From 864d0ec9db9c0c18b79cebb9d8b7ac75c3b70571 Mon Sep 17 00:00:00 2001 From: Thomas Kunze Date: Mon, 19 May 2008 22:06:51 +0100 Subject: [ARM] 5025/2: fix collie cpu initialisation collie.h: * add some meaningfull names to some gpios collie.c: * initialize cpu registers correctly Signed-off-by: Thomas Kunze Signed-off-by: Russell King --- include/asm-arm/arch-sa1100/collie.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/asm-arm/arch-sa1100/collie.h b/include/asm-arm/arch-sa1100/collie.h index 14a344aa3cc7..762eba535813 100644 --- a/include/asm-arm/arch-sa1100/collie.h +++ b/include/asm-arm/arch-sa1100/collie.h @@ -34,9 +34,12 @@ #define COLLIE_GPIO_ON_KEY GPIO_GPIO (0) #define COLLIE_GPIO_AC_IN GPIO_GPIO (1) +#define COLLIE_GPIO_SDIO_INT GPIO_GPIO (11) #define COLLIE_GPIO_CF_IRQ GPIO_GPIO (14) #define COLLIE_GPIO_nREMOCON_INT GPIO_GPIO (15) #define COLLIE_GPIO_UCB1x00_RESET GPIO_GPIO (16) +#define COLLIE_GPIO_nMIC_ON GPIO_GPIO (17) +#define COLLIE_GPIO_nREMOCON_ON GPIO_GPIO (18) #define COLLIE_GPIO_CO GPIO_GPIO (20) #define COLLIE_GPIO_MCP_CLK GPIO_GPIO (21) #define COLLIE_GPIO_CF_CD GPIO_GPIO (22) @@ -49,6 +52,7 @@ #define COLLIE_IRQ_GPIO_ON_KEY IRQ_GPIO0 #define COLLIE_IRQ_GPIO_AC_IN IRQ_GPIO1 +#define COLLIE_IRQ_GPIO_SDIO_IRQ IRQ_GPIO11 #define COLLIE_IRQ_GPIO_CF_IRQ IRQ_GPIO14 #define COLLIE_IRQ_GPIO_nREMOCON_INT IRQ_GPIO15 #define COLLIE_IRQ_GPIO_CO IRQ_GPIO20 -- cgit v1.2.3 From b851cb289d905ea04e5f0b518bf3f28407a72118 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 22 May 2008 16:38:50 +0100 Subject: [ARM] omap: fix omap clk support build errors arch/arm/plat-omap/clock.c:397: warning: "struct cpufreq_frequency_table" declared inside parameter list arch/arm/plat-omap/clock.c:397: warning: its scope is only this definition or declaration, which is probably not what you want arch/arm/plat-omap/clock.c: In function `clk_init_cpufreq_table': arch/arm/plat-omap/clock.c:402: error: structure has no member named `clk_init_cpufreq_table' arch/arm/plat-omap/clock.c:403: error: structure has no member named `clk_init_cpufreq_table' Signed-off-by: Russell King --- arch/arm/plat-omap/clock.c | 1 + include/asm-arm/arch-omap/clock.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c index 2946c193a7d6..2db5580048d8 100644 --- a/arch/arm/plat-omap/clock.c +++ b/arch/arm/plat-omap/clock.c @@ -21,6 +21,7 @@ #include #include #include +#include #include diff --git a/include/asm-arm/arch-omap/clock.h b/include/asm-arm/arch-omap/clock.h index 57523bdb642b..12a5e4de9518 100644 --- a/include/asm-arm/arch-omap/clock.h +++ b/include/asm-arm/arch-omap/clock.h @@ -73,6 +73,8 @@ struct clk { #endif }; +struct cpufreq_frequency_table; + struct clk_functions { int (*clk_enable)(struct clk *clk); void (*clk_disable)(struct clk *clk); @@ -83,6 +85,9 @@ struct clk_functions { void (*clk_allow_idle)(struct clk *clk); void (*clk_deny_idle)(struct clk *clk); void (*clk_disable_unused)(struct clk *clk); +#ifdef CONFIG_CPU_FREQ + void (*clk_init_cpufreq_table)(struct cpufreq_frequency_table **); +#endif }; extern unsigned int mpurate; -- cgit v1.2.3 From b9a2f2e450b0f770bb4347ae8d48eb2dea701e24 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 22 May 2008 10:48:59 -0700 Subject: netlink: Fix nla_parse_nested_compat() to call nla_parse() directly The purpose of nla_parse_nested_compat() is to parse attributes which contain a struct followed by a stream of nested attributes. So far, it called nla_parse_nested() to parse the stream of nested attributes which was wrong, as nla_parse_nested() expects a container attribute as data which holds the attribute stream. It needs to call nla_parse() directly while pointing at the next possible alignment point after the struct in the beginning of the attribute. With this patch, I can no longer reproduce the reported leftover warnings. Signed-off-by: Thomas Graf Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netlink.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index a5506c42f03c..112dcdf7e34e 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -772,12 +772,13 @@ static inline int __nla_parse_nested_compat(struct nlattr *tb[], int maxtype, const struct nla_policy *policy, int len) { - if (nla_len(nla) < len) + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len < 0) return -1; - if (nla_len(nla) >= NLA_ALIGN(len) + sizeof(struct nlattr)) - return nla_parse_nested(tb, maxtype, - nla_data(nla) + NLA_ALIGN(len), - policy); + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy); memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } -- cgit v1.2.3 From 06a901c5621f85e07e00ac4816c7ca95620ee74a Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 21 May 2008 16:24:31 +1000 Subject: [POWERPC] mpic: Fix use of uninitialized variable Compiling ppc64_defconfig with gcc 4.3 gives thes warnings: arch/powerpc/sysdev/mpic.c: In function 'mpic_irq_get_priority': arch/powerpc/sysdev/mpic.c:1351: warning: 'is_ipi' may be used uninitialized in this function arch/powerpc/sysdev/mpic.c: In function 'mpic_irq_set_priority': arch/powerpc/sysdev/mpic.c:1328: warning: 'is_ipi' may be used uninitialized in this function It turns out that in the cases where is_ipi is uninitialized, another variable (mpic) will be NULL and it is dereferenced. Protect against this by returning if mpic is NULL in mpic_irq_set_priority, and removing mpic_irq_get_priority completely as it has no in tree callers. This has the nice side effect of making the warning go away. Signed-off-by: Stephen Rothwell Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/sysdev/mpic.c | 20 +++----------------- include/asm-powerpc/mpic.h | 3 +-- 2 files changed, 4 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 8619f2a3f1f6..7680001676a6 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1331,6 +1331,9 @@ void mpic_irq_set_priority(unsigned int irq, unsigned int pri) unsigned long flags; u32 reg; + if (!mpic) + return; + spin_lock_irqsave(&mpic_lock, flags); if (is_ipi) { reg = mpic_ipi_read(src - mpic->ipi_vecs[0]) & @@ -1346,23 +1349,6 @@ void mpic_irq_set_priority(unsigned int irq, unsigned int pri) spin_unlock_irqrestore(&mpic_lock, flags); } -unsigned int mpic_irq_get_priority(unsigned int irq) -{ - unsigned int is_ipi; - struct mpic *mpic = mpic_find(irq, &is_ipi); - unsigned int src = mpic_irq_to_hw(irq); - unsigned long flags; - u32 reg; - - spin_lock_irqsave(&mpic_lock, flags); - if (is_ipi) - reg = mpic_ipi_read(src = mpic->ipi_vecs[0]); - else - reg = mpic_irq_read(src, MPIC_INFO(IRQ_VECTOR_PRI)); - spin_unlock_irqrestore(&mpic_lock, flags); - return (reg & MPIC_VECPRI_PRIORITY_MASK) >> MPIC_VECPRI_PRIORITY_SHIFT; -} - void mpic_setup_this_cpu(void) { #ifdef CONFIG_SMP diff --git a/include/asm-powerpc/mpic.h b/include/asm-powerpc/mpic.h index 943c5a3fac8a..a4d0f876b427 100644 --- a/include/asm-powerpc/mpic.h +++ b/include/asm-powerpc/mpic.h @@ -428,12 +428,11 @@ extern void mpic_init(struct mpic *mpic); */ -/* Change/Read the priority of an interrupt. Default is 8 for irqs and +/* Change the priority of an interrupt. Default is 8 for irqs and * 10 for IPIs. You can call this on both IPIs and IRQ numbers, but the * IPI number is then the offset'ed (linux irq number mapped to the IPI) */ extern void mpic_irq_set_priority(unsigned int irq, unsigned int pri); -extern unsigned int mpic_irq_get_priority(unsigned int irq); /* Setup a non-boot CPU */ extern void mpic_setup_this_cpu(void); -- cgit v1.2.3 From 289c79a4bd350e8a25065102563ad1a183d1b402 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 23 May 2008 00:22:04 -0700 Subject: vlan: Use bitmask of feature flags instead of seperate feature bits Herbert Xu points out that the use of seperate feature bits for features to be propagated to VLAN devices is going to get messy real soon. Replace the VLAN feature bits by a bitmask of feature flags to be propagated and restore the old GSO_SHIFT/MASK values. Signed-off-by: Patrick McHardy Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++---- net/8021q/vlan.c | 10 ++-------- net/8021q/vlan.h | 2 -- net/8021q/vlan_dev.c | 5 +---- 4 files changed, 8 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2b0266484c84..f27fd2009334 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -514,12 +514,10 @@ struct net_device #define NETIF_F_NETNS_LOCAL 8192 /* Does not change network namespaces */ #define NETIF_F_MULTI_QUEUE 16384 /* Has multiple TX/RX queues */ #define NETIF_F_LRO 32768 /* large receive offload */ -#define NETIF_F_VLAN_TSO 65536 /* Supports TSO for VLANs */ -#define NETIF_F_VLAN_CSUM 131072 /* Supports TX checksumming for VLANs */ /* Segmentation offload features */ -#define NETIF_F_GSO_SHIFT 20 -#define NETIF_F_GSO_MASK 0xfff00000 +#define NETIF_F_GSO_SHIFT 16 +#define NETIF_F_GSO_MASK 0xffff0000 #define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT) #define NETIF_F_UFO (SKB_GSO_UDP << NETIF_F_GSO_SHIFT) #define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT) @@ -747,6 +745,9 @@ struct net_device /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; + /* VLAN feature mask */ + unsigned long vlan_features; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 51961300b586..ab2225da0ee2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -387,14 +387,8 @@ static void vlan_transfer_features(struct net_device *dev, { unsigned long old_features = vlandev->features; - if (dev->features & NETIF_F_VLAN_TSO) { - vlandev->features &= ~VLAN_TSO_FEATURES; - vlandev->features |= dev->features & VLAN_TSO_FEATURES; - } - if (dev->features & NETIF_F_VLAN_CSUM) { - vlandev->features &= ~NETIF_F_ALL_CSUM; - vlandev->features |= dev->features & NETIF_F_ALL_CSUM; - } + vlandev->features &= ~dev->vlan_features; + vlandev->features |= dev->features & dev->vlan_features; if (old_features != vlandev->features) netdev_features_change(vlandev); diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 79625696e86a..5229a72c7ea1 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -7,8 +7,6 @@ #define VLAN_GRP_HASH_SIZE (1 << VLAN_GRP_HASH_SHIFT) #define VLAN_GRP_HASH_MASK (VLAN_GRP_HASH_SIZE - 1) -#define VLAN_TSO_FEATURES (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG) - /* Find a VLAN device by the MAC address of its Ethernet device, and * it's VLAN ID. The default configuration is to have VLAN's scope * to be box-wide, so the MAC will be ignored. The mac will only be diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b1cfbaa88db2..5d055c242ed8 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -663,10 +663,7 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); - if (real_dev->features & NETIF_F_VLAN_TSO) - dev->features |= real_dev->features & VLAN_TSO_FEATURES; - if (real_dev->features & NETIF_F_VLAN_CSUM) - dev->features |= real_dev->features & NETIF_F_ALL_CSUM; + dev->features |= real_dev->features & real_dev->vlan_features; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; -- cgit v1.2.3 From 50346e621252617a07eb800dfa3f876ccd52d534 Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Fri, 23 May 2008 07:16:52 +0100 Subject: [ARM] 5051/1: define pgtable_t for the !CONFIG_MMU case too The non-MMU case also needs the type definition of pgtable_t. So move it out of a CONFIG_MMU conditional section. Signed-off-by: Greg Ungerer Signed-off-by: Russell King --- include/asm-arm/page.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-arm/page.h b/include/asm-arm/page.h index 5c22b0112106..8e05bdb5f12f 100644 --- a/include/asm-arm/page.h +++ b/include/asm-arm/page.h @@ -179,10 +179,10 @@ typedef unsigned long pgprot_t; #endif /* STRICT_MM_TYPECHECKS */ -typedef struct page *pgtable_t; - #endif /* CONFIG_MMU */ +typedef struct page *pgtable_t; + #include #endif /* !__ASSEMBLY__ */ -- cgit v1.2.3 From 415ad1e50abcc86c235a42fbab57f2b6134412d7 Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Fri, 23 May 2008 08:31:39 +0100 Subject: [ARM] 5053/1: define before use of processor_id For the simple read_cpuid() macro case the variable processor_id has no definition on use of the macro. Add an extern for it. Move all the processor ID macros into the #ifndef __ASSEMBLEY__ block. Signed-off-by: Greg Ungerer Signed-off-by: Russell King --- include/asm-arm/system.h | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/asm-arm/system.h b/include/asm-arm/system.h index 6335de9a2bb3..514af792a598 100644 --- a/include/asm-arm/system.h +++ b/include/asm-arm/system.h @@ -48,20 +48,6 @@ #define CPUID_TCM 2 #define CPUID_TLBTYPE 3 -#ifdef CONFIG_CPU_CP15 -#define read_cpuid(reg) \ - ({ \ - unsigned int __val; \ - asm("mrc p15, 0, %0, c0, c0, " __stringify(reg) \ - : "=r" (__val) \ - : \ - : "cc"); \ - __val; \ - }) -#else -#define read_cpuid(reg) (processor_id) -#endif - /* * This is used to ensure the compiler did actually allocate the register we * asked it for some inline assembly sequences. Apparently we can't trust @@ -78,6 +64,21 @@ #include #include +#ifdef CONFIG_CPU_CP15 +#define read_cpuid(reg) \ + ({ \ + unsigned int __val; \ + asm("mrc p15, 0, %0, c0, c0, " __stringify(reg) \ + : "=r" (__val) \ + : \ + : "cc"); \ + __val; \ + }) +#else +extern unsigned int processor_id; +#define read_cpuid(reg) (processor_id) +#endif + /* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID -- cgit v1.2.3 From cfb41bf756cac168c829e27def36072dbfbe6fd0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 23 May 2008 15:38:07 +0100 Subject: [ARM] fix OMAP include loops OMAP has two include loops in its header files: asm-arm/hardware.h <- asm-arm/arch-omap/io.h <- asm-arm/arch-omap/hardware.h <- asm-arm/hardware.h asm-arm/arch-omap/board-palmte.h <- asm-arm/arch-omap/hardware.h <- asm-arm/hardware.h <- asm-arm/arch-omap/gpio.h <- asm-arm/arch-omap/board-palmte.h Circular include dependencies are dangerous since they can result in inconsistent definitions being provided to other code, especially if '#ifndef' constructs are used. Solve these by removing the offending includes, and add additional includes where necessary. Acked-by: Tony Lindgren Signed-off-by: Russell King --- include/asm-arm/arch-omap/board-palmte.h | 2 -- include/asm-arm/arch-omap/entry-macro.S | 1 + include/asm-arm/arch-omap/gpio.h | 1 - include/asm-arm/arch-omap/hardware.h | 1 - 4 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/asm-arm/arch-omap/board-palmte.h b/include/asm-arm/arch-omap/board-palmte.h index cd22035a7160..6fac2c8935be 100644 --- a/include/asm-arm/arch-omap/board-palmte.h +++ b/include/asm-arm/arch-omap/board-palmte.h @@ -14,8 +14,6 @@ #ifndef __OMAP_BOARD_PALMTE_H #define __OMAP_BOARD_PALMTE_H -#include - #define PALMTE_USBDETECT_GPIO 0 #define PALMTE_USB_OR_DC_GPIO 1 #define PALMTE_TSC_GPIO 4 diff --git a/include/asm-arm/arch-omap/entry-macro.S b/include/asm-arm/arch-omap/entry-macro.S index 74cd57221c8e..369093a45fcf 100644 --- a/include/asm-arm/arch-omap/entry-macro.S +++ b/include/asm-arm/arch-omap/entry-macro.S @@ -8,6 +8,7 @@ * warranty of any kind, whether express or implied. */ #include +#include #include #if defined(CONFIG_ARCH_OMAP1) diff --git a/include/asm-arm/arch-omap/gpio.h b/include/asm-arm/arch-omap/gpio.h index 86621a04cd8f..5ee6a49864c3 100644 --- a/include/asm-arm/arch-omap/gpio.h +++ b/include/asm-arm/arch-omap/gpio.h @@ -26,7 +26,6 @@ #ifndef __ASM_ARCH_OMAP_GPIO_H #define __ASM_ARCH_OMAP_GPIO_H -#include #include #include diff --git a/include/asm-arm/arch-omap/hardware.h b/include/asm-arm/arch-omap/hardware.h index da572092e255..91d85b3417b7 100644 --- a/include/asm-arm/arch-omap/hardware.h +++ b/include/asm-arm/arch-omap/hardware.h @@ -41,7 +41,6 @@ #include #include #endif -#include #include /* -- cgit v1.2.3 From b1979a5fda7869a790f4fd83fb06c78498d26ba1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:21:15 +0200 Subject: x86: prevent PGE flush from interruption/preemption CR4 manipulation is not protected against interrupts and preemption, but KVM uses smp_function_call to manipulate the X86_CR4_VMXE bit either from the CPU hotplug code or from the kvm_init call. We need to protect the CR4 manipulation from both interrupts and preemption. Original bug report: http://lkml.org/lkml/2008/5/7/48 Bugzilla entry: http://bugzilla.kernel.org/show_bug.cgi?id=10642 This is not a regression from 2.6.25, it's a long standing and hard to trigger bug. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/tlbflush.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h index 0c0674d94255..35c76ceb9f40 100644 --- a/include/asm-x86/tlbflush.h +++ b/include/asm-x86/tlbflush.h @@ -22,12 +22,23 @@ static inline void __native_flush_tlb(void) static inline void __native_flush_tlb_global(void) { - unsigned long cr4 = read_cr4(); + unsigned long flags; + unsigned long cr4; + /* + * Read-modify-write to CR4 - protect it from preemption and + * from interrupts. (Use the raw variant because this code can + * be called from deep inside debugging code.) + */ + raw_local_irq_save(flags); + + cr4 = read_cr4(); /* clear PGE */ write_cr4(cr4 & ~X86_CR4_PGE); /* write old PGE again and flush TLBs */ write_cr4(cr4); + + raw_local_irq_restore(flags); } static inline void __native_flush_tlb_single(unsigned long addr) -- cgit v1.2.3 From b8fdaf5a05adbf80e5a943bb3f65b46b5fb9b488 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 23 May 2008 13:04:25 -0700 Subject: i5k_amb: support Intel 5400 chipset Minor rework to support the Intel 5400 chipset. Signed-off-by: Darrick J. Wong Cc: "Mark M. Hoffman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/hwmon/i5k_amb.c | 39 ++++++++++++++++++++++++++++++++++----- include/linux/pci_ids.h | 3 +++ 2 files changed, 37 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/hwmon/i5k_amb.c b/drivers/hwmon/i5k_amb.c index 6ac5c6f53585..f9e2ed621f7b 100644 --- a/drivers/hwmon/i5k_amb.c +++ b/drivers/hwmon/i5k_amb.c @@ -111,6 +111,7 @@ struct i5k_amb_data { void __iomem *amb_mmio; struct i5k_device_attribute *attrs; unsigned int num_attrs; + unsigned long chipset_id; }; static ssize_t show_name(struct device *dev, struct device_attribute *devattr, @@ -382,7 +383,8 @@ err: return res; } -static int __devinit i5k_find_amb_registers(struct i5k_amb_data *data) +static int __devinit i5k_find_amb_registers(struct i5k_amb_data *data, + unsigned long devid) { struct pci_dev *pcidev; u32 val32; @@ -390,7 +392,7 @@ static int __devinit i5k_find_amb_registers(struct i5k_amb_data *data) /* Find AMB register memory space */ pcidev = pci_get_device(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_5000_ERR, + devid, NULL); if (!pcidev) return -ENODEV; @@ -409,6 +411,8 @@ static int __devinit i5k_find_amb_registers(struct i5k_amb_data *data) goto out; } + data->chipset_id = devid; + res = 0; out: pci_dev_put(pcidev); @@ -441,10 +445,30 @@ out: return res; } +static unsigned long i5k_channel_pci_id(struct i5k_amb_data *data, + unsigned long channel) +{ + switch (data->chipset_id) { + case PCI_DEVICE_ID_INTEL_5000_ERR: + return PCI_DEVICE_ID_INTEL_5000_FBD0 + channel; + case PCI_DEVICE_ID_INTEL_5400_ERR: + return PCI_DEVICE_ID_INTEL_5400_FBD0 + channel; + default: + BUG(); + } +} + +static unsigned long chipset_ids[] = { + PCI_DEVICE_ID_INTEL_5000_ERR, + PCI_DEVICE_ID_INTEL_5400_ERR, + 0 +}; + static int __devinit i5k_amb_probe(struct platform_device *pdev) { struct i5k_amb_data *data; struct resource *reso; + int i; int res = -ENODEV; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -452,19 +476,24 @@ static int __devinit i5k_amb_probe(struct platform_device *pdev) return -ENOMEM; /* Figure out where the AMB registers live */ - res = i5k_find_amb_registers(data); + i = 0; + do { + res = i5k_find_amb_registers(data, chipset_ids[i]); + i++; + } while (res && chipset_ids[i]); + if (res) goto err; /* Copy the DIMM presence map for the first two channels */ res = i5k_channel_probe(&data->amb_present[0], - PCI_DEVICE_ID_INTEL_5000_FBD0); + i5k_channel_pci_id(data, 0)); if (res) goto err; /* Copy the DIMM presence map for the optional second two channels */ i5k_channel_probe(&data->amb_present[2], - PCI_DEVICE_ID_INTEL_5000_FBD1); + i5k_channel_pci_id(data, 1)); /* Set up resource regions */ reso = request_mem_region(data->amb_base, data->amb_len, DRVNAME); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cf6dbd759395..342b55afb0c3 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2383,6 +2383,9 @@ #define PCI_DEVICE_ID_INTEL_ICH10_4 0x3a30 #define PCI_DEVICE_ID_INTEL_ICH10_5 0x3a60 #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f +#define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 +#define PCI_DEVICE_ID_INTEL_5400_FBD0 0x4035 +#define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 #define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_TOLAPAI_0 0x5031 #define PCI_DEVICE_ID_INTEL_TOLAPAI_1 0x5032 -- cgit v1.2.3 From 9d5437a15884bfb3429aee99f76fc014c7de039a Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Fri, 23 May 2008 13:04:26 -0700 Subject: fix parenthesis in include/asm-mips/gic.h Parenthesis fix in include/asm-mips/gic.h Signed-off-by: Mariusz Kozlowski Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-mips/gic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mips/gic.h b/include/asm-mips/gic.h index 01b2f92dc33d..3a492f225f00 100644 --- a/include/asm-mips/gic.h +++ b/include/asm-mips/gic.h @@ -330,7 +330,7 @@ #define GIC_SH_RMASK_OFS 0x0300 #define GIC_CLR_INTR_MASK(intr, val) \ - GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_RMASK_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), ((val) << ((intr) % 32)) + GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_RMASK_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), ((val) << ((intr) % 32))) /* Register Map for Local Section */ #define GIC_VPE_CTL_OFS 0x0000 -- cgit v1.2.3 From 25829b0e977a7e396b284dad0f523099394390e7 Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Fri, 23 May 2008 13:04:28 -0700 Subject: fix parenthesis in include/asm-mips/mach-au1x00/au1000.h Parenthesis fix in include/asm-mips/mach-au1x00/au1000.h Signed-off-by: Mariusz Kozlowski Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-mips/mach-au1x00/au1000.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mips/mach-au1x00/au1000.h b/include/asm-mips/mach-au1x00/au1000.h index 363a14ee0ae5..1b5064dac007 100644 --- a/include/asm-mips/mach-au1x00/au1000.h +++ b/include/asm-mips/mach-au1x00/au1000.h @@ -1036,7 +1036,7 @@ enum soc_au1200_ints { #define USBD_INTSTAT 0xB020001C # define USBDEV_INT_SOF (1 << 12) # define USBDEV_INT_HF_BIT 6 -# define USBDEV_INT_HF_MASK 0x3f << USBDEV_INT_HF_BIT) +# define USBDEV_INT_HF_MASK (0x3f << USBDEV_INT_HF_BIT) # define USBDEV_INT_CMPLT_BIT 0 # define USBDEV_INT_CMPLT_MASK (0x3f << USBDEV_INT_CMPLT_BIT) #define USBD_CONFIG 0xB0200020 -- cgit v1.2.3 From 4b6f6ce97ecc20eb8f3ece3c8370faacfe73e8c2 Mon Sep 17 00:00:00 2001 From: Ignacio García Pérez Date: Fri, 23 May 2008 13:04:28 -0700 Subject: serial: support for InstaShield IS-400 four port RS-232 PCI card MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for the InstaShield IS-400 four port RS-232 PCI card. Signed-off-by: Ignacio García Pérez Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/serial/8250_pci.c | 7 ++++++- include/linux/pci_ids.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/serial/8250_pci.c b/drivers/serial/8250_pci.c index 53fa19cf2f06..788c3559522d 100644 --- a/drivers/serial/8250_pci.c +++ b/drivers/serial/8250_pci.c @@ -2602,7 +2602,12 @@ static struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_INTASHIELD, PCI_DEVICE_ID_INTASHIELD_IS200, PCI_ANY_ID, PCI_ANY_ID, 0, 0, /* 135a.0811 */ pbn_b2_2_115200 }, - + /* + * IntaShield IS-400 + */ + { PCI_VENDOR_ID_INTASHIELD, PCI_DEVICE_ID_INTASHIELD_IS400, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, /* 135a.0dc0 */ + pbn_b2_4_115200 }, /* * Perle PCI-RAS cards */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 342b55afb0c3..9b940e644179 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1761,6 +1761,7 @@ #define PCI_VENDOR_ID_INTASHIELD 0x135a #define PCI_DEVICE_ID_INTASHIELD_IS200 0x0d80 +#define PCI_DEVICE_ID_INTASHIELD_IS400 0x0dc0 #define PCI_VENDOR_ID_QUATECH 0x135C #define PCI_DEVICE_ID_QUATECH_QSC100 0x0010 -- cgit v1.2.3 From 6c7c6afbb8c0e60d32a563cae7c6889211e9d9d8 Mon Sep 17 00:00:00 2001 From: maximilian attems Date: Fri, 23 May 2008 13:04:29 -0700 Subject: types.h: don't expose struct ustat to userspace can't be used together with because they both define struct ustat: $ cat test.c #include #include $ gcc -c test.c In file included from test.c:2: /usr/include/linux/types.h:165: error: redefinition of 'struct ustat' has been reported a while ago to debian, but seems to have been lost in cat fighting: http://bugs.debian.org/429064 Signed-off-by: maximilian attems Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/types.h b/include/linux/types.h index 9dc2346627b4..d4a9ce6e2760 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -197,8 +197,6 @@ typedef u64 resource_size_t; typedef u32 resource_size_t; #endif -#endif /* __KERNEL__ */ - struct ustat { __kernel_daddr_t f_tfree; __kernel_ino_t f_tinode; @@ -206,4 +204,6 @@ struct ustat { char f_fpack[6]; }; +#endif /* __KERNEL__ */ + #endif /* _LINUX_TYPES_H */ -- cgit v1.2.3 From 80119ef5c8153e0a6cc5edf00c083dc98a9bd348 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 23 May 2008 13:04:31 -0700 Subject: mm: fix atomic_t overflow in vm The atomic_t type is 32bit but a 64bit system can have more than 2^32 pages of virtual address space available. Without this we overflow on ludicrously large mappings Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_misc.c | 2 +- include/linux/mman.h | 4 ++-- mm/mmap.c | 4 ++-- mm/nommu.c | 4 ++-- mm/swap.c | 4 ++-- 5 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 74a323d2b850..32dc14cd8900 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -139,7 +139,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off, #define K(x) ((x) << (PAGE_SHIFT - 10)) si_meminfo(&i); si_swapinfo(&i); - committed = atomic_read(&vm_committed_space); + committed = atomic_long_read(&vm_committed_space); allowed = ((totalram_pages - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100) + total_swap_pages; diff --git a/include/linux/mman.h b/include/linux/mman.h index 87920a0852a3..dab8892e6ff1 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -17,14 +17,14 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; -extern atomic_t vm_committed_space; +extern atomic_long_t vm_committed_space; #ifdef CONFIG_SMP extern void vm_acct_memory(long pages); #else static inline void vm_acct_memory(long pages) { - atomic_add(pages, &vm_committed_space); + atomic_long_add(pages, &vm_committed_space); } #endif diff --git a/mm/mmap.c b/mm/mmap.c index fac66337da2a..669499e7c2f5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -80,7 +80,7 @@ EXPORT_SYMBOL(vm_get_page_prot); int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; -atomic_t vm_committed_space = ATOMIC_INIT(0); +atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0); /* * Check that a process has enough memory to allocate a new virtual @@ -177,7 +177,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * cast `allowed' as a signed long because vm_committed_space * sometimes has a negative value */ - if (atomic_read(&vm_committed_space) < (long)allowed) + if (atomic_long_read(&vm_committed_space) < (long)allowed) return 0; error: vm_unacct_memory(pages); diff --git a/mm/nommu.c b/mm/nommu.c index ef8c62cec697..dca93fcb8b7a 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -39,7 +39,7 @@ struct page *mem_map; unsigned long max_mapnr; unsigned long num_physpages; unsigned long askedalloc, realalloc; -atomic_t vm_committed_space = ATOMIC_INIT(0); +atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0); int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; @@ -1410,7 +1410,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * cast `allowed' as a signed long because vm_committed_space * sometimes has a negative value */ - if (atomic_read(&vm_committed_space) < (long)allowed) + if (atomic_long_read(&vm_committed_space) < (long)allowed) return 0; error: vm_unacct_memory(pages); diff --git a/mm/swap.c b/mm/swap.c index 91e194445a5e..45c9f25a8a3b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -503,7 +503,7 @@ void vm_acct_memory(long pages) local = &__get_cpu_var(committed_space); *local += pages; if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) { - atomic_add(*local, &vm_committed_space); + atomic_long_add(*local, &vm_committed_space); *local = 0; } preempt_enable(); @@ -520,7 +520,7 @@ static int cpu_swap_callback(struct notifier_block *nfb, committed = &per_cpu(committed_space, (long)hcpu); if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { - atomic_add(*committed, &vm_committed_space); + atomic_long_add(*committed, &vm_committed_space); *committed = 0; drain_cpu_pagevecs((long)hcpu); } -- cgit v1.2.3 From 03de250a269bfa8e6a9e6ccb4a1dbce19dae8a61 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 23 May 2008 13:04:33 -0700 Subject: md: proper extern for mdp_major This patch adds a proper extern for mdp_major in include/linux/raid/md.h Signed-off-by: Adrian Bunk Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md.h | 2 ++ init/do_mounts_md.