
+#define cpu_to_node(cpu)        ((void)(cpu),0)
 #endif
 #ifndef parent_node
-#define parent_node(node)       (0)
+#define parent_node(node)       ((void)(node),0)
 #endif
 #ifndef node_to_cpumask
-#define node_to_cpumask(node)   (cpu_online_map)
+#define node_to_cpumask(node)   ((void)node, cpu_online_map)
 #endif
 #ifndef node_to_first_cpu
-#define node_to_first_cpu(node) (0)
+#define node_to_first_cpu(node) ((void)(node),0)
 #endif
 #ifndef pcibus_to_node
-#define pcibus_to_node(node)    (-1)
+#define pcibus_to_node(bus)     ((void)(bus), -1)
 #endif
 
 #ifndef pcibus_to_cpumask
diff --git a/include/asm-ia64/param.h b/include/asm-ia64/param.h
index 49c62dd5eccf..0964c32c1358 100644
--- a/include/asm-ia64/param.h
+++ b/include/asm-ia64/param.h
@@ -19,15 +19,7 @@
 #define MAXHOSTNAMELEN  64      /* max length of hostname */
 
 #ifdef __KERNEL__
-# ifdef CONFIG_IA64_HP_SIM
-  /*
-   * Yeah, simulating stuff is slow, so let us catch some breath between
-   * timer interrupts...
-   */
-#  define HZ      32
-# else
-#  define HZ    CONFIG_HZ
-# endif
+# define HZ             CONFIG_HZ
 # define USER_HZ        HZ
 # define CLOCKS_PER_SEC HZ      /* frequency at which times() counts */
 #else
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index f8c9a2752f06..0a26be353cb3 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -26,8 +26,6 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
 void cpuset_update_task_memory_state(void);
-#define cpuset_nodes_subset_current_mems_allowed(nodes) \
-                nodes_subset((nodes), current->mems_allowed)
 int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
 
 extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask);
@@ -103,7 +101,6 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 #define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY])
 static inline void cpuset_init_current_mems_allowed(void) {}
 static inline void cpuset_update_task_memory_state(void) {}
-#define cpuset_nodes_subset_current_mems_allowed(nodes) (1)
 
 static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
 {
diff --git a/mm/memory.c b/mm/memory.c
index e5628a5fd678..717aa0e3be2d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -989,6 +989,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         int i;
         unsigned int vm_flags;
 
+        if (len <= 0)
+                return 0;
         /* 
          * Require read or write permissions.
          * If 'force' is set, we only require the "MAY" flags.
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 83c69f8a64c2..8d246c3b340f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -116,22 +116,51 @@ static void mpol_rebind_policy(struct mempolicy *pol,
 /* Do sanity checking on a policy */
 static int mpol_check_policy(int mode, nodemask_t *nodes)
 {
-        int empty = nodes_empty(*nodes);
+        int was_empty, is_empty;
+
+        if (!nodes)
+                return 0;
+
+        /*
+         * "Contextualize" the in-coming nodemast for cpusets:
+         * Remember whether in-coming nodemask was empty,  If not,
+         * restrict the nodes to the allowed nodes in the cpuset.
+         * This is guaranteed to be a subset of nodes with memory.
+         */
+        cpuset_update_task_memory_state();
+        is_empty = was_empty = nodes_empty(*nodes);
+        if (!was_empty) {
+                nodes_and(*nodes, *nodes, cpuset_current_mems_allowed);
+                is_empty = nodes_empty(*nodes); /* after "contextualization" */
+        }
 
         switch (mode) {
         case MPOL_DEFAULT:
-                if (!empty)
+                /*
+                 * require caller to specify an empty nodemask
+                 * before "contextualization"
+                 */
+                if (!was_empty)
                         return -EINVAL;
                 break;
         case MPOL_BIND:
         case MPOL_INTERLEAVE:
-                /* Preferred will only use the first bit, but allow
-                   more for now. */
-                if (empty)
+                /*
+                 * require at least 1 valid node after "contextualization"
+                 */
+                if (is_empty)
+                        return -EINVAL;
+                break;
+        case MPOL_PREFERRED:
+                /*
+                 * Did caller specify invalid nodes?
+                 * Don't silently accept this as "local allocation".
+                 */
+                if (!was_empty && is_empty)
                         return -EINVAL;
                 break;
         }
-        return nodes_subset(*nodes, node_states[N_HIGH_MEMORY]) ? 0 : -EINVAL;
+        return 0;
 }
 
 /* Generate a custom zonelist for the BIND policy. */
@@ -188,8 +217,6 @@ static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
         switch (mode) {
         case MPOL_INTERLEAVE:
                 policy->v.nodes = *nodes;
-                nodes_and(policy->v.nodes, policy->v.nodes,
-                                        node_states[N_HIGH_MEMORY]);
                 if (nodes_weight(policy->v.nodes) == 0) {
                         kmem_cache_free(policy_cache, policy);
                         return ERR_PTR(-EINVAL);
@@ -421,18 +448,6 @@ static int mbind_range(struct vm_area_struct *vma, unsigned long start,
         return err;
 }
 
-static int contextualize_policy(int mode, nodemask_t *nodes)
-{
-        if (!nodes)
-                return 0;
-
-        cpuset_update_task_memory_state();
-        if (!cpuset_nodes_subset_current_mems_allowed(*nodes))
-                return -EINVAL;
-        return mpol_check_policy(mode, nodes);
-}
-
-
 /*
  * Update task->flags PF_MEMPOLICY bit: set iff non-default
  * mempolicy.  Allows more rapid checking of this (combined perhaps
@@ -468,7 +483,7 @@ static long do_set_mempolicy(int mode, nodemask_t *nodes)
 {
         struct mempolicy *new;
 
-        if (contextualize_policy(mode, nodes))
+        if (mpol_check_policy(mode, nodes))
                 return -EINVAL;
         new = mpol_new(mode, nodes);
         if (IS_ERR(new))
@@ -915,10 +930,6 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len,
         err = get_nodes(&nodes, nmask, maxnode);
         if (err)
                 return err;
-#ifdef CONFIG_CPUSETS
-        /* Restrict the nodes to the allowed nodes in the cpuset */
-        nodes_and(nodes, nodes, current->mems_allowed);
-#endif
         return do_mbind(start, len, mode, &nodes, flags);
 }