# HG changeset patch
# User cl349@xxxxxxxxxxxxxxxxxxxx
# Node ID 5a63f675107cd84970e299a291485420d97bc139
# Parent d609de73b9faca3da11509e04f09e092e065ffcd
Update to Linux 2.6.15.
Signed-off-by: Christian Limpach <Christian.Limpach@xxxxxxxxxxxx>
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xen0_x86_32
--- a/buildconfigs/linux-defconfig_xen0_x86_32 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xen0_x86_32 Wed Feb 1 18:00:19 2006
@@ -1,10 +1,11 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xen0
-# Tue Jan 31 18:56:38 2006
-#
+# Linux kernel version: 2.6.15-xen0
+# Wed Feb 1 15:54:13 2006
+#
+CONFIG_X86_32=y
+CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
-CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y
@@ -35,6 +36,7 @@
CONFIG_KOBJECT_UEVENT=y
# CONFIG_IKCONFIG is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -62,6 +64,24 @@
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
+
+#
+# Block layer
+#
+# CONFIG_LBD is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Processor type and features
@@ -108,8 +128,10 @@
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
+CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
# CONFIG_SMP is not set
CONFIG_PREEMPT_NONE=y
# CONFIG_PREEMPT_VOLUNTARY is not set
@@ -142,6 +164,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
CONFIG_MTRR=y
# CONFIG_REGPARM is not set
CONFIG_SECCOMP=y
@@ -257,6 +280,10 @@
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
# CONFIG_NETFILTER_NETLINK is not set
#
@@ -346,8 +373,11 @@
# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
# CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
#
# Network testing
@@ -409,16 +439,7 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=4096
CONFIG_BLK_DEV_INITRD=y
-# CONFIG_LBD is not set
# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
# CONFIG_ATA_OVER_ETH is not set
#
@@ -464,6 +485,7 @@
# CONFIG_BLK_DEV_CY82C693 is not set
# CONFIG_BLK_DEV_CS5520 is not set
# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_CS5535 is not set
# CONFIG_BLK_DEV_HPT34X is not set
# CONFIG_BLK_DEV_HPT366 is not set
# CONFIG_BLK_DEV_SC1200 is not set
@@ -519,6 +541,7 @@
#
# SCSI low-level drivers
#
+# CONFIG_ISCSI_TCP is not set
CONFIG_BLK_DEV_3W_XXXX_RAID=y
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_ACARD is not set
@@ -548,16 +571,17 @@
CONFIG_SCSI_ATA_PIIX=y
# CONFIG_SCSI_SATA_MV is not set
# CONFIG_SCSI_SATA_NV is not set
+# CONFIG_SCSI_PDC_ADMA is not set
+# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_PROMISE=y
-# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_SX4=y
CONFIG_SCSI_SATA_SIL=y
+CONFIG_SCSI_SATA_SIL24=y
# CONFIG_SCSI_SATA_SIS is not set
# CONFIG_SCSI_SATA_ULI is not set
# CONFIG_SCSI_SATA_VIA is not set
# CONFIG_SCSI_SATA_VITESSE is not set
CONFIG_SCSI_SATA_INTEL_COMBINED=y
-# CONFIG_SCSI_CPQFCTS is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA_PIO is not set
# CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -566,7 +590,6 @@
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_ISP is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=y
@@ -807,7 +830,6 @@
#
# Serial drivers
#
-# CONFIG_SERIAL_8250 is not set
#
# Non-8250 serial port support
@@ -870,6 +892,7 @@
# TPM devices
#
# CONFIG_TCG_TPM is not set
+# CONFIG_TELCLOCK is not set
#
# I2C support
@@ -954,12 +977,15 @@
#
# USB Device Class drivers
#
-# CONFIG_USB_BLUETOOTH_TTY is not set
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed;
see USB_STORAGE Help for more information
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
#
# CONFIG_USB_STORAGE is not set
@@ -1212,6 +1238,11 @@
# CONFIG_NLS_UTF8 is not set
#
+# Instrumentation Support
+#
+# CONFIG_KPROBES is not set
+
+#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
@@ -1228,10 +1259,11 @@
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_INFO is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
CONFIG_FRAME_POINTER=y
+# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_EARLY_PRINTK=y
# CONFIG_DEBUG_STACKOVERFLOW is not set
-# CONFIG_KPROBES is not set
# CONFIG_DEBUG_STACK_USAGE is not set
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_4KSTACKS is not set
@@ -1312,4 +1344,3 @@
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_X86_BIOS_REBOOT=y
-CONFIG_PC=y
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xen0_x86_64
--- a/buildconfigs/linux-defconfig_xen0_x86_64 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xen0_x86_64 Wed Feb 1 18:00:19 2006
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xen0
-# Tue Jan 31 16:21:00 2006
+# Linux kernel version: 2.6.15-xen0
+# Wed Feb 1 15:50:08 2006
#
CONFIG_X86_64=y
CONFIG_64BIT=y
@@ -40,6 +40,7 @@
CONFIG_KOBJECT_UEVENT=y
# CONFIG_IKCONFIG is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -67,6 +68,24 @@
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
+
+#
+# Block layer
+#
+# CONFIG_LBD is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Processor type and features
@@ -88,7 +107,6 @@
CONFIG_PREEMPT_NONE=y
# CONFIG_PREEMPT_VOLUNTARY is not set
# CONFIG_PREEMPT is not set
-# CONFIG_NUMA is not set
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
@@ -97,6 +115,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
CONFIG_SWIOTLB=y
CONFIG_DUMMY_IOMMU=y
@@ -196,6 +215,10 @@
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
# CONFIG_NETFILTER_NETLINK is not set
#
@@ -285,8 +308,11 @@
# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
# CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
#
# Network testing
@@ -348,16 +374,7 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_INITRD=y
-# CONFIG_LBD is not set
# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
# CONFIG_ATA_OVER_ETH is not set
#
@@ -458,6 +475,7 @@
#
# SCSI low-level drivers
#
+# CONFIG_ISCSI_TCP is not set
CONFIG_BLK_DEV_3W_XXXX_RAID=y
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_ACARD is not set
@@ -488,10 +506,12 @@
CONFIG_SCSI_ATA_PIIX=y
# CONFIG_SCSI_SATA_MV is not set
# CONFIG_SCSI_SATA_NV is not set
+# CONFIG_SCSI_PDC_ADMA is not set
+# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_PROMISE=y
-# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_SX4=y
CONFIG_SCSI_SATA_SIL=y
+CONFIG_SCSI_SATA_SIL24=y
# CONFIG_SCSI_SATA_SIS is not set
# CONFIG_SCSI_SATA_ULI is not set
# CONFIG_SCSI_SATA_VIA is not set
@@ -499,7 +519,6 @@
CONFIG_SCSI_SATA_INTEL_COMBINED=y
CONFIG_SCSI_BUSLOGIC=y
# CONFIG_SCSI_OMIT_FLASHPOINT is not set
-# CONFIG_SCSI_CPQFCTS is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA is not set
# CONFIG_SCSI_EATA_PIO is not set
@@ -510,7 +529,6 @@
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_ISP is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=y
@@ -750,7 +768,6 @@
#
# Serial drivers
#
-# CONFIG_SERIAL_8250 is not set
#
# Non-8250 serial port support
@@ -800,6 +817,7 @@
# TPM devices
#
# CONFIG_TCG_TPM is not set
+# CONFIG_TELCLOCK is not set
#
# I2C support
@@ -884,12 +902,15 @@
#
# USB Device Class drivers
#
-# CONFIG_USB_BLUETOOTH_TTY is not set
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed;
see USB_STORAGE Help for more information
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
#
# CONFIG_USB_STORAGE is not set
@@ -989,6 +1010,7 @@
CONFIG_INFINIBAND_IPOIB=y
CONFIG_INFINIBAND_IPOIB_DEBUG=y
CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
+CONFIG_INFINIBAND_SRP=y
#
# SN Devices
@@ -1155,9 +1177,10 @@
# CONFIG_NLS_UTF8 is not set
#
-# Profiling support
+# Instrumentation Support
#
# CONFIG_PROFILING is not set
+# CONFIG_KPROBES is not set
#
# Kernel hacking
@@ -1173,10 +1196,10 @@
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
CONFIG_FRAME_POINTER=y
-# CONFIG_CHECKING is not set
+# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_INIT_DEBUG is not set
-# CONFIG_KPROBES is not set
#
# Security options
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xenU_x86_32
--- a/buildconfigs/linux-defconfig_xenU_x86_32 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xenU_x86_32 Wed Feb 1 18:00:19 2006
@@ -1,10 +1,11 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xenU
-# Tue Jan 31 18:57:16 2006
-#
+# Linux kernel version: 2.6.15-xenU
+# Wed Feb 1 17:28:35 2006
+#
+CONFIG_X86_32=y
+CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
-CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y
@@ -35,6 +36,7 @@
# CONFIG_IKCONFIG is not set
# CONFIG_CPUSETS is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -63,6 +65,24 @@
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
CONFIG_STOP_MACHINE=y
+
+#
+# Block layer
+#
+# CONFIG_LBD is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Processor type and features
@@ -109,8 +129,10 @@
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
+CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
CONFIG_SMP=y
CONFIG_SMP_ALTERNATIVES=y
CONFIG_NR_CPUS=8
@@ -141,6 +163,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
# CONFIG_REGPARM is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
@@ -212,8 +235,11 @@
# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
# CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
#
# Network testing
@@ -248,16 +274,7 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=4096
CONFIG_BLK_DEV_INITRD=y
-# CONFIG_LBD is not set
# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
# CONFIG_ATA_OVER_ETH is not set
#
@@ -295,6 +312,7 @@
#
# SCSI low-level drivers
#
+# CONFIG_ISCSI_TCP is not set
# CONFIG_SCSI_SATA is not set
# CONFIG_SCSI_DEBUG is not set
@@ -503,6 +521,11 @@
# CONFIG_NLS_UTF8 is not set
#
+# Instrumentation Support
+#
+# CONFIG_KPROBES is not set
+
+#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
@@ -519,10 +542,11 @@
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_INFO is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
CONFIG_FRAME_POINTER=y
+# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_EARLY_PRINTK=y
# CONFIG_DEBUG_STACKOVERFLOW is not set
-# CONFIG_KPROBES is not set
# CONFIG_DEBUG_STACK_USAGE is not set
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_4KSTACKS is not set
@@ -598,4 +622,3 @@
CONFIG_X86_SMP=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_X86_TRAMPOLINE=y
-CONFIG_PC=y
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xenU_x86_64
--- a/buildconfigs/linux-defconfig_xenU_x86_64 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xenU_x86_64 Wed Feb 1 18:00:19 2006
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xenU
-# Tue Jan 31 19:51:18 2006
+# Linux kernel version: 2.6.15-xenU
+# Wed Feb 1 15:49:27 2006
#
CONFIG_X86_64=y
CONFIG_64BIT=y
@@ -42,6 +42,7 @@
# CONFIG_IKCONFIG is not set
# CONFIG_CPUSETS is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -72,6 +73,24 @@
CONFIG_STOP_MACHINE=y
#
+# Block layer
+#
+CONFIG_LBD=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+
+#
# Processor type and features
#
# CONFIG_MK8 is not set
@@ -90,7 +109,6 @@
# CONFIG_PREEMPT_VOLUNTARY is not set
# CONFIG_PREEMPT is not set
CONFIG_PREEMPT_BKL=y
-# CONFIG_NUMA is not set
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
@@ -99,6 +117,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
CONFIG_NR_CPUS=8
# CONFIG_HOTPLUG_CPU is not set
@@ -219,6 +238,10 @@
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
# CONFIG_NETFILTER_NETLINK is not set
#
@@ -384,10 +407,18 @@
CONFIG_NET_DIVERT=y
# CONFIG_ECONET is not set
CONFIG_WAN_ROUTER=m
+
+#
+# QoS and/or fair queueing
+#
CONFIG_NET_SCHED=y
CONFIG_NET_SCH_CLK_JIFFIES=y
# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
# CONFIG_NET_SCH_CLK_CPU is not set
+
+#
+# Queueing/Scheduling
+#
CONFIG_NET_SCH_CBQ=m
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_HFSC=m
@@ -401,8 +432,10 @@
CONFIG_NET_SCH_DSMARK=m
CONFIG_NET_SCH_NETEM=m
CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_QOS=y
-CONFIG_NET_ESTIMATOR=y
+
+#
+# Classification
+#
CONFIG_NET_CLS=y
# CONFIG_NET_CLS_BASIC is not set
CONFIG_NET_CLS_TCINDEX=m
@@ -411,13 +444,14 @@
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
CONFIG_CLS_U32_PERF=y
-CONFIG_NET_CLS_IND=y
# CONFIG_CLS_U32_MARK is not set
CONFIG_NET_CLS_RSVP=m
CONFIG_NET_CLS_RSVP6=m
# CONFIG_NET_EMATCH is not set
# CONFIG_NET_CLS_ACT is not set
CONFIG_NET_CLS_POLICE=y
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_ESTIMATOR=y
#
# Network testing
@@ -496,7 +530,6 @@
CONFIG_BT_HCIUART=m
CONFIG_BT_HCIUART_H4=y
CONFIG_BT_HCIUART_BCSP=y
-CONFIG_BT_HCIUART_BCSP_TXCRC=y
CONFIG_BT_HCIVHCI=m
# CONFIG_IEEE80211 is not set
@@ -524,16 +557,7 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_INITRD=y
-CONFIG_LBD=y
# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
# CONFIG_ATA_OVER_ETH is not set
#
@@ -572,6 +596,7 @@
#
# SCSI low-level drivers
#
+# CONFIG_ISCSI_TCP is not set
CONFIG_SCSI_SATA=m
# CONFIG_SCSI_DEBUG is not set
@@ -647,6 +672,7 @@
#
# ATM drivers
#
+# CONFIG_ATM_DUMMY is not set
CONFIG_ATM_TCP=m
CONFIG_PPP=m
CONFIG_PPP_MULTILINK=y
@@ -655,6 +681,7 @@
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
# CONFIG_PPP_BSDCOMP is not set
+# CONFIG_PPP_MPPE is not set
CONFIG_PPPOE=m
CONFIG_PPPOATM=m
# CONFIG_SLIP is not set
@@ -705,7 +732,7 @@
CONFIG_FS_POSIX_ACL=y
CONFIG_XFS_FS=m
CONFIG_XFS_EXPORT=y
-CONFIG_XFS_QUOTA=m
+# CONFIG_XFS_QUOTA is not set
CONFIG_XFS_SECURITY=y
CONFIG_XFS_POSIX_ACL=y
# CONFIG_XFS_RT is not set
@@ -877,9 +904,10 @@
CONFIG_NLS_UTF8=m
#
-# Profiling support
+# Instrumentation Support
#
# CONFIG_PROFILING is not set
+# CONFIG_KPROBES is not set
#
# Kernel hacking
@@ -895,9 +923,10 @@
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
CONFIG_FRAME_POINTER=y
+# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_INIT_DEBUG is not set
-# CONFIG_KPROBES is not set
#
# Security options
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xen_x86_32
--- a/buildconfigs/linux-defconfig_xen_x86_32 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xen_x86_32 Wed Feb 1 18:00:19 2006
@@ -1,10 +1,11 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xen
-# Tue Jan 31 19:01:58 2006
-#
+# Linux kernel version: 2.6.15-xen
+# Wed Feb 1 17:28:24 2006
+#
+CONFIG_X86_32=y
+CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
-CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y
@@ -38,6 +39,7 @@
# CONFIG_IKCONFIG is not set
# CONFIG_CPUSETS is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_EMBEDDED=y
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -47,7 +49,6 @@
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_SHMEM=y
CONFIG_CC_ALIGN_FUNCTIONS=0
CONFIG_CC_ALIGN_LABELS=0
@@ -67,6 +68,24 @@
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
CONFIG_STOP_MACHINE=y
+
+#
+# Block layer
+#
+CONFIG_LBD=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Processor type and features
@@ -113,8 +132,10 @@
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
+CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
CONFIG_SMP=y
CONFIG_SMP_ALTERNATIVES=y
CONFIG_NR_CPUS=8
@@ -148,6 +169,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
CONFIG_MTRR=y
# CONFIG_REGPARM is not set
CONFIG_SECCOMP=y
@@ -156,8 +178,8 @@
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
CONFIG_PHYSICAL_START=0x100000
+# CONFIG_CRASH_DUMP is not set
CONFIG_HOTPLUG_CPU=y
-# CONFIG_CRASH_DUMP is not set
#
# Power management options (ACPI, APM)
@@ -175,6 +197,7 @@
CONFIG_ACPI_HOTKEY=m
CONFIG_ACPI_FAN=m
CONFIG_ACPI_PROCESSOR=m
+CONFIG_ACPI_HOTPLUG_CPU=y
CONFIG_ACPI_THERMAL=m
CONFIG_ACPI_ASUS=m
CONFIG_ACPI_IBM=m
@@ -185,7 +208,7 @@
CONFIG_ACPI_POWER=y
CONFIG_ACPI_SYSTEM=y
# CONFIG_X86_PM_TIMER is not set
-# CONFIG_ACPI_CONTAINER is not set
+CONFIG_ACPI_CONTAINER=m
#
# CPU Frequency scaling
@@ -206,7 +229,6 @@
# CONFIG_PCI_LEGACY_PROC is not set
# CONFIG_PCI_DEBUG is not set
CONFIG_SCx200=m
-# CONFIG_HOTPLUG_CPU is not set
#
# PCCARD (PCMCIA/CardBus) support
@@ -341,6 +363,10 @@
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
CONFIG_NETFILTER_NETLINK=m
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NETFILTER_NETLINK_LOG=m
@@ -534,10 +560,18 @@
CONFIG_ECONET_AUNUDP=y
CONFIG_ECONET_NATIVE=y
CONFIG_WAN_ROUTER=m
+
+#
+# QoS and/or fair queueing
+#
CONFIG_NET_SCHED=y
CONFIG_NET_SCH_CLK_JIFFIES=y
# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
# CONFIG_NET_SCH_CLK_CPU is not set
+
+#
+# Queueing/Scheduling
+#
CONFIG_NET_SCH_CBQ=m
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_HFSC=m
@@ -551,8 +585,10 @@
CONFIG_NET_SCH_DSMARK=m
CONFIG_NET_SCH_NETEM=m
CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_QOS=y
-CONFIG_NET_ESTIMATOR=y
+
+#
+# Classification
+#
CONFIG_NET_CLS=y
CONFIG_NET_CLS_BASIC=m
CONFIG_NET_CLS_TCINDEX=m
@@ -561,7 +597,6 @@
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
# CONFIG_CLS_U32_PERF is not set
-# CONFIG_NET_CLS_IND is not set
# CONFIG_CLS_U32_MARK is not set
CONFIG_NET_CLS_RSVP=m
CONFIG_NET_CLS_RSVP6=m
@@ -574,6 +609,8 @@
CONFIG_NET_EMATCH_TEXT=m
# CONFIG_NET_CLS_ACT is not set
CONFIG_NET_CLS_POLICE=y
+# CONFIG_NET_CLS_IND is not set
+CONFIG_NET_ESTIMATOR=y
#
# Network testing
@@ -676,7 +713,6 @@
CONFIG_BT_HCIUART=m
CONFIG_BT_HCIUART_H4=y
CONFIG_BT_HCIUART_BCSP=y
-# CONFIG_BT_HCIUART_BCSP_TXCRC is not set
CONFIG_BT_HCIBCM203X=m
# CONFIG_BT_HCIBPA10X is not set
CONFIG_BT_HCIBFUSB=m
@@ -731,6 +767,7 @@
CONFIG_NFTL=m
CONFIG_NFTL_RW=y
CONFIG_INFTL=m
+CONFIG_RFD_FTL=m
#
# RAM/ROM/Flash chip drivers
@@ -821,6 +858,12 @@
CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADDRESS=0
# CONFIG_MTD_NAND_DISKONCHIP_BBTWRITE is not set
# CONFIG_MTD_NAND_NANDSIM is not set
+
+#
+# OneNAND Flash Device Drivers
+#
+CONFIG_MTD_ONENAND=m
+# CONFIG_MTD_ONENAND_VERIFY_WRITE is not set
#
# Parallel port support
@@ -896,18 +939,9 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_INITRD=y
-CONFIG_LBD=y
CONFIG_CDROM_PKTCDVD=m
CONFIG_CDROM_PKTCDVD_BUFFERS=8
# CONFIG_CDROM_PKTCDVD_WCACHE is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
CONFIG_ATA_OVER_ETH=m
#
@@ -957,6 +991,7 @@
CONFIG_BLK_DEV_CY82C693=y
CONFIG_BLK_DEV_CS5520=y
CONFIG_BLK_DEV_CS5530=y
+CONFIG_BLK_DEV_CS5535=m
CONFIG_BLK_DEV_HPT34X=y
# CONFIG_HPT34X_AUTODMA is not set
CONFIG_BLK_DEV_HPT366=y
@@ -1010,12 +1045,13 @@
#
CONFIG_SCSI_SPI_ATTRS=m
CONFIG_SCSI_FC_ATTRS=m
-# CONFIG_SCSI_ISCSI_ATTRS is not set
+CONFIG_SCSI_ISCSI_ATTRS=m
CONFIG_SCSI_SAS_ATTRS=m
#
# SCSI low-level drivers
#
+CONFIG_ISCSI_TCP=m
CONFIG_BLK_DEV_3W_XXXX_RAID=m
CONFIG_SCSI_3W_9XXX=m
CONFIG_SCSI_ACARD=m
@@ -1046,16 +1082,17 @@
CONFIG_SCSI_ATA_PIIX=m
CONFIG_SCSI_SATA_MV=m
CONFIG_SCSI_SATA_NV=m
+CONFIG_SCSI_PDC_ADMA=m
+# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_PROMISE=m
-# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_SX4=m
CONFIG_SCSI_SATA_SIL=m
+CONFIG_SCSI_SATA_SIL24=m
CONFIG_SCSI_SATA_SIS=m
CONFIG_SCSI_SATA_ULI=m
CONFIG_SCSI_SATA_VIA=m
CONFIG_SCSI_SATA_VITESSE=m
CONFIG_SCSI_SATA_INTEL_COMBINED=y
-# CONFIG_SCSI_CPQFCTS is not set
CONFIG_SCSI_DMX3191D=m
CONFIG_SCSI_EATA_PIO=m
CONFIG_SCSI_FUTURE_DOMAIN=m
@@ -1074,11 +1111,9 @@
CONFIG_SCSI_IPR=m
# CONFIG_SCSI_IPR_TRACE is not set
# CONFIG_SCSI_IPR_DUMP is not set
-CONFIG_SCSI_QLOGIC_ISP=m
CONFIG_SCSI_QLOGIC_FC=m
CONFIG_SCSI_QLOGIC_FC_FIRMWARE=y
CONFIG_SCSI_QLOGIC_1280=m
-CONFIG_SCSI_QLOGIC_1280_1040=y
CONFIG_SCSI_QLA2XXX=m
CONFIG_SCSI_QLA21XX=m
CONFIG_SCSI_QLA22XX=m
@@ -1206,7 +1241,6 @@
# PHY device support
#
CONFIG_PHYLIB=m
-CONFIG_PHYCONTROL=y
#
# MII PHY device drivers
@@ -1302,7 +1336,6 @@
# CONFIG_IXGB_NAPI is not set
CONFIG_S2IO=m
# CONFIG_S2IO_NAPI is not set
-# CONFIG_2BUFF_MODE is not set
#
# Token Ring devices
@@ -1418,6 +1451,7 @@
#
# ATM drivers
#
+CONFIG_ATM_DUMMY=m
CONFIG_ATM_TCP=m
CONFIG_ATM_LANAI=m
CONFIG_ATM_ENI=m
@@ -1462,6 +1496,7 @@
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_MPPE=m
CONFIG_PPPOE=m
CONFIG_PPPOATM=m
CONFIG_SLIP=m
@@ -1674,6 +1709,7 @@
CONFIG_TOUCHSCREEN_MK712=m
CONFIG_INPUT_MISC=y
CONFIG_INPUT_PCSPKR=m
+CONFIG_INPUT_WISTRON_BTNS=m
CONFIG_INPUT_UINPUT=m
#
@@ -1816,17 +1852,20 @@
# PCMCIA character devices
#
CONFIG_SYNCLINK_CS=m
+CONFIG_CARDMAN_4000=m
+CONFIG_CARDMAN_4040=m
CONFIG_MWAVE=m
CONFIG_SCx200_GPIO=m
CONFIG_RAW_DRIVER=m
+CONFIG_MAX_RAW_DEVS=256
# CONFIG_HPET is not set
-CONFIG_MAX_RAW_DEVS=256
CONFIG_HANGCHECK_TIMER=m
#
# TPM devices
#
# CONFIG_TCG_TPM is not set
+CONFIG_TELCLOCK=m
#
# I2C support
@@ -1883,6 +1922,7 @@
CONFIG_SENSORS_PCF8591=m
CONFIG_SENSORS_RTC8564=m
CONFIG_SENSORS_MAX6875=m
+CONFIG_RTC_X1205_I2C=m
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
@@ -1964,6 +2004,7 @@
# Video Adapters
#
CONFIG_VIDEO_BT848=m
+# CONFIG_VIDEO_BT848_DVB is not set
CONFIG_VIDEO_SAA6588=m
CONFIG_VIDEO_BWQCAM=m
CONFIG_VIDEO_CQCAM=m
@@ -1990,7 +2031,10 @@
CONFIG_VIDEO_HEXIUM_GEMINI=m
CONFIG_VIDEO_CX88=m
# CONFIG_VIDEO_CX88_DVB is not set
+CONFIG_VIDEO_EM28XX=m
CONFIG_VIDEO_OVCAMCHIP=m
+CONFIG_VIDEO_AUDIO_DECODER=m
+CONFIG_VIDEO_DECODER=m
#
# Radio Adapters
@@ -2098,6 +2142,7 @@
# ATSC (North American/Korean Terresterial DTV) frontends
#
CONFIG_DVB_NXT2002=m
+CONFIG_DVB_NXT200X=m
CONFIG_DVB_OR51211=m
CONFIG_DVB_OR51132=m
CONFIG_DVB_BCM3510=m
@@ -2118,7 +2163,6 @@
CONFIG_FB_CFB_FILLRECT=m
CONFIG_FB_CFB_COPYAREA=m
CONFIG_FB_CFB_IMAGEBLIT=m
-CONFIG_FB_SOFT_CURSOR=m
# CONFIG_FB_MACMODES is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
@@ -2134,6 +2178,7 @@
CONFIG_VIDEO_SELECT=y
CONFIG_FB_HGA=m
# CONFIG_FB_HGA_ACCEL is not set
+CONFIG_FB_S1D13XXX=m
CONFIG_FB_NVIDIA=m
CONFIG_FB_NVIDIA_I2C=y
CONFIG_FB_RIVA=m
@@ -2176,7 +2221,6 @@
# CONFIG_FB_PM3 is not set
CONFIG_FB_GEODE=y
CONFIG_FB_GEODE_GX1=m
-CONFIG_FB_S1D13XXX=m
CONFIG_FB_VIRTUAL=m
#
@@ -2185,6 +2229,7 @@
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=m
+# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
# CONFIG_FONTS is not set
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
@@ -2204,6 +2249,8 @@
# Advanced Linux Sound Architecture
#
CONFIG_SND=m
+CONFIG_SND_AC97_CODEC=m
+CONFIG_SND_AC97_BUS=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_HWDEP=m
@@ -2231,8 +2278,6 @@
CONFIG_SND_MTPAV=m
CONFIG_SND_SERIAL_U16550=m
CONFIG_SND_MPU401=m
-CONFIG_SND_AC97_CODEC=m
-CONFIG_SND_AC97_BUS=m
#
# PCI devices
@@ -2295,30 +2340,13 @@
# Open Sound System
#
CONFIG_SOUND_PRIME=m
-CONFIG_SOUND_BT878=m
-CONFIG_SOUND_CMPCI=m
-# CONFIG_SOUND_CMPCI_FM is not set
-# CONFIG_SOUND_CMPCI_MIDI is not set
-CONFIG_SOUND_CMPCI_JOYSTICK=y
-CONFIG_SOUND_EMU10K1=m
+# CONFIG_OBSOLETE_OSS_DRIVER is not set
CONFIG_SOUND_FUSION=m
-CONFIG_SOUND_CS4281=m
-CONFIG_SOUND_ES1370=m
-CONFIG_SOUND_ES1371=m
-CONFIG_SOUND_ESSSOLO1=m
-CONFIG_SOUND_MAESTRO=m
-CONFIG_SOUND_MAESTRO3=m
CONFIG_SOUND_ICH=m
-CONFIG_SOUND_SONICVIBES=m
CONFIG_SOUND_TRIDENT=m
# CONFIG_SOUND_MSNDCLAS is not set
# CONFIG_SOUND_MSNDPIN is not set
-CONFIG_SOUND_VIA82CXXX=m
CONFIG_SOUND_TVMIXER=m
-CONFIG_SOUND_ALI5455=m
-CONFIG_SOUND_FORTE=m
-CONFIG_SOUND_RME96XX=m
-CONFIG_SOUND_AD1980=m
#
# USB support
@@ -2355,15 +2383,15 @@
# USB Device Class drivers
#
# CONFIG_OBSOLETE_OSS_USB_DRIVER is not set
-
-#
-# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem
-#
CONFIG_USB_ACM=m
CONFIG_USB_PRINTER=m
#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed;
see USB_STORAGE Help for more information
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
#
CONFIG_USB_STORAGE=m
# CONFIG_USB_STORAGE_DEBUG is not set
@@ -2375,7 +2403,6 @@
CONFIG_USB_STORAGE_SDDR09=y
CONFIG_USB_STORAGE_SDDR55=y
CONFIG_USB_STORAGE_JUMPSHOT=y
-CONFIG_USB_STORAGE_ONETOUCH=y
#
# USB Input Devices
@@ -2460,6 +2487,7 @@
CONFIG_USB_SERIAL=m
CONFIG_USB_SERIAL_GENERIC=y
CONFIG_USB_SERIAL_AIRPRIME=m
+CONFIG_USB_SERIAL_ANYDATA=m
CONFIG_USB_SERIAL_BELKIN=m
CONFIG_USB_SERIAL_WHITEHEAT=m
CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m
@@ -2593,7 +2621,7 @@
CONFIG_FS_POSIX_ACL=y
CONFIG_XFS_FS=m
CONFIG_XFS_EXPORT=y
-CONFIG_XFS_QUOTA=m
+# CONFIG_XFS_QUOTA is not set
CONFIG_XFS_SECURITY=y
CONFIG_XFS_POSIX_ACL=y
CONFIG_XFS_RT=y
@@ -2660,6 +2688,7 @@
CONFIG_JFFS2_FS=m
CONFIG_JFFS2_FS_DEBUG=0
CONFIG_JFFS2_FS_WRITEBUFFER=y
+# CONFIG_JFFS2_SUMMARY is not set
# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set
CONFIG_JFFS2_ZLIB=y
CONFIG_JFFS2_RTIME=y
@@ -2787,6 +2816,11 @@
CONFIG_NLS_UTF8=m
#
+# Instrumentation Support
+#
+# CONFIG_KPROBES is not set
+
+#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
@@ -2803,10 +2837,11 @@
# CONFIG_DEBUG_BUGVERBOSE is not set
# CONFIG_DEBUG_INFO is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
# CONFIG_FRAME_POINTER is not set
+# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_EARLY_PRINTK is not set
# CONFIG_DEBUG_STACKOVERFLOW is not set
-# CONFIG_KPROBES is not set
# CONFIG_DEBUG_STACK_USAGE is not set
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_4KSTACKS is not set
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/linux-defconfig_xen_x86_64
--- a/buildconfigs/linux-defconfig_xen_x86_64 Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/linux-defconfig_xen_x86_64 Wed Feb 1 18:00:19 2006
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-xen
-# Tue Jan 31 18:19:07 2006
+# Linux kernel version: 2.6.15-xen
+# Wed Feb 1 15:51:35 2006
#
CONFIG_X86_64=y
CONFIG_64BIT=y
@@ -42,6 +42,7 @@
# CONFIG_IKCONFIG is not set
# CONFIG_CPUSETS is not set
CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
@@ -70,6 +71,24 @@
CONFIG_MODULE_SRCVERSION_ALL=y
CONFIG_KMOD=y
CONFIG_STOP_MACHINE=y
+
+#
+# Block layer
+#
+CONFIG_LBD=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Processor type and features
@@ -92,7 +111,6 @@
# CONFIG_PREEMPT_VOLUNTARY is not set
# CONFIG_PREEMPT is not set
CONFIG_PREEMPT_BKL=y
-# CONFIG_NUMA is not set
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
@@ -101,6 +119,7 @@
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4096
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
CONFIG_NR_CPUS=8
# CONFIG_HOTPLUG_CPU is not set
@@ -259,6 +278,10 @@
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
CONFIG_NETFILTER_NETLINK=m
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NETFILTER_NETLINK_LOG=m
@@ -444,10 +467,18 @@
CONFIG_NET_DIVERT=y
# CONFIG_ECONET is not set
CONFIG_WAN_ROUTER=m
+
+#
+# QoS and/or fair queueing
+#
CONFIG_NET_SCHED=y
CONFIG_NET_SCH_CLK_JIFFIES=y
# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
# CONFIG_NET_SCH_CLK_CPU is not set
+
+#
+# Queueing/Scheduling
+#
CONFIG_NET_SCH_CBQ=m
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_HFSC=m
@@ -461,8 +492,10 @@
CONFIG_NET_SCH_DSMARK=m
CONFIG_NET_SCH_NETEM=m
CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_QOS=y
-CONFIG_NET_ESTIMATOR=y
+
+#
+# Classification
+#
CONFIG_NET_CLS=y
CONFIG_NET_CLS_BASIC=m
CONFIG_NET_CLS_TCINDEX=m
@@ -471,7 +504,6 @@
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
CONFIG_CLS_U32_PERF=y
-CONFIG_NET_CLS_IND=y
CONFIG_CLS_U32_MARK=y
CONFIG_NET_CLS_RSVP=m
CONFIG_NET_CLS_RSVP6=m
@@ -484,6 +516,8 @@
CONFIG_NET_EMATCH_TEXT=m
# CONFIG_NET_CLS_ACT is not set
CONFIG_NET_CLS_POLICE=y
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_ESTIMATOR=y
#
# Network testing
@@ -570,7 +604,6 @@
CONFIG_BT_HCIUART=m
CONFIG_BT_HCIUART_H4=y
CONFIG_BT_HCIUART_BCSP=y
-CONFIG_BT_HCIUART_BCSP_TXCRC=y
CONFIG_BT_HCIBCM203X=m
CONFIG_BT_HCIBPA10X=m
CONFIG_BT_HCIBFUSB=m
@@ -621,6 +654,7 @@
CONFIG_NFTL=m
CONFIG_NFTL_RW=y
CONFIG_INFTL=m
+CONFIG_RFD_FTL=m
#
# RAM/ROM/Flash chip drivers
@@ -701,6 +735,12 @@
CONFIG_MTD_NAND_IDS=m
# CONFIG_MTD_NAND_DISKONCHIP is not set
# CONFIG_MTD_NAND_NANDSIM is not set
+
+#
+# OneNAND Flash Device Drivers
+#
+CONFIG_MTD_ONENAND=m
+# CONFIG_MTD_ONENAND_VERIFY_WRITE is not set
#
# Parallel port support
@@ -767,18 +807,9 @@
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_INITRD=y
-CONFIG_LBD=y
CONFIG_CDROM_PKTCDVD=m
CONFIG_CDROM_PKTCDVD_BUFFERS=8
# CONFIG_CDROM_PKTCDVD_WCACHE is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
CONFIG_ATA_OVER_ETH=m
#
@@ -885,6 +916,7 @@
#
# SCSI low-level drivers
#
+CONFIG_ISCSI_TCP=m
CONFIG_BLK_DEV_3W_XXXX_RAID=m
CONFIG_SCSI_3W_9XXX=m
CONFIG_SCSI_ACARD=m
@@ -914,10 +946,12 @@
CONFIG_SCSI_ATA_PIIX=y
CONFIG_SCSI_SATA_MV=m
CONFIG_SCSI_SATA_NV=m
+CONFIG_SCSI_PDC_ADMA=m
+CONFIG_SCSI_SATA_QSTOR=m
CONFIG_SCSI_SATA_PROMISE=m
-CONFIG_SCSI_SATA_QSTOR=m
CONFIG_SCSI_SATA_SX4=m
CONFIG_SCSI_SATA_SIL=m
+CONFIG_SCSI_SATA_SIL24=m
CONFIG_SCSI_SATA_SIS=m
CONFIG_SCSI_SATA_ULI=m
CONFIG_SCSI_SATA_VIA=m
@@ -925,7 +959,6 @@
CONFIG_SCSI_SATA_INTEL_COMBINED=y
CONFIG_SCSI_BUSLOGIC=m
# CONFIG_SCSI_OMIT_FLASHPOINT is not set
-# CONFIG_SCSI_CPQFCTS is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA is not set
# CONFIG_SCSI_EATA_PIO is not set
@@ -944,10 +977,8 @@
CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64
# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set
# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_ISP is not set
# CONFIG_SCSI_QLOGIC_FC is not set
CONFIG_SCSI_QLOGIC_1280=m
-CONFIG_SCSI_QLOGIC_1280_1040=y
CONFIG_SCSI_QLA2XXX=y
CONFIG_SCSI_QLA21XX=m
CONFIG_SCSI_QLA22XX=m
@@ -1055,7 +1086,6 @@
# PHY device support
#
CONFIG_PHYLIB=m
-CONFIG_PHYCONTROL=y
#
# MII PHY device drivers
@@ -1152,7 +1182,6 @@
CONFIG_IXGB_NAPI=y
CONFIG_S2IO=m
CONFIG_S2IO_NAPI=y
-# CONFIG_2BUFF_MODE is not set
#
# Token Ring devices
@@ -1208,6 +1237,7 @@
#
# ATM drivers
#
+CONFIG_ATM_DUMMY=m
CONFIG_ATM_TCP=m
CONFIG_ATM_LANAI=m
CONFIG_ATM_ENI=m
@@ -1239,6 +1269,7 @@
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
# CONFIG_PPP_BSDCOMP is not set
+CONFIG_PPP_MPPE=m
CONFIG_PPPOE=m
CONFIG_PPPOATM=m
CONFIG_SLIP=m
@@ -1466,7 +1497,6 @@
#
# Serial drivers
#
-# CONFIG_SERIAL_8250 is not set
#
# Non-8250 serial port support
@@ -1558,6 +1588,7 @@
# TPM devices
#
# CONFIG_TCG_TPM is not set
+CONFIG_TELCLOCK=m
#
# I2C support
@@ -1611,6 +1642,7 @@
CONFIG_SENSORS_PCF8591=m
CONFIG_SENSORS_RTC8564=m
CONFIG_SENSORS_MAX6875=m
+CONFIG_RTC_X1205_I2C=m
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
@@ -1692,6 +1724,7 @@
# Video Adapters
#
CONFIG_VIDEO_BT848=m
+# CONFIG_VIDEO_BT848_DVB is not set
CONFIG_VIDEO_SAA6588=m
CONFIG_VIDEO_BWQCAM=m
CONFIG_VIDEO_CQCAM=m
@@ -1711,14 +1744,20 @@
CONFIG_VIDEO_ZORAN_LML33R10=m
# CONFIG_VIDEO_ZR36120 is not set
CONFIG_VIDEO_SAA7134=m
+CONFIG_VIDEO_SAA7134_ALSA=m
CONFIG_VIDEO_SAA7134_DVB=m
+CONFIG_VIDEO_SAA7134_DVB_ALL_FRONTENDS=y
CONFIG_VIDEO_MXB=m
CONFIG_VIDEO_DPC=m
CONFIG_VIDEO_HEXIUM_ORION=m
CONFIG_VIDEO_HEXIUM_GEMINI=m
CONFIG_VIDEO_CX88=m
CONFIG_VIDEO_CX88_DVB=m
+CONFIG_VIDEO_CX88_DVB_ALL_FRONTENDS=y
+CONFIG_VIDEO_EM28XX=m
CONFIG_VIDEO_OVCAMCHIP=m
+CONFIG_VIDEO_AUDIO_DECODER=m
+CONFIG_VIDEO_DECODER=m
#
# Radio Adapters
@@ -1831,6 +1870,7 @@
# ATSC (North American/Korean Terresterial DTV) frontends
#
CONFIG_DVB_NXT2002=m
+CONFIG_DVB_NXT200X=m
CONFIG_DVB_OR51211=m
CONFIG_DVB_OR51132=m
CONFIG_DVB_BCM3510=m
@@ -1852,7 +1892,6 @@
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
-CONFIG_FB_SOFT_CURSOR=y
# CONFIG_FB_MACMODES is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
@@ -1866,6 +1905,7 @@
CONFIG_FB_VESA=y
CONFIG_VIDEO_SELECT=y
# CONFIG_FB_HGA is not set
+# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
CONFIG_FB_RIVA=m
# CONFIG_FB_RIVA_I2C is not set
@@ -1901,7 +1941,6 @@
CONFIG_FB_TRIDENT_ACCEL=y
# CONFIG_FB_PM3 is not set
# CONFIG_FB_GEODE is not set
-# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_VIRTUAL is not set
#
@@ -1910,6 +1949,7 @@
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
# CONFIG_FONTS is not set
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
@@ -1936,6 +1976,8 @@
# Advanced Linux Sound Architecture
#
CONFIG_SND=m
+CONFIG_SND_AC97_CODEC=m
+CONFIG_SND_AC97_BUS=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_HWDEP=m
@@ -1963,8 +2005,6 @@
CONFIG_SND_MTPAV=m
# CONFIG_SND_SERIAL_U16550 is not set
CONFIG_SND_MPU401=m
-CONFIG_SND_AC97_CODEC=m
-CONFIG_SND_AC97_BUS=m
#
# PCI devices
@@ -2059,15 +2099,15 @@
# USB Device Class drivers
#
# CONFIG_OBSOLETE_OSS_USB_DRIVER is not set
-
-#
-# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem
-#
CONFIG_USB_ACM=m
CONFIG_USB_PRINTER=m
#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed;
see USB_STORAGE Help for more information
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
#
CONFIG_USB_STORAGE=m
# CONFIG_USB_STORAGE_DEBUG is not set
@@ -2079,7 +2119,6 @@
CONFIG_USB_STORAGE_SDDR09=y
CONFIG_USB_STORAGE_SDDR55=y
CONFIG_USB_STORAGE_JUMPSHOT=y
-CONFIG_USB_STORAGE_ONETOUCH=y
#
# USB Input Devices
@@ -2161,6 +2200,7 @@
CONFIG_USB_SERIAL=m
CONFIG_USB_SERIAL_GENERIC=y
CONFIG_USB_SERIAL_AIRPRIME=m
+CONFIG_USB_SERIAL_ANYDATA=m
CONFIG_USB_SERIAL_BELKIN=m
CONFIG_USB_SERIAL_WHITEHEAT=m
CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m
@@ -2252,6 +2292,7 @@
# CONFIG_INFINIBAND_MTHCA_DEBUG is not set
CONFIG_INFINIBAND_IPOIB=m
# CONFIG_INFINIBAND_IPOIB_DEBUG is not set
+CONFIG_INFINIBAND_SRP=m
#
# SN Devices
@@ -2293,7 +2334,7 @@
CONFIG_FS_POSIX_ACL=y
CONFIG_XFS_FS=m
CONFIG_XFS_EXPORT=y
-CONFIG_XFS_QUOTA=m
+# CONFIG_XFS_QUOTA is not set
CONFIG_XFS_SECURITY=y
CONFIG_XFS_POSIX_ACL=y
# CONFIG_XFS_RT is not set
@@ -2355,6 +2396,7 @@
CONFIG_JFFS2_FS=m
CONFIG_JFFS2_FS_DEBUG=0
CONFIG_JFFS2_FS_WRITEBUFFER=y
+# CONFIG_JFFS2_SUMMARY is not set
# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set
CONFIG_JFFS2_ZLIB=y
CONFIG_JFFS2_RTIME=y
@@ -2474,9 +2516,10 @@
CONFIG_NLS_UTF8=m
#
-# Profiling support
+# Instrumentation Support
#
# CONFIG_PROFILING is not set
+# CONFIG_KPROBES is not set
#
# Kernel hacking
@@ -2492,9 +2535,10 @@
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
# CONFIG_FRAME_POINTER is not set
+# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_INIT_DEBUG is not set
-# CONFIG_KPROBES is not set
#
# Security options
diff -r d609de73b9fa -r 5a63f675107c buildconfigs/mk.linux-2.6-xen
--- a/buildconfigs/mk.linux-2.6-xen Wed Feb 1 17:06:16 2006
+++ b/buildconfigs/mk.linux-2.6-xen Wed Feb 1 18:00:19 2006
@@ -2,7 +2,7 @@
OS = linux
LINUX_SERIES = 2.6
-LINUX_VER = 2.6.14
+LINUX_VER = 2.6.15
EXTRAVERSION ?= xen
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/arch/i386/Kconfig
--- a/linux-2.6-xen-sparse/arch/i386/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/Kconfig Wed Feb 1 18:00:19 2006
@@ -5,7 +5,7 @@
mainmenu "Linux Kernel Configuration"
-config X86
+config X86_32
bool
default y
help
@@ -15,6 +15,10 @@
AMD, Cyrix, and others.
config SEMAPHORE_SLEEPERS
+ bool
+ default y
+
+config X86
bool
default y
@@ -160,304 +164,7 @@
default y
depends on SMP && X86_ES7000 && MPENTIUMIII
-if !X86_ELAN
-
-choice
- prompt "Processor family"
- default M686
-
-config M386
- bool "386"
- ---help---
- This is the processor type of your CPU. This information is used for
- optimizing purposes. In order to compile a kernel that can run on
- all x86 CPU types (albeit not optimally fast), you can specify
- "386" here.
-
- The kernel will not necessarily run on earlier architectures than
- the one you have chosen, e.g. a Pentium optimized kernel will run on
- a PPro, but not necessarily on a i486.
-
- Here are the settings recommended for greatest speed:
- - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI
- 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels
- will run on a 386 class machine.
- - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
- SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
- - "586" for generic Pentium CPUs lacking the TSC
- (time stamp counter) register.
- - "Pentium-Classic" for the Intel Pentium.
- - "Pentium-MMX" for the Intel Pentium MMX.
- - "Pentium-Pro" for the Intel Pentium Pro.
- - "Pentium-II" for the Intel Pentium II or pre-Coppermine Celeron.
- - "Pentium-III" for the Intel Pentium III or Coppermine Celeron.
- - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
- - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
- - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
- - "Crusoe" for the Transmeta Crusoe series.
- - "Efficeon" for the Transmeta Efficeon series.
- - "Winchip-C6" for original IDT Winchip.
- - "Winchip-2" for IDT Winchip 2.
- - "Winchip-2A" for IDT Winchips with 3dNow! capabilities.
- - "GeodeGX1" for Geode GX1 (Cyrix MediaGX).
- - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
- - "VIA C3-2 for VIA C3-2 "Nehemiah" (model 9 and above).
-
- If you don't know what to do, choose "386".
-
-config M486
- bool "486"
- help
- Select this for a 486 series processor, either Intel or one of the
- compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX,
- DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or
- U5S.
-
-config M586
- bool "586/K5/5x86/6x86/6x86MX"
- help
- Select this for an 586 or 686 series processor such as the AMD K5,
- the Cyrix 5x86, 6x86 and 6x86MX. This choice does not
- assume the RDTSC (Read Time Stamp Counter) instruction.
-
-config M586TSC
- bool "Pentium-Classic"
- help
- Select this for a Pentium Classic processor with the RDTSC (Read
- Time Stamp Counter) instruction for benchmarking.
-
-config M586MMX
- bool "Pentium-MMX"
- help
- Select this for a Pentium with the MMX graphics/multimedia
- extended instructions.
-
-config M686
- bool "Pentium-Pro"
- help
- Select this for Intel Pentium Pro chips. This enables the use of
- Pentium Pro extended instructions, and disables the init-time guard
- against the f00f bug found in earlier Pentiums.
-
-config MPENTIUMII
- bool "Pentium-II/Celeron(pre-Coppermine)"
- help
- Select this for Intel chips based on the Pentium-II and
- pre-Coppermine Celeron core. This option enables an unaligned
- copy optimization, compiles the kernel with optimization flags
- tailored for the chip, and applies any applicable Pentium Pro
- optimizations.
-
-config MPENTIUMIII
- bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon"
- help
- Select this for Intel chips based on the Pentium-III and
- Celeron-Coppermine core. This option enables use of some
- extended prefetch instructions in addition to the Pentium II
- extensions.
-
-config MPENTIUMM
- bool "Pentium M"
- help
- Select this for Intel Pentium M (not Pentium-4 M)
- notebook chips.
-
-config MPENTIUM4
- bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/Xeon"
- help
- Select this for Intel Pentium 4 chips. This includes the
- Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M
- (not Pentium M) chips. This option enables compile flags
- optimized for the chip, uses the correct cache shift, and
- applies any applicable Pentium III optimizations.
-
-config MK6
- bool "K6/K6-II/K6-III"
- help
- Select this for an AMD K6-family processor. Enables use of
- some extended instructions, and passes appropriate optimization
- flags to GCC.
-
-config MK7
- bool "Athlon/Duron/K7"
- help
- Select this for an AMD Athlon K7-family processor. Enables use of
- some extended instructions, and passes appropriate optimization
- flags to GCC.
-
-config MK8
- bool "Opteron/Athlon64/Hammer/K8"
- help
- Select this for an AMD Opteron or Athlon64 Hammer-family processor.
Enables
- use of some extended instructions, and passes appropriate optimization
- flags to GCC.
-
-config MCRUSOE
- bool "Crusoe"
- help
- Select this for a Transmeta Crusoe processor. Treats the processor
- like a 586 with TSC, and sets some GCC optimization flags (like a
- Pentium Pro with no alignment requirements).
-
-config MEFFICEON
- bool "Efficeon"
- help
- Select this for a Transmeta Efficeon processor.