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index 81a1a02d4566..b7386ae9d288 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -72,6 +72,8 @@ */ #define MD_PATCHLEVEL_VERSION 3 +extern int mdp_major; + extern int register_md_personality (struct mdk_personality *p); extern int unregister_md_personality (struct mdk_personality *p); extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev), diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 7473b0c59d4d..693d24694a6c 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -24,7 +24,6 @@ static struct { static int md_setup_ents __initdata; -extern int mdp_major; /* * Parse the command-line parameters given our kernel, but do not * actually try to invoke the MD device now; that is handled by -- cgit v1.2.3 From 6bcfd601861cce45ca73ac1d714f1286b6b3f0d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 May 2008 13:04:34 -0700 Subject: md: kill file_path wrapper Kill the trivial and rather pointless file_path wrapper around d_path. Signed-off-by: Christoph Hellwig Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/bitmap.c | 17 ++++------------- drivers/md/md.c | 4 ++-- include/linux/raid/bitmap.h | 1 - 3 files changed, 6 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index c14dacdacfac..b26927ce889c 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -203,17 +203,6 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) * bitmap file handling - read and write the bitmap file and its superblock */ -/* copy the pathname of a file to a buffer */ -char *file_path(struct file *file, char *buf, int count) -{ - if (!buf) - return NULL; - - buf = d_path(&file->f_path, buf, count); - - return IS_ERR(buf) ? NULL : buf; -} - /* * basic page I/O operations */ @@ -721,11 +710,13 @@ static void bitmap_file_kick(struct bitmap *bitmap) if (bitmap->file) { path = kmalloc(PAGE_SIZE, GFP_KERNEL); if (path) - ptr = file_path(bitmap->file, path, PAGE_SIZE); + ptr = d_path(&bitmap->file->f_path, path, + PAGE_SIZE); + printk(KERN_ALERT "%s: kicking failed bitmap file %s from array!\n", - bmname(bitmap), ptr ? ptr : ""); + bmname(bitmap), IS_ERR(ptr) ? "" : ptr); kfree(path); } else diff --git a/drivers/md/md.c b/drivers/md/md.c index 83eb78b00137..d31aa6f33a6a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3987,8 +3987,8 @@ static int get_bitmap_file(mddev_t * mddev, void __user * arg) if (!buf) goto out; - ptr = file_path(mddev->bitmap->file, buf, sizeof(file->pathname)); - if (!ptr) + ptr = d_path(&mddev->bitmap->file->f_path, buf, sizeof(file->pathname)); + if (IS_ERR(ptr)) goto out; strcpy(file->pathname, ptr); diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 47fbcba11850..78bfdea24a8e 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -262,7 +262,6 @@ int bitmap_create(mddev_t *mddev); void bitmap_flush(mddev_t *mddev); void bitmap_destroy(mddev_t *mddev); -char *file_path(struct file *file, char *buf, int count); void bitmap_print_sb(struct bitmap *bitmap); void bitmap_update_sb(struct bitmap *bitmap); -- cgit v1.2.3 From 90b08710e41a07d4ff0fb8940dcce3a552991a56 Mon Sep 17 00:00:00 2001 From: Bernd Schubert Date: Fri, 23 May 2008 13:04:38 -0700 Subject: md: allow parallel resync of md-devices. In some configurations, a raid6 resync can be limited by CPU speed (Calculating P and Q and moving data) rather than by device speed. In these cases there is nothing to be gained byt serialising resync of arrays that share a device, and doing the resync in parallel can provide benefit. So add a sysfs tunable to flag an array as being allowed to resync in parallel with other arrays that use (a different part of) the same device. Signed-off-by: Bernd Schubert Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/md.c | 40 ++++++++++++++++++++++++++++++++++++---- include/linux/raid/md_k.h | 3 +++ 2 files changed, 39 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/md/md.c b/drivers/md/md.c index e57213dacd25..295be1a68806 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -74,6 +74,8 @@ static DEFINE_SPINLOCK(pers_lock); static void md_print_devices(void); +static DECLARE_WAIT_QUEUE_HEAD(resync_wait); + #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); } /* @@ -3012,6 +3014,36 @@ degraded_show(mddev_t *mddev, char *page) } static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded); +static ssize_t +sync_force_parallel_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%d\n", mddev->parallel_resync); +} + +static ssize_t +sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len) +{ + long n; + + if (strict_strtol(buf, 10, &n)) + return -EINVAL; + + if (n != 0 && n != 1) + return -EINVAL; + + mddev->parallel_resync = n; + + if (mddev->sync_thread) + wake_up(&resync_wait); + + return len; +} + +/* force parallel resync, even with shared block devices */ +static struct md_sysfs_entry md_sync_force_parallel = +__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR, + sync_force_parallel_show, sync_force_parallel_store); + static ssize_t sync_speed_show(mddev_t *mddev, char *page) { @@ -3187,6 +3219,7 @@ static struct attribute *md_redundancy_attrs[] = { &md_sync_min.attr, &md_sync_max.attr, &md_sync_speed.attr, + &md_sync_force_parallel.attr, &md_sync_completed.attr, &md_max_sync.attr, &md_suspend_lo.attr, @@ -5487,8 +5520,6 @@ void md_allow_write(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_allow_write); -static DECLARE_WAIT_QUEUE_HEAD(resync_wait); - #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) void md_do_sync(mddev_t *mddev) @@ -5552,8 +5583,9 @@ void md_do_sync(mddev_t *mddev) for_each_mddev(mddev2, tmp) { if (mddev2 == mddev) continue; - if (mddev2->curr_resync && - match_mddev_units(mddev,mddev2)) { + if (!mddev->parallel_resync + && mddev2->curr_resync + && match_mddev_units(mddev, mddev2)) { DEFINE_WAIT(wq); if (mddev < mddev2 && mddev->curr_resync == 2) { /* arbitrarily yield */ diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 812ffa590cff..a6d7ab688ede 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -180,6 +180,9 @@ struct mddev_s int sync_speed_min; int sync_speed_max; + /* resync even though the same disks are shared among md-devices */ + int parallel_resync; + int ok_start_degraded; /* recovery/resync flags * NEEDED: we might need to start a resync/recover -- cgit v1.2.3 From dfc7064500061677720fa26352963c772d3ebe6b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 23 May 2008 13:04:39 -0700 Subject: md: restart recovery cleanly after device failure. When we get any IO error during a recovery (rebuilding a spare), we abort the recovery and restart it. For RAID6 (and multi-drive RAID1) it may not be best to restart at the beginning: when multiple failures can be tolerated, the recovery may be able to continue and re-doing all that has already been done doesn't make sense. We already have the infrastructure to record where a recovery is up to and restart from there, but it is not being used properly. This is because: - We sometimes abort with MD_RECOVERY_ERR rather than just MD_RECOVERY_INTR, which causes the recovery not be be checkpointed. - We remove spares and then re-added them which loses important state information. The distinction between MD_RECOVERY_ERR and MD_RECOVERY_INTR really isn't needed. If there is an error, the relevant drive will be marked as Faulty, and that is enough to ensure correct handling of the error. So we first remove MD_RECOVERY_ERR, changing some of the uses of it to MD_RECOVERY_INTR. Then we cause the attempt to remove a non-faulty device from an array to fail (unless recovery is impossible as the array is too degraded). Then when remove_and_add_spares attempts to remove the devices on which recovery can continue, it will fail, they will remain in place, and recovery will continue on them as desired. Issue: If we are halfway through rebuilding a spare and another drive fails, and a new spare is immediately available, do we want to: 1/ complete the current rebuild, then go back and rebuild the new spare or 2/ restart the rebuild from the start and rebuild both devices in parallel. Both options can be argued for. The code currently takes option 2 as a/ this requires least code change b/ this results in a minimally-degraded array in minimal time. Cc: "Eivind Sarto" Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/md.c | 22 +++++++++++----------- drivers/md/multipath.c | 3 ++- drivers/md/raid1.c | 10 +++++++++- drivers/md/raid10.c | 14 ++++++++++++-- drivers/md/raid5.c | 10 +++++++++- include/linux/raid/md_k.h | 4 +--- 6 files changed, 44 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/md/md.c b/drivers/md/md.c index 295be1a68806..51c19f86ff99 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5434,7 +5434,7 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok) atomic_sub(blocks, &mddev->recovery_active); wake_up(&mddev->recovery_wait); if (!ok) { - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread(mddev->thread); // stop recovery, signal do_sync .... } @@ -5690,7 +5690,7 @@ void md_do_sync(mddev_t *mddev) sectors = mddev->pers->sync_request(mddev, j, &skipped, currspeed < speed_min(mddev)); if (sectors == 0) { - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); goto out; } @@ -5713,8 +5713,7 @@ void md_do_sync(mddev_t *mddev) last_check = io_sectors; - if (test_bit(MD_RECOVERY_INTR, &mddev->recovery) || - test_bit(MD_RECOVERY_ERR, &mddev->recovery)) + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; repeat: @@ -5768,8 +5767,7 @@ void md_do_sync(mddev_t *mddev) /* tell personality that we are finished */ mddev->pers->sync_request(mddev, max_sectors, &skipped, 1); - if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) && - !test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && + if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && mddev->curr_resync > 2) { if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { @@ -5838,7 +5836,10 @@ static int remove_and_add_spares(mddev_t *mddev) } if (mddev->degraded) { - rdev_for_each(rdev, rtmp, mddev) + rdev_for_each(rdev, rtmp, mddev) { + if (rdev->raid_disk >= 0 && + !test_bit(In_sync, &rdev->flags)) + spares++; if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { rdev->recovery_offset = 0; @@ -5856,6 +5857,7 @@ static int remove_and_add_spares(mddev_t *mddev) } else break; } + } } return spares; } @@ -5869,7 +5871,7 @@ static int remove_and_add_spares(mddev_t *mddev) * to do that as needed. * When it is determined that resync is needed, we set MD_RECOVERY_RUNNING in * "->recovery" and create a thread at ->sync_thread. - * When the thread finishes it sets MD_RECOVERY_DONE (and might set MD_RECOVERY_ERR) + * When the thread finishes it sets MD_RECOVERY_DONE * and wakeups up this thread which will reap the thread and finish up. * This thread also removes any faulty devices (with nr_pending == 0). * @@ -5944,8 +5946,7 @@ void md_check_recovery(mddev_t *mddev) /* resync has finished, collect result */ md_unregister_thread(mddev->sync_thread); mddev->sync_thread = NULL; - if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) && - !test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { + if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* success...*/ /* activate any spares */ mddev->pers->spare_active(mddev); @@ -5969,7 +5970,6 @@ void md_check_recovery(mddev_t *mddev) * might be left set */ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - clear_bit(MD_RECOVERY_ERR, &mddev->recovery); clear_bit(MD_RECOVERY_INTR, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 4f4d1f383842..e968116e0de9 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -327,7 +327,8 @@ static int multipath_remove_disk(mddev_t *mddev, int number) if (rdev) { if (test_bit(In_sync, &rdev->flags) || atomic_read(&rdev->nr_pending)) { - printk(KERN_ERR "hot-remove-disk, slot %d is identified" " but is still operational!\n", number); + printk(KERN_ERR "hot-remove-disk, slot %d is identified" + " but is still operational!\n", number); err = -EBUSY; goto abort; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d0f4021bbc2e..c610b947218a 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1027,7 +1027,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) /* * if recovery is running, make sure it aborts. */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); } else set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -1148,6 +1148,14 @@ static int raid1_remove_disk(mddev_t *mddev, int number) err = -EBUSY; goto abort; } + /* Only remove non-faulty devices is recovery + * is not possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + mddev->degraded < conf->raid_disks) { + err = -EBUSY; + goto abort; + } p->rdev = NULL; synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 8536ede1e712..1de17da34a95 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1020,7 +1020,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) /* * if recovery is running, make sure it aborts. */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); } set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -1171,6 +1171,14 @@ static int raid10_remove_disk(mddev_t *mddev, int number) err = -EBUSY; goto abort; } + /* Only remove faulty devices in recovery + * is not possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + enough(conf)) { + err = -EBUSY; + goto abort; + } p->rdev = NULL; synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { @@ -1237,6 +1245,7 @@ static void end_sync_write(struct bio *bio, int error) if (!uptodate) md_error(mddev, conf->mirrors[d].rdev); + update_head_pos(i, r10_bio); while (atomic_dec_and_test(&r10_bio->remaining)) { @@ -1844,7 +1853,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i if (rb2) atomic_dec(&rb2->remaining); r10_bio = rb2; - if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery)) + if (!test_and_set_bit(MD_RECOVERY_INTR, + &mddev->recovery)) printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n", mdname(mddev)); break; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2f28745dacf9..425958a76b84 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1268,7 +1268,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) /* * if recovery was running, make sure it aborts. */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); } set_bit(Faulty, &rdev->flags); printk (KERN_ALERT @@ -4574,6 +4574,14 @@ static int raid5_remove_disk(mddev_t *mddev, int number) err = -EBUSY; goto abort; } + /* Only remove non-faulty devices if recovery + * isn't possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + mddev->degraded <= conf->max_degraded) { + err = -EBUSY; + goto abort; + } p->rdev = NULL; synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index a6d7ab688ede..3dea9f545c8f 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -188,8 +188,7 @@ struct mddev_s * NEEDED: we might need to start a resync/recover * RUNNING: a thread is running, or about to be started * SYNC: actually doing a resync, not a recovery - * ERR: and IO error was detected - abort the resync/recovery - * INTR: someone requested a (clean) early abort. + * INTR: resync needs to be aborted for some reason * DONE: thread is done and is waiting to be reaped * REQUEST: user-space has requested a sync (used with SYNC) * CHECK: user-space request for for check-only, no repair @@ -199,7 +198,6 @@ struct mddev_s */ #define MD_RECOVERY_RUNNING 0 #define MD_RECOVERY_SYNC 1 -#define MD_RECOVERY_ERR 2 #define MD_RECOVERY_INTR 3 #define MD_RECOVERY_DONE 4 #define MD_RECOVERY_NEEDED 5 -- cgit v1.2.3 From cdc83ae2453ddb19060e05e6afd22b1254128c42 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 23 May 2008 13:04:53 -0700 Subject: SM501: reverse FPEN/VBIASEN flags behaviour To keep backwards compatibility, reverse the meanings of these flags so that when they are not set, the driver uses the original behvaiour. Signed-off-by: Ben Dooks Cc: Arnaud Patard Acked-by: Krzysztof Helt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/sm501fb.c | 8 ++++---- include/linux/sm501.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/video/sm501fb.c b/drivers/video/sm501fb.c index 742b5c656d66..15d4a768b1f6 100644 --- a/drivers/video/sm501fb.c +++ b/drivers/video/sm501fb.c @@ -663,14 +663,14 @@ static void sm501fb_panel_power(struct sm501fb_info *fbi, int to) sm501fb_sync_regs(fbi); mdelay(10); - if (pd->flags & SM501FB_FLAG_PANEL_USE_VBIASEN) { + if (!(pd->flags & SM501FB_FLAG_PANEL_NO_VBIASEN)) { control |= SM501_DC_PANEL_CONTROL_BIAS; /* VBIASEN */ writel(control, ctrl_reg); sm501fb_sync_regs(fbi); mdelay(10); } - if (pd->flags & SM501FB_FLAG_PANEL_USE_FPEN) { + if (!(pd->flags & SM501FB_FLAG_PANEL_NO_FPEN)) { control |= SM501_DC_PANEL_CONTROL_FPEN; writel(control, ctrl_reg); sm501fb_sync_regs(fbi); @@ -678,14 +678,14 @@ static void sm501fb_panel_power(struct sm501fb_info *fbi, int to) } } else if (!to && (control & SM501_DC_PANEL_CONTROL_VDD) != 0) { /* disable panel power */ - if (pd->flags & SM501FB_FLAG_PANEL_USE_FPEN) { + if (!(pd->flags & SM501FB_FLAG_PANEL_NO_FPEN)) { control &= ~SM501_DC_PANEL_CONTROL_FPEN; writel(control, ctrl_reg); sm501fb_sync_regs(fbi); mdelay(10); } - if (pd->flags & SM501FB_FLAG_PANEL_USE_VBIASEN) { + if (!(pd->flags & SM501FB_FLAG_PANEL_NO_VBIASEN)) { control &= ~SM501_DC_PANEL_CONTROL_BIAS; writel(control, ctrl_reg); sm501fb_sync_regs(fbi); diff --git a/include/linux/sm501.h b/include/linux/sm501.h index bca134544700..95c1c39ba445 100644 --- a/include/linux/sm501.h +++ b/include/linux/sm501.h @@ -71,8 +71,8 @@ extern unsigned long sm501_gpio_get(struct device *dev, #define SM501FB_FLAG_DISABLE_AT_EXIT (1<<1) #define SM501FB_FLAG_USE_HWCURSOR (1<<2) #define SM501FB_FLAG_USE_HWACCEL (1<<3) -#define SM501FB_FLAG_PANEL_USE_FPEN (1<<4) -#define SM501FB_FLAG_PANEL_USE_VBIASEN (1<<5) +#define SM501FB_FLAG_PANEL_NO_FPEN (1<<4) +#define SM501FB_FLAG_PANEL_NO_VBIASEN (1<<5) struct sm501_platdata_fbsub { struct fb_videomode *def_mode; -- cgit v1.2.3 From 6ea0205b56546cef782b74d9f4664ec00290a6ae Mon Sep 17 00:00:00 2001 From: David Brownell Date: Fri, 23 May 2008 13:04:58 -0700 Subject: gpio: build fixes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes various gpio-related build errors (mostly potential) reported in part by Russell King and Uwe Kleine-König. Signed-off-by: David Brownell Cc: Uwe Kleine-König Cc: Russell King Cc: Arnaud Patard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/gpio.h | 6 +++++- include/linux/gpio.h | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index ecf675a59d21..6be061d09da9 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -1,8 +1,12 @@ #ifndef _ASM_GENERIC_GPIO_H #define _ASM_GENERIC_GPIO_H +#include + #ifdef CONFIG_HAVE_GPIO_LIB +#include + /* Platforms may implement their GPIO interface with library code, * at a small performance cost for non-inlined operations and some * extra memory (for code and for per-GPIO table entries). @@ -74,7 +78,7 @@ struct gpio_chip { extern const char *gpiochip_is_requested(struct gpio_chip *chip, unsigned offset); -extern int __init __must_check gpiochip_reserve(int start, int ngpio); +extern int __must_check gpiochip_reserve(int start, int ngpio); /* add/remove chips */ extern int gpiochip_add(struct gpio_chip *chip); diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 4987a84078ef..98be6c5762b9 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -8,6 +8,9 @@ #else +#include +#include + /* * Some platforms don't support the GPIO programming interface. * -- cgit v1.2.3 From 12d15f0d51d47cec39d1d7250e81573c5cbd8b5d Mon Sep 17 00:00:00 2001 From: Fernando Luis Vazquez Cao Date: Fri, 23 May 2008 13:05:01 -0700 Subject: for_each_online_pgdat(): kerneldoc fix for_each_pgdat() was renamed to for_each_online_pgdat() and kerneldoc comments should be updated accordingly. Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c463cd8a15a4..443bc7cd8c62 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -703,7 +703,7 @@ extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** - * for_each_pgdat - helper macro to iterate over all nodes + * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat - pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ -- cgit v1.2.3 From 551dec47bb5964478db594385a896eb0d4ab2b0a Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 25 May 2008 22:50:16 -0700 Subject: sparc64: global_reg_snapshot is not for userspace global_reg_snapshot shouldn't be visible in our userspace headers. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- include/asm-sparc64/ptrace.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-sparc64/ptrace.h b/include/asm-sparc64/ptrace.h index d8a56cddf7f2..b163da79bb6d 100644 --- a/include/asm-sparc64/ptrace.h +++ b/include/asm-sparc64/ptrace.h @@ -126,6 +126,8 @@ struct sparc_trapf { #define TRACEREG32_SZ sizeof(struct pt_regs32) #define STACKFRAME32_SZ sizeof(struct sparc_stackf32) +#ifdef __KERNEL__ + struct global_reg_snapshot { unsigned long tstate; unsigned long tpc; @@ -137,8 +139,6 @@ struct global_reg_snapshot { unsigned long pad2; }; -#ifdef __KERNEL__ - #define __ARCH_WANT_COMPAT_SYS_PTRACE #define force_successful_syscall_return() \ @@ -306,6 +306,8 @@ extern void __show_regs(struct pt_regs *); #define SF_XARG5 0x58 #define SF_XXARG 0x5c +#ifdef __KERNEL__ + /* global_reg_snapshot offsets */ #define GR_SNAP_TSTATE 0x00 #define GR_SNAP_TPC 0x08 @@ -316,6 +318,8 @@ extern void __show_regs(struct pt_regs *); #define GR_SNAP_PAD1 0x30 #define GR_SNAP_PAD2 0x38 +#endif /* __KERNEL__ */ + /* Stuff for the ptrace system call */ #define PTRACE_SPARC_DETACH 11 #define PTRACE_GETREGS 12 -- cgit v1.2.3 From 2548baa07ddf37ea8604e9627f042616d1cdc43e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 26 May 2008 16:08:40 +0200 Subject: i2c: Align i2c_device_id Align i2c_device_id.driver_data to 8 bytes to not fail on crossbuilds. (Added in d2653e92732bd3911feff6bee5e23dbf959381db.) Signed-off-by: Jiri Slaby Signed-off-by: Jean Delvare --- include/linux/mod_devicetable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index d73eceaa7afb..69b2342d5ebb 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -375,7 +375,8 @@ struct virtio_device_id { struct i2c_device_id { char name[I2C_NAME_SIZE]; - kernel_ulong_t driver_data; /* Data private to the driver */ + kernel_ulong_t driver_data /* Data private to the driver */ + __attribute__((aligned(sizeof(kernel_ulong_t)))); }; -- cgit v1.2.3 From 624080eded68738daee041ad64672a9d2614754f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 6 Jun 2008 17:50:40 -0400 Subject: jbd2: If a journal checksum error is detected, propagate the error to ext4 If a journal checksum error is detected, the ext4 filesystem will call ext4_error(), and the mount will either continue, become a read-only mount, or cause a kernel panic based on the superblock flags indicating the user's preference of what to do in case of filesystem corruption being detected. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 23 +++++++++++++++++++++++ fs/jbd2/recovery.c | 11 ++++------- include/linux/jbd2.h | 3 +++ 3 files changed, 30 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 09d9359c8055..d01a32e8b50a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2189,6 +2189,29 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { if (ext4_load_journal(sb, es, journal_devnum)) goto failed_mount3; + if (!(sb->s_flags & MS_RDONLY) && + EXT4_SB(sb)->s_journal->j_failed_commit) { + printk(KERN_CRIT "EXT4-fs error (device %s): " + "ext4_fill_super: Journal transaction " + "%u is corrupt\n", sb->s_id, + EXT4_SB(sb)->s_journal->j_failed_commit); + if (test_opt (sb, ERRORS_RO)) { + printk (KERN_CRIT + "Mounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + } + if (test_opt(sb, ERRORS_PANIC)) { + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + ext4_commit_super(sb, es, 1); + printk(KERN_CRIT + "EXT4-fs (device %s): mount failed\n", + sb->s_id); + goto failed_mount4; + } + } } else if (journal_inum) { if (ext4_create_journal(sb, es, journal_inum)) goto failed_mount3; diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 7199db52b2fd..058f50f65b76 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -611,9 +611,8 @@ static int do_one_pass(journal_t *journal, chksum_err = chksum_seen = 0; if (info->end_transaction) { - printk(KERN_ERR "JBD: Transaction %u " - "found to be corrupt.\n", - next_commit_ID - 1); + journal->j_failed_commit = + info->end_transaction; brelse(bh); break; } @@ -644,10 +643,8 @@ static int do_one_pass(journal_t *journal, if (!JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){ - printk(KERN_ERR - "JBD: Transaction %u " - "found to be corrupt.\n", - next_commit_ID); + journal->j_failed_commit = + next_commit_ID; brelse(bh); break; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 05e2b307161a..d147f0f90360 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -919,6 +919,9 @@ struct journal_s struct proc_dir_entry *j_proc_entry; struct transaction_stats_s j_stats; + /* Failed journal commit ID */ + unsigned int j_failed_commit; + /* * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here -- cgit v1.2.3 From cbaffba12ce08beb3e80bfda148ee0fa14aac188 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 26 May 2008 20:55:42 +0400 Subject: posix timers: discard SI_TIMER signals on exec Based on Roland's patch. This approach was suggested by Austin Clements from the very beginning, and then by Linus. As Austin pointed out, the execing task can be killed by SI_TIMER signal because exec flushes the signal handlers, but doesn't discard the pending signals generated by posix timers. Perhaps not a bug, but people find this surprising. See http://bugzilla.kernel.org/show_bug.cgi?id=10460 Signed-off-by: Oleg Nesterov Cc: Austin Clements Cc: Roland McGrath Signed-off-by: Linus Torvalds --- fs/exec.c | 1 + include/linux/sched.h | 2 ++ kernel/signal.