-
-config MWINCHIPC6
- bool "Winchip-C6"
- help
- Select this for an IDT Winchip C6 chip. Linux and GCC
- treat this chip as a 586TSC with some extended instructions
- and alignment requirements.
-
-config MWINCHIP2
- bool "Winchip-2"
- help
- Select this for an IDT Winchip-2. Linux and GCC
- treat this chip as a 586TSC with some extended instructions
- and alignment requirements.
-
-config MWINCHIP3D
- bool "Winchip-2A/Winchip-3"
- help
- Select this for an IDT Winchip-2A or 3. Linux and GCC
- treat this chip as a 586TSC with some extended instructions
- and alignment reqirements. Also enable out of order memory
- stores for this CPU, which can increase performance of some
- operations.
-
-config MGEODEGX1
- bool "GeodeGX1"
- help
- Select this for a Geode GX1 (Cyrix MediaGX) chip.
-
-config MCYRIXIII
- bool "CyrixIII/VIA-C3"
- help
- Select this for a Cyrix III or C3 chip. Presently Linux and GCC
- treat this chip as a generic 586. Whilst the CPU is 686 class,
- it lacks the cmov extension which gcc assumes is present when
- generating 686 code.
- Note that Nehemiah (Model 9) and above will not boot with this
- kernel due to them lacking the 3DNow! instructions used in earlier
- incarnations of the CPU.
-
-config MVIAC3_2
- bool "VIA C3-2 (Nehemiah)"
- help
- Select this for a VIA C3 "Nehemiah". Selecting this enables usage
- of SSE and tells gcc to treat the CPU as a 686.
- Note, this kernel will not boot on older (pre model 9) C3s.
-
-endchoice
-
-config X86_GENERIC
- bool "Generic x86 support"
- help
- Instead of just including optimizations for the selected
- x86 variant (e.g. PII, Crusoe or Athlon), include some more
- generic optimizations as well. This will make the kernel
- perform better on x86 CPUs other than that selected.
-
- This is really intended for distributors who need more
- generic optimizations.
-
-endif
-
-#
-# Define implied options from the CPU selection here
-#
-config X86_CMPXCHG
- bool
- depends on !M386
- default y
-
-config X86_XADD
- bool
- depends on !M386
- default y
-
-config X86_L1_CACHE_SHIFT
- int
- default "7" if MPENTIUM4 || X86_GENERIC
- default "4" if X86_ELAN || M486 || M386
- default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE ||
MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX
|| M586TSC || M586 || MVIAC3_2 || MGEODEGX1
- default "6" if MK7 || MK8 || MPENTIUMM
-
-config RWSEM_GENERIC_SPINLOCK
- bool
- depends on M386
- default y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
- depends on !M386
- default y
-
-config GENERIC_CALIBRATE_DELAY
- bool
- default y
-
-config X86_PPRO_FENCE
- bool
- depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 ||
MGEODEGX1
- default y
-
-config X86_F00F_BUG
- bool
- depends on M586MMX || M586TSC || M586 || M486 || M386
- default y
-
-config X86_WP_WORKS_OK
- bool
- depends on !M386
- default y
-
-config X86_INVLPG
- bool
- depends on !M386
- default y
-
-config X86_BSWAP
- bool
- depends on !M386
- default y
-
-config X86_POPAD_OK
- bool
- depends on !M386
- default y
-
-config X86_ALIGNMENT_16
- bool
- depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII ||
X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
- default y
-
-config X86_GOOD_APIC
- bool
- depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII
|| M686 || M586MMX || MK8 || MEFFICEON
- default y
-
-config X86_INTEL_USERCOPY
- bool
- depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII ||
M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON
- default y
-
-config X86_USE_PPRO_CHECKSUM
- bool
- depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 ||
MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 ||
MVIAC3_2 || MEFFICEON
- default y
-
-config X86_USE_3DNOW
- bool
- depends on MCYRIXIII || MK7
- default y
-
-config X86_OOSTORE
- bool
- depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR
- default y
+source "arch/i386/Kconfig.cpu"
config HPET_TIMER
bool "HPET Timer Support"
@@ -1041,7 +748,7 @@
config APM
tristate "APM (Advanced Power Management) BIOS support"
- depends on PM
+ depends on PM && PM_LEGACY
---help---
APM is a BIOS specification for saving power using several different
techniques. This is mostly useful for battery powered laptops with
@@ -1333,9 +1040,22 @@
source "fs/Kconfig"
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
if !X86_XEN
source "arch/i386/oprofile/Kconfig"
endif
+
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
source "arch/i386/Kconfig.debug"
@@ -1382,8 +1102,3 @@
bool
depends on X86_SMP || (X86_VOYAGER && SMP)
default y
-
-config PC
- bool
- depends on X86 && !EMBEDDED
- default y
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/arch/i386/Makefile
--- a/linux-2.6-xen-sparse/arch/i386/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/Makefile Wed Feb 1 18:00:19 2006
@@ -34,35 +34,8 @@
# prevent gcc from keeping the stack 16 byte aligned
CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
-align := $(cc-option-align)
-cflags-$(CONFIG_M386) += -march=i386
-cflags-$(CONFIG_M486) += -march=i486
-cflags-$(CONFIG_M586) += -march=i586
-cflags-$(CONFIG_M586TSC) += -march=i586
-cflags-$(CONFIG_M586MMX) += $(call
cc-option,-march=pentium-mmx,-march=i586)
-cflags-$(CONFIG_M686) += -march=i686
-cflags-$(CONFIG_MPENTIUMII) += -march=i686 $(call cc-option,-mtune=pentium2)
-cflags-$(CONFIG_MPENTIUMIII) += -march=i686 $(call cc-option,-mtune=pentium3)
-cflags-$(CONFIG_MPENTIUMM) += -march=i686 $(call cc-option,-mtune=pentium3)
-cflags-$(CONFIG_MPENTIUM4) += -march=i686 $(call cc-option,-mtune=pentium4)
-cflags-$(CONFIG_MK6) += -march=k6
-# Please note, that patches that add -march=athlon-xp and friends are
pointless.
-# They make zero difference whatsosever to performance at this time.
-cflags-$(CONFIG_MK7) += $(call cc-option,-march=athlon,-march=i686
$(align)-functions=4)
-cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,$(call
cc-option,-march=athlon,-march=i686 $(align)-functions=4))
-cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0
$(align)-jumps=0 $(align)-loops=0
-cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call
cc-option,-mtune=pentium3) $(align)-functions=0 $(align)-jumps=0
$(align)-loops=0
-cflags-$(CONFIG_MWINCHIPC6) += $(call
cc-option,-march=winchip-c6,-march=i586)
-cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586)
-cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586)
-cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486)
$(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
-cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686)
-
-# AMD Elan support
-cflags-$(CONFIG_X86_ELAN) += -march=i486
-
-# Geode GX1 support
-cflags-$(CONFIG_MGEODEGX1) += $(call
cc-option,-march=pentium-mmx,-march=i486)
+# CPU-specific tuning. Anything which can be shared with UML should go here.
+include $(srctree)/arch/i386/Makefile.cpu
# -mregparm=3 works ok on gcc-3.0 and later
#
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/Makefile
--- a/linux-2.6-xen-sparse/arch/i386/kernel/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/Makefile Wed Feb 1 18:00:19 2006
@@ -86,6 +86,7 @@
include $(srctree)/scripts/Makefile.xen
obj-y += fixup.o
+microcode-$(subst m,y,$(CONFIG_MICROCODE)) := microcode-xen.o
n-obj-xen := i8259.o doublefault.o timers/ reboot.o smpboot.o trampoline.o
obj-y := $(call filterxen, $(obj-y), $(n-obj-xen))
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/acpi/boot-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/acpi/boot-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/acpi/boot-xen.c Wed Feb 1
18:00:19 2006
@@ -36,22 +36,16 @@
#include <asm/apic.h>
#include <asm/io.h>
#include <asm/mpspec.h>
-#ifdef CONFIG_XEN
-#include <asm/fixmap.h>
-#endif
#ifdef CONFIG_X86_64
-static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-}
extern void __init clustered_apic_check(void);
-static inline int ioapic_setup_disabled(void)
-{
- return 0;
-}
-
+
+extern int gsi_irq_sharing(int gsi);
#include <asm/proto.h>
+
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) {
return 0; }
+
#else /* X86 */
@@ -59,6 +53,8 @@
#include <mach_apic.h>
#include <mach_mpparse.h>
#endif /* CONFIG_X86_LOCAL_APIC */
+
+static inline int gsi_irq_sharing(int gsi) { return gsi; }
#endif /* X86 */
@@ -138,7 +134,7 @@
int idx;
#ifndef CONFIG_XEN
- if (phys + size < 8 * 1024 * 1024)
+ if (phys + size < 8 * 1024 * 1024)
return __va(phys);
#endif
@@ -254,9 +250,7 @@
acpi_table_print_madt_entry(header);
- /* no utility in registering a disabled processor */
- if (processor->flags.enabled == 0)
- return 0;
+ /* Register even disabled CPUs for cpu hotplug */
x86_acpiid_to_apicid[processor->acpi_id] = processor->id;
@@ -464,7 +458,7 @@
*irq = IO_APIC_VECTOR(gsi);
else
#endif
- *irq = gsi;
+ *irq = gsi_irq_sharing(gsi);
return 0;
}
@@ -538,7 +532,7 @@
EXPORT_SYMBOL(acpi_unregister_ioapic);
static unsigned long __init
-acpi_scan_rsdp (unsigned long start, unsigned long length)
+acpi_scan_rsdp(unsigned long start, unsigned long length)
{
unsigned long offset = 0;
unsigned long sig_len = sizeof("RSD PTR ") - 1;
@@ -647,6 +641,13 @@
return 0;
pmtmr_ioport = fadt->xpm_tmr_blk.address;
+ /*
+ * "X" fields are optional extensions to the original V1.0
+ * fields, so we must selectively expand V1.0 fields if the
+ * corresponding X field is zero.
+ */
+ if (!pmtmr_ioport)
+ pmtmr_ioport = fadt->V1_pm_tmr_blk;
} else {
/* FADT rev. 1 */
pmtmr_ioport = fadt->V1_pm_tmr_blk;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/cpu/common-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/cpu/common-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/cpu/common-xen.c Wed Feb 1
18:00:19 2006
@@ -33,8 +33,6 @@
struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
-extern void mcheck_init(struct cpuinfo_x86 *c);
-
extern void machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c);
extern int disable_pse;
@@ -238,10 +236,10 @@
cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
c->x86 = (tfms >> 8) & 15;
c->x86_model = (tfms >> 4) & 15;
- if (c->x86 == 0xf) {
+ if (c->x86 == 0xf)
c->x86 += (tfms >> 20) & 0xff;
+ if (c->x86 >= 0x6)
c->x86_model += ((tfms >> 16) & 0xF) << 4;
- }
c->x86_mask = tfms & 15;
if (cap0 & (1<<19))
c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
@@ -340,7 +338,7 @@
c->x86_model = c->x86_mask = 0; /* So far unknown... */
c->x86_vendor_id[0] = '\0'; /* Unset */
c->x86_model_id[0] = '\0'; /* Unset */
- c->x86_num_cores = 1;
+ c->x86_max_cores = 1;
memset(&c->x86_capability, 0, sizeof c->x86_capability);
if (!have_cpuid_p()) {
@@ -436,9 +434,8 @@
}
/* Init Machine Check Exception if available. */
-#ifdef CONFIG_X86_MCE
mcheck_init(c);
-#endif
+
if (c == &boot_cpu_data)
sysenter_setup();
enable_sep_cpu();
@@ -453,52 +450,44 @@
void __devinit detect_ht(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
- int index_msb, tmp;
+ int index_msb, core_bits;
int cpu = smp_processor_id();
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+
+ c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0);
if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
return;
- cpuid(1, &eax, &ebx, &ecx, &edx);
smp_num_siblings = (ebx & 0xff0000) >> 16;
if (smp_num_siblings == 1) {
printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
} else if (smp_num_siblings > 1 ) {
- index_msb = 31;
if (smp_num_siblings > NR_CPUS) {
printk(KERN_WARNING "CPU: Unsupported number of the
siblings %d", smp_num_siblings);
smp_num_siblings = 1;
return;
}
- tmp = smp_num_siblings;
- while ((tmp & 0x80000000 ) == 0) {
- tmp <<=1 ;
- index_msb--;
- }
- if (smp_num_siblings & (smp_num_siblings - 1))
- index_msb++;
+
+ index_msb = get_count_order(smp_num_siblings);
phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
phys_proc_id[cpu]);
- smp_num_siblings = smp_num_siblings / c->x86_num_cores;
-
- tmp = smp_num_siblings;
- index_msb = 31;
- while ((tmp & 0x80000000) == 0) {
- tmp <<=1 ;
- index_msb--;
- }
-
- if (smp_num_siblings & (smp_num_siblings - 1))
- index_msb++;
-
- cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
-
- if (c->x86_num_cores > 1)
+ smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+ index_msb = get_count_order(smp_num_siblings) ;
+
+ core_bits = get_count_order(c->x86_max_cores);
+
+ cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) &
+ ((1 << core_bits) - 1);
+
+ if (c->x86_max_cores > 1)
printk(KERN_INFO "CPU: Processor Core ID: %d\n",
cpu_core_id[cpu]);
}
@@ -615,12 +604,6 @@
set_in_cr4(X86_CR4_TSD);
}
- /*
- * Set up the per-thread TLS descriptor cache:
- */
- memcpy(thread->tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN],
- GDT_ENTRY_TLS_ENTRIES * 8);
-
cpu_gdt_init(&cpu_gdt_descr[cpu]);
/*
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/entry-xen.S
--- a/linux-2.6-xen-sparse/arch/i386/kernel/entry-xen.S Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/entry-xen.S Wed Feb 1 18:00:19 2006
@@ -746,11 +746,10 @@
nmi_debug_stack_check:
cmpw $__KERNEL_CS,16(%esp)
jne nmi_stack_correct
- cmpl $debug - 1,(%esp)
- jle nmi_stack_correct
+ cmpl $debug,(%esp)
+ jb nmi_stack_correct
cmpl $debug_esp_fix_insn,(%esp)
- jle nmi_debug_stack_fixup
-nmi_debug_stack_fixup:
+ ja nmi_stack_correct
FIX_STACK(24,nmi_stack_correct, 1)
jmp nmi_stack_correct
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/io_apic-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/io_apic-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/io_apic-xen.c Wed Feb 1
18:00:19 2006
@@ -88,6 +88,9 @@
int (*ioapic_renumber_irq)(int ioapic, int irq);
atomic_t irq_mis_count;
+/* Where if anywhere is the i8259 connect in external int mode */
+static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
+
static DEFINE_SPINLOCK(ioapic_lock);
/*
@@ -784,10 +787,11 @@
}
#ifndef CONFIG_XEN
+#endif
/*
* Find the pin to which IRQ[irq] (ISA) is connected
*/
-static int find_isa_irq_pin(int irq, int type)
+static int __init find_isa_irq_pin(int irq, int type)
{
int i;
@@ -806,7 +810,33 @@
}
return -1;
}
-#endif
+
+static int __init find_isa_irq_apic(int irq, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].mpc_srcbus;
+
+ if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_NEC98
+ ) &&
+ (mp_irqs[i].mpc_irqtype == type) &&
+ (mp_irqs[i].mpc_srcbusirq == irq))
+ break;
+ }
+ if (i < mp_irq_entries) {
+ int apic;
+ for(apic = 0; apic < nr_ioapics; apic++) {
+ if (mp_ioapics[apic].mpc_apicid ==
mp_irqs[i].mpc_dstapic)
+ return apic;
+ }
+ }
+
+ return -1;
+}
/*
* Find a specific PCI IRQ entry.
@@ -1306,7 +1336,7 @@
* Set up the 8259A-master output pin:
*/
#ifndef CONFIG_XEN
-static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
+static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin,
int vector)
{
struct IO_APIC_route_entry entry;
unsigned long flags;
@@ -1340,8 +1370,8 @@
* Add it to the IO-APIC irq-routing table:
*/
spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
- io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
+ io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0));
spin_unlock_irqrestore(&ioapic_lock, flags);
enable_8259A_irq(0);
@@ -1647,7 +1677,8 @@
static void __init enable_IO_APIC(void)
{
union IO_APIC_reg_01 reg_01;
- int i;
+ int i8259_apic, i8259_pin;
+ int i, apic;
unsigned long flags;
for (i = 0; i < PIN_MAP_SIZE; i++) {
@@ -1661,11 +1692,52 @@
/*
* The number of IO-APIC IRQ registers (== #pins):
*/
- for (i = 0; i < nr_ioapics; i++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
spin_lock_irqsave(&ioapic_lock, flags);
- reg_01.raw = io_apic_read(i, 1);
+ reg_01.raw = io_apic_read(apic, 1);
spin_unlock_irqrestore(&ioapic_lock, flags);
- nr_ioapic_registers[i] = reg_01.bits.entries+1;
+ nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+ }
+ for(apic = 0; apic < nr_ioapics; apic++) {
+ int pin;
+ /* See if any of the pins is in ExtINT mode */
+ for(pin = 0; pin < nr_ioapic_registers[i]; pin++) {
+ struct IO_APIC_route_entry entry;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int *)&entry) + 0) = io_apic_read(apic, 0x10 + 2 *
pin);
+ *(((int *)&entry) + 1) = io_apic_read(apic, 0x11 + 2 *
pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+
+ /* If the interrupt line is enabled and in ExtInt mode
+ * I have found the pin where the i8259 is connected.
+ */
+ if ((entry.mask == 0) && (entry.delivery_mode ==
dest_ExtINT)) {
+ ioapic_i8259.apic = apic;
+ ioapic_i8259.pin = pin;
+ goto found_i8259;
+ }
+ }
+ }
+ found_i8259:
+ /* Look to see what if the MP table has reported the ExtINT */
+ /* If we could not find the appropriate pin by looking at the ioapic
+ * the i8259 probably is not connected the ioapic but give the
+ * mptable a chance anyway.
+ */
+ i8259_pin = find_isa_irq_pin(0, mp_ExtINT);
+ i8259_apic = find_isa_irq_apic(0, mp_ExtINT);
+ /* Trust the MP table if nothing is setup in the hardware */
+ if ((ioapic_i8259.pin == -1) && (i8259_pin >= 0)) {
+ printk(KERN_WARNING "ExtINT not setup in hardware but reported
by MP table\n");
+ ioapic_i8259.pin = i8259_pin;
+ ioapic_i8259.apic = i8259_apic;
+ }
+ /* Complain if the MP table and the hardware disagree */
+ if (((ioapic_i8259.apic != i8259_apic) || (ioapic_i8259.pin !=
i8259_pin)) &&
+ (i8259_pin >= 0) && (ioapic_i8259.pin >= 0))
+ {
+ printk(KERN_WARNING "ExtINT in hardware and MP table differ\n");
}
/*
@@ -1679,9 +1751,6 @@
*/
void disable_IO_APIC(void)
{
-#ifndef CONFIG_XEN
- int pin;
-#endif
/*
* Clear the IO-APIC before rebooting:
*/
@@ -1693,8 +1762,7 @@
* Put that IOAPIC in virtual wire mode
* so legacy interrupts can be delivered.
*/
- pin = find_isa_irq_pin(0, mp_ExtINT);
- if (pin != -1) {
+ if (ioapic_i8259.pin != -1) {
struct IO_APIC_route_entry entry;
unsigned long flags;
@@ -1705,7 +1773,7 @@
entry.polarity = 0; /* High */
entry.delivery_status = 0;
entry.dest_mode = 0; /* Physical */
- entry.delivery_mode = 7; /* ExtInt */
+ entry.delivery_mode = dest_ExtINT; /* ExtInt */
entry.vector = 0;
entry.dest.physical.physical_dest = 0;
@@ -1714,11 +1782,13 @@
* Add it to the IO-APIC irq-routing table:
*/
spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
- io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
+ io_apic_write(ioapic_i8259.apic, 0x11+2*ioapic_i8259.pin,
+ *(((int *)&entry)+1));
+ io_apic_write(ioapic_i8259.apic, 0x10+2*ioapic_i8259.pin,
+ *(((int *)&entry)+0));
spin_unlock_irqrestore(&ioapic_lock, flags);
}
- disconnect_bsp_APIC(pin != -1);
+ disconnect_bsp_APIC(ioapic_i8259.pin != -1);
#endif
}
@@ -1994,7 +2064,7 @@
{
int irq = vector_to_irq(vector);
- move_irq(vector);
+ move_native_irq(vector);
ack_edge_ioapic_irq(irq);
}
@@ -2009,7 +2079,7 @@
{
int irq = vector_to_irq(vector);
- move_irq(vector);
+ move_native_irq(vector);
end_level_ioapic_irq(irq);
}
@@ -2174,20 +2244,21 @@
*/
static inline void unlock_ExtINT_logic(void)
{
- int pin, i;
+ int apic, pin, i;
struct IO_APIC_route_entry entry0, entry1;
unsigned char save_control, save_freq_select;
unsigned long flags;
- pin = find_isa_irq_pin(8, mp_INT);
+ pin = find_isa_irq_pin(8, mp_INT);
+ apic = find_isa_irq_apic(8, mp_INT);
if (pin == -1)
return;
spin_lock_irqsave(&ioapic_lock, flags);
- *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin);
- *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin);
+ *(((int *)&entry0) + 1) = io_apic_read(apic, 0x11 + 2 * pin);
+ *(((int *)&entry0) + 0) = io_apic_read(apic, 0x10 + 2 * pin);
spin_unlock_irqrestore(&ioapic_lock, flags);
- clear_IO_APIC_pin(0, pin);
+ clear_IO_APIC_pin(apic, pin);
memset(&entry1, 0, sizeof(entry1));
@@ -2200,8 +2271,8 @@
entry1.vector = 0;
spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
- io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
+ io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
+ io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
spin_unlock_irqrestore(&ioapic_lock, flags);
save_control = CMOS_READ(RTC_CONTROL);
@@ -2219,11 +2290,11 @@
CMOS_WRITE(save_control, RTC_CONTROL);
CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
- clear_IO_APIC_pin(0, pin);
+ clear_IO_APIC_pin(apic, pin);
spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
- io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
+ io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
+ io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -2235,7 +2306,7 @@
*/
static inline void check_timer(void)
{
- int pin1, pin2;
+ int apic1, pin1, apic2, pin2;
int vector;
/*
@@ -2257,10 +2328,13 @@
timer_ack = 1;
enable_8259A_irq(0);
- pin1 = find_isa_irq_pin(0, mp_INT);
- pin2 = find_isa_irq_pin(0, mp_ExtINT);
-
- printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector,
pin1, pin2);
+ pin1 = find_isa_irq_pin(0, mp_INT);
+ apic1 = find_isa_irq_apic(0, mp_INT);
+ pin2 = ioapic_i8259.pin;
+ apic2 = ioapic_i8259.apic;
+
+ printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d
pin2=%d\n",
+ vector, apic1, pin1, apic2, pin2);
if (pin1 != -1) {
/*
@@ -2277,8 +2351,9 @@
clear_IO_APIC_pin(0, pin1);
return;
}
- clear_IO_APIC_pin(0, pin1);
- printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to
IO-APIC\n");
+ clear_IO_APIC_pin(apic1, pin1);
+ printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
+ "IO-APIC\n");
}
printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A
... ");
@@ -2287,13 +2362,13 @@
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(pin2, vector);
+ setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
if (timer_irq_works()) {
printk("works.\n");
if (pin1 != -1)
- replace_pin_at_irq(0, 0, pin1, 0, pin2);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
else
- add_pin_to_irq(0, 0, pin2);
+ add_pin_to_irq(0, apic2, pin2);
if (nmi_watchdog == NMI_IO_APIC) {
setup_nmi();
}
@@ -2302,7 +2377,7 @@
/*
* Cleanup, just in case ...
*/
- clear_IO_APIC_pin(0, pin2);
+ clear_IO_APIC_pin(apic2, pin2);
}
printk(" failed.\n");
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/irq-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/irq-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/irq-xen.c Wed Feb 1 18:00:19 2006
@@ -218,7 +218,7 @@
if (i == 0) {
seq_printf(p, " ");
- for_each_cpu(j)
+ for_each_online_cpu(j)
seq_printf(p, "CPU%d ",j);
seq_putc(p, '\n');
}
@@ -232,7 +232,7 @@
#ifndef CONFIG_SMP
seq_printf(p, "%10u ", kstat_irqs(i));
#else
- for_each_cpu(j)
+ for_each_online_cpu(j)
seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
#endif
seq_printf(p, " %14s", irq_desc[i].handler->typename);
@@ -246,12 +246,12 @@
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
} else if (i == NR_IRQS) {
seq_printf(p, "NMI: ");
- for_each_cpu(j)
+ for_each_online_cpu(j)
seq_printf(p, "%10u ", nmi_count(j));
seq_putc(p, '\n');
#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "LOC: ");
- for_each_cpu(j)
+ for_each_online_cpu(j)
seq_printf(p, "%10u ",
per_cpu(irq_stat,j).apic_timer_irqs);
seq_putc(p, '\n');
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/ldt-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/ldt-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/ldt-xen.c Wed Feb 1 18:00:19 2006
@@ -18,6 +18,7 @@
#include <asm/system.h>
#include <asm/ldt.h>
#include <asm/desc.h>
+#include <asm/mmu_context.h>
#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */
static void flush_ldt(void *null)
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/mpparse-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/mpparse-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/mpparse-xen.c Wed Feb 1
18:00:19 2006
@@ -69,7 +69,7 @@
/* Processor that is doing the boot up */
unsigned int boot_cpu_physical_apicid = -1U;
/* Internal processor count */
-static unsigned int __initdata num_processors;
+static unsigned int __devinitdata num_processors;
/* Bitmask of physically existing CPUs */
physid_mask_t phys_cpu_present_map;
@@ -120,7 +120,7 @@
#endif
#ifndef CONFIG_XEN
-static void __init MP_processor_info (struct mpc_config_processor *m)
+static void __devinit MP_processor_info (struct mpc_config_processor *m)
{
int ver, apicid;
physid_mask_t phys_cpu;
@@ -183,17 +183,6 @@
boot_cpu_physical_apicid = m->mpc_apicid;
}
- if (num_processors >= NR_CPUS) {
- printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
- " Processor ignored.\n", NR_CPUS);
- return;
- }
-
- if (num_processors >= maxcpus) {
- printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
- " Processor ignored.\n", maxcpus);
- return;
- }
ver = m->mpc_apicver;
if (!MP_valid_apicid(apicid, ver)) {
@@ -201,11 +190,6 @@
m->mpc_apicid, MAX_APICS);
return;
}
-
- cpu_set(num_processors, cpu_possible_map);
- num_processors++;
- phys_cpu = apicid_to_cpu_present(apicid);
- physids_or(phys_cpu_present_map, phys_cpu_present_map, phys_cpu);
/*
* Validate version
@@ -217,9 +201,29 @@
ver = 0x10;
}
apic_version[m->mpc_apicid] = ver;
+
+ phys_cpu = apicid_to_cpu_present(apicid);
+ physids_or(phys_cpu_present_map, phys_cpu_present_map, phys_cpu);
+
+ if (num_processors >= NR_CPUS) {
+ printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+ " Processor ignored.\n", NR_CPUS);
+ return;
+ }
+
+ if (num_processors >= maxcpus) {
+ printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
+ " Processor ignored.\n", maxcpus);
+ return;
+ }
+
+ cpu_set(num_processors, cpu_possible_map);
+ num_processors++;
+
if ((num_processors > 8) &&
- APIC_XAPIC(ver) &&
- (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL))
+ ((APIC_XAPIC(ver) &&
+ (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)) ||
+ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)))
def_to_bigsmp = 1;
else
def_to_bigsmp = 0;
@@ -850,7 +854,7 @@
}
-void __init mp_register_lapic (
+void __devinit mp_register_lapic (
u8 id,
u8 enabled)
{
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/process-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/process-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/process-xen.c Wed Feb 1
18:00:19 2006
@@ -108,15 +108,31 @@
if (need_resched()) {
local_irq_enable();
} else {
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+ smp_mb__after_clear_bit();
stop_hz_timer();
/* Blocking includes an implicit local_irq_enable(). */
HYPERVISOR_sched_op(SCHEDOP_block, 0);
start_hz_timer();
+ set_thread_flag(TIF_POLLING_NRFLAG);
}
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(default_idle);
#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+static inline void play_dead(void)
+{
+ HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
+ local_irq_enable();
+}
+#else
+static inline void play_dead(void)
+{
+ BUG();
+}
+#endif /* CONFIG_HOTPLUG_CPU */
/*
* The idle thread. There's no useful work to be
@@ -126,9 +142,9 @@
*/
void cpu_idle(void)
{
-#if defined(CONFIG_HOTPLUG_CPU)
- int cpu = raw_smp_processor_id();
-#endif
+ int cpu = smp_processor_id();
+
+ set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while (1) {
@@ -139,17 +155,15 @@
rmb();
-#if defined(CONFIG_HOTPLUG_CPU)
- if (cpu_is_offline(cpu)) {
- HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL);
- local_irq_enable();
- }
-#endif
+ if (cpu_is_offline(cpu))
+ play_dead();
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
xen_idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
@@ -187,6 +201,8 @@
void show_regs(struct pt_regs * regs)
{
+ unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
+
printk("\n");
printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip,
smp_processor_id());
@@ -203,6 +219,13 @@
printk(" DS: %04x ES: %04x\n",
0xffff & regs->xds,0xffff & regs->xes);
+ cr0 = read_cr0();
+ cr2 = read_cr2();
+ cr3 = read_cr3();
+ if (current_cpu_data.x86 > 4) {
+ cr4 = read_cr4();
+ }
+ printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3,
cr4);
show_trace(NULL, ®s->esp);
}
@@ -274,13 +297,6 @@
void flush_thread(void)
{
struct task_struct *tsk = current;
-
- /*
- * Remove function-return probe instances associated with this task
- * and put them back on the free list. Do not insert an exit probe for
- * this function, it will be disabled by kprobe_flush_task if you do.
- */
- kprobe_flush_task(tsk);
memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
@@ -445,7 +461,9 @@
struct pt_regs ptregs;
ptregs = *(struct pt_regs *)
- ((unsigned long)tsk->thread_info+THREAD_SIZE - sizeof(ptregs));
+ ((unsigned long)tsk->thread_info +
+ /* see comments in copy_thread() about -8 */
+ THREAD_SIZE - sizeof(ptregs) - 8);
ptregs.xcs &= 0xffff;
ptregs.xds &= 0xffff;
ptregs.xes &= 0xffff;
@@ -453,7 +471,6 @@
elf_core_copy_regs(regs, &ptregs);
- boot_option_idle_override = 1;
return 1;
}
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/setup-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/setup-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/setup-xen.c Wed Feb 1 18:00:19 2006
@@ -142,9 +142,7 @@
EXPORT_SYMBOL(drive_info);
#endif
struct screen_info screen_info;
-#ifdef CONFIG_VT
EXPORT_SYMBOL(screen_info);
-#endif
struct apm_info apm_info;
EXPORT_SYMBOL(apm_info);
struct sys_desc_table_struct {
@@ -425,14 +423,24 @@
}
}
for (i = 0; i < e820.nr_map; i++) {
- if (e820.map[i].type == E820_RAM) {
- current_addr = e820.map[i].addr + e820.map[i].size;
- if (current_addr >= size) {
- e820.map[i].size -= current_addr-size;
- e820.nr_map = i + 1;
- return;
- }
- }
+ current_addr = e820.map[i].addr + e820.map[i].size;
+ if (current_addr < size)
+ continue;
+
+ if (e820.map[i].type != E820_RAM)
+ continue;
+
+ if (e820.map[i].addr >= size) {
+ /*
+ * This region starts past the end of the
+ * requested size, skip it completely.
+ */
+ e820.nr_map = i;
+ } else {
+ e820.nr_map = i + 1;
+ e820.map[i].size -= current_addr - size;
+ }
+ return;
}
}
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/smpboot.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/smpboot.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/smpboot.c Wed Feb 1 18:00:19 2006
@@ -68,15 +68,15 @@
/* Package ID of each logical CPU */
int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
-EXPORT_SYMBOL(phys_proc_id);
/* Core ID of each logical CPU */
int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
-EXPORT_SYMBOL(cpu_core_id);
-
+
+/* representing HT siblings of each logical CPU */
cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_sibling_map);
+/* representing HT and core siblings of each logical CPU */
cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_core_map);
@@ -87,7 +87,11 @@
cpumask_t cpu_callin_map;
cpumask_t cpu_callout_map;
EXPORT_SYMBOL(cpu_callout_map);
+#ifdef CONFIG_HOTPLUG_CPU
+cpumask_t cpu_possible_map = CPU_MASK_ALL;
+#else
cpumask_t cpu_possible_map;
+#endif
EXPORT_SYMBOL(cpu_possible_map);
static cpumask_t smp_commenced_mask;
@@ -440,35 +444,60 @@
static int cpucount;
+/* representing cpus for which sibling maps can be computed */
+static cpumask_t cpu_sibling_setup_map;
+
static inline void
set_cpu_sibling_map(int cpu)
{
int i;
+ struct cpuinfo_x86 *c = cpu_data;
+
+ cpu_set(cpu, cpu_sibling_setup_map);
if (smp_num_siblings > 1) {
- for (i = 0; i < NR_CPUS; i++) {
- if (!cpu_isset(i, cpu_callout_map))
- continue;
- if (cpu_core_id[cpu] == cpu_core_id[i]) {
+ for_each_cpu_mask(i, cpu_sibling_setup_map) {
+ if (phys_proc_id[cpu] == phys_proc_id[i] &&
+ cpu_core_id[cpu] == cpu_core_id[i]) {
cpu_set(i, cpu_sibling_map[cpu]);
cpu_set(cpu, cpu_sibling_map[i]);
- }
- }
- } else {
- cpu_set(cpu, cpu_sibling_map[cpu]);
- }
-
- if (current_cpu_data.x86_num_cores > 1) {
- for (i = 0; i < NR_CPUS; i++) {
- if (!cpu_isset(i, cpu_callout_map))
- continue;
- if (phys_proc_id[cpu] == phys_proc_id[i]) {
cpu_set(i, cpu_core_map[cpu]);
cpu_set(cpu, cpu_core_map[i]);
}
}
} else {
+ cpu_set(cpu, cpu_sibling_map[cpu]);
+ }
+
+ if (current_cpu_data.x86_max_cores == 1) {
cpu_core_map[cpu] = cpu_sibling_map[cpu];
+ c[cpu].booted_cores = 1;
+ return;
+ }
+
+ for_each_cpu_mask(i, cpu_sibling_setup_map) {
+ if (phys_proc_id[cpu] == phys_proc_id[i]) {
+ cpu_set(i, cpu_core_map[cpu]);
+ cpu_set(cpu, cpu_core_map[i]);
+ /*
+ * Does this new cpu bringup a new core?
+ */
+ if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+ /*
+ * for each core in package, increment
+ * the booted_cores for this new cpu
+ */
+ if (first_cpu(cpu_sibling_map[i]) == i)
+ c[cpu].booted_cores++;
+ /*
+ * increment the core count for all
+ * the other cpus in this package
+ */
+ if (i != cpu)
+ c[i].booted_cores++;
+ } else if (i != cpu && !c[cpu].booted_cores)
+ c[cpu].booted_cores = c[i].booted_cores;
+ }
}
}
@@ -483,6 +512,7 @@
* things done here to the most necessary things.
*/
cpu_init();
+ preempt_disable();
smp_callin();
while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
rep_nop();
@@ -608,7 +638,7 @@
printk("Inquiring remote APIC #%d...\n", apicid);
- for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) {
+ for (i = 0; i < ARRAY_SIZE(regs); i++) {
printk("... APIC #%d %s: ", apicid, names[i]);
/*
@@ -1092,11 +1122,8 @@
current_thread_info()->cpu = 0;
smp_tune_scheduling();
- cpus_clear(cpu_sibling_map[0]);
- cpu_set(0, cpu_sibling_map[0]);
-
- cpus_clear(cpu_core_map[0]);
- cpu_set(0, cpu_core_map[0]);
+
+ set_cpu_sibling_map(0);
/*
* If we couldn't find an SMP configuration at boot time,
@@ -1280,15 +1307,24 @@
remove_siblinginfo(int cpu)
{
int sibling;
-
+ struct cpuinfo_x86 *c = cpu_data;
+
+ for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
+ cpu_clear(cpu, cpu_core_map[sibling]);
+ /*
+ * last thread sibling in this cpu core going down
+ */
+ if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+ c[sibling].booted_cores--;
+ }
+
for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
cpu_clear(cpu, cpu_sibling_map[sibling]);
- for_each_cpu_mask(sibling, cpu_core_map[cpu])
- cpu_clear(cpu, cpu_core_map[sibling]);
cpus_clear(cpu_sibling_map[cpu]);
cpus_clear(cpu_core_map[cpu]);
phys_proc_id[cpu] = BAD_APICID;
cpu_core_id[cpu] = BAD_APICID;
+ cpu_clear(cpu, cpu_sibling_setup_map);
}
int __cpu_disable(void)
@@ -1307,8 +1343,7 @@
if (cpu == 0)
return -EBUSY;
- /* We enable the timer again on the exit path of the death loop */
- disable_APIC_timer();
+ clear_local_APIC();
/* Allow any queued timer interrupts to get serviced */
local_irq_enable();
mdelay(1);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c Wed Feb 1 18:00:19 2006
@@ -69,8 +69,6 @@
#include <asm/arch_hooks.h>
-#include "io_ports.h"
-
#include <xen/evtchn.h>
#if defined (__i386__)
@@ -78,10 +76,6 @@
#endif
int pit_latch_buggy; /* extern */
-
-u64 jiffies_64 = INITIAL_JIFFIES;
-
-EXPORT_SYMBOL(jiffies_64);
#if defined(__x86_64__)
unsigned long vxtime_hz = PIT_TICK_RATE;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/traps-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/traps-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/traps-xen.c Wed Feb 1 18:00:19 2006
@@ -626,13 +626,6 @@
nmi_enter();
cpu = smp_processor_id();
-
-#ifdef CONFIG_HOTPLUG_CPU
- if (!cpu_online(cpu)) {
- nmi_exit();
- return;
- }
-#endif
++nmi_count(cpu);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/kernel/traps.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/traps.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/traps.c Wed Feb 1 18:00:19 2006
@@ -488,6 +488,7 @@
tss->io_bitmap_max - thread->io_bitmap_max);
tss->io_bitmap_max = thread->io_bitmap_max;
tss->io_bitmap_base = IO_BITMAP_OFFSET;
+ tss->io_bitmap_owner = thread;
put_cpu();
return;
}
@@ -641,13 +642,6 @@
nmi_enter();
cpu = smp_processor_id();
-
-#ifdef CONFIG_HOTPLUG_CPU
- if (!cpu_online(cpu)) {
- nmi_exit();
- return;
- }
-#endif
++nmi_count(cpu);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/mach-xen/Makefile
--- a/linux-2.6-xen-sparse/arch/i386/mach-xen/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/mach-xen/Makefile Wed Feb 1 18:00:19 2006
@@ -3,5 +3,5 @@
#
obj-y := setup.o topology.o
-
+
topology-y := ../mach-default/topology.o
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/mm/fault-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/mm/fault-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/mm/fault-xen.c Wed Feb 1 18:00:19 2006
@@ -22,7 +22,6 @@
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/kprobes.h>
-#include <linux/percpu.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -30,8 +29,6 @@
#include <asm/kdebug.h>
extern void die(const char *,struct pt_regs *,long);
-
-DEFINE_PER_CPU(pgd_t *, cur_pgd);
/*
* Unlock any spinlocks which will prevent us from getting the
@@ -111,7 +108,7 @@
desc = (void *)desc + (seg & ~7);
} else {
/* Must disable preemption while reading the GDT. */
- desc = (u32 *)get_cpu_gdt_table(get_cpu());
+ desc = (u32 *)get_cpu_gdt_table(get_cpu());
desc = (void *)desc + (seg & ~7);
}
@@ -223,10 +220,7 @@
unsigned long *p, page;
unsigned long mfn;
- preempt_disable();
- page = __pa(per_cpu(cur_pgd, smp_processor_id()));
- preempt_enable();
-
+ page = read_cr3();
p = (unsigned long *)__va(page);
p += (address >> 30) * 2;
printk(KERN_ALERT "%08lx -> *pde = %08lx:%08lx\n", page, p[1], p[0]);
@@ -256,13 +250,8 @@
{
unsigned long page;
- preempt_disable();
- page = ((unsigned long *) per_cpu(cur_pgd, smp_processor_id()))
- [address >> 22];
- preempt_enable();
-
- page = ((unsigned long *) per_cpu(cur_pgd, get_cpu()))
- [address >> 22];
+ page = read_cr3();
+ page = ((unsigned long *) __va(page))[address >> 22];
printk(KERN_ALERT "*pde = ma %08lx pa %08lx\n", page,
machine_to_phys(page));
/*
@@ -304,8 +293,8 @@
unsigned long address;
int write, si_code;
- address = HYPERVISOR_shared_info->vcpu_info[
- smp_processor_id()].arch.cr2;
+ /* get the address */
+ address = read_cr2();
/* Set the "privileged fault" bit to something sane. */
error_code &= ~4;
@@ -582,14 +571,14 @@
* an interrupt in the middle of a task switch..
*/
int index = pgd_index(address);
+ unsigned long pgd_paddr;
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
- preempt_disable();
- pgd = index + per_cpu(cur_pgd, smp_processor_id());
- preempt_enable();
+ pgd_paddr = read_cr3();
+ pgd = index + (pgd_t *)__va(pgd_paddr);
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k))
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/mm/init-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/mm/init-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/mm/init-xen.c Wed Feb 1 18:00:19 2006
@@ -27,6 +27,8 @@
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/efi.h>
+#include <linux/memory_hotplug.h>
+#include <linux/initrd.h>
#include <asm/processor.h>
#include <asm/system.h>
@@ -313,18 +315,47 @@
pkmap_page_table = pte;
}
-void __init one_highpage_init(struct page *page, int pfn, int bad_ppro)
+static void __devinit free_new_highpage(struct page *page, int pfn)
+{
+ set_page_count(page, 1);
+ if (pfn < xen_start_info->nr_pages)
+ __free_page(page);
+ totalhigh_pages++;
+}
+
+void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
{
if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
ClearPageReserved(page);
- set_page_count(page, 1);
- if (pfn < xen_start_info->nr_pages)
- __free_page(page);
- totalhigh_pages++;
+ free_new_highpage(page, pfn);
} else
SetPageReserved(page);
}
+static int add_one_highpage_hotplug(struct page *page, unsigned long pfn)
+{
+ free_new_highpage(page, pfn);
+ totalram_pages++;
+#ifdef CONFIG_FLATMEM
+ max_mapnr = max(pfn, max_mapnr);
+#endif
+ num_physpages++;
+ return 0;
+}
+
+/*
+ * Not currently handling the NUMA case.
+ * Assuming single node and all memory that
+ * has been added dynamically that would be
+ * onlined here is in HIGHMEM
+ */
+void online_page(struct page *page)
+{
+ ClearPageReserved(page);
+ add_one_highpage_hotplug(page, page_to_pfn(page));
+}
+
+
#ifdef CONFIG_NUMA
extern void set_highmem_pages_init(int);
#else
@@ -332,7 +363,7 @@
{
int pfn;
for (pfn = highstart_pfn; pfn < highend_pfn; pfn++)
- one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
+ add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
totalram_pages += totalhigh_pages;
}
#endif /* CONFIG_FLATMEM */
@@ -359,12 +390,9 @@
{
unsigned long vaddr;
pgd_t *pgd_base = (pgd_t *)xen_start_info->pt_base;
- int i;
swapper_pg_dir = pgd_base;
init_mm.pgd = pgd_base;
- for (i = 0; i < NR_CPUS; i++)
- per_cpu(cur_pgd, i) = pgd_base;
/* Enable PSE if available */
if (cpu_has_pse) {
@@ -693,6 +721,28 @@
set_bit(PG_pinned, &virt_to_page(init_mm.pgd)->flags);
}
+
+/*
+ * this is for the non-NUMA, single node SMP system case.
+ * Specifically, in the case of x86, we will always add
+ * memory to the highmem for now.
+ */
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+int add_memory(u64 start, u64 size)
+{
+ struct pglist_data *pgdata = &contig_page_data;
+ struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+
+ return __add_pages(zone, start_pfn, nr_pages);
+}
+
+int remove_memory(u64 start, u64 size)
+{
+ return -EINVAL;
+}
+#endif
kmem_cache_t *pgd_cache;
kmem_cache_t *pmd_cache;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/mm/ioremap-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/mm/ioremap-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/mm/ioremap-xen.c Wed Feb 1 18:00:19 2006
@@ -323,9 +323,15 @@
}
EXPORT_SYMBOL(ioremap_nocache);
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
void iounmap(volatile void __iomem *addr)
{
- struct vm_struct *p;
+ struct vm_struct *p, *o;
if ((void __force *)addr <= high_memory)
return;
@@ -338,14 +344,27 @@
if ((unsigned long) addr >= fix_to_virt(FIX_ISAMAP_BEGIN))
return;
- write_lock(&vmlist_lock);
- p = __remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
- if (!p) {
- printk(KERN_WARNING "iounmap: bad address %p\n", addr);
+ addr = (volatile void __iomem *)(PAGE_MASK & (unsigned long
__force)addr);
+
+ /* Use the vm area unlocked, assuming the caller
+ ensures there isn't another iounmap for the same address
+ in parallel. Reuse of the virtual address is prevented by
+ leaving it in the global lists until we're done with it.
+ cpa takes care of the direct mappings. */
+ read_lock(&vmlist_lock);
+ for (p = vmlist; p; p = p->next) {
+ if (p->addr == addr)
+ break;
+ }
+ read_unlock(&vmlist_lock);
+
+ if (!p) {
+ printk("iounmap: bad address %p\n", addr);
dump_stack();
- goto out_unlock;
- }
-
+ return;
+ }
+
+ /* Reset the direct mapping. Can block */
if ((p->flags >> 20) && is_local_lowmem(p->phys_addr)) {
/* p->size includes the guard page, but cpa doesn't like that */
change_page_attr(virt_to_page(bus_to_virt(p->phys_addr)),
@@ -353,8 +372,10 @@
PAGE_KERNEL);
global_flush_tlb();
}
-out_unlock:
- write_unlock(&vmlist_lock);
+
+ /* Finally remove it */
+ o = remove_vm_area((void *)addr);
+ BUG_ON(p != o || o == NULL);
kfree(p);
}
EXPORT_SYMBOL(iounmap);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/mm/pgtable-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/mm/pgtable-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/mm/pgtable-xen.c Wed Feb 1 18:00:19 2006
@@ -39,11 +39,13 @@
pg_data_t *pgdat;
unsigned long i;
struct page_state ps;
+ unsigned long flags;
printk(KERN_INFO "Mem-info:\n");
show_free_areas();
printk(KERN_INFO "Free swap: %6ldkB\n",
nr_swap_pages<<(PAGE_SHIFT-10));
for_each_pgdat(pgdat) {
+ pgdat_resize_lock(pgdat, &flags);
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
page = pgdat_page_nr(pgdat, i);
total++;
@@ -56,6 +58,7 @@
else if (page_count(page))
shared += page_count(page) - 1;
}
+ pgdat_resize_unlock(pgdat, &flags);
}
printk(KERN_INFO "%d pages of RAM\n", total);
printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
@@ -267,19 +270,19 @@
struct page *page = virt_to_page(pgd);
page->index = (unsigned long)pgd_list;
if (pgd_list)
- pgd_list->private = (unsigned long)&page->index;
+ set_page_private(pgd_list, (unsigned long)&page->index);
pgd_list = page;
- page->private = (unsigned long)&pgd_list;
+ set_page_private(page, (unsigned long)&pgd_list);
}
static inline void pgd_list_del(pgd_t *pgd)
{
struct page *next, **pprev, *page = virt_to_page(pgd);
next = (struct page *)page->index;
- pprev = (struct page **)page->private;
+ pprev = (struct page **)page_private(page);
*pprev = next;
if (next)
- next->private = (unsigned long)pprev;
+ set_page_private(next, (unsigned long)pprev);
}
void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/arch/i386/pci/Makefile
--- a/linux-2.6-xen-sparse/arch/i386/pci/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/pci/Makefile Wed Feb 1 18:00:19 2006
@@ -1,7 +1,7 @@
obj-y := i386.o
obj-$(CONFIG_PCI_BIOS) += pcbios.o
-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o
+obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o direct.o
obj-$(CONFIG_PCI_DIRECT) += direct.o
pci-y := fixup.o
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/pci/irq-xen.c
--- a/linux-2.6-xen-sparse/arch/i386/pci/irq-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/pci/irq-xen.c Wed Feb 1 18:00:19 2006
@@ -550,31 +550,48 @@
return 0;
}
-static __init int via_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+static __init int via_router_probe(struct irq_router *r,
+ struct pci_dev *router, u16 device)
{
/* FIXME: We should move some of the quirk fixup stuff here */
- if (router->device == PCI_DEVICE_ID_VIA_82C686 &&
- device == PCI_DEVICE_ID_VIA_82C586_0) {
- /* Asus k7m bios wrongly reports 82C686A as 586-compatible */
- device = PCI_DEVICE_ID_VIA_82C686;
- }
-
- switch(device)
- {
- case PCI_DEVICE_ID_VIA_82C586_0:
- r->name = "VIA";
- r->get = pirq_via586_get;
- r->set = pirq_via586_set;
- return 1;
- case PCI_DEVICE_ID_VIA_82C596:
+ /*
+ * work arounds for some buggy BIOSes
+ */
+ if (device == PCI_DEVICE_ID_VIA_82C586_0) {
+ switch(router->device) {
case PCI_DEVICE_ID_VIA_82C686:
- case PCI_DEVICE_ID_VIA_8231:
+ /*
+ * Asus k7m bios wrongly reports 82C686A
+ * as 586-compatible
+ */
+ device = PCI_DEVICE_ID_VIA_82C686;
+ break;
+ case PCI_DEVICE_ID_VIA_8235:
+ /**
+ * Asus a7v-x bios wrongly reports 8235
+ * as 586-compatible
+ */
+ device = PCI_DEVICE_ID_VIA_8235;
+ break;
+ }
+ }
+
+ switch(device) {
+ case PCI_DEVICE_ID_VIA_82C586_0:
+ r->name = "VIA";
+ r->get = pirq_via586_get;
+ r->set = pirq_via586_set;
+ return 1;
+ case PCI_DEVICE_ID_VIA_82C596:
+ case PCI_DEVICE_ID_VIA_82C686:
+ case PCI_DEVICE_ID_VIA_8231:
+ case PCI_DEVICE_ID_VIA_8235:
/* FIXME: add new ones for 8233/5 */
- r->name = "VIA";
- r->get = pirq_via_get;
- r->set = pirq_via_set;
- return 1;
+ r->name = "VIA";
+ r->get = pirq_via_get;
+ r->set = pirq_via_set;
+ return 1;
}
return 0;
}
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/um/kernel/physmem.c
--- a/linux-2.6-xen-sparse/arch/um/kernel/physmem.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/um/kernel/physmem.c Wed Feb 1 18:00:19 2006
@@ -248,7 +248,7 @@
/* Changed during early boot */
unsigned long high_physmem;
-extern unsigned long physmem_size;
+extern unsigned long long physmem_size;
int init_maps(unsigned long physmem, unsigned long iomem, unsigned long
highmem)
{
@@ -323,7 +323,7 @@
extern int __syscall_stub_start, __binary_start;
void setup_physmem(unsigned long start, unsigned long reserve_end,
- unsigned long len, unsigned long highmem)
+ unsigned long len, unsigned long long highmem)
{
unsigned long reserve = reserve_end - start;
int pfn = PFN_UP(__pa(reserve_end));
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/arch/x86_64/Kconfig
--- a/linux-2.6-xen-sparse/arch/x86_64/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/Kconfig Wed Feb 1 18:00:19 2006
@@ -242,22 +242,42 @@
source "kernel/Kconfig.preempt"
-config K8_NUMA
- bool "K8 NUMA support"
- select NUMA
+config NUMA
+ bool "Non Uniform Memory Access (NUMA) Support"
depends on SMP && !X86_64_XEN
help
- Enable NUMA (Non Unified Memory Architecture) support for
- AMD Opteron Multiprocessor systems. The kernel will try to allocate
- memory used by a CPU on the local memory controller of the CPU
- and add some more NUMA awareness to the kernel.
- This code is recommended on all multiprocessor Opteron systems
- and normally doesn't hurt on others.
+ Enable NUMA (Non Uniform Memory Access) support. The kernel
+ will try to allocate memory used by a CPU on the local memory
+ controller of the CPU and add some more NUMA awareness to the kernel.
+ This code is recommended on all multiprocessor Opteron systems.
+ If the system is EM64T, you should say N unless your system is EM64T
+ NUMA.
+
+config K8_NUMA
+ bool "Old style AMD Opteron NUMA detection"
+ depends on NUMA
+ default y
+ help
+ Enable K8 NUMA node topology detection. You should say Y here if
+ you have a multi processor AMD K8 system. This uses an old
+ method to read the NUMA configurtion directly from the builtin
+ Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA
+ instead, which also takes priority if both are compiled in.
+
+# Dummy CONFIG option to select ACPI_NUMA from drivers/acpi/Kconfig.
+
+config X86_64_ACPI_NUMA
+ bool "ACPI NUMA detection"
+ depends on NUMA
+ select ACPI
+ select ACPI_NUMA
+ default y
+ help
+ Enable ACPI SRAT based node topology detection.
config NUMA_EMU
- bool "NUMA emulation support"
- select NUMA
- depends on SMP && !X86_64_XEN
+ bool "NUMA emulation"
+ depends on NUMA
help
Enable NUMA emulation. A flat machine will be split
into virtual nodes when booted with "numa=fake=N", where N is the
@@ -268,9 +288,6 @@
depends on NUMA
default y
-config NUMA
- bool
- default n
config ARCH_DISCONTIGMEM_ENABLE
def_bool y
@@ -393,6 +410,14 @@
Additional support for intel specific MCE features such as
the thermal monitor.
+config X86_MCE_AMD
+ bool "AMD MCE features"
+ depends on X86_MCE && X86_LOCAL_APIC
+ default y
+ help
+ Additional support for AMD specific MCE features such as
+ the DRAM Error Threshold.
+
config PHYSICAL_START
hex "Physical address where the kernel is loaded" if EMBEDDED
default "0x100000"
@@ -528,7 +553,7 @@
left.
config IA32_AOUT
- bool "IA32 a.out support"
+ tristate "IA32 a.out support"
depends on IA32_EMULATION
help
Support old a.out binaries in the 32bit emulation.
@@ -558,8 +583,21 @@
source fs/Kconfig
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
source "arch/x86_64/oprofile/Kconfig"
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
+
source "arch/x86_64/Kconfig.debug"
source "security/Kconfig"
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/Makefile
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/Makefile Wed Feb 1 18:00:19 2006
@@ -11,6 +11,7 @@
obj-$(CONFIG_X86_MCE) += mce.o
obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o
+obj-$(CONFIG_X86_MCE_AMD) += mce_amd.o
obj-$(CONFIG_MTRR) += ../../i386/kernel/cpu/mtrr/
obj-$(CONFIG_ACPI) += acpi/
obj-$(CONFIG_X86_MSR) += msr.o
@@ -22,13 +23,13 @@
obj-$(CONFIG_X86_IO_APIC) += io_apic.o mpparse.o \
genapic.o genapic_cluster.o genapic_flat.o
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o
-obj-$(CONFIG_PM) += suspend.o
+obj-$(CONFIG_SOFTWARE_SUSPEND) += suspend.o
+obj-$(CONFIG_ACPI_SLEEP) += suspend.o
obj-$(CONFIG_SOFTWARE_SUSPEND) += suspend_asm.o
obj-$(CONFIG_CPU_FREQ) += cpufreq/
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_GART_IOMMU) += pci-gart.o aperture.o
obj-$(CONFIG_DUMMY_IOMMU) += pci-nommu.o pci-dma.o
-obj-$(CONFIG_SWIOTLB) += swiotlb.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer.o
@@ -42,7 +43,6 @@
bootflag-y += ../../i386/kernel/bootflag.o
cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../i386/kernel/cpuid.o
topology-y += ../../i386/mach-default/topology.o
-swiotlb-$(CONFIG_SWIOTLB) += ../../ia64/lib/swiotlb.o
microcode-$(subst m,y,$(CONFIG_MICROCODE)) += ../../i386/kernel/microcode.o
intel_cacheinfo-y += ../../i386/kernel/cpu/intel_cacheinfo.o
quirks-y += ../../i386/kernel/quirks.o
@@ -51,6 +51,7 @@
ifdef CONFIG_XEN
time-y += ../../i386/kernel/time-xen.o
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
swiotlb-$(CONFIG_SWIOTLB) := ../../i386/kernel/swiotlb.o
pci-dma-y += ../../i386/kernel/pci-dma-xen.o
microcode-$(subst m,y,$(CONFIG_MICROCODE)) :=
../../i386/kernel/microcode-xen.o
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/apic-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/apic-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/apic-xen.c Wed Feb 1
18:00:19 2006
@@ -33,8 +33,6 @@
#include <asm/desc.h>
#include <asm/arch_hooks.h>
#include <asm/hpet.h>
-
-#include "io_ports.h"
/*
* Debug level
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/e820-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/e820-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/e820-xen.c Wed Feb 1
18:00:19 2006
@@ -23,6 +23,7 @@
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/bootsetup.h>
+#include <asm/sections.h>
#include <xen/interface/memory.h>
unsigned long pci_mem_start = 0xaeedbabe;
@@ -54,7 +55,6 @@
}
#ifndef CONFIG_XEN
-extern char _end[];
/*
* end_pfn only includes RAM, while end_pfn_map includes all e820 entries.
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/entry-xen.S
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/entry-xen.S Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/entry-xen.S Wed Feb 1
18:00:19 2006
@@ -609,7 +609,14 @@
CFI_ENDPROC
.endm
-#if 0
+#ifndef CONFIG_XEN
+ENTRY(thermal_interrupt)
+ apicinterrupt THERMAL_APIC_VECTOR,smp_thermal_interrupt
+
+ENTRY(threshold_interrupt)
+ apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
+
+#ifdef CONFIG_SMP
ENTRY(reschedule_interrupt)
apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
@@ -630,6 +637,7 @@
ENTRY(call_function_interrupt)
apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
#endif
+#endif /* !CONFIG_XEN */
#ifdef CONFIG_X86_LOCAL_APIC
ENTRY(apic_timer_interrupt)
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/head-xen.S
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/head-xen.S Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/head-xen.S Wed Feb 1
18:00:19 2006
@@ -25,6 +25,7 @@
#include <linux/threads.h>
+#include <linux/init.h>
#include <asm/desc.h>
#include <asm/segment.h>
#include <asm/page.h>
@@ -243,6 +244,26 @@
.quad 0x0000000000003007 + __PHYSICAL_START /* -> level3_kernel_pgt
*/
#endif
+#ifndef CONFIG_XEN
+#ifndef CONFIG_HOTPLUG_CPU
+ __INITDATA
+#endif
+ /*
+ * This default setting generates an ident mapping at address 0x100000
+ * and a mapping for the kernel that precisely maps virtual address
+ * 0xffffffff80000000 to physical address 0x000000. (always using
+ * 2Mbyte large pages provided by PAE mode)
+ */
+ .align PAGE_SIZE
+ENTRY(boot_level4_pgt)
+ .quad 0x0000000000002007 + __PHYSICAL_START /* -> level3_ident_pgt
*/
+ .fill 255,8,0
+ .quad 0x000000000000a007 + __PHYSICAL_START
+ .fill 254,8,0
+ /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+ .quad 0x0000000000003007 + __PHYSICAL_START /* -> level3_kernel_pgt
*/
+#endif
+
.data
.align 16
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/head64-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/head64-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/head64-xen.c Wed Feb 1
18:00:19 2006
@@ -22,6 +22,8 @@
#include <asm/bootsetup.h>
#include <asm/setup.h>
#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
unsigned long start_pfn;
@@ -30,9 +32,8 @@
#if 0
static void __init clear_bss(void)
{
- extern char __bss_start[], __bss_end[];
memset(__bss_start, 0,
- (unsigned long) __bss_end - (unsigned long) __bss_start);
+ (unsigned long) __bss_stop - (unsigned long) __bss_start);
}
#endif
@@ -84,8 +85,6 @@
boot_cpu_data.x86_mask = eax & 0xf;
}
-extern char _end[];
-
void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/io_apic-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/io_apic-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/io_apic-xen.c Wed Feb 1
18:00:19 2006
@@ -57,7 +57,7 @@
* Rough estimation of how many shared IRQs there are, can
* be changed anytime.
*/
-#define MAX_PLUS_SHARED_IRQS NR_IRQS
+#define MAX_PLUS_SHARED_IRQS NR_IRQ_VECTORS
#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
/*
@@ -162,6 +162,7 @@
static int first_free_entry = NR_IRQS;
struct irq_pin_list *entry = irq_2_pin + irq;
+ BUG_ON(irq >= NR_IRQS);
while (entry->next)
entry = irq_2_pin + entry->next;
@@ -169,7 +170,7 @@
entry->next = first_free_entry;
entry = irq_2_pin + entry->next;
if (++first_free_entry >= PIN_MAP_SIZE)
- panic("io_apic.c: whoops");
+ panic("io_apic.c: ran out of irq_2_pin entries!");
}
entry->apic = apic;
entry->pin = pin;
@@ -182,6 +183,7 @@
int pin; \
struct irq_pin_list *entry = irq_2_pin + irq; \
\
+ BUG_ON(irq >= NR_IRQS); \
for (;;) { \
unsigned int reg; \
pin = entry->pin; \
@@ -258,6 +260,8 @@
}
#endif /* !CONFIG_XEN */
+
+static u8 gsi_2_irq[NR_IRQ_VECTORS] = { [0 ... NR_IRQ_VECTORS-1] = 0xFF };
/*
* support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
@@ -470,6 +474,7 @@
best_guess = irq;
}
}
+ BUG_ON(best_guess >= NR_IRQS);
return best_guess;
}
@@ -660,6 +665,64 @@
return MPBIOS_trigger(idx);
}
+static int next_irq = 16;
+
+/*
+ * gsi_irq_sharing -- Name overload! "irq" can be either a legacy IRQ
+ * in the range 0-15, a linux IRQ in the range 0-223, or a GSI number
+ * from ACPI, which can reach 800 in large boxen.
+ *
+ * Compact the sparse GSI space into a sequential IRQ series and reuse
+ * vectors if possible.
+ */
+int gsi_irq_sharing(int gsi)
+{
+ int i, tries, vector;
+
+ BUG_ON(gsi >= NR_IRQ_VECTORS);
+
+ if (platform_legacy_irq(gsi))
+ return gsi;
+
+ if (gsi_2_irq[gsi] != 0xFF)
+ return (int)gsi_2_irq[gsi];
+
+ tries = NR_IRQS;
+ try_again:
+ vector = assign_irq_vector(gsi);
+
+ /*
+ * Sharing vectors means sharing IRQs, so scan irq_vectors for previous
+ * use of vector and if found, return that IRQ. However, we never want
+ * to share legacy IRQs, which usually have a different trigger mode
+ * than PCI.
+ */
+ for (i = 0; i < NR_IRQS; i++)
+ if (IO_APIC_VECTOR(i) == vector)
+ break;
+ if (platform_legacy_irq(i)) {
+ if (--tries >= 0) {
+ IO_APIC_VECTOR(i) = 0;
+ goto try_again;
+ }
+ panic("gsi_irq_sharing: didn't find an IRQ using vector 0x%02X
for GSI %d", vector, gsi);
+ }
+ if (i < NR_IRQS) {
+ gsi_2_irq[gsi] = i;
+ printk(KERN_INFO "GSI %d sharing vector 0x%02X and IRQ %d\n",
+ gsi, vector, i);
+ return i;
+ }
+
+ i = next_irq++;
+ BUG_ON(i >= NR_IRQS);
+ gsi_2_irq[gsi] = i;
+ IO_APIC_VECTOR(i) = vector;
+ printk(KERN_INFO "GSI %d assigned vector 0x%02X and IRQ %d\n",
+ gsi, vector, i);
+ return i;
+}
+
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
@@ -689,6 +752,7 @@
while (i < apic)
irq += nr_ioapic_registers[i++];
irq += pin;
+ irq = gsi_irq_sharing(irq);
break;
}
default:
@@ -698,6 +762,7 @@
break;
}
}
+ BUG_ON(irq >= NR_IRQS);
/*
* PCI IRQ command line redirection. Yes, limits are hardcoded.
@@ -713,6 +778,7 @@
}
}
}
+ BUG_ON(irq >= NR_IRQS);
return irq;
}
@@ -741,7 +807,7 @@
static int current_vector = FIRST_DEVICE_VECTOR;
physdev_op_t op;
- BUG_ON(irq >= NR_IRQ_VECTORS);
+ BUG_ON(irq != AUTO_ASSIGN && (unsigned)irq >= NR_IRQ_VECTORS);
if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0)
return IO_APIC_VECTOR(irq);
@@ -1990,6 +2056,7 @@
entry.polarity = active_high_low;
entry.mask = 1; /* Disabled (masked) */
+ irq = gsi_irq_sharing(irq);
/*
* IRQs < 16 are already in the irq_2_pin[] map
*/
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/mpparse-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/mpparse-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/mpparse-xen.c Wed Feb 1
18:00:19 2006
@@ -42,7 +42,7 @@
* Various Linux-internal data structures created from the
* MP-table.
*/
-int apic_version [MAX_APICS];
+unsigned char apic_version [MAX_APICS];
unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] =
-1 };
int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 };
@@ -65,7 +65,9 @@
/* Processor that is doing the boot up */
unsigned int boot_cpu_id = -1U;
/* Internal processor count */
-static unsigned int num_processors = 0;
+unsigned int num_processors __initdata = 0;
+
+unsigned disabled_cpus __initdata;
/* Bitmask of physically existing CPUs */
physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE;
@@ -107,11 +109,14 @@
#ifndef CONFIG_XEN
static void __init MP_processor_info (struct mpc_config_processor *m)
{
- int ver, cpu;
+ int cpu;
+ unsigned char ver;
static int found_bsp=0;
- if (!(m->mpc_cpuflag & CPU_ENABLED))
+ if (!(m->mpc_cpuflag & CPU_ENABLED)) {
+ disabled_cpus++;
return;
+ }
printk(KERN_INFO "Processor #%d %d:%d APIC version %d\n",
m->mpc_apicid,
@@ -130,12 +135,14 @@
}
cpu = num_processors++;
-
- if (m->mpc_apicid > MAX_APICS) {
+
+#if MAX_APICS < 255
+ if ((int)m->mpc_apicid > MAX_APICS) {
printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n",
m->mpc_apicid, MAX_APICS);
return;
}
+#endif
ver = m->mpc_apicver;
physid_set(m->mpc_apicid, phys_cpu_present_map);
@@ -225,7 +232,7 @@
m->mpc_irqtype, m->mpc_irqflag & 3,
(m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq);
- if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ if (++mp_irq_entries >= MAX_IRQ_SOURCES)
panic("Max # of irq sources exceeded!!\n");
}
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/pci-nommu-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/pci-nommu-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/pci-nommu-xen.c Wed Feb 1
18:00:19 2006
@@ -25,7 +25,7 @@
*/
void *dma_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, unsigned gfp)
+ dma_addr_t *dma_handle, gfp_t gfp)
{
void *ret;
u64 mask;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/process-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/process-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/process-xen.c Wed Feb 1
18:00:19 2006
@@ -96,10 +96,13 @@
if (need_resched()) {
local_irq_enable();
} else {
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+ smp_mb__after_clear_bit();
stop_hz_timer();
/* Blocking includes an implicit local_irq_enable(). */
HYPERVISOR_sched_op(SCHEDOP_block, 0);
start_hz_timer();
+ set_thread_flag(TIF_POLLING_NRFLAG);
}
}
@@ -143,6 +146,8 @@
*/
void cpu_idle (void)
{
+ set_thread_flag(TIF_POLLING_NRFLAG);
+
/* endless idle loop with no priority at all */
while (1) {
while (!need_resched()) {
@@ -156,7 +161,9 @@
xen_idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
@@ -180,7 +187,8 @@
do {
ssleep(1);
for_each_online_cpu(cpu) {
- if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state,
cpu))
+ if (cpu_isset(cpu, map) &&
+ !per_cpu(cpu_idle_state, cpu))
cpu_clear(cpu, map);
}
cpus_and(map, map, cpu_online_map);
@@ -208,7 +216,8 @@
system_utsname.version);
printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
printk_address(regs->rip);
- printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp,
regs->eflags);
+ printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp,
+ regs->eflags);
printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
regs->rax, regs->rbx, regs->rcx);
printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
@@ -281,13 +290,6 @@
{
struct task_struct *tsk = current;
struct thread_info *t = current_thread_info();
-
- /*
- * Remove function-return probe instances associated with this task
- * and put them back on the free list. Do not insert an exit probe for
- * this function, it will be disabled by kprobe_flush_task if you do.
- */
- kprobe_flush_task(tsk);
if (t->flags & _TIF_ABI_PENDING)
t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);
@@ -361,15 +363,14 @@
struct pt_regs * childregs;
struct task_struct *me = current;
- childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long)
p->thread_info)) - 1;
-
+ childregs = ((struct pt_regs *)
+ (THREAD_SIZE + (unsigned long) p->thread_info)) - 1;
*childregs = *regs;
childregs->rax = 0;
childregs->rsp = rsp;
- if (rsp == ~0UL) {
+ if (rsp == ~0UL)
childregs->rsp = (unsigned long)childregs;
- }
p->thread.rsp = (unsigned long) childregs;
p->thread.rsp0 = (unsigned long) (childregs+1);
@@ -391,7 +392,8 @@
p->thread.io_bitmap_max = 0;
return -ENOMEM;
}
- memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
IO_BITMAP_BYTES);
+ memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
+ IO_BITMAP_BYTES);
}
/*
@@ -432,7 +434,8 @@
* - fold all the options into a flag word and test it with a single test.
* - could test fs/gs bitsliced
*/
-struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct
*next_p)
+struct task_struct *
+__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
@@ -530,7 +533,8 @@
prev->userrsp = read_pda(oldrsp);
write_pda(oldrsp, next->userrsp);
write_pda(pcurrent, next_p);
- write_pda(kernelstack, (unsigned long)next_p->thread_info + THREAD_SIZE
- PDA_STACKOFFSET);
+ write_pda(kernelstack,
+ (unsigned long)next_p->thread_info + THREAD_SIZE - PDA_STACKOFFSET);
/*
* Now maybe reload the debug registers
@@ -591,7 +595,9 @@
return do_fork(SIGCHLD, regs->rsp, regs, 0, NULL, NULL);
}
-asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void
__user *parent_tid, void __user *child_tid, struct pt_regs *regs)
+asmlinkage long
+sys_clone(unsigned long clone_flags, unsigned long newsp,
+ void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
{
if (!newsp)
newsp = regs->rsp;
@@ -627,7 +633,8 @@
return 0;
fp = *(u64 *)(p->thread.rsp);
do {
- if (fp < (unsigned long)stack || fp > (unsigned
long)stack+THREAD_SIZE)
+ if (fp < (unsigned long)stack ||
+ fp > (unsigned long)stack+THREAD_SIZE)
return 0;
rip = *(u64 *)(fp+8);
if (!in_sched_functions(rip))
@@ -662,8 +669,9 @@
task->thread.gsindex = 0;
task->thread.gs = addr;
if (doit) {
- load_gs_index(0);
- ret = HYPERVISOR_set_segment_base(SEGBASE_GS_USER, addr);
+ load_gs_index(0);
+ ret = HYPERVISOR_set_segment_base(
+ SEGBASE_GS_USER, addr);
}
}
put_cpu();
@@ -680,7 +688,7 @@
set_32bit_tls(task, FS_TLS, addr);
if (doit) {
load_TLS(&task->thread, cpu);
- asm volatile("mov %0,%%fs" :: "r" (FS_TLS_SEL));
+ asm volatile("movl %0,%%fs" :: "r"(FS_TLS_SEL));
}
task->thread.fsindex = FS_TLS_SEL;
task->thread.fs = 0;
@@ -690,9 +698,9 @@
if (doit) {
/* set the selector to 0 to not confuse
__switch_to */
- asm volatile("mov %0,%%fs" :: "r" (0));
- ret = HYPERVISOR_set_segment_base(SEGBASE_FS,
addr);
-
+ asm volatile("movl %0,%%fs" :: "r" (0));
+ ret = HYPERVISOR_set_segment_base(SEGBASE_FS,
+ addr);
}
}
put_cpu();
@@ -701,9 +709,9 @@
unsigned long base;
if (task->thread.fsindex == FS_TLS_SEL)
base = read_32bit_tls(task, FS_TLS);
- else if (doit) {
+ else if (doit)
rdmsrl(MSR_FS_BASE, base);
- } else
+ else
base = task->thread.fs;
ret = put_user(base, (unsigned long __user *)addr);
break;
@@ -712,9 +720,9 @@
unsigned long base;
if (task->thread.gsindex == GS_TLS_SEL)
base = read_32bit_tls(task, GS_TLS);
- else if (doit) {
+ else if (doit)
rdmsrl(MSR_KERNEL_GS_BASE, base);
- } else
+ else
base = task->thread.gs;
ret = put_user(base, (unsigned long __user *)addr);
break;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/setup-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/setup-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/setup-xen.c Wed Feb 1
18:00:19 2006
@@ -60,6 +60,7 @@
#include <asm/setup.h>
#include <asm/mach_apic.h>
#include <asm/numa.h>
+#include <asm/sections.h>
#ifdef CONFIG_XEN
#include <linux/percpu.h>
#include <xen/interface/physdev.h>
@@ -139,7 +140,6 @@
struct e820map e820;
extern int root_mountflags;
-extern char _text, _etext, _edata, _end;
char command_line[COMMAND_LINE_SIZE];
@@ -473,7 +473,6 @@
{
unsigned long bootmap_size, bootmap;
- memory_present(0, start_pfn, end_pfn);
bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size);
if (bootmap == -1L)
@@ -773,8 +772,6 @@
}
#endif
- sparse_init();
-
paging_init();
#ifdef CONFIG_X86_LOCAL_APIC
/*
@@ -855,6 +852,8 @@
check_ioapic();
#endif
+ zap_low_mappings(0);
+
#ifdef CONFIG_ACPI
/*
* Initialize the ACPI boot-time table parser (gets the RSDP and SDT).
@@ -1032,7 +1031,7 @@
#endif
bits = 0;
- while ((1 << bits) < c->x86_num_cores)
+ while ((1 << bits) < c->x86_max_cores)
bits++;
/* Low order bits define the core id (index of core in socket) */
@@ -1062,10 +1061,10 @@
if (!node_online(node))
node = nearby_node(apicid);
}
- cpu_to_node[cpu] = node;
+ numa_set_node(cpu, node);
printk(KERN_INFO "CPU %d(%d) -> Node %d -> Core %d\n",
- cpu, c->x86_num_cores, node, cpu_core_id[cpu]);
+ cpu, c->x86_max_cores, node, cpu_core_id[cpu]);
#endif
#endif
}
@@ -1114,9 +1113,9 @@
display_cacheinfo(c);
if (c->extended_cpuid_level >= 0x80000008) {
- c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
- if (c->x86_num_cores & (c->x86_num_cores - 1))
- c->x86_num_cores = 1;
+ c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+ if (c->x86_max_cores & (c->x86_max_cores - 1))
+ c->x86_max_cores = 1;
amd_detect_cmp(c);
}
@@ -1128,54 +1127,44 @@
{
#ifdef CONFIG_SMP
u32 eax, ebx, ecx, edx;
- int index_msb, tmp;
+ int index_msb, core_bits;
int cpu = smp_processor_id();
-
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+
+ c->apicid = phys_pkg_id(0);
+
if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
return;
- cpuid(1, &eax, &ebx, &ecx, &edx);
smp_num_siblings = (ebx & 0xff0000) >> 16;
-
+
if (smp_num_siblings == 1) {
printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
- } else if (smp_num_siblings > 1) {
- index_msb = 31;
- /*
- * At this point we only support two siblings per
- * processor package.
- */
+ } else if (smp_num_siblings > 1 ) {
+
if (smp_num_siblings > NR_CPUS) {
printk(KERN_WARNING "CPU: Unsupported number of the
siblings %d", smp_num_siblings);
smp_num_siblings = 1;
return;
}
- tmp = smp_num_siblings;
- while ((tmp & 0x80000000 ) == 0) {
- tmp <<=1 ;
- index_msb--;
- }
- if (smp_num_siblings & (smp_num_siblings - 1))
- index_msb++;
+
+ index_msb = get_count_order(smp_num_siblings);
phys_proc_id[cpu] = phys_pkg_id(index_msb);
-
+
printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
phys_proc_id[cpu]);
- smp_num_siblings = smp_num_siblings / c->x86_num_cores;
-
- tmp = smp_num_siblings;
- index_msb = 31;
- while ((tmp & 0x80000000) == 0) {
- tmp <<=1 ;
- index_msb--;
- }
- if (smp_num_siblings & (smp_num_siblings - 1))
- index_msb++;
-
- cpu_core_id[cpu] = phys_pkg_id(index_msb);
-
- if (c->x86_num_cores > 1)
+ smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+ index_msb = get_count_order(smp_num_siblings) ;
+
+ core_bits = get_count_order(c->x86_max_cores);
+
+ cpu_core_id[cpu] = phys_pkg_id(index_msb) &
+ ((1 << core_bits) - 1);
+
+ if (c->x86_max_cores > 1)
printk(KERN_INFO "CPU: Processor Core ID: %d\n",
cpu_core_id[cpu]);
}
@@ -1214,7 +1203,7 @@
node = apicid_to_node[hard_smp_processor_id()];
if (node == NUMA_NO_NODE)
node = 0;
- cpu_to_node[cpu] = node;
+ numa_set_node(cpu, node);
if (acpi_numa > 0)
printk(KERN_INFO "CPU %d -> Node %d\n", cpu, node);
@@ -1232,13 +1221,18 @@
unsigned eax = cpuid_eax(0x80000008);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
+ /* CPUID workaround for Intel 0F34 CPU */
+ if (c->x86_vendor == X86_VENDOR_INTEL &&
+ c->x86 == 0xF && c->x86_model == 0x3 &&
+ c->x86_mask == 0x4)
+ c->x86_phys_bits = 36;
}
if (c->x86 == 15)
c->x86_cache_alignment = c->x86_clflush_size * 2;
if (c->x86 >= 15)
set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
- c->x86_num_cores = intel_num_cpu_cores(c);
+ c->x86_max_cores = intel_num_cpu_cores(c);
srat_detect_node();
}
@@ -1276,7 +1270,7 @@
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_clflush_size = 64;
c->x86_cache_alignment = c->x86_clflush_size;
- c->x86_num_cores = 1;
+ c->x86_max_cores = 1;
c->extended_cpuid_level = 0;
memset(&c->x86_capability, 0, sizeof c->x86_capability);
@@ -1299,10 +1293,10 @@
c->x86 = (tfms >> 8) & 0xf;
c->x86_model = (tfms >> 4) & 0xf;
c->x86_mask = tfms & 0xf;
- if (c->x86 == 0xf) {
+ if (c->x86 == 0xf)
c->x86 += (tfms >> 20) & 0xff;
+ if (c->x86 >= 0x6)
c->x86_model += ((tfms >> 16) & 0xF) << 4;
- }
if (c->x86_capability[0] & (1<<19))
c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
} else {
@@ -1452,7 +1446,7 @@
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
/* Intel-defined (#2) */
- "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "est",
+ "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", NULL, "est",
"tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
@@ -1510,13 +1504,12 @@
seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
#ifdef CONFIG_SMP
- if (smp_num_siblings * c->x86_num_cores > 1) {
+ if (smp_num_siblings * c->x86_max_cores > 1) {
int cpu = c - cpu_data;
seq_printf(m, "physical id\t: %d\n", phys_proc_id[cpu]);
- seq_printf(m, "siblings\t: %d\n",
- c->x86_num_cores * smp_num_siblings);
+ seq_printf(m, "siblings\t: %d\n",
cpus_weight(cpu_core_map[cpu]));
seq_printf(m, "core id\t\t: %d\n", cpu_core_id[cpu]);
- seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores);
+ seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
}
#endif
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/setup64-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/setup64-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/setup64-xen.c Wed Feb 1
18:00:19 2006
@@ -255,6 +255,7 @@
/* CPU 0 is initialised in head64.c */
if (cpu != 0) {
pda_init(cpu);
+ zap_low_mappings(cpu);
} else
estacks = boot_exception_stacks;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/smp-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/smp-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/smp-xen.c Wed Feb 1 18:00:19 2006
@@ -70,8 +70,6 @@
want false sharing in the per cpu data segment. */
static DEFINE_PER_CPU(union smp_flush_state, flush_state);
#endif
-
-#define __cpuinit __init
/*
* We cannot call mmdrop() because we are in interrupt context,
@@ -478,15 +476,16 @@
void smp_stop_cpu(void)
{
+ unsigned long flags;
/*
* Remove this CPU:
*/
cpu_clear(smp_processor_id(), cpu_online_map);
- local_irq_disable();
+ local_irq_save(flags);
#ifndef CONFIG_XEN
disable_local_APIC();
#endif
- local_irq_enable();
+ local_irq_restore(flags);
}
static void smp_really_stop_cpu(void *dummy)
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/traps-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/traps-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/traps-xen.c Wed Feb 1
18:00:19 2006
@@ -430,19 +430,6 @@
{
conditional_sti(regs);
-#ifdef CONFIG_CHECKING
- {
- unsigned long gs;
- struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
- rdmsrl(MSR_GS_BASE, gs);
- if (gs != (unsigned long)pda) {
- wrmsrl(MSR_GS_BASE, pda);
- printk("%s: wrong gs %lx expected %p rip %lx\n", str,
gs, pda,
- regs->rip);
- }
- }
-#endif
-
if (user_mode(regs)) {
struct task_struct *tsk = current;
@@ -514,20 +501,6 @@
long error_code)
{
conditional_sti(regs);
-
-#ifdef CONFIG_CHECKING
- {
- unsigned long gs;
- struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
- rdmsrl(MSR_GS_BASE, gs);
- if (gs != (unsigned long)pda) {
- wrmsrl(MSR_GS_BASE, pda);
- oops_in_progress++;
- printk("general protection handler: wrong gs %lx
expected %p\n", gs, pda);
- oops_in_progress--;
- }
- }
-#endif
if (user_mode(regs)) {
struct task_struct *tsk = current;
@@ -670,19 +643,6 @@
unsigned long condition;
struct task_struct *tsk = current;
siginfo_t info;
-
-#ifdef CONFIG_CHECKING
- {
- /* RED-PEN interaction with debugger - could destroy gs */
- unsigned long gs;
- struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
- rdmsrl(MSR_GS_BASE, gs);
- if (gs != (unsigned long)pda) {
- wrmsrl(MSR_GS_BASE, pda);
- printk("debug handler: wrong gs %lx expected %p\n", gs,
pda);
- }
- }
-#endif
get_debugreg(condition, 6);
@@ -896,6 +856,10 @@
}
#endif
+asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void)
+{
+}
+
/*
* 'math_state_restore()' saves the current math information in the
* old math state array, and gets the new ones from the current task
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/kernel/x8664_ksyms-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/kernel/x8664_ksyms-xen.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/x8664_ksyms-xen.c Wed Feb 1
18:00:19 2006
@@ -204,3 +204,6 @@
#endif
EXPORT_SYMBOL(cpu_khz);
+
+EXPORT_SYMBOL(load_gs_index);
+
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/mm/fault-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/mm/fault-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/mm/fault-xen.c Wed Feb 1 18:00:19 2006
@@ -24,7 +24,6 @@
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/kprobes.h>
-#include <linux/percpu.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -35,8 +34,6 @@
#include <asm/kdebug.h>
#include <asm-generic/sections.h>
#include <asm/kdebug.h>
-
-DEFINE_PER_CPU(pgd_t *, cur_pgd);
void bust_spinlocks(int yes)
{
@@ -149,9 +146,10 @@
pmd_t *pmd;
pte_t *pte;
- preempt_disable();
- pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id());
- preempt_enable();
+ asm("movq %%cr3,%0" : "=r" (pgd));
+ pgd = (pgd_t *)machine_to_phys((maddr_t)pgd);
+
+ pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
pgd += pgd_index(address);
printk("PGD %lx ", pgd_val(*pgd));
if (bad_address(pgd)) goto bad;
@@ -252,9 +250,9 @@
/* On Xen the line below does not always work. Needs investigating! */
/*pgd = pgd_offset(current->mm ?: &init_mm, address);*/
- preempt_disable();
- pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id());
- preempt_enable();
+ asm("movq %%cr3,%0" : "=r" (pgd));
+ pgd = (pgd_t *)machine_to_phys((maddr_t)pgd);
+ pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
pgd += pgd_index(address);
pgd_ref = pgd_offset_k(address);
if (pgd_none(*pgd_ref))
@@ -330,22 +328,9 @@
if (!user_mode(regs))
error_code &= ~4; /* means kernel */
-#ifdef CONFIG_CHECKING
- {
- unsigned long gs;
- struct x8664_pda *pda = cpu_pda + stack_smp_processor_id();
- rdmsrl(MSR_GS_BASE, gs);
- if (gs != (unsigned long)pda) {
- wrmsrl(MSR_GS_BASE, pda);
- printk("page_fault: wrong gs %lx expected %p\n", gs,
pda);
- }
- }
-#endif
-
/* get the address */
address = HYPERVISOR_shared_info->vcpu_info[
smp_processor_id()].arch.cr2;
-
if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
SIGSEGV) == NOTIFY_STOP)
return;
@@ -595,3 +580,10 @@
force_sig_info(SIGBUS, &info, tsk);
return;
}
+
+static int __init enable_pagefaulttrace(char *str)
+{
+ page_fault_trace = 1;
+ return 0;
+}
+__setup("pagefaulttrace", enable_pagefaulttrace);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/mm/init-xen.c
--- a/linux-2.6-xen-sparse/arch/x86_64/mm/init-xen.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/mm/init-xen.c Wed Feb 1 18:00:19 2006
@@ -25,6 +25,7 @@
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
+#include <linux/pci.h>
#include <asm/processor.h>
#include <asm/system.h>
@@ -39,6 +40,7 @@
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
+#include <asm/sections.h>
#include <xen/features.h>
@@ -52,7 +54,7 @@
extern void swiotlb_init(void);
#endif
-extern char _stext[];
+static unsigned long dma_reserve __initdata;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
extern unsigned long start_pfn;
@@ -193,9 +195,6 @@
}
/* References to section boundaries */
-
-extern char _text, _etext, _edata, __bss_start, _end[];
-extern char __init_begin, __init_end;
int after_bootmem;
@@ -492,10 +491,6 @@
void __init xen_init_pt(void)
{
unsigned long addr, *page;
- int i;
-
- for (i = 0; i < NR_CPUS; i++)
- per_cpu(cur_pgd, i) = init_mm.pgd;
memset((void *)init_level4_pgt, 0, PAGE_SIZE);
memset((void *)level3_kernel_pgt, 0, PAGE_SIZE);
@@ -628,9 +623,7 @@
__flush_tlb_all();
}
-extern struct x8664_pda cpu_pda[NR_CPUS];
-
-void zap_low_mappings(void)
+void __cpuinit zap_low_mappings(int cpu)
{
/* this is not required for Xen */
#if 0
@@ -638,32 +631,74 @@
#endif
}
+/* Compute zone sizes for the DMA and DMA32 zones in a node. */
+__init void
+size_zones(unsigned long *z, unsigned long *h,
+ unsigned long start_pfn, unsigned long end_pfn)
+{
+ int i;
+#ifndef CONFIG_XEN
+ unsigned long w;
+#endif
+
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ z[i] = 0;
+
+#ifndef CONFIG_XEN
+ if (start_pfn < MAX_DMA_PFN)
+ z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
+ if (start_pfn < MAX_DMA32_PFN) {
+ unsigned long dma32_pfn = MAX_DMA32_PFN;
+ if (dma32_pfn > end_pfn)
+ dma32_pfn = end_pfn;
+ z[ZONE_DMA32] = dma32_pfn - start_pfn;
+ }
+ z[ZONE_NORMAL] = end_pfn - start_pfn;
+
+ /* Remove lower zones from higher ones. */
+ w = 0;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ if (z[i])
+ z[i] -= w;
+ w += z[i];
+ }
+
+ /* Compute holes */
+ w = start_pfn;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ unsigned long s = w;
+ w += z[i];
+ h[i] = e820_hole_size(s, w);
+ }
+
+ /* Add the space pace needed for mem_map to the holes too. */
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
+
+ /* The 16MB DMA zone has the kernel and other misc mappings.
+ Account them too */
+ if (h[ZONE_DMA]) {
+ h[ZONE_DMA] += dma_reserve;
+ if (h[ZONE_DMA] >= z[ZONE_DMA]) {
+ printk(KERN_WARNING
+ "Kernel too large and filling up ZONE_DMA?\n");
+ h[ZONE_DMA] = z[ZONE_DMA];
+ }
+ }
+#else
+ z[ZONE_DMA] = end_pfn;
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ h[i] = 0;
+#endif
+}
+
#ifndef CONFIG_NUMA
void __init paging_init(void)
{
- {
- unsigned long zones_size[MAX_NR_ZONES];
- unsigned long holes[MAX_NR_ZONES];
- /* unsigned int max_dma; */
-
- memset(zones_size, 0, sizeof(zones_size));
- memset(holes, 0, sizeof(holes));
-
- /* max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >>
PAGE_SHIFT; */
- /* if (end_pfn < max_dma) { */
- zones_size[ZONE_DMA] = end_pfn;
-#if 0
- holes[ZONE_DMA] = e820_hole_size(0, end_pfn);
- } else {
- zones_size[ZONE_DMA] = max_dma;
- holes[ZONE_DMA] = e820_hole_size(0, max_dma);
- zones_size[ZONE_NORMAL] = end_pfn - max_dma;
- holes[ZONE_NORMAL] = e820_hole_size(max_dma, end_pfn);
- }
-#endif
- free_area_init_node(0, NODE_DATA(0), zones_size,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
- }
+ unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
+ size_zones(zones, holes, 0, end_pfn);
+ free_area_init_node(0, NODE_DATA(0), zones,
+ __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info);
HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO);
@@ -780,18 +815,17 @@
datasize >> 10,
initsize >> 10);
+#ifndef CONFIG_XEN
+#ifdef CONFIG_SMP
/*
- * Subtle. SMP is doing its boot stuff late (because it has to
- * fork idle threads) - but it also needs low mappings for the
- * protected-mode entry to work. We zap these entries only after
- * the WP-bit has been tested.
+ * Sync boot_level4_pgt mappings with the init_level4_pgt
+ * except for the low identity mappings which are already zapped
+ * in init_level4_pgt. This sync-up is essential for AP's bringup
*/
-#ifndef CONFIG_SMP
- zap_low_mappings();
-#endif
-}
-
-extern char __initdata_begin[], __initdata_end[];
+ memcpy(boot_level4_pgt+1, init_level4_pgt+1,
(PTRS_PER_PGD-1)*sizeof(pgd_t));
+#endif
+#endif
+}
void free_initmem(void)
{
@@ -819,7 +853,7 @@
totalram_pages++;
}
memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
- printk ("Freeing unused kernel memory: %luk freed\n", (&__init_end -
&__init_begin) >> 10);
+ printk ("Freeing unused kernel memory: %luk freed\n", (__init_end -
__init_begin) >> 10);
#endif
}
@@ -847,6 +881,8 @@
#else
reserve_bootmem(phys, len);
#endif
+ if (phys+len <= MAX_DMA_PFN*PAGE_SIZE)
+ dma_reserve += len / PAGE_SIZE;
}
int kern_addr_valid(unsigned long addr)
@@ -888,10 +924,6 @@
static ctl_table debug_table2[] = {
{ 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL,
proc_dointvec },
-#ifdef CONFIG_CHECKING
- { 100, "page-fault-trace", &page_fault_trace, sizeof(int), 0644, NULL,
- proc_dointvec },
-#endif
{ 0, }
};
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/x86_64/pci/Makefile
--- a/linux-2.6-xen-sparse/arch/x86_64/pci/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/x86_64/pci/Makefile Wed Feb 1 18:00:19 2006
@@ -11,7 +11,7 @@
obj-$(CONFIG_ACPI) += acpi.o
obj-y += legacy.o irq.o common.o
# mmconfig has a 64bit special
-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o
+obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o direct.o
obj-$(CONFIG_NUMA) += k8-bus.o
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/Makefile
--- a/linux-2.6-xen-sparse/drivers/Makefile Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/Makefile Wed Feb 1 18:00:19 2006
@@ -7,6 +7,7 @@
obj-$(CONFIG_PCI) += pci/
obj-$(CONFIG_PARISC) += parisc/
+obj-$(CONFIG_RAPIDIO) += rapidio/
obj-y += video/
obj-$(CONFIG_ACPI) += acpi/
# PnP must come after ACPI since it will eventually need to check if acpi
@@ -49,6 +50,7 @@
obj-$(CONFIG_PARIDE) += block/paride/
obj-$(CONFIG_TC) += tc/
obj-$(CONFIG_USB) += usb/
+obj-$(CONFIG_PCI) += usb/
obj-$(CONFIG_USB_GADGET) += usb/gadget/
obj-$(CONFIG_GAMEPORT) += input/gameport/
obj-$(CONFIG_INPUT) += input/
@@ -68,3 +70,4 @@
obj-$(CONFIG_SGI_IOC4) += sn/
obj-y += firmware/
obj-$(CONFIG_CRYPTO) += crypto/
+obj-$(CONFIG_SUPERH) += sh/
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/acpi/Kconfig
--- a/linux-2.6-xen-sparse/drivers/acpi/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/acpi/Kconfig Wed Feb 1 18:00:19 2006
@@ -197,7 +197,6 @@
config ACPI_IBM
tristate "IBM ThinkPad Laptop Extras"
depends on X86
- default y
---help---
This is a Linux ACPI driver for the IBM ThinkPad laptops. It adds
support for Fn-Fx key combinations, Bluetooth control, video
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/char/mem.c
--- a/linux-2.6-xen-sparse/drivers/char/mem.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/mem.c Wed Feb 1 18:00:19 2006
@@ -233,9 +233,7 @@
static int mmap_mem(struct file * file, struct vm_area_struct * vma)
{
#if defined(__HAVE_PHYS_MEM_ACCESS_PROT)
- unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
-
- vma->vm_page_prot = phys_mem_access_prot(file, offset,
+ vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
vma->vm_end - vma->vm_start,
vma->vm_page_prot);
#elif defined(pgprot_noncached)
@@ -926,7 +924,8 @@
mem_class = class_create(THIS_MODULE, "mem");
for (i = 0; i < ARRAY_SIZE(devlist); i++) {
- class_device_create(mem_class, MKDEV(MEM_MAJOR,
devlist[i].minor),
+ class_device_create(mem_class, NULL,
+ MKDEV(MEM_MAJOR, devlist[i].minor),
NULL, devlist[i].name);
devfs_mk_cdev(MKDEV(MEM_MAJOR, devlist[i].minor),
S_IFCHR | devlist[i].mode, devlist[i].name);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/drivers/char/tpm/Kconfig
--- a/linux-2.6-xen-sparse/drivers/char/tpm/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/tpm/Kconfig Wed Feb 1 18:00:19 2006
@@ -6,7 +6,7 @@
config TCG_TPM
tristate "TPM Hardware Support"
- depends on EXPERIMENTAL && (PCI || XEN)
+ depends on EXPERIMENTAL
---help---
If you have a TPM security chip in your system, which
implements the Trusted Computing Group's specification,
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/char/tpm/tpm.c
--- a/linux-2.6-xen-sparse/drivers/char/tpm/tpm.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/tpm/tpm.c Wed Feb 1 18:00:19 2006
@@ -47,6 +47,13 @@
{
struct tpm_chip *chip = (struct tpm_chip *) ptr;
+ schedule_work(&chip->work);
+}
+
+static void timeout_work(void * ptr)
+{
+ struct tpm_chip *chip = ptr;
+
down(&chip->buffer_mutex);
atomic_set(&chip->data_pending, 0);
memset(chip->data_buffer, 0, chip->vendor->buffersize);
@@ -146,8 +153,7 @@
__be32 index;
char *str = buf;
- struct tpm_chip *chip =
- pci_get_drvdata(to_pci_dev(dev));
+ struct tpm_chip *chip = dev_get_drvdata(dev);
if (chip == NULL)
return -ENODEV;
@@ -170,7 +176,8 @@
< READ_PCR_RESULT_SIZE){
dev_dbg(chip->dev, "A TPM error (%d) occurred"
" attempting to read PCR %d of %d\n",
- be32_to_cpu(*((__be32 *) (data + 6))), i,
num_pcrs);
+ be32_to_cpu(*((__be32 *) (data + 6))),
+ i, num_pcrs);
goto out;
}
str += sprintf(str, "PCR-%02d: ", i);
@@ -198,17 +205,15 @@
int i, rc;
char *str = buf;
- struct tpm_chip *chip =
- pci_get_drvdata(to_pci_dev(dev));
+ struct tpm_chip *chip = dev_get_drvdata(dev);
if (chip == NULL)
return -ENODEV;
- data = kmalloc(READ_PUBEK_RESULT_SIZE, GFP_KERNEL);
+ data = kzalloc(READ_PUBEK_RESULT_SIZE, GFP_KERNEL);
if (!data)
return -ENOMEM;
memcpy(data, readpubek, sizeof(readpubek));
- memset(data + sizeof(readpubek), 0, 20); /* zero nonce */
if ((len = tpm_transmit(chip, data, READ_PUBEK_RESULT_SIZE)) <
READ_PUBEK_RESULT_SIZE) {
@@ -252,7 +257,6 @@
kfree(data);
return rc;
}
-
EXPORT_SYMBOL_GPL(tpm_show_pubek);
#define CAP_VER_RESULT_SIZE 18
@@ -281,8 +285,7 @@
ssize_t len;
char *str = buf;
- struct tpm_chip *chip =
- pci_get_drvdata(to_pci_dev(dev));
+ struct tpm_chip *chip = dev_get_drvdata(dev);
if (chip == NULL)
return -ENODEV;
@@ -321,7 +324,6 @@
return count;
}
EXPORT_SYMBOL_GPL(tpm_store_cancel);
-
/*
* Device file system interface to the TPM
@@ -346,8 +348,7 @@
}
if (chip->num_opens) {
- dev_dbg(chip->dev,
- "Another process owns this TPM\n");
+ dev_dbg(chip->dev, "Another process owns this TPM\n");
rc = -EBUSY;
goto err_out;
}
@@ -373,7 +374,6 @@
spin_unlock(&driver_lock);
return rc;
}
-
EXPORT_SYMBOL_GPL(tpm_open);
int tpm_release(struct inode *inode, struct file *file)
@@ -384,16 +384,16 @@
file->private_data = NULL;
chip->num_opens--;
del_singleshot_timer_sync(&chip->user_read_timer);
+ flush_scheduled_work();
atomic_set(&chip->data_pending, 0);
put_device(chip->dev);
kfree(chip->data_buffer);
spin_unlock(&driver_lock);
return 0;
}
-
EXPORT_SYMBOL_GPL(tpm_release);
-ssize_t tpm_write(struct file * file, const char __user * buf,
+ssize_t tpm_write(struct file *file, const char __user *buf,
size_t size, loff_t * off)
{
struct tpm_chip *chip = file->private_data;
@@ -431,13 +431,14 @@
EXPORT_SYMBOL_GPL(tpm_write);
-ssize_t tpm_read(struct file * file, char __user * buf,
+ssize_t tpm_read(struct file * file, char __user *buf,
size_t size, loff_t * off)
{
struct tpm_chip *chip = file->private_data;
int ret_size;
int pos, pending = 0;
+ flush_scheduled_work();
ret_size = atomic_read(&chip->data_pending);
if (ret_size > 0) { /* relay data */
if (size < ret_size)
@@ -446,8 +447,7 @@
pos = atomic_read(&chip->data_position);
down(&chip->buffer_mutex);
- if (copy_to_user
- ((void __user *) buf, &chip->data_buffer[pos], ret_size)) {
+ if (copy_to_user(buf, &chip->data_buffer[pos], ret_size)) {
ret_size = -EFAULT;
} else {
pending = atomic_read(&chip->data_pending) - ret_size;
@@ -466,7 +466,6 @@
return ret_size;
}
-
EXPORT_SYMBOL_GPL(tpm_read);
void tpm_remove_hardware(struct device *dev)
@@ -490,13 +489,13 @@
sysfs_remove_group(&dev->kobj, chip->vendor->attr_group);
- dev_mask[chip->dev_num / TPM_NUM_MASK_ENTRIES ] &= !(1 <<
(chip->dev_num % TPM_NUM_MASK_ENTRIES));
+ dev_mask[chip->dev_num / TPM_NUM_MASK_ENTRIES ] &=
+ ~(1 << (chip->dev_num % TPM_NUM_MASK_ENTRIES));
kfree(chip);
put_device(dev);
}
-
EXPORT_SYMBOL_GPL(tpm_remove_hardware);
static u8 savestate[] = {
@@ -509,32 +508,30 @@
* We are about to suspend. Save the TPM state
* so that it can be restored.