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 37 insertions(+) (limited to 'include') diff --git a/fs/exec.c b/fs/exec.c index 3c2ba7ce11d4..9448f1b50b4a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -860,6 +860,7 @@ static int de_thread(struct task_struct *tsk) no_thread_group: exit_itimers(sig); + flush_itimer_signals(); if (leader) release_task(leader); diff --git a/include/linux/sched.h b/include/linux/sched.h index 5395a6176f4b..3e05e5474749 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1848,7 +1848,9 @@ extern void exit_thread(void); extern void exit_files(struct task_struct *); extern void __cleanup_signal(struct signal_struct *); extern void __cleanup_sighand(struct sighand_struct *); + extern void exit_itimers(struct signal_struct *); +extern void flush_itimer_signals(void); extern NORET_TYPE void do_group_exit(int); diff --git a/kernel/signal.c b/kernel/signal.c index 2955f6c4f36e..6c0958e52ea7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -231,6 +231,40 @@ void flush_signals(struct task_struct *t) spin_unlock_irqrestore(&t->sighand->siglock, flags); } +static void __flush_itimer_signals(struct sigpending *pending) +{ + sigset_t signal, retain; + struct sigqueue *q, *n; + + signal = pending->signal; + sigemptyset(&retain); + + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } + } + + sigorsets(&pending->signal, &signal, &retain); +} + +void flush_itimer_signals(void) +{ + struct task_struct *tsk = current; + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); +} + void ignore_signals(struct task_struct *t) { int i; -- cgit v1.2.3 From 43f83a8f9963a11a9c3f41beecc363da21ae3602 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 27 May 2008 01:37:26 -0400 Subject: Input: wm9713 - support five wire panels Signed-off-by: Mark Brown Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/wm9713.c | 22 ++++++++++++++++++++++ include/linux/wm97xx.h | 1 + 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/drivers/input/touchscreen/wm9713.c b/drivers/input/touchscreen/wm9713.c index 01278bd7e65c..838458792ea0 100644 --- a/drivers/input/touchscreen/wm9713.c +++ b/drivers/input/touchscreen/wm9713.c @@ -84,6 +84,15 @@ static int delay = 4; module_param(delay, int, 0); MODULE_PARM_DESC(delay, "Set adc sample delay."); +/* + * Set five_wire = 1 to use a 5 wire touchscreen. + * + * NOTE: Five wire mode does not allow for readback of pressure. + */ +static int five_wire; +module_param(five_wire, int, 0); +MODULE_PARM_DESC(five_wire, "Set to '1' to use 5-wire touchscreen."); + /* * Set adc mask function. * @@ -162,6 +171,19 @@ static void wm9713_phy_init(struct wm97xx *wm) 64000 / rpu); } + /* Five wire panel? */ + if (five_wire) { + dig3 |= WM9713_45W; + dev_info(wm->dev, "setting 5-wire touchscreen mode."); + + if (pil) { + dev_warn(wm->dev, + "Pressure measurement not supported in 5 " + "wire mode, disabling\n"); + pil = 0; + } + } + /* touchpanel pressure */ if (pil == 2) { dig3 |= WM9712_PIL; diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 4d13732e9cf0..6f69968eab24 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -100,6 +100,7 @@ #define WM9713_ADCSEL_Y 0x0004 /* Y measurement */ #define WM9713_ADCSEL_PRES 0x0008 /* Pressure measurement */ #define WM9713_COO 0x0001 /* enable coordinate mode */ +#define WM9713_45W 0x1000 /* set for 5 wire panel */ #define WM9713_PDEN 0x0800 /* measure only when pen down */ #define WM9713_ADCSEL_MASK 0x00fe /* ADC selection mask */ #define WM9713_WAIT 0x0200 /* coordinate wait */ -- cgit v1.2.3 From 4dcc29e1574d88f4465ba865ed82800032f76418 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 27 May 2008 13:23:16 -0700 Subject: [IA64] Workaround for RSE issue Problem: An application violating the architectural rules regarding operation dependencies and having specific Register Stack Engine (RSE) state at the time of the violation, may result in an illegal operation fault and invalid RSE state. Such faults may initiate a cascade of repeated illegal operation faults within OS interruption handlers. The specific behavior is OS dependent. Implication: An application causing an illegal operation fault with specific RSE state may result in a series of illegal operation faults and an eventual OS stack overflow condition. Workaround: OS interruption handlers that switch to kernel backing store implement a check for invalid RSE state to avoid the series of illegal operation faults. The core of the workaround is the RSE_WORKAROUND code sequence inserted into each invocation of the SAVE_MIN_WITH_COVER and SAVE_MIN_WITH_COVER_R19 macros. This sequence includes hard-coded constants that depend on the number of stacked physical registers being 96. The rest of this patch consists of code to disable this workaround should this not be the case (with the presumption that if a future Itanium processor increases the number of registers, it would also remove the need for this patch). Move the start of the RBS up to a mod32 boundary to avoid some corner cases. The dispatch_illegal_op_fault code outgrew the spot it was squatting in when built with this patch and CONFIG_VIRT_CPU_ACCOUNTING=y Move it out to the end of the ivt. Signed-off-by: Tony Luck --- arch/ia64/kernel/ivt.S | 84 +++++++++++++++++++++--------------------- arch/ia64/kernel/minstate.h | 46 +++++++++++++++++++++-- arch/ia64/kernel/patch.c | 23 ++++++++++++ arch/ia64/kernel/setup.c | 11 ++++++ arch/ia64/kernel/vmlinux.lds.S | 7 ++++ include/asm-ia64/patch.h | 1 + include/asm-ia64/ptrace.h | 2 +- include/asm-ia64/sections.h | 1 + 8 files changed, 128 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S index 6678c49daba3..80b44ea052d7 100644 --- a/arch/ia64/kernel/ivt.S +++ b/arch/ia64/kernel/ivt.S @@ -1076,48 +1076,6 @@ END(ia64_syscall_setup) DBG_FAULT(15) FAULT(15) - /* - * Squatting in this space ... - * - * This special case dispatcher for illegal operation faults allows preserved - * registers to be modified through a callback function (asm only) that is handed - * back from the fault handler in r8. Up to three arguments can be passed to the - * callback function by returning an aggregate with the callback as its first - * element, followed by the arguments. - */ -ENTRY(dispatch_illegal_op_fault) - .prologue - .body - SAVE_MIN_WITH_COVER - ssm psr.ic | PSR_DEFAULT_BITS - ;; - srlz.i // guarantee that interruption collection is on - ;; -(p15) ssm psr.i // restore psr.i - adds r3=8,r2 // set up second base pointer for SAVE_REST - ;; - alloc r14=ar.pfs,0,0,1,0 // must be first in insn group - mov out0=ar.ec - ;; - SAVE_REST - PT_REGS_UNWIND_INFO(0) - ;; - br.call.sptk.many rp=ia64_illegal_op_fault -.ret0: ;; - alloc r14=ar.pfs,0,0,3,0 // must be first in insn group - mov out0=r9 - mov out1=r10 - mov out2=r11 - movl r15=ia64_leave_kernel - ;; - mov rp=r15 - mov b6=r8 - ;; - cmp.ne p6,p0=0,r8 -(p6) br.call.dpnt.many b6=b6 // call returns to ia64_leave_kernel - br.sptk.many ia64_leave_kernel -END(dispatch_illegal_op_fault) - .org ia64_ivt+0x4000 ///////////////////////////////////////////////////////////////////////////////////////// // 0x4000 Entry 16 (size 64 bundles) Reserved @@ -1715,6 +1673,48 @@ END(ia32_interrupt) DBG_FAULT(67) FAULT(67) + /* + * Squatting in this space ... + * + * This special case dispatcher for illegal operation faults allows preserved + * registers to be modified through a callback function (asm only) that is handed + * back from the fault handler in r8. Up to three arguments can be passed to the + * callback function by returning an aggregate with the callback as its first + * element, followed by the arguments. + */ +ENTRY(dispatch_illegal_op_fault) + .prologue + .body + SAVE_MIN_WITH_COVER + ssm psr.ic | PSR_DEFAULT_BITS + ;; + srlz.i // guarantee that interruption collection is on + ;; +(p15) ssm psr.i // restore psr.i + adds r3=8,r2 // set up second base pointer for SAVE_REST + ;; + alloc r14=ar.pfs,0,0,1,0 // must be first in insn group + mov out0=ar.ec + ;; + SAVE_REST + PT_REGS_UNWIND_INFO(0) + ;; + br.call.sptk.many rp=ia64_illegal_op_fault +.ret0: ;; + alloc r14=ar.pfs,0,0,3,0 // must be first in insn group + mov out0=r9 + mov out1=r10 + mov out2=r11 + movl r15=ia64_leave_kernel + ;; + mov rp=r15 + mov b6=r8 + ;; + cmp.ne p6,p0=0,r8 +(p6) br.call.dpnt.many b6=b6 // call returns to ia64_leave_kernel + br.sptk.many ia64_leave_kernel +END(dispatch_illegal_op_fault) + #ifdef CONFIG_IA32_SUPPORT /* diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h index 7c548ac52bbc..74b6d670aaef 100644 --- a/arch/ia64/kernel/minstate.h +++ b/arch/ia64/kernel/minstate.h @@ -15,6 +15,9 @@ #define ACCOUNT_SYS_ENTER #endif +.section ".data.patch.rse", "a" +.previous + /* * DO_SAVE_MIN switches to the kernel stacks (if necessary) and saves * the minimum state necessary that allows us to turn psr.ic back @@ -40,7 +43,7 @@ * Note that psr.ic is NOT turned on by this macro. This is so that * we can pass interruption state as arguments to a handler. */ -#define DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA) \ +#define DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA,WORKAROUND) \ mov r16=IA64_KR(CURRENT); /* M */ \ mov r27=ar.rsc; /* M */ \ mov r20=r1; /* A */ \ @@ -87,6 +90,7 @@ tbit.nz p15,p0=r29,IA64_PSR_I_BIT; \ mov r29=b0 \ ;; \ + WORKAROUND; \ adds r16=PT(R8),r1; /* initialize first base pointer */ \ adds r17=PT(R9),r1; /* initialize second base pointer */ \ (pKStk) mov r18=r0; /* make sure r18 isn't NaT */ \ @@ -206,6 +210,40 @@ st8 [r25]=r10; /* ar.ssd */ \ ;; -#define SAVE_MIN_WITH_COVER DO_SAVE_MIN(cover, mov r30=cr.ifs,) -#define SAVE_MIN_WITH_COVER_R19 DO_SAVE_MIN(cover, mov r30=cr.ifs, mov r15=r19) -#define SAVE_MIN DO_SAVE_MIN( , mov r30=r0, ) +#define RSE_WORKAROUND \ +(pUStk) extr.u r17=r18,3,6; \ +(pUStk) sub r16=r18,r22; \ +[1:](pKStk) br.cond.sptk.many 1f; \ + .xdata4 ".data.patch.rse",1b-. \ + ;; \ + cmp.ge p6,p7 = 33,r17; \ + ;; \ +(p6) mov r17=0x310; \ +(p7) mov r17=0x308; \ + ;; \ + cmp.leu p1,p0=r16,r17; \ +(p1) br.cond.sptk.many 1f; \ + dep.z r17=r26,0,62; \ + movl r16=2f; \ + ;; \ + mov ar.pfs=r17; \ + dep r27=r0,r27,16,14; \ + mov b0=r16; \ + ;; \ + br.ret.sptk b0; \ + ;; \ +2: \ + mov ar.rsc=r0 \ + ;; \ + flushrs; \ + ;; \ + mov ar.bspstore=r22 \ + ;; \ + mov r18=ar.bsp; \ + ;; \ +1: \ + .pred.rel "mutex", pKStk, pUStk + +#define SAVE_MIN_WITH_COVER DO_SAVE_MIN(cover, mov r30=cr.ifs, , RSE_WORKAROUND) +#define SAVE_MIN_WITH_COVER_R19 DO_SAVE_MIN(cover, mov r30=cr.ifs, mov r15=r19, RSE_WORKAROUND) +#define SAVE_MIN DO_SAVE_MIN( , mov r30=r0, , ) diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c index e0dca8743dbb..b83b2c516008 100644 --- a/arch/ia64/kernel/patch.c +++ b/arch/ia64/kernel/patch.c @@ -115,6 +115,29 @@ ia64_patch_vtop (unsigned long start, unsigned long end) ia64_srlz_i(); } +/* + * Disable the RSE workaround by turning the conditional branch + * that we tagged in each place the workaround was used into an + * unconditional branch. + */ +void __init +ia64_patch_rse (unsigned long start, unsigned long end) +{ + s32 *offp = (s32 *) start; + u64 ip, *b; + + while (offp < (s32 *) end) { + ip = (u64) offp + *offp; + + b = (u64 *)(ip & -16); + b[1] &= ~0xf800000L; + ia64_fc((void *) ip); + ++offp; + } + ia64_sync_i(); + ia64_srlz_i(); +} + void __init ia64_patch_mckinley_e9 (unsigned long start, unsigned long end) { diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index e9596cd0cdab..f48a809c686d 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -560,6 +560,17 @@ setup_arch (char **cmdline_p) /* process SAL system table: */ ia64_sal_init(__va(efi.sal_systab)); +#ifdef CONFIG_ITANIUM + ia64_patch_rse((u64) __start___rse_patchlist, (u64) __end___rse_patchlist); +#else + { + u64 num_phys_stacked; + + if (ia64_pal_rse_info(&num_phys_stacked, 0) == 0 && num_phys_stacked > 96) + ia64_patch_rse((u64) __start___rse_patchlist, (u64) __end___rse_patchlist); + } +#endif + #ifdef CONFIG_SMP cpu_physical_id(0) = hard_smp_processor_id(); #endif diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 80622acc95de..5929ab10a289 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -156,6 +156,13 @@ SECTIONS __end___vtop_patchlist = .; } + .data.patch.rse : AT(ADDR(.data.patch.rse) - LOAD_OFFSET) + { + __start___rse_patchlist = .; + *(.data.patch.rse) + __end___rse_patchlist = .; + } + .data.patch.mckinley_e9 : AT(ADDR(.data.patch.mckinley_e9) - LOAD_OFFSET) { __start___mckinley_e9_bundles = .; diff --git a/include/asm-ia64/patch.h b/include/asm-ia64/patch.h index a71543084fb4..295fe6ab4584 100644 --- a/include/asm-ia64/patch.h +++ b/include/asm-ia64/patch.h @@ -21,6 +21,7 @@ extern void ia64_patch_imm60 (u64 insn_addr, u64 val); /* patch "brl" w/ip-rel extern void ia64_patch_mckinley_e9 (unsigned long start, unsigned long end); extern void ia64_patch_vtop (unsigned long start, unsigned long end); extern void ia64_patch_phys_stack_reg(unsigned long val); +extern void ia64_patch_rse (unsigned long start, unsigned long end); extern void ia64_patch_gate (void); #endif /* _ASM_IA64_PATCH_H */ diff --git a/include/asm-ia64/ptrace.h b/include/asm-ia64/ptrace.h index 4b2a8d40ebc5..15f8dcfe6eee 100644 --- a/include/asm-ia64/ptrace.h +++ b/include/asm-ia64/ptrace.h @@ -76,7 +76,7 @@ # define KERNEL_STACK_SIZE_ORDER 0 #endif -#define IA64_RBS_OFFSET ((IA64_TASK_SIZE + IA64_THREAD_INFO_SIZE + 15) & ~15) +#define IA64_RBS_OFFSET ((IA64_TASK_SIZE + IA64_THREAD_INFO_SIZE + 31) & ~31) #define IA64_STK_OFFSET ((1 << KERNEL_STACK_SIZE_ORDER)*PAGE_SIZE) #define KERNEL_STACK_SIZE IA64_STK_OFFSET diff --git a/include/asm-ia64/sections.h b/include/asm-ia64/sections.h index dc42a359894f..7286e4a9fe84 100644 --- a/include/asm-ia64/sections.h +++ b/include/asm-ia64/sections.h @@ -10,6 +10,7 @@ extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[]; extern char __start___vtop_patchlist[], __end___vtop_patchlist[]; +extern char __start___rse_patchlist[], __end___rse_patchlist[]; extern char __start___mckinley_e9_bundles[], __end___mckinley_e9_bundles[]; extern char __start___phys_stack_reg_patchlist[], __end___phys_stack_reg_patchlist[]; extern char __start_gate_section[]; -- cgit v1.2.3 From 9d5f09a424a67ddb959829894efb4c71cbf6d600 Mon Sep 17 00:00:00 2001 From: "Alan D. Brunelle" Date: Tue, 27 May 2008 14:54:41 +0200 Subject: Added in MESSAGE notes for blktraces Allows messages to be inserted into blktrace streams. Signed-off-by: Alan D. Brunelle Signed-off-by: Jens Axboe --- block/blktrace.c | 14 ++++++++++++++ include/linux/blktrace_api.h | 25 +++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include') diff --git a/block/blktrace.c b/block/blktrace.c index b2cbb4e5d767..20e11f354f11 100644 --- a/block/blktrace.c +++ b/block/blktrace.c @@ -75,6 +75,20 @@ static void trace_note_time(struct blk_trace *bt) local_irq_restore(flags); } +void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) +{ + int n; + va_list args; + static char bt_msg_buf[BLK_TN_MAX_MSG]; + + va_start(args, fmt); + n = vscnprintf(bt_msg_buf, BLK_TN_MAX_MSG, fmt, args); + va_end(args); + + trace_note(bt, 0, BLK_TN_MESSAGE, bt_msg_buf, n); +} +EXPORT_SYMBOL_GPL(__trace_note_message); + static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) { diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cfc3147e5cf9..b7cd8f1eedbe 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -55,6 +55,7 @@ enum blktrace_act { enum blktrace_notify { __BLK_TN_PROCESS = 0, /* establish pid/name mapping */ __BLK_TN_TIMESTAMP, /* include system clock */ + __BLK_TN_MESSAGE, /* Character string message */ }; @@ -79,6 +80,7 @@ enum blktrace_notify { #define BLK_TN_PROCESS (__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY)) #define BLK_TN_TIMESTAMP (__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY)) +#define BLK_TN_MESSAGE (__BLK_TN_MESSAGE | BLK_TC_ACT(BLK_TC_NOTIFY)) #define BLK_IO_TRACE_MAGIC 0x65617400 #define BLK_IO_TRACE_VERSION 0x07 @@ -149,7 +151,28 @@ extern void blk_trace_shutdown(struct request_queue *); extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct blk_user_trace_setup *buts); +extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); +/** + * blk_add_trace_msg - Add a (simple) message to the blktrace stream + * @q: queue the io is for + * @fmt: format to print message in + * args... Variable argument list for format + * + * Description: + * Records a (simple) message onto the blktrace stream. + * + * NOTE: BLK_TN_MAX_MSG characters are output at most. + * NOTE: Can not use 'static inline' due to presence of var args... + * + **/ +#define blk_add_trace_msg(q, fmt, ...) \ + do { \ + struct blk_trace *bt = (q)->blk_trace; \ + if (unlikely(bt)) \ + __trace_note_message(bt, fmt, ##__VA_ARGS__); \ + } while (0) +#define BLK_TN_MAX_MSG 1024 /** * blk_add_trace_rq - Add a trace for a request oriented action @@ -299,6 +322,8 @@ extern int blk_trace_remove(struct request_queue *q); #define blk_trace_setup(q, name, dev, arg) (-ENOTTY) #define blk_trace_startstop(q, start) (-ENOTTY) #define blk_trace_remove(q) (-ENOTTY) +#define blk_add_trace_msg(q, fmt, ...) do { } while (0) + #endif /* CONFIG_BLK_DEV_IO_TRACE */ #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From 64565911cdb57c2f512a9715b985b5617402cc67 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 28 May 2008 14:45:33 +0200 Subject: block: make blktrace use per-cpu buffers for message notes Currently it uses a single static char array, but that risks being corrupted when multiple users issue message notes at the same time. Make the buffers dynamically allocated when the trace is setup and make them per-cpu instead. The default max message size of 1k is also very large, the interface is mainly for small text notes. So shrink it to 128 bytes. Signed-off-by: Jens Axboe --- block/blktrace.c | 15 ++++++++++++--- include/linux/blktrace_api.h | 3 ++- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/block/blktrace.c b/block/blktrace.c index 20e11f354f11..7ae87cc4a163 100644 --- a/block/blktrace.c +++ b/block/blktrace.c @@ -79,13 +79,16 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) { int n; va_list args; - static char bt_msg_buf[BLK_TN_MAX_MSG]; + char *buf; + preempt_disable(); + buf = per_cpu_ptr(bt->msg_data, smp_processor_id()); va_start(args, fmt); - n = vscnprintf(bt_msg_buf, BLK_TN_MAX_MSG, fmt, args); + n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); - trace_note(bt, 0, BLK_TN_MESSAGE, bt_msg_buf, n); + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n); + preempt_enable(); } EXPORT_SYMBOL_GPL(__trace_note_message); @@ -246,6 +249,7 @@ static void blk_trace_cleanup(struct blk_trace *bt) debugfs_remove(bt->dropped_file); blk_remove_tree(bt->dir); free_percpu(bt->sequence); + free_percpu(bt->msg_data); kfree(bt); } @@ -360,6 +364,10 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->sequence) goto err; + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG); + if (!bt->msg_data) + goto err; + ret = -ENOENT; dir = blk_create_tree(buts->name); if (!dir) @@ -406,6 +414,7 @@ err: if (bt->dropped_file) debugfs_remove(bt->dropped_file); free_percpu(bt->sequence); + free_percpu(bt->msg_data); if (bt->rchan) relay_close(bt->rchan); kfree(bt); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b7cd8f1eedbe..e3ef903aae88 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -121,6 +121,7 @@ struct blk_trace { int trace_state; struct rchan *rchan; unsigned long *sequence; + unsigned char *msg_data; u16 act_mask; u64 start_lba; u64 end_lba; @@ -172,7 +173,7 @@ extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); if (unlikely(bt)) \ __trace_note_message(bt, fmt, ##__VA_ARGS__); \ } while (0) -#define BLK_TN_MAX_MSG 1024 +#define BLK_TN_MAX_MSG 128 /** * blk_add_trace_rq - Add a trace for a request oriented action -- cgit v1.2.3 From 5e55843bb8ed1ec7d134a759c53e34beb1618952 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Wed, 28 May 2008 13:55:24 +0100 Subject: MN10300: Fix typo in header guard Fix a typo in the header guard of asm/ipc.h. Signed-off-by: Vegard Nossum Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/asm-mn10300/ipcbuf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mn10300/ipcbuf.h b/include/asm-mn10300/ipcbuf.h index efbbef8d1c69..f6f63d448272 100644 --- a/include/asm-mn10300/ipcbuf.h +++ b/include/asm-mn10300/ipcbuf.h @@ -1,4 +1,4 @@ -#ifndef _ASM_IPCBUF_H_ +#ifndef _ASM_IPCBUF_H #define _ASM_IPCBUF_H /* -- cgit v1.2.3 From dc1d60a014aa9614518f9856ff661716d0969ffd Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 May 2008 15:36:34 +0100 Subject: FRV: Specify the minimum slab/kmalloc alignment Specify the minimum slab/kmalloc alignment to be 8 bytes. This fixes a crash when SLOB is selected as the memory allocator. The FRV arch needs this so that it can use the load- and store-double instructions without faulting. By default SLOB sets the minimum to be 4 bytes. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/asm-frv/mem-layout.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/asm-frv/mem-layout.h b/include/asm-frv/mem-layout.h index 734a1d0583b6..8a15c90431b9 100644 --- a/include/asm-frv/mem-layout.h +++ b/include/asm-frv/mem-layout.h @@ -31,6 +31,13 @@ #define PAGE_MASK (~(PAGE_SIZE-1)) +/* + * the slab must be aligned such that load- and store-double instructions don't + * fault if used + */ +#define ARCH_KMALLOC_MINALIGN (sizeof(long) * 2) +#define ARCH_SLAB_MINALIGN (sizeof(long) * 2) + /*****************************************************************************/ /* * virtual memory layout from kernel's point of view -- cgit v1.2.3 From 0a2ce2ffc358da96792d514c1024b72c52be9cc1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 May 2008 16:49:01 +0100 Subject: Fix FRV minimum slab/kmalloc alignment > +#define ARCH_KMALLOC_MINALIGN (sizeof(long) * 2) > +#define ARCH_SLAB_MINALIGN (sizeof(long) * 2) This doesn't work if SLAB is selected and slab debugging is enabled as these are passed to the preprocessor, and the preprocessor doesn't understand sizeof. Signed-off-by: Linus Torvalds --- include/asm-frv/mem-layout.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-frv/mem-layout.h b/include/asm-frv/mem-layout.h index 8a15c90431b9..2947764fc0e0 100644 --- a/include/asm-frv/mem-layout.h +++ b/include/asm-frv/mem-layout.h @@ -35,8 +35,8 @@ * the slab must be aligned such that load- and store-double instructions don't * fault if used */ -#define ARCH_KMALLOC_MINALIGN (sizeof(long) * 2) -#define ARCH_SLAB_MINALIGN (sizeof(long) * 2) +#define ARCH_KMALLOC_MINALIGN 8 +#define ARCH_SLAB_MINALIGN 8 /*****************************************************************************/ /* -- cgit v1.2.3 From 6363ca57c76b7b83639ca8c83fc285fa26a7880e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 29 May 2008 11:28:57 +0200 Subject: revert ("sched: fair-group: SMP-nice for group scheduling") Yanmin Zhang reported: Comparing with 2.6.25, volanoMark has big regression with kernel 2.6.26-rc1. It's about 50% on my 8-core stoakley, 16-core tigerton, and Itanium Montecito. With bisect, I located the following patch: | 18d95a2832c1392a2d63227a7a6d433cb9f2037e is first bad commit | commit 18d95a2832c1392a2d63227a7a6d433cb9f2037e | Author: Peter Zijlstra | Date: Sat Apr 19 19:45:00 2008 +0200 | | sched: fair-group: SMP-nice for group scheduling Revert it so that we get v2.6.25 behavior. Bisected-by: Yanmin Zhang Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/sched.c | 430 ++++---------------------------------------------- kernel/sched_debug.c | 5 - kernel/sched_fair.c | 124 ++++++--------- kernel/sched_rt.c | 4 - 5 files changed, 75 insertions(+), 489 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5395a6176f4b..8a888499954e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -766,7 +766,6 @@ struct sched_domain { struct sched_domain *child; /* bottom domain must be null terminated */ struct sched_group *groups; /* the balancing groups of the domain */ cpumask_t span; /* span of all CPUs in this domain */ - int first_cpu; /* cache of the first cpu in this domain */ unsigned long min_interval; /* Minimum balance interval ms */ unsigned long max_interval; /* Maximum balance interval ms */ unsigned int busy_factor; /* less balancing by factor if busy */ diff --git a/kernel/sched.c b/kernel/sched.c index 3dc13f05b10e..bfb8ad8ed171 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -398,43 +398,6 @@ struct cfs_rq { */ struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ - -#ifdef CONFIG_SMP - unsigned long task_weight; - unsigned long shares; - /* - * We need space to build a sched_domain wide view of the full task - * group tree, in order to avoid depending on dynamic memory allocation - * during the load balancing we place this in the per cpu task group - * hierarchy. This limits the load balancing to one instance per cpu, - * but more should not be needed anyway. - */ - struct aggregate_struct { - /* - * load = weight(cpus) * f(tg) - * - * Where f(tg) is the recursive weight fraction assigned to - * this group. - */ - unsigned long load; - - /* - * part of the group weight distributed to this span. - */ - unsigned long shares; - - /* - * The sum of all runqueue weights within this span. - */ - unsigned long rq_weight; - - /* - * Weight contributed by tasks; this is the part we can - * influence by moving tasks around. - */ - unsigned long task_weight; - } aggregate; -#endif #endif }; @@ -1508,326 +1471,6 @@ static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); static unsigned long cpu_avg_load_per_task(int cpu); static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - -#ifdef CONFIG_FAIR_GROUP_SCHED - -/* - * Group load balancing. - * - * We calculate a few balance domain wide aggregate numbers; load and weight. - * Given the pictures below, and assuming each item has equal weight: - * - * root 1 - thread - * / | \ A - group - * A 1 B - * /|\ / \ - * C 2 D 3 4 - * | | - * 5 6 - * - * load: - * A and B get 1/3-rd of the total load. C and D get 1/3-rd of A's 1/3-rd, - * which equals 1/9-th of the total load. - * - * shares: - * The weight of this group on the selected cpus. - * - * rq_weight: - * Direct sum of all the cpu's their rq weight, e.g. A would get 3 while - * B would get 2. - * - * task_weight: - * Part of the rq_weight contributed by tasks; all groups except B would - * get 1, B gets 2. - */ - -static inline struct aggregate_struct * -aggregate(struct task_group *tg, struct sched_domain *sd) -{ - return &tg->cfs_rq[sd->first_cpu]->aggregate; -} - -typedef void (*aggregate_func)(struct task_group *, struct sched_domain *); - -/* - * Iterate the full tree, calling @down when first entering a node and @up when - * leaving it for the final time. - */ -static -void aggregate_walk_tree(aggregate_func down, aggregate_func up, - struct sched_domain *sd) -{ - struct task_group *parent, *child; - - rcu_read_lock(); - parent = &root_task_group; -down: - (*down)(parent, sd); - list_for_each_entry_rcu(child, &parent->children, siblings) { - parent = child; - goto down; - -up: - continue; - } - (*up)(parent, sd); - - child = parent; - parent = parent->parent; - if (parent) - goto up; - rcu_read_unlock(); -} - -/* - * Calculate the aggregate runqueue weight. - */ -static -void aggregate_group_weight(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long rq_weight = 0; - unsigned long task_weight = 0; - int i; - - for_each_cpu_mask(i, sd->span) { - rq_weight += tg->cfs_rq[i]->load.weight; - task_weight += tg->cfs_rq[i]->task_weight; - } - - aggregate(tg, sd)->rq_weight = rq_weight; - aggregate(tg, sd)->task_weight = task_weight; -} - -/* - * Compute the weight of this group on the given cpus. - */ -static -void aggregate_group_shares(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long shares = 0; - int i; - - for_each_cpu_mask(i, sd->span) - shares += tg->cfs_rq[i]->shares; - - if ((!shares && aggregate(tg, sd)->rq_weight) || shares > tg->shares) - shares = tg->shares; - - aggregate(tg, sd)->shares = shares; -} - -/* - * Compute the load fraction assigned to this group, relies on the aggregate - * weight and this group's parent's load, i.e. top-down. - */ -static -void aggregate_group_load(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long load; - - if (!tg->parent) { - int i; - - load = 0; - for_each_cpu_mask(i, sd->span) - load += cpu_rq(i)->load.weight; - - } else { - load = aggregate(tg->parent, sd)->load; - - /* - * shares is our weight in the parent's rq so - * shares/parent->rq_weight gives our fraction of the load - */ - load *= aggregate(tg, sd)->shares; - load /= aggregate(tg->parent, sd)->rq_weight + 1; - } - - aggregate(tg, sd)->load = load; -} - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - -/* - * Calculate and set the cpu's group shares. - */ -static void -__update_group_shares_cpu(struct task_group *tg, struct sched_domain *sd, - int tcpu) -{ - int boost = 0; - unsigned long shares; - unsigned long rq_weight; - - if (!tg->se[tcpu]) - return; - - rq_weight = tg->cfs_rq[tcpu]->load.weight; - - /* - * If there are currently no tasks on the cpu pretend there is one of - * average load so that when a new task gets to run here it will not - * get delayed by group starvation. - */ - if (!rq_weight) { - boost = 1; - rq_weight = NICE_0_LOAD; - } - - /* - * \Sum shares * rq_weight - * shares = ----------------------- - * \Sum rq_weight - * - */ - shares = aggregate(tg, sd)->shares * rq_weight; - shares /= aggregate(tg, sd)->rq_weight + 1; - - /* - * record the actual number of shares, not the boosted amount. - */ - tg->cfs_rq[tcpu]->shares = boost ? 