*/
-int tpm_pm_suspend(struct pci_dev *pci_dev, pm_message_t pm_state)
-{
- struct tpm_chip *chip = pci_get_drvdata(pci_dev);
+int tpm_pm_suspend(struct device *dev, pm_message_t pm_state)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
if (chip == NULL)
return -ENODEV;
tpm_transmit(chip, savestate, sizeof(savestate));
return 0;
}
-
EXPORT_SYMBOL_GPL(tpm_pm_suspend);
/*
* Resume from a power safe. The BIOS already restored
* the TPM state.
*/
-int tpm_pm_resume(struct pci_dev *pci_dev)
-{
- struct tpm_chip *chip = pci_get_drvdata(pci_dev);
+int tpm_pm_resume(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
if (chip == NULL)
return -ENODEV;
return 0;
}
-
EXPORT_SYMBOL_GPL(tpm_pm_resume);
/*
@@ -544,8 +541,7 @@
* upon errant exit from this function specific probe function should call
* pci_disable_device
*/
-int tpm_register_hardware(struct device *dev,
- struct tpm_vendor_specific *entry)
+int tpm_register_hardware(struct device *dev, struct tpm_vendor_specific
*entry)
{
#define DEVNAME_SIZE 7
@@ -554,15 +550,15 @@
int i, j;
/* Driver specific per-device data */
- chip = kmalloc(sizeof(*chip), GFP_KERNEL);
+ chip = kzalloc(sizeof(*chip), GFP_KERNEL);
if (chip == NULL)
return -ENOMEM;
-
- memset(chip, 0, sizeof(struct tpm_chip));
init_MUTEX(&chip->buffer_mutex);
init_MUTEX(&chip->tpm_mutex);
INIT_LIST_HEAD(&chip->list);
+
+ INIT_WORK(&chip->work, timeout_work, chip);
init_timer(&chip->user_read_timer);
chip->user_read_timer.function = user_reader_timeout;
@@ -589,8 +585,7 @@
dev_num_search_complete:
if (chip->dev_num < 0) {
- dev_err(dev,
- "No available tpm device numbers\n");
+ dev_err(dev, "No available tpm device numbers\n");
kfree(chip);
return -ENODEV;
} else if (chip->dev_num == 0)
@@ -628,7 +623,6 @@
return 0;
}
-
EXPORT_SYMBOL_GPL(tpm_register_hardware);
MODULE_AUTHOR("Leendert van Doorn (leendert@xxxxxxxxxxxxxx)");
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/char/tpm/tpm.h
--- a/linux-2.6-xen-sparse/drivers/char/tpm/tpm.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/tpm/tpm.h Wed Feb 1 18:00:19 2006
@@ -19,11 +19,11 @@
*
*/
#include <linux/module.h>
-#include <linux/version.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
+#include <linux/platform_device.h>
enum tpm_timeout {
TPM_TIMEOUT = 5, /* msecs */
@@ -76,6 +76,7 @@
struct semaphore buffer_mutex;
struct timer_list user_read_timer; /* user needs to claim result */
+ struct work_struct work;
struct semaphore tpm_mutex; /* tpm is processing */
struct tpm_vendor_specific *vendor;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/drivers/char/tpm/tpm_atmel.c
--- a/linux-2.6-xen-sparse/drivers/char/tpm/tpm_atmel.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/tpm/tpm_atmel.c Wed Feb 1 18:00:19 2006
@@ -20,12 +20,7 @@
*/
#include "tpm.h"
-
-/* Atmel definitions */
-enum tpm_atmel_addr {
- TPM_ATMEL_BASE_ADDR_LO = 0x08,
- TPM_ATMEL_BASE_ADDR_HI = 0x09
-};
+#include "tpm_atmel.h"
/* write status bits */
enum tpm_atmel_write_status {
@@ -40,7 +35,7 @@
ATML_STATUS_READY = 0x08
};
-static int tpm_atml_recv(struct tpm_chip *chip, u8 * buf, size_t count)
+static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
{
u8 status, *hdr = buf;
u32 size;
@@ -52,13 +47,12 @@
return -EIO;
for (i = 0; i < 6; i++) {
- status = inb(chip->vendor->base + 1);
+ status = atmel_getb(chip, 1);
if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
- dev_err(chip->dev,
- "error reading header\n");
+ dev_err(chip->dev, "error reading header\n");
return -EIO;
}
- *buf++ = inb(chip->vendor->base);
+ *buf++ = atmel_getb(chip, 0);
}
/* size of the data received */
@@ -69,10 +63,9 @@
dev_err(chip->dev,
"Recv size(%d) less than available space\n", size);
for (; i < size; i++) { /* clear the waiting data anyway */
- status = inb(chip->vendor->base + 1);
+ status = atmel_getb(chip, 1);
if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
- dev_err(chip->dev,
- "error reading data\n");
+ dev_err(chip->dev, "error reading data\n");
return -EIO;
}
}
@@ -81,17 +74,16 @@
/* read all the data available */
for (; i < size; i++) {
- status = inb(chip->vendor->base + 1);
+ status = atmel_getb(chip, 1);
if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
- dev_err(chip->dev,
- "error reading data\n");
+ dev_err(chip->dev, "error reading data\n");
return -EIO;
}
- *buf++ = inb(chip->vendor->base);
+ *buf++ = atmel_getb(chip, 0);
}
/* make sure data available is gone */
- status = inb(chip->vendor->base + 1);
+ status = atmel_getb(chip, 1);
if (status & ATML_STATUS_DATA_AVAIL) {
dev_err(chip->dev, "data available is stuck\n");
return -EIO;
@@ -100,14 +92,14 @@
return size;
}
-static int tpm_atml_send(struct tpm_chip *chip, u8 * buf, size_t count)
+static int tpm_atml_send(struct tpm_chip *chip, u8 *buf, size_t count)
{
int i;
dev_dbg(chip->dev, "tpm_atml_send:\n");
for (i = 0; i < count; i++) {
dev_dbg(chip->dev, "%d 0x%x(%d)\n", i, buf[i], buf[i]);
- outb(buf[i], chip->vendor->base);
+ atmel_putb(buf[i], chip, 0);
}
return count;
@@ -115,12 +107,12 @@
static void tpm_atml_cancel(struct tpm_chip *chip)
{
- outb(ATML_STATUS_ABORT, chip->vendor->base + 1);
+ atmel_putb(ATML_STATUS_ABORT, chip, 1);
}
static u8 tpm_atml_status(struct tpm_chip *chip)
{
- return inb(chip->vendor->base + 1);
+ return atmel_getb(chip, 1);
}
static struct file_operations atmel_ops = {
@@ -142,7 +134,7 @@
&dev_attr_pcrs.attr,
&dev_attr_caps.attr,
&dev_attr_cancel.attr,
- 0,
+ NULL,
};
static struct attribute_group atmel_attr_grp = { .attrs = atmel_attrs };
@@ -159,27 +151,39 @@
.miscdev = { .fops = &atmel_ops, },
};
-static int __devinit tpm_atml_init(struct pci_dev *pci_dev,
- const struct pci_device_id *pci_id)
-{
- u8 version[4];
+static struct platform_device *pdev;
+
+static void atml_plat_remove(void)
+{
+ struct tpm_chip *chip = dev_get_drvdata(&pdev->dev);
+
+ if (chip) {
+ if (chip->vendor->have_region)
+ atmel_release_region(chip->vendor->base,
+ chip->vendor->region_size);
+ atmel_put_base_addr(chip->vendor);
+ tpm_remove_hardware(chip->dev);
+ platform_device_unregister(pdev);
+ }
+}
+
+static struct device_driver atml_drv = {
+ .name = "tpm_atmel",
+ .bus = &platform_bus_type,
+ .owner = THIS_MODULE,
+ .suspend = tpm_pm_suspend,
+ .resume = tpm_pm_resume,
+};
+
+static int __init init_atmel(void)
+{
int rc = 0;
- int lo, hi;
-
- if (pci_enable_device(pci_dev))
- return -EIO;
-
- lo = tpm_read_index(TPM_ADDR, TPM_ATMEL_BASE_ADDR_LO);
- hi = tpm_read_index(TPM_ADDR, TPM_ATMEL_BASE_ADDR_HI);
-
- tpm_atmel.base = (hi<<8)|lo;
- dev_dbg( &pci_dev->dev, "Operating with base: 0x%x\n", tpm_atmel.base);
-
- /* verify that it is an Atmel part */
- if (tpm_read_index(TPM_ADDR, 4) != 'A' || tpm_read_index(TPM_ADDR, 5)
!= 'T'
- || tpm_read_index(TPM_ADDR, 6) != 'M' || tpm_read_index(TPM_ADDR,
7) != 'L') {
+
+ driver_register(&atml_drv);
+
+ if ((tpm_atmel.iobase = atmel_get_base_addr(&tpm_atmel)) == NULL) {
rc = -ENODEV;
- goto out_err;
+ goto err_unreg_drv;
}
/* query chip for its version number */
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/char/tty_io.c
--- a/linux-2.6-xen-sparse/drivers/char/tty_io.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/char/tty_io.c Wed Feb 1 18:00:19 2006
@@ -811,7 +811,7 @@
check_tty_count(tty, "do_tty_hangup");
file_list_lock();
/* This breaks for file handles being sent over AF_UNIX sockets ? */
- list_for_each_entry(filp, &tty->tty_files, f_list) {
+ list_for_each_entry(filp, &tty->tty_files, f_u.fu_list) {
if (filp->f_op->write == redirected_tty_write)
cons_filp = filp;
if (filp->f_op->write != tty_write)
@@ -1418,14 +1418,11 @@
/* Release locally allocated memory ... nothing placed in slots */
free_mem_out:
- if (o_tp)
- kfree(o_tp);
+ kfree(o_tp);
if (o_tty)
free_tty_struct(o_tty);
- if (ltp)
- kfree(ltp);
- if (tp)
- kfree(tp);
+ kfree(ltp);
+ kfree(tp);
free_tty_struct(tty);
fail_no_mem:
@@ -2730,7 +2727,7 @@
pty_line_name(driver, index, name);
else
tty_line_name(driver, index, name);
- class_device_create(tty_class, dev, device, name);
+ class_device_create(tty_class, NULL, dev, device, "%s", name);
}
/**
@@ -2985,14 +2982,14 @@
register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0)
panic("Couldn't register /dev/tty driver\n");
devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 0), S_IFCHR|S_IRUGO|S_IWUGO, "tty");
- class_device_create(tty_class, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty");
+ class_device_create(tty_class, NULL, MKDEV(TTYAUX_MAJOR, 0), NULL,
"tty");
cdev_init(&console_cdev, &console_fops);
if (cdev_add(&console_cdev, MKDEV(TTYAUX_MAJOR, 1), 1) ||
register_chrdev_region(MKDEV(TTYAUX_MAJOR, 1), 1, "/dev/console") <
0)
panic("Couldn't register /dev/console driver\n");
devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 1), S_IFCHR|S_IRUSR|S_IWUSR,
"console");
- class_device_create(tty_class, MKDEV(TTYAUX_MAJOR, 1), NULL, "console");
+ class_device_create(tty_class, NULL, MKDEV(TTYAUX_MAJOR, 1), NULL,
"console");
#ifdef CONFIG_UNIX98_PTYS
cdev_init(&ptmx_cdev, &ptmx_fops);
@@ -3000,7 +2997,7 @@
register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0)
panic("Couldn't register /dev/ptmx driver\n");
devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 2), S_IFCHR|S_IRUGO|S_IWUGO, "ptmx");
- class_device_create(tty_class, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx");
+ class_device_create(tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL,
"ptmx");
#endif
#ifdef CONFIG_VT
@@ -3011,7 +3008,7 @@
register_chrdev_region(MKDEV(TTY_MAJOR, 0), 1, "/dev/vc/0") < 0)
panic("Couldn't register /dev/tty0 driver\n");
devfs_mk_cdev(MKDEV(TTY_MAJOR, 0), S_IFCHR|S_IRUSR|S_IWUSR, "vc/0");
- class_device_create(tty_class, MKDEV(TTY_MAJOR, 0), NULL, "tty0");
+ class_device_create(tty_class, NULL, MKDEV(TTY_MAJOR, 0), NULL, "tty0");
vty_init();
out_vt:
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/drivers/firmware/Kconfig
--- a/linux-2.6-xen-sparse/drivers/firmware/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/firmware/Kconfig Wed Feb 1 18:00:19 2006
@@ -60,6 +60,7 @@
config DELL_RBU
tristate "BIOS update support for DELL systems via sysfs"
+ depends on X86
select FW_LOADER
help
Say m if you want to have the option of updating the BIOS for your
@@ -70,8 +71,7 @@
config DCDBAS
tristate "Dell Systems Management Base Driver"
- depends on X86 || X86_64
- default m
+ depends on X86
help
The Dell Systems Management Base Driver provides a sysfs interface
for systems management software to perform System Management
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/drivers/serial/Kconfig
--- a/linux-2.6-xen-sparse/drivers/serial/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/serial/Kconfig Wed Feb 1 18:00:19 2006
@@ -10,7 +10,8 @@
# The new 8250/16550 serial drivers
config SERIAL_8250
tristate "8250/16550 and compatible serial support"
- depends on (BROKEN || !(SPARC64 || SPARC32 || XEN_DISABLE_SERIAL))
+ depends on (BROKEN || !SPARC)
+ depends on !XEN_DISABLE_SERIAL
select SERIAL_CORE
---help---
This selects whether you want to include the driver for the standard
@@ -207,6 +208,14 @@
system, say Y to this option. The driver can handle 1, 2, or 3 port
cards. If unsure, say N.
+config SERIAL_8250_AU1X00
+ bool "AU1X00 serial port support"
+ depends on SERIAL_8250 != n && SOC_AU1X00
+ help
+ If you have an Au1x00 board and want to use the serial port, say Y
+ to this option. The driver can handle 1 or 2 serial ports.
+ If unsure, say N.
+
comment "Non-8250 serial port support"
config SERIAL_AMBA_PL010
@@ -461,14 +470,14 @@
config SERIAL_SUNCORE
bool
- depends on SPARC32 || SPARC64
+ depends on SPARC
select SERIAL_CORE
select SERIAL_CORE_CONSOLE
default y
config SERIAL_SUNZILOG
tristate "Sun Zilog8530 serial support"
- depends on SPARC32 || SPARC64
+ depends on SPARC
help
This driver supports the Zilog8530 serial ports found on many Sparc
systems. Say Y or M if you want to be able to these serial ports.
@@ -483,7 +492,7 @@
config SERIAL_SUNSU
tristate "Sun SU serial support"
- depends on (SPARC32 || SPARC64) && PCI
+ depends on SPARC && PCI
help
This driver supports the 8250 serial ports that run the keyboard and
mouse on (PCI) UltraSPARC systems. Say Y or M if you want to be able
@@ -499,7 +508,7 @@
config SERIAL_MUX
tristate "Serial MUX support"
- depends on PARISC
+ depends on GSC
select SERIAL_CORE
default y
---help---
@@ -539,7 +548,7 @@
config SERIAL_SUNSAB
tristate "Sun Siemens SAB82532 serial support"
- depends on (SPARC32 || SPARC64) && PCI
+ depends on SPARC && PCI
help
This driver supports the Siemens SAB82532 DUSCC serial ports on newer
(PCI) UltraSPARC systems. Say Y or M if you want to be able to these
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c
--- a/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Wed Feb 1
18:00:19 2006
@@ -92,14 +92,14 @@
static struct timer_list balloon_timer;
/* Use the private and mapping fields of struct page as a list. */
-#define PAGE_TO_LIST(p) ((struct list_head *)&p->private)
+#define PAGE_TO_LIST(p) ((struct list_head *)&p->u.private)
#define LIST_TO_PAGE(l) \
- (list_entry(((unsigned long *)l), struct page, private))
+ (list_entry(((unsigned long *)l), struct page, u.private))
#define UNLIST_PAGE(p) \
do { \
list_del(PAGE_TO_LIST(p)); \
p->mapping = NULL; \
- p->private = 0; \
+ p->u.private = 0; \
} while(0)
#define IPRINTK(fmt, args...) \
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/drivers/xen/core/smpboot.c
--- a/linux-2.6-xen-sparse/drivers/xen/core/smpboot.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/drivers/xen/core/smpboot.c Wed Feb 1 18:00:19 2006
@@ -126,8 +126,10 @@
static void cpu_bringup(void)
{
- if (!cpu_isset(smp_processor_id(), cpu_initialized))
+ if (!cpu_isset(smp_processor_id(), cpu_initialized)) {
cpu_init();
+ preempt_disable();
+ }
local_irq_enable();
cpu_idle();
}
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/fs/Kconfig
--- a/linux-2.6-xen-sparse/fs/Kconfig Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/fs/Kconfig Wed Feb 1 18:00:19 2006
@@ -810,7 +810,7 @@
config HUGETLBFS
bool "HugeTLB file system support"
- depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || X86_64 || BROKEN
+ depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || BROKEN
depends !XEN
config HUGETLB_PAGE
@@ -899,6 +899,7 @@
config HFS_FS
tristate "Apple Macintosh file system support (EXPERIMENTAL)"
depends on EXPERIMENTAL
+ select NLS
help
If you say Y here, you will be able to mount Macintosh-formatted
floppy disks and hard drive partitions with full read-write access.
@@ -1051,6 +1052,19 @@
- NOR flash with transparent ECC
- DataFlash
+config JFFS2_SUMMARY
+ bool "JFFS2 summary support (EXPERIMENTAL)"
+ depends on JFFS2_FS && EXPERIMENTAL
+ default n
+ help
+ This feature makes it possible to use summary information
+ for faster filesystem mount.
+
+ The summary information can be inserted into a filesystem image
+ by the utility 'sumtool'.
+
+ If unsure, say 'N'.
+
config JFFS2_COMPRESSION_OPTIONS
bool "Advanced compression options for JFFS2"
depends on JFFS2_FS
@@ -1072,10 +1086,10 @@
default y
help
Zlib is designed to be a free, general-purpose, legally unencumbered,
- lossless data-compression library for use on virtually any computer
+ lossless data-compression library for use on virtually any computer
hardware and operating system. See <http://www.gzip.org/zlib/> for
further information.
-
+
Say 'Y' if unsure.
config JFFS2_RTIME
@@ -1097,7 +1111,7 @@
default JFFS2_CMODE_PRIORITY
depends on JFFS2_FS
help
- You can set here the default compression mode of JFFS2 from
+ You can set here the default compression mode of JFFS2 from
the available compression modes. Don't touch if unsure.
config JFFS2_CMODE_NONE
@@ -1108,13 +1122,13 @@
config JFFS2_CMODE_PRIORITY
bool "priority"
help
- Tries the compressors in a predefinied order and chooses the first
+ Tries the compressors in a predefinied order and chooses the first
successful one.
config JFFS2_CMODE_SIZE
bool "size (EXPERIMENTAL)"
help
- Tries all compressors and chooses the one which has the smallest
+ Tries all compressors and chooses the one which has the smallest
result.
endchoice
@@ -1588,9 +1602,10 @@
PC operating systems. The CIFS protocol is fully supported by
file servers such as Windows 2000 (including Windows 2003, NT 4
and Windows XP) as well by Samba (which provides excellent CIFS
- server support for Linux and many other operating systems). Currently
- you must use the smbfs client filesystem to access older SMB servers
- such as Windows 9x and OS/2.
+ server support for Linux and many other operating systems). Limited
+ support for Windows ME and similar servers is provided as well.
+ You must use the smbfs client filesystem to access older SMB servers
+ such as OS/2 and DOS.
The intent of the cifs module is to provide an advanced
network file system client for mounting to CIFS compliant servers,
@@ -1601,7 +1616,7 @@
cifs if running only a (Samba) server. It is possible to enable both
smbfs and cifs (e.g. if you are using CIFS for accessing Windows 2003
and Samba 3 servers, and smbfs for accessing old servers). If you
need
- to mount to Samba or Windows 2003 servers from this machine, say Y.
+ to mount to Samba or Windows from this machine, say Y.
config CIFS_STATS
bool "CIFS statistics"
@@ -1610,8 +1625,22 @@
Enabling this option will cause statistics for each server share
mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
+config CIFS_STATS2
+ bool "CIFS extended statistics"
+ depends on CIFS_STATS
+ help
+ Enabling this option will allow more detailed statistics on SMB
+ request timing to be displayed in /proc/fs/cifs/DebugData and also
+ allow optional logging of slow responses to dmesg (depending on the
+ value of /proc/fs/cifs/cifsFYI, see fs/cifs/README for more details).
+ These additional statistics may have a minor effect on performance
+ and memory utilization.
+
+ Unless you are a developer or are doing network performance analysis
+ or tuning, say N.
+
config CIFS_XATTR
- bool "CIFS extended attributes (EXPERIMENTAL)"
+ bool "CIFS extended attributes"
depends on CIFS
help
Extended attributes are name:value pairs associated with inodes by
@@ -1623,11 +1652,11 @@
prefaced by the user namespace prefix. The system namespace
(used by some filesystems to store ACLs) is not supported at
this time.
-
+
If unsure, say N.
config CIFS_POSIX
- bool "CIFS POSIX Extensions (EXPERIMENTAL)"
+ bool "CIFS POSIX Extensions"
depends on CIFS_XATTR
help
Enabling this option will cause the cifs client to attempt to
@@ -1640,10 +1669,28 @@
config CIFS_EXPERIMENTAL
bool "CIFS Experimental Features (EXPERIMENTAL)"
- depends on CIFS
+ depends on CIFS && EXPERIMENTAL
help
- Enables cifs features under testing. These features
- are highly experimental. If unsure, say N.
+ Enables cifs features under testing. These features are
+ experimental and currently include support for writepages
+ (multipage writebehind performance improvements) and directory
+ change notification ie fcntl(F_DNOTIFY) as well as some security
+ improvements. Some also depend on setting at runtime the
+ pseudo-file /proc/fs/cifs/Experimental (which is disabled by
+ default). See the file fs/cifs/README for more details.
+
+ If unsure, say N.
+
+config CIFS_UPCALL
+ bool "CIFS Kerberos/SPNEGO advanced session setup (EXPERIMENTAL)"
+ depends on CIFS_EXPERIMENTAL
+ select CONNECTOR
+ help
+ Enables an upcall mechanism for CIFS which will be used to contact
+ userspace helper utilities to provide SPNEGO packaged Kerberos
+ tickets which are needed to mount to certain secure servers
+ (for which more secure Kerberos authentication is required). If
+ unsure, say N.
config NCP_FS
tristate "NCP file system support (to mount NetWare volumes)"
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/atomic.h
--- a/linux-2.6-xen-sparse/include/asm-i386/atomic.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/atomic.h Wed Feb 1 18:00:19 2006
@@ -210,6 +210,27 @@
return atomic_add_return(-i,v);
}
+#define atomic_cmpxchg(v, old, new) ((int)cmpxchg(&((v)->counter), old, new))
+
+/**
+ * atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+#define atomic_add_unless(v, a, u) \
+({ \
+ int c, old; \
+ c = atomic_read(v); \
+ while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+ c = old; \
+ c != (u); \
+})
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
#define atomic_inc_return(v) (atomic_add_return(1,v))
#define atomic_dec_return(v) (atomic_sub_return(1,v))
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/desc.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/desc.h Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/desc.h Wed Feb 1
18:00:19 2006
@@ -14,6 +14,8 @@
#include <asm/mmu.h>
extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
+
+#define get_cpu_gdt_table(_cpu) ((struct desc_struct
*)cpu_gdt_descr[(_cpu)].address)
DECLARE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
@@ -37,8 +39,6 @@
#define store_idt(dtr) __asm__ ("sidt %0":"=m" (*dtr))
#define store_tr(tr) __asm__ ("str %0":"=mr" (tr))
#define store_ldt(ldt) __asm__ ("sldt %0":"=mr" (ldt))
-
-#define get_cpu_gdt_table(_cpu) ((struct desc_struct
*)cpu_gdt_descr[(_cpu)].address)
/*
* This is the ldt that every process will get unless we need
@@ -68,8 +68,7 @@
static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int
size)
{
- _set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT],
- (int)addr, ((size << 3)-1), 0x82);
+ _set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], (int)addr,
((size << 3)-1), 0x82);
}
#define LDT_entry_a(info) \
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h Wed Feb
1 18:00:19 2006
@@ -63,7 +63,6 @@
cpu_set(cpu, next->cpu_vm_mask);
/* Re-load page tables: load_cr3(next->pgd) */
- per_cpu(cur_pgd, cpu) = next->pgd;
op->cmd = MMUEXT_NEW_BASEPTR;
op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT);
op++;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/param.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/param.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/param.h Wed Feb
1 18:00:19 2006
@@ -1,9 +1,8 @@
-#include <linux/config.h>
-
#ifndef _ASMi386_PARAM_H
#define _ASMi386_PARAM_H
#ifdef __KERNEL__
+# include <linux/config.h>
# define HZ CONFIG_HZ /* Internal kernel timer frequency */
# define USER_HZ 100 /* .. some user interfaces are in
"ticks" */
# define CLOCKS_PER_SEC (USER_HZ) /* like times() */
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level.h
Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level.h
Wed Feb 1 18:00:19 2006
@@ -76,11 +76,6 @@
#define pfn_pte_ma(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) |
pgprot_val(prot))
#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
-
-#define pmd_page_kernel(pmd) \
-((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-
/*
* All present user pages are user-executable:
*/
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level.h
Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level.h
Wed Feb 1 18:00:19 2006
@@ -103,11 +103,6 @@
*/
static inline void pud_clear (pud_t * pud) { }
-#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
-
-#define pmd_page_kernel(pmd) \
-((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-
#define pud_page(pud) \
((struct page *) __va(pud_val(pud) & PAGE_MASK))
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable.h Wed Feb
1 18:00:19 2006
@@ -25,6 +25,9 @@
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
+
+struct mm_struct;
+struct vm_area_struct;
/*
* ZERO_PAGE is a global shared page that is always zero: used
@@ -204,7 +207,8 @@
#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); }
while (0)
-#define pmd_none(x) (!pmd_val(x))
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x) (!(unsigned long)pmd_val(x))
/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t.
can temporarily clear it. */
#define pmd_present(x) (pmd_val(x))
@@ -326,8 +330,6 @@
return pte;
}
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
#define pmd_large(pmd) \
((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
@@ -371,6 +373,11 @@
(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset_kernel(dir, address) \
((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address))
+
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_page_kernel(pmd) \
+ ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
/*
* Helper function that returns the kernel pagetable entry controlling
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/processor.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/processor.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/processor.h Wed Feb
1 18:00:19 2006
@@ -66,7 +66,9 @@
int f00f_bug;
int coma_bug;
unsigned long loops_per_jiffy;
- unsigned char x86_num_cores;
+ unsigned char x86_max_cores; /* cpuid returned max cores value */
+ unsigned char booted_cores; /* number of cores as seen by OS */
+ unsigned char apicid;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
#define X86_VENDOR_INTEL 0
@@ -89,7 +91,6 @@
extern struct cpuinfo_x86 new_cpu_data;
extern struct tss_struct doublefault_tss;
DECLARE_PER_CPU(struct tss_struct, init_tss);
-DECLARE_PER_CPU(pgd_t *, cur_pgd);
#ifdef CONFIG_SMP
extern struct cpuinfo_x86 cpu_data[];
@@ -724,4 +725,10 @@
#define mtrr_bp_init() do {} while (0)
#endif
+#ifdef CONFIG_X86_MCE
+extern void mcheck_init(struct cpuinfo_x86 *c);
+#else
+#define mcheck_init(c) do {} while(0)
+#endif
+
#endif /* __ASM_I386_PROCESSOR_H */
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/smp.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/smp.h Wed Feb 1
17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/smp.h Wed Feb 1
18:00:19 2006
@@ -45,6 +45,8 @@
#define MAX_APICID 256
extern u8 x86_cpu_to_apicid[];
+#define cpu_physical_id(cpu) x86_cpu_to_apicid[cpu]
+
#ifdef CONFIG_HOTPLUG_CPU
extern void cpu_exit_clear(void);
extern void cpu_uninit(void);
@@ -91,6 +93,10 @@
extern void __cpu_die(unsigned int cpu);
#endif /* !__ASSEMBLY__ */
+#else /* CONFIG_SMP */
+
+#define cpu_physical_id(cpu) boot_cpu_physical_apicid
+
#define NO_PROC_ID 0xFF /* No processor magic marker */
#endif
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/system.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/system.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/system.h Wed Feb
1 18:00:19 2006
@@ -122,21 +122,22 @@
#define write_cr0(x) \
__asm__ __volatile__("movl %0,%%cr0": :"r" (x));
-#define read_cr2() ({ \
- unsigned int __dummy; \
- __asm__ __volatile__( \
- "movl %%cr2,%0\n\t" \
- :"=r" (__dummy)); \
- __dummy; \
-})
+#define read_cr2() \
+ (HYPERVISOR_shared_info->vcpu_info[smp_processor_id()].arch.cr2)
#define write_cr2(x) \
__asm__ __volatile__("movl %0,%%cr2": :"r" (x));
-#define read_cr3() per_cpu(cur_pgd, smp_processor_id())
-#define write_cr3(x) do { \
- xen_pt_switch((x)); \
- per_cpu(cur_pgd, smp_processor_id()) = (x); \
-} while (/* CONSTCOND */0)
+#define read_cr3() ({ \
+ unsigned int __dummy; \
+ __asm__ ( \
+ "movl %%cr3,%0\n\t" \
+ :"=r" (__dummy)); \
+ machine_to_phys(__dummy); \
+})
+#define write_cr3(x) ({ \
+ maddr_t __dummy = phys_to_machine(x); \
+ __asm__ __volatile__("movl %0,%%cr3": :"r" (__dummy)); \
+})
#define read_cr4() ({ \
unsigned int __dummy; \
@@ -147,7 +148,6 @@
})
#define write_cr4(x) \
__asm__ __volatile__("movl %0,%%cr4": :"r" (x));
-
#define stts() (HYPERVISOR_fpu_taskswitch(1))
#endif /* __KERNEL__ */
@@ -172,6 +172,8 @@
struct __xchg_dummy { unsigned long a[100]; };
#define __xg(x) ((struct __xchg_dummy *)(x))
+
+#ifdef CONFIG_X86_CMPXCHG64
/*
* The semantics of XCHGCMP8B are a bit strange, this is why
@@ -226,6 +228,8 @@
(__builtin_constant_p(value) ? \
__set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
__set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+#endif
/*
* Note: no "lock" prefix even on SMP: xchg always implies lock anyway
@@ -265,6 +269,9 @@
#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
#endif
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
@@ -281,22 +288,78 @@
case 2:
__asm__ __volatile__(LOCK "cmpxchgw %w1,%2"
: "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
case 4:
__asm__ __volatile__(LOCK "cmpxchgl %1,%2"
: "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
}
return old;
}
-#define cmpxchg(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
+#ifndef CONFIG_X86_CMPXCHG
+/*
+ * Building a kernel capable running on 80386. It may be necessary to
+ * simulate the cmpxchg on the 80386 CPU. For that purpose we define
+ * a function for each of the sizes we support.
+ */
+
+extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
+extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
+extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
+
+static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ switch (size) {
+ case 1:
+ return cmpxchg_386_u8(ptr, old, new);
+ case 2:
+ return cmpxchg_386_u16(ptr, old, new);
+ case 4:
+ return cmpxchg_386_u32(ptr, old, new);
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ if (likely(boot_cpu_data.x86 > 3)) \
+ __ret = __cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ else \
+ __ret = cmpxchg_386((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ __ret; \
+})
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+
+static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long
long old,
+ unsigned long long new)
+{
+ unsigned long long prev;
+ __asm__ __volatile__(LOCK "cmpxchg8b %3"
+ : "=A"(prev)
+ : "b"((unsigned long)new),
+ "c"((unsigned long)(new >> 32)),
+ "m"(*__xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+}
+
+#define cmpxchg64(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
+ (unsigned long long)(n)))
+
+#endif
#ifdef __KERNEL__
struct alt_instr {
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/rwsem.h
--- a/linux-2.6-xen-sparse/include/asm-i386/rwsem.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/rwsem.h Wed Feb 1 18:00:19 2006
@@ -285,5 +285,10 @@
return tmp+delta;
}
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+ return (sem->count != 0);
+}
+
#endif /* __KERNEL__ */
#endif /* _I386_RWSEM_H */
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-i386/system.h
--- a/linux-2.6-xen-sparse/include/asm-i386/system.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-i386/system.h Wed Feb 1 18:00:19 2006
@@ -167,6 +167,8 @@
#define __xg(x) ((struct __xchg_dummy *)(x))
+#ifdef CONFIG_X86_CMPXCHG64
+
/*
* The semantics of XCHGCMP8B are a bit strange, this is why
* there is a loop and the loading of %%eax and %%edx has to
@@ -220,6 +222,8 @@
(__builtin_constant_p(value) ? \
__set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
__set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+#endif
/*
* Note: no "lock" prefix even on SMP: xchg always implies lock anyway
@@ -259,6 +263,9 @@
#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
#endif
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
@@ -275,22 +282,78 @@
case 2:
__asm__ __volatile__(LOCK "cmpxchgw %w1,%2"
: "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
case 4:
__asm__ __volatile__(LOCK "cmpxchgl %1,%2"
: "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "r"(new), "m"(*__xg(ptr)), "0"(old)
: "memory");
return prev;
}
return old;
}
-#define cmpxchg(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
+#ifndef CONFIG_X86_CMPXCHG
+/*
+ * Building a kernel capable running on 80386. It may be necessary to
+ * simulate the cmpxchg on the 80386 CPU. For that purpose we define
+ * a function for each of the sizes we support.
+ */
+
+extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
+extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
+extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
+
+static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ switch (size) {
+ case 1:
+ return cmpxchg_386_u8(ptr, old, new);
+ case 2:
+ return cmpxchg_386_u16(ptr, old, new);
+ case 4:
+ return cmpxchg_386_u32(ptr, old, new);
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ if (likely(boot_cpu_data.x86 > 3)) \
+ __ret = __cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ else \
+ __ret = cmpxchg_386((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ __ret; \
+})
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+
+static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long
long old,
+ unsigned long long new)
+{
+ unsigned long long prev;
+ __asm__ __volatile__(LOCK "cmpxchg8b %3"
+ : "=A"(prev)
+ : "b"((unsigned long)new),
+ "c"((unsigned long)(new >> 32)),
+ "m"(*__xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+}
+
+#define cmpxchg64(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
+ (unsigned long long)(n)))
+
+#endif
#ifdef __KERNEL__
struct alt_instr {
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/include/asm-um/page.h
--- a/linux-2.6-xen-sparse/include/asm-um/page.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-um/page.h Wed Feb 1 18:00:19 2006
@@ -115,7 +115,7 @@
#define pfn_valid(pfn) ((pfn) < max_mapnr)
#define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v)))
-extern struct page *arch_validate(struct page *page, int mask, int order);
+extern struct page *arch_validate(struct page *page, gfp_t mask, int order);
#define HAVE_ARCH_VALIDATE
extern int arch_free_page(struct page *page, int order);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/desc.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/desc.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/desc.h Wed Feb
1 18:00:19 2006
@@ -114,16 +114,19 @@
static inline void set_intr_gate(int nr, void *func)
{
+ BUG_ON((unsigned)nr > 0xFF);
_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0);
}
static inline void set_intr_gate_ist(int nr, void *func, unsigned ist)
{
+ BUG_ON((unsigned)nr > 0xFF);
_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0,
ist);
}
static inline void set_system_gate(int nr, void *func)
{
+ BUG_ON((unsigned)nr > 0xFF);
_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0);
}
@@ -145,10 +148,16 @@
static inline void set_tss_desc(unsigned cpu, void *addr)
{
+ /*
+ * sizeof(unsigned long) coming from an extra "long" at the end
+ * of the iobitmap. See tss_struct definition in processor.h
+ *
+ * -1? seg base+limit should be pointing to the address of the
+ * last valid byte
+ */
set_tssldt_descriptor((struct ldttss_desc
*)&get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS],
- (unsigned long)addr,
- DESC_TSS,
- sizeof(struct tss_struct) - 1);
+ (unsigned long)addr, DESC_TSS,
+ IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1);
}
static inline void set_ldt_desc(unsigned cpu, void *addr, int size)
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hw_irq.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hw_irq.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hw_irq.h Wed Feb
1 18:00:19 2006
@@ -56,7 +56,7 @@
#define CALL_FUNCTION_VECTOR 0xfc
#define KDB_VECTOR 0xfb /* reserved for KDB */
#define THERMAL_APIC_VECTOR 0xfa
-/* 0xf9 free */
+#define THRESHOLD_APIC_VECTOR 0xf9
#define INVALIDATE_TLB_VECTOR_END 0xf8
#define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f8 used for TLB flush */
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu_context.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu_context.h
Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu_context.h
Wed Feb 1 18:00:19 2006
@@ -60,6 +60,12 @@
extern void mm_unpin(struct mm_struct *mm);
void mm_pin_all(void);
+static inline void load_cr3(pgd_t *pgd)
+{
+ asm volatile("movq %0,%%cr3" :: "r" (phys_to_machine(__pa(pgd))) :
+ "memory");
+}
+
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -79,7 +85,6 @@
set_bit(cpu, &next->cpu_vm_mask);
/* load_cr3(next->pgd) */
- per_cpu(cur_pgd, smp_processor_id()) = next->pgd;
op->cmd = MMUEXT_NEW_BASEPTR;
op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT);
op++;
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/page.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/page.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/page.h Wed Feb
1 18:00:19 2006
@@ -31,7 +31,7 @@
#define PAGE_SIZE (1UL << PAGE_SHIFT)
#endif
#define PAGE_MASK (~(PAGE_SIZE-1))
-#define PHYSICAL_PAGE_MASK (~(PAGE_SIZE-1) & (__PHYSICAL_MASK <<
PAGE_SHIFT))
+#define PHYSICAL_PAGE_MASK (~(PAGE_SIZE-1) & __PHYSICAL_MASK)
#define THREAD_ORDER 1
#ifdef __ASSEMBLY__
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/param.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/param.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/param.h Wed Feb
1 18:00:19 2006
@@ -1,9 +1,8 @@
-#include <linux/config.h>
-
#ifndef _ASMx86_64_PARAM_H
#define _ASMx86_64_PARAM_H
#ifdef __KERNEL__
+# include <linux/config.h>
# define HZ CONFIG_HZ /* Internal kernel timer frequency */
# define USER_HZ 100 /* .. some user interfaces are in
"ticks */
# define CLOCKS_PER_SEC (USER_HZ) /* like times() */
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgtable.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgtable.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgtable.h Wed Feb
1 18:00:19 2006
@@ -39,6 +39,7 @@
extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pgd_t init_level4_pgt[];
+extern pgd_t boot_level4_pgt[];
extern unsigned long __supported_pte_mask;
#define swapper_pg_dir init_level4_pgt
@@ -142,6 +143,8 @@
return pte;
}
#endif
+
+struct mm_struct;
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned
long addr, pte_t *ptep, int full)
{
@@ -405,8 +408,6 @@
* and a page entry and page directory to the page they refer to.
*/
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
/*
* Level 4 access.
* Never use these in the common code.
@@ -450,7 +451,7 @@
#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_PRESENT))
!= (_KERNPG_TABLE & ~_PAGE_PRESENT))
#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
-#define pmd_pfn(x) ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+#define pmd_pfn(x) ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/processor.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/processor.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/processor.h Wed Feb
1 18:00:19 2006
@@ -61,10 +61,12 @@
int x86_cache_alignment;
int x86_tlbsize; /* number of 4K pages in DTLB/ITLB combined(in
pages)*/
__u8 x86_virt_bits, x86_phys_bits;
- __u8 x86_num_cores;
+ __u8 x86_max_cores; /* cpuid returned max cores value */
__u32 x86_power;
__u32 extended_cpuid_level; /* Max extended CPUID function
supported */
unsigned long loops_per_jiffy;
+ __u8 apicid;
+ __u8 booted_cores; /* number of cores as seen by OS */
} ____cacheline_aligned;
#define X86_VENDOR_INTEL 0
@@ -167,11 +169,6 @@
#endif
}
-
-#define load_cr3(pgdir) do { \
- xen_pt_switch(__pa(pgdir)); \
- per_cpu(cur_pgd, smp_processor_id()) = pgdir; \
-} while (/* CONSTCOND */0)
/*
* Bus types
@@ -247,7 +244,6 @@
extern struct cpuinfo_x86 boot_cpu_data;
DECLARE_PER_CPU(struct tss_struct,init_tss);
-DECLARE_PER_CPU(pgd_t *, cur_pgd);
#define ARCH_MIN_TASKALIGN 16
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/smp.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/smp.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/smp.h Wed Feb
1 18:00:19 2006
@@ -46,7 +46,6 @@
extern void unlock_ipi_call_lock(void);
extern int smp_num_siblings;
extern void smp_send_reschedule(int cpu);
-extern void zap_low_mappings(void);
void smp_stop_cpu(void);
extern int smp_call_function_single(int cpuid, void (*func) (void *info),
void *info, int retry, int wait);
@@ -83,6 +82,8 @@
extern int __cpu_disable(void);
extern void __cpu_die(unsigned int cpu);
extern void prefill_possible_map(void);
+extern unsigned num_processors;
+extern unsigned disabled_cpus;
#endif /* !ASSEMBLY */
@@ -139,5 +140,11 @@
#endif
#endif
+#ifdef CONFIG_SMP
+#define cpu_physical_id(cpu) x86_cpu_to_apicid[cpu]
+#else
+#define cpu_physical_id(cpu) boot_cpu_id
#endif
+#endif
+
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/system.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/system.h Wed Feb
1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/system.h Wed Feb
1 18:00:19 2006
@@ -9,6 +9,12 @@
#include <xen/interface/arch-x86_64.h>
#ifdef __KERNEL__
+
+#ifdef CONFIG_SMP
+#define __vcpu_id smp_processor_id()
+#else
+#define __vcpu_id 0
+#endif
#ifdef CONFIG_SMP
#define LOCK_PREFIX "lock ; "
@@ -325,7 +331,7 @@
do { \
vcpu_info_t *_vcpu; \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
_vcpu->evtchn_upcall_mask = 1; \
preempt_enable_no_resched(); \
barrier(); \
@@ -336,7 +342,7 @@
vcpu_info_t *_vcpu; \
barrier(); \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
_vcpu->evtchn_upcall_mask = 0; \
barrier(); /* unmask then check (avoid races) */ \
if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
@@ -348,7 +354,7 @@
do { \
vcpu_info_t *_vcpu; \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
(x) = _vcpu->evtchn_upcall_mask; \
preempt_enable(); \
} while (0)
@@ -358,7 +364,7 @@
vcpu_info_t *_vcpu; \
barrier(); \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \
barrier(); /* unmask then check (avoid races) */ \
if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
@@ -374,7 +380,7 @@
do { \
vcpu_info_t *_vcpu; \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
(x) = _vcpu->evtchn_upcall_mask; \
_vcpu->evtchn_upcall_mask = 1; \
preempt_enable_no_resched(); \
@@ -394,7 +400,7 @@
({ int ___x; \
vcpu_info_t *_vcpu; \
preempt_disable(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_info[__vcpu_id]; \
___x = (_vcpu->evtchn_upcall_mask != 0); \
preempt_enable_no_resched(); \
___x; })
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/include/linux/gfp.h
--- a/linux-2.6-xen-sparse/include/linux/gfp.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/linux/gfp.h Wed Feb 1 18:00:19 2006
@@ -11,9 +11,16 @@
/*
* GFP bitmasks..
*/
-/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low two bits) */
-#define __GFP_DMA 0x01u
-#define __GFP_HIGHMEM 0x02u
+/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low three bits) */
+#define __GFP_DMA ((__force gfp_t)0x01u)
+#define __GFP_HIGHMEM ((__force gfp_t)0x02u)
+#ifdef CONFIG_DMA_IS_DMA32
+#define __GFP_DMA32 ((__force gfp_t)0x01) /* ZONE_DMA is ZONE_DMA32 */
+#elif BITS_PER_LONG < 64
+#define __GFP_DMA32 ((__force gfp_t)0x00) /* ZONE_NORMAL is ZONE_DMA32 */
+#else
+#define __GFP_DMA32 ((__force gfp_t)0x04) /* Has own ZONE_DMA32 */
+#endif
/*
* Action modifiers - doesn't change the zoning
@@ -26,30 +33,29 @@
*
* __GFP_NORETRY: The VM implementation must not retry indefinitely.
*/
-#define __GFP_WAIT 0x10u /* Can wait and reschedule? */
-#define __GFP_HIGH 0x20u /* Should access emergency pools? */
-#define __GFP_IO 0x40u /* Can start physical IO? */
-#define __GFP_FS 0x80u /* Can call down to low-level FS? */
-#define __GFP_COLD 0x100u /* Cache-cold page required */
-#define __GFP_NOWARN 0x200u /* Suppress page allocation failure warning */
-#define __GFP_REPEAT 0x400u /* Retry the allocation. Might fail */
-#define __GFP_NOFAIL 0x800u /* Retry for ever. Cannot fail */
-#define __GFP_NORETRY 0x1000u /* Do not retry. Might fail */
-#define __GFP_NO_GROW 0x2000u /* Slab internal usage */
-#define __GFP_COMP 0x4000u /* Add compound page metadata */
-#define __GFP_ZERO 0x8000u /* Return zeroed page on success */
-#define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */
-#define __GFP_NORECLAIM 0x20000u /* No realy zone reclaim during allocation */
-#define __GFP_HARDWALL 0x40000u /* Enforce hardwall cpuset memory allocs */
+#define __GFP_WAIT ((__force gfp_t)0x10u) /* Can wait and reschedule? */
+#define __GFP_HIGH ((__force gfp_t)0x20u) /* Should access emergency
pools? */
+#define __GFP_IO ((__force gfp_t)0x40u) /* Can start physical IO? */
+#define __GFP_FS ((__force gfp_t)0x80u) /* Can call down to low-level
FS? */
+#define __GFP_COLD ((__force gfp_t)0x100u) /* Cache-cold page required */
+#define __GFP_NOWARN ((__force gfp_t)0x200u) /* Suppress page allocation
failure warning */
+#define __GFP_REPEAT ((__force gfp_t)0x400u) /* Retry the allocation. Might
fail */
+#define __GFP_NOFAIL ((__force gfp_t)0x800u) /* Retry for ever. Cannot fail
*/
+#define __GFP_NORETRY ((__force gfp_t)0x1000u)/* Do not retry. Might fail */
+#define __GFP_NO_GROW ((__force gfp_t)0x2000u)/* Slab internal usage */
+#define __GFP_COMP ((__force gfp_t)0x4000u)/* Add compound page metadata */
+#define __GFP_ZERO ((__force gfp_t)0x8000u)/* Return zeroed page on
success */
+#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency
reserves */
+#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset
memory allocs */
#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
-#define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
+#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/* if you forget to add the bitmask here kernel will crash, period */
#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
__GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
- __GFP_NOMEMALLOC|__GFP_NORECLAIM|__GFP_HARDWALL)
+ __GFP_NOMEMALLOC|__GFP_HARDWALL)
#define GFP_ATOMIC (__GFP_HIGH)
#define GFP_NOIO (__GFP_WAIT)
@@ -64,6 +70,16 @@
#define GFP_DMA __GFP_DMA
+/* 4GB DMA on some platforms */
+#define GFP_DMA32 __GFP_DMA32
+
+
+static inline int gfp_zone(gfp_t gfp)
+{
+ int zone = GFP_ZONEMASK & (__force int) gfp;
+ BUG_ON(zone >= GFP_ZONETYPES);
+ return zone;
+}
/*
* There is only one page-allocator function, and two main namespaces to
@@ -98,7 +114,7 @@
return NULL;
return __alloc_pages(gfp_mask, order,
- NODE_DATA(nid)->node_zonelists + (gfp_mask & GFP_ZONEMASK));
+ NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask));
}
#ifdef CONFIG_NUMA
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/include/linux/irq.h
--- a/linux-2.6-xen-sparse/include/linux/irq.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/linux/irq.h Wed Feb 1 18:00:19 2006
@@ -10,6 +10,7 @@
*/
#include <linux/config.h>
+#include <linux/smp.h>
#if !defined(CONFIG_ARCH_S390)
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/include/linux/mm.h
--- a/linux-2.6-xen-sparse/include/linux/mm.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/linux/mm.h Wed Feb 1 18:00:19 2006
@@ -144,7 +144,8 @@
#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
#define VM_GROWSUP 0x00000200
-#define VM_SHM 0x00000400 /* shared memory area, don't swap out */
+#define VM_SHM 0x00000000 /* Means nothing: delete it later */
+#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct
page", just pure PFN */
#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
#define VM_EXECUTABLE 0x00001000
@@ -157,13 +158,14 @@
#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
-#define VM_RESERVED 0x00080000 /* Don't unmap it from swap_out */
+#define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
#define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu
mmap) */
+#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()"
done on it */
#ifdef CONFIG_XEN
-#define VM_FOREIGN 0x02000000 /* Has pages belonging to another VM */
+#define VM_FOREIGN 0x04000000 /* Has pages belonging to another VM */
#endif
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
@@ -209,12 +211,6 @@
struct mmu_gather;
struct inode;
-#ifdef ARCH_HAS_ATOMIC_UNSIGNED
-typedef unsigned page_flags_t;
-#else
-typedef unsigned long page_flags_t;
-#endif
-
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
@@ -222,20 +218,25 @@
* a page.
*/
struct page {
- page_flags_t flags; /* Atomic flags, some possibly
+ unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
atomic_t _count; /* Usage count, see below. */
atomic_t _mapcount; /* Count of ptes mapped in mms,
* to show when page is mapped
* & limit reverse map searches.
*/
- unsigned long private; /* Mapping-private opaque data:
+ union {
+ unsigned long private; /* Mapping-private opaque data:
* usually used for buffer_heads
* if PagePrivate set; used for
* swp_entry_t if PageSwapCache
* When page is free, this indicates
* order in the buddy system.
*/
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+ spinlock_t ptl;
+#endif
+ } u;
struct address_space *mapping; /* If low bit clear, points to
* inode address_space, or NULL.
* If page mapped as anonymous
@@ -263,6 +264,9 @@
#endif /* WANT_PAGE_VIRTUAL */
};
+#define page_private(page) ((page)->u.private)
+#define set_page_private(page, v) ((page)->u.private = (v))
+
/*
* FIXME: take this include out, include page-flags.h in
* files which need it (119 of them)
@@ -312,40 +316,21 @@
extern void FASTCALL(__page_cache_release(struct page *));
-#ifdef CONFIG_HUGETLB_PAGE
-
-static inline int page_count(struct page *p)
-{
- if (PageCompound(p))
- p = (struct page *)p->private;
- return atomic_read(&(p)->_count) + 1;
+static inline int page_count(struct page *page)
+{
+ if (PageCompound(page))
+ page = (struct page *)page_private(page);
+ return atomic_read(&page->_count) + 1;
}
static inline void get_page(struct page *page)
{
if (unlikely(PageCompound(page)))
- page = (struct page *)page->private;
+ page = (struct page *)page_private(page);
atomic_inc(&page->_count);
}
void put_page(struct page *page);
-
-#else /* CONFIG_HUGETLB_PAGE */
-
-#define page_count(p) (atomic_read(&(p)->_count) + 1)
-
-static inline void get_page(struct page *page)
-{
- atomic_inc(&page->_count);
-}
-
-static inline void put_page(struct page *page)
-{
- if (!PageReserved(page) && put_page_testzero(page))
- __page_cache_release(page);
-}
-
-#endif /* CONFIG_HUGETLB_PAGE */
/*
* Multiple processes may "see" the same page. E.g. for untouched
@@ -430,7 +415,7 @@
#endif
/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
-#define SECTIONS_PGOFF ((sizeof(page_flags_t)*8) - SECTIONS_WIDTH)
+#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
@@ -590,7 +575,7 @@
static inline pgoff_t page_index(struct page *page)
{
if (unlikely(PageSwapCache(page)))
- return page->private;
+ return page_private(page);
return page->index;
}
@@ -683,9 +668,10 @@
unsigned long truncate_count; /* Compare vm_truncate_count */
};
+struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *);
-unsigned long unmap_vmas(struct mmu_gather **tlb, struct mm_struct *mm,
+unsigned long unmap_vmas(struct mmu_gather **tlb,
struct vm_area_struct *start_vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *);
@@ -707,10 +693,6 @@
}
extern int vmtruncate(struct inode * inode, loff_t offset);
-extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned
long address));
-extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned
long address));
-extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd,
unsigned long address));
-extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
unsigned long address));
extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, struct page *page, pgprot_t prot);
extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long pgoff, pgprot_t prot);
extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
unsigned long address, int write_access);
@@ -726,6 +708,7 @@
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned
long start,
int len, int write, int force, struct page **pages, struct
vm_area_struct **vmas);
+void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
int __set_page_dirty_buffers(struct page *page);
int __set_page_dirty_nobuffers(struct page *page);
@@ -750,7 +733,7 @@
* The callback will be passed nr_to_scan == 0 when the VM is querying the
* cache size, so a fastpath for that case is appropriate.
*/
-typedef int (*shrinker_t)(int nr_to_scan, unsigned int gfp_mask);
+typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask);
/*
* Add an aging callback. The int is the number of 'seeks' it takes
@@ -762,38 +745,85 @@
extern struct shrinker *set_shrinker(int, shrinker_t);
extern void remove_shrinker(struct shrinker *shrinker);
-/*
- * On a two-level or three-level page table, this ends up being trivial. Thus
- * the inlining and the symmetry break with pte_alloc_map() that does all
- * of this out-of-line.
- */
+extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long
addr, spinlock_t **ptl));
+
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
+
/*
* The following ifdef needed to get the 4level-fixup.h header to work.
* Remove it when 4level-fixup.h has been removed.
*/
-#ifdef CONFIG_MMU
-#ifndef __ARCH_HAS_4LEVEL_HACK
+#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
{
- if (pgd_none(*pgd))
- return __pud_alloc(mm, pgd, address);
- return pud_offset(pgd, address);
+ return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
+ NULL: pud_offset(pgd, address);
}
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long
address)
{
- if (pud_none(*pud))
- return __pmd_alloc(mm, pud, address);
- return pmd_offset(pud, address);
-}
-#endif
-#endif /* CONFIG_MMU */
+ return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
+ NULL: pmd_offset(pud, address);
+}
+#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
+
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * We tuck a spinlock to guard each pagetable page into its struct page,
+ * at page->private, with BUILD_BUG_ON to make sure that this will not
+ * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
+ * When freeing, reset page->mapping so free_pages_check won't complain.
+ */
+#define __pte_lockptr(page) &((page)->u.ptl)
+#define pte_lock_init(_page) do { \
+ spin_lock_init(__pte_lockptr(_page)); \
+} while (0)
+#define pte_lock_deinit(page) ((page)->mapping = NULL)
+#define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
+#else
+/*
+ * We use mm->page_table_lock to guard all pagetable pages of the mm.
+ */
+#define pte_lock_init(page) do {} while (0)
+#define pte_lock_deinit(page) do {} while (0)
+#define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;})
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define pte_offset_map_lock(mm, pmd, address, ptlp) \
+({ \
+ spinlock_t *__ptl = pte_lockptr(mm, pmd); \
+ pte_t *__pte = pte_offset_map(pmd, address); \
+ *(ptlp) = __ptl; \
+ spin_lock(__ptl); \
+ __pte; \
+})
+
+#define pte_unmap_unlock(pte, ptl) do { \
+ spin_unlock(ptl); \
+ pte_unmap(pte); \
+} while (0)
+
+#define pte_alloc_map(mm, pmd, address) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+ NULL: pte_offset_map(pmd, address))
+
+#define pte_alloc_map_lock(mm, pmd, address, ptlp) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+ NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+
+#define pte_alloc_kernel(pmd, address) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
+ NULL: pte_offset_kernel(pmd, address))
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, pg_data_t *pgdat,
unsigned long * zones_size, unsigned long zone_start_pfn,
unsigned long *zholes_size);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
+extern void setup_per_zone_pages_min(void);
extern void mem_init(void);
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
@@ -837,6 +867,7 @@
extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
struct rb_node **, struct rb_node *);
+extern void unlink_file_vma(struct vm_area_struct *);
extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
unsigned long addr, unsigned long len, pgoff_t pgoff);
extern void exit_mmap(struct mm_struct *);
@@ -884,20 +915,23 @@
* turning readahead off */
int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
- unsigned long offset, unsigned long nr_to_read);
+ pgoff_t offset, unsigned long nr_to_read);
int force_page_cache_readahead(struct address_space *mapping, struct file
*filp,
- unsigned long offset, unsigned long nr_to_read);
-unsigned long page_cache_readahead(struct address_space *mapping,
+ pgoff_t offset, unsigned long nr_to_read);
+unsigned long page_cache_readahead(struct address_space *mapping,
struct file_ra_state *ra,
struct file *filp,
- unsigned long offset,
+ pgoff_t offset,
unsigned long size);
void handle_ra_miss(struct address_space *mapping,
struct file_ra_state *ra, pgoff_t offset);
unsigned long max_sane_readahead(unsigned long nr);
/* Do stack extension */
-extern int expand_stack(struct vm_area_struct * vma, unsigned long address);
+extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
+#ifdef CONFIG_IA64
+extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
+#endif
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long
addr);
@@ -920,15 +954,19 @@
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}
-extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned
long addr);
-
-extern struct page * vmalloc_to_page(void *addr);
-extern unsigned long vmalloc_to_pfn(void *addr);
-extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
- int write);
-extern int check_user_page_readable(struct mm_struct *mm, unsigned long
address);
-int remap_pfn_range(struct vm_area_struct *, unsigned long,
- unsigned long, unsigned long, pgprot_t);
+struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
+struct page *vmalloc_to_page(void *addr);
+unsigned long vmalloc_to_pfn(void *addr);
+int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t);
+int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+
+struct page *follow_page(struct vm_area_struct *, unsigned long address,
+ unsigned int foll_flags);
+#define FOLL_WRITE 0x01 /* check pte is writable */
+#define FOLL_TOUCH 0x02 /* mark page accessed */
+#define FOLL_GET 0x04 /* do get_page on page */
+#define FOLL_ANON 0x08 /* give ZERO_PAGE if no pgtable */
#ifdef CONFIG_XEN
typedef int (*pte_fn_t)(pte_t *pte, struct page *pte_page, unsigned long addr,
@@ -938,28 +976,13 @@
#endif
#ifdef CONFIG_PROC_FS
-void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
+void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
#else
-static inline void __vm_stat_account(struct mm_struct *mm,
+static inline void vm_stat_account(struct mm_struct *mm,
unsigned long flags, struct file *file, long pages)
{
}
#endif /* CONFIG_PROC_FS */
-
-static inline void vm_stat_account(struct vm_area_struct *vma)
-{
- __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
- vma_pages(vma));
-}
-
-static inline void vm_stat_unaccount(struct vm_area_struct *vma)
-{
- __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
- -vma_pages(vma));
-}
-
-/* update per process rss and vm hiwater data */
-extern void update_mem_hiwater(struct task_struct *tsk);
#ifndef CONFIG_DEBUG_PAGEALLOC
static inline void
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/include/linux/skbuff.h
--- a/linux-2.6-xen-sparse/include/linux/skbuff.h Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/include/linux/skbuff.h Wed Feb 1 18:00:19 2006
@@ -137,6 +137,8 @@
unsigned int nr_frags;
unsigned short tso_size;
unsigned short tso_segs;
+ unsigned short ufo_size;
+ unsigned int ip6_frag_id;
struct sk_buff *frag_list;
skb_frag_t frags[MAX_SKB_FRAGS];
};
@@ -171,7 +173,6 @@
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
- * @list: List we are on
* @sk: Socket we are owned by
* @tstamp: Time we arrived
* @dev: Device we arrived on/are leaving by
@@ -192,6 +193,7 @@
* @proto_csum_valid: Protocol csum validated since arriving at localhost
* @proto_csum_blank: Protocol csum must be added before leaving localhost
* @pkt_type: Packet class
+ * @fclone: skbuff clone status
* @ip_summed: Driver fed us an IP checksum
* @priority: Packet queueing priority
* @users: User count - see {datagram,tcp}.c
@@ -204,7 +206,9 @@
* @destructor: Destruct function
* @nfmark: Can be used for communication between hooks
* @nfct: Associated connection, if any
+ * @ipvs_property: skbuff is owned by ipvs
* @nfctinfo: Relationship of this skb to the connection
+ * @nfct_reasm: netfilter conntrack re-assembly pointer
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
@@ -263,13 +267,13 @@
nohdr:1,
nfctinfo:3;
__u8 pkt_type:3,
+ fclone:2,
#ifndef CONFIG_XEN
- fclone:2;
+ ipvs_property:1;
#else
- fclone:2,
+ ipvs_property:1,
proto_csum_valid:1,
proto_csum_blank:1;
- /* 1 bit spare */
#endif
__be16 protocol;
@@ -277,8 +281,8 @@
#ifdef CONFIG_NETFILTER
__u32 nfmark;
struct nf_conntrack *nfct;
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
- __u8 ipvs_property:1;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ struct sk_buff *nfct_reasm;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
@@ -350,6 +354,11 @@
extern void skb_under_panic(struct sk_buff *skb, int len,
void *here);
+extern int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
+ int getfrag(void *from, char *to, int offset,
+ int len,int odd, struct sk_buff *skb),
+ void *from, int length);
+
struct skb_seq_state
{
__u32 lower_offset;
@@ -605,27 +614,44 @@
*/
/**
- * __skb_queue_head - queue a buffer at the list head
+ * __skb_queue_after - queue a buffer at the list head
* @list: list to use
+ * @prev: place after this buffer
* @newsk: buffer to queue
*
- * Queue a buffer at the start of a list. This function takes no locks
+ * Queue a buffer int the middle of a list. This function takes no locks
* and you must therefore hold required locks before calling it.
*
* A buffer cannot be placed on two lists at the same time.
*/
-extern void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
-static inline void __skb_queue_head(struct sk_buff_head *list,
- struct sk_buff *newsk)
-{
- struct sk_buff *prev, *next;
-
+static inline void __skb_queue_after(struct sk_buff_head *list,
+ struct sk_buff *prev,
+ struct sk_buff *newsk)
+{
+ struct sk_buff *next;
list->qlen++;
- prev = (struct sk_buff *)list;
+
next = prev->next;
newsk->next = next;
newsk->prev = prev;
next->prev = prev->next = newsk;
+}
+
+/**
+ * __skb_queue_head - queue a buffer at the list head
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the start of a list. This function takes no locks
+ * and you must therefore hold required locks before calling it.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+extern void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
+static inline void __skb_queue_head(struct sk_buff_head *list,
+ struct sk_buff *newsk)
+{
+ __skb_queue_after(list, (struct sk_buff *)list, newsk);
}
/**
@@ -1205,6 +1231,11 @@
prefetch(skb->next), (skb != (struct sk_buff *)(queue));
\
skb = skb->next)
+#define skb_queue_reverse_walk(queue, skb) \
+ for (skb = (queue)->prev;
\
+ prefetch(skb->prev), (skb != (struct sk_buff *)(queue));
\
+ skb = skb->prev)
+
extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
int noblock, int *err);
@@ -1213,8 +1244,7 @@
extern int skb_copy_datagram_iovec(const struct sk_buff *from,
int offset, struct iovec *to,
int size);
-extern int skb_copy_and_csum_datagram_iovec(const
- struct sk_buff *skb,
+extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
int hlen,
struct iovec *iov);
extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
@@ -1282,6 +1312,30 @@
extern void __net_timestamp(struct sk_buff *skb);
+extern unsigned int __skb_checksum_complete(struct sk_buff *skb);
+
+/**
+ * skb_checksum_complete - Calculate checksum of an entire packet
+ * @skb: packet to process
+ *
+ * This function calculates the checksum over the entire packet plus
+ * the value of skb->csum. The latter can be used to supply the
+ * checksum of a pseudo header as used by TCP/UDP. It returns the
+ * checksum.
+ *
+ * For protocols that contain complete checksums such as ICMP/TCP/UDP,
+ * this function can be used to verify that checksum on received
+ * packets. In that case the function should return zero if the
+ * checksum is correct. In particular, this function will return zero
+ * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the
+ * hardware has already verified the correctness of the checksum.
+ */
+static inline unsigned int skb_checksum_complete(struct sk_buff *skb)
+{
+ return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+ __skb_checksum_complete(skb);
+}
+
#ifdef CONFIG_NETFILTER
static inline void nf_conntrack_put(struct nf_conntrack *nfct)
{
@@ -1293,10 +1347,26 @@
if (nfct)
atomic_inc(&nfct->use);
}
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
+{
+ if (skb)
+ atomic_inc(&skb->users);
+}
+static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
+{
+ if (skb)
+ kfree_skb(skb);
+}
+#endif
static inline void nf_reset(struct sk_buff *skb)
{
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ nf_conntrack_put_reasm(skb->nfct_reasm);
+ skb->nfct_reasm = NULL;
+#endif
}
#ifdef CONFIG_BRIDGE_NETFILTER
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/kernel/irq/manage.c
--- a/linux-2.6-xen-sparse/kernel/irq/manage.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/kernel/irq/manage.c Wed Feb 1 18:00:19 2006
@@ -24,6 +24,7 @@
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ * @irq: interrupt number to wait for
*
* This function waits for any pending IRQ handlers for this interrupt
* to complete before returning. If you use this function while
@@ -34,6 +35,9 @@
void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_desc + irq;
+
+ if (irq >= NR_IRQS)
+ return;
while (desc->status & IRQ_INPROGRESS)
cpu_relax();
@@ -58,6 +62,9 @@
{
irq_desc_t *desc = irq_desc + irq;
unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
spin_lock_irqsave(&desc->lock, flags);
if (!desc->depth++) {
@@ -85,6 +92,9 @@
{
irq_desc_t *desc = irq_desc + irq;
+ if (irq >= NR_IRQS)
+ return;
+
disable_irq_nosync(irq);
if (desc->action)
synchronize_irq(irq);
@@ -106,6 +116,9 @@
{
irq_desc_t *desc = irq_desc + irq;
unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
spin_lock_irqsave(&desc->lock, flags);
switch (desc->depth) {
@@ -166,6 +179,9 @@
struct irqaction *old, **p;
unsigned long flags;
int shared = 0;
+
+ if (irq >= NR_IRQS)
+ return -EINVAL;
if (desc->handler == &no_irq_type)
return -ENOSYS;
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/lib/Kconfig.debug
--- a/linux-2.6-xen-sparse/lib/Kconfig.debug Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/lib/Kconfig.debug Wed Feb 1 18:00:19 2006
@@ -128,7 +128,7 @@
config DEBUG_BUGVERBOSE
bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED
depends on BUG
- depends on ARM || ARM26 || M32R || M68K || SPARC32 || SPARC64 || (X86
&& !X86_64) || FRV
+ depends on ARM || ARM26 || M32R || M68K || SPARC32 || SPARC64 || X86_32
|| FRV
default !EMBEDDED
help
Say Y here to make BUG() panics output the file name and line number
@@ -168,13 +168,34 @@
If unsure, say N.
+config DEBUG_VM
+ bool "Debug VM"
+ depends on DEBUG_KERNEL
+ help
+ Enable this to debug the virtual-memory system.
+
+ If unsure, say N.
+
config FRAME_POINTER
bool "Compile the kernel with frame pointers"
depends on DEBUG_KERNEL && (X86 || CRIS || M68K || M68KNOMMU || FRV ||
UML)
default y if DEBUG_INFO && UML
help
If you say Y here the resulting kernel image will be slightly larger
- and slower, but it might give very useful debugging information
- on some architectures or you use external debuggers.
+ and slower, but it might give very useful debugging information on
+ some architectures or if you use external debuggers.
If you don't debug the kernel, you can say N.
+config RCU_TORTURE_TEST
+ tristate "torture tests for RCU"
+ depends on DEBUG_KERNEL
+ default n
+ help
+ This option provides a kernel module that runs torture tests
+ on the RCU infrastructure. The kernel module may be built
+ after the fact on the running kernel to be tested, if desired.
+
+ Say Y here if you want RCU torture tests to start automatically
+ at boot time (you probably don't).
+ Say M if you want the RCU torture tests to build as a module.
+ Say N if you are unsure.
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/mm/highmem.c
--- a/linux-2.6-xen-sparse/mm/highmem.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/mm/highmem.c Wed Feb 1 18:00:19 2006
@@ -30,11 +30,9 @@
static mempool_t *page_pool, *isa_page_pool;
-static void *page_pool_alloc(gfp_t gfp_mask, void *data)
-{
- unsigned int gfp = gfp_mask | (unsigned int) (long) data;
-
- return alloc_page(gfp);
+static void *page_pool_alloc_isa(gfp_t gfp_mask, void *data)
+{
+ return alloc_page(gfp_mask | GFP_DMA);
}
static void page_pool_free(void *page, void *data)
@@ -51,6 +49,12 @@
* n means that there are (n-1) current users of it.
*/
#ifdef CONFIG_HIGHMEM
+
+static void *page_pool_alloc(gfp_t gfp_mask, void *data)
+{
+ return alloc_page(gfp_mask);
+}
+
static int pkmap_count[LAST_PKMAP];
static unsigned int last_pkmap_nr;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
@@ -278,7 +282,7 @@
if (isa_page_pool)
return 0;
- isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc,
page_pool_free, (void *) __GFP_DMA);
+ isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc_isa,
page_pool_free, NULL);
if (!isa_page_pool)
BUG();
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/mm/memory.c
--- a/linux-2.6-xen-sparse/mm/memory.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/mm/memory.c Wed Feb 1 18:00:19 2006
@@ -114,6 +114,7 @@
{
struct page *page = pmd_page(*pmd);
pmd_clear(pmd);
+ pte_lock_deinit(page);
pte_free_tlb(tlb, page);
dec_page_state(nr_page_table_pages);
tlb->mm->nr_ptes--;
@@ -249,7 +250,7 @@
free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
- if (!tlb_is_full_mm(*tlb))
+ if (!(*tlb)->fullmm)
flush_tlb_pgtables((*tlb)->mm, start, end);
}
@@ -259,6 +260,12 @@
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
+
+ /*
+ * Hide vma from rmap and vmtruncate before freeing pgtables
+ */
+ anon_vma_unlink(vma);
+ unlink_file_vma(vma);
if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
@@ -272,6 +279,8 @@
HPAGE_SIZE)) {
vma = next;
next = vma->vm_next;
+ anon_vma_unlink(vma);
+ unlink_file_vma(vma);
}
free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
@@ -280,75 +289,141 @@
}
}
-pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
- unsigned long address)
-{
- if (!pmd_present(*pmd)) {
- struct page *new;
-
- spin_unlock(&mm->page_table_lock);
- new = pte_alloc_one(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
- return NULL;
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
- if (pmd_present(*pmd)) {
- pte_free(new);
- goto out;
- }
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+ struct page *new = pte_alloc_one(mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ pte_lock_init(new);
+ spin_lock(&mm->page_table_lock);
+ if (pmd_present(*pmd)) { /* Another has populated it */
+ pte_lock_deinit(new);
+ pte_free(new);
+ } else {
mm->nr_ptes++;
inc_page_state(nr_page_table_pages);
pmd_populate(mm, pmd, new);
}
-out:
- return pte_offset_map(pmd, address);
-}
-
-pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned
long address)
-{
- if (!pmd_present(*pmd)) {
- pte_t *new;
-
- spin_unlock(&mm->page_table_lock);
- new = pte_alloc_one_kernel(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
+ spin_unlock(&mm->page_table_lock);
+ return 0;
+}
+
+int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
+{
+ pte_t *new = pte_alloc_one_kernel(&init_mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ spin_lock(&init_mm.page_table_lock);
+ if (pmd_present(*pmd)) /* Another has populated it */
+ pte_free_kernel(new);
+ else
+ pmd_populate_kernel(&init_mm, pmd, new);
+ spin_unlock(&init_mm.page_table_lock);
+ return 0;
+}
+
+static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
+{
+ if (file_rss)
+ add_mm_counter(mm, file_rss, file_rss);
+ if (anon_rss)
+ add_mm_counter(mm, anon_rss, anon_rss);
+}
+
+/*
+ * This function is called to print an error when a bad pte
+ * is found. For example, we might have a PFN-mapped pte in
+ * a region that doesn't allow it.
+ *
+ * The calling function must still handle the error.
+ */
+void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr)
+{
+ printk(KERN_ERR "Bad pte = %08llx, process = %s, "
+ "vm_flags = %lx, vaddr = %lx\n",
+ (long long)pte_val(pte),
+ (vma->vm_mm == current->mm ? current->comm : "???"),
+ vma->vm_flags, vaddr);
+ dump_stack();
+}
+
+static inline int is_cow_mapping(unsigned int flags)
+{
+ return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
+
+/*
+ * This function gets the "struct page" associated with a pte.
+ *
+ * NOTE! Some mappings do not have "struct pages". A raw PFN mapping
+ * will have each page table entry just pointing to a raw page frame
+ * number, and as far as the VM layer is concerned, those do not have
+ * pages associated with them - even if the PFN might point to memory
+ * that otherwise is perfectly fine and has a "struct page".
+ *
+ * The way we recognize those mappings is through the rules set up
+ * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set,
+ * and the vm_pgoff will point to the first PFN mapped: thus every
+ * page that is a raw mapping will always honor the rule
+ *
+ * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
+ *
+ * and if that isn't true, the page has been COW'ed (in which case it
+ * _does_ have a "struct page" associated with it even if it is in a
+ * VM_PFNMAP range).
+ */
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
+
+ if (vma->vm_flags & VM_PFNMAP) {
+ unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT;
+ if (pfn == vma->vm_pgoff + off)
return NULL;
-
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
- if (pmd_present(*pmd)) {
- pte_free_kernel(new);
- goto out;
- }
- pmd_populate_kernel(mm, pmd, new);
- }
-out:
- return pte_offset_kernel(pmd, address);
+ if (!is_cow_mapping(vma->vm_flags))
+ return NULL;
+ }
+
+ /*
+ * Add some anal sanity checks for now. Eventually,
+ * we should just do "return pfn_to_page(pfn)", but
+ * in the meantime we check that we get a valid pfn,
+ * and that the resulting page looks ok.
+ *
+ * Remove this test eventually!
+ */
+ if (unlikely(!pfn_valid(pfn))) {
+ if (!vma->vm_flags & VM_RESERVED)
+ print_bad_pte(vma, pte, addr);
+ return NULL;
+ }
+
+ /*
+ * NOTE! We still have PageReserved() pages in the page
+ * tables.
+ *
+ * The PAGE_ZERO() pages and various VDSO mappings can
+ * cause them to exist.
+ */
+ return pfn_to_page(pfn);
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
- *
- * dst->page_table_lock is held on entry and exit,
- * but may be dropped within p[mg]d_alloc() and pte_alloc_map().
*/
static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
- unsigned long addr)
-{
+ pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
+ unsigned long addr, int *rss)
+{
+ unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
- unsigned long pfn;
/* pte contains position in swap or file, so copy. */
if (unlikely(!pte_present(pte))) {
@@ -357,34 +432,20 @@
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
- list_add(&dst_mm->mmlist, &src_mm->mmlist);
+ if (list_empty(&dst_mm->mmlist))
+ list_add(&dst_mm->mmlist,
+ &src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
}
- set_pte_at(dst_mm, addr, dst_pte, pte);
- return;
- }
-
- pfn = pte_pfn(pte);
- /* the pte points outside of valid memory, the
- * mapping is assumed to be good, meaningful
- * and not mapped via rmap - duplicate the
- * mapping as is.
- */
- page = NULL;
- if (pfn_valid(pfn))
- page = pfn_to_page(pfn);
-
- if (!page || PageReserved(page)) {
- set_pte_at(dst_mm, addr, dst_pte, pte);
- return;
+ goto out_set_pte;
}
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
- if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
+ if (is_cow_mapping(vm_flags)) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = *src_pte;
}
@@ -396,12 +457,16 @@
if (vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
- get_page(page);
- inc_mm_counter(dst_mm, rss);
- if (PageAnon(page))
- inc_mm_counter(dst_mm, anon_rss);
+
+ page = vm_normal_page(vma, addr, pte);
+ if (page) {
+ get_page(page);
+ page_dup_rmap(page);
+ rss[!!PageAnon(page)]++;
+ }
+
+out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
- page_dup_rmap(page);
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -409,38 +474,44 @@
unsigned long addr, unsigned long end)
{
pte_t *src_pte, *dst_pte;
- unsigned long vm_flags = vma->vm_flags;
- int progress;
+ spinlock_t *src_ptl, *dst_ptl;
+ int progress = 0;
+ int rss[2];
again:
- dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
+ rss[1] = rss[0] = 0;
+ dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
return -ENOMEM;
src_pte = pte_offset_map_nested(src_pmd, addr);
-
- progress = 0;
- spin_lock(&src_mm->page_table_lock);
+ src_ptl = pte_lockptr(src_mm, src_pmd);
+ spin_lock(src_ptl);
+
do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
- if (progress >= 32 && (need_resched() ||
- need_lockbreak(&src_mm->page_table_lock) ||
- need_lockbreak(&dst_mm->page_table_lock)))
- break;
+ if (progress >= 32) {
+ progress = 0;
+ if (need_resched() ||
+ need_lockbreak(src_ptl) ||
+ need_lockbreak(dst_ptl))
+ break;
+ }
if (pte_none(*src_pte)) {
progress++;
continue;
}
- copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr);
+ copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
- spin_unlock(&src_mm->page_table_lock);
-
+
+ spin_unlock(src_ptl);
pte_unmap_nested(src_pte - 1);
- pte_unmap(dst_pte - 1);
- cond_resched_lock(&dst_mm->page_table_lock);
+ add_mm_rss(dst_mm, rss[0], rss[1]);
+ pte_unmap_unlock(dst_pte - 1, dst_ptl);
+ cond_resched();
if (addr != end)
goto again;
return 0;
@@ -504,7 +575,7 @@
* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
- if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) {
+ if (!(vma->vm_flags &
(VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) {
if (!vma->anon_vma)
return 0;
}
@@ -525,25 +596,30 @@
return 0;
}
-static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+static unsigned long zap_pte_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
- struct zap_details *details)
-{
+ long *zap_work, struct zap_details *details)
+{
+ struct mm_struct *mm = tlb->mm;
pte_t *pte;
-
- pte = pte_offset_map(pmd, addr);
+ spinlock_t *ptl;
+ int file_rss = 0;
+ int anon_rss = 0;
+
+ pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
do {
pte_t ptent = *pte;
- if (pte_none(ptent))
+ if (pte_none(ptent)) {
+ (*zap_work)--;
continue;
+ }
if (pte_present(ptent)) {
- struct page *page = NULL;
- unsigned long pfn = pte_pfn(ptent);
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (PageReserved(page))
- page = NULL;
- }
+ struct page *page;
+
+ (*zap_work) -= PAGE_SIZE;
+
+ page = vm_normal_page(vma, addr, ptent);
if (unlikely(details) && page) {
/*
* unmap_shared_mapping_pages() wants to
@@ -562,7 +638,7 @@
page->index > details->last_index))
continue;
}
- ptent = ptep_get_and_clear_full(tlb->mm, addr, pte,
+ ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
@@ -570,15 +646,17 @@
if (unlikely(details) && details->nonlinear_vma
&& linear_page_index(details->nonlinear_vma,
addr) != page->index)
- set_pte_at(tlb->mm, addr, pte,
+ set_pte_at(mm, addr, pte,
pgoff_to_pte(page->index));
- if (pte_dirty(ptent))
- set_page_dirty(page);
if (PageAnon(page))
- dec_mm_counter(tlb->mm, anon_rss);
- else if (pte_young(ptent))
- mark_page_accessed(page);
- tlb->freed++;
+ anon_rss--;
+ else {
+ if (pte_dirty(ptent))
+ set_page_dirty(page);
+ if (pte_young(ptent))
+ mark_page_accessed(page);
+ file_rss--;
+ }
page_remove_rmap(page);
tlb_remove_page(tlb, page);
continue;
@@ -591,14 +669,19 @@
continue;
if (!pte_file(ptent))
free_swap_and_cache(pte_to_swp_entry(ptent));
- pte_clear_full(tlb->mm, addr, pte, tlb->fullmm);
- } while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap(pte - 1);
-}
-
-static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+ pte_clear_full(mm, addr, pte, tlb->fullmm);
+ } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
+
+ add_mm_rss(mm, file_rss, anon_rss);
+ pte_unmap_unlock(pte - 1, ptl);
+
+ return addr;
+}
+
+static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
- struct zap_details *details)
+ long *zap_work, struct zap_details *details)
{
pmd_t *pmd;
unsigned long next;
@@ -606,15 +689,21 @@
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
- if (pmd_none_or_clear_bad(pmd))
+ if (pmd_none_or_clear_bad(pmd)) {
+ (*zap_work)--;
continue;
- zap_pte_range(tlb, pmd, addr, next, details);
- } while (pmd++, addr = next, addr != end);
-}
-
-static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+ }
+ next = zap_pte_range(tlb, vma, pmd, addr, next,
+ zap_work, details);
+ } while (pmd++, addr = next, (addr != end && *zap_work > 0));
+
+ return addr;
+}
+
+static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
- struct zap_details *details)
+ long *zap_work, struct zap_details *details)
{
pud_t *pud;
unsigned long next;
@@ -622,15 +711,21 @@
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud))
+ if (pud_none_or_clear_bad(pud)) {
+ (*zap_work)--;
continue;
- zap_pmd_range(tlb, pud, addr, next, details);
- } while (pud++, addr = next, addr != end);
-}
-
-static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct
*vma,
+ }
+ next = zap_pmd_range(tlb, vma, pud, addr, next,
+ zap_work, details);
+ } while (pud++, addr = next, (addr != end && *zap_work > 0));
+
+ return addr;
+}
+
+static unsigned long unmap_page_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
- struct zap_details *details)
+ long *zap_work, struct zap_details *details)
{
pgd_t *pgd;
unsigned long next;
@@ -643,11 +738,16 @@
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
+ if (pgd_none_or_clear_bad(pgd)) {
+ (*zap_work)--;
continue;
- zap_pud_range(tlb, pgd, addr, next, details);
- } while (pgd++, addr = next, addr != end);
+ }
+ next = zap_pud_range(tlb, vma, pgd, addr, next,
+ zap_work, details);
+ } while (pgd++, addr = next, (addr != end && *zap_work > 0));
tlb_end_vma(tlb, vma);
+
+ return addr;
}
#ifdef CONFIG_PREEMPT
@@ -660,7 +760,6 @@
/**
* unmap_vmas - unmap a range of memory covered by a list of vma's
* @tlbp: address of the caller's struct mmu_gather
- * @mm: the controlling mm_struct
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
@@ -669,10 +768,10 @@
*
* Returns the end address of the unmapping (restart addr if interrupted).
*
- * Unmap all pages in the vma list. Called under page_table_lock.
- *
- * We aim to not hold page_table_lock for too long (for scheduling latency
- * reasons). So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to
+ * Unmap all pages in the vma list.
+ *
+ * We aim to not hold locks for too long (for scheduling latency reasons).
+ * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to
* return the ending mmu_gather to the caller.
*
* Only addresses between `start' and `end' will be unmapped.
@@ -684,17 +783,17 @@
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
-unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
+unsigned long unmap_vmas(struct mmu_gather **tlbp,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *details)
{
- unsigned long zap_bytes = ZAP_BLOCK_SIZE;
+ long zap_work = ZAP_BLOCK_SIZE;
unsigned long tlb_start = 0; /* For tlb_finish_mmu */
int tlb_start_valid = 0;
unsigned long start = start_addr;
spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
- int fullmm = tlb_is_full_mm(*tlbp);
+ int fullmm = (*tlbp)->fullmm;
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
unsigned long end;
@@ -710,45 +809,39 @@
*nr_accounted += (end - start) >> PAGE_SHIFT;
while (start != end) {
- unsigned long block;
-
if (!tlb_start_valid) {
tlb_start = start;
tlb_start_valid = 1;
}
- if (is_vm_hugetlb_page(vma)) {
- block = end - start;
+ if (unlikely(is_vm_hugetlb_page(vma))) {
unmap_hugepage_range(vma, start, end);
- } else {
- block = min(zap_bytes, end - start);
- unmap_page_range(*tlbp, vma, start,
- start + block, details);
+ zap_work -= (end - start) /
+ (HPAGE_SIZE / PAGE_SIZE);
+ start = end;
+ } else
+ start = unmap_page_range(*tlbp, vma,
+ start, end, &zap_work, details);
+
+ if (zap_work > 0) {
+ BUG_ON(start != end);
+ break;
}
- start += block;
- zap_bytes -= block;
- if ((long)zap_bytes > 0)
- continue;
-
tlb_finish_mmu(*tlbp, tlb_start, start);
if (need_resched() ||
- need_lockbreak(&mm->page_table_lock) ||
(i_mmap_lock && need_lockbreak(i_mmap_lock))) {
if (i_mmap_lock) {
- /* must reset count of rss freed */
- *tlbp = tlb_gather_mmu(mm, fullmm);
+ *tlbp = NULL;
goto out;
}
- spin_unlock(&mm->page_table_lock);
cond_resched();
- spin_lock(&mm->page_table_lock);
}
- *tlbp = tlb_gather_mmu(mm, fullmm);
+ *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
tlb_start_valid = 0;
- zap_bytes = ZAP_BLOCK_SIZE;
+ zap_work = ZAP_BLOCK_SIZE;
}
}
out:
@@ -770,123 +863,92 @@
unsigned long end = address + size;
unsigned long nr_accounted = 0;
- if (is_vm_hugetlb_page(vma)) {
- zap_hugepage_range(vma, address, size);
- return end;
- }
-
lru_add_drain();
- spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
- end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
- tlb_finish_mmu(tlb, address, end);
- spin_unlock(&mm->page_table_lock);
+ update_hiwater_rss(mm);
+ end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
+ if (tlb)
+ tlb_finish_mmu(tlb, address, end);
return end;
}
/*
* Do a quick page-table lookup for a single page.
- * mm->page_table_lock must be held.
- */
-static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
- int read, int write, int accessed)
+ */
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
+ unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
- unsigned long pfn;
+ spinlock_t *ptl;
struct page *page;
-
- page = follow_huge_addr(mm, address, write);
- if (! IS_ERR(page))
- return page;
-
+ struct mm_struct *mm = vma->vm_mm;
+
+ page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
+ if (!IS_ERR(page)) {
+ BUG_ON(flags & FOLL_GET);
+ goto out;
+ }
+
+ page = NULL;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
- goto out;
+ goto no_page_table;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
- goto out;
+ goto no_page_table;
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+ goto no_page_table;
+
+ if (pmd_huge(*pmd)) {
+ BUG_ON(flags & FOLL_GET);
+ page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
goto out;
- if (pmd_huge(*pmd))
- return follow_huge_pmd(mm, address, pmd, write);
-
- ptep = pte_offset_map(pmd, address);
+ }
+
+ ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!ptep)
goto out;
pte = *ptep;
- pte_unmap(ptep);
- if (pte_present(pte)) {
- if (write && !pte_write(pte))
- goto out;
- if (read && !pte_read(pte))
- goto out;
- pfn = pte_pfn(pte);
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (accessed) {
- if (write && !pte_dirty(pte) &&!PageDirty(page))
- set_page_dirty(page);
- mark_page_accessed(page);
- }
- return page;
- }
- }
-
+ if (!pte_present(pte))
+ goto unlock;
+ if ((flags & FOLL_WRITE) && !pte_write(pte))
+ goto unlock;
+ page = vm_normal_page(vma, address, pte);
+ if (unlikely(!page))
+ goto unlock;
+
+ if (flags & FOLL_GET)
+ get_page(page);
+ if (flags & FOLL_TOUCH) {
+ if ((flags & FOLL_WRITE) &&
+ !pte_dirty(pte) && !PageDirty(page))
+ set_page_dirty(page);
+ mark_page_accessed(page);
+ }
+unlock:
+ pte_unmap_unlock(ptep, ptl);
out:
- return NULL;
-}
-
-inline struct page *
-follow_page(struct mm_struct *mm, unsigned long address, int write)
-{
- return __follow_page(mm, address, 0, write, 1);
-}
-
-/*
- * check_user_page_readable() can be called frm niterrupt context by oprofile,
- * so we need to avoid taking any non-irq-safe locks
- */
-int check_user_page_readable(struct mm_struct *mm, unsigned long address)
-{
- return __follow_page(mm, address, 1, 0, 0) != NULL;
-}
-EXPORT_SYMBOL(check_user_page_readable);
-
-static inline int
-untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
- unsigned long address)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
-
- /* Check if the vma is for an anonymous mapping. */
- if (vma->vm_ops && vma->vm_ops->nopage)
- return 0;
-
- /* Check if page directory entry exists. */
- pgd = pgd_offset(mm, address);
- if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
- return 1;
-
- pud = pud_offset(pgd, address);
- if (pud_none(*pud) || unlikely(pud_bad(*pud)))
- return 1;
-
- /* Check if page middle directory entry exists. */
- pmd = pmd_offset(pud, address);
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- return 1;
-
- /* There is a pte slot for 'address' in 'mm'. */
- return 0;
+ return page;
+
+no_page_table:
+ /*
+ * When core dumping an enormous anonymous area that nobody
+ * has touched so far, we don't want to allocate page tables.
+ */
+ if (flags & FOLL_ANON) {
+ page = ZERO_PAGE(address);
+ if (flags & FOLL_GET)
+ get_page(page);
+ BUG_ON(flags & FOLL_WRITE);
+ }
+ return page;
}
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
@@ -894,18 +956,19 @@
struct page **pages, struct vm_area_struct **vmas)
{
int i;
- unsigned int flags;
+ unsigned int vm_flags;
/*
* Require read or write permissions.
* If 'force' is set, we only require the "MAY" flags.
*/
- flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
- flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
i = 0;
do {
- struct vm_area_struct * vma;
+ struct vm_area_struct *vma;
+ unsigned int foll_flags;
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(tsk, start)) {
@@ -933,8 +996,10 @@
return i ? : -EFAULT;
}
if (pages) {
- pages[i] = pte_page(*pte);
- get_page(pages[i]);
+ struct page *page = vm_normal_page(gate_vma,
start, *pte);
+ pages[i] = page;
+ if (page)
+ get_page(page);
}
pte_unmap(pte);
if (vmas)
@@ -962,8 +1027,8 @@
}
}
#endif
- if (!vma || (vma->vm_flags & VM_IO)
- || !(flags & vma->vm_flags))
+ if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ || !(vm_flags & vma->vm_flags))
return i ? : -EFAULT;
if (is_vm_hugetlb_page(vma)) {
@@ -971,29 +1036,25 @@
&start, &len, i);
continue;
}
- spin_lock(&mm->page_table_lock);
+
+ foll_flags = FOLL_TOUCH;
+ if (pages)
+ foll_flags |= FOLL_GET;
+ if (!write && !(vma->vm_flags & VM_LOCKED) &&
+ (!vma->vm_ops || !vma->vm_ops->nopage))
+ foll_flags |= FOLL_ANON;
+
do {
- int write_access = write;
struct page *page;
- cond_resched_lock(&mm->page_table_lock);
- while (!(page = follow_page(mm, start, write_access))) {
+ if (write)
+ foll_flags |= FOLL_WRITE;
+
+ cond_resched();
+ while (!(page = follow_page(vma, start, foll_flags))) {
int ret;
-
- /*
- * Shortcut for anonymous pages. We don't want
- * to force the creation of pages tables for
- * insanely big anonymously mapped areas that
- * nobody touched so far. This is important
- * for doing a core dump for these mappings.
- */
- if (!write &&
untouched_anonymous_page(mm,vma,start)) {
- page = ZERO_PAGE(start);
- break;
- }
- spin_unlock(&mm->page_table_lock);
- ret = __handle_mm_fault(mm, vma, start,
write_access);
-
+ ret = __handle_mm_fault(mm, vma, start,
+ foll_flags & FOLL_WRITE);
/*
* The VM_FAULT_WRITE bit tells us that
do_wp_page has
* broken COW when necessary, even if
maybe_mkwrite
@@ -1001,7 +1062,7 @@
* subsequent page lookups as if they were
reads.
*/
if (ret & VM_FAULT_WRITE)
- write_access = 0;
+ foll_flags &= ~FOLL_WRITE;
switch (ret & ~VM_FAULT_WRITE) {
case VM_FAULT_MINOR:
@@ -1017,13 +1078,10 @@
default:
BUG();
}
- spin_lock(&mm->page_table_lock);
}
if (pages) {
pages[i] = page;
flush_dcache_page(page);
- if (!PageReserved(page))
- page_cache_get(page);
}
if (vmas)
vmas[i] = vma;
@@ -1031,7 +1089,6 @@
start += PAGE_SIZE;
len--;
} while (len && start < vma->vm_end);
- spin_unlock(&mm->page_table_lock);
} while (len);
return i;
}
@@ -1041,16 +1098,21 @@
unsigned long addr, unsigned long end, pgprot_t prot)
{
pte_t *pte;
-
- pte = pte_alloc_map(mm, pmd, addr);
+ spinlock_t *ptl;
+
+ pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
do {
- pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot));
+ struct page *page = ZERO_PAGE(addr);
+ pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
+ page_cache_get(page);
+ page_add_file_rmap(page);
+ inc_mm_counter(mm, file_rss);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, addr, pte, zero_pte);
} while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap(pte - 1);
+ pte_unmap_unlock(pte - 1, ptl);
return 0;
}
@@ -1100,16 +1162,94 @@
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
- spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
err = zeromap_pud_range(mm, pgd, addr, next, prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
- spin_unlock(&mm->page_table_lock);
return err;
}
+
+pte_t * fastcall get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
+{
+ pgd_t * pgd = pgd_offset(mm, addr);
+ pud_t * pud = pud_alloc(mm, pgd, addr);
+ if (pud) {
+ pmd_t * pmd = pmd_alloc(mm, pud, addr);
+ if (pmd)
+ return pte_alloc_map_lock(mm, pmd, addr, ptl);
+ }
+ return NULL;
+}
+
+/*
+ * This is the old fallback for page remapping.
+ *
+ * For historical reasons, it only allows reserved pages. Only
+ * old drivers should use this, and they needed to mark their
+ * pages reserved for the old functions anyway.
+ */
+static int insert_page(struct mm_struct *mm, unsigned long addr, struct page
*page, pgprot_t prot)
+{
+ int retval;
+ pte_t *pte;
+ spinlock_t *ptl;
+
+ retval = -EINVAL;
+ if (PageAnon(page))
+ goto out;
+ retval = -ENOMEM;
+ flush_dcache_page(page);
+ pte = get_locked_pte(mm, addr, &ptl);
+ if (!pte)
+ goto out;
+ retval = -EBUSY;
+ if (!pte_none(*pte))
+ goto out_unlock;
+
+ /* Ok, finally just insert the thing.. */
+ get_page(page);
+ inc_mm_counter(mm, file_rss);
+ page_add_file_rmap(page);
+ set_pte_at(mm, addr, pte, mk_pte(page, prot));
+
+ retval = 0;
+out_unlock:
+ pte_unmap_unlock(pte, ptl);
+out:
+ return retval;
+}
+
+/*
+ * This allows drivers to insert individual pages they've allocated
+ * into a user vma.
+ *
+ * The page has to be a nice clean _individual_ kernel allocation.
+ * If you allocate a compound page, you need to have marked it as
+ * such (__GFP_COMP), or manually just split the page up yourself
+ * (which is mainly an issue of doing "set_page_count(page, 1)" for
+ * each sub-page, and then freeing them one by one when you free
+ * them rather than freeing it as a compound page).
+ *
+ * NOTE! Traditionally this was done with "remap_pfn_range()" which
+ * took an arbitrary page protection parameter. This doesn't allow
+ * that. Your vma protection will have to be set up correctly, which
+ * means that if you want a shared writable mapping, you'd better
+ * ask for a shared writable mapping!
+ *
+ * The page does not need to be reserved.
+ */
+int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page
*page)
+{
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ return -EFAULT;
+ if (!page_count(page))
+ return -EINVAL;
+ vma->vm_flags |= VM_INSERTPAGE;
+ return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_page);
/*
* maps a range of physical memory into the requested pages. the old
@@ -1121,17 +1261,17 @@
unsigned long pfn, pgprot_t prot)
{
pte_t *pte;
-
- pte = pte_alloc_map(mm, pmd, addr);
+ spinlock_t *ptl;
+
+ pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
- if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
- set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+ set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap(pte - 1);
+ pte_unmap_unlock(pte - 1, ptl);
return 0;
}
@@ -1190,16 +1330,31 @@
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
- * VM_RESERVED tells swapout not to try to touch
- * this region.
+ * VM_RESERVED is specified all over the place, because
+ * in 2.4 it kept swapout's vma scan off this vma; but
+ * in 2.6 the LRU scan won't even find its pages, so this
+ * flag means no more than count its pages in reserved_vm,
+ * and omit it from core dump, even when VM_IO turned off.
+ * VM_PFNMAP tells the core MM that the base pages are just
+ * raw PFN mappings, and do not have a "struct page" associated
+ * with them.
+ *
+ * There's a horrible special case to handle copy-on-write
+ * behaviour that some programs depend on. We mark the "original"
+ * un-COW'ed pages by matching them up with "vma->vm_pgoff".
*/
- vma->vm_flags |= VM_IO | VM_RESERVED;
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (addr != vma->vm_start || end != vma->vm_end)
+ return -EINVAL;
+ vma->vm_pgoff = pfn;
+ }
+
+ vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
- spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
err = remap_pud_range(mm, pgd, addr, next,
@@ -1207,7 +1362,6 @@
if (err)
break;
} while (pgd++, addr = next, addr != end);
- spin_unlock(&mm->page_table_lock);
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
@@ -1224,7 +1378,7 @@
struct page *pte_page;
pte = (mm == &init_mm) ?
- pte_alloc_kernel(mm, pmd, addr) :
+ pte_alloc_kernel(pmd, addr) :
pte_alloc_map(mm, pmd, addr);
if (!pte)
return -ENOMEM;
@@ -1300,17 +1454,40 @@
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
- spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
err = generic_pud_range(mm, pgd, addr, next, fn, data);
if (err)
break;
} while (pgd++, addr = next, addr != end);
- spin_unlock(&mm->page_table_lock);
return err;
}
#endif
+
+/*
+ * handle_pte_fault chooses page fault handler according to an entry
+ * which was read non-atomically. Before making any commitment, on
+ * those architectures or configurations (e.g. i386 with PAE) which
+ * might give a mix of unmatched parts, do_swap_page and do_file_page
+ * must check under lock before unmapping the pte and proceeding
+ * (but do_wp_page is only called after already making such a check;
+ * and do_anonymous_page and do_no_page can safely check later on).