0 : shares; - - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; - - __set_se_shares(tg->se[tcpu], shares); -} - -/* - * Re-adjust the weights on the cpu the task came from and on the cpu the - * task went to. - */ -static void -__move_group_shares(struct task_group *tg, struct sched_domain *sd, - int scpu, int dcpu) -{ - unsigned long shares; - - shares = tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares; - - __update_group_shares_cpu(tg, sd, scpu); - __update_group_shares_cpu(tg, sd, dcpu); - - /* - * ensure we never loose shares due to rounding errors in the - * above redistribution. - */ - shares -= tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares; - if (shares) - tg->cfs_rq[dcpu]->shares += shares; -} - -/* - * Because changing a group's shares changes the weight of the super-group - * we need to walk up the tree and change all shares until we hit the root. - */ -static void -move_group_shares(struct task_group *tg, struct sched_domain *sd, - int scpu, int dcpu) -{ - while (tg) { - __move_group_shares(tg, sd, scpu, dcpu); - tg = tg->parent; - } -} - -static -void aggregate_group_set_shares(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long shares = aggregate(tg, sd)->shares; - int i; - - for_each_cpu_mask(i, sd->span) { - struct rq *rq = cpu_rq(i); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __update_group_shares_cpu(tg, sd, i); - spin_unlock_irqrestore(&rq->lock, flags); - } - - aggregate_group_shares(tg, sd); - - /* - * ensure we never loose shares due to rounding errors in the - * above redistribution. - */ - shares -= aggregate(tg, sd)->shares; - if (shares) { - tg->cfs_rq[sd->first_cpu]->shares += shares; - aggregate(tg, sd)->shares += shares; - } -} - -/* - * Calculate the accumulative weight and recursive load of each task group - * while walking down the tree. - */ -static -void aggregate_get_down(struct task_group *tg, struct sched_domain *sd) -{ - aggregate_group_weight(tg, sd); - aggregate_group_shares(tg, sd); - aggregate_group_load(tg, sd); -} - -/* - * Rebalance the cpu shares while walking back up the tree. - */ -static -void aggregate_get_up(struct task_group *tg, struct sched_domain *sd) -{ - aggregate_group_set_shares(tg, sd); -} - -static DEFINE_PER_CPU(spinlock_t, aggregate_lock); - -static void __init init_aggregate(void) -{ - int i; - - for_each_possible_cpu(i) - spin_lock_init(&per_cpu(aggregate_lock, i)); -} - -static int get_aggregate(struct sched_domain *sd) -{ - if (!spin_trylock(&per_cpu(aggregate_lock, sd->first_cpu))) - return 0; - - aggregate_walk_tree(aggregate_get_down, aggregate_get_up, sd); - return 1; -} - -static void put_aggregate(struct sched_domain *sd) -{ - spin_unlock(&per_cpu(aggregate_lock, sd->first_cpu)); -} - -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) -{ - cfs_rq->shares = shares; -} - -#else - -static inline void init_aggregate(void) -{ -} - -static inline int get_aggregate(struct sched_domain *sd) -{ - return 0; -} - -static inline void put_aggregate(struct sched_domain *sd) -{ -} -#endif - #else /* CONFIG_SMP */ #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1848,14 +1491,26 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #define sched_class_highest (&rt_sched_class) -static void inc_nr_running(struct rq *rq) +static inline void inc_load(struct rq *rq, const struct task_struct *p) +{ + update_load_add(&rq->load, p->se.load.weight); +} + +static inline void dec_load(struct rq *rq, const struct task_struct *p) +{ + update_load_sub(&rq->load, p->se.load.weight); +} + +static void inc_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running++; + inc_load(rq, p); } -static void dec_nr_running(struct rq *rq) +static void dec_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running--; + dec_load(rq, p); } static void set_load_weight(struct task_struct *p) @@ -1947,7 +1602,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) rq->nr_uninterruptible--; enqueue_task(rq, p, wakeup); - inc_nr_running(rq); + inc_nr_running(p, rq); } /* @@ -1959,7 +1614,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) rq->nr_uninterruptible++; dequeue_task(rq, p, sleep); - dec_nr_running(rq); + dec_nr_running(p, rq); } /** @@ -2612,7 +2267,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * management (if any): */ p->sched_class->task_new(rq, p); - inc_nr_running(rq); + inc_nr_running(p, rq); } check_preempt_curr(rq, p); #ifdef CONFIG_SMP @@ -3603,12 +3258,9 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long imbalance; struct rq *busiest; unsigned long flags; - int unlock_aggregate; cpus_setall(*cpus); - unlock_aggregate = get_aggregate(sd); - /* * When power savings policy is enabled for the parent domain, idle * sibling can pick up load irrespective of busy siblings. In this case, @@ -3724,9 +3376,8 @@ redo: if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - - goto out; + return -1; + return ld_moved; out_balanced: schedstat_inc(sd, lb_balanced[idle]); @@ -3741,13 +3392,8 @@ out_one_pinned: if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - else - ld_moved = 0; -out: - if (unlock_aggregate) - put_aggregate(sd); - return ld_moved; + return -1; + return 0; } /* @@ -4934,8 +4580,10 @@ void set_user_nice(struct task_struct *p, long nice) goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) + if (on_rq) { dequeue_task(rq, p, 0); + dec_load(rq, p); + } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4945,6 +4593,7 @@ void set_user_nice(struct task_struct *p, long nice) if (on_rq) { enqueue_task(rq, p, 0); + inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -7319,7 +6968,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, ALLNODES); set_domain_attribute(sd, attr); sd->span = *cpu_map; - sd->first_cpu = first_cpu(sd->span); cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); p = sd; sd_allnodes = 1; @@ -7330,7 +6978,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, NODE); set_domain_attribute(sd, attr); sched_domain_node_span(cpu_to_node(i), &sd->span); - sd->first_cpu = first_cpu(sd->span); sd->parent = p; if (p) p->child = sd; @@ -7342,7 +6989,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, CPU); set_domain_attribute(sd, attr); sd->span = *nodemask; - sd->first_cpu = first_cpu(sd->span); sd->parent = p; if (p) p->child = sd; @@ -7354,7 +7000,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, MC); set_domain_attribute(sd, attr); sd->span = cpu_coregroup_map(i); - sd->first_cpu = first_cpu(sd->span); cpus_and(sd->span, sd->span, *cpu_map); sd->parent = p; p->child = sd; @@ -7367,7 +7012,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, SIBLING); set_domain_attribute(sd, attr); sd->span = per_cpu(cpu_sibling_map, i); - sd->first_cpu = first_cpu(sd->span); cpus_and(sd->span, sd->span, *cpu_map); sd->parent = p; p->child = sd; @@ -8037,7 +7681,6 @@ void __init sched_init(void) } #ifdef CONFIG_SMP - init_aggregate(); init_defrootdomain(); #endif @@ -8602,11 +8245,14 @@ void sched_move_task(struct task_struct *tsk) #endif #ifdef CONFIG_FAIR_GROUP_SCHED -static void __set_se_shares(struct sched_entity *se, unsigned long shares) +static void set_se_shares(struct sched_entity *se, unsigned long shares) { struct cfs_rq *cfs_rq = se->cfs_rq; + struct rq *rq = cfs_rq->rq; int on_rq; + spin_lock_irq(&rq->lock); + on_rq = se->on_rq; if (on_rq) dequeue_entity(cfs_rq, se, 0); @@ -8616,17 +8262,8 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares) if (on_rq) enqueue_entity(cfs_rq, se, 0); -} -static void set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - struct rq *rq = cfs_rq->rq; - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __set_se_shares(se, shares); - spin_unlock_irqrestore(&rq->lock, flags); + spin_unlock_irq(&rq->lock); } static DEFINE_MUTEX(shares_mutex); @@ -8665,13 +8302,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) * w/o tripping rebalance_share or load_balance_fair. */ tg->shares = shares; - for_each_possible_cpu(i) { - /* - * force a rebalance - */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); + for_each_possible_cpu(i) set_se_shares(tg->se[i], shares); - } /* * Enable load balance activity on this group, by inserting it back on diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 5f06118fbc31..8bb713040ac9 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -167,11 +167,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #endif SEQ_printf(m, " .%-30s: %ld\n", "nr_spread_over", cfs_rq->nr_spread_over); -#ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); -#endif -#endif } static void print_cpu(struct seq_file *m, int cpu) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0eb0ae879542..f0f25fc12d0a 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -510,27 +510,10 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ -#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ - cfs_rq->task_weight += weight; -} -#else -static inline void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ -} -#endif - static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - inc_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) - add_cfs_task_weight(cfs_rq, se->load.weight); cfs_rq->nr_running++; se->on_rq = 1; list_add(&se->group_node, &cfs_rq->tasks); @@ -540,10 +523,6 @@ static void account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - dec_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) - add_cfs_task_weight(cfs_rq, -se->load.weight); cfs_rq->nr_running--; se->on_rq = 0; list_del_init(&se->group_node); @@ -1327,90 +1306,75 @@ static struct task_struct *load_balance_next_fair(void *arg) return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator); } -static unsigned long -__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, struct sched_domain *sd, - enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, - struct cfs_rq *cfs_rq) +#ifdef CONFIG_FAIR_GROUP_SCHED +static int cfs_rq_best_prio(struct cfs_rq *cfs_rq) { - struct rq_iterator cfs_rq_iterator; + struct sched_entity *curr; + struct task_struct *p; - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; - cfs_rq_iterator.arg = cfs_rq; + if (!cfs_rq->nr_running || !first_fair(cfs_rq)) + return MAX_PRIO; + + curr = cfs_rq->curr; + if (!curr) + curr = __pick_next_entity(cfs_rq); - return balance_tasks(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &cfs_rq_iterator); + p = task_of(curr); + + return p->prio; } +#endif -#ifdef CONFIG_FAIR_GROUP_SCHED static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio) { + struct cfs_rq *busy_cfs_rq; long rem_load_move = max_load_move; - int busiest_cpu = cpu_of(busiest); - struct task_group *tg; - - rcu_read_lock(); - list_for_each_entry(tg, &task_groups, list) { - long imbalance; - unsigned long this_weight, busiest_weight; - long rem_load, max_load, moved_load; - - /* - * empty group - */ - if (!aggregate(tg, sd)->task_weight) - continue; - - rem_load = rem_load_move * aggregate(tg, sd)->rq_weight; - rem_load /= aggregate(tg, sd)->load + 1; - - this_weight = tg->cfs_rq[this_cpu]->task_weight; - busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight; + struct rq_iterator cfs_rq_iterator; - imbalance = (busiest_weight - this_weight) / 2; + cfs_rq_iterator.start = load_balance_start_fair; + cfs_rq_iterator.next = load_balance_next_fair; - if (imbalance < 0) - imbalance = busiest_weight; + for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { +#ifdef CONFIG_FAIR_GROUP_SCHED + struct cfs_rq *this_cfs_rq; + long imbalance; + unsigned long maxload; - max_load = max(rem_load, imbalance); - moved_load = __load_balance_fair(this_rq, this_cpu, busiest, - max_load, sd, idle, all_pinned, this_best_prio, - tg->cfs_rq[busiest_cpu]); + this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu); - if (!moved_load) + imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight; + /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */ + if (imbalance <= 0) continue; - move_group_shares(tg, sd, busiest_cpu, this_cpu); + /* Don't pull more than imbalance/2 */ + imbalance /= 2; + maxload = min(rem_load_move, imbalance); - moved_load *= aggregate(tg, sd)->load; - moved_load /= aggregate(tg, sd)->rq_weight + 1; + *this_best_prio = cfs_rq_best_prio(this_cfs_rq); +#else +# define maxload rem_load_move +#endif + /* + * pass busy_cfs_rq argument into + * load_balance_[start|next]_fair iterators + */ + cfs_rq_iterator.arg = busy_cfs_rq; + rem_load_move -= balance_tasks(this_rq, this_cpu, busiest, + maxload, sd, idle, all_pinned, + this_best_prio, + &cfs_rq_iterator); - rem_load_move -= moved_load; - if (rem_load_move < 0) + if (rem_load_move <= 0) break; } - rcu_read_unlock(); return max_load_move - rem_load_move; } -#else -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) -{ - return __load_balance_fair(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &busiest->cfs); -} -#endif static int move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 060e87b0cb1c..3432d573205d 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -513,8 +513,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) */ for_each_sched_rt_entity(rt_se) enqueue_rt_entity(rt_se); - - inc_cpu_load(rq, p->se.load.weight); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) @@ -534,8 +532,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) if (rt_rq && rt_rq->rt_nr_running) enqueue_rt_entity(rt_se); } - - dec_cpu_load(rq, p->se.load.weight); } /* -- cgit v1.2.3 From ea3f01f8afd3bc5daff915cc4ea5cc5ea9e7d427 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 29 May 2008 14:32:23 +0200 Subject: sched: re-tune NUMA topologies improve the sysbench ramp-up phase and its peak throughput on a 16way NUMA box, by turning on WAKE_AFFINE: tip/sched tip/sched+wake-affine ------------------------------------------------- 1: 700 830 +15.65% 2: 1465 1391 -5.28% 4: 3017 3105 +2.81% 8: 5100 6021 +15.30% 16: 10725 10745 +0.19% 32: 10135 10150 +0.16% 64: 9338 9240 -1.06% 128: 8599 8252 -4.21% 256: 8475 8144 -4.07% ------------------------------------------------- SUM: 57558 57882 +0.56% this change also improves lat_ctx from 6.69 usecs to 1.11 usec: $ ./lat_ctx -s 0 2 "size=0k ovr=1.19 2 1.11 $ ./lat_ctx -s 0 2 "size=0k ovr=1.22 2 6.69 in sysbench it's an overall win with some weakness at the lots-of-clients side. That happens because we now under-balance this workload a bit. To counter that effect, turn on NEWIDLE: wake-idle wake-idle+newidle ------------------------------------------------- 1: 830 834 +0.43% 2: 1391 1401 +0.65% 4: 3105 3091 -0.43% 8: 6021 6046 +0.42% 16: 10745 10736 -0.08% 32: 10150 10206 +0.55% 64: 9240 9533 +3.08% 128: 8252 8355 +1.24% 256: 8144 8384 +2.87% ------------------------------------------------- SUM: 57882 58591 +1.21% as a bonus this not only improves the many-clients case but also improves the (more important) rampup phase. sysbench is a workload that quickly breaks down if the scheduler over-balances, so since it showed an improvement under NEWIDLE this change is definitely good. --- include/linux/topology.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index 4bb7074a2c3a..24f3d2282e11 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -166,7 +166,9 @@ void arch_update_cpu_topology(void); .busy_idx = 3, \ .idle_idx = 3, \ .flags = SD_LOAD_BALANCE \ - | SD_SERIALIZE, \ + | SD_BALANCE_NEWIDLE \ + | SD_WAKE_AFFINE \ + | SD_SERIALIZE, \ .last_balance = jiffies, \ .balance_interval = 64, \ } -- cgit v1.2.3 From 413c239fad68258157f903b3ffd9bfcc53f5e34b Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 30 May 2008 10:16:40 +1000 Subject: driver-core: prepare for 2.6.27 api change by adding dev_set_name Create the dev_set_name function now so that various subsystems can start changing over to it before other changes in 2.6.27 will make it compulsory. Cc: Kay Sievers Signed-off-by: Stephen Rothwell Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 15 +++++++++++++++ include/linux/device.h | 3 +++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 72eccae4904b..422cfcad486d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -759,6 +759,21 @@ static void device_remove_class_symlinks(struct device *dev) sysfs_remove_link(&dev->kobj, "subsystem"); } +/** + * dev_set_name - set a device name + * @dev: device + */ +int dev_set_name(struct device *dev, const char *fmt, ...) +{ + va_list vargs; + + va_start(vargs, fmt); + vsnprintf(dev->bus_id, sizeof(dev->bus_id), fmt, vargs); + va_end(vargs); + return 0; +} +EXPORT_SYMBOL_GPL(dev_set_name); + /** * device_add - add device to device hierarchy. * @dev: device. diff --git a/include/linux/device.h b/include/linux/device.h index 14616e80213c..6a2d04c011bc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -385,6 +385,9 @@ static inline const char *dev_name(struct device *dev) return dev->bus_id; } +extern int dev_set_name(struct device *dev, const char *name, ...) + __attribute__((format(printf, 2, 3))); + #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { -- cgit v1.2.3 From 3ef536095446552823fc488fec1c5451aab1260d Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 16 May 2008 11:17:03 +0200 Subject: virtio_blk: allow read-only disks Hello Rusty, sometimes it is useful to share a disk (e.g. usr). To avoid file system corruption, the disk should be mounted read-only in that case. This patch adds a new feature flag, that allows the host to specify, if the disk should be considered read-only. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 6 +++++- include/linux/virtio_blk.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index c4804f3465db..dd7ea203f940 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -260,6 +260,10 @@ static int virtblk_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL); + /* If disk is read-only in the host, the guest should obey */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) + set_disk_ro(vblk->disk, 1); + /* Host must always specify the capacity. */ vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity), &cap, sizeof(cap)); @@ -326,7 +330,7 @@ static struct virtio_device_id id_table[] = { static unsigned int features[] = { VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, - VIRTIO_BLK_F_GEOMETRY, + VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, }; static struct virtio_driver virtio_blk = { diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index d4695a3356d0..b80919fad0ef 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -10,6 +10,7 @@ #define VIRTIO_BLK_F_SIZE_MAX 1 /* Indicates maximum segment size */ #define VIRTIO_BLK_F_SEG_MAX 2 /* Indicates maximum # of segments */ #define VIRTIO_BLK_F_GEOMETRY 4 /* Legacy geometry available */ +#define VIRTIO_BLK_F_RO 5 /* Disk is read-only */ struct virtio_blk_config { -- cgit v1.2.3 From f7f510ec195781c857ab76366a3e1c59e1caae42 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 30 May 2008 15:09:44 -0500 Subject: virtio: An entropy device, as suggested by hpa. Note that by itself, having a "hardware" random generator does very little: you should probably run "rngd" in your guest to feed this into the kernel entropy pool. Included: virtio_rng: dont use vmalloced addresses for virtio If virtio_rng is build as a module, random_data is an address in vmalloc space. As virtio expects guest real addresses, this can cause any kind of funny behaviour, so lets allocate random_data dynamically with kmalloc. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- drivers/char/hw_random/Kconfig | 9 +++ drivers/char/hw_random/Makefile | 1 + drivers/char/hw_random/virtio-rng.c | 155 ++++++++++++++++++++++++++++++++++++ include/linux/virtio_rng.h | 8 ++ 4 files changed, 173 insertions(+) create mode 100644 drivers/char/hw_random/virtio-rng.c create mode 100644 include/linux/virtio_rng.h (limited to 'include') diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index 8d6c2089d2a8..efd0b4db7c8e 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -112,3 +112,12 @@ config HW_RANDOM_PASEMI If unsure, say Y. +config HW_RANDOM_VIRTIO + tristate "VirtIO Random Number Generator support" + depends on HW_RANDOM && VIRTIO + ---help--- + This driver provides kernel-side support for the virtual Random Number + Generator hardware. + + To compile this driver as a module, choose M here: the + module will be called virtio-rng. If unsure, say N. diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile index c8b7300e2fb1..b4940ddbb35f 100644 --- a/drivers/char/hw_random/Makefile +++ b/drivers/char/hw_random/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_HW_RANDOM_VIA) += via-rng.o obj-$(CONFIG_HW_RANDOM_IXP4XX) += ixp4xx-rng.o obj-$(CONFIG_HW_RANDOM_OMAP) += omap-rng.o obj-$(CONFIG_HW_RANDOM_PASEMI) += pasemi-rng.o +obj-$(CONFIG_HW_RANDOM_VIRTIO) += virtio-rng.o diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c new file mode 100644 index 000000000000..d0e563e4fc39 --- /dev/null +++ b/drivers/char/hw_random/virtio-rng.c @@ -0,0 +1,155 @@ +/* + * Randomness driver for virtio + * Copyright (C) 2007, 2008 Rusty Russell IBM 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 of the License, 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#include +#include +#include +#include +#include +#include + +/* The host will fill any buffer we give it with sweet, sweet randomness. We + * give it 64 bytes at a time, and the hwrng framework takes it 4 bytes at a + * time. */ +#define RANDOM_DATA_SIZE 64 + +static struct virtqueue *vq; +static u32 *random_data; +static unsigned int data_left; +static DECLARE_COMPLETION(have_data); + +static void random_recv_done(struct virtqueue *vq) +{ + int len; + + /* We never get spurious callbacks. */ + if (!vq->vq_ops->get_buf(vq, &len)) + BUG(); + + data_left = len / sizeof(random_data[0]); + complete(&have_data); +} + +static void register_buffer(void) +{ + struct scatterlist sg; + + sg_init_one(&sg, random_data, RANDOM_DATA_SIZE); + /* There should always be room for one buffer. */ + if (vq->vq_ops->add_buf(vq, &sg, 0, 1, random_data) != 0) + BUG(); + vq->vq_ops->kick(vq); +} + +/* At least we don't udelay() in a loop like some other drivers. */ +static int virtio_data_present(struct hwrng *rng, int wait) +{ + if (data_left) + return 1; + + if (!wait) + return 0; + + wait_for_completion(&have_data); + return 1; +} + +/* virtio_data_present() must have succeeded before this is called. */ +static int virtio_data_read(struct hwrng *rng, u32 *data) +{ + BUG_ON(!data_left); + + *data = random_data[--data_left]; + + if (!data_left) { + init_completion(&have_data); + register_buffer(); + } + return sizeof(*data); +} + +static struct hwrng virtio_hwrng = { + .name = "virtio", + .data_present = virtio_data_present, + .data_read = virtio_data_read, +}; + +static int virtrng_probe(struct virtio_device *vdev) +{ + int err; + + /* We expect a single virtqueue. */ + vq = vdev->config->find_vq(vdev, 0, random_recv_done); + if (IS_ERR(vq)) + return PTR_ERR(vq); + + err = hwrng_register(&virtio_hwrng); + if (err) { + vdev->config->del_vq(vq); + return err; + } + + register_buffer(); + return 0; +} + +static void virtrng_remove(struct virtio_device *vdev) +{ + vdev->config->reset(vdev); + hwrng_unregister(&virtio_hwrng); + vdev->config->del_vq(vq); +} + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_RNG, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct virtio_driver virtio_rng = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtrng_probe, + .remove = __devexit_p(virtrng_remove), +}; + +static int __init init(void) +{ + int err; + + random_data = kmalloc(RANDOM_DATA_SIZE, GFP_KERNEL); + if (!random_data) + return -ENOMEM; + + err = register_virtio_driver(&virtio_rng); + if (err) + kfree(random_data); + return err; +} + +static void __exit fini(void) +{ + kfree(random_data); + unregister_virtio_driver(&virtio_rng); +} +module_init(init); +module_exit(fini); + +MODULE_DEVICE_TABLE(virtio, id_table); +MODULE_DESCRIPTION("Virtio random number driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/virtio_rng.h b/include/linux/virtio_rng.h new file mode 100644 index 000000000000..331afb6c9f62 --- /dev/null +++ b/include/linux/virtio_rng.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_VIRTIO_RNG_H +#define _LINUX_VIRTIO_RNG_H +#include + +/* The ID for virtio_rng */ +#define VIRTIO_ID_RNG 4 + +#endif /* _LINUX_VIRTIO_RNG_H */ -- cgit v1.2.3 From 7f31fe05000af54e1af81f65a96cab90db8d7ed8 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 29 May 2008 11:08:01 +0200 Subject: virtio_config: fix len calculation of config elements Rusty, This patch is a prereq for the virtio_blk blocksize patch, please apply it first. Adding an u32 value to the virtio_blk_config unconvered a small bug the config space defintions: v is a pointer, to we have to use sizeof(*v) instead of sizeof(v). Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- include/linux/virtio_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 50db245c81ad..71d6c102497e 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -99,7 +99,7 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, * The return value is -ENOENT if the feature doesn't exist. Otherwise * the config value is copied into whatever is pointed to by v. */ #define virtio_config_val(vdev, fbit, offset, v) \ - virtio_config_buf((vdev), (fbit), (offset), (v), sizeof(v)) + virtio_config_buf((vdev), (fbit), (offset), (v), sizeof(*v)) static inline int virtio_config_buf(struct virtio_device *vdev, unsigned int fbit, -- cgit v1.2.3 From 7757f09c70af87887dfc195e6d6ddd54f5cc7c39 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 29 May 2008 11:10:01 +0200 Subject: virtio_blk: fix endianess annotations Since commit 72e61eb40b55dd57031ec5971e810649f82b0259 (virtio: change config to guest endian) config space is no longer fixed endian. Lets change the virtio_blk_config variables. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- include/linux/virtio_blk.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index b80919fad0ef..5f79a5f9de79 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -15,14 +15,14 @@ struct virtio_blk_config { /* The capacity (in 512-byte sectors). */ - __le64 capacity; + __u64 capacity; /* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */ - __le32 size_max; + __u32 size_max; /* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */ - __le32 seg_max; + __u32 seg_max; /* geometry the device (if VIRTIO_BLK_F_GEOMETRY) */ struct virtio_blk_geometry { - __le16 cylinders; + __u16 cylinders; __u8 heads; __u8 sectors; } geometry; -- cgit v1.2.3 From b4f68be6c5d507afdcd74f5be3df0b1209cda503 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 30 May 2008 15:09:45 -0500 Subject: virtio: force callback on empty. virtio allows drivers to suppress callbacks (ie. interrupts) for efficiency (no locking, it's just an optimization). There's a similar mechanism for the host to suppress notifications coming from the guest: in that case, we ignore the suppression if the ring is completely full. It turns out that life is simpler if the host similarly ignores callback suppression when the ring is completely empty: the network driver wants to free up old packets in a timely manner, and otherwise has to use a timer to poll. We have to remove the code which ignores interrupts when the driver has disabled them (again, it had no locking and hence was unreliable anyway). Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 7 ------- include/linux/virtio_config.h | 4 ++++ 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 96d2567a7df8..72bf8bc09014 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -253,13 +253,6 @@ irqreturn_t vring_interrupt(int irq, void *_vq) if (unlikely(vq->broken)) return IRQ_HANDLED; - /* Other side may have missed us turning off the interrupt, - * but we should preserve disable semantic for virtio users. */ - if (unlikely(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) { - pr_debug("virtqueue interrupt after disable for %p\n", vq); - return IRQ_HANDLED; - } - pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback); if (vq->vq.callback) vq->vq.callback(&vq->vq); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 71d6c102497e..f364bbf63c34 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -15,6 +15,10 @@ /* We've given up on this device. */ #define VIRTIO_CONFIG_S_FAILED 0x80 +/* Do we get callbacks when the ring is completely used, even if we've + * suppressed them? */ +#define VIRTIO_F_NOTIFY_ON_EMPTY 24 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From bebd9a455b2593ba6543b961bc82c43350c2d8d9 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 30 May 2008 10:03:26 +0200 Subject: [S390] s390 types: make dma_addr_t 64 bit capable virtio tests with guests larger than 4 GB revealed that the dma_addr_t definition for s390 did not make it into the 64bit world. This patch changes the definition on s390 to have an u64 on 64bit and u32 on 32bit systems. Signed-off-by: Christian Borntraeger Signed-off-by: Martin Schwidefsky --- include/asm-s390/types.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/asm-s390/types.h b/include/asm-s390/types.h index 0e959e20e9a3..41c547656130 100644 --- a/include/asm-s390/types.h +++ b/include/asm-s390/types.h @@ -40,7 +40,13 @@ typedef __signed__ long saddr_t; #ifndef __ASSEMBLY__ +typedef u64 dma64_addr_t; +#ifdef __s390x__ +/* DMA addresses come in 32-bit and 64-bit flavours. */ +typedef u64 dma_addr_t; +#else typedef u32 dma_addr_t; +#endif #ifndef __s390x__ typedef union { -- cgit v1.2.3 From fbaa20f66a8283359523dfe961ebe66f0b8fac59 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 30 May 2008 02:01:28 -0700 Subject: sparc64: IO accessors fix From: Benjamin Herrenschmidt I added a full memory clobber on all asm accessors except the _raw ones. Signed-off-by: David S. Miller --- include/asm-sparc64/io.h | 66 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 44 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/asm-sparc64/io.h b/include/asm-sparc64/io.h index c299b853b5ba..3158960f3eb5 100644 --- a/include/asm-sparc64/io.h +++ b/include/asm-sparc64/io.h @@ -24,7 +24,8 @@ static inline u8 _inb(unsigned long addr) __asm__ __volatile__("lduba\t[%1] %2, %0\t/* pci_inb */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -35,7 +36,8 @@ static inline u16 _inw(unsigned long addr) __asm__ __volatile__("lduha\t[%1] %2, %0\t/* pci_inw */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -46,7 +48,8 @@ static inline u32 _inl(unsigned long addr) __asm__ __volatile__("lduwa\t[%1] %2, %0\t/* pci_inl */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -55,21 +58,24 @@ static inline void _outb(u8 b, unsigned long addr) { __asm__ __volatile__("stba\t%r0, [%1] %2\t/* pci_outb */" : /* no outputs */ - : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } static inline void _outw(u16 w, unsigned long addr) { __asm__ __volatile__("stha\t%r0, [%1] %2\t/* pci_outw */" : /* no outputs */ - : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } static inline void _outl(u32 l, unsigned long addr) { __asm__ __volatile__("stwa\t%r0, [%1] %2\t/* pci_outl */" : /* no outputs */ - : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } #define inb(__addr) (_inb((unsigned long)(__addr))) @@ -128,7 +134,8 @@ static inline u8 _readb(const volatile void __iomem *addr) __asm__ __volatile__("lduba\t[%1] %2, %0\t/* pci_readb */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -137,7 +144,8 @@ static inline u16 _readw(const volatile void __iomem *addr) __asm__ __volatile__("lduha\t[%1] %2, %0\t/* pci_readw */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -147,7 +155,8 @@ static inline u32 _readl(const volatile void __iomem *addr) __asm__ __volatile__("lduwa\t[%1] %2, %0\t/* pci_readl */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -157,7 +166,8 @@ static inline u64 _readq(const volatile void __iomem *addr) __asm__ __volatile__("ldxa\t[%1] %2, %0\t/* pci_readq */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); return ret; } @@ -166,28 +176,32 @@ static inline void _writeb(u8 b, volatile void __iomem *addr) { __asm__ __volatile__("stba\t%r0, [%1] %2\t/* pci_writeb */" : /* no outputs */ - : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } static inline void _writew(u16 w, volatile void __iomem *addr) { __asm__ __volatile__("stha\t%r0, [%1] %2\t/* pci_writew */" : /* no outputs */ - : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } static inline void _writel(u32 l, volatile void __iomem *addr) { __asm__ __volatile__("stwa\t%r0, [%1] %2\t/* pci_writel */" : /* no outputs */ - : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } static inline void _writeq(u64 q, volatile void __iomem *addr) { __asm__ __volatile__("stxa\t%r0, [%1] %2\t/* pci_writeq */" : /* no outputs */ - : "Jr" (q), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L)); + : "Jr" (q), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E_L) + : "memory"); } #define readb(__addr) _readb(__addr) @@ -299,7 +313,8 @@ static inline u8 _sbus_readb(const volatile void __iomem *addr) __asm__ __volatile__("lduba\t[%1] %2, %0\t/* sbus_readb */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); return ret; } @@ -310,7 +325,8 @@ static inline u16 _sbus_readw(const volatile void __iomem *addr) __asm__ __volatile__("lduha\t[%1] %2, %0\t/* sbus_readw */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); return ret; } @@ -321,7 +337,8 @@ static inline u32 _sbus_readl(const volatile void __iomem *addr) __asm__ __volatile__("lduwa\t[%1] %2, %0\t/* sbus_readl */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); return ret; } @@ -332,7 +349,8 @@ static inline u64 _sbus_readq(const volatile void __iomem *addr) __asm__ __volatile__("ldxa\t[%1] %2, %0\t/* sbus_readq */" : "=r" (ret) - : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); return ret; } @@ -341,28 +359,32 @@ static inline void _sbus_writeb(u8 b, volatile void __iomem *addr) { __asm__ __volatile__("stba\t%r0, [%1] %2\t/* sbus_writeb */" : /* no outputs */ - : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "Jr" (b), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); } static inline void _sbus_writew(u16 w, volatile void __iomem *addr) { __asm__ __volatile__("stha\t%r0, [%1] %2\t/* sbus_writew */" : /* no outputs */ - : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "Jr" (w), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); } static inline void _sbus_writel(u32 l, volatile void __iomem *addr) { __asm__ __volatile__("stwa\t%r0, [%1] %2\t/* sbus_writel */" : /* no outputs */ - : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); } static inline void _sbus_writeq(u64 l, volatile void __iomem *addr) { __asm__ __volatile__("stxa\t%r0, [%1] %2\t/* sbus_writeq */" : /* no outputs */ - : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E)); + : "Jr" (l), "r" (addr), "i" (ASI_PHYS_BYPASS_EC_E) + : "memory"); } #define sbus_readb(__addr) _sbus_readb(__addr) -- cgit v1.2.3 From e48d6d97bb6bd8c008045ea0522ea8278fdccc55 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 29 May 2008 08:16:56 +0200 Subject: [ALSA] ac97 - Fix ASUS A9T laptop output ASUS A9T laptop uses line-out pin as the real front-output while other devices use it as the surround. Signed-off-by: Takashi Iwai --- include/sound/ac97_codec.h | 1 + sound/pci/ac97/ac97_patch.c | 48 ++++++++++++++++++++++++++++++++------------- 2 files changed, 35 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h index 049edc5e6461..9c309daf492b 100644 --- a/include/sound/ac97_codec.h +++ b/include/sound/ac97_codec.h @@ -505,6 +505,7 @@ struct snd_ac97 { unsigned short pcmreg[3]; // PCM registers unsigned short codec_cfg[3]; // CODEC_CFG bits unsigned char swap_mic_linein; // AD1986/AD1986A only + unsigned char lo_as_master; /* LO as master */ } ad18xx; unsigned int dev_flags; /* device specific */ } spec; diff --git a/sound/pci/ac97/ac97_patch.c b/sound/pci/ac97/ac97_patch.c index 2da89810ca10..1292dcee072d 100644 --- a/sound/pci/ac97/ac97_patch.c +++ b/sound/pci/ac97/ac97_patch.c @@ -1971,6 +1971,9 @@ static int snd_ac97_ad1888_lohpsel_get(struct snd_kcontrol *kcontrol, struct snd val = ac97->regs[AC97_AD_MISC]; ucontrol->value.integer.value[0] = !(val & AC97_AD198X_LOSEL); + if (ac97->spec.ad18xx.lo_as_master) + ucontrol->value.integer.value[0] = + !ucontrol->value.integer.value[0]; return 0; } @@ -1979,8 +1982,10 @@ static int snd_ac97_ad1888_lohpsel_put(struct snd_kcontrol *kcontrol, struct snd struct snd_ac97 *ac97 = snd_kcontrol_chip(kcontrol); unsigned short val; - val = !ucontrol->value.integer.value[0] - ? (AC97_AD198X_LOSEL | AC97_AD198X_HPSEL) : 0; + val = !ucontrol->value.integer.value[0]; + if (ac97->spec.ad18xx.lo_as_master) + val = !val; + val = val ? (AC97_AD198X_LOSEL | AC97_AD198X_HPSEL) : 0; return snd_ac97_update_bits(ac97, AC97_AD_MISC, AC97_AD198X_LOSEL | AC97_AD198X_HPSEL, val); } @@ -2031,7 +2036,7 @@ static void ad1888_update_jacks(struct snd_ac97 *ac97) { unsigned short val = 0; /* clear LODIS if shared jack is to be used for Surround out */ - if (is_shared_linein(ac97)) + if (!ac97->spec.ad18xx.lo_as_master && is_shared_linein(ac97)) val |= (1 << 12); /* clear CLDIS if shared jack is to be used for C/LFE out */ if (is_shared_micin(ac97)) @@ -2067,9 +2072,13 @@ static const struct snd_kcontrol_new snd_ac97_ad1888_controls[] = { static int patch_ad1888_specific(struct snd_ac97 *ac97) { - /* rename 0x04 as "Master" and 0x02 as "Master Surround" */ - snd_ac97_rename_vol_ctl(ac97, "Master Playback", "Master Surround Playback"); - snd_ac97_rename_vol_ctl(ac97, "Headphone Playback", "Master Playback"); + if (!ac97->spec.ad18xx.lo_as_master) { + /* rename 0x04 as "Master" and 0x02 as "Master Surround" */ + snd_ac97_rename_vol_ctl(ac97, "Master Playback", + "Master Surround Playback"); + snd_ac97_rename_vol_ctl(ac97, "Headphone Playback", + "Master Playback"); + } return patch_build_controls(ac97, snd_ac97_ad1888_controls, ARRAY_SIZE(snd_ac97_ad1888_controls)); } @@ -2088,16 +2097,27 @@ static int patch_ad1888(struct snd_ac97 * ac97) patch_ad1881(ac97); ac97->build_ops = &patch_ad1888_build_ops; - /* Switch FRONT/SURROUND LINE-OUT/HP-OUT default connection */ - /* it seems that most vendors connect line-out connector to headphone out of AC'97 */ + + /* + * LO can be used as a real line-out on some devices, + * and we need to revert the front/surround mixer switches + */ + if (ac97->subsystem_vendor == 0x1043 && + ac97->subsystem_device == 0x1193) /* ASUS A9T laptop */ + ac97->spec.ad18xx.lo_as_master = 1; + + misc = snd_ac97_read(ac97, AC97_AD_MISC); /* AD-compatible mode */ /* Stereo mutes enabled */ - misc = snd_ac97_read(ac97, AC97_AD_MISC); - snd_ac97_write_cache(ac97, AC97_AD_MISC, misc | - AC97_AD198X_LOSEL | - AC97_AD198X_HPSEL | - AC97_AD198X_MSPLT | - AC97_AD198X_AC97NC); + misc |= AC97_AD198X_MSPLT | AC97_AD198X_AC97NC; + if (!ac97->spec.ad18xx.lo_as_master) + /* Switch FRONT/SURROUND LINE-OUT/HP-OUT default connection */ + /* it seems that most vendors connect line-out connector to + * headphone out of AC'97 + */ + misc |= AC97_AD198X_LOSEL | AC97_AD198X_HPSEL; + + snd_ac97_write_cache(ac97, AC97_AD_MISC, misc); ac97->flags |= AC97_STEREO_MUTES; return 0; } -- cgit v1.2.3 From 5adad0133907790c50283bf03271d920d6897043 Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Fri, 30 May 2008 10:40:46 -0400 Subject: Input: rename SW_RADIO to SW_RFKILL_ALL The SW_RADIO code for EV_SW events has a name that is not descriptive enough of its intended function, and could induce someone to think KEY_RADIO is its EV_KEY counterpart, which is false. Rename it to SW_RFKILL_ALL, and document what this event is for. Keep the old name around, to avoid userspace ABI breaks. The SW_RFKILL_ALL event is meant to be used by rfkill master switches. It is not bound to a particular radio switch type, and usually applies to all types. It is semantically tied to master rfkill switches that enable or disable every radio in a system. Signed-off-by: Henrique de Moraes Holschuh Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 28a094fcfe20..e075c4b762fb 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -637,7 +637,9 @@ struct input_absinfo { #define SW_LID 0x00 /* set = lid shut */ #define SW_TABLET_MODE 0x01 /* set = tablet mode */ #define SW_HEADPHONE_INSERT 0x02 /* set = inserted */ -#define SW_RADIO 0x03 /* set = radio enabled */ +#define SW_RFKILL_ALL 0x03 /* rfkill master switch, type "any" + set = radio enabled */ +#define SW_RADIO SW_RFKILL_ALL /* deprecated */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) -- cgit v1.2.3 From cfab3bdf8292edec19492c89520b1ad11279a648 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 28 May 2008 10:18:17 +1000 Subject: [POWERPC] Add "memory" clobber to MMIO accessors Gcc might re-order MMIO accessors vs. surrounding consistent memory accesses, which is a "bad thing", and could break drivers. This fixes it by adding a "memory" clobber to the MMIO accessors, which should prevent gcc from doing that reordering. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- include/asm-powerpc/io.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h index e0062d73db1c..89189488e286 100644 --- a/include/asm-powerpc/io.h +++ b/include/asm-powerpc/io.h @@ -100,7 +100,7 @@ static inline type name(const volatile type __iomem *addr) \ { \ type ret; \ __asm__ __volatile__("sync;" insn ";twi 0,%0,0;isync" \ - : "=r" (ret) : "r" (addr), "m" (*addr)); \ + : "=r" (ret) : "r" (addr), "m" (*addr) : "memory"); \ return ret; \ } @@ -108,8 +108,8 @@ static inline type name(const volatile type __iomem *addr) \ static inline void name(volatile type __iomem *addr, type val) \ { \ __asm__ __volatile__("sync;" insn \ - : "=m" (*addr) : "r" (val), "r" (addr)); \ - IO_SET_SYNC_FLAG(); \ + : "=m" (*addr) : "r" (val), "r" (addr) : "memory"); \ + IO_SET_SYNC_FLAG(); \ } @@ -333,7 +333,8 @@ static inline unsigned int name(unsigned int port) \ " .long 3b,5b\n" \ ".previous" \ : "=&r" (x) \ - : "r" (port + _IO_BASE)); \ + : "r" (port + _IO_BASE) \ + : "memory"); \ return x; \ } @@ -350,7 +351,8 @@ static inline void name(unsigned int val, unsigned int port) \ " .long 0b,2b\n" \ " .long 1b,2b\n" \ ".previous" \ - : : "r" (val), "r" (port + _IO_BASE)); \ + : : "r" (val), "r" (port + _IO_BASE) \ + : "memory"); \ } __do_in_asm(_rec_inb, "lbzx") -- cgit v1.2.3 From b06dcee9c8d24ef903dc0d192af22b8e179eef4b Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Sat, 31 May 2008 15:35:40 +0800 Subject: Blackfin arch: Remove bad and usless code Signed-off-by: Michael Hennerich Signed-off-by: Bryan Wu --- arch/blackfin/mach-bf537/boards/Makefile | 2 +- arch/blackfin/mach-bf537/boards/led.S | 183 ------------------------------- arch/blackfin/mach-bf548/boards/Makefile | 2 +- arch/blackfin/mach-bf548/boards/led.S | 172 ----------------------------- include/asm-blackfin/bfin-global.h | 7 -- 5 files changed, 2 insertions(+), 364 deletions(-) delete mode 100644 arch/blackfin/mach-bf537/boards/led.S delete mode 100644 arch/blackfin/mach-bf548/boards/led.S (limited to 'include') diff --git a/arch/blackfin/mach-bf537/boards/Makefile b/arch/blackfin/mach-bf537/boards/Makefile index 87e450f29e37..c94f7a5b8211 100644 --- a/arch/blackfin/mach-bf537/boards/Makefile +++ b/arch/blackfin/mach-bf537/boards/Makefile @@ -3,7 +3,7 @@ # obj-$(CONFIG_GENERIC_BF537_BOARD) += generic_board.o -obj-$(CONFIG_BFIN537_STAMP) += stamp.o led.o +obj-$(CONFIG_BFIN537_STAMP) += stamp.o obj-$(CONFIG_BFIN537_BLUETECHNIX_CM) += cm_bf537.o obj-$(CONFIG_PNAV10) += pnav10.o obj-$(CONFIG_CAMSIG_MINOTAUR) += minotaur.o diff --git a/arch/blackfin/mach-bf537/boards/led.S b/arch/blackfin/mach-bf537/boards/led.S deleted file mode 100644 index 4e9ea4283e5f..000000000000 --- a/arch/blackfin/mach-bf537/boards/led.S +++ /dev/null @@ -1,183 +0,0 @@ -/**************************************************** - * LED1 ---- PF6 LED2 ---- PF7 * - * LED3 ---- PF8 LED4 ---- PF9 * - * LED5 ---- PF10 LED6 ---- PF11 * - ****************************************************/ - -#include -#include - -/* All functions in this file save the registers they uses. - So there is no need to save any registers before calling them. */ - - .text; - -/* Initialize LEDs. */ - -ENTRY(_led_init) - LINK 12; - [--SP] = P0; - [--SP] = R0; - [--SP] = R1; - [--SP] = R2; - R1 = PF6|PF7|PF8|PF9|PF10|PF11 (Z); - R2 = ~R1; - - P0.H = hi(PORTF_FER); - P0.L = lo(PORTF_FER); - R0 = W[P0](Z); - SSYNC; - R0 = R0 & R2; - W[P0] = R0.L; - SSYNC; - - P0.H = hi(PORTFIO_DIR); - P0.L = lo(PORTFIO_DIR); - R0 = W[P0](Z); - SSYNC; - R0 = R0 | R1; - W[P0] = R0.L; - SSYNC; - - P0.H = hi(PORTFIO_INEN); - P0.L = lo(PORTFIO_INEN); - R0 = W[P0](Z); - SSYNC; - R0 = R0 & R2; - W[P0] = R0.L; - SSYNC; - - R2 = [SP++]; - R1 = [SP++]; - R0 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_init, .-_led_init - -/* Set one LED on. Leave other LEDs unchanged. - It expects the LED number passed through R0. */ - -ENTRY(_led_on) - LINK 12; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - P0.H = hi(PORTFIO); - P0.L = lo(PORTFIO); - R0 = W[P0](Z); - SSYNC; - R0 = R0 | R1; - W[P0] = R0.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_on, .-_led_on - -/* Set one LED off. Leave other LEDs unchanged. */ - -ENTRY(_led_off) - LINK 12; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - R1 = ~R1; - P0.H = hi(PORTFIO); - P0.L = lo(PORTFIO); - R0 = W[P0](Z); - SSYNC; - R0 = R0 & R1; - W[P0] = R0.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_off, .-_led_off - -/* Toggle one LED. Leave other LEDs unchanged. */ - -ENTRY(_led_toggle) - LINK 12; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - P0.H = hi(PORTFIO); - P0.L = lo(PORTFIO); - R0 = W[P0](Z); - SSYNC; - R0 = R0 ^ R1; - W[P0] = R0.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_toggle, .-_led_toggle - -/* Display the number using LEDs in binary format. */ - -ENTRY(_led_disp_num) - LINK 12; - [--SP] = P0; - [--SP] = R1; - [--SP] = R2; - CALL _led_init; - R1 = 0x3f(X); - R0 = R0 & R1; - R2 = 6(X); - R0 <<= R2; - R1 <<= R2; - P0.H = hi(PORTFIO); - P0.L = lo(PORTFIO); - R2 = W[P0](Z); - SSYNC; - R1 = ~R1; - R2 = R2 & R1; - R2 = R2 | R0; - W[P0] = R2.L; - SSYNC; - R2 = [SP++]; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_disp_num, .-_led_disp_num - -/* Toggle the number using LEDs in binary format. */ - -ENTRY(_led_toggle_num) - LINK 12; - [--SP] = P0; - [--SP] = R1; - [--SP] = R2; - CALL _led_init; - R1 = 0x3f(X); - R0 = R0 & R1; - R1 = 6(X); - R0 <<= R1; - P0.H = hi(PORTFIO); - P0.L = lo(PORTFIO); - R1 = W[P0](Z); - SSYNC; - R1 = R1 ^ R0; - W[P0] = R1.L; - SSYNC; - R2 = [SP++]; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_toggle_num, .-_led_toggle_num - diff --git a/arch/blackfin/mach-bf548/boards/Makefile b/arch/blackfin/mach-bf548/boards/Makefile index eed161dd7845..319ef54c4221 100644 --- a/arch/blackfin/mach-bf548/boards/Makefile +++ b/arch/blackfin/mach-bf548/boards/Makefile @@ -2,5 +2,5 @@ # arch/blackfin/mach-bf548/boards/Makefile # -obj-$(CONFIG_BFIN548_EZKIT) += ezkit.o led.o +obj-$(CONFIG_BFIN548_EZKIT) += ezkit.o obj-$(CONFIG_BFIN548_BLUETECHNIX_CM) += cm_bf548.o diff --git a/arch/blackfin/mach-bf548/boards/led.S b/arch/blackfin/mach-bf548/boards/led.S deleted file mode 100644 index f47daf3770d0..000000000000 --- a/arch/blackfin/mach-bf548/boards/led.S +++ /dev/null @@ -1,172 +0,0 @@ -/**************************************************** - * LED1 ---- PG6 LED2 ---- PG7 * - * LED3 ---- PG8 LED4 ---- PG9 * - * LED5 ---- PG10 LED6 ---- PG11 * - ****************************************************/ - -#include -#include - -/* All functions in this file save the registers they uses. - So there is no need to save any registers before calling them. */ - - .text; - -/* Initialize LEDs. */ - -ENTRY(_led_init) - LINK 0; - [--SP] = P0; - [--SP] = R0; - [--SP] = R1; - [--SP] = R2; - R1 = (PG6|PG7|PG8|PG9|PG10|PG11)(Z); - R2 = ~R1; - - P0.H = hi(PORTG_FER); - P0.L = lo(PORTG_FER); - R0 = W[P0](Z); - SSYNC; - R0 = R0 & R2; - W[P0] = R0.L; - SSYNC; - - P0.H = hi(PORTG_DIR_SET); - P0.L = lo(PORTG_DIR_SET); - W[P0] = R1.L; - SSYNC; - - P0.H = hi(PORTG_INEN); - P0.L = lo(PORTG_INEN); - R0 = W[P0](Z); - SSYNC; - R0 = R0 & R2; - W[P0] = R0.L; - SSYNC; - - R2 = [SP++]; - R1 = [SP++]; - R0 = [SP++]; - P0 = [SP++]; - RTS; - .size _led_init, .-_led_init - -/* Set one LED on. Leave other LEDs unchanged. - It expects the LED number passed through R0. */ - -ENTRY(_led_on) - LINK 0; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - P0.H = hi(PORTG_SET); - P0.L = lo(PORTG_SET); - W[P0] = R1.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_on, .-_led_on - -/* Set one LED off. Leave other LEDs unchanged. */ - -ENTRY(_led_off) - LINK 0; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - P0.H = hi(PORTG_CLEAR); - P0.L = lo(PORTG_CLEAR); - W[P0] = R1.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_off, .-_led_off - -/* Toggle one LED. Leave other LEDs unchanged. */ - -ENTRY(_led_toggle) - LINK 0; - [--SP] = P0; - [--SP] = R1; - CALL _led_init; - R1 = 1; - R0 += 5; - R1 <<= R0; - P0.H = hi(PORTG); - P0.L = lo(PORTG); - R0 = W[P0](Z); - SSYNC; - R0 = R0 ^ R1; - W[P0] = R0.L; - SSYNC; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_toggle, .-_led_toggle - -/* Display the number using LEDs in binary format. */ - -ENTRY(_led_disp_num) - LINK 0; - [--SP] = P0; - [--SP] = R1; - [--SP] = R2; - CALL _led_init; - R1 = 0x3f(X); - R0 = R0 & R1; - R2 = 6(X); - R0 <<= R2; - R1 <<= R2; - P0.H = hi(PORTG); - P0.L = lo(PORTG); - R2 = W[P0](Z); - SSYNC; - R1 = ~R1; - R2 = R2 & R1; - R2 = R2 | R0; - W[P0] = R2.L; - SSYNC; - R2 = [SP++]; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_disp_num, .-_led_disp_num - -/* Toggle the number using LEDs in binary format. */ - -ENTRY(_led_toggle_num) - LINK 0; - [--SP] = P0; - [--SP] = R1; - [--SP] = R2; - CALL _led_init; - R1 = 0x3f(X); - R0 = R0 & R1; - R1 = 6(X); - R0 <<= R1; - P0.H = hi(PORTG); - P0.L = lo(PORTG); - R1 = W[P0](Z); - SSYNC; - R1 = R1 ^ R0; - W[P0] = R1.L; - SSYNC; - R2 = [SP++]; - R1 = [SP++]; - P0 = [SP++]; - UNLINK; - RTS; - .size _led_toggle_num, .