+ */
+static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
+ pte_t *page_table, pte_t orig_pte)
+{
+ int same = 1;
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
+ if (sizeof(pte_t) > sizeof(unsigned long)) {
+ spinlock_t *ptl = pte_lockptr(mm, pmd);
+ spin_lock(ptl);
+ same = pte_same(*page_table, orig_pte);
+ spin_unlock(ptl);
+ }
+#endif
+ pte_unmap(page_table);
+ return same;
+}
/*
* Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when
@@ -1325,28 +1502,37 @@
return pte;
}
-/*
- * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
- */
-static inline void break_cow(struct vm_area_struct * vma, struct page *
new_page, unsigned long address,
- pte_t *page_table)
-{
- pte_t entry;
-
- entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
- vma);
- ptep_establish(vma, address, page_table, entry);
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
+static inline void cow_user_page(struct page *dst, struct page *src, unsigned
long va)
+{
+ /*
+ * If the source page was a PFN mapping, we don't have
+ * a "struct page" for it. We do a best-effort copy by
+ * just copying from the original user address. If that
+ * fails, we just zero-fill it. Live with it.
+ */
+ if (unlikely(!src)) {
+ void *kaddr = kmap_atomic(dst, KM_USER0);
+ void __user *uaddr = (void __user *)(va & PAGE_MASK);
+
+ /*
+ * This really shouldn't fail, because the page is there
+ * in the page tables. But it might just be unreadable,
+ * in which case we just give up and fill the result with
+ * zeroes.
+ */
+ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
+ memset(kaddr, 0, PAGE_SIZE);
+ kunmap_atomic(kaddr, KM_USER0);
+ return;
+
+ }
+ copy_user_highpage(dst, src, va);
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
- *
- * Goto-purists beware: the only reason for goto's here is that it results
- * in better assembly code.. The "default" path will see no jumps at all.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
@@ -1357,105 +1543,76 @@
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
- * We hold the mm semaphore and the page_table_lock on entry and exit
- * with the page_table_lock released.
- */
-static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
- unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), with pte both mapped and locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ spinlock_t *ptl, pte_t orig_pte)
{
struct page *old_page, *new_page;
- unsigned long pfn = pte_pfn(pte);
pte_t entry;
- int ret;
-#ifdef CONFIG_XEN
- struct page invalid_page;
-#endif
-
- if (unlikely(!pfn_valid(pfn))) {
-#ifdef CONFIG_XEN
- /* This can happen with /dev/mem (PROT_WRITE, MAP_PRIVATE). */
- invalid_page.flags = (1<<PG_reserved) | (1<<PG_locked);
- old_page = &invalid_page;
- } else {
- old_page = pfn_to_page(pfn);
-#else
- /*
- * This should really halt the system so it can be debugged or
- * at least the kernel stops what it's doing before it corrupts
- * data, but for the moment just pretend this is OOM.
- */
- pte_unmap(page_table);
- printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
- address);
- spin_unlock(&mm->page_table_lock);
- return VM_FAULT_OOM;
-#endif
- }
-#ifndef CONFIG_XEN
- old_page = pfn_to_page(pfn);
-#endif
+ int ret = VM_FAULT_MINOR;
+
+ old_page = vm_normal_page(vma, address, orig_pte);
+ if (!old_page)
+ goto gotten;
if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
int reuse = can_share_swap_page(old_page);
unlock_page(old_page);
if (reuse) {
- flush_cache_page(vma, address, pfn);
- entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
- vma);
+ flush_cache_page(vma, address, pte_pfn(orig_pte));
+ entry = pte_mkyoung(orig_pte);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
ptep_set_access_flags(vma, address, page_table, entry,
1);
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
- return VM_FAULT_MINOR|VM_FAULT_WRITE;
+ ret |= VM_FAULT_WRITE;
+ goto unlock;
}
}
- pte_unmap(page_table);
/*
* Ok, we need to copy. Oh, well..
*/
- if (!PageReserved(old_page))
- page_cache_get(old_page);
- spin_unlock(&mm->page_table_lock);
+ page_cache_get(old_page);
+gotten:
+ pte_unmap_unlock(page_table, ptl);
if (unlikely(anon_vma_prepare(vma)))
- goto no_new_page;
+ goto oom;
if (old_page == ZERO_PAGE(address)) {
new_page = alloc_zeroed_user_highpage(vma, address);
if (!new_page)
- goto no_new_page;
+ goto oom;
} else {
new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
if (!new_page)
- goto no_new_page;
-#ifndef CONFIG_XEN
- copy_user_highpage(new_page, old_page, address);
-#else
- if (old_page == &invalid_page) {
- char *vto = kmap_atomic(new_page, KM_USER1);
- copy_page(vto, (void *)(address & PAGE_MASK));
- kunmap_atomic(vto, KM_USER1);
- } else {
- copy_user_highpage(new_page, old_page, address);
- }
-#endif
- }
+ goto oom;
+ cow_user_page(new_page, old_page, address);
+ }
+
/*
* Re-check the pte - we dropped the lock
*/
- ret = VM_FAULT_MINOR;
- spin_lock(&mm->page_table_lock);
- page_table = pte_offset_map(pmd, address);
- if (likely(pte_same(*page_table, pte))) {
- if (PageAnon(old_page))
- dec_mm_counter(mm, anon_rss);
- if (PageReserved(old_page))
- inc_mm_counter(mm, rss);
- else
+ page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (likely(pte_same(*page_table, orig_pte))) {
+ if (old_page) {
page_remove_rmap(old_page);
- flush_cache_page(vma, address, pfn);
- break_cow(vma, new_page, address, page_table);
+ if (!PageAnon(old_page)) {
+ dec_mm_counter(mm, file_rss);
+ inc_mm_counter(mm, anon_rss);
+ }
+ } else
+ inc_mm_counter(mm, anon_rss);
+ flush_cache_page(vma, address, pte_pfn(orig_pte));
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ ptep_establish(vma, address, page_table, entry);
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
@@ -1463,14 +1620,16 @@
new_page = old_page;
ret |= VM_FAULT_WRITE;
}
- pte_unmap(page_table);
- page_cache_release(new_page);
- page_cache_release(old_page);
- spin_unlock(&mm->page_table_lock);
+ if (new_page)
+ page_cache_release(new_page);
+ if (old_page)
+ page_cache_release(old_page);
+unlock:
+ pte_unmap_unlock(page_table, ptl);
return ret;
-
-no_new_page:
- page_cache_release(old_page);
+oom:
+ if (old_page)
+ page_cache_release(old_page);
return VM_FAULT_OOM;
}
@@ -1539,13 +1698,6 @@
restart_addr = zap_page_range(vma, start_addr,
end_addr - start_addr, details);
-
- /*
- * We cannot rely on the break test in unmap_vmas:
- * on the one hand, we don't want to restart our loop
- * just because that broke out for the page_table_lock;
- * on the other hand, it does no test when vma is small.
- */
need_break = need_resched() ||
need_lockbreak(details->i_mmap_lock);
@@ -1794,38 +1946,37 @@
}
/*
- * We hold the mm semaphore and the page_table_lock on entry and
- * should release the pagetable lock on exit..
- */
-static int do_swap_page(struct mm_struct * mm,
- struct vm_area_struct * vma, unsigned long address,
- pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
-{
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access, pte_t orig_pte)
+{
+ spinlock_t *ptl;
struct page *page;
- swp_entry_t entry = pte_to_swp_entry(orig_pte);
+ swp_entry_t entry;
pte_t pte;
int ret = VM_FAULT_MINOR;
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
+ if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
+ goto out;
+
+ entry = pte_to_swp_entry(orig_pte);
page = lookup_swap_cache(entry);
if (!page) {
swapin_readahead(entry, address, vma);
page = read_swap_cache_async(entry, vma, address);
if (!page) {
/*
- * Back out if somebody else faulted in this pte while
- * we released the page table lock.
+ * Back out if somebody else faulted in this pte
+ * while we released the pte lock.
*/
- spin_lock(&mm->page_table_lock);
- page_table = pte_offset_map(pmd, address);
+ page_table = pte_offset_map_lock(mm, pmd, address,
&ptl);
if (likely(pte_same(*page_table, orig_pte)))
ret = VM_FAULT_OOM;
- else
- ret = VM_FAULT_MINOR;
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
- goto out;
+ goto unlock;
}
/* Had to read the page from swap area: Major fault */
@@ -1838,15 +1989,11 @@
lock_page(page);
/*
- * Back out if somebody else faulted in this pte while we
- * released the page table lock.
+ * Back out if somebody else already faulted in this pte.
*/
- spin_lock(&mm->page_table_lock);
- page_table = pte_offset_map(pmd, address);
- if (unlikely(!pte_same(*page_table, orig_pte))) {
- ret = VM_FAULT_MINOR;
+ page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (unlikely(!pte_same(*page_table, orig_pte)))
goto out_nomap;
- }
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
@@ -1855,7 +2002,7 @@
/* The page isn't present yet, go ahead with the fault. */
- inc_mm_counter(mm, rss);
+ inc_mm_counter(mm, anon_rss);
pte = mk_pte(page, vma->vm_page_prot);
if (write_access && can_share_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
@@ -1873,7 +2020,7 @@
if (write_access) {
if (do_wp_page(mm, vma, address,
- page_table, pmd, pte) == VM_FAULT_OOM)
+ page_table, pmd, ptl, pte) == VM_FAULT_OOM)
ret = VM_FAULT_OOM;
goto out;
}
@@ -1881,74 +2028,76 @@
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
lazy_mmu_prot_update(pte);
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
+unlock:
+ pte_unmap_unlock(page_table, ptl);
out:
return ret;
out_nomap:
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
+ pte_unmap_unlock(page_table, ptl);
unlock_page(page);
page_cache_release(page);
- goto out;
-}
-
-/*
- * We are called with the MM semaphore and page_table_lock
- * spinlock held to protect against concurrent faults in
- * multithreaded programs.
- */
-static int
-do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
- pte_t *page_table, pmd_t *pmd, int write_access,
- unsigned long addr)
-{
+ return ret;
+}
+
+/*
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access)
+{
+ struct page *page;
+ spinlock_t *ptl;
pte_t entry;
- struct page * page = ZERO_PAGE(addr);
-
- /* Read-only mapping of ZERO_PAGE. */
- entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
-
- /* ..except if it's a write access */
+
if (write_access) {
/* Allocate our own private page. */
pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
if (unlikely(anon_vma_prepare(vma)))
- goto no_mem;
- page = alloc_zeroed_user_highpage(vma, addr);
+ goto oom;
+ page = alloc_zeroed_user_highpage(vma, address);
if (!page)
- goto no_mem;
-
- spin_lock(&mm->page_table_lock);
- page_table = pte_offset_map(pmd, addr);
-
- if (!pte_none(*page_table)) {
- pte_unmap(page_table);
- page_cache_release(page);
- spin_unlock(&mm->page_table_lock);
- goto out;
- }
- inc_mm_counter(mm, rss);
- entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
- vma->vm_page_prot)),
- vma);
+ goto oom;
+
+ entry = mk_pte(page, vma->vm_page_prot);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+
+ page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (!pte_none(*page_table))
+ goto release;
+ inc_mm_counter(mm, anon_rss);
lru_cache_add_active(page);
SetPageReferenced(page);
- page_add_anon_rmap(page, vma, addr);
- }
-
- set_pte_at(mm, addr, page_table, entry);
- pte_unmap(page_table);
+ page_add_anon_rmap(page, vma, address);
+ } else {
+ /* Map the ZERO_PAGE - vm_page_prot is readonly */
+ page = ZERO_PAGE(address);
+ page_cache_get(page);
+ entry = mk_pte(page, vma->vm_page_prot);
+
+ ptl = pte_lockptr(mm, pmd);
+ spin_lock(ptl);
+ if (!pte_none(*page_table))
+ goto release;
+ inc_mm_counter(mm, file_rss);
+ page_add_file_rmap(page);
+ }
+
+ set_pte_at(mm, address, page_table, entry);
/* No need to invalidate - it was non-present before */
- update_mmu_cache(vma, addr, entry);
+ update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
- spin_unlock(&mm->page_table_lock);
-out:
+unlock:
+ pte_unmap_unlock(page_table, ptl);
return VM_FAULT_MINOR;
-no_mem:
+release:
+ page_cache_release(page);
+ goto unlock;
+oom:
return VM_FAULT_OOM;
}
@@ -1961,25 +2110,24 @@
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
- * This is called with the MM semaphore held and the page table
- * spinlock held. Exit with the spinlock released.
- */
-static int
-do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
-{
- struct page * new_page;
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access)
+{
+ spinlock_t *ptl;
+ struct page *new_page;
struct address_space *mapping = NULL;
pte_t entry;
unsigned int sequence = 0;
int ret = VM_FAULT_MINOR;
int anon = 0;
- if (!vma->vm_ops || !vma->vm_ops->nopage)
- return do_anonymous_page(mm, vma, page_table,
- pmd, write_access, address);
pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
+ BUG_ON(vma->vm_flags & VM_PFNMAP);
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
@@ -1987,7 +2135,6 @@
smp_rmb(); /* serializes i_size against truncate_count */
}
retry:
- cond_resched();
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
/*
* No smp_rmb is needed here as long as there's a full
@@ -2020,19 +2167,20 @@
anon = 1;
}
- spin_lock(&mm->page_table_lock);
+ page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
/*
* For a file-backed vma, someone could have truncated or otherwise
* invalidated this page. If unmap_mapping_range got called,
* retry getting the page.
*/
if (mapping && unlikely(sequence != mapping->truncate_count)) {
+ pte_unmap_unlock(page_table, ptl);
+ page_cache_release(new_page);
+ cond_resched();
sequence = mapping->truncate_count;
- spin_unlock(&mm->page_table_lock);
- page_cache_release(new_page);
+ smp_rmb();
goto retry;
}
- page_table = pte_offset_map(pmd, address);
/*
* This silly early PAGE_DIRTY setting removes a race
@@ -2046,68 +2194,67 @@
*/
/* Only go through if we didn't race with anybody else... */
if (pte_none(*page_table)) {
- if (!PageReserved(new_page))
- inc_mm_counter(mm, rss);
-
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
set_pte_at(mm, address, page_table, entry);
if (anon) {
+ inc_mm_counter(mm, anon_rss);
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
- } else
+ } else {
+ inc_mm_counter(mm, file_rss);
page_add_file_rmap(new_page);
- pte_unmap(page_table);
+ }
} else {
/* One of our sibling threads was faster, back out. */
- pte_unmap(page_table);
page_cache_release(new_page);
- spin_unlock(&mm->page_table_lock);
- goto out;
+ goto unlock;
}
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
- spin_unlock(&mm->page_table_lock);
-out:
+unlock:
+ pte_unmap_unlock(page_table, ptl);
return ret;
oom:
page_cache_release(new_page);
- ret = VM_FAULT_OOM;
- goto out;
+ return VM_FAULT_OOM;
}
/*
* Fault of a previously existing named mapping. Repopulate the pte
* from the encoded file_pte if possible. This enables swappable
* nonlinear vmas.
- */
-static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
- unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
-{
- unsigned long pgoff;
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access, pte_t orig_pte)
+{
+ pgoff_t pgoff;
int err;
- BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
- /*
- * Fall back to the linear mapping if the fs does not support
- * ->populate:
- */
- if (!vma->vm_ops->populate ||
- (write_access && !(vma->vm_flags & VM_SHARED))) {
- pte_clear(mm, address, pte);
- return do_no_page(mm, vma, address, write_access, pte, pmd);
- }
-
- pgoff = pte_to_pgoff(*pte);
-
- pte_unmap(pte);
- spin_unlock(&mm->page_table_lock);
-
- err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
vma->vm_page_prot, pgoff, 0);
+ if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
+ return VM_FAULT_MINOR;
+
+ if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
+ /*
+ * Page table corrupted: show pte and kill process.
+ */
+ print_bad_pte(vma, orig_pte, address);
+ return VM_FAULT_OOM;
+ }
+ /* We can then assume vm->vm_ops && vma->vm_ops->populate */
+
+ pgoff = pte_to_pgoff(orig_pte);
+ err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
+ vma->vm_page_prot, pgoff, 0);
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err)
@@ -2124,56 +2271,68 @@
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
- * Note the "page_table_lock". It is to protect against kswapd removing
- * pages from under us. Note that kswapd only ever _removes_ pages, never
- * adds them. As such, once we have noticed that the page is not present,
- * we can drop the lock early.
- *
- * The adding of pages is protected by the MM semaphore (which we hold),
- * so we don't need to worry about a page being suddenly been added into
- * our VM.
- *
- * We enter with the pagetable spinlock held, we are supposed to
- * release it when done.
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
*/
static inline int handle_pte_fault(struct mm_struct *mm,
- struct vm_area_struct * vma, unsigned long address,
- int write_access, pte_t *pte, pmd_t *pmd)
+ struct vm_area_struct *vma, unsigned long address,
+ pte_t *pte, pmd_t *pmd, int write_access)
{
pte_t entry;
-
- entry = *pte;
+ pte_t old_entry;
+ spinlock_t *ptl;
+
+ old_entry = entry = *pte;
if (!pte_present(entry)) {
- /*
- * If it truly wasn't present, we know that kswapd
- * and the PTE updates will not touch it later. So
- * drop the lock.
- */
- if (pte_none(entry))
- return do_no_page(mm, vma, address, write_access, pte,
pmd);
+ if (pte_none(entry)) {
+ if (!vma->vm_ops || !vma->vm_ops->nopage)
+ return do_anonymous_page(mm, vma, address,
+ pte, pmd, write_access);
+ return do_no_page(mm, vma, address,
+ pte, pmd, write_access);
+ }
if (pte_file(entry))
- return do_file_page(mm, vma, address, write_access,
pte, pmd);
- return do_swap_page(mm, vma, address, pte, pmd, entry,
write_access);
- }
-
+ return do_file_page(mm, vma, address,
+ pte, pmd, write_access, entry);
+ return do_swap_page(mm, vma, address,
+ pte, pmd, write_access, entry);
+ }
+
+ ptl = pte_lockptr(mm, pmd);
+ spin_lock(ptl);
+ if (unlikely(!pte_same(*pte, entry)))
+ goto unlock;
if (write_access) {
if (!pte_write(entry))
- return do_wp_page(mm, vma, address, pte, pmd, entry);
+ return do_wp_page(mm, vma, address,
+ pte, pmd, ptl, entry);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- ptep_set_access_flags(vma, address, pte, entry, write_access);
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
- pte_unmap(pte);
- spin_unlock(&mm->page_table_lock);
+ if (!pte_same(old_entry, entry)) {
+ ptep_set_access_flags(vma, address, pte, entry, write_access);
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
+ } else {
+ /*
+ * This is needed only for protection faults but the arch code
+ * is not yet telling us if this is a protection fault or not.
+ * This still avoids useless tlb flushes for .text page faults
+ * with threads.
+ */
+ if (write_access)
+ flush_tlb_page(vma, address);
+ }
+unlock:
+ pte_unmap_unlock(pte, ptl);
return VM_FAULT_MINOR;
}
/*
* By the time we get here, we already hold the mm semaphore
*/
-int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, int write_access)
{
pgd_t *pgd;
@@ -2188,100 +2347,78 @@
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, write_access);
- /*
- * We need the page table lock to synchronize with kswapd
- * and the SMP-safe atomic PTE updates.
- */
pgd = pgd_offset(mm, address);
- spin_lock(&mm->page_table_lock);
-
pud = pud_alloc(mm, pgd, address);
if (!pud)
- goto oom;
-
+ return VM_FAULT_OOM;
pmd = pmd_alloc(mm, pud, address);
if (!pmd)
- goto oom;
-
+ return VM_FAULT_OOM;
pte = pte_alloc_map(mm, pmd, address);
if (!pte)
- goto oom;
-
- return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
-
- oom:
+ return VM_FAULT_OOM;
+
+ return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+}
+
+#ifndef __PAGETABLE_PUD_FOLDED
+/*
+ * Allocate page upper directory.
+ * We've already handled the fast-path in-line.
+ */
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ pud_t *new = pud_alloc_one(mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ spin_lock(&mm->page_table_lock);
+ if (pgd_present(*pgd)) /* Another has populated it */
+ pud_free(new);
+ else
+ pgd_populate(mm, pgd, new);
spin_unlock(&mm->page_table_lock);
- return VM_FAULT_OOM;
-}
-
-#ifndef __PAGETABLE_PUD_FOLDED
-/*
- * Allocate page upper directory.
- *
- * We've already handled the fast-path in-line, and we own the
- * page table lock.
- */
-pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
-{
- pud_t *new;
-
+ return 0;
+}
+#else
+/* Workaround for gcc 2.96 */
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ return 0;
+}
+#endif /* __PAGETABLE_PUD_FOLDED */
+
+#ifndef __PAGETABLE_PMD_FOLDED
+/*
+ * Allocate page middle directory.
+ * We've already handled the fast-path in-line.
+ */
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
+{
+ pmd_t *new = pmd_alloc_one(mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ spin_lock(&mm->page_table_lock);
+#ifndef __ARCH_HAS_4LEVEL_HACK
+ if (pud_present(*pud)) /* Another has populated it */
+ pmd_free(new);
+ else
+ pud_populate(mm, pud, new);
+#else
+ if (pgd_present(*pud)) /* Another has populated it */
+ pmd_free(new);
+ else
+ pgd_populate(mm, pud, new);
+#endif /* __ARCH_HAS_4LEVEL_HACK */
spin_unlock(&mm->page_table_lock);
- new = pud_alloc_one(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
- return NULL;
-
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
- if (pgd_present(*pgd)) {
- pud_free(new);
- goto out;
- }
- pgd_populate(mm, pgd, new);
- out:
- return pud_offset(pgd, address);
-}
-#endif /* __PAGETABLE_PUD_FOLDED */
-
-#ifndef __PAGETABLE_PMD_FOLDED
-/*
- * Allocate page middle directory.
- *
- * We've already handled the fast-path in-line, and we own the
- * page table lock.
- */
-pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long
address)
-{
- pmd_t *new;
-
- spin_unlock(&mm->page_table_lock);
- new = pmd_alloc_one(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
- return NULL;
-
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
-#ifndef __ARCH_HAS_4LEVEL_HACK
- if (pud_present(*pud)) {
- pmd_free(new);
- goto out;
- }
- pud_populate(mm, pud, new);
+ return 0;
+}
#else
- if (pgd_present(*pud)) {
- pmd_free(new);
- goto out;
- }
- pgd_populate(mm, pud, new);
-#endif /* __ARCH_HAS_4LEVEL_HACK */
-
- out:
- return pmd_offset(pud, address);
+/* Workaround for gcc 2.96 */
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
+{
+ return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */
@@ -2346,22 +2483,6 @@
EXPORT_SYMBOL(vmalloc_to_pfn);
-/*
- * update_mem_hiwater
- * - update per process rss and vm high water data
- */
-void update_mem_hiwater(struct task_struct *tsk)
-{
- if (tsk->mm) {
- unsigned long rss = get_mm_counter(tsk->mm, rss);
-
- if (tsk->mm->hiwater_rss < rss)
- tsk->mm->hiwater_rss = rss;
- if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
- tsk->mm->hiwater_vm = tsk->mm->total_vm;
- }
-}
-
#if !defined(__HAVE_ARCH_GATE_AREA)
#if defined(AT_SYSINFO_EHDR)
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/mm/mmap.c
--- a/linux-2.6-xen-sparse/mm/mmap.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/mm/mmap.c Wed Feb 1 18:00:19 2006
@@ -155,10 +155,6 @@
return -ENOMEM;
}
-EXPORT_SYMBOL(sysctl_overcommit_memory);
-EXPORT_SYMBOL(sysctl_overcommit_ratio);
-EXPORT_SYMBOL(sysctl_max_map_count);
-EXPORT_SYMBOL(vm_committed_space);
EXPORT_SYMBOL(__vm_enough_memory);
/*
@@ -181,26 +177,36 @@
}
/*
- * Remove one vm structure and free it.
- */
-static void remove_vm_struct(struct vm_area_struct *vma)
+ * Unlink a file-based vm structure from its prio_tree, to hide
+ * vma from rmap and vmtruncate before freeing its page tables.
+ */
+void unlink_file_vma(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
- might_sleep();
if (file) {
struct address_space *mapping = file->f_mapping;
spin_lock(&mapping->i_mmap_lock);
__remove_shared_vm_struct(vma, file, mapping);
spin_unlock(&mapping->i_mmap_lock);
}
+}
+
+/*
+ * Close a vm structure and free it, returning the next.
+ */
+static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+{
+ struct vm_area_struct *next = vma->vm_next;
+
+ might_sleep();
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
- if (file)
- fput(file);
- anon_vma_unlink(vma);
+ if (vma->vm_file)
+ fput(vma->vm_file);
mpol_free(vma_policy(vma));
kmem_cache_free(vm_area_cachep, vma);
+ return next;
}
asmlinkage unsigned long sys_brk(unsigned long brk)
@@ -605,7 +611,7 @@
* If the vma has a ->close operation then the driver probably needs to release
* per-vma resources, so we don't attempt to merge those.
*/
-#define VM_SPECIAL (VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_RESERVED)
+#define VM_SPECIAL (VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_RESERVED |
VM_PFNMAP)
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags)
@@ -832,7 +838,7 @@
}
#ifdef CONFIG_PROC_FS
-void __vm_stat_account(struct mm_struct *mm, unsigned long flags,
+void vm_stat_account(struct mm_struct *mm, unsigned long flags,
struct file *file, long pages)
{
const unsigned long stack_flags
@@ -1110,7 +1116,7 @@
}
out:
mm->total_vm += len >> PAGE_SHIFT;
- __vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
+ vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
mm->locked_vm += len >> PAGE_SHIFT;
make_pages_present(addr, addr + len);
@@ -1475,15 +1481,19 @@
mm->total_vm += grow;
if (vma->vm_flags & VM_LOCKED)
mm->locked_vm += grow;
- __vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
+ vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
return 0;
}
-#ifdef CONFIG_STACK_GROWSUP
-/*
- * vma is the first one with address > vma->vm_end. Have to extend vma.
- */
-int expand_stack(struct vm_area_struct * vma, unsigned long address)
+#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
+/*
+ * PA-RISC uses this for its stack; IA64 for its Register Backing Store.
+ * vma is the last one with address > vma->vm_end. Have to extend vma.
+ */
+#ifndef CONFIG_IA64
+static inline
+#endif
+int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
int error;
@@ -1520,6 +1530,13 @@
}
anon_vma_unlock(vma);
return error;
+}
+#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
+
+#ifdef CONFIG_STACK_GROWSUP
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+ return expand_upwards(vma, address);
}
struct vm_area_struct *
@@ -1603,36 +1620,24 @@
}
#endif
-/* Normal function to fix up a mapping
- * This function is the default for when an area has no specific
- * function. This may be used as part of a more specific routine.
+/*
+ * Ok - we have the memory areas we should free on the vma list,
+ * so release them, and do the vma updates.
*
- * By the time this function is called, the area struct has been
- * removed from the process mapping list.
- */
-static void unmap_vma(struct mm_struct *mm, struct vm_area_struct *area)
-{
- size_t len = area->vm_end - area->vm_start;
-
- area->vm_mm->total_vm -= len >> PAGE_SHIFT;
- if (area->vm_flags & VM_LOCKED)
- area->vm_mm->locked_vm -= len >> PAGE_SHIFT;
- vm_stat_unaccount(area);
- remove_vm_struct(area);
-}
-
-/*
- * Update the VMA and inode share lists.
- *
- * Ok - we have the memory areas we should free on the 'free' list,
- * so release them, and do the vma updates.
- */
-static void unmap_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
-{
+ * Called with the mm semaphore held.
+ */
+static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ /* Update high watermark before we lower total_vm */
+ update_hiwater_vm(mm);
do {
- struct vm_area_struct *next = vma->vm_next;
- unmap_vma(mm, vma);
- vma = next;
+ long nrpages = vma_pages(vma);
+
+ mm->total_vm -= nrpages;
+ if (vma->vm_flags & VM_LOCKED)
+ mm->locked_vm -= nrpages;
+ vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
+ vma = remove_vma(vma);
} while (vma);
validate_mm(mm);
}
@@ -1651,14 +1656,13 @@
unsigned long nr_accounted = 0;
lru_add_drain();
- spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
- unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
+ update_hiwater_rss(mm);
+ unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
next? next->vm_start: 0);
tlb_finish_mmu(tlb, start, end);
- spin_unlock(&mm->page_table_lock);
}
/*
@@ -1799,7 +1803,7 @@
unmap_region(mm, vma, prev, start, end);
/* Fix up all other VM information */
- unmap_vma_list(mm, vma);
+ remove_vma_list(mm, vma);
return 0;
}
@@ -1821,7 +1825,7 @@
static inline void verify_mm_writelocked(struct mm_struct *mm)
{
-#ifdef CONFIG_DEBUG_KERNEL
+#ifdef CONFIG_DEBUG_VM
if (unlikely(down_read_trylock(&mm->mmap_sem))) {
WARN_ON(1);
up_read(&mm->mmap_sem);
@@ -1937,34 +1941,21 @@
#endif
lru_add_drain();
-
- spin_lock(&mm->page_table_lock);
-
flush_cache_mm(mm);
tlb = tlb_gather_mmu(mm, 1);
+ /* Don't update_hiwater_rss(mm) here, do_exit already did */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
- end = unmap_vmas(&tlb, mm, vma, 0, -1, &nr_accounted, NULL);
+ end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(tlb, 0, end);
- mm->mmap = mm->mmap_cache = NULL;
- mm->mm_rb = RB_ROOT;
- set_mm_counter(mm, rss, 0);
- mm->total_vm = 0;
- mm->locked_vm = 0;
-
- spin_unlock(&mm->page_table_lock);
-
- /*
- * Walk the list again, actually closing and freeing it
- * without holding any MM locks.
- */
- while (vma) {
- struct vm_area_struct *next = vma->vm_next;
- remove_vm_struct(vma);
- vma = next;
- }
+ /*
+ * Walk the list again, actually closing and freeing it,
+ * with preemption enabled, without holding any MM locks.
+ */
+ while (vma)
+ vma = remove_vma(vma);
BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
}
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/mm/page_alloc.c
--- a/linux-2.6-xen-sparse/mm/page_alloc.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/mm/page_alloc.c Wed Feb 1 18:00:19 2006
@@ -33,6 +33,7 @@
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
+#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
@@ -59,11 +60,13 @@
* NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
* HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
* HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
- */
-int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 32 };
+ *
+ * TBD: should special case ZONE_DMA32 machines here - in those we normally
+ * don't need any ZONE_NORMAL reservation
+ */
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 256, 32 };
EXPORT_SYMBOL(totalram_pages);
-EXPORT_SYMBOL(nr_swap_pages);
/*
* Used by page_zone() to look up the address of the struct zone whose
@@ -72,27 +75,50 @@
struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
EXPORT_SYMBOL(zone_table);
-static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
+static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem"
};
int min_free_kbytes = 1024;
unsigned long __initdata nr_kernel_pages;
unsigned long __initdata nr_all_pages;
-/*
- * Temporary debugging check for pages not lying within a given zone.
- */
-static int bad_range(struct zone *zone, struct page *page)
-{
- if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages)
- return 1;
- if (page_to_pfn(page) < zone->zone_start_pfn)
- return 1;
+static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
+{
+ int ret = 0;
+ unsigned seq;
+ unsigned long pfn = page_to_pfn(page);
+
+ do {
+ seq = zone_span_seqbegin(zone);
+ if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
+ ret = 1;
+ else if (pfn < zone->zone_start_pfn)
+ ret = 1;
+ } while (zone_span_seqretry(zone, seq));
+
+ return ret;
+}
+
+static int page_is_consistent(struct zone *zone, struct page *page)
+{
#ifdef CONFIG_HOLES_IN_ZONE
if (!pfn_valid(page_to_pfn(page)))
- return 1;
+ return 0;
#endif
if (zone != page_zone(page))
+ return 0;
+
+ return 1;
+}
+/*
+ * Temporary debugging check for pages not lying within a given zone.
+ */
+static int bad_range(struct zone *zone, struct page *page)
+{
+ if (page_outside_zone_boundaries(zone, page))
return 1;
+ if (!page_is_consistent(zone, page))
+ return 1;
+
return 0;
}
@@ -101,7 +127,7 @@
printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n",
function, current->comm, page);
printk(KERN_EMERG "flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
- (int)(2*sizeof(page_flags_t)), (unsigned long)page->flags,
+ (int)(2*sizeof(unsigned long)), (unsigned long)page->flags,
page->mapping, page_mapcount(page), page_count(page));
printk(KERN_EMERG "Backtrace:\n");
dump_stack();
@@ -114,17 +140,13 @@
1 << PG_reclaim |
1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback);
+ 1 << PG_writeback );
set_page_count(page, 0);
reset_page_mapcount(page);
page->mapping = NULL;
add_taint(TAINT_BAD_PAGE);
}
-#ifndef CONFIG_HUGETLB_PAGE
-#define prep_compound_page(page, order) do { } while (0)
-#define destroy_compound_page(page, order) do { } while (0)
-#else
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
@@ -153,7 +175,7 @@
struct page *p = page + i;
SetPageCompound(p);
- p->private = (unsigned long)page;
+ set_page_private(p, (unsigned long)page);
}
}
@@ -173,12 +195,11 @@
if (!PageCompound(p))
bad_page(__FUNCTION__, page);
- if (p->private != (unsigned long)page)
+ if (page_private(p) != (unsigned long)page)
bad_page(__FUNCTION__, page);
ClearPageCompound(p);
}
}
-#endif /* CONFIG_HUGETLB_PAGE */
/*
* function for dealing with page's order in buddy system.
@@ -186,18 +207,18 @@
* So, we don't need atomic page->flags operations here.
*/
static inline unsigned long page_order(struct page *page) {
- return page->private;
+ return page_private(page);
}
static inline void set_page_order(struct page *page, int order) {
- page->private = order;
+ set_page_private(page, order);
__SetPagePrivate(page);
}
static inline void rmv_page_order(struct page *page)
{
__ClearPagePrivate(page);
- page->private = 0;
+ set_page_private(page, 0);
}
/*
@@ -237,14 +258,13 @@
* (a) the buddy is free &&
* (b) the buddy is on the buddy system &&
* (c) a page and its buddy have the same order.
- * for recording page's order, we use page->private and PG_private.
+ * for recording page's order, we use page_private(page) and PG_private.
*
*/
static inline int page_is_buddy(struct page *page, int order)
{
if (PagePrivate(page) &&
(page_order(page) == order) &&
- !PageReserved(page) &&
page_count(page) == 0)
return 1;
return 0;
@@ -264,7 +284,7 @@
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
* free pages of length of (1 << order) and marked with PG_Private.Page's
- * order is recorded in page->private field.
+ * order is recorded in page_private(page) field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
@@ -314,7 +334,7 @@
zone->free_area[order].nr_free++;
}
-static inline void free_pages_check(const char *function, struct page *page)
+static inline int free_pages_check(const char *function, struct page *page)
{
if ( page_mapcount(page) ||
page->mapping != NULL ||
@@ -327,10 +347,17 @@
1 << PG_reclaim |
1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback )))
+ 1 << PG_writeback |
+ 1 << PG_reserved )))
bad_page(function, page);
if (PageDirty(page))
__ClearPageDirty(page);
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not free the page. But we shall soon need
+ * to do more, for when the ZERO_PAGE count wraps negative.
+ */
+ return PageReserved(page);
}
/*
@@ -370,11 +397,10 @@
{
LIST_HEAD(list);
int i;
+ int reserved = 0;
if (arch_free_page(page, order))
return;
-
- mod_page_state(pgfree, 1 << order);
#ifndef CONFIG_MMU
if (order > 0)
@@ -383,8 +409,12 @@
#endif
for (i = 0 ; i < (1 << order) ; ++i)
- free_pages_check(__FUNCTION__, page + i);
+ reserved += free_pages_check(__FUNCTION__, page + i);
+ if (reserved)
+ return;
+
list_add(&page->lru, &list);
+ mod_page_state(pgfree, 1 << order);
kernel_map_pages(page, 1<<order, 0);
free_pages_bulk(page_zone(page), 1, &list, order);
}
@@ -442,7 +472,7 @@
/*
* This page is about to be returned from the page allocator
*/
-static void prep_new_page(struct page *page, int order)
+static int prep_new_page(struct page *page, int order)
{
if ( page_mapcount(page) ||
page->mapping != NULL ||
@@ -456,15 +486,24 @@
1 << PG_reclaim |
1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback )))
+ 1 << PG_writeback |
+ 1 << PG_reserved )))
bad_page(__FUNCTION__, page);
+
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not allocate the page: as a safety net.
+ */
+ if (PageReserved(page))
+ return 1;
page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
1 << PG_referenced | 1 << PG_arch_1 |
1 << PG_checked | 1 << PG_mappedtodisk);
- page->private = 0;
+ set_page_private(page, 0);
set_page_refs(page, order);
kernel_map_pages(page, 1 << order, 1);
+ return 0;
}
/*
@@ -648,11 +687,14 @@
if (arch_free_page(page, 0))
return;
- kernel_map_pages(page, 1, 0);
- inc_page_state(pgfree);
if (PageAnon(page))
page->mapping = NULL;
- free_pages_check(__FUNCTION__, page);
+ if (free_pages_check(__FUNCTION__, page))
+ return;
+
+ inc_page_state(pgfree);
+ kernel_map_pages(page, 1, 0);
+
pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
local_irq_save(flags);
list_add(&page->lru, &pcp->list);
@@ -691,12 +733,14 @@
buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
{
unsigned long flags;
- struct page *page = NULL;
+ struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
+again:
if (order == 0) {
struct per_cpu_pages *pcp;
+ page = NULL;
pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
local_irq_save(flags);
if (pcp->count <= pcp->low)
@@ -709,9 +753,7 @@
}
local_irq_restore(flags);
put_cpu();
- }
-
- if (page == NULL) {
+ } else {
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order);
spin_unlock_irqrestore(&zone->lock, flags);
@@ -720,7 +762,8 @@
if (page != NULL) {
BUG_ON(bad_range(zone, page));
mod_page_state_zone(zone, pgalloc, 1 << order);
- prep_new_page(page, order);
+ if (prep_new_page(page, order))
+ goto again;
if (gfp_flags & __GFP_ZERO)
prep_zero_page(page, order, gfp_flags);
@@ -731,20 +774,28 @@
return page;
}
+#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
+#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
+#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
+#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
+#define ALLOC_HARDER 0x10 /* try to alloc harder */
+#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+
/*
* Return 1 if free pages are above 'mark'. This takes into account the order
* of the allocation.
*/
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int can_try_harder, int gfp_high)
+ int classzone_idx, int alloc_flags)
{
/* free_pages my go negative - that's OK */
long min = mark, free_pages = z->free_pages - (1 << order) + 1;
int o;
- if (gfp_high)
+ if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- if (can_try_harder)
+ if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
if (free_pages <= min + z->lowmem_reserve[classzone_idx])
@@ -762,123 +813,127 @@
return 1;
}
-static inline int
-should_reclaim_zone(struct zone *z, gfp_t gfp_mask)
-{
- if (!z->reclaim_pages)
- return 0;
- if (gfp_mask & __GFP_NORECLAIM)
- return 0;
- return 1;
-}
-
-/*
- * This is the 'heart' of the zoned buddy allocator.
- */
-struct page * fastcall
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist)
-{
- const int wait = gfp_mask & __GFP_WAIT;
- struct zone **zones, *z;
- struct page *page;
- struct reclaim_state reclaim_state;
- struct task_struct *p = current;
- int i;
- int classzone_idx;
- int do_retry;
- int can_try_harder;
- int did_some_progress;
-
- might_sleep_if(wait);
-
- /*
- * The caller may dip into page reserves a bit more if the caller
- * cannot run direct reclaim, or is the caller has realtime scheduling
- * policy
- */
- can_try_harder = (unlikely(rt_task(p)) && !in_interrupt()) || !wait;
-
- zones = zonelist->zones; /* the list of zones suitable for gfp_mask */
-
- if (unlikely(zones[0] == NULL)) {
- /* Should this ever happen?? */
- return NULL;
- }
-
- classzone_idx = zone_idx(zones[0]);
-
-restart:
+/*
+ * get_page_from_freeliest goes through the zonelist trying to allocate
+ * a page.
+ */
+static struct page *
+get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, int alloc_flags)
+{
+ struct zone **z = zonelist->zones;
+ struct page *page = NULL;
+ int classzone_idx = zone_idx(*z);
+
/*
* Go through the zonelist once, looking for a zone with enough free.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- for (i = 0; (z = zones[i]) != NULL; i++) {
- int do_reclaim = should_reclaim_zone(z, gfp_mask);
-
- if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
+ do {
+ if ((alloc_flags & ALLOC_CPUSET) &&
+ !cpuset_zone_allowed(*z, gfp_mask))
continue;
- /*
- * If the zone is to attempt early page reclaim then this loop
- * will try to reclaim pages and check the watermark a second
- * time before giving up and falling back to the next zone.
- */
-zone_reclaim_retry:
- if (!zone_watermark_ok(z, order, z->pages_low,
- classzone_idx, 0, 0)) {
- if (!do_reclaim)
+ if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
+ unsigned long mark;
+ if (alloc_flags & ALLOC_WMARK_MIN)
+ mark = (*z)->pages_min;
+ else if (alloc_flags & ALLOC_WMARK_LOW)
+ mark = (*z)->pages_low;
+ else
+ mark = (*z)->pages_high;
+ if (!zone_watermark_ok(*z, order, mark,
+ classzone_idx, alloc_flags))
continue;
- else {
- zone_reclaim(z, gfp_mask, order);
- /* Only try reclaim once */
- do_reclaim = 0;
- goto zone_reclaim_retry;
- }
}
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
- }
-
- for (i = 0; (z = zones[i]) != NULL; i++)
- wakeup_kswapd(z, order);
+ page = buffered_rmqueue(*z, order, gfp_mask);
+ if (page) {
+ zone_statistics(zonelist, *z);
+ break;
+ }
+ } while (*(++z) != NULL);
+ return page;
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page * fastcall
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist)
+{
+ const gfp_t wait = gfp_mask & __GFP_WAIT;
+ struct zone **z;
+ struct page *page;
+ struct reclaim_state reclaim_state;
+ struct task_struct *p = current;
+ int do_retry;
+ int alloc_flags;
+ int did_some_progress;
+
+ might_sleep_if(wait);
+
+restart:
+ z = zonelist->zones; /* the list of zones suitable for gfp_mask */
+
+ if (unlikely(*z == NULL)) {
+ /* Should this ever happen?? */
+ return NULL;
+ }
+
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ if (page)
+ goto got_pg;
+
+ do {
+ wakeup_kswapd(*z, order);
+ } while (*(++z));
+
+ /*
+ * OK, we're below the kswapd watermark and have kicked background
+ * reclaim. Now things get more complex, so set up alloc_flags according
+ * to how we want to proceed.
+ *
+ * The caller may dip into page reserves a bit more if the caller
+ * cannot run direct reclaim, or if the caller has realtime scheduling
+ * policy.
+ */
+ alloc_flags = ALLOC_WMARK_MIN;
+ if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
+ alloc_flags |= ALLOC_HARDER;
+ if (gfp_mask & __GFP_HIGH)
+ alloc_flags |= ALLOC_HIGH;
+ if (wait)
+ alloc_flags |= ALLOC_CPUSET;
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
- * coming from realtime tasks to go deeper into reserves
+ * coming from realtime tasks go deeper into reserves.
*
* This is the last chance, in general, before the goto nopage.
* Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- for (i = 0; (z = zones[i]) != NULL; i++) {
- if (!zone_watermark_ok(z, order, z->pages_min,
- classzone_idx, can_try_harder,
- gfp_mask & __GFP_HIGH))
- continue;
-
- if (wait && !cpuset_zone_allowed(z, gfp_mask))
- continue;
-
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
- }
+ page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+ if (page)
+ goto got_pg;
/* This allocation should allow future memory freeing. */
if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
&& !in_interrupt()) {
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
- for (i = 0; (z = zones[i]) != NULL; i++) {
- if (!cpuset_zone_allowed(z, gfp_mask))
- continue;
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
+ page = get_page_from_freelist(gfp_mask, order,
+ zonelist, ALLOC_NO_WATERMARKS|ALLOC_CPUSET);
+ if (page)
+ goto got_pg;
+ if (gfp_mask & __GFP_NOFAIL) {
+ blk_congestion_wait(WRITE, HZ/50);
+ goto nofail_alloc;
}
}
goto nopage;
@@ -896,7 +951,7 @@
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- did_some_progress = try_to_free_pages(zones, gfp_mask);
+ did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
@@ -904,19 +959,10 @@
cond_resched();
if (likely(did_some_progress)) {
- for (i = 0; (z = zones[i]) != NULL; i++) {
- if (!zone_watermark_ok(z, order, z->pages_min,
- classzone_idx, can_try_harder,
- gfp_mask & __GFP_HIGH))
- continue;
-
- if (!cpuset_zone_allowed(z, gfp_mask))
- continue;
-
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
- }
+ page = get_page_from_freelist(gfp_mask, order,
+ zonelist, alloc_flags);
+ if (page)
+ goto got_pg;
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
/*
* Go through the zonelist yet one more time, keep
@@ -924,18 +970,10 @@
* a parallel oom killing, we must fail if we're still
* under heavy pressure.
*/
- for (i = 0; (z = zones[i]) != NULL; i++) {
- if (!zone_watermark_ok(z, order, z->pages_high,
- classzone_idx, 0, 0))
- continue;
-
- if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
- continue;
-
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
- }
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+ if (page)
+ goto got_pg;
out_of_memory(gfp_mask, order);
goto restart;
@@ -968,9 +1006,7 @@
dump_stack();
show_mem();
}
- return NULL;
got_pg:
- zone_statistics(zonelist, z);
return page;
}
@@ -998,7 +1034,7 @@
* get_zeroed_page() returns a 32-bit address, which cannot represent
* a highmem page
*/
- BUG_ON(gfp_mask & __GFP_HIGHMEM);
+ BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
if (page)
@@ -1018,7 +1054,7 @@
fastcall void __free_pages(struct page *page, unsigned int order)
{
- if (!PageReserved(page) && put_page_testzero(page)) {
+ if (put_page_testzero(page)) {
if (order == 0)
free_hot_page(page);
else
@@ -1091,7 +1127,7 @@
*/
unsigned int nr_free_buffer_pages(void)
{
- return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK);
+ return nr_free_zone_pages(gfp_zone(GFP_USER));
}
/*
@@ -1099,7 +1135,7 @@
*/
unsigned int nr_free_pagecache_pages(void)
{
- return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK);
+ return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
}
#ifdef CONFIG_HIGHMEM
@@ -1307,11 +1343,8 @@
} else
printk("\n");
- for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+ for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
-
- if (!cpu_possible(cpu))
- continue;
pageset = zone_pcp(zone, cpu);
@@ -1421,6 +1454,10 @@
zone = pgdat->node_zones + ZONE_NORMAL;
if (zone->present_pages)
zonelist->zones[j++] = zone;
+ case ZONE_DMA32:
+ zone = pgdat->node_zones + ZONE_DMA32;
+ if (zone->present_pages)
+ zonelist->zones[j++] = zone;
case ZONE_DMA:
zone = pgdat->node_zones + ZONE_DMA;
if (zone->present_pages)
@@ -1428,6 +1465,18 @@
}
return j;
+}
+
+static inline int highest_zone(int zone_bits)
+{
+ int res = ZONE_NORMAL;
+ if (zone_bits & (__force int)__GFP_HIGHMEM)
+ res = ZONE_HIGHMEM;
+ if (zone_bits & (__force int)__GFP_DMA32)
+ res = ZONE_DMA32;
+ if (zone_bits & (__force int)__GFP_DMA)
+ res = ZONE_DMA;
+ return res;
}
#ifdef CONFIG_NUMA
@@ -1526,11 +1575,7 @@
zonelist = pgdat->node_zonelists + i;
for (j = 0; zonelist->zones[j] != NULL; j++);
- k = ZONE_NORMAL;
- if (i & __GFP_HIGHMEM)
- k = ZONE_HIGHMEM;
- if (i & __GFP_DMA)
- k = ZONE_DMA;
+ k = highest_zone(i);
j = build_zonelists_node(NODE_DATA(node), zonelist, j,
k);
zonelist->zones[j] = NULL;
@@ -1551,12 +1596,7 @@
zonelist = pgdat->node_zonelists + i;
j = 0;
- k = ZONE_NORMAL;
- if (i & __GFP_HIGHMEM)
- k = ZONE_HIGHMEM;
- if (i & __GFP_DMA)
- k = ZONE_DMA;
-
+ k = highest_zone(i);
j = build_zonelists_node(pgdat, zonelist, j, k);
/*
* Now we build the zonelist so that it contains the zones
@@ -1661,7 +1701,7 @@
* up by free_all_bootmem() once the early boot process is
* done. Non-atomic initialization, single-pass.
*/
-void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+void __devinit memmap_init_zone(unsigned long size, int nid, unsigned long
zone,
unsigned long start_pfn)
{
struct page *page;
@@ -1675,7 +1715,7 @@
continue;
page = pfn_to_page(pfn);
set_page_links(page, zone, nid, pfn);
- set_page_count(page, 0);
+ set_page_count(page, 1);
reset_page_mapcount(page);
SetPageReserved(page);
INIT_LIST_HEAD(&page->lru);
@@ -1722,14 +1762,13 @@
/*
* The per-cpu-pages pools are set to around 1000th of the
- * size of the zone. But no more than 1/4 of a meg - there's
- * no point in going beyond the size of L2 cache.
+ * size of the zone. But no more than 1/2 of a meg.
*
* OK, so we don't know how big the cache is. So guess.