-_led_toggle_num - diff --git a/include/asm-blackfin/bfin-global.h b/include/asm-blackfin/bfin-global.h index a9248d883675..76033831eb35 100644 --- a/include/asm-blackfin/bfin-global.h +++ b/include/asm-blackfin/bfin-global.h @@ -105,13 +105,6 @@ extern int sram_free(const void*); extern void *sram_alloc_with_lsl(size_t, unsigned long); extern int sram_free_with_lsl(const void*); -extern void led_on(int); -extern void led_off(int); -extern void led_toggle(int); -extern void led_disp_num(int); -extern void led_toggle_num(int); -extern void init_leds(void); - extern const char bfin_board_name[]; extern unsigned long wall_jiffies; -- cgit v1.2.3 From a70ce072b3883e431575449f3e294c27235590e5 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Sat, 31 May 2008 15:47:17 +0800 Subject: Blackfin arch: update anomaly headers from toolchain trunk Signed-off-by: Mike Frysinger Signed-off-by: Bryan Wu --- include/asm-blackfin/mach-bf527/anomaly.h | 5 ++++- include/asm-blackfin/mach-bf533/anomaly.h | 31 ++++++++++++++++--------------- include/asm-blackfin/mach-bf537/anomaly.h | 10 ++++------ include/asm-blackfin/mach-bf548/anomaly.h | 2 ++ include/asm-blackfin/mach-bf561/anomaly.h | 2 +- 5 files changed, 27 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/asm-blackfin/mach-bf527/anomaly.h b/include/asm-blackfin/mach-bf527/anomaly.h index 735fa02fafb2..4725268a5ada 100644 --- a/include/asm-blackfin/mach-bf527/anomaly.h +++ b/include/asm-blackfin/mach-bf527/anomaly.h @@ -15,12 +15,16 @@ /* Multi-Issue Instruction with dsp32shiftimm in slot1 and P-reg Store in slot2 Not Supported */ #define ANOMALY_05000074 (1) +/* DMA_RUN Bit Is Not Valid after a Peripheral Receive Channel DMA Stops */ +#define ANOMALY_05000119 (1) /* Rx.H Cannot Be Used to Access 16-bit System MMR Registers */ #define ANOMALY_05000122 (1) /* Spurious Hardware Error from an Access in the Shadow of a Conditional Branch */ #define ANOMALY_05000245 (1) /* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ #define ANOMALY_05000265 (1) +/* Errors when SSYNC, CSYNC, or Loads to LT, LB and LC Registers Are Interrupted */ +#define ANOMALY_05000312 (1) /* Incorrect Access of OTP_STATUS During otp_write() Function */ #define ANOMALY_05000328 (1) /* Disallowed Configuration Prevents Subsequent Allowed Configuration on Host DMA Port */ @@ -92,7 +96,6 @@ #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) #define ANOMALY_05000311 (0) -#define ANOMALY_05000312 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000363 (0) diff --git a/include/asm-blackfin/mach-bf533/anomaly.h b/include/asm-blackfin/mach-bf533/anomaly.h index 5a6dcc5fa36c..8f7ea112fd3a 100644 --- a/include/asm-blackfin/mach-bf533/anomaly.h +++ b/include/asm-blackfin/mach-bf533/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf533/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2007 Analog Devices Inc. + * Copyright (C) 2004-2008 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -176,6 +176,21 @@ #define ANOMALY_05000315 (1) /* Internal Voltage Regulator Values of 1.05V, 1.10V and 1.15V Not Allowed for LQFP Packages */ #define ANOMALY_05000319 (ANOMALY_BF531 || ANOMALY_BF532) +/* Serial Port (SPORT) Multichannel Transmit Failure when Channel 0 Is Disabled */ +#define ANOMALY_05000357 (1) +/* UART Break Signal Issues */ +#define ANOMALY_05000363 (__SILICON_REVISION__ < 5) +/* PPI Underflow Error Goes Undetected in ITU-R 656 Mode */ +#define ANOMALY_05000366 (1) +/* Possible RETS Register Corruption when Subroutine Is under 5 Cycles in Duration */ +#define ANOMALY_05000371 (1) +/* PPI Does Not Start Properly In Specific Mode */ +#define ANOMALY_05000400 (__SILICON_REVISION__ >= 5) +/* SSYNC Stalls Processor when Executed from Non-Cacheable Memory */ +#define ANOMALY_05000402 (__SILICON_REVISION__ >= 5) +/* Level-Sensitive External GPIO Wakeups May Cause Indefinite Stall */ +#define ANOMALY_05000403 (1) + /* These anomalies have been "phased" out of analog.com anomaly sheets and are * here to show running on older silicon just isn't feasible. @@ -249,20 +264,6 @@ #define ANOMALY_05000192 (__SILICON_REVISION__ < 3) /* Internal Voltage Regulator may not start up */ #define ANOMALY_05000206 (__SILICON_REVISION__ < 3) -/* Serial Port (SPORT) Multichannel Transmit Failure when Channel 0 Is Disabled */ -#define ANOMALY_05000357 (1) -/* UART Break Signal Issues */ -#define ANOMALY_05000363 (__SILICON_REVISION__ < 5) -/* PPI Underflow Error Goes Undetected in ITU-R 656 Mode */ -#define ANOMALY_05000366 (1) -/* Possible RETS Register Corruption when Subroutine Is under 5 Cycles in Duration */ -#define ANOMALY_05000371 (1) -/* PPI Does Not Start Properly In Specific Mode */ -#define ANOMALY_05000400 (__SILICON_REVISION__ == 5) -/* SSYNC Stalls Processor when Executed from Non-Cacheable Memory */ -#define ANOMALY_05000402 (__SILICON_REVISION__ == 5) -/* Level-Sensitive External GPIO Wakeups May Cause Indefinite Stall */ -#define ANOMALY_05000403 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000266 (0) diff --git a/include/asm-blackfin/mach-bf537/anomaly.h b/include/asm-blackfin/mach-bf537/anomaly.h index a6b08facb242..8460ab9c324f 100644 --- a/include/asm-blackfin/mach-bf537/anomaly.h +++ b/include/asm-blackfin/mach-bf537/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf537/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2007 Analog Devices Inc. + * Copyright (C) 2004-2008 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -132,8 +132,8 @@ #define ANOMALY_05000322 (1) /* Ethernet MAC MDIO Reads Do Not Meet IEEE Specification */ #define ANOMALY_05000341 (__SILICON_REVISION__ >= 3) -/* New Feature: UART Remains Enabled after UART Boot (Not Available on Older Silicon) */ -#define ANOMALY_05000350 (__SILICON_REVISION__ < 3) +/* New Feature: UART Remains Enabled after UART Boot */ +#define ANOMALY_05000350 (__SILICON_REVISION__ >= 3) /* Regulator Programming Blocked when Hibernate Wakeup Source Remains Active */ #define ANOMALY_05000355 (1) /* Serial Port (SPORT) Multichannel Transmit Failure when Channel 0 Is Disabled */ @@ -145,12 +145,10 @@ /* Possible RETS Register Corruption when Subroutine Is under 5 Cycles in Duration */ #define ANOMALY_05000371 (1) /* SSYNC Stalls Processor when Executed from Non-Cacheable Memory */ -#define ANOMALY_05000402 (__SILICON_REVISION__ >= 3) +#define ANOMALY_05000402 (__SILICON_REVISION__ >= 5) /* Level-Sensitive External GPIO Wakeups May Cause Indefinite Stall */ #define ANOMALY_05000403 (1) - - /* Anomalies that don't exist on this proc */ #define ANOMALY_05000125 (0) #define ANOMALY_05000158 (0) diff --git a/include/asm-blackfin/mach-bf548/anomaly.h b/include/asm-blackfin/mach-bf548/anomaly.h index 49d3cebc5293..3ad59655881a 100644 --- a/include/asm-blackfin/mach-bf548/anomaly.h +++ b/include/asm-blackfin/mach-bf548/anomaly.h @@ -75,6 +75,8 @@ #define ANOMALY_05000365 (1) /* Addressing Conflict between Boot ROM and Asynchronous Memory */ #define ANOMALY_05000369 (1) +/* Possible RETS Register Corruption when Subroutine Is under 5 Cycles in Duration */ +#define ANOMALY_05000371 (1) /* Mobile DDR Operation Not Functional */ #define ANOMALY_05000377 (1) /* Security/Authentication Speedpath Causes Authentication To Fail To Initiate */ diff --git a/include/asm-blackfin/mach-bf561/anomaly.h b/include/asm-blackfin/mach-bf561/anomaly.h index 82157caa96a2..5c5d7d7d695f 100644 --- a/include/asm-blackfin/mach-bf561/anomaly.h +++ b/include/asm-blackfin/mach-bf561/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf561/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2007 Analog Devices Inc. + * Copyright (C) 2004-2008 Analog Devices Inc. * Licensed under the GPL-2 or later. */ -- cgit v1.2.3 From ca05a99a54db1db5bca72eccb5866d2a86f8517f Mon Sep 17 00:00:00 2001 From: "Andrew G. Morgan" Date: Tue, 27 May 2008 22:05:17 -0700 Subject: capabilities: remain source compatible with 32-bit raw legacy capability support. Source code out there hard-codes a notion of what the _LINUX_CAPABILITY_VERSION #define means in terms of the semantics of the raw capability system calls capget() and capset(). Its unfortunate, but true. Since the confusing header file has been in a released kernel, there is software that is erroneously using 64-bit capabilities with the semantics of 32-bit compatibilities. These recently compiled programs may suffer corruption of their memory when sys_getcap() overwrites more memory than they are coded to expect, and the raising of added capabilities when using sys_capset(). As such, this patch does a number of things to clean up the situation for all. It 1. forces the _LINUX_CAPABILITY_VERSION define to always retain its legacy value. 2. adopts a new #define strategy for the kernel's internal implementation of the preferred magic. 3. deprecates v2 capability magic in favor of a new (v3) magic number. The functionality of v3 is entirely equivalent to v2, the only difference being that the v2 magic causes the kernel to log a "deprecated" warning so the admin can find applications that may be using v2 inappropriately. [User space code continues to be encouraged to use the libcap API which protects the application from details like this. libcap-2.10 is the first to support v3 capabilities.] Fixes issue reported in https://bugzilla.redhat.com/show_bug.cgi?id=447518. Thanks to Bojan Smojver for the report. [akpm@linux-foundation.org: s/depreciate/deprecate/g] [akpm@linux-foundation.org: be robust about put_user size] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrew G. Morgan Cc: Serge E. Hallyn Cc: Bojan Smojver Cc: stable@kernel.org Signed-off-by: Andrew Morton Signed-off-by: Chris Wright --- fs/proc/array.c | 2 +- include/linux/capability.h | 29 ++++++++---- kernel/capability.c | 111 +++++++++++++++++++++++++++++---------------- 3 files changed, 95 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/fs/proc/array.c b/fs/proc/array.c index 9e3b8c33c24b..797d775e0354 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -288,7 +288,7 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_printf(m, "%s", header); CAP_FOR_EACH_U32(__capi) { seq_printf(m, "%08x", - a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]); + a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]); } seq_printf(m, "\n"); } diff --git a/include/linux/capability.h b/include/linux/capability.h index f4ea0dd9a618..fa830f8de032 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -31,11 +31,11 @@ struct task_struct; #define _LINUX_CAPABILITY_VERSION_1 0x19980330 #define _LINUX_CAPABILITY_U32S_1 1 -#define _LINUX_CAPABILITY_VERSION_2 0x20071026 +#define _LINUX_CAPABILITY_VERSION_2 0x20071026 /* deprecated - use v3 */ #define _LINUX_CAPABILITY_U32S_2 2 -#define _LINUX_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_2 -#define _LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_2 +#define _LINUX_CAPABILITY_VERSION_3 0x20080522 +#define _LINUX_CAPABILITY_U32S_3 2 typedef struct __user_cap_header_struct { __u32 version; @@ -77,10 +77,23 @@ struct vfs_cap_data { } data[VFS_CAP_U32]; }; -#ifdef __KERNEL__ +#ifndef __KERNEL__ + +/* + * Backwardly compatible definition for source code - trapped in a + * 32-bit world. If you find you need this, please consider using + * libcap to untrap yourself... + */ +#define _LINUX_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_1 +#define _LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_1 + +#else + +#define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 +#define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 typedef struct kernel_cap_struct { - __u32 cap[_LINUX_CAPABILITY_U32S]; + __u32 cap[_KERNEL_CAPABILITY_U32S]; } kernel_cap_t; #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) @@ -351,7 +364,7 @@ typedef struct kernel_cap_struct { */ #define CAP_FOR_EACH_U32(__capi) \ - for (__capi = 0; __capi < _LINUX_CAPABILITY_U32S; ++__capi) + for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi) # define CAP_FS_MASK_B0 (CAP_TO_MASK(CAP_CHOWN) \ | CAP_TO_MASK(CAP_DAC_OVERRIDE) \ @@ -361,7 +374,7 @@ typedef struct kernel_cap_struct { # define CAP_FS_MASK_B1 (CAP_TO_MASK(CAP_MAC_OVERRIDE)) -#if _LINUX_CAPABILITY_U32S != 2 +#if _KERNEL_CAPABILITY_U32S != 2 # error Fix up hand-coded capability macro initializers #else /* HAND-CODED capability initializers */ @@ -372,7 +385,7 @@ typedef struct kernel_cap_struct { # define CAP_NFSD_SET ((kernel_cap_t){{ CAP_FS_MASK_B0|CAP_TO_MASK(CAP_SYS_RESOURCE), \ CAP_FS_MASK_B1 } }) -#endif /* _LINUX_CAPABILITY_U32S != 2 */ +#endif /* _KERNEL_CAPABILITY_U32S != 2 */ #define CAP_INIT_INH_SET CAP_EMPTY_SET diff --git a/kernel/capability.c b/kernel/capability.c index 39e8193b41ea..cfbe44299488 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -52,6 +52,69 @@ static void warn_legacy_capability_use(void) } } +/* + * Version 2 capabilities worked fine, but the linux/capability.h file + * that accompanied their introduction encouraged their use without + * the necessary user-space source code changes. As such, we have + * created a version 3 with equivalent functionality to version 2, but + * with a header change to protect legacy source code from using + * version 2 when it wanted to use version 1. If your system has code + * that trips the following warning, it is using version 2 specific + * capabilities and may be doing so insecurely. + * + * The remedy is to either upgrade your version of libcap (to 2.10+, + * if the application is linked against it), or recompile your + * application with modern kernel headers and this warning will go + * away. + */ + +static void warn_deprecated_v2(void) +{ + static int warned; + + if (!warned) { + char name[sizeof(current->comm)]; + + printk(KERN_INFO "warning: `%s' uses deprecated v2" + " capabilities in a way that may be insecure.\n", + get_task_comm(name, current)); + warned = 1; + } +} + +/* + * Version check. Return the number of u32s in each capability flag + * array, or a negative value on error. + */ +static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) +{ + __u32 version; + + if (get_user(version, &header->version)) + return -EFAULT; + + switch (version) { + case _LINUX_CAPABILITY_VERSION_1: + warn_legacy_capability_use(); + *tocopy = _LINUX_CAPABILITY_U32S_1; + break; + case _LINUX_CAPABILITY_VERSION_2: + warn_deprecated_v2(); + /* + * fall through - v3 is otherwise equivalent to v2. + */ + case _LINUX_CAPABILITY_VERSION_3: + *tocopy = _LINUX_CAPABILITY_U32S_3; + break; + default: + if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) + return -EFAULT; + return -EINVAL; + } + + return 0; +} + /* * For sys_getproccap() and sys_setproccap(), any of the three * capability set pointers may be NULL -- indicating that that set is @@ -71,27 +134,13 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) { int ret = 0; pid_t pid; - __u32 version; struct task_struct *target; unsigned tocopy; kernel_cap_t pE, pI, pP; - if (get_user(version, &header->version)) - return -EFAULT; - - switch (version) { - case _LINUX_CAPABILITY_VERSION_1: - warn_legacy_capability_use(); - tocopy = _LINUX_CAPABILITY_U32S_1; - break; - case _LINUX_CAPABILITY_VERSION_2: - tocopy = _LINUX_CAPABILITY_U32S_2; - break; - default: - if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) - return -EFAULT; - return -EINVAL; - } + ret = cap_validate_magic(header, &tocopy); + if (ret != 0) + return ret; if (get_user(pid, &header->pid)) return -EFAULT; @@ -118,7 +167,7 @@ out: spin_unlock(&task_capability_lock); if (!ret) { - struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; for (i = 0; i < tocopy; i++) { @@ -128,7 +177,7 @@ out: } /* - * Note, in the case, tocopy < _LINUX_CAPABILITY_U32S, + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability @@ -240,30 +289,16 @@ static inline int cap_set_all(kernel_cap_t *effective, */ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) { - struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy; kernel_cap_t inheritable, permitted, effective; - __u32 version; struct task_struct *target; int ret; pid_t pid; - if (get_user(version, &header->version)) - return -EFAULT; - - switch (version) { - case _LINUX_CAPABILITY_VERSION_1: - warn_legacy_capability_use(); - tocopy = _LINUX_CAPABILITY_U32S_1; - break; - case _LINUX_CAPABILITY_VERSION_2: - tocopy = _LINUX_CAPABILITY_U32S_2; - break; - default: - if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) - return -EFAULT; - return -EINVAL; - } + ret = cap_validate_magic(header, &tocopy); + if (ret != 0) + return ret; if (get_user(pid, &header->pid)) return -EFAULT; @@ -281,7 +316,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) permitted.cap[i] = kdata[i].permitted; inheritable.cap[i] = kdata[i].inheritable; } - while (i < _LINUX_CAPABILITY_U32S) { + while (i < _KERNEL_CAPABILITY_U32S) { effective.cap[i] = 0; permitted.cap[i] = 0; inheritable.cap[i] = 0; -- cgit v1.2.3 From ee48a75c95145bf6af3be329cd7cbbca2ec89a2a Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 1 Jun 2008 11:19:33 +0100 Subject: [ARM] fix AT91 include loops AT91 has one include loop in its header files: include/asm-arm/io.h <- include/asm-arm/arch-at91/io.h <- include/asm-arm/io.h Circular include dependencies are dangerous since they can result in inconsistent definitions being provided to other code, especially if '#ifndef' constructs are used. Solve this by removing the offending includes. Built tested using my AT91 configuration. Acked-by: Andrew Victor Signed-off-by: Russell King --- include/asm-arm/arch-at91/io.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/asm-arm/arch-at91/io.h b/include/asm-arm/arch-at91/io.h index 80073fd36b8e..f8beaa228467 100644 --- a/include/asm-arm/arch-at91/io.h +++ b/include/asm-arm/arch-at91/io.h @@ -21,8 +21,6 @@ #ifndef __ASM_ARCH_IO_H #define __ASM_ARCH_IO_H -#include - #define IO_SPACE_LIMIT 0xFFFFFFFF #define __io(a) ((void __iomem *)(a)) -- cgit v1.2.3 From 759e9408ad2e7f2115ce8341854be982e0186a8c Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Sun, 25 May 2008 12:35:38 +0100 Subject: [ARM] 5060/1: remove unnecessary include of asm/io.h Remove unnecessary include of asm/io.h. Signed-off-by: Greg Ungerer Signed-off-by: Russell King --- include/asm-arm/pgtable-nommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/asm-arm/pgtable-nommu.h b/include/asm-arm/pgtable-nommu.h index 2e5868bbe03b..386fcc10a973 100644 --- a/include/asm-arm/pgtable-nommu.h +++ b/include/asm-arm/pgtable-nommu.h @@ -16,7 +16,6 @@ #include #include #include -#include /* * Trivial page table functions. -- cgit v1.2.3 From d02d6be5d52a98be32c93d2ea7a0068991774a20 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 2 Jun 2008 12:40:14 +0900 Subject: sh: fix miscompilation of ip_fast_csum with gcc >= 4.3 As noted by Matthew Wilcox: Kyle McMartin just tracked down a bug on parisc to a missing "memory" clobber in the inline assembly implementation of ip_fast_csum. The FRV, SH and Xtensa ports are also missing a memory clobber, so I thought it would be polite to let you know. The bug manifests as dropped network packets (obviously they have the wrong checksum). It started appearing for parisc with GCC 4.3. The GCC manual says: If your assembler instructions access memory in an unpredictable fashion, add `memory' to the list of clobbered registers. This will cause GCC to not keep memory values cached in registers across the assembler instruction and not optimize stores or loads to that memory. I see that FRV has a 400 byte memory output which may prevent this problem from appearing, but SH and Xtensa have nothing to prevent this bug. Hope this saves you a few days of debugging. Signed-off-by: Paul Mundt --- include/asm-sh/checksum_32.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-sh/checksum_32.h b/include/asm-sh/checksum_32.h index 4bc8357e8892..14b7ac2f0a07 100644 --- a/include/asm-sh/checksum_32.h +++ b/include/asm-sh/checksum_32.h @@ -109,7 +109,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) will assume they contain their original values. */ : "=r" (sum), "=r" (iph), "=r" (ihl), "=&r" (__dummy0), "=&z" (__dummy1) : "1" (iph), "2" (ihl) - : "t"); + : "t", "memory"); return csum_fold(sum); } -- cgit v1.2.3 From 106f62701fe79fd5c251e5d3e182516344882962 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 28 May 2008 18:37:14 +0100 Subject: [ARM] 5068/1: PXA2xx Additional gpio definitions Some additional alternate gpio definitions relating to FFUART and USB on the pxa27x. These are used on the xbow imote2 platform. Signed-off-by: Jonathan Cameron Signed-off-by: Russell King --- include/asm-arm/arch-pxa/pxa2xx-gpio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/asm-arm/arch-pxa/pxa2xx-gpio.h b/include/asm-arm/arch-pxa/pxa2xx-gpio.h index 763313c5e6be..b81cd63cb2eb 100644 --- a/include/asm-arm/arch-pxa/pxa2xx-gpio.h +++ b/include/asm-arm/arch-pxa/pxa2xx-gpio.h @@ -134,7 +134,11 @@ #define GPIO93_CIF_DD_6 93 /* Camera data pin 6 */ #define GPIO94_CIF_DD_5 94 /* Camera data pin 5 */ #define GPIO95_CIF_DD_4 95 /* Camera data pin 4 */ +#define GPIO96_FFRXD 96 /* FFUART recieve */ +#define GPIO98_FFRTS 98 /* FFUART request to send */ #define GPIO98_CIF_DD_0 98 /* Camera data pin 0 */ +#define GPIO99_FFTXD 99 /* FFUART transmit data */ +#define GPIO100_FFCTS 100 /* FFUART Clear to send */ #define GPIO102_nPCE_1 102 /* PCMCIA (PXA27x) */ #define GPIO103_CIF_DD_3 103 /* Camera data pin 3 */ #define GPIO104_CIF_DD_2 104 /* Camera data pin 2 */ @@ -316,6 +320,8 @@ #define GPIO85_nPCE_1_MD (85 | GPIO_ALT_FN_1_OUT) #define GPIO85_CIF_LV_MD (85 | GPIO_ALT_FN_3_IN) #define GPIO86_nPCE_1_MD (86 | GPIO_ALT_FN_1_OUT) +#define GPIO88_USBH1_PWR_MD (88 | GPIO_ALT_FN_1_IN) +#define GPIO89_USBH1_PEN_MD (89 | GPIO_ALT_FN_2_OUT) #define GPIO90_CIF_DD_4_MD (90 | GPIO_ALT_FN_3_IN) #define GPIO91_CIF_DD_5_MD (91 | GPIO_ALT_FN_3_IN) #define GPIO92_MMCDAT0_MD (92 | GPIO_ALT_FN_1_OUT) @@ -324,8 +330,11 @@ #define GPIO95_CIF_DD_4_MD (95 | GPIO_ALT_FN_2_IN) #define GPIO95_KP_MKIN6_MD (95 | GPIO_ALT_FN_3_IN) #define GPIO96_KP_DKIN3_MD (96 | GPIO_ALT_FN_1_IN) +#define GPIO96_FFRXD_MD (96 | GPIO_ALT_FN_3_IN) #define GPIO97_KP_MKIN3_MD (97 | GPIO_ALT_FN_3_IN) #define GPIO98_CIF_DD_0_MD (98 | GPIO_ALT_FN_2_IN) +#define GPIO98_FFRTS_MD (98 | GPIO_ALT_FN_3_OUT) +#define GPIO99_FFTXD_MD (99 | GPIO_ALT_FN_3_OUT) #define GPIO100_KP_MKIN0_MD (100 | GPIO_ALT_FN_1_IN) #define GPIO101_KP_MKIN1_MD (101 | GPIO_ALT_FN_1_IN) #define GPIO102_nPCE_1_MD (102 | GPIO_ALT_FN_1_OUT) -- cgit v1.2.3 From ea6a7404da4b381b35bcec48338d376a3873ea46 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 30 May 2008 18:53:55 +0100 Subject: [ARM] 5070/1: pxa: add GPIO104_PSKTSEL to pxa27x MFP configuration PSKTSEL can be routed to GPIO pin 104. This configuration is used by HP iPAQ hx4700. Signed-off-by: Philipp Zabel Acked-by: Jrgen Schindele Signed-off-by: Russell King --- include/asm-arm/arch-pxa/mfp-pxa27x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-arm/arch-pxa/mfp-pxa27x.h b/include/asm-arm/arch-pxa/mfp-pxa27x.h index eb6eaa174f8d..bc73ab84167c 100644 --- a/include/asm-arm/arch-pxa/mfp-pxa27x.h +++ b/include/asm-arm/arch-pxa/mfp-pxa27x.h @@ -112,6 +112,7 @@ #define GPIO57_nIOIS16 MFP_CFG_IN(GPIO57, AF1) #define GPIO56_nPWAIT MFP_CFG_IN(GPIO56, AF1) #define GPIO79_PSKTSEL MFP_CFG_OUT(GPIO79, AF1, DRIVE_HIGH) +#define GPIO104_PSKTSEL MFP_CFG_OUT(GPIO104, AF1, DRIVE_HIGH) /* I2C */ #define GPIO117_I2C_SCL MFP_CFG_IN(GPIO117, AF1) -- cgit v1.2.3 From 1e5c594607778f551b729577b046ee5d9333cfb5 Mon Sep 17 00:00:00 2001 From: surinder Date: Wed, 28 May 2008 09:51:16 +0100 Subject: [ARM] 5067/1: _raw_write_can_lock macro bugfix The current __raw_write_can_lock macro tests whether the lock can be locked by checking if it is equal to 0x80000000, whereas the lock should be lockable if its value is 0 i.e. unlocked state is represented by 0. Hence the macro should test the value of lock against 0 and not 0x80000000. Signed-off-by: Surinder Pal Singh Signed-off-by: Russell King --- include/asm-arm/spinlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-arm/spinlock.h b/include/asm-arm/spinlock.h index 800ba5254daf..2b41ebbfa7ff 100644 --- a/include/asm-arm/spinlock.h +++ b/include/asm-arm/spinlock.h @@ -142,7 +142,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) } /* write_can_lock - would write_trylock() succeed? */ -#define __raw_write_can_lock(x) ((x)->lock == 0x80000000) +#define __raw_write_can_lock(x) ((x)->lock == 0) /* * Read locks are a bit more hairy: -- cgit v1.2.3 From 63e14626eddb534ab429e9c2b95d3f7038b596b6 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sun, 1 Jun 2008 11:49:32 +0200 Subject: mmc_spi: mmc_spi.h should include linux/interrupts.h Since mmc_spi.h uses irqreturn_t type, it should include appropriate header, otherwise build will break if users didn't include it (some of them do not use interrupts). Signed-off-by: Anton Vorontsov Signed-off-by: Pierre Ossman Signed-off-by: Linus Torvalds --- include/linux/spi/mmc_spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/spi/mmc_spi.h b/include/linux/spi/mmc_spi.h index e9bbe3ebd721..d5ca78b93a3b 100644 --- a/include/linux/spi/mmc_spi.h +++ b/include/linux/spi/mmc_spi.h @@ -1,6 +1,8 @@ #ifndef __LINUX_SPI_MMC_SPI_H #define __LINUX_SPI_MMC_SPI_H +#include + struct device; struct mmc_host; -- cgit v1.2.3 From 1feaa51d84e9611521ec6e59172f9f90db274588 Mon Sep 17 00:00:00 2001 From: Sonic Zhang Date: Tue, 3 Jun 2008 12:19:45 +0800 Subject: Blackfin Serial Driver: Clean up BF54x macro in blackfin UART driver. Hide difference in head file. Signed-off-by: Sonic Zhang Signed-off-by: Bryan Wu --- drivers/serial/bfin_5xx.c | 30 ++++------------------- include/asm-blackfin/mach-bf527/bfin_serial_5xx.h | 6 +++++ include/asm-blackfin/mach-bf533/bfin_serial_5xx.h | 6 +++++ include/asm-blackfin/mach-bf537/bfin_serial_5xx.h | 6 +++++ include/asm-blackfin/mach-bf548/bfin_serial_5xx.h | 6 +++++ include/asm-blackfin/mach-bf561/bfin_serial_5xx.h | 6 +++++ 6 files changed, 35 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/serial/bfin_5xx.c b/drivers/serial/bfin_5xx.c index d6b4ead693b7..636b6876c6fb 100644 --- a/drivers/serial/bfin_5xx.c +++ b/drivers/serial/bfin_5xx.c @@ -530,11 +530,7 @@ static unsigned int bfin_serial_get_mctrl(struct uart_port *port) if (uart->cts_pin < 0) return TIOCM_CTS | TIOCM_DSR | TIOCM_CAR; -# ifdef BF54x - if (UART_GET_MSR(uart) & CTS) -# else - if (gpio_get_value(uart->cts_pin)) -# endif + if (UART_GET_CTS(uart)) return TIOCM_DSR | TIOCM_CAR; else #endif @@ -549,17 +545,9 @@ static void bfin_serial_set_mctrl(struct uart_port *port, unsigned int mctrl) return; if (mctrl & TIOCM_RTS) -# ifdef BF54x - UART_PUT_MCR(uart, UART_GET_MCR(uart) & ~MRTS); -# else - gpio_set_value(uart->rts_pin, 0); -# endif + UART_CLEAR_RTS(uart); else -# ifdef BF54x - UART_PUT_MCR(uart, UART_GET_MCR(uart) | MRTS); -# else - gpio_set_value(uart->rts_pin, 1); -# endif + UART_SET_RTS(uart); #endif } @@ -752,11 +740,7 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios, /* Disable UART */ ier = UART_GET_IER(uart); -#ifdef CONFIG_BF54x - UART_CLEAR_IER(uart, 0xF); -#else - UART_PUT_IER(uart, 0); -#endif + UART_DISABLE_INTS(uart); /* Set DLAB in LCR to Access DLL and DLH */ UART_SET_DLAB(uart); @@ -771,11 +755,7 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios, UART_PUT_LCR(uart, lcr); /* Enable UART */ -#ifdef CONFIG_BF54x - UART_SET_IER(uart, ier); -#else - UART_PUT_IER(uart, ier); -#endif + UART_ENABLE_INTS(uart, ier); val = UART_GET_GCTL(uart); val |= UCEN; diff --git a/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h index 26e3c8076b4e..96bd09e31e36 100644 --- a/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h +++ b/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h @@ -53,6 +53,12 @@ #define UART_SET_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) | DLAB); SSYNC(); } while (0) #define UART_CLEAR_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) & ~DLAB); SSYNC(); } while (0) +#define UART_GET_CTS(x) gpio_get_value(x->cts_pin) +#define UART_SET_RTS(x) gpio_set_value(x->rts_pin, 1) +#define UART_CLEAR_RTS(x) gpio_set_value(x->rts_pin, 0) +#define UART_ENABLE_INTS(x, v) UART_PUT_IER(x, v) +#define UART_DISABLE_INTS(x) UART_PUT_IER(x, 0) + #if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) # define CONFIG_SERIAL_BFIN_CTSRTS diff --git a/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h index d016603b6615..e924569ad1d8 100644 --- a/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h +++ b/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h @@ -53,6 +53,12 @@ #define UART_SET_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) | DLAB); SSYNC(); } while (0) #define UART_CLEAR_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) & ~DLAB); SSYNC(); } while (0) +#define UART_GET_CTS(x) gpio_get_value(x->cts_pin) +#define UART_SET_RTS(x) gpio_set_value(x->rts_pin, 1) +#define UART_CLEAR_RTS(x) gpio_set_value(x->rts_pin, 0) +#define UART_ENABLE_INTS(x, v) UART_PUT_IER(x, v) +#define UART_DISABLE_INTS(x) UART_PUT_IER(x, 0) + #ifdef CONFIG_BFIN_UART0_CTSRTS # define CONFIG_SERIAL_BFIN_CTSRTS # ifndef CONFIG_UART0_CTS_PIN diff --git a/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h index f79d1a0e9129..41d7b6490bb1 100644 --- a/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h +++ b/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h @@ -53,6 +53,12 @@ #define UART_SET_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) | DLAB); SSYNC(); } while (0) #define UART_CLEAR_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) & ~DLAB); SSYNC(); } while (0) +#define UART_GET_CTS(x) gpio_get_value(x->cts_pin) +#define UART_SET_RTS(x) gpio_set_value(x->rts_pin, 1) +#define UART_CLEAR_RTS(x) gpio_set_value(x->rts_pin, 0) +#define UART_ENABLE_INTS(x, v) UART_PUT_IER(x, v) +#define UART_DISABLE_INTS(x) UART_PUT_IER(x, 0) + #if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) # define CONFIG_SERIAL_BFIN_CTSRTS diff --git a/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h index 5eb46a77d919..59b4ad4e5b4a 100644 --- a/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h +++ b/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h @@ -57,6 +57,12 @@ #define UART_SET_DLAB(uart) /* MMRs not muxed on BF54x */ #define UART_CLEAR_DLAB(uart) /* MMRs not muxed on BF54x */ +#define UART_GET_CTS(x) (UART_GET_MSR(x) & CTS) +#define UART_SET_RTS(x) (UART_PUT_MCR(x, UART_GET_MCR(x) | MRTS)) +#define UART_CLEAR_RTS(x) (UART_PUT_MCR(x, UART_GET_MCR(x) & ~MRTS)) +#define UART_ENABLE_INTS(x, v) UART_SET_IER(x, v) +#define UART_DISABLE_INTS(x) UART_CLEAR_IER(x, 0xF) + #if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) # define CONFIG_SERIAL_BFIN_CTSRTS diff --git a/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h index 7a9628769296..30d90b580f18 100644 --- a/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h +++ b/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h @@ -53,6 +53,12 @@ #define UART_SET_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) | DLAB); SSYNC(); } while (0) #define UART_CLEAR_DLAB(uart) do { UART_PUT_LCR(uart, UART_GET_LCR(uart) & ~DLAB); SSYNC(); } while (0) +#define UART_GET_CTS(x) gpio_get_value(x->cts_pin) +#define UART_SET_RTS(x) gpio_set_value(x->rts_pin, 1) +#define UART_CLEAR_RTS(x) gpio_set_value(x->rts_pin, 0) +#define UART_ENABLE_INTS(x, v) UART_PUT_IER(x, v) +#define UART_DISABLE_INTS(x) UART_PUT_IER(x, 0) + #ifdef CONFIG_BFIN_UART0_CTSRTS # define CONFIG_SERIAL_BFIN_CTSRTS # ifndef CONFIG_UART0_CTS_PIN -- cgit v1.2.3 From 64e9159f5d2c4edf5fa6425031e556f8fddaf7e6 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 3 Jun 2008 15:18:54 +0100 Subject: serial_core: uart_set_ldisc infrastructure The tty layer provides a callback that is used when the line discipline is changed. Some hardware uses this to configure hardware specific features such as IrDA mode on serial ports. Unfortunately the serial layer does not provide this feature or pass it down to drivers. Blackfin used to hack around this by rewriting the tty ops, but those are now properly shared and const so the hack fails. Instead provide the proper operations. This change plus a follow up from the Blackfin guys is needed to avoid blackfin losing features in this release. Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- drivers/serial/serial_core.c | 10 ++++++++++ include/linux/serial_core.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c index 53b03c629aff..951a75ea6e3e 100644 --- a/drivers/serial/serial_core.c +++ b/drivers/serial/serial_core.c @@ -1165,6 +1165,15 @@ out: return ret; } +static void uart_set_ldisc(struct tty_struct *tty, int ldisc) +{ + struct uart_state *state = tty->driver_data; + struct uart_port *port = state->port; + + if (port->ops->set_ldisc) + port->ops->set_ldisc(port); +} + static void uart_set_termios(struct tty_struct *tty, struct ktermios *old_termios) { @@ -2288,6 +2297,7 @@ static const struct tty_operations uart_ops = { .unthrottle = uart_unthrottle, .send_xchar = uart_send_xchar, .set_termios = uart_set_termios, + .set_ldisc = uart_set_ldisc, .stop = uart_stop, .start = uart_start, .hangup = uart_hangup, diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d32123ae08ad..d8f31de632c5 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -192,6 +192,7 @@ struct uart_ops { void (*shutdown)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + void (*set_ldisc)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); int (*set_wake)(struct uart_port *, unsigned int state); -- cgit v1.2.3 From 51b77cae0d5aa8e1546fca855dcfe48ddfadfa9c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Jun 2008 16:36:01 -0700 Subject: route: Mark unused route cache flags as such. Also removes an obsolete check for the unused flag RTCF_MASQ. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/in_route.h | 12 ++++++------ net/ipv4/route.c | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/in_route.h b/include/linux/in_route.h index 61f25c30a2a0..b261b8c915f0 100644 --- a/include/linux/in_route.h +++ b/include/linux/in_route.h @@ -10,19 +10,19 @@ #define RTCF_NOPMTUDISC RTM_F_NOPMTUDISC #define RTCF_NOTIFY 0x00010000 -#define RTCF_DIRECTDST 0x00020000 +#define RTCF_DIRECTDST 0x00020000 /* unused */ #define RTCF_REDIRECTED 0x00040000 -#define RTCF_TPROXY 0x00080000 +#define RTCF_TPROXY 0x00080000 /* unused */ -#define RTCF_FAST 0x00200000 -#define RTCF_MASQ 0x00400000 -#define RTCF_SNAT 0x00800000 +#define RTCF_FAST 0x00200000 /* unused */ +#define RTCF_MASQ 0x00400000 /* unused */ +#define RTCF_SNAT 0x00800000 /* unused */ #define RTCF_DOREDIRECT 0x01000000 #define RTCF_DIRECTSRC 0x04000000 #define RTCF_DNAT 0x08000000 #define RTCF_BROADCAST 0x10000000 #define RTCF_MULTICAST 0x20000000 -#define RTCF_REJECT 0x40000000 +#define RTCF_REJECT 0x40000000 /* unused */ #define RTCF_LOCAL 0x80000000 #define RTCF_NAT (RTCF_DNAT|RTCF_SNAT) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index df41026b60db..96be336064fb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1792,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb, if (err) flags |= RTCF_DIRECTSRC; - if (out_dev == in_dev && err && !(flags & RTCF_MASQ) && + if (out_dev == in_dev && err && (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) flags |= RTCF_DOREDIRECT; -- cgit v1.2.3 From 1f9d11c7c99da706e33646c3a9080dd5a8ef9a0b Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Jun 2008 16:36:27 -0700 Subject: route: Mark unused routing attributes as such Also removes an unused policy entry for an attribute which is only used in kernel->user direction. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 ++-- net/ipv4/fib_frontend.c | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 44c81c744538..a2aec2c0cfb5 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -267,10 +267,10 @@ enum rtattr_type_t RTA_PREFSRC, RTA_METRICS, RTA_MULTIPATH, - RTA_PROTOINFO, + RTA_PROTOINFO, /* no longer used */ RTA_FLOW, RTA_CACHEINFO, - RTA_SESSION, + RTA_SESSION, /* no longer used */ RTA_MP_ALGO, /* no longer used */ RTA_TABLE, __RTA_MAX diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0f1557a4ac7a..0b2ac6a3d903 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -506,7 +506,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, - [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, }; -- cgit v1.2.3 From bc3ed28caaef55e7e3a9316464256353c5f9b1df Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Jun 2008 16:36:54 -0700 Subject: netlink: Improve returned error codes Make nlmsg_trim(), nlmsg_cancel(), genlmsg_cancel(), and nla_nest_cancel() void functions. Return -EMSGSIZE instead of -1 if the provided message buffer is not big enough. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/genetlink.h | 4 ++-- include/net/netlink.h | 20 +++++++++----------- net/core/neighbour.c | 3 ++- net/core/rtnetlink.c | 3 ++- net/netlink/attr.c | 12 ++++++------ net/netlink/genetlink.c | 6 ++++-- net/sched/sch_dsmark.c | 6 ++++-- net/sched/sch_gred.c | 3 ++- net/sched/sch_hfsc.c | 2 +- net/sched/sch_red.c | 3 ++- net/wireless/nl80211.c | 12 ++++++++---- 11 files changed, 42 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index decdda546829..747c255d1df0 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -162,9 +162,9 @@ static inline int genlmsg_end(struct sk_buff *skb, void *hdr) * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ -static inline int genlmsg_cancel(struct sk_buff *skb, void *hdr) +static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { - return nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/netlink.h b/include/net/netlink.h index 112dcdf7e34e..dfc3701dfcc3 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -556,14 +556,12 @@ static inline void *nlmsg_get_pos(struct sk_buff *skb) * @skb: socket buffer the message is stored in * @mark: mark to trim to * - * Trims the message to the provided mark. Returns -1. + * Trims the message to the provided mark. */ -static inline int nlmsg_trim(struct sk_buff *skb, const void *mark) +static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) skb_trim(skb, (unsigned char *) mark - skb->data); - - return -1; } /** @@ -572,11 +570,11 @@ static inline int nlmsg_trim(struct sk_buff *skb, const void *mark) * @nlh: netlink message header * * Removes the complete netlink message including all - * attributes from the socket buffer again. Returns -1. + * attributes from the socket buffer again. */ -static inline int nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) +static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { - return nlmsg_trim(skb, nlh); + nlmsg_trim(skb, nlh); } /** @@ -775,7 +773,7 @@ static inline int __nla_parse_nested_compat(struct nlattr *tb[], int maxtype, int nested_len = nla_len(nla) - NLA_ALIGN(len); if (nested_len < 0) - return -1; + return -EINVAL; if (nested_len >= nla_attr_size(0)) return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy); @@ -1080,11 +1078,11 @@ static inline int nla_nest_compat_end(struct sk_buff *skb, struct nlattr *start) * @start: container attribute * * Removes the container attribute and including all nested - * attributes. Returns -1. + * attributes. Returns -EMSGSIZE */ -static inline int nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) +static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { - return nlmsg_trim(skb, start); + nlmsg_trim(skb, start); } /** diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 3896de79dfbf..65f01f71b3f3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1714,7 +1714,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) return nla_nest_end(skb, nest); nla_put_failure: - return nla_nest_cancel(skb, nest); + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cf857c4dc7b1..a9a77216310e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -498,7 +498,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) return nla_nest_end(skb, mx); nla_put_failure: - return nla_nest_cancel(skb, mx); + nla_nest_cancel(skb, mx); + return -EMSGSIZE; } int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, diff --git a/net/netlink/attr.c b/net/netlink/attr.c index feb326f4a752..47bbf45ae5d7 100644 --- a/net/netlink/attr.c +++ b/net/netlink/attr.c @@ -400,13 +400,13 @@ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) - return -1; + return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; @@ -418,13 +418,13 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; @@ -436,13 +436,13 @@ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; memcpy(skb_put(skb, attrlen), data, attrlen); return 0; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d16929c9b4bc..f5aa23c3e886 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -554,7 +554,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, @@ -590,7 +591,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0df911fd67b1..64465bacbe79 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -444,7 +444,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -466,7 +467,8 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static const struct Qdisc_class_ops dsmark_class_ops = { diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 3a9d226ff1e4..c89fba56db56 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -582,7 +582,8 @@ append_opt: return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static void gred_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 87293d0db1d7..fdfaa3fcc16d 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1360,7 +1360,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, nla_put_failure: nla_nest_cancel(skb, nest); - return -1; + return -EMSGSIZE; } static int diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 3dcd493f4f4a..5c569853b9c0 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -281,7 +281,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2bdd4dddc0e1..fb75f265b39c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -187,7 +187,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) @@ -273,7 +274,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *cb) @@ -928,7 +930,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_station(struct sk_buff *skb, @@ -1267,7 +1270,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_mpath(struct sk_buff *skb, -- cgit v1.2.3 From ab32cd793dca21eec846a8204390d9594ed994d5 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Jun 2008 16:37:33 -0700 Subject: route: Remove unused ifa_anycast field The field was supposed to allow the creation of an anycast route by assigning an anycast address to an address prefix. It was never implemented so this field is unused and serves no purpose. Remove it. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 - net/ipv4/devinet.c | 9 --------- 2 files changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 7009b0cdd06f..c6f51ad52d5b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -117,7 +117,6 @@ struct in_ifaddr __be32 ifa_address; __be32 ifa_mask; __be32 ifa_broadcast; - __be32 ifa_anycast; unsigned char ifa_scope; unsigned char ifa_flags; unsigned char ifa_prefixlen; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6848e4760f34..79a7ef6209ff 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -90,7 +90,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, - [IFA_ANYCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; @@ -536,9 +535,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); - if (tb[IFA_ANYCAST]) - ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]); - if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else @@ -745,7 +741,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; - ifa->ifa_anycast = 0; ifa->ifa_scope = 0; } @@ -1113,7 +1108,6 @@ static inline size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(4) /* IFA_ANYCAST */ + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } @@ -1143,9 +1137,6 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, if (ifa->ifa_broadcast) NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); - if (ifa->ifa_anycast) - NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast); - if (ifa->ifa_label[0]) NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); -- cgit v1.2.3 From 4f0ebe3cc57f18ba26317b56b80b108c2848b1de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 May 2008 02:17:50 +0900 Subject: libata: kill unused constants Kill a few unused constants. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 4a92fbafce9d..93e2b89d0c57 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -111,13 +111,10 @@ enum { /* various global constants */ LIBATA_MAX_PRD = ATA_MAX_PRD / 2, LIBATA_DUMB_MAX_PRD = ATA_MAX_PRD / 4, /* Worst case */ - ATA_MAX_PORTS = 8, ATA_DEF_QUEUE = 1, /* tag ATA_MAX_QUEUE - 1 is reserved for internal commands */ ATA_MAX_QUEUE = 32, ATA_TAG_INTERNAL = ATA_MAX_QUEUE - 1, - ATA_MAX_BUS = 2, - ATA_DEF_BUSY_WAIT = 10000, ATA_SHORT_PAUSE = (HZ >> 6) + 1, ATAPI_MAX_DRAIN = 16 << 10, -- cgit v1.2.3 From a57c1bade5a0ee5cd8b74502db9cbebb7f5780b2 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 29 May 2008 22:10:58 +0100 Subject: libata-sff: Fix oops reported in kerneloops.org for pnp devices with no ctl - Make ata_sff_altstatus private so nobody uses it by mistake - Drop the 400nS delay from it Add ata_sff_irq_status - encapsulates the IRQ check logic This function keeps the existing behaviour for altstatus using devices. I actually suspect the logic was wrong before the changes but -rc isn't the time to play with that ata_sff_sync - ensure writes hit the device Really we want an io* operation for 'is posted' eg ioisposted(ioaddr) so that we can fix the nasty delay this causes on most systems. - ata_sff_pause - 400nS delay Ensure the command hit the device and delay 400nS - ata_sff_dma_pause Ensure the I/O hit the device and enforce an HDMA1:0 transition delay. Requires altstatus register exists, BUG if not so we don't risk corruption in MWDMA modes. (UDMA the checksum will save your backside in theory) The only other complication then is devices with their own handlers. rb532 can use dma_pause but scc needs to access its own altstatus register for internal errata workarounds so directly call the drivers own altstatus function. Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- drivers/ata/libata-sff.c | 115 ++++++++++++++++++++++++++++++++++++++------ drivers/ata/pata_icside.c | 2 +- drivers/ata/pata_rb532_cf.c | 4 +- drivers/ata/pata_scc.c | 5 +- include/linux/libata.h | 16 +----- 5 files changed, 109 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 3c2d2289f85e..90d20c615ef5 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -247,7 +247,7 @@ u8 ata_sff_check_status(struct ata_port *ap) * LOCKING: * Inherited from caller. */ -u8 ata_sff_altstatus(struct ata_port *ap) +static u8 ata_sff_altstatus(struct ata_port *ap) { if (ap->ops->sff_check_altstatus) return ap->ops->sff_check_altstatus(ap); @@ -255,6 +255,93 @@ u8 ata_sff_altstatus(struct ata_port *ap) return ioread8(ap->ioaddr.altstatus_addr); } +/** + * ata_sff_irq_status - Check if the device is busy + * @ap: port where the device is + * + * Determine if the port is currently busy. Uses altstatus + * if available in order to avoid clearing shared IRQ status + * when finding an IRQ source. Non ctl capable devices don't + * share interrupt lines fortunately for us. + * + * LOCKING: + * Inherited from caller. + */ +static u8 ata_sff_irq_status(struct ata_port *ap) +{ + u8 status; + + if (ap->ops->sff_check_altstatus || ap->ioaddr.altstatus_addr) { + status = ata_sff_altstatus(ap); + /* Not us: We are busy */ + if (status & ATA_BUSY) + return status; + } + /* Clear INTRQ latch */ + status = ata_sff_check_status(ap); + return status; +} + +/** + * ata_sff_sync - Flush writes + * @ap: Port to wait for. + * + * CAUTION: + * If we have an mmio device with no ctl and no altstatus + * method this will fail. No such devices are known to exist. + * + * LOCKING: + * Inherited from caller. + */ + +static void ata_sff_sync(struct ata_port *ap) +{ + if (ap->ops->sff_check_altstatus) + ap->ops->sff_check_altstatus(ap); + else if (ap->ioaddr.altstatus_addr) + ioread8(ap->ioaddr.altstatus_addr); +} + +/** + * ata_sff_pause - Flush writes and wait 400nS + * @ap: Port to pause for. + * + * CAUTION: + * If we have an mmio device with no ctl and no altstatus + * method this will fail. No such devices are known to exist. + * + * LOCKING: + * Inherited from caller. + */ + +void ata_sff_pause(struct ata_port *ap) +{ + ata_sff_sync(ap); + ndelay(400); +} + +/** + * ata_sff_dma_pause - Pause before commencing DMA + * @ap: Port to pause for. + * + * Perform I/O fencing and ensure sufficient cycle delays occur + * for the HDMA1:0 transition + */ + +void ata_sff_dma_pause(struct ata_port *ap) +{ + if (ap->ops->sff_check_altstatus || ap->ioaddr.altstatus_addr) { + /* An altstatus read will cause the needed delay without + messing up the IRQ status */ + ata_sff_altstatus(ap); + return; + } + /* There are no DMA controllers without ctl. BUG here to ensure + we never violate the HDMA1:0 transition timing and risk + corruption. */ + BUG(); +} + /** * ata_sff_busy_sleep - sleep until BSY clears, or timeout * @ap: port containing status register to be polled @@ -742,7 +829,7 @@ static void ata_pio_sectors(struct ata_queued_cmd *qc) } else ata_pio_sector(qc); - ata_sff_altstatus(qc->ap); /* flush */ + ata_sff_sync(qc->ap); /* flush */ } /** @@ -763,8 +850,9 @@ static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc) WARN_ON(qc->dev->cdb_len < 12); ap->ops->sff_data_xfer(qc->dev, qc->cdb, qc->dev->cdb_len, 1); - ata_sff_altstatus(ap); /* flush */ - + ata_sff_sync(ap); + /* FIXME: If the CDB is for DMA do we need to do the transition delay + or is bmdma_start guaranteed to do it ? */ switch (qc->tf.protocol) { case ATAPI_PROT_PIO: ap->hsm_task_state = HSM_ST; @@ -905,7 +993,7 @@ static void atapi_pio_bytes(struct ata_queued_cmd *qc) if (unlikely(__atapi_pio_bytes(qc, bytes))) goto err_out; - ata_sff_altstatus(ap); /* flush */ + ata_sff_sync(ap); /* flush */ return; @@ -1489,14 +1577,10 @@ inline unsigned int ata_sff_host_intr(struct ata_port *ap, goto idle_irq; } - /* check altstatus */ - status = ata_sff_altstatus(ap); - if (status & ATA_BUSY) - goto idle_irq; - /* check main status, clearing INTRQ */ - status = ap->ops->sff_check_status(ap); - if (unlikely(status & ATA_BUSY)) + /* check main status, clearing INTRQ if needed */ + status = ata_sff_irq_status(ap); + if (status & ATA_BUSY) goto idle_irq; /* ack bmdma irq events */ @@ -2030,7 +2114,7 @@ void ata_sff_error_handler(struct ata_port *ap) ap->ops->bmdma_stop(qc); } - ata_sff_altstatus(ap); + ata_sff_sync(ap); /* FIXME: We don't need this */ ap->ops->sff_check_status(ap); ap->ops->sff_irq_clear(ap); @@ -2203,7 +2287,7 @@ void ata_bmdma_stop(struct ata_queued_cmd *qc) mmio + ATA_DMA_CMD); /* one-PIO-cycle guaranteed wait, per spec, for HDMA1:0 transition */ - ata_sff_altstatus(ap); /* dummy read */ + ata_sff_dma_pause(ap); } /** @@ -2722,7 +2806,8 @@ EXPORT_SYMBOL_GPL(ata_sff_qc_prep); EXPORT_SYMBOL_GPL(ata_sff_dumb_qc_prep); EXPORT_SYMBOL_GPL(ata_sff_dev_select); EXPORT_SYMBOL_GPL(ata_sff_check_status); -EXPORT_SYMBOL_GPL(ata_sff_altstatus); +EXPORT_SYMBOL_GPL(ata_sff_dma_pause); +EXPORT_SYMBOL_GPL(ata_sff_pause); EXPORT_SYMBOL_GPL(ata_sff_busy_sleep); EXPORT_SYMBOL_GPL(ata_sff_wait_ready); EXPORT_SYMBOL_GPL(ata_sff_tf_load); diff --git a/drivers/ata/pata_icside.c b/drivers/ata/pata_icside.c index 17138436423d..cf9e9848f8b5 100644 --- a/drivers/ata/pata_icside.c +++ b/drivers/ata/pata_icside.c @@ -270,7 +270,7 @@ static void pata_icside_bmdma_stop(struct ata_queued_cmd *qc) disable_dma(state->dma); /* see ata_bmdma_stop */ - ata_sff_altstatus(ap); + ata_sff_dma_pause(ap); } static u8 pata_icside_bmdma_status(struct ata_port *ap) diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index a108d259f19d..f8b3ffc8ae9e 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -57,7 +57,9 @@ static inline void rb532_pata_finish_io(struct ata_port *ap) struct ata_host *ah = ap->host; struct rb532_cf_info *info = ah->private_data; - ata_sff_altstatus(ap); + /* FIXME: Keep previous delay. If this is merely a fence then + ata_sff_sync might be sufficient. */ + ata_sff_dma_pause(ap); ndelay(RB500_CF_IO_DELAY); set_irq_type(info->irq, IRQ_TYPE_LEVEL_HIGH); diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c index e965b251ca24..bbf5aa345e68 100644 --- a/drivers/ata/pata_scc.c +++ b/drivers/ata/pata_scc.c @@ -726,7 +726,7 @@ static void scc_bmdma_stop (struct ata_queued_cmd *qc) in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START); /* one-PIO-cycle guaranteed wait, per spec, for HDMA1:0 transition */ - ata_sff_altstatus(ap); /* dummy read */ + ata_sff_dma_pause(ap); /* dummy read */ } /** @@ -747,7 +747,8 @@ static u8 scc_bmdma_status (struct ata_port *ap) return host_stat; /* errata A252,A308 workaround: Step4 */ - if ((ata_sff_altstatus(ap) & ATA_ERR) && (int_status & INTSTS_INTRQ)) + if ((scc_check_altstatus(ap) & ATA_ERR) + && (int_status & INTSTS_INTRQ)) return (host_stat | ATA_DMA_INTR); /* errata A308 workaround Step5 */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 93e2b89d0c57..e57e5d08312d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1432,7 +1432,8 @@ extern void ata_sff_qc_prep(struct ata_queued_cmd *qc); extern void ata_sff_dumb_qc_prep(struct ata_queued_cmd *qc); extern void ata_sff_dev_select(struct ata_port *ap, unsigned int device); extern u8 ata_sff_check_status(struct ata_port *ap); -extern u8 ata_sff_altstatus(struct ata_port *ap); +extern void ata_sff_pause(struct ata_port *ap); +extern void ata_sff_dma_pause(struct ata_port *ap); extern int ata_sff_busy_sleep(struct ata_port *ap, unsigned long timeout_pat, unsigned long timeout); extern int ata_sff_wait_ready(struct ata_link *link, unsigned long deadline); @@ -1492,19 +1493,6 @@ extern int ata_pci_sff_init_one(struct pci_dev *pdev, struct scsi_host_template *sht, void *host_priv); #endif /* CONFIG_PCI */ -/** - * ata_sff_pause - Flush writes and pause 400 nanoseconds. - * @ap: Port to wait for. - * - * LOCKING: - * Inherited from caller. - */ -static inline void ata_sff_pause(struct ata_port *ap) -{ - ata_sff_altstatus(ap); - ndelay(400); -} - /** * ata_sff_busy_wait - Wait for a port status register * @ap: Port to wait for. -- cgit v1.2.3 From e8a496ac8cd00cabbdaa373db4818a9ad19a1c5a Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 23 May 2008 16:26:37 -0700 Subject: x86: fix broken math-emu with lazy allocation of fpu area Fix the math emulation that got broken with the recent lazy allocation of FPU area. init_fpu() need to be added for the math-emulation path aswell for the FPU area allocation. math emulation enabled kernel booted fine with this, in the presence of "no387 nofxsr" boot param. Signed-off-by: Suresh Siddha Cc: hpa@zytor.com Cc: mingo@elte.hu Signed-off-by: Thomas Gleixner --- arch/x86/kernel/i387.c | 44 ++++++++++++++++++++++++++++--------------- arch/x86/math-emu/fpu_entry.c | 13 ++++++++----- include/asm-x86/i387.h | 2 ++ 3 files changed, 39 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e03cc952f233..eb9ddd8efb82 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void) void __init init_thread_xstate(void) { + if (!HAVE_HWFP) { + xstate_size = sizeof(struct i387_soft_struct); + return; + } + if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); #ifdef CONFIG_X86_32 @@ -94,7 +99,7 @@ void __cpuinit fpu_init(void) int init_fpu(struct task_struct *tsk) { if (tsk_used_math(tsk)) { - if (tsk == current) + if (HAVE_HWFP && tsk == current) unlazy_fpu(tsk); return 0; } @@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk) return -ENOMEM; } +#ifdef CONFIG_X86_32 + if (!HAVE_HWFP) { + memset(tsk->thread.xstate, 0, xstate_size); + finit(); + set_stopped_child_used_math(tsk); + return 0; + } +#endif + if (cpu_has_fxsr) { struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; @@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; + if (!HAVE_HWFP) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, @@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; set_stopped_child_used_math(target); + if (!HAVE_HWFP) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, -1); @@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf) int restore_i387_ia32(struct _fpstate_ia32 __user *buf) { int err; + struct task_struct *tsk = current; - if (HAVE_HWFP) { - struct task_struct *tsk = current; - + if (HAVE_HWFP) clear_fpu(tsk); - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + if (HAVE_HWFP) { if (cpu_has_fxsr) err = restore_i387_fxsave(buf); else diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 6e38d877ea77..c7b06feb139b 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "fpu_system.h" #include "fpu_emu.h" @@ -146,6 +147,13 @@ asmlinkage void math_emulate(long arg) unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + if (!used_math()) { + if (init_fpu(current)) { + do_group_exit(SIGKILL); + return; + } + } + #ifdef RE_ENTRANT_CHECKING if (emulating) { printk("ERROR: wm-FPU-emu is not RE-ENTRANT!