*/
batch = zone->present_pages / 1024;
- if (batch * PAGE_SIZE > 256 * 1024)
- batch = (256 * 1024) / PAGE_SIZE;
+ if (batch * PAGE_SIZE > 512 * 1024)
+ batch = (512 * 1024) / PAGE_SIZE;
batch /= 4; /* We effectively *= 4 below */
if (batch < 1)
batch = 1;
@@ -1744,7 +1783,8 @@
* of pages of one half of the possible page colors
* and the other with pages of the other colors.
*/
- batch = (1 << fls(batch + batch/2)) - 1;
+ batch = (1 << (fls(batch + batch/2)-1)) - 1;
+
return batch;
}
@@ -1756,7 +1796,7 @@
pcp = &p->pcp[0]; /* hot */
pcp->count = 0;
- pcp->low = 2 * batch;
+ pcp->low = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
INIT_LIST_HEAD(&pcp->list);
@@ -1765,7 +1805,7 @@
pcp->count = 0;
pcp->low = 0;
pcp->high = 2 * batch;
- pcp->batch = max(1UL, 1 * batch);
+ pcp->batch = max(1UL, batch/2);
INIT_LIST_HEAD(&pcp->list);
}
@@ -1845,11 +1885,10 @@
if (process_zones(cpu))
ret = NOTIFY_BAD;
break;
-#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_UP_CANCELED:
case CPU_DEAD:
free_zone_pagesets(cpu);
break;
-#endif
default:
break;
}
@@ -1859,7 +1898,7 @@
static struct notifier_block pageset_notifier =
{ &pageset_cpuup_callback, NULL, 0 };
-void __init setup_per_cpu_pageset()
+void __init setup_per_cpu_pageset(void)
{
int err;
@@ -1874,6 +1913,60 @@
#endif
+static __devinit
+void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
+{
+ int i;
+ struct pglist_data *pgdat = zone->zone_pgdat;
+
+ /*
+ * The per-page waitqueue mechanism uses hashed waitqueues
+ * per zone.
+ */
+ zone->wait_table_size = wait_table_size(zone_size_pages);
+ zone->wait_table_bits = wait_table_bits(zone->wait_table_size);
+ zone->wait_table = (wait_queue_head_t *)
+ alloc_bootmem_node(pgdat, zone->wait_table_size
+ * sizeof(wait_queue_head_t));
+
+ for(i = 0; i < zone->wait_table_size; ++i)
+ init_waitqueue_head(zone->wait_table + i);
+}
+
+static __devinit void zone_pcp_init(struct zone *zone)
+{
+ int cpu;
+ unsigned long batch = zone_batchsize(zone);
+
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+#ifdef CONFIG_NUMA
+ /* Early boot. Slab allocator not functional yet */
+ zone->pageset[cpu] = &boot_pageset[cpu];
+ setup_pageset(&boot_pageset[cpu],0);
+#else
+ setup_pageset(zone_pcp(zone,cpu), batch);
+#endif
+ }
+ printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
+ zone->name, zone->present_pages, batch);
+}
+
+static __devinit void init_currently_empty_zone(struct zone *zone,
+ unsigned long zone_start_pfn, unsigned long size)
+{
+ struct pglist_data *pgdat = zone->zone_pgdat;
+
+ zone_wait_table_init(zone, size);
+ pgdat->nr_zones = zone_idx(zone) + 1;
+
+ zone->zone_mem_map = pfn_to_page(zone_start_pfn);
+ zone->zone_start_pfn = zone_start_pfn;
+
+ memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
+
+ zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+}
+
/*
* Set up the zone data structures:
* - mark all pages reserved
@@ -1883,10 +1976,11 @@
static void __init free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
- unsigned long i, j;
- int cpu, nid = pgdat->node_id;
+ unsigned long j;
+ int nid = pgdat->node_id;
unsigned long zone_start_pfn = pgdat->node_start_pfn;
+ pgdat_resize_init(pgdat);
pgdat->nr_zones = 0;
init_waitqueue_head(&pgdat->kswapd_wait);
pgdat->kswapd_max_order = 0;
@@ -1894,13 +1988,12 @@
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize;
- unsigned long batch;
realsize = size = zones_size[j];
if (zholes_size)
realsize -= zholes_size[j];
- if (j == ZONE_DMA || j == ZONE_NORMAL)
+ if (j < ZONE_HIGHMEM)
nr_kernel_pages += realsize;
nr_all_pages += realsize;
@@ -1909,24 +2002,13 @@
zone->name = zone_names[j];
spin_lock_init(&zone->lock);
spin_lock_init(&zone->lru_lock);
+ zone_seqlock_init(zone);
zone->zone_pgdat = pgdat;
zone->free_pages = 0;
zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
- batch = zone_batchsize(zone);
-
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
-#ifdef CONFIG_NUMA
- /* Early boot. Slab allocator not functional yet */
- zone->pageset[cpu] = &boot_pageset[cpu];
- setup_pageset(&boot_pageset[cpu],0);
-#else
- setup_pageset(zone_pcp(zone,cpu), batch);
-#endif
- }
- printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
- zone_names[j], realsize, batch);
+ zone_pcp_init(zone);
INIT_LIST_HEAD(&zone->active_list);
INIT_LIST_HEAD(&zone->inactive_list);
zone->nr_scan_active = 0;
@@ -1937,32 +2019,9 @@
if (!size)
continue;
- /*
- * The per-page waitqueue mechanism uses hashed waitqueues
- * per zone.
- */
- zone->wait_table_size = wait_table_size(size);
- zone->wait_table_bits =
- wait_table_bits(zone->wait_table_size);
- zone->wait_table = (wait_queue_head_t *)
- alloc_bootmem_node(pgdat, zone->wait_table_size
- * sizeof(wait_queue_head_t));
-
- for(i = 0; i < zone->wait_table_size; ++i)
- init_waitqueue_head(zone->wait_table + i);
-
- pgdat->nr_zones = j+1;
-
- zone->zone_mem_map = pfn_to_page(zone_start_pfn);
- zone->zone_start_pfn = zone_start_pfn;
-
- memmap_init(size, nid, j, zone_start_pfn);
-
zonetable_add(zone, nid, j, zone_start_pfn, size);
-
+ init_currently_empty_zone(zone, zone_start_pfn, size);
zone_start_pfn += size;
-
- zone_init_free_lists(pgdat, zone, zone->spanned_pages);
}
}
@@ -2362,7 +2421,7 @@
* that the pages_{min,low,high} values for each zone are set correctly
* with respect to min_free_kbytes.
*/
-static void setup_per_zone_pages_min(void)
+void setup_per_zone_pages_min(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
@@ -2376,13 +2435,18 @@
}
for_each_zone(zone) {
+ unsigned long tmp;
spin_lock_irqsave(&zone->lru_lock, flags);
+ tmp = (pages_min * zone->present_pages) / lowmem_pages;
if (is_highmem(zone)) {
/*
- * Often, highmem doesn't need to reserve any pages.
- * But the pages_min/low/high values are also used for
- * batching up page reclaim activity so we need a
- * decent value here.
+ * __GFP_HIGH and PF_MEMALLOC allocations usually don't
+ * need highmem pages, so cap pages_min to a small
+ * value here.
+ *
+ * The (pages_high-pages_low) and (pages_low-pages_min)
+ * deltas controls asynch page reclaim, and so should
+ * not be capped for highmem.
*/
int min_pages;
@@ -2393,19 +2457,15 @@
min_pages = 128;
zone->pages_min = min_pages;
} else {
- /* if it's a lowmem zone, reserve a number of pages
+ /*
+ * If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->pages_min = (pages_min * zone->present_pages) /
- lowmem_pages;
+ zone->pages_min = tmp;
}
- /*
- * When interpreting these watermarks, just keep in mind that:
- * zone->pages_min == (zone->pages_min * 4) / 4;
- */
- zone->pages_low = (zone->pages_min * 5) / 4;
- zone->pages_high = (zone->pages_min * 6) / 4;
+ zone->pages_low = zone->pages_min + tmp / 4;
+ zone->pages_high = zone->pages_min + tmp / 2;
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
}
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/net/core/dev.c
--- a/linux-2.6-xen-sparse/net/core/dev.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/net/core/dev.c Wed Feb 1 18:00:19 2006
@@ -1114,6 +1114,19 @@
return ret;
}
+/* Take action when hardware reception checksum errors are detected. */
+#ifdef CONFIG_BUG
+void netdev_rx_csum_fault(struct net_device *dev)
+{
+ if (net_ratelimit()) {
+ printk(KERN_ERR "%s: hw csum failure.\n",
+ dev ? dev->name : "<unknown>");
+ dump_stack();
+ }
+}
+EXPORT_SYMBOL(netdev_rx_csum_fault);
+#endif
+
#ifdef CONFIG_HIGHMEM
/* Actually, we should eliminate this check as soon as we know, that:
* 1. IOMMU is present and allows to map all the memory.
@@ -2767,6 +2780,20 @@
dev->name);
dev->features &= ~NETIF_F_TSO;
}
+ if (dev->features & NETIF_F_UFO) {
+ if (!(dev->features & NETIF_F_HW_CSUM)) {
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
+ "NETIF_F_HW_CSUM feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_UFO;
+ }
+ if (!(dev->features & NETIF_F_SG)) {
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
+ "NETIF_F_SG feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_UFO;
+ }
+ }
/*
* nil rebuild_header routine,
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/net/core/skbuff.c
--- a/linux-2.6-xen-sparse/net/core/skbuff.c Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/net/core/skbuff.c Wed Feb 1 18:00:19 2006
@@ -122,6 +122,8 @@
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
+ * @fclone: allocate from fclone cache instead of head cache
+ * and allocate a cloned (child) skb
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
* tail room of size bytes. The object has a reference count of one.
@@ -175,6 +177,8 @@
skb_shinfo(skb)->tso_size = 0;
skb_shinfo(skb)->tso_segs = 0;
skb_shinfo(skb)->frag_list = NULL;
+ skb_shinfo(skb)->ufo_size = 0;
+ skb_shinfo(skb)->ip6_frag_id = 0;
out:
return skb;
nodata:
@@ -247,6 +251,8 @@
skb_shinfo(skb)->tso_size = 0;
skb_shinfo(skb)->tso_segs = 0;
skb_shinfo(skb)->frag_list = NULL;
+ skb_shinfo(skb)->ufo_size = 0;
+ skb_shinfo(skb)->ip6_frag_id = 0;
out:
return skb;
nodata:
@@ -354,6 +360,9 @@
}
#ifdef CONFIG_NETFILTER
nf_conntrack_put(skb->nfct);
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ nf_conntrack_put_reasm(skb->nfct_reasm);
+#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
#endif
@@ -436,8 +445,16 @@
C(nfct);
nf_conntrack_get(skb->nfct);
C(nfctinfo);
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ C(nfct_reasm);
+ nf_conntrack_get_reasm(skb->nfct_reasm);
+#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
C(ipvs_property);
+#endif
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ C(nfct_reasm);
+ nf_conntrack_get_reasm(skb->nfct_reasm);
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
C(nf_bridge);
@@ -496,6 +513,10 @@
new->nfct = old->nfct;
nf_conntrack_get(old->nfct);
new->nfctinfo = old->nfctinfo;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+ new->nfct_reasm = old->nfct_reasm;
+ nf_conntrack_get_reasm(old->nfct_reasm);
+#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
new->ipvs_property = old->ipvs_property;
#endif
@@ -1718,6 +1739,78 @@
skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));
return textsearch_find(config, state);
+}
+
+/**
+ * skb_append_datato_frags: - append the user data to a skb
+ * @sk: sock structure
+ * @skb: skb structure to be appened with user data.
+ * @getfrag: call back function to be used for getting the user data
+ * @from: pointer to user message iov
+ * @length: length of the iov message
+ *
+ * Description: This procedure append the user data in the fragment part
+ * of the skb if any page alloc fails user this procedure returns -ENOMEM
+ */
+int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
+ int (*getfrag)(void *from, char *to, int offset,
+ int len, int odd, struct sk_buff *skb),
+ void *from, int length)
+{
+ int frg_cnt = 0;
+ skb_frag_t *frag = NULL;
+ struct page *page = NULL;
+ int copy, left;
+ int offset = 0;
+ int ret;
+
+ do {
+ /* Return error if we don't have space for new frag */
+ frg_cnt = skb_shinfo(skb)->nr_frags;
+ if (frg_cnt >= MAX_SKB_FRAGS)
+ return -EFAULT;
+
+ /* allocate a new page for next frag */
+ page = alloc_pages(sk->sk_allocation, 0);
+
+ /* If alloc_page fails just return failure and caller will
+ * free previous allocated pages by doing kfree_skb()
+ */
+ if (page == NULL)
+ return -ENOMEM;
+
+ /* initialize the next frag */
+ sk->sk_sndmsg_page = page;
+ sk->sk_sndmsg_off = 0;
+ skb_fill_page_desc(skb, frg_cnt, page, 0, 0);
+ skb->truesize += PAGE_SIZE;
+ atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
+
+ /* get the new initialized frag */
+ frg_cnt = skb_shinfo(skb)->nr_frags;
+ frag = &skb_shinfo(skb)->frags[frg_cnt - 1];
+
+ /* copy the user data to page */
+ left = PAGE_SIZE - frag->page_offset;
+ copy = (length > left)? left : length;
+
+ ret = getfrag(from, (page_address(frag->page) +
+ frag->page_offset + frag->size),
+ offset, copy, 0, skb);
+ if (ret < 0)
+ return -EFAULT;
+
+ /* copy was successful so update the size parameters */
+ sk->sk_sndmsg_off += copy;
+ frag->size += copy;
+ skb->len += copy;
+ skb->data_len += copy;
+ offset += copy;
+ length -= copy;
+
+ } while (length > 0);
+
+ return 0;
}
void __init skb_init(void)
@@ -1771,3 +1864,4 @@
EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
EXPORT_SYMBOL(skb_find_text);
+EXPORT_SYMBOL(skb_append_datato_frags);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/arch/i386/power/Makefile
--- /dev/null Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/arch/i386/power/Makefile Wed Feb 1 18:00:19 2006
@@ -0,0 +1,4 @@
+obj-$(CONFIG_PM_LEGACY) += cpu.o
+obj-$(CONFIG_SOFTWARE_SUSPEND) += cpu.o
+obj-$(CONFIG_ACPI_SLEEP) += cpu.o
+obj-$(CONFIG_SOFTWARE_SUSPEND) += swsusp.o
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/lib/Makefile
--- /dev/null Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/lib/Makefile Wed Feb 1 18:00:19 2006
@@ -0,0 +1,60 @@
+#
+# Makefile for some libs needed in the kernel.
+#
+
+lib-y := errno.o ctype.o string.o vsprintf.o cmdline.o \
+ bust_spinlocks.o rbtree.o radix-tree.o dump_stack.o \
+ idr.o div64.o int_sqrt.o bitmap.o extable.o prio_tree.o \
+ sha1.o
+
+lib-y += kobject.o kref.o kobject_uevent.o klist.o
+
+obj-y += sort.o parser.o halfmd4.o
+
+ifeq ($(CONFIG_DEBUG_KOBJECT),y)
+CFLAGS_kobject.o += -DDEBUG
+CFLAGS_kobject_uevent.o += -DDEBUG
+endif
+
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
+lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
+lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
+obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
+obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
+
+ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
+ lib-y += dec_and_lock.o
+endif
+
+obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
+obj-$(CONFIG_CRC16) += crc16.o
+obj-$(CONFIG_CRC32) += crc32.o
+obj-$(CONFIG_LIBCRC32C) += libcrc32c.o
+obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
+obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
+
+obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
+obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
+
+obj-$(CONFIG_TEXTSEARCH) += textsearch.o
+obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
+obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
+obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
+
+ifneq ($(CONFIG_XEN),y)
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
+endif
+
+hostprogs-y := gen_crc32table
+clean-files := crc32table.h
+
+$(obj)/crc32.o: $(obj)/crc32table.h
+
+quiet_cmd_crc32 = GEN $@
+ cmd_crc32 = $< > $@
+
+$(obj)/crc32table.h: $(obj)/gen_crc32table
+ $(call cmd,crc32)
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/mm/Kconfig
--- /dev/null Wed Feb 1 17:06:16 2006
+++ b/linux-2.6-xen-sparse/mm/Kconfig Wed Feb 1 18:00:19 2006
@@ -0,0 +1,137 @@
+config SELECT_MEMORY_MODEL
+ def_bool y
+ depends on EXPERIMENTAL || ARCH_SELECT_MEMORY_MODEL
+
+choice
+ prompt "Memory model"
+ depends on SELECT_MEMORY_MODEL
+ default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
+ default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
+ default FLATMEM_MANUAL
+
+config FLATMEM_MANUAL
+ bool "Flat Memory"
+ depends on !ARCH_DISCONTIGMEM_ENABLE || ARCH_FLATMEM_ENABLE
+ help
+ This option allows you to change some of the ways that
+ Linux manages its memory internally. Most users will
+ only have one option here: FLATMEM. This is normal
+ and a correct option.
+
+ Some users of more advanced features like NUMA and
+ memory hotplug may have different options here.
+ DISCONTIGMEM is an more mature, better tested system,
+ but is incompatible with memory hotplug and may suffer
+ decreased performance over SPARSEMEM. If unsure between
+ "Sparse Memory" and "Discontiguous Memory", choose
+ "Discontiguous Memory".
+
+ If unsure, choose this option (Flat Memory) over any other.
+
+config DISCONTIGMEM_MANUAL
+ bool "Discontiguous Memory"
+ depends on ARCH_DISCONTIGMEM_ENABLE
+ help
+ This option provides enhanced support for discontiguous
+ memory systems, over FLATMEM. These systems have holes
+ in their physical address spaces, and this option provides
+ more efficient handling of these holes. However, the vast
+ majority of hardware has quite flat address spaces, and
+ can have degraded performance from extra overhead that
+ this option imposes.
+
+ Many NUMA configurations will have this as the only option.
+
+ If unsure, choose "Flat Memory" over this option.
+
+config SPARSEMEM_MANUAL
+ bool "Sparse Memory"
+ depends on ARCH_SPARSEMEM_ENABLE
+ help
+ This will be the only option for some systems, including
+ memory hotplug systems. This is normal.
+
+ For many other systems, this will be an alternative to
+ "Discontiguous Memory". This option provides some potential
+ performance benefits, along with decreased code complexity,
+ but it is newer, and more experimental.
+
+ If unsure, choose "Discontiguous Memory" or "Flat Memory"
+ over this option.
+
+endchoice
+
+config DISCONTIGMEM
+ def_bool y
+ depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) ||
DISCONTIGMEM_MANUAL
+
+config SPARSEMEM
+ def_bool y
+ depends on SPARSEMEM_MANUAL
+
+config FLATMEM
+ def_bool y
+ depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
+
+config FLAT_NODE_MEM_MAP
+ def_bool y
+ depends on !SPARSEMEM
+
+#
+# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
+# to represent different areas of memory. This variable allows
+# those dependencies to exist individually.
+#
+config NEED_MULTIPLE_NODES
+ def_bool y
+ depends on DISCONTIGMEM || NUMA
+
+config HAVE_MEMORY_PRESENT
+ def_bool y
+ depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
+
+#
+# SPARSEMEM_EXTREME (which is the default) does some bootmem
+# allocations when memory_present() is called. If this can not
+# be done on your architecture, select this option. However,
+# statically allocating the mem_section[] array can potentially
+# consume vast quantities of .bss, so be careful.
+#
+# This option will also potentially produce smaller runtime code
+# with gcc 3.4 and later.
+#
+config SPARSEMEM_STATIC
+ def_bool n
+
+#
+# Architectecture platforms which require a two level mem_section in SPARSEMEM
+# must select this option. This is usually for architecture platforms with
+# an extremely sparse physical address space.
+#
+config SPARSEMEM_EXTREME
+ def_bool y
+ depends on SPARSEMEM && !SPARSEMEM_STATIC
+
+# eventually, we can have this option just 'select SPARSEMEM'
+config MEMORY_HOTPLUG
+ bool "Allow for memory hot-add"
+ depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND
+
+comment "Memory hotplug is currently incompatible with Software Suspend"
+ depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND
+
+# Heavily threaded applications may benefit from splitting the mm-wide
+# page_table_lock, so that faults on different parts of the user address
+# space can be handled with less contention: split it at this NR_CPUS.
+# Default to 4 for wider testing, though 8 might be more appropriate.
+# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
+# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
+# XEN uses the mapping field on pagetable pages to store a pointer to
+# the destructor.
+#
+config SPLIT_PTLOCK_CPUS
+ int
+ default "4096" if ARM && !CPU_CACHE_VIPT
+ default "4096" if PARISC && !PA20
+ default "4096" if XEN
+ default "4"
diff -r d609de73b9fa -r 5a63f675107c linux-2.6-xen-sparse/arch/i386/kernel/apm.c
--- a/linux-2.6-xen-sparse/arch/i386/kernel/apm.c Wed Feb 1 17:06:16 2006
+++ /dev/null Wed Feb 1 18:00:19 2006
@@ -1,2420 +0,0 @@
-/* -*- linux-c -*-
- * APM BIOS driver for Linux
- * Copyright 1994-2001 Stephen Rothwell (sfr@xxxxxxxxxxxxxxxx)
- *
- * Initial development of this driver was funded by NEC Australia P/L
- * and NEC Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2, or (at your option) any
- * later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * October 1995, Rik Faith (faith@xxxxxxxxxx):
- * Minor enhancements and updates (to the patch set) for 1.3.x
- * Documentation
- * January 1996, Rik Faith (faith@xxxxxxxxxx):
- * Make /proc/apm easy to format (bump driver version)
- * March 1996, Rik Faith (faith@xxxxxxxxxx):
- * Prohibit APM BIOS calls unless apm_enabled.
- * (Thanks to Ulrich Windl <Ulrich.Windl@xxxxxxxxxxxxxxxxxxxx>)
- * April 1996, Stephen Rothwell (sfr@xxxxxxxxxxxxxxxx)
- * Version 1.0 and 1.1
- * May 1996, Version 1.2
- * Feb 1998, Version 1.3
- * Feb 1998, Version 1.4
- * Aug 1998, Version 1.5
- * Sep 1998, Version 1.6
- * Nov 1998, Version 1.7
- * Jan 1999, Version 1.8
- * Jan 1999, Version 1.9
- * Oct 1999, Version 1.10
- * Nov 1999, Version 1.11
- * Jan 2000, Version 1.12
- * Feb 2000, Version 1.13
- * Nov 2000, Version 1.14
- * Oct 2001, Version 1.15
- * Jan 2002, Version 1.16
- * Oct 2002, Version 1.16ac
- *
- * History:
- * 0.6b: first version in official kernel, Linux 1.3.46
- * 0.7: changed /proc/apm format, Linux 1.3.58
- * 0.8: fixed gcc 2.7.[12] compilation problems, Linux 1.3.59
- * 0.9: only call bios if bios is present, Linux 1.3.72
- * 1.0: use fixed device number, consolidate /proc/apm into this file,
- * Linux 1.3.85
- * 1.1: support user-space standby and suspend, power off after system
- * halted, Linux 1.3.98
- * 1.2: When resetting RTC after resume, take care so that the time
- * is only incorrect by 30-60mS (vs. 1S previously) (Gabor J. Toth
- * <jtoth@xxxxxxxxxxxxx>); improve interaction between
- * screen-blanking and gpm (Stephen Rothwell); Linux 1.99.4
- * 1.2a:Simple change to stop mysterious bug reports with SMP also added
- * levels to the printk calls. APM is not defined for SMP machines.
- * The new replacment for it is, but Linux doesn't yet support this.
- * Alan Cox Linux 2.1.55
- * 1.3: Set up a valid data descriptor 0x40 for buggy BIOS's
- * 1.4: Upgraded to support APM 1.2. Integrated ThinkPad suspend patch by
- * Dean Gaudet <dgaudet@xxxxxxxxxx>.
- * C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx> Linux 2.1.87
- * 1.5: Fix segment register reloading (in case of bad segments saved
- * across BIOS call).
- * Stephen Rothwell
- * 1.6: Cope with complier/assembler differences.
- * Only try to turn off the first display device.
- * Fix OOPS at power off with no APM BIOS by Jan Echternach
- * <echter@xxxxxxxxxxxxxxxxxxxxxxxxx>
- * Stephen Rothwell
- * 1.7: Modify driver's cached copy of the disabled/disengaged flags
- * to reflect current state of APM BIOS.
- * Chris Rankin <rankinc@xxxxxxxxxxxxx>
- * Reset interrupt 0 timer to 100Hz after suspend
- * Chad Miller <cmiller@xxxxxxxxxxxxx>
- * Add CONFIG_APM_IGNORE_SUSPEND_BOUNCE
- * Richard Gooch <rgooch@xxxxxxxxxxxxx>
- * Allow boot time disabling of APM
- * Make boot messages far less verbose by default
- * Make asm safer
- * Stephen Rothwell
- * 1.8: Add CONFIG_APM_RTC_IS_GMT
- * Richard Gooch <rgooch@xxxxxxxxxxxxx>
- * change APM_NOINTS to CONFIG_APM_ALLOW_INTS
- * remove dependency on CONFIG_PROC_FS
- * Stephen Rothwell
- * 1.9: Fix small typo. <laslo@xxxxxxxxxxxxxx>
- * Try to cope with BIOS's that need to have all display
- * devices blanked and not just the first one.
- * Ross Paterson <ross@xxxxxxxxxxxxxx>
- * Fix segment limit setting it has always been wrong as
- * the segments needed to have byte granularity.
- * Mark a few things __init.
- * Add hack to allow power off of SMP systems by popular request.
- * Use CONFIG_SMP instead of __SMP__
- * Ignore BOUNCES for three seconds.
- * Stephen Rothwell
- * 1.10: Fix for Thinkpad return code.
- * Merge 2.2 and 2.3 drivers.
- * Remove APM dependencies in arch/i386/kernel/process.c
- * Remove APM dependencies in drivers/char/sysrq.c
- * Reset time across standby.
- * Allow more inititialisation on SMP.
- * Remove CONFIG_APM_POWER_OFF and make it boot time
- * configurable (default on).
- * Make debug only a boot time parameter (remove APM_DEBUG).
- * Try to blank all devices on any error.
- * 1.11: Remove APM dependencies in drivers/char/console.c
- * Check nr_running to detect if we are idle (from
- * Borislav Deianov <borislav@xxxxxxxxxxxxxxxxxxxx>)
- * Fix for bioses that don't zero the top part of the
- * entrypoint offset (Mario Sitta <sitta@xxxxxxxxxxxx>)
- * (reported by Panos Katsaloulis <teras@xxxxxxxxxxx>).
- * Real mode power off patch (Walter Hofmann
- * <Walter.Hofmann@xxxxxxxxxxxxxxxxxxxxxxxxxxx>).
- * 1.12: Remove CONFIG_SMP as the compiler will optimize
- * the code away anyway (smp_num_cpus == 1 in UP)
- * noted by Artur Skawina <skawina@xxxxxxxxxxxxx>.
- * Make power off under SMP work again.
- * Fix thinko with initial engaging of BIOS.
- * Make sure power off only happens on CPU 0
- * (Paul "Rusty" Russell <rusty@xxxxxxxxxxxxxxx>).
- * Do error notification to user mode if BIOS calls fail.
- * Move entrypoint offset fix to ...boot/setup.S
- * where it belongs (Cosmos <gis88564@xxxxxxxxxxxxxxx>).
- * Remove smp-power-off. SMP users must now specify
- * "apm=power-off" on the kernel command line. Suggested
- * by Jim Avera <jima@xxxxxxx>, modified by Alan Cox
- * <alan@xxxxxxxxxxxxxxxxxxx>.
- * Register the /proc/apm entry even on SMP so that
- * scripts that check for it before doing power off
- * work (Jim Avera <jima@xxxxxxx>).
- * 1.13: Changes for new pm_ interfaces (Andy Henroid
- * <andy_henroid@xxxxxxxxx>).
- * Modularize the code.
- * Fix the Thinkpad (again) :-( (CONFIG_APM_IGNORE_MULTIPLE_SUSPENDS
- * is now the way life works).
- * Fix thinko in suspend() (wrong return).
- * Notify drivers on critical suspend.
- * Make kapmd absorb more idle time (Pavel Machek <pavel@xxxxxxx>
- * modified by sfr).
- * Disable interrupts while we are suspended (Andy Henroid
- * <andy_henroid@xxxxxxxxx> fixed by sfr).
- * Make power off work on SMP again (Tony Hoyle
- * <tmh@xxxxxxxxxxxxxxxxx> and <zlatko@xxxxxxxx>) modified by sfr.
- * Remove CONFIG_APM_SUSPEND_BOUNCE. The bounce ignore
- * interval is now configurable.
- * 1.14: Make connection version persist across module unload/load.
- * Enable and engage power management earlier.
- * Disengage power management on module unload.
- * Changed to use the sysrq-register hack for registering the
- * power off function called by magic sysrq based upon discussions
- * in irc://irc.openprojects.net/#kernelnewbies
- * (Crutcher Dunnavant <crutcher+kernel@xxxxxxxxxxxxxx>).
- * Make CONFIG_APM_REAL_MODE_POWER_OFF run time configurable.
- * (Arjan van de Ven <arjanv@xxxxxxxxxx>) modified by sfr.
- * Work around byte swap bug in one of the Vaio's BIOS's
- * (Marc Boucher <marc@xxxxxxx>).
- * Exposed the disable flag to dmi so that we can handle known
- * broken APM (Alan Cox <alan@xxxxxxxxxx>).
- * 1.14ac: If the BIOS says "I slowed the CPU down" then don't spin
- * calling it - instead idle. (Alan Cox <alan@xxxxxxxxxx>)
- * If an APM idle fails log it and idle sensibly
- * 1.15: Don't queue events to clients who open the device O_WRONLY.
- * Don't expect replies from clients who open the device O_RDONLY.
- * (Idea from Thomas Hood)
- * Minor waitqueue cleanups. (John Fremlin <chief@xxxxxxxxxxx>)
- * 1.16: Fix idle calling. (Andreas Steinmetz <ast@xxxxxxxx> et al.)
- * Notify listeners of standby or suspend events before notifying
- * drivers. Return EBUSY to ioctl() if suspend is rejected.
- * (Russell King <rmk@xxxxxxxxxxxxxxxx> and Thomas Hood)
- * Ignore first resume after we generate our own resume event
- * after a suspend (Thomas Hood)
- * Daemonize now gets rid of our controlling terminal (sfr).
- * CONFIG_APM_CPU_IDLE now just affects the default value of
- * idle_threshold (sfr).
- * Change name of kernel apm daemon (as it no longer idles) (sfr).
- * 1.16ac: Fix up SMP support somewhat. You can now force SMP on and we
- * make _all_ APM calls on the CPU#0. Fix unsafe sign bug.
- * TODO: determine if its "boot CPU" or "CPU0" we want to lock to.
- *
- * APM 1.1 Reference:
- *
- * Intel Corporation, Microsoft Corporation. Advanced Power Management
- * (APM) BIOS Interface Specification, Revision 1.1, September 1993.
- * Intel Order Number 241704-001. Microsoft Part Number 781-110-X01.
- *
- * [This document is available free from Intel by calling 800.628.8686 (fax
- * 916.356.6100) or 800.548.4725; or via anonymous ftp from
- * ftp://ftp.intel.com/pub/IAL/software_specs/apmv11.doc. It is also
- * available from Microsoft by calling 206.882.8080.]
- *
- * APM 1.2 Reference:
- * Intel Corporation, Microsoft Corporation. Advanced Power Management
- * (APM) BIOS Interface Specification, Revision 1.2, February 1996.
- *
- * [This document is available from Microsoft at:
- * http://www.microsoft.com/hwdev/busbios/amp_12.htm]
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-
-#include <linux/poll.h>
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <linux/timer.h>
-#include <linux/fcntl.h>
-#include <linux/slab.h>
-#include <linux/stat.h>
-#include <linux/proc_fs.h>
-#include <linux/miscdevice.h>
-#include <linux/apm_bios.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/sched.h>
-#include <linux/pm.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/dmi.h>
-#include <linux/suspend.h>
-
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/desc.h>
-#include <asm/i8253.h>
-
-#include "io_ports.h"
-
-extern unsigned long get_cmos_time(void);
-extern void machine_real_restart(unsigned char *, int);
-
-#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
-extern int (*console_blank_hook)(int);
-#endif
-
-/*
- * The apm_bios device is one of the misc char devices.
- * This is its minor number.
- */
-#define APM_MINOR_DEV 134
-
-/*
- * See Documentation/Config.help for the configuration options.
- *
- * Various options can be changed at boot time as follows:
- * (We allow underscores for compatibility with the modules code)
- * apm=on/off enable/disable APM
- * [no-]allow[-_]ints allow interrupts during BIOS calls
- * [no-]broken[-_]psr BIOS has a broken GetPowerStatus call
- * [no-]realmode[-_]power[-_]off switch to real mode before
- * powering off
- * [no-]debug log some debugging messages
- * [no-]power[-_]off power off on shutdown
- * [no-]smp Use apm even on an SMP box
- * bounce[-_]interval=<n> number of ticks to ignore suspend
- * bounces
- * idle[-_]threshold=<n> System idle percentage above which to
- * make APM BIOS idle calls. Set it to
- * 100 to disable.
- * idle[-_]period=<n> Period (in 1/100s of a second) over
- * which the idle percentage is
- * calculated.
- */
-
-/* KNOWN PROBLEM MACHINES:
- *
- * U: TI 4000M TravelMate: BIOS is *NOT* APM compliant
- * [Confirmed by TI representative]
- * ?: ACER 486DX4/75: uses dseg 0040, in violation of APM specification
- * [Confirmed by BIOS disassembly]
- * [This may work now ...]
- * P: Toshiba 1950S: battery life information only gets updated after resume
- * P: Midwest Micro Soundbook Elite DX2/66 monochrome: screen blanking
- * broken in BIOS [Reported by Garst R. Reese <reese@xxxxxxx>]
- * ?: AcerNote-950: oops on reading /proc/apm - workaround is a WIP
- * Neale Banks <neale@xxxxxxxxxxxxxxxx> December 2000
- *
- * Legend: U = unusable with APM patches
- * P = partially usable with APM patches
- */
-
-/*
- * Define as 1 to make the driver always call the APM BIOS busy
- * routine even if the clock was not reported as slowed by the
- * idle routine. Otherwise, define as 0.
- */
-#define ALWAYS_CALL_BUSY 1
-
-/*
- * Define to make the APM BIOS calls zero all data segment registers (so
- * that an incorrect BIOS implementation will cause a kernel panic if it
- * tries to write to arbitrary memory).
- */
-#define APM_ZERO_SEGS
-
-#include "apm.h"
-
-/*
- * Define to make all _set_limit calls use 64k limits. The APM 1.1 BIOS is
- * supposed to provide limit information that it recognizes. Many machines
- * do this correctly, but many others do not restrict themselves to their
- * claimed limit. When this happens, they will cause a segmentation
- * violation in the kernel at boot time. Most BIOS's, however, will
- * respect a 64k limit, so we use that. If you want to be pedantic and
- * hold your BIOS to its claims, then undefine this.
- */
-#define APM_RELAX_SEGMENTS
-
-/*
- * Define to re-initialize the interrupt 0 timer to 100 Hz after a suspend.
- * This patched by Chad Miller <cmiller@xxxxxxxxxxxxx>, original code by
- * David Chen <chen@xxxxxxxxxxxxxx>
- */
-#undef INIT_TIMER_AFTER_SUSPEND
-
-#ifdef INIT_TIMER_AFTER_SUSPEND
-#include <linux/timex.h>
-#include <asm/io.h>
-#include <linux/delay.h>
-#endif
-
-/*
- * Need to poll the APM BIOS every second
- */
-#define APM_CHECK_TIMEOUT (HZ)
-
-/*
- * Ignore suspend events for this amount of time after a resume
- */
-#define DEFAULT_BOUNCE_INTERVAL (3 * HZ)
-
-/*
- * Maximum number of events stored
- */
-#define APM_MAX_EVENTS 20
-
-/*
- * The per-file APM data
- */
-struct apm_user {
- int magic;
- struct apm_user * next;
- unsigned int suser: 1;
- unsigned int writer: 1;
- unsigned int reader: 1;
- unsigned int suspend_wait: 1;
- int suspend_result;
- int suspends_pending;
- int standbys_pending;
- int suspends_read;
- int standbys_read;
- int event_head;
- int event_tail;
- apm_event_t events[APM_MAX_EVENTS];
-};
-
-/*
- * The magic number in apm_user
- */
-#define APM_BIOS_MAGIC 0x4101
-
-/*
- * idle percentage above which bios idle calls are done
- */
-#ifdef CONFIG_APM_CPU_IDLE
-#define DEFAULT_IDLE_THRESHOLD 95
-#else
-#define DEFAULT_IDLE_THRESHOLD 100
-#endif
-#define DEFAULT_IDLE_PERIOD (100 / 3)
-
-/*
- * Local variables
- */
-static struct {
- unsigned long offset;
- unsigned short segment;
-} apm_bios_entry;
-static int clock_slowed;
-static int idle_threshold = DEFAULT_IDLE_THRESHOLD;
-static int idle_period = DEFAULT_IDLE_PERIOD;
-static int set_pm_idle;
-static int suspends_pending;
-static int standbys_pending;
-static int ignore_sys_suspend;
-static int ignore_normal_resume;
-static int bounce_interval = DEFAULT_BOUNCE_INTERVAL;
-
-#ifdef CONFIG_APM_RTC_IS_GMT
-# define clock_cmos_diff 0
-# define got_clock_diff 1
-#else
-static long clock_cmos_diff;
-static int got_clock_diff;
-#endif
-static int debug;
-static int smp;
-static int apm_disabled = -1;
-#ifdef CONFIG_SMP
-static int power_off;
-#else
-static int power_off = 1;
-#endif
-#ifdef CONFIG_APM_REAL_MODE_POWER_OFF
-static int realmode_power_off = 1;
-#else
-static int realmode_power_off;
-#endif
-static int exit_kapmd;
-static int kapmd_running;
-#ifdef CONFIG_APM_ALLOW_INTS
-static int allow_ints = 1;
-#else
-static int allow_ints;
-#endif
-static int broken_psr;
-
-static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue);
-static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue);
-static struct apm_user * user_list;
-static DEFINE_SPINLOCK(user_list_lock);
-static struct desc_struct bad_bios_desc = { 0, 0x00409200 };
-
-static char driver_version[] = "1.16ac"; /* no spaces */
-
-/*
- * APM event names taken from the APM 1.2 specification. These are
- * the message codes that the BIOS uses to tell us about events
- */
-static char * apm_event_name[] = {
- "system standby",
- "system suspend",
- "normal resume",
- "critical resume",
- "low battery",
- "power status change",
- "update time",
- "critical suspend",
- "user standby",
- "user suspend",
- "system standby resume",
- "capabilities change"
-};
-#define NR_APM_EVENT_NAME \
- (sizeof(apm_event_name) / sizeof(apm_event_name[0]))
-
-typedef struct lookup_t {
- int key;
- char * msg;
-} lookup_t;
-
-/*
- * The BIOS returns a set of standard error codes in AX when the
- * carry flag is set.
- */
-
-static const lookup_t error_table[] = {
-/* N/A { APM_SUCCESS, "Operation succeeded" }, */
- { APM_DISABLED, "Power management disabled" },
- { APM_CONNECTED, "Real mode interface already connected" },
- { APM_NOT_CONNECTED, "Interface not connected" },
- { APM_16_CONNECTED, "16 bit interface already connected" },
-/* N/A { APM_16_UNSUPPORTED, "16 bit interface not supported" }, */
- { APM_32_CONNECTED, "32 bit interface already connected" },
- { APM_32_UNSUPPORTED, "32 bit interface not supported" },
- { APM_BAD_DEVICE, "Unrecognized device ID" },
- { APM_BAD_PARAM, "Parameter out of range" },
- { APM_NOT_ENGAGED, "Interface not engaged" },
- { APM_BAD_FUNCTION, "Function not supported" },
- { APM_RESUME_DISABLED, "Resume timer disabled" },
- { APM_BAD_STATE, "Unable to enter requested state" },
-/* N/A { APM_NO_EVENTS, "No events pending" }, */
- { APM_NO_ERROR, "BIOS did not set a return code" },
- { APM_NOT_PRESENT, "No APM present" }
-};
-#define ERROR_COUNT (sizeof(error_table)/sizeof(lookup_t))
-
-/**
- * apm_error - display an APM error
- * @str: information string
- * @err: APM BIOS return code
- *
- * Write a meaningful log entry to the kernel log in the event of
- * an APM error.
- */
-
-static void apm_error(char *str, int err)
-{
- int i;
-
- for (i = 0; i < ERROR_COUNT; i++)
- if (error_table[i].key == err) break;
- if (i < ERROR_COUNT)
- printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
- else
- printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
- str, err);
-}
-
-/*
- * Lock APM functionality to physical CPU 0
- */
-
-#ifdef CONFIG_SMP
-
-static cpumask_t apm_save_cpus(void)
-{
- cpumask_t x = current->cpus_allowed;
- /* Some bioses don't like being called from CPU != 0 */
- set_cpus_allowed(current, cpumask_of_cpu(0));
- BUG_ON(smp_processor_id() != 0);
- return x;
-}
-
-static inline void apm_restore_cpus(cpumask_t mask)
-{
- set_cpus_allowed(current, mask);
-}
-
-#else
-
-/*
- * No CPU lockdown needed on a uniprocessor
- */
-
-#define apm_save_cpus() (current->cpus_allowed)
-#define apm_restore_cpus(x) (void)(x)
-
-#endif
-
-/*
- * These are the actual BIOS calls. Depending on APM_ZERO_SEGS and
- * apm_info.allow_ints, we are being really paranoid here! Not only
- * are interrupts disabled, but all the segment registers (except SS)
- * are saved and zeroed this means that if the BIOS tries to reference
- * any data without explicitly loading the segment registers, the kernel
- * will fault immediately rather than have some unforeseen circumstances
- * for the rest of the kernel. And it will be very obvious! :-) Doing
- * this depends on CS referring to the same physical memory as DS so that
- * DS can be zeroed before the call. Unfortunately, we can't do anything
- * about the stack segment/pointer. Also, we tell the compiler that
- * everything could change.
- *
- * Also, we KNOW that for the non error case of apm_bios_call, there
- * is no useful data returned in the low order 8 bits of eax.
- */
-#define APM_DO_CLI \
- if (apm_info.allow_ints) \
- local_irq_enable(); \
- else \
- local_irq_disable();
-
-#ifdef APM_ZERO_SEGS
-# define APM_DECL_SEGS \
- unsigned int saved_fs; unsigned int saved_gs;
-# define APM_DO_SAVE_SEGS \
- savesegment(fs, saved_fs); savesegment(gs, saved_gs)
-# define APM_DO_RESTORE_SEGS \
- loadsegment(fs, saved_fs); loadsegment(gs, saved_gs)
-#else
-# define APM_DECL_SEGS
-# define APM_DO_SAVE_SEGS
-# define APM_DO_RESTORE_SEGS
-#endif
-
-/**
- * apm_bios_call - Make an APM BIOS 32bit call
- * @func: APM function to execute
- * @ebx_in: EBX register for call entry
- * @ecx_in: ECX register for call entry
- * @eax: EAX register return
- * @ebx: EBX register return
- * @ecx: ECX register return
- * @edx: EDX register return
- * @esi: ESI register return
- *
- * Make an APM call using the 32bit protected mode interface. The
- * caller is responsible for knowing if APM BIOS is configured and
- * enabled. This call can disable interrupts for a long period of
- * time on some laptops. The return value is in AH and the carry
- * flag is loaded into AL. If there is an error, then the error
- * code is returned in AH (bits 8-15 of eax) and this function
- * returns non-zero.
- */
-
-static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
- u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
-{
- APM_DECL_SEGS
- unsigned long flags;
- cpumask_t cpus;
- int cpu;
- struct desc_struct save_desc_40;
-
- cpus = apm_save_cpus();
-
- cpu = get_cpu();
- save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8];
- get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc;
-
- local_save_flags(flags);
- APM_DO_CLI;
- APM_DO_SAVE_SEGS;
- apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
- APM_DO_RESTORE_SEGS;
- local_irq_restore(flags);
- get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40;
- put_cpu();
- apm_restore_cpus(cpus);
-
- return *eax & 0xff;
-}
-
-/**
- * apm_bios_call_simple - make a simple APM BIOS 32bit call
- * @func: APM function to invoke
- * @ebx_in: EBX register value for BIOS call
- * @ecx_in: ECX register value for BIOS call
- * @eax: EAX register on return from the BIOS call
- *
- * Make a BIOS call that does only returns one value, or just status.
- * If there is an error, then the error code is returned in AH
- * (bits 8-15 of eax) and this function returns non-zero. This is
- * used for simpler BIOS operations. This call may hold interrupts
- * off for a long time on some laptops.
- */
-
-static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
-{
- u8 error;
- APM_DECL_SEGS
- unsigned long flags;
- cpumask_t cpus;
- int cpu;
- struct desc_struct save_desc_40;
-
-
- cpus = apm_save_cpus();
-
- cpu = get_cpu();
- save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8];
- get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc;
-
- local_save_flags(flags);
- APM_DO_CLI;
- APM_DO_SAVE_SEGS;
- error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
- APM_DO_RESTORE_SEGS;
- local_irq_restore(flags);
- get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40;
- put_cpu();
- apm_restore_cpus(cpus);
- return error;
-}
-
-/**
- * apm_driver_version - APM driver version
- * @val: loaded with the APM version on return
- *
- * Retrieve the APM version supported by the BIOS. This is only
- * supported for APM 1.1 or higher. An error indicates APM 1.0 is
- * probably present.
- *
- * On entry val should point to a value indicating the APM driver
- * version with the high byte being the major and the low byte the
- * minor number both in BCD
- *
- * On return it will hold the BIOS revision supported in the
- * same format.
- */
-
-static int apm_driver_version(u_short *val)
-{
- u32 eax;
-
- if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
- return (eax >> 8) & 0xff;
- *val = eax;
- return APM_SUCCESS;
-}
-
-/**
- * apm_get_event - get an APM event from the BIOS
- * @event: pointer to the event
- * @info: point to the event information
- *
- * The APM BIOS provides a polled information for event
- * reporting. The BIOS expects to be polled at least every second
- * when events are pending. When a message is found the caller should
- * poll until no more messages are present. However, this causes
- * problems on some laptops where a suspend event notification is
- * not cleared until it is acknowledged.
- *
- * Additional information is returned in the info pointer, providing
- * that APM 1.2 is in use. If no messges are pending the value 0x80
- * is returned (No power management events pending).
- */
-
-static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
-{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 dummy;
-
- if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
- &dummy, &dummy))
- return (eax >> 8) & 0xff;
- *event = ebx;
- if (apm_info.connection_version < 0x0102)
- *info = ~0; /* indicate info not valid */
- else
- *info = ecx;
- return APM_SUCCESS;
-}
-
-/**
- * set_power_state - set the power management state
- * @what: which items to transition
- * @state: state to transition to
- *
- * Request an APM change of state for one or more system devices. The
- * processor state must be transitioned last of all. what holds the
- * class of device in the upper byte and the device number (0xFF for
- * all) for the object to be transitioned.
- *
- * The state holds the state to transition to, which may in fact
- * be an acceptance of a BIOS requested state change.
- */
-
-static int set_power_state(u_short what, u_short state)
-{
- u32 eax;
-
- if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
- return (eax >> 8) & 0xff;
- return APM_SUCCESS;
-}
-
-/**
- * set_system_power_state - set system wide power state
- * @state: which state to enter
- *
- * Transition the entire system into a new APM power state.
- */
-
-static int set_system_power_state(u_short state)
-{
- return set_power_state(APM_DEVICE_ALL, state);
-}
-
-/**
- * apm_do_idle - perform power saving
- *
- * This function notifies the BIOS that the processor is (in the view
- * of the OS) idle. It returns -1 in the event that the BIOS refuses
- * to handle the idle request. On a success the function returns 1
- * if the BIOS did clock slowing or 0 otherwise.
- */
-
-static int apm_do_idle(void)
-{
- u32 eax;
-
- if (apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax)) {
- static unsigned long t;
-
- /* This always fails on some SMP boards running UP kernels.
- * Only report the failure the first 5 times.
- */
- if (++t < 5)
- {
- printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
- (eax >> 8) & 0xff);
- t = jiffies;
- }
- return -1;
- }
- clock_slowed = (apm_info.bios.flags & APM_IDLE_SLOWS_CLOCK) != 0;
- return clock_slowed;
-}
-
-/**
- * apm_do_busy - inform the BIOS the CPU is busy
- *
- * Request that the BIOS brings the CPU back to full performance.
- */
-
-static void apm_do_busy(void)
-{
- u32 dummy;
-
- if (clock_slowed || ALWAYS_CALL_BUSY) {
- (void) apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
- clock_slowed = 0;
- }
-}
-
-/*
- * If no process has really been interested in
- * the CPU for some time, we want to call BIOS
- * power management - we probably want
- * to conserve power.
- */
-#define IDLE_CALC_LIMIT (HZ * 100)
-#define IDLE_LEAKY_MAX 16
-
-static void (*original_pm_idle)(void);
-
-extern void default_idle(void);
-
-/**
- * apm_cpu_idle - cpu idling for APM capable Linux
- *
- * This is the idling function the kernel executes when APM is available. It
- * tries to do BIOS powermanagement based on the average system idle time.
- * Furthermore it calls the system default idle routine.