\n"); @@ -153,11 +161,6 @@ asmlinkage void math_emulate(long arg) RE_ENTRANT_CHECK_ON; #endif /* RE_ENTRANT_CHECKING */ - if (!used_math()) { - finit(); - set_used_math(); - } - SETUP_DATA_AREA(arg); FPU_ORIG_EIP = FPU_EIP; diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h index 6b722d315936..37672f79dcc8 100644 --- a/include/asm-x86/i387.h +++ b/include/asm-x86/i387.h @@ -193,6 +193,8 @@ static inline int restore_i387(struct _fpstate __user *buf) #else /* CONFIG_X86_32 */ +extern void finit(void); + static inline void tolerant_fwait(void) { asm volatile("fnclex ; fwait"); -- cgit v1.2.3 From e51171019bb0e1f9fb57c25bd2e38ce652eaea27 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 29 May 2008 19:55:05 +0900 Subject: [SCTP]: Fix NULL dereference of asoc. Commit 7cbca67c073263c179f605bdbbdc565ab29d801d ("[IPV6]: Support Source Address Selection API (RFC5014)") introduced NULL dereference of asoc to sctp_v6_get_saddr in net/sctp/ipv6.c. Pointed out by Johann Felix Soden . Signed-off-by: YOSHIFUJI Hideaki --- include/net/sctp/structs.h | 3 ++- net/sctp/ipv6.c | 5 +++-- net/sctp/protocol.c | 3 ++- net/sctp/transport.c | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0ce0443c5b79..917d425f0542 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -548,7 +548,8 @@ struct sctp_af { struct dst_entry *(*get_dst) (struct sctp_association *asoc, union sctp_addr *daddr, union sctp_addr *saddr); - void (*get_saddr) (struct sctp_association *asoc, + void (*get_saddr) (struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e45e44c60635..e4aac3266fcd 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, /* Fills in the source address(saddr) based on the destination address(daddr) * and asoc's bind address list. */ -static void sctp_v6_get_saddr(struct sctp_association *asoc, +static void sctp_v6_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (!asoc) { ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, - inet6_sk(asoc->base.sk)->srcprefs, + inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 0ec234b762c2..13ee7fa92e07 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -519,7 +519,8 @@ out: /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ -static void sctp_v4_get_saddr(struct sctp_association *asoc, +static void sctp_v4_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index f4938f6c5abe..62082e7b7972 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -291,7 +291,7 @@ void sctp_transport_route(struct sctp_transport *transport, if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else - af->get_saddr(asoc, dst, daddr, &transport->saddr); + af->get_saddr(opt, asoc, dst, daddr, &transport->saddr); transport->dst = dst; if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { -- cgit v1.2.3 From 4bed72e4f5502ea3322f0a00794815fa58951abe Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 27 May 2008 17:37:49 +0900 Subject: [IPV6] ADDRCONF: Allow longer lifetime on 64bit archs. - Allow longer lifetimes (>= 0x7fffffff/HZ) on 64bit archs by using unsigned long. - Shadow this arithmetic overflow workaround by introducing helper functions: addrconf_timeout_fixup() and addrconf_finite_timeout(). Signed-off-by: YOSHIFUJI Hideaki --- include/net/addrconf.h | 22 ++++++++++++ net/ipv6/addrconf.c | 97 ++++++++++++++++++++++++++------------------------ net/ipv6/route.c | 12 ++----- 3 files changed, 75 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 0a2f0372df31..bbd3d583c6e6 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -94,6 +94,28 @@ extern void addrconf_join_solict(struct net_device *dev, extern void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr); +static inline unsigned long addrconf_timeout_fixup(u32 timeout, + unsigned unit) +{ + if (timeout == 0xffffffff) + return ~0UL; + + /* + * Avoid arithmetic overflow. + * Assuming unit is constant and non-zero, this "if" statement + * will go away on 64bit archs. + */ + if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit) + return LONG_MAX / unit; + + return timeout; +} + +static inline int addrconf_finite_timeout(unsigned long timeout) +{ + return ~timeout; +} + /* * IPv6 Address Label subsystem (addrlabel.c) */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c3b20c5afa3e..147588f4c7c0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -731,8 +731,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) onlink = -1; spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ if (time_before(expires, ifa->tstamp + lifetime * HZ)) expires = ifa->tstamp + lifetime * HZ; @@ -1722,7 +1727,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; pinfo = (struct prefix_info *) opt; @@ -1764,28 +1768,23 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) * 2) Configure prefixes with the auto flag set */ - if (valid_lft == INFINITY_LIFE_TIME) - rt_expires = ~0UL; - else if (valid_lft >= 0x7FFFFFFF/HZ) { + if (pinfo->onlink) { + struct rt6_info *rt; + unsigned long rt_expires; + /* Avoid arithmetic overflow. Really, we could * save rt_expires in seconds, likely valid_lft, * but it would require division in fib gc, that it * not good. */ - rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); - } else - rt_expires = valid_lft * HZ; + if (HZ > USER_HZ) + rt_expires = addrconf_timeout_fixup(valid_lft, HZ); + else + rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); - /* - * We convert this (in jiffies) to clock_t later. - * Avoid arithmetic overflow there as well. - * Overflow can happen only if HZ < USER_HZ. - */ - if (HZ < USER_HZ && ~rt_expires && rt_expires > 0x7FFFFFFF / USER_HZ) - rt_expires = 0x7FFFFFFF / USER_HZ; + if (addrconf_finite_timeout(rt_expires)) + rt_expires *= HZ; - if (pinfo->onlink) { - struct rt6_info *rt; rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, dev->ifindex, 1); @@ -1794,7 +1793,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (valid_lft == 0) { ip6_del_rt(rt); rt = NULL; - } else if (~rt_expires) { + } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ rt->rt6i_expires = jiffies + rt_expires; rt->rt6i_flags |= RTF_EXPIRES; @@ -1803,9 +1802,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) rt->rt6i_expires = 0; } } else if (valid_lft) { - int flags = RTF_ADDRCONF | RTF_PREFIX_RT; clock_t expires = 0; - if (~rt_expires) { + int flags = RTF_ADDRCONF | RTF_PREFIX_RT; + if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ flags |= RTF_EXPIRES; expires = jiffies_to_clock_t(rt_expires); @@ -2036,6 +2035,7 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, int scope; u32 flags; clock_t expires; + unsigned long timeout; ASSERT_RTNL(); @@ -2055,22 +2055,23 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, scope = ipv6_addr_scope(pfx); - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); @@ -3175,26 +3176,28 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, { u32 flags; clock_t expires; + unsigned long timeout; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } spin_lock_bh(&ifp->lock); ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 48534c6c0735..220cffe9e63b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -446,7 +446,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; unsigned int pref; - u32 lifetime; + unsigned long lifetime; struct rt6_info *rt; if (len < sizeof(struct route_info)) { @@ -472,13 +472,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (pref == ICMPV6_ROUTER_PREF_INVALID) pref = ICMPV6_ROUTER_PREF_MEDIUM; - lifetime = ntohl(rinfo->lifetime); - if (lifetime == 0xffffffff) { - /* infinity */ - } else if (lifetime > 0x7fffffff/HZ - 1) { - /* Avoid arithmetic overflow */ - lifetime = 0x7fffffff/HZ - 1; - } + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; @@ -506,7 +500,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (lifetime == 0xffffffff) { + if (!addrconf_finite_timeout(lifetime)) { rt->rt6i_flags &= ~RTF_EXPIRES; } else { rt->rt6i_expires = jiffies + HZ * lifetime; -- cgit v1.2.3 From 91e1908f569dd96a25a3947de8771e6cc93999dd Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 4 Jun 2008 13:02:49 +0900 Subject: [IPV6] NETNS: Handle ancillary data in appropriate namespace. Signed-off-by: YOSHIFUJI Hideaki --- include/net/transp_v6.h | 3 ++- net/ipv6/datagram.c | 7 ++++--- net/ipv6/ip6_flowlabel.c | 2 +- net/ipv6/ipv6_sockglue.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 27394e0447d8..112934a3288d 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -40,7 +40,8 @@ extern int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); -extern int datagram_send_ctl(struct msghdr *msg, +extern int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 53e3883f7666..b9c2de84a8a2 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -496,7 +496,8 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) return 0; } -int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, +int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass) { @@ -540,7 +541,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, addr_type = __ipv6_addr_type(&src_info->ipi6_addr); if (fl->oif) { - dev = dev_get_by_index(&init_net, fl->oif); + dev = dev_get_by_index(net, fl->oif); if (!dev) return -ENODEV; } else if (addr_type & IPV6_ADDR_LINKLOCAL) @@ -548,7 +549,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!ipv6_chk_addr(&init_net, &src_info->ipi6_addr, + if (!ipv6_chk_addr(net, &src_info->ipi6_addr, strict ? dev : NULL, 0)) err = -EINVAL; else diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index eb7a940310f4..37a4e777e347 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -354,7 +354,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 9293b9f0ac23..3eef8e5b3636 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -416,7 +416,7 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); if (retv) goto done; update: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 232e0dc45bf5..603df76e0522 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -813,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 47123bf5eb0f..1b35c4722004 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -731,7 +731,7 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; -- cgit v1.2.3 From 36d926b94a9908937593e5669162305a071b9cc3 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Wed, 4 Jun 2008 15:49:07 +0400 Subject: [IPV6]: inet_sk(sk)->cork.opt leak IPv6 UDP sockets wth IPv4 mapped address use udp_sendmsg to send the data actually. In this case ip_flush_pending_frames should be called instead of ip6_flush_pending_frames. Signed-off-by: Denis V. Lunev Signed-off-by: YOSHIFUJI Hideaki --- include/net/udp.h | 1 + net/ipv4/udp.c | 3 ++- net/ipv6/udp.c | 4 +++- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 3e55a99b0ba3..ccce83707046 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -135,6 +135,7 @@ extern void udp_err(struct sk_buff *, u32); extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); +extern void udp_flush_pending_frames(struct sock *sk); extern int udp_rcv(struct sk_buff *skb); extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db1cb7c96d63..56fcda3694ba 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info) /* * Throw away all pending data and cancel the corking. Socket is locked. */ -static void udp_flush_pending_frames(struct sock *sk) +void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } +EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum_outgoing - handle outgoing HW checksumming diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1b35c4722004..dd309626ae9a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -534,7 +534,9 @@ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); - if (up->pending) { + if (up->pending == AF_INET) + udp_flush_pending_frames(sk); + else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); -- cgit v1.2.3 From a6465234814efda9ed1dccdba852953f7508e827 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:38:43 -0700 Subject: sctp: Correctly implement Fast Recovery cwnd manipulations. Correctly keep track of Fast Recovery state and do not reduce congestion window multiple times during sucht state. Signed-off-by: Vlad Yasevich Tested-by: Wei Yongjun Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 8 +++++++- net/sctp/transport.c | 44 ++++++++++++++++++++++++++++++++------------ 2 files changed, 39 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 917d425f0542..67592072a32e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -902,7 +902,10 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - int rto_pending; + __u8 rto_pending; + + /* Flag to track the current fast recovery state */ + __u8 fast_recovery; /* * These are the congestion stats. @@ -921,6 +924,9 @@ struct sctp_transport { /* Data that has been sent, but not acknowledged. */ __u32 flight_size; + /* TSN marking the fast recovery exit point */ + __u32 fast_recovery_exit; + /* Destination */ struct dst_entry *dst; /* Source address. */ diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 62082e7b7972..9647fb277221 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; + peer->fast_recovery = 0; peer->last_time_heard = jiffies; peer->last_time_used = jiffies; @@ -403,11 +404,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, cwnd = transport->cwnd; flight_size = transport->flight_size; + /* See if we need to exit Fast Recovery first */ + if (transport->fast_recovery && + TSN_lte(transport->fast_recovery_exit, sack_ctsn)) + transport->fast_recovery = 0; + /* The appropriate cwnd increase algorithm is performed if, and only - * if the cumulative TSN has advanced and the congestion window is + * if the cumulative TSN whould advanced and the congestion window is * being fully utilized. */ - if ((transport->asoc->ctsn_ack_point >= sack_ctsn) || + if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) || (flight_size < cwnd)) return; @@ -416,17 +422,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, pmtu = transport->asoc->pathmtu; if (cwnd <= ssthresh) { - /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less - * than or equal to ssthresh an SCTP endpoint MUST use the - * slow start algorithm to increase cwnd only if the current - * congestion window is being fully utilized and an incoming - * SACK advances the Cumulative TSN Ack Point. Only when these - * two conditions are met can the cwnd be increased otherwise - * the cwnd MUST not be increased. If these conditions are met - * then cwnd MUST be increased by at most the lesser of - * 1) the total size of the previously outstanding DATA - * chunk(s) acknowledged, and 2) the destination's path MTU. + /* RFC 4960 7.2.1 + * o When cwnd is less than or equal to ssthresh, an SCTP + * endpoint MUST use the slow-start algorithm to increase + * cwnd only if the current congestion window is being fully + * utilized, an incoming SACK advances the Cumulative TSN + * Ack Point, and the data sender is not in Fast Recovery. + * Only when these three conditions are met can the cwnd be + * increased; otherwise, the cwnd MUST not be increased. + * If these conditions are met, then cwnd MUST be increased + * by, at most, the lesser of 1) the total size of the + * previously outstanding DATA chunk(s) acknowledged, and + * 2) the destination's path MTU. This upper bound protects + * against the ACK-Splitting attack outlined in [SAVAGE99]. */ + if (transport->fast_recovery) + return; + if (bytes_acked > pmtu) cwnd += pmtu; else @@ -502,6 +514,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * cwnd = ssthresh * partial_bytes_acked = 0 */ + if (transport->fast_recovery) + return; + + /* Mark Fast recovery */ + transport->fast_recovery = 1; + transport->fast_recovery_exit = transport->asoc->next_tsn - 1; + transport->ssthresh = max(transport->cwnd/2, 4*transport->asoc->pathmtu); transport->cwnd = transport->ssthresh; @@ -586,6 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t) t->flight_size = 0; t->error_count = 0; t->rto_pending = 0; + t->fast_recovery = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; -- cgit v1.2.3 From 62aeaff5ccd96462b7077046357a6d7886175a57 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:39:11 -0700 Subject: sctp: Start T3-RTX timer when fast retransmitting lowest TSN When we are trying to fast retransmit the lowest outstanding TSN, we need to restart the T3-RTX timer, so that subsequent timeouts will correctly tag all the packets necessary for retransmissions. Signed-off-by: Vlad Yasevich Tested-by: Wei Yongjun Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 5 ++++- net/sctp/outqueue.c | 42 +++++++++++++++++++++++++++++++----------- net/sctp/transport.c | 4 ++-- 3 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 67592072a32e..714dc43c0345 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1051,7 +1051,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, struct sctp_sock *); void sctp_transport_pmtu(struct sctp_transport *); void sctp_transport_free(struct sctp_transport *); -void sctp_transport_reset_timers(struct sctp_transport *); +void sctp_transport_reset_timers(struct sctp_transport *, int); void sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1141,6 +1141,9 @@ struct sctp_outq { /* How many unackd bytes do we have in-flight? */ __u32 outstanding_bytes; + /* Are we doing fast-rtx on this queue */ + char fast_rtx; + /* Corked? */ char cork; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 59edfd25a19c..5d3c441e84d3 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + q->fast_rtx = 0; q->outstanding_bytes = 0; q->empty = 1; q->cork = 0; @@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); + q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); @@ -543,10 +545,13 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, sctp_xmit_t status; struct sctp_chunk *chunk, *chunk1; struct sctp_association *asoc; + int fast_rtx; int error = 0; + int timer = 0; asoc = q->asoc; lqueue = &q->retransmit; + fast_rtx = q->fast_rtx; /* RFC 2960 6.3.3 Handle T3-rtx Expiration * @@ -587,13 +592,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, switch (status) { case SCTP_XMIT_PMTU_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* If we are retransmitting, we should only * send a single packet. */ - if (rtx_timeout) { + if (rtx_timeout || fast_rtx) { list_add(lchunk, lqueue); lchunk = NULL; } @@ -603,8 +607,7 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA as there is no more room * at the receiver. @@ -615,8 +618,7 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, case SCTP_XMIT_NAGLE_DELAY: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA because of nagle delay. */ list_add(lchunk, lqueue); @@ -635,7 +637,14 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->fast_retransmit > 0) chunk->fast_retransmit = -1; - *start_timer = 1; + /* Force start T3-rtx timer when fast retransmitting + * the earliest outstanding TSN + */ + if (!timer && fast_rtx && + ntohl(chunk->subh.data_hdr->tsn) == + asoc->ctsn_ack_point + 1) + timer = 2; + q->empty = 0; /* Retrieve a new chunk to bundle. */ @@ -643,12 +652,16 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, break; } + /* Set the timer if there were no errors */ + if (!error && !timer) + timer = 1; + /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ - if (rtx_timeout && !lchunk) { + if (rtx_timeout && fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit > 0) chunk1->fast_retransmit = -1; @@ -656,6 +669,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, } } + *start_timer = timer; + + /* Clear fast retransmit hint */ + if (fast_rtx) + q->fast_rtx = 0; + return error; } @@ -862,7 +881,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) rtx_timeout, &start_timer); if (start_timer) - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, + start_timer-1); /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. @@ -977,7 +997,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) list_add_tail(&chunk->transmitted_list, &transport->transmitted); - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, start_timer-1); q->empty = 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 9647fb277221..3f34f61221ec 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -191,7 +191,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport) /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ -void sctp_transport_reset_timers(struct sctp_transport *transport) +void sctp_transport_reset_timers(struct sctp_transport *transport, int force) { /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -201,7 +201,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport) * address. */ - if (!timer_pending(&transport->T3_rtx_timer)) + if (force || !timer_pending(&transport->T3_rtx_timer)) if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); -- cgit v1.2.3 From b9031d9d87b24e24cd32ea15b5f4220a1e8da909 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:40:15 -0700 Subject: sctp: Fix ECN markings for IPv6 Commit e9df2e8fd8fbc95c57dbd1d33dada66c4627b44c ("[IPV6]: Use appropriate sock tclass setting for routing lookup.") also changed the way that ECN capable transports mark this capability in IPv6. As a result, SCTP was not marking ECN capablity because the traffic class was never set. This patch brings back the markings for IPv6 traffic. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + net/sctp/ipv6.c | 6 ++++++ net/sctp/output.c | 2 +- net/sctp/protocol.c | 6 ++++++ 4 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 714dc43c0345..7f25195f9855 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -588,6 +588,7 @@ struct sctp_af { int (*is_ce) (const struct sk_buff *sk); void (*seq_dump_addr)(struct seq_file *seq, union sctp_addr *addr); + void (*ecn_capable)(struct sock *sk); __u16 net_header_len; int sockaddr_len; sa_family_t sa_family; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e4aac3266fcd..a2f4d4d51593 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -727,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr)); } +static void sctp_v6_ecn_capable(struct sock *sk) +{ + inet6_sk(sk)->tclass |= INET_ECN_ECT_0; +} + /* Initialize a PF_INET6 socket msg_name. */ static void sctp_inet6_msgname(char *msgname, int *addr_len) { @@ -997,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = { .skb_iif = sctp_v6_skb_iif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, + .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), #ifdef CONFIG_COMPAT diff --git a/net/sctp/output.c b/net/sctp/output.c index cf4f9fb6819d..6d45bae93b46 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - INET_ECN_xmit(nskb->sk); + (*tp->af_specific->ecn_capable)(nskb->sk); /* Set up the IP options. */ /* BUG: not implemented diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 56bdaf7fc425..b435a193c5df 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -617,6 +617,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); } +static void sctp_v4_ecn_capable(struct sock *sk) +{ + INET_ECN_xmit(sk); +} + /* Event handler for inet address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same @@ -935,6 +940,7 @@ static struct sctp_af sctp_af_inet = { .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, + .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT -- cgit v1.2.3 From 70345fbe4a76621808219c506f2480b39131e575 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 22 May 2008 19:30:40 -0300 Subject: V4L/DVB (7911): Remove v4l2_video_std_fps prototype declaration The v4l2_video_std_fps function has been removed by Adrian Bunk in 2004 but then its prototype re-appeared in include/media/v4l2-dev.h. Remove it. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index a807d2f86ee8..33f01ae08f76 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -40,7 +40,6 @@ #define VFL_TYPE_VTX 3 /* Video standard functions */ -extern unsigned int v4l2_video_std_fps(struct v4l2_standard *vs); extern char *v4l2_norm_to_name(v4l2_std_id id); extern int v4l2_video_std_construct(struct v4l2_standard *vs, int id, char *name); -- cgit v1.2.3 From 39028ec69b13712ec1dcd9aa14844bf60f19cb20 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 2 Jun 2008 15:46:51 -0300 Subject: V4L/DVB (7166): [v4l] Add new user class controls and deprecate others These were removed in commit 26d507fcfef7f7d0cd2eec874a87169cc121c835: > -#define V4L2_CID_HCENTER (V4L2_CID_BASE+22) > -#define V4L2_CID_VCENTER (V4L2_CID_BASE+23) > -#define V4L2_CID_LASTP1 (V4L2_CID_BASE+24) /* > last CID + 1 */ > + > +/* Deprecated, use V4L2_CID_PAN_RESET and V4L2_CID_TILT_RESET */ > +#define V4L2_CID_HCENTER_DEPRECATED (V4L2_CID_BASE+22) > +#define V4L2_CID_VCENTER_DEPRECATED (V4L2_CID_BASE+23) But there was no warning in Documentation/feature-removal-schedule.txt and I'm receiving reports that it's breaking userspace apps (the gstreamer-v4l2 plugin breaks in Fedora rawhide). You can't just pull things from the published userspace API like that. Please can we revert the addition of _DEPRECATED to these ioctl definitions. Perhaps we can add a runtime warning if they actually get used? Or a compile-time warning if we can manage that? Signed-off-by: David Woodhouse Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index c1411189ba6c..4a535ea1e123 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -865,9 +865,9 @@ struct v4l2_querymenu #define V4L2_CID_HFLIP (V4L2_CID_BASE+20) #define V4L2_CID_VFLIP (V4L2_CID_BASE+21) -/* Deprecated, use V4L2_CID_PAN_RESET and V4L2_CID_TILT_RESET */ -#define V4L2_CID_HCENTER_DEPRECATED (V4L2_CID_BASE+22) -#define V4L2_CID_VCENTER_DEPRECATED (V4L2_CID_BASE+23) +/* Deprecated; use V4L2_CID_PAN_RESET and V4L2_CID_TILT_RESET */ +#define V4L2_CID_HCENTER (V4L2_CID_BASE+22) +#define V4L2_CID_VCENTER (V4L2_CID_BASE+23) #define V4L2_CID_POWER_LINE_FREQUENCY (V4L2_CID_BASE+24) enum v4l2_power_line_frequency { -- cgit v1.2.3 From ccdb0034f8d5321be42c479dd7fc872ba2a46adb Mon Sep 17 00:00:00 2001 From: Manuel Lauss Date: Wed, 7 May 2008 13:45:23 +0200 Subject: [MIPS] Alchemy: dbdma: add API to delete custom DDMA device ids. Add API to delete custom DDMA device ids create with au1xxx_ddma_device_add(). Signed-off-by: Manuel Lauss Signed-off-by: Ralf Baechle --- arch/mips/au1000/common/dbdma.c | 11 +++++++++++ include/asm-mips/mach-au1x00/au1xxx_dbdma.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/arch/mips/au1000/common/dbdma.c b/arch/mips/au1000/common/dbdma.c index 42d555236de1..601ee9180ee4 100644 --- a/arch/mips/au1000/common/dbdma.c +++ b/arch/mips/au1000/common/dbdma.c @@ -216,6 +216,17 @@ u32 au1xxx_ddma_add_device(dbdev_tab_t *dev) } EXPORT_SYMBOL(au1xxx_ddma_add_device); +void au1xxx_ddma_del_device(u32 devid) +{ + dbdev_tab_t *p = find_dbdev_id(devid); + + if (p != NULL) { + memset(p, 0, sizeof(dbdev_tab_t)); + p->dev_id = ~0; + } +} +EXPORT_SYMBOL(au1xxx_ddma_del_device); + /* Allocate a channel and return a non-zero descriptor if successful. */ u32 au1xxx_dbdma_chan_alloc(u32 srcid, u32 destid, void (*callback)(int, void *), void *callparam) diff --git a/include/asm-mips/mach-au1x00/au1xxx_dbdma.h b/include/asm-mips/mach-au1x00/au1xxx_dbdma.h index ad17d7ce516a..44a67bf05dc1 100644 --- a/include/asm-mips/mach-au1x00/au1xxx_dbdma.h +++ b/include/asm-mips/mach-au1x00/au1xxx_dbdma.h @@ -355,6 +355,7 @@ void au1xxx_dbdma_dump(u32 chanid); u32 au1xxx_dbdma_put_dscr(u32 chanid, au1x_ddma_desc_t *dscr); u32 au1xxx_ddma_add_device(dbdev_tab_t *dev); +extern void au1xxx_ddma_del_device(u32 devid); void *au1xxx_ddma_get_nextptr_virt(au1x_ddma_desc_t *dp); /* -- cgit v1.2.3 From 057229f9efc7ebebd3ce0496195ed46df631f383 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 2 May 2008 14:08:20 +0300 Subject: [MIPS] Add missing braces to pte_mkyoung MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only the version pte_mkyoung for 36-bit pagetables on 32-bit hw was affected and with this bug being around since November 29, 2004 there is evidence to suport the assumption it was benign ;-) Signed-off-by: Ilpo Järvinen Signed-off-by: Ralf Baechle --- include/asm-mips/pgtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mips/pgtable.h b/include/asm-mips/pgtable.h index 2f597eea4448..6a0edf72ffbc 100644 --- a/include/asm-mips/pgtable.h +++ b/include/asm-mips/pgtable.h @@ -239,9 +239,10 @@ static inline pte_t pte_mkdirty(pte_t pte) static inline pte_t pte_mkyoung(pte_t pte) { pte.pte_low |= _PAGE_ACCESSED; - if (pte.pte_low & _PAGE_READ) + if (pte.pte_low & _PAGE_READ) { pte.pte_low |= _PAGE_SILENT_READ; pte.pte_high |= _PAGE_SILENT_READ; + } return pte; } #else -- cgit v1.2.3 From 272bace7f3753ea8bf6ee80e3a6b32fa64190744 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Mon, 26 May 2008 09:35:47 +0100 Subject: [MIPS] Add accessors for random register. Signed-off-by