- */
-
-static void apm_cpu_idle(void)
-{
- static int use_apm_idle; /* = 0 */
- static unsigned int last_jiffies; /* = 0 */
- static unsigned int last_stime; /* = 0 */
-
- int apm_idle_done = 0;
- unsigned int jiffies_since_last_check = jiffies - last_jiffies;
- unsigned int bucket;
-
-recalc:
- if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
- use_apm_idle = 0;
- last_jiffies = jiffies;
- last_stime = current->stime;
- } else if (jiffies_since_last_check > idle_period) {
- unsigned int idle_percentage;
-
- idle_percentage = current->stime - last_stime;
- idle_percentage *= 100;
- idle_percentage /= jiffies_since_last_check;
- use_apm_idle = (idle_percentage > idle_threshold);
- if (apm_info.forbid_idle)
- use_apm_idle = 0;
- last_jiffies = jiffies;
- last_stime = current->stime;
- }
-
- bucket = IDLE_LEAKY_MAX;
-
- while (!need_resched()) {
- if (use_apm_idle) {
- unsigned int t;
-
- t = jiffies;
- switch (apm_do_idle()) {
- case 0: apm_idle_done = 1;
- if (t != jiffies) {
- if (bucket) {
- bucket = IDLE_LEAKY_MAX;
- continue;
- }
- } else if (bucket) {
- bucket--;
- continue;
- }
- break;
- case 1: apm_idle_done = 1;
- break;
- default: /* BIOS refused */
- break;
- }
- }
- if (original_pm_idle)
- original_pm_idle();
- else
- default_idle();
- jiffies_since_last_check = jiffies - last_jiffies;
- if (jiffies_since_last_check > idle_period)
- goto recalc;
- }
-
- if (apm_idle_done)
- apm_do_busy();
-}
-
-/**
- * apm_power_off - ask the BIOS to power off
- *
- * Handle the power off sequence. This is the one piece of code we
- * will execute even on SMP machines. In order to deal with BIOS
- * bugs we support real mode APM BIOS power off calls. We also make
- * the SMP call on CPU0 as some systems will only honour this call
- * on their first cpu.
- */
-
-static void apm_power_off(void)
-{
- unsigned char po_bios_call[] = {
- 0xb8, 0x00, 0x10, /* movw $0x1000,ax */
- 0x8e, 0xd0, /* movw ax,ss */
- 0xbc, 0x00, 0xf0, /* movw $0xf000,sp */
- 0xb8, 0x07, 0x53, /* movw $0x5307,ax */
- 0xbb, 0x01, 0x00, /* movw $0x0001,bx */
- 0xb9, 0x03, 0x00, /* movw $0x0003,cx */
- 0xcd, 0x15 /* int $0x15 */
- };
-
- /* Some bioses don't like being called from CPU != 0 */
- if (apm_info.realmode_power_off)
- {
- (void)apm_save_cpus();
- machine_real_restart(po_bios_call, sizeof(po_bios_call));
- }
- else
- (void) set_system_power_state(APM_STATE_OFF);
-}
-
-#ifdef CONFIG_APM_DO_ENABLE
-
-/**
- * apm_enable_power_management - enable BIOS APM power management
- * @enable: enable yes/no
- *
- * Enable or disable the APM BIOS power services.
- */
-
-static int apm_enable_power_management(int enable)
-{
- u32 eax;
-
- if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
- return APM_NOT_ENGAGED;
- if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
- enable, &eax))
- return (eax >> 8) & 0xff;
- if (enable)
- apm_info.bios.flags &= ~APM_BIOS_DISABLED;
- else
- apm_info.bios.flags |= APM_BIOS_DISABLED;
- return APM_SUCCESS;
-}
-#endif
-
-/**
- * apm_get_power_status - get current power state
- * @status: returned status
- * @bat: battery info
- * @life: estimated life
- *
- * Obtain the current power status from the APM BIOS. We return a
- * status which gives the rough battery status, and current power
- * source. The bat value returned give an estimate as a percentage
- * of life and a status value for the battery. The estimated life
- * if reported is a lifetime in secodnds/minutes at current powwer
- * consumption.
- */
-
-static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
-{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 dummy;
-
- if (apm_info.get_power_status_broken)
- return APM_32_UNSUPPORTED;
- if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
- &eax, &ebx, &ecx, &edx, &dummy))
- return (eax >> 8) & 0xff;
- *status = ebx;
- *bat = ecx;
- if (apm_info.get_power_status_swabinminutes) {
- *life = swab16((u16)edx);
- *life |= 0x8000;
- } else
- *life = edx;
- return APM_SUCCESS;
-}
-
-#if 0
-static int apm_get_battery_status(u_short which, u_short *status,
- u_short *bat, u_short *life, u_short *nbat)
-{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 esi;
-
- if (apm_info.connection_version < 0x0102) {
- /* pretend we only have one battery. */
- if (which != 1)
- return APM_BAD_DEVICE;
- *nbat = 1;
- return apm_get_power_status(status, bat, life);
- }
-
- if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax,
- &ebx, &ecx, &edx, &esi))
- return (eax >> 8) & 0xff;
- *status = ebx;
- *bat = ecx;
- *life = edx;
- *nbat = esi;
- return APM_SUCCESS;
-}
-#endif
-
-/**
- * apm_engage_power_management - enable PM on a device
- * @device: identity of device
- * @enable: on/off
- *
- * Activate or deactive power management on either a specific device
- * or the entire system (%APM_DEVICE_ALL).
- */
-
-static int apm_engage_power_management(u_short device, int enable)
-{
- u32 eax;
-
- if ((enable == 0) && (device == APM_DEVICE_ALL)
- && (apm_info.bios.flags & APM_BIOS_DISABLED))
- return APM_DISABLED;
- if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax))
- return (eax >> 8) & 0xff;
- if (device == APM_DEVICE_ALL) {
- if (enable)
- apm_info.bios.flags &= ~APM_BIOS_DISENGAGED;
- else
- apm_info.bios.flags |= APM_BIOS_DISENGAGED;
- }
- return APM_SUCCESS;
-}
-
-#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
-
-/**
- * apm_console_blank - blank the display
- * @blank: on/off
- *
- * Attempt to blank the console, firstly by blanking just video device
- * zero, and if that fails (some BIOSes don't support it) then it blanks
- * all video devices. Typically the BIOS will do laptop backlight and
- * monitor powerdown for us.
- */
-
-static int apm_console_blank(int blank)
-{
- int error;
- u_short state;
-
- state = blank ? APM_STATE_STANDBY : APM_STATE_READY;
- /* Blank the first display device */
- error = set_power_state(0x100, state);
- if ((error != APM_SUCCESS) && (error != APM_NO_ERROR)) {
- /* try to blank them all instead */
- error = set_power_state(0x1ff, state);
- if ((error != APM_SUCCESS) && (error != APM_NO_ERROR))
- /* try to blank device one instead */
- error = set_power_state(0x101, state);
- }
- if ((error == APM_SUCCESS) || (error == APM_NO_ERROR))
- return 1;
- if (error == APM_NOT_ENGAGED) {
- static int tried;
- int eng_error;
- if (tried++ == 0) {
- eng_error = apm_engage_power_management(APM_DEVICE_ALL,
1);
- if (eng_error) {
- apm_error("set display", error);
- apm_error("engage interface", eng_error);
- return 0;
- } else
- return apm_console_blank(blank);
- }
- }
- apm_error("set display", error);
- return 0;
-}
-#endif
-
-static int queue_empty(struct apm_user *as)
-{
- return as->event_head == as->event_tail;
-}
-
-static apm_event_t get_queued_event(struct apm_user *as)
-{
- as->event_tail = (as->event_tail + 1) % APM_MAX_EVENTS;
- return as->events[as->event_tail];
-}
-
-static void queue_event(apm_event_t event, struct apm_user *sender)
-{
- struct apm_user * as;
-
- spin_lock(&user_list_lock);
- if (user_list == NULL)
- goto out;
- for (as = user_list; as != NULL; as = as->next) {
- if ((as == sender) || (!as->reader))
- continue;
- as->event_head = (as->event_head + 1) % APM_MAX_EVENTS;
- if (as->event_head == as->event_tail) {
- static int notified;
-
- if (notified++ == 0)
- printk(KERN_ERR "apm: an event queue overflowed\n");
- as->event_tail = (as->event_tail + 1) % APM_MAX_EVENTS;
- }
- as->events[as->event_head] = event;
- if ((!as->suser) || (!as->writer))
- continue;
- switch (event) {
- case APM_SYS_SUSPEND:
- case APM_USER_SUSPEND:
- as->suspends_pending++;
- suspends_pending++;
- break;
-
- case APM_SYS_STANDBY:
- case APM_USER_STANDBY:
- as->standbys_pending++;
- standbys_pending++;
- break;
- }
- }
- wake_up_interruptible(&apm_waitqueue);
-out:
- spin_unlock(&user_list_lock);
-}
-
-static void set_time(void)
-{
- if (got_clock_diff) { /* Must know time zone in order to set clock */
- xtime.tv_sec = get_cmos_time() + clock_cmos_diff;
- xtime.tv_nsec = 0;
- }
-}
-
-static void get_time_diff(void)
-{
-#ifndef CONFIG_APM_RTC_IS_GMT
- /*
- * Estimate time zone so that set_time can update the clock
- */
- clock_cmos_diff = -get_cmos_time();
- clock_cmos_diff += get_seconds();
- got_clock_diff = 1;
-#endif
-}
-
-static void reinit_timer(void)
-{
-#ifdef INIT_TIMER_AFTER_SUSPEND
- unsigned long flags;
-
- spin_lock_irqsave(&i8253_lock, flags);
- /* set the clock to 100 Hz */
- outb_p(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */
- udelay(10);
- outb_p(LATCH & 0xff, PIT_CH0); /* LSB */
- udelay(10);
- outb(LATCH >> 8, PIT_CH0); /* MSB */
- udelay(10);
- spin_unlock_irqrestore(&i8253_lock, flags);
-#endif
-}
-
-static int suspend(int vetoable)
-{
- int err;
- struct apm_user *as;
-
- if (pm_send_all(PM_SUSPEND, (void *)3)) {
- /* Vetoed */
- if (vetoable) {
- if (apm_info.connection_version > 0x100)
- set_system_power_state(APM_STATE_REJECT);
- err = -EBUSY;
- ignore_sys_suspend = 0;
- printk(KERN_WARNING "apm: suspend was vetoed.\n");
- goto out;
- }
- printk(KERN_CRIT "apm: suspend was vetoed, but suspending
anyway.\n");
- }
-
- device_suspend(PMSG_SUSPEND);
- local_irq_disable();
- device_power_down(PMSG_SUSPEND);
-
- /* serialize with the timer interrupt */
- write_seqlock(&xtime_lock);
-
- /* protect against access to timer chip registers */
- spin_lock(&i8253_lock);
-
- get_time_diff();
- /*
- * Irq spinlock must be dropped around set_system_power_state.
- * We'll undo any timer changes due to interrupts below.
- */
- spin_unlock(&i8253_lock);
- write_sequnlock(&xtime_lock);
- local_irq_enable();
-
- save_processor_state();
- err = set_system_power_state(APM_STATE_SUSPEND);
- ignore_normal_resume = 1;
- restore_processor_state();
-
- local_irq_disable();
- write_seqlock(&xtime_lock);
- spin_lock(&i8253_lock);
- reinit_timer();
- set_time();
-
- spin_unlock(&i8253_lock);
- write_sequnlock(&xtime_lock);
-
- if (err == APM_NO_ERROR)
- err = APM_SUCCESS;
- if (err != APM_SUCCESS)
- apm_error("suspend", err);
- err = (err == APM_SUCCESS) ? 0 : -EIO;
- device_power_up();
- local_irq_enable();
- device_resume();
- pm_send_all(PM_RESUME, (void *)0);
- queue_event(APM_NORMAL_RESUME, NULL);
- out:
- spin_lock(&user_list_lock);
- for (as = user_list; as != NULL; as = as->next) {
- as->suspend_wait = 0;
- as->suspend_result = err;
- }
- spin_unlock(&user_list_lock);
- wake_up_interruptible(&apm_suspend_waitqueue);
- return err;
-}
-
-static void standby(void)
-{
- int err;
-
- local_irq_disable();
- device_power_down(PMSG_SUSPEND);
- /* serialize with the timer interrupt */
- write_seqlock(&xtime_lock);
- /* If needed, notify drivers here */
- get_time_diff();
- write_sequnlock(&xtime_lock);
- local_irq_enable();
-
- err = set_system_power_state(APM_STATE_STANDBY);
- if ((err != APM_SUCCESS) && (err != APM_NO_ERROR))
- apm_error("standby", err);
-
- local_irq_disable();
- device_power_up();
- local_irq_enable();
-}
-
-static apm_event_t get_event(void)
-{
- int error;
- apm_event_t event;
- apm_eventinfo_t info;
-
- static int notified;
-
- /* we don't use the eventinfo */
- error = apm_get_event(&event, &info);
- if (error == APM_SUCCESS)
- return event;
-
- if ((error != APM_NO_EVENTS) && (notified++ == 0))
- apm_error("get_event", error);
-
- return 0;
-}
-
-static void check_events(void)
-{
- apm_event_t event;
- static unsigned long last_resume;
- static int ignore_bounce;
-
- while ((event = get_event()) != 0) {
- if (debug) {
- if (event <= NR_APM_EVENT_NAME)
- printk(KERN_DEBUG "apm: received %s notify\n",
- apm_event_name[event - 1]);
- else
- printk(KERN_DEBUG "apm: received unknown "
- "event 0x%02x\n", event);
- }
- if (ignore_bounce
- && ((jiffies - last_resume) > bounce_interval))
- ignore_bounce = 0;
-
- switch (event) {
- case APM_SYS_STANDBY:
- case APM_USER_STANDBY:
- queue_event(event, NULL);
- if (standbys_pending <= 0)
- standby();
- break;
-
- case APM_USER_SUSPEND:
-#ifdef CONFIG_APM_IGNORE_USER_SUSPEND
- if (apm_info.connection_version > 0x100)
- set_system_power_state(APM_STATE_REJECT);
- break;
-#endif
- case APM_SYS_SUSPEND:
- if (ignore_bounce) {
- if (apm_info.connection_version > 0x100)
-
set_system_power_state(APM_STATE_REJECT);
- break;
- }
- /*
- * If we are already processing a SUSPEND,
- * then further SUSPEND events from the BIOS
- * will be ignored. We also return here to
- * cope with the fact that the Thinkpads keep
- * sending a SUSPEND event until something else
- * happens!
- */
- if (ignore_sys_suspend)
- return;
- ignore_sys_suspend = 1;
- queue_event(event, NULL);
- if (suspends_pending <= 0)
- (void) suspend(1);
- break;
-
- case APM_NORMAL_RESUME:
- case APM_CRITICAL_RESUME:
- case APM_STANDBY_RESUME:
- ignore_sys_suspend = 0;
- last_resume = jiffies;
- ignore_bounce = 1;
- if ((event != APM_NORMAL_RESUME)
- || (ignore_normal_resume == 0)) {
- write_seqlock_irq(&xtime_lock);
- set_time();
- write_sequnlock_irq(&xtime_lock);
- device_resume();
- pm_send_all(PM_RESUME, (void *)0);
- queue_event(event, NULL);
- }
- ignore_normal_resume = 0;
- break;
-
- case APM_CAPABILITY_CHANGE:
- case APM_LOW_BATTERY:
- case APM_POWER_STATUS_CHANGE:
- queue_event(event, NULL);
- /* If needed, notify drivers here */
- break;
-
- case APM_UPDATE_TIME:
- write_seqlock_irq(&xtime_lock);
- set_time();
- write_sequnlock_irq(&xtime_lock);
- break;
-
- case APM_CRITICAL_SUSPEND:
- /*
- * We are not allowed to reject a critical suspend.
- */
- (void) suspend(0);
- break;
- }
- }
-}
-
-static void apm_event_handler(void)
-{
- static int pending_count = 4;
- int err;
-
- if ((standbys_pending > 0) || (suspends_pending > 0)) {
- if ((apm_info.connection_version > 0x100) &&
- (pending_count-- <= 0)) {
- pending_count = 4;
- if (debug)
- printk(KERN_DEBUG "apm: setting state busy\n");
- err = set_system_power_state(APM_STATE_BUSY);
- if (err)
- apm_error("busy", err);
- }
- } else
- pending_count = 4;
- check_events();
-}
-
-/*
- * This is the APM thread main loop.
- */
-
-static void apm_mainloop(void)
-{
- DECLARE_WAITQUEUE(wait, current);
-
- add_wait_queue(&apm_waitqueue, &wait);
- set_current_state(TASK_INTERRUPTIBLE);
- for (;;) {
- schedule_timeout(APM_CHECK_TIMEOUT);
- if (exit_kapmd)
- break;
- /*
- * Ok, check all events, check for idle (and mark us sleeping
- * so as not to count towards the load average)..
- */
- set_current_state(TASK_INTERRUPTIBLE);
- apm_event_handler();
- }
- remove_wait_queue(&apm_waitqueue, &wait);
-}
-
-static int check_apm_user(struct apm_user *as, const char *func)
-{
- if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) {
- printk(KERN_ERR "apm: %s passed bad filp\n", func);
- return 1;
- }
- return 0;
-}
-
-static ssize_t do_read(struct file *fp, char __user *buf, size_t count, loff_t
*ppos)
-{
- struct apm_user * as;
- int i;
- apm_event_t event;
-
- as = fp->private_data;
- if (check_apm_user(as, "read"))
- return -EIO;
- if ((int)count < sizeof(apm_event_t))
- return -EINVAL;
- if ((queue_empty(as)) && (fp->f_flags & O_NONBLOCK))
- return -EAGAIN;
- wait_event_interruptible(apm_waitqueue, !queue_empty(as));
- i = count;
- while ((i >= sizeof(event)) && !queue_empty(as)) {
- event = get_queued_event(as);
- if (copy_to_user(buf, &event, sizeof(event))) {
- if (i < count)
- break;
- return -EFAULT;
- }
- switch (event) {
- case APM_SYS_SUSPEND:
- case APM_USER_SUSPEND:
- as->suspends_read++;
- break;
-
- case APM_SYS_STANDBY:
- case APM_USER_STANDBY:
- as->standbys_read++;
- break;
- }
- buf += sizeof(event);
- i -= sizeof(event);
- }
- if (i < count)
- return count - i;
- if (signal_pending(current))
- return -ERESTARTSYS;
- return 0;
-}
-
-static unsigned int do_poll(struct file *fp, poll_table * wait)
-{
- struct apm_user * as;
-
- as = fp->private_data;
- if (check_apm_user(as, "poll"))
- return 0;
- poll_wait(fp, &apm_waitqueue, wait);
- if (!queue_empty(as))
- return POLLIN | POLLRDNORM;
- return 0;
-}
-
-static int do_ioctl(struct inode * inode, struct file *filp,
- u_int cmd, u_long arg)
-{
- struct apm_user * as;
-
- as = filp->private_data;
- if (check_apm_user(as, "ioctl"))
- return -EIO;
- if ((!as->suser) || (!as->writer))
- return -EPERM;
- switch (cmd) {
- case APM_IOC_STANDBY:
- if (as->standbys_read > 0) {
- as->standbys_read--;
- as->standbys_pending--;
- standbys_pending--;
- } else
- queue_event(APM_USER_STANDBY, as);
- if (standbys_pending <= 0)
- standby();
- break;
- case APM_IOC_SUSPEND:
- if (as->suspends_read > 0) {
- as->suspends_read--;
- as->suspends_pending--;
- suspends_pending--;
- } else
- queue_event(APM_USER_SUSPEND, as);
- if (suspends_pending <= 0) {
- return suspend(1);
- } else {
- as->suspend_wait = 1;
- wait_event_interruptible(apm_suspend_waitqueue,
- as->suspend_wait == 0);
- return as->suspend_result;
- }
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int do_release(struct inode * inode, struct file * filp)
-{
- struct apm_user * as;
-
- as = filp->private_data;
- if (check_apm_user(as, "release"))
- return 0;
- filp->private_data = NULL;
- if (as->standbys_pending > 0) {
- standbys_pending -= as->standbys_pending;
- if (standbys_pending <= 0)
- standby();
- }
- if (as->suspends_pending > 0) {
- suspends_pending -= as->suspends_pending;
- if (suspends_pending <= 0)
- (void) suspend(1);
- }
- spin_lock(&user_list_lock);
- if (user_list == as)
- user_list = as->next;
- else {
- struct apm_user * as1;
-
- for (as1 = user_list;
- (as1 != NULL) && (as1->next != as);
- as1 = as1->next)
- ;
- if (as1 == NULL)
- printk(KERN_ERR "apm: filp not in user list\n");
- else
- as1->next = as->next;
- }
- spin_unlock(&user_list_lock);
- kfree(as);
- return 0;
-}
-
-static int do_open(struct inode * inode, struct file * filp)
-{
- struct apm_user * as;
-
- as = (struct apm_user *)kmalloc(sizeof(*as), GFP_KERNEL);
- if (as == NULL) {
- printk(KERN_ERR "apm: cannot allocate struct of size %d
bytes\n",
- sizeof(*as));
- return -ENOMEM;
- }
- as->magic = APM_BIOS_MAGIC;
- as->event_tail = as->event_head = 0;
- as->suspends_pending = as->standbys_pending = 0;
- as->suspends_read = as->standbys_read = 0;
- /*
- * XXX - this is a tiny bit broken, when we consider BSD
- * process accounting. If the device is opened by root, we
- * instantly flag that we used superuser privs. Who knows,
- * we might close the device immediately without doing a
- * privileged operation -- cevans
- */
- as->suser = capable(CAP_SYS_ADMIN);
- as->writer = (filp->f_mode & FMODE_WRITE) == FMODE_WRITE;
- as->reader = (filp->f_mode & FMODE_READ) == FMODE_READ;
- spin_lock(&user_list_lock);
- as->next = user_list;
- user_list = as;
- spin_unlock(&user_list_lock);
- filp->private_data = as;
- return 0;
-}
-
-static int apm_get_info(char *buf, char **start, off_t fpos, int length)
-{
- char * p;
- unsigned short bx;
- unsigned short cx;
- unsigned short dx;
- int error;
- unsigned short ac_line_status = 0xff;
- unsigned short battery_status = 0xff;
- unsigned short battery_flag = 0xff;
- int percentage = -1;
- int time_units = -1;
- char *units = "?";
-
- p = buf;
-
- if ((num_online_cpus() == 1) &&
- !(error = apm_get_power_status(&bx, &cx, &dx))) {
- ac_line_status = (bx >> 8) & 0xff;
- battery_status = bx & 0xff;
- if ((cx & 0xff) != 0xff)
- percentage = cx & 0xff;
-
- if (apm_info.connection_version > 0x100) {
- battery_flag = (cx >> 8) & 0xff;
- if (dx != 0xffff) {
- units = (dx & 0x8000) ? "min" : "sec";
- time_units = dx & 0x7fff;
- }
- }
- }
- /* Arguments, with symbols from linux/apm_bios.h. Information is
- from the Get Power Status (0x0a) call unless otherwise noted.
-
- 0) Linux driver version (this will change if format changes)
- 1) APM BIOS Version. Usually 1.0, 1.1 or 1.2.
- 2) APM flags from APM Installation Check (0x00):
- bit 0: APM_16_BIT_SUPPORT
- bit 1: APM_32_BIT_SUPPORT
- bit 2: APM_IDLE_SLOWS_CLOCK
- bit 3: APM_BIOS_DISABLED
- bit 4: APM_BIOS_DISENGAGED
- 3) AC line status
- 0x00: Off-line
- 0x01: On-line
- 0x02: On backup power (BIOS >= 1.1 only)
- 0xff: Unknown
- 4) Battery status
- 0x00: High
- 0x01: Low
- 0x02: Critical
- 0x03: Charging
- 0x04: Selected battery not present (BIOS >= 1.2 only)
- 0xff: Unknown
- 5) Battery flag
- bit 0: High
- bit 1: Low
- bit 2: Critical
- bit 3: Charging
- bit 7: No system battery
- 0xff: Unknown
- 6) Remaining battery life (percentage of charge):
- 0-100: valid
- -1: Unknown
- 7) Remaining battery life (time units):
- Number of remaining minutes or seconds
- -1: Unknown
- 8) min = minutes; sec = seconds */
-
- p += sprintf(p, "%s %d.%d 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
- driver_version,
- (apm_info.bios.version >> 8) & 0xff,
- apm_info.bios.version & 0xff,
- apm_info.bios.flags,
- ac_line_status,
- battery_status,
- battery_flag,
- percentage,
- time_units,
- units);
-
- return p - buf;
-}
-
-static int apm(void *unused)
-{
- unsigned short bx;
- unsigned short cx;
- unsigned short dx;
- int error;
- char * power_stat;
- char * bat_stat;
-
- kapmd_running = 1;
-
- daemonize("kapmd");
-
- current->flags |= PF_NOFREEZE;
-
-#ifdef CONFIG_SMP
- /* 2002/08/01 - WT
- * This is to avoid random crashes at boot time during initialization
- * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D.
- * Some bioses don't like being called from CPU != 0.
- * Method suggested by Ingo Molnar.
- */
- set_cpus_allowed(current, cpumask_of_cpu(0));
- BUG_ON(smp_processor_id() != 0);
-#endif
-
- if (apm_info.connection_version == 0) {
- apm_info.connection_version = apm_info.bios.version;
- if (apm_info.connection_version > 0x100) {
- /*
- * We only support BIOSs up to version 1.2
- */
- if (apm_info.connection_version > 0x0102)
- apm_info.connection_version = 0x0102;
- error =
apm_driver_version(&apm_info.connection_version);
- if (error != APM_SUCCESS) {
- apm_error("driver version", error);
- /* Fall back to an APM 1.0 connection. */
- apm_info.connection_version = 0x100;
- }
- }
- }
-
- if (debug)
- printk(KERN_INFO "apm: Connection version %d.%d\n",
- (apm_info.connection_version >> 8) & 0xff,
- apm_info.connection_version & 0xff);
-
-#ifdef CONFIG_APM_DO_ENABLE
- if (apm_info.bios.flags & APM_BIOS_DISABLED) {
- /*
- * This call causes my NEC UltraLite Versa 33/C to hang if it
- * is booted with PM disabled but not in the docking station.
- * Unfortunate ...
- */
- error = apm_enable_power_management(1);
- if (error) {
- apm_error("enable power management", error);
- return -1;
- }
- }
-#endif
-
- if ((apm_info.bios.flags & APM_BIOS_DISENGAGED)
- && (apm_info.connection_version > 0x0100)) {
- error = apm_engage_power_management(APM_DEVICE_ALL, 1);
- if (error) {
- apm_error("engage power management", error);
- return -1;
- }
- }
-
- if (debug && (num_online_cpus() == 1 || smp )) {
- error = apm_get_power_status(&bx, &cx, &dx);
- if (error)
- printk(KERN_INFO "apm: power status not available\n");
- else {
- switch ((bx >> 8) & 0xff) {
- case 0: power_stat = "off line"; break;
- case 1: power_stat = "on line"; break;
- case 2: power_stat = "on backup power"; break;
- default: power_stat = "unknown"; break;
- }
- switch (bx & 0xff) {
- case 0: bat_stat = "high"; break;
- case 1: bat_stat = "low"; break;
- case 2: bat_stat = "critical"; break;
- case 3: bat_stat = "charging"; break;
- default: bat_stat = "unknown"; break;
- }
- printk(KERN_INFO
- "apm: AC %s, battery status %s, battery life ",
- power_stat, bat_stat);
- if ((cx & 0xff) == 0xff)
- printk("unknown\n");
- else
- printk("%d%%\n", cx & 0xff);
- if (apm_info.connection_version > 0x100) {
- printk(KERN_INFO
- "apm: battery flag 0x%02x, battery life
",
- (cx >> 8) & 0xff);
- if (dx == 0xffff)
- printk("unknown\n");
- else
- printk("%d %s\n", dx & 0x7fff,
- (dx & 0x8000) ?
- "minutes" : "seconds");
- }
- }
- }
-
- /* Install our power off handler.. */
- if (power_off)
- pm_power_off = apm_power_off;
-
- if (num_online_cpus() == 1 || smp) {
-#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
- console_blank_hook = apm_console_blank;
-#endif
- apm_mainloop();
-#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
- console_blank_hook = NULL;
-#endif
- }
- kapmd_running = 0;
-
- return 0;
-}
-
-#ifndef MODULE
-static int __init apm_setup(char *str)
-{
- int invert;
-
- while ((str != NULL) && (*str != '\0')) {
- if (strncmp(str, "off", 3) == 0)
- apm_disabled = 1;
- if (strncmp(str, "on", 2) == 0)
- apm_disabled = 0;
- if ((strncmp(str, "bounce-interval=", 16) == 0) ||
- (strncmp(str, "bounce_interval=", 16) == 0))
- bounce_interval = simple_strtol(str + 16, NULL, 0);
- if ((strncmp(str, "idle-threshold=", 15) == 0) ||
- (strncmp(str, "idle_threshold=", 15) == 0))
- idle_threshold = simple_strtol(str + 15, NULL, 0);
- if ((strncmp(str, "idle-period=", 12) == 0) ||
- (strncmp(str, "idle_period=", 12) == 0))
- idle_period = simple_strtol(str + 12, NULL, 0);
- invert = (strncmp(str, "no-", 3) == 0) ||
- (strncmp(str, "no_", 3) == 0);
- if (invert)
- str += 3;
- if (strncmp(str, "debug", 5) == 0)
- debug = !invert;
- if ((strncmp(str, "power-off", 9) == 0) ||
- (strncmp(str, "power_off", 9) == 0))
- power_off = !invert;
- if (strncmp(str, "smp", 3) == 0)
- {
- smp = !invert;
- idle_threshold = 100;
- }
- if ((strncmp(str, "allow-ints", 10) == 0) ||
- (strncmp(str, "allow_ints", 10) == 0))
- apm_info.allow_ints = !invert;
- if ((strncmp(str, "broken-psr", 10) == 0) ||
- (strncmp(str, "broken_psr", 10) == 0))
- apm_info.get_power_status_broken = !invert;
- if ((strncmp(str, "realmode-power-off", 18) == 0) ||
- (strncmp(str, "realmode_power_off", 18) == 0))
- apm_info.realmode_power_off = !invert;
- str = strchr(str, ',');
- if (str != NULL)
- str += strspn(str, ", \t");
- }
- return 1;
-}
-
-__setup("apm=", apm_setup);
-#endif
-
-static struct file_operations apm_bios_fops = {
- .owner = THIS_MODULE,
- .read = do_read,
- .poll = do_poll,
- .ioctl = do_ioctl,
- .open = do_open,
- .release = do_release,
-};
-
-static struct miscdevice apm_device = {
- APM_MINOR_DEV,
- "apm_bios",
- &apm_bios_fops
-};
-
-
-/* Simple "print if true" callback */
-static int __init print_if_true(struct dmi_system_id *d)
-{
- printk("%s\n", d->ident);
- return 0;
-}
-
-/*
- * Some Bioses enable the PS/2 mouse (touchpad) at resume, even if it was
- * disabled before the suspend. Linux used to get terribly confused by that.
- */
-static int __init broken_ps2_resume(struct dmi_system_id *d)
-{
- printk(KERN_INFO "%s machine detected. Mousepad Resume Bug workaround
hopefully not needed.\n", d->ident);
- return 0;
-}
-
-/* Some bioses have a broken protected mode poweroff and need to use realmode
*/
-static int __init set_realmode_power_off(struct dmi_system_id *d)
-{
- if (apm_info.realmode_power_off == 0) {
- apm_info.realmode_power_off = 1;
- printk(KERN_INFO "%s bios detected. Using realmode poweroff
only.\n", d->ident);
- }
- return 0;
-}
-
-/* Some laptops require interrupts to be enabled during APM calls */
-static int __init set_apm_ints(struct dmi_system_id *d)
-{
- if (apm_info.allow_ints == 0) {
- apm_info.allow_ints = 1;
- printk(KERN_INFO "%s machine detected. Enabling interrupts
during APM calls.\n", d->ident);
- }
- return 0;
-}
-
-/* Some APM bioses corrupt memory or just plain do not work */
-static int __init apm_is_horked(struct dmi_system_id *d)
-{
- if (apm_info.disabled == 0) {
- apm_info.disabled = 1;
- printk(KERN_INFO "%s machine detected. Disabling APM.\n",
d->ident);
- }
- return 0;
-}
-
-static int __init apm_is_horked_d850md(struct dmi_system_id *d)
-{
- if (apm_info.disabled == 0) {
- apm_info.disabled = 1;
- printk(KERN_INFO "%s machine detected. Disabling APM.\n",
d->ident);
- printk(KERN_INFO "This bug is fixed in bios P15 which is
available for \n");
- printk(KERN_INFO "download from support.intel.com \n");
- }
- return 0;
-}
-
-/* Some APM bioses hang on APM idle calls */
-static int __init apm_likes_to_melt(struct dmi_system_id *d)
-{
- if (apm_info.forbid_idle == 0) {
- apm_info.forbid_idle = 1;
- printk(KERN_INFO "%s machine detected. Disabling APM idle
calls.\n", d->ident);
- }
- return 0;
-}
-
-/*
- * Check for clue free BIOS implementations who use
- * the following QA technique
- *
- * [ Write BIOS Code ]<------
- * | ^
- * < Does it Compile >----N--
- * |Y ^
- * < Does it Boot Win98 >-N--
- * |Y
- * [Ship It]
- *
- * Phoenix A04 08/24/2000 is known bad (Dell Inspiron 5000e)
- * Phoenix A07 09/29/2000 is known good (Dell Inspiron 5000)
- */
-static int __init broken_apm_power(struct dmi_system_id *d)
-{
- apm_info.get_power_status_broken = 1;
- printk(KERN_WARNING "BIOS strings suggest APM bugs, disabling power
status reporting.\n");
- return 0;
-}
-
-/*
- * This bios swaps the APM minute reporting bytes over (Many sony laptops
- * have this problem).
- */
-static int __init swab_apm_power_in_minutes(struct dmi_system_id *d)
-{
- apm_info.get_power_status_swabinminutes = 1;
- printk(KERN_WARNING "BIOS strings suggest APM reports battery life in
minutes and wrong byte order.\n");
- return 0;
-}
-
-static struct dmi_system_id __initdata apm_dmi_table[] = {
- {
- print_if_true,
- KERN_WARNING "IBM T23 - BIOS 1.03b+ and controller firmware
1.02+ may be needed for Linux APM.",
- { DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
- DMI_MATCH(DMI_BIOS_VERSION, "1AET38WW (1.01b)"), },
- },
- { /* Handle problems with APM on the C600 */
- broken_ps2_resume, "Dell Latitude C600",
- { DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Latitude C600"), },
- },
- { /* Allow interrupts during suspend on Dell Latitude laptops*/
- set_apm_ints, "Dell Latitude",
- { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Latitude C510"), }
- },
- { /* APM crashes */
- apm_is_horked, "Dell Inspiron 2500",
- { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"),
- DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
- },
- { /* Allow interrupts during suspend on Dell Inspiron laptops*/
- set_apm_ints, "Dell Inspiron", {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 4000"), },
- },
- { /* Handle problems with APM on Inspiron 5000e */
- broken_apm_power, "Dell Inspiron 5000e",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "A04"),
- DMI_MATCH(DMI_BIOS_DATE, "08/24/2000"), },
- },
- { /* Handle problems with APM on Inspiron 2500 */
- broken_apm_power, "Dell Inspiron 2500",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "A12"),
- DMI_MATCH(DMI_BIOS_DATE, "02/04/2002"), },
- },
- { /* APM crashes */
- apm_is_horked, "Dell Dimension 4100",
- { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "XPS-Z"),
- DMI_MATCH(DMI_BIOS_VENDOR,"Intel Corp."),
- DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
- },
- { /* Allow interrupts during suspend on Compaq Laptops*/
- set_apm_ints, "Compaq 12XL125",
- { DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Compaq PC"),
- DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION,"4.06"), },
- },
- { /* Allow interrupts during APM or the clock goes slow */
- set_apm_ints, "ASUSTeK",
- { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "L8400K series Notebook
PC"), },
- },
- { /* APM blows on shutdown */
- apm_is_horked, "ABIT KX7-333[R]",
- { DMI_MATCH(DMI_BOARD_VENDOR, "ABIT"),
- DMI_MATCH(DMI_BOARD_NAME, "VT8367-8233A (KX7-333[R])"),
},
- },
- { /* APM crashes */
- apm_is_horked, "Trigem Delhi3",
- { DMI_MATCH(DMI_SYS_VENDOR, "TriGem Computer, Inc"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Delhi3"), },
- },
- { /* APM crashes */
- apm_is_horked, "Fujitsu-Siemens",
- { DMI_MATCH(DMI_BIOS_VENDOR, "hoenix/FUJITSU SIEMENS"),
- DMI_MATCH(DMI_BIOS_VERSION, "Version1.01"), },
- },
- { /* APM crashes */
- apm_is_horked_d850md, "Intel D850MD",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."),
- DMI_MATCH(DMI_BIOS_VERSION,
"MV85010A.86A.0016.P07.0201251536"), },
- },
- { /* APM crashes */
- apm_is_horked, "Intel D810EMO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."),
- DMI_MATCH(DMI_BIOS_VERSION,
"MO81010A.86A.0008.P04.0004170800"), },
- },
- { /* APM crashes */
- apm_is_horked, "Dell XPS-Z",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."),
- DMI_MATCH(DMI_BIOS_VERSION, "A11"),
- DMI_MATCH(DMI_PRODUCT_NAME, "XPS-Z"), },
- },
- { /* APM crashes */
- apm_is_horked, "Sharp PC-PJ/AX",
- { DMI_MATCH(DMI_SYS_VENDOR, "SHARP"),
- DMI_MATCH(DMI_PRODUCT_NAME, "PC-PJ/AX"),
- DMI_MATCH(DMI_BIOS_VENDOR,"SystemSoft"),
- DMI_MATCH(DMI_BIOS_VERSION,"Version R2.08"), },
- },
- { /* APM crashes */
- apm_is_horked, "Dell Inspiron 2500",
- { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"),
- DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
- },
- { /* APM idle hangs */
- apm_likes_to_melt, "Jabil AMD",
- { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
- DMI_MATCH(DMI_BIOS_VERSION, "0AASNP06"), },
- },
- { /* APM idle hangs */
- apm_likes_to_melt, "AMI Bios",
- { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
- DMI_MATCH(DMI_BIOS_VERSION, "0AASNP05"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-N505X(DE) */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0206H"),
- DMI_MATCH(DMI_BIOS_DATE, "08/23/99"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-N505VX */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "W2K06H0"),
- DMI_MATCH(DMI_BIOS_DATE, "02/03/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-XG29 */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0117A0"),
- DMI_MATCH(DMI_BIOS_DATE, "04/25/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z600NE */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0121Z1"),
- DMI_MATCH(DMI_BIOS_DATE, "05/11/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z600NE */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "WME01Z1"),
- DMI_MATCH(DMI_BIOS_DATE, "08/11/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z600LEK(DE) */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0206Z3"),
- DMI_MATCH(DMI_BIOS_DATE, "12/25/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z505LS */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0203D0"),
- DMI_MATCH(DMI_BIOS_DATE, "05/12/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z505LS */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0203Z3"),
- DMI_MATCH(DMI_BIOS_DATE, "08/25/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-Z505LS (with
updated BIOS) */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0209Z3"),
- DMI_MATCH(DMI_BIOS_DATE, "05/12/01"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-F104K */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0204K2"),
- DMI_MATCH(DMI_BIOS_DATE, "08/28/00"), },
- },
-
- { /* Handle problems with APM on Sony Vaio PCG-C1VN/C1VE */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0208P1"),
- DMI_MATCH(DMI_BIOS_DATE, "11/09/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-C1VE */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "R0204P1"),
- DMI_MATCH(DMI_BIOS_DATE, "09/12/00"), },
- },
- { /* Handle problems with APM on Sony Vaio PCG-C1VE */
- swab_apm_power_in_minutes, "Sony VAIO",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "WXPO1Z3"),
- DMI_MATCH(DMI_BIOS_DATE, "10/26/01"), },
- },
- { /* broken PM poweroff bios */
- set_realmode_power_off, "Award Software v4.60 PGMA",
- { DMI_MATCH(DMI_BIOS_VENDOR, "Award Software
International, Inc."),
- DMI_MATCH(DMI_BIOS_VERSION, "4.60 PGMA"),
- DMI_MATCH(DMI_BIOS_DATE, "134526184"), },
- },
-
- /* Generic per vendor APM settings */
-
- { /* Allow interrupts during suspend on IBM laptops */
- set_apm_ints, "IBM",
- { DMI_MATCH(DMI_SYS_VENDOR, "IBM"), },
- },
-
- { }
-};
-
-/*
- * Just start the APM thread. We do NOT want to do APM BIOS
- * calls from anything but the APM thread, if for no other reason
- * than the fact that we don't trust the APM BIOS. This way,
- * most common APM BIOS problems that lead to protection errors
- * etc will have at least some level of being contained...
- *
- * In short, if something bad happens, at least we have a choice
- * of just killing the apm thread..
- */
-static int __init apm_init(void)
-{
- struct proc_dir_entry *apm_proc;
- int ret;
- int i;
-
- dmi_check_system(apm_dmi_table);
-
- if (apm_info.bios.version == 0) {
- printk(KERN_INFO "apm: BIOS not found.\n");
- return -ENODEV;
- }
- printk(KERN_INFO
- "apm: BIOS version %d.%d Flags 0x%02x (Driver version %s)\n",
- ((apm_info.bios.version >> 8) & 0xff),
- (apm_info.bios.version & 0xff),
- apm_info.bios.flags,
- driver_version);
- if ((apm_info.bios.flags & APM_32_BIT_SUPPORT) == 0) {
- printk(KERN_INFO "apm: no 32 bit BIOS support\n");
- return -ENODEV;
- }
-
- if (allow_ints)
- apm_info.allow_ints = 1;
- if (broken_psr)
- apm_info.get_power_status_broken = 1;
- if (realmode_power_off)
- apm_info.realmode_power_off = 1;
- /* User can override, but default is to trust DMI */
- if (apm_disabled != -1)
- apm_info.disabled = apm_disabled;
-
- /*
- * Fix for the Compaq Contura 3/25c which reports BIOS version 0.1
- * but is reportedly a 1.0 BIOS.
- */
- if (apm_info.bios.version == 0x001)
- apm_info.bios.version = 0x100;
-
- /* BIOS < 1.2 doesn't set cseg_16_len */
- if (apm_info.bios.version < 0x102)
- apm_info.bios.cseg_16_len = 0; /* 64k */
-
- if (debug) {
- printk(KERN_INFO "apm: entry %x:%lx cseg16 %x dseg %x",
- apm_info.bios.cseg, apm_info.bios.offset,
- apm_info.bios.cseg_16, apm_info.bios.dseg);
- if (apm_info.bios.version > 0x100)
- printk(" cseg len %x, dseg len %x",
- apm_info.bios.cseg_len,
- apm_info.bios.dseg_len);
- if (apm_info.bios.version > 0x101)
- printk(" cseg16 len %x", apm_info.bios.cseg_16_len);
- printk("\n");
- }
-
- if (apm_info.disabled) {
- printk(KERN_NOTICE "apm: disabled on user request.\n");
- return -ENODEV;
- }
- if ((num_online_cpus() > 1) && !power_off && !smp) {
- printk(KERN_NOTICE "apm: disabled - APM is not SMP safe.\n");
- apm_info.disabled = 1;
- return -ENODEV;
- }
- if (PM_IS_ACTIVE()) {
- printk(KERN_NOTICE "apm: overridden by ACPI.\n");
- apm_info.disabled = 1;
- return -ENODEV;
- }
- pm_active = 1;
-
- /*
- * Set up a segment that references the real mode segment 0x40
- * that extends up to the end of page zero (that we have reserved).
- * This is for buggy BIOS's that refer to (real mode) segment 0x40
- * even though they are called in protected mode.
- */
- set_base(bad_bios_desc, __va((unsigned long)0x40 << 4));
- _set_limit((char *)&bad_bios_desc, 4095 - (0x40 << 4));
-
- apm_bios_entry.offset = apm_info.bios.offset;
- apm_bios_entry.segment = APM_CS;
-
- for (i = 0; i < NR_CPUS; i++) {
- set_base(get_cpu_gdt_table(i)[APM_CS >> 3],
- __va((unsigned long)apm_info.bios.cseg << 4));
- set_base(get_cpu_gdt_table(i)[APM_CS_16 >> 3],
- __va((unsigned long)apm_info.bios.cseg_16 << 4));
- set_base(get_cpu_gdt_table(i)[APM_DS >> 3],
- __va((unsigned long)apm_info.bios.dseg << 4));
-#ifndef APM_RELAX_SEGMENTS
- if (apm_info.bios.version == 0x100) {
-#endif
- /* For ASUS motherboard, Award BIOS rev 110 (and
others?) */
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS >> 3],
64 * 1024 - 1);
- /* For some unknown machine. */
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS_16 >>
3], 64 * 1024 - 1);
- /* For the DEC Hinote Ultra CT475 (and others?) */
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_DS >> 3],
64 * 1024 - 1);
-#ifndef APM_RELAX_SEGMENTS
- } else {
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS >> 3],
- (apm_info.bios.cseg_len - 1) & 0xffff);
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS_16 >>
3],
- (apm_info.bios.cseg_16_len - 1) & 0xffff);
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_DS >> 3],
- (apm_info.bios.dseg_len - 1) & 0xffff);
- /* workaround for broken BIOSes */
- if (apm_info.bios.cseg_len <= apm_info.bios.offset)
- _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS
>> 3], 64 * 1024 -1);
- if (apm_info.bios.dseg_len <= 0x40) { /* 0x40 * 4kB ==
64kB */
- /* for the BIOS that assumes granularity = 1 */
- get_cpu_gdt_table(i)[APM_DS >> 3].b |= 0x800000;
- printk(KERN_NOTICE "apm: we set the granularity
of dseg.\n");
- }
- }
-#endif
- }
-
- apm_proc = create_proc_info_entry("apm", 0, NULL, apm_get_info);
- if (apm_proc)
- apm_proc->owner = THIS_MODULE;
-
- ret = kernel_thread(apm, NULL, CLONE_KERNEL | SIGCHLD);
- if (ret < 0) {
- printk(KERN_ERR "apm: disabled - Unable to start kernel
thread.\n");
- return -ENOMEM;
- }
-
- if (num_online_cpus() > 1 && !smp ) {
- printk(KERN_NOTICE
- "apm: disabled - APM is not SMP safe (power off active).\n");
- return 0;
- }
-
- misc_register(&apm_device);
-
- if (HZ != 100)
- idle_period = (idle_period * HZ) / 100;
- if (idle_threshold < 100) {
- original_pm_idle = pm_idle;
- pm_idle = apm_cpu_idle;
- set_pm_idle = 1;
- }
-
- return 0;
-}
-
-static void __exit apm_exit(void)
-{
- int error;
-
- if (set_pm_idle) {
- pm_idle = original_pm_idle;
- /*
- * We are about to unload the current idle thread pm callback
- * (pm_idle), Wait for all processors to update cached/local
- * copies of pm_idle before proceeding.
- */
- cpu_idle_wait();
- }
- if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0)
- && (apm_info.connection_version > 0x0100)) {
- error = apm_engage_power_management(APM_DEVICE_ALL, 0);
- if (error)
- apm_error("disengage power management", error);
- }
- misc_deregister(&apm_device);
- remove_proc_entry("apm", NULL);
- if (power_off)
- pm_power_off = NULL;
- exit_kapmd = 1;
- while (kapmd_running)
- schedule();
- pm_active = 0;
-}
-
-module_init(apm_init);
-module_exit(apm_exit);
-
-MODULE_AUTHOR("Stephen Rothwell");
-MODULE_DESCRIPTION("Advanced Power Management");
-MODULE_LICENSE("GPL");
-module_param(debug, bool, 0644);
-MODULE_PARM_DESC(debug, "Enable debug mode");
-module_param(power_off, bool, 0444);
-MODULE_PARM_DESC(power_off, "Enable power off");
-module_param(bounce_interval, int, 0444);
-MODULE_PARM_DESC(bounce_interval,
- "Set the number of ticks to ignore suspend bounces");
-module_param(allow_ints, bool, 0444);
-MODULE_PARM_DESC(allow_ints, "Allow interrupts during BIOS calls");
-module_param(broken_psr, bool, 0444);
-MODULE_PARM_DESC(broken_psr, "BIOS has a broken GetPowerStatus call");
-module_param(realmode_power_off, bool, 0444);
-MODULE_PARM_DESC(realmode_power_off,
- "Switch to real mode before powering off");
-module_param(idle_threshold, int, 0444);
-MODULE_PARM_DESC(idle_threshold,
- "System idle percentage above which to make APM BIOS idle calls");
-module_param(idle_period, int, 0444);
-MODULE_PARM_DESC(idle_period,
- "Period (in sec/100) over which to caculate the idle percentage");
-module_param(smp, bool, 0444);
-MODULE_PARM_DESC(smp,
- "Set this to enable APM use on an SMP platform. Use with caution on
older systems");
-MODULE_ALIAS_MISCDEV(APM_MINOR_DEV);
diff -r d609de73b9fa -r 5a63f675107c
linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/io_ports.h
--- a/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/io_ports.h Wed Feb
1 17:06:16 2006
+++ /dev/null Wed Feb 1 18:00:19 2006
@@ -1,30 +0,0 @@
-/*
- * arch/i386/mach-generic/io_ports.h
- *
- * Machine specific IO port address definition for generic.
- * Written by Osamu Tomita <tomita@xxxxxxxxxxx>
- */
-#ifndef _MACH_IO_PORTS_H
-#define _MACH_IO_PORTS_H
-
-/* i8253A PIT registers */
-#define PIT_MODE 0x43
-#define PIT_CH0 0x40
-#define PIT_CH2 0x42
-
-/* i8259A PIC registers */
-#define PIC_MASTER_CMD 0x20
-#define PIC_MASTER_IMR 0x21
-#define PIC_MASTER_ISR PIC_MASTER_CMD
-#define PIC_MASTER_POLL PIC_MASTER_ISR
-#define PIC_MASTER_OCW3 PIC_MASTER_ISR
-#define PIC_SLAVE_CMD 0xa0
-#define PIC_SLAVE_IMR 0xa1
-
-/* i8259A PIC related value */
-#define PIC_CASCADE_IR 2
-#define MASTER_ICW4_DEFAULT 0x01
-#define SLAVE_ICW4_DEFAULT 0x01
-#define PIC_ICW4_AEOI 2
-
-#endif /* !_MACH_IO_PORTS_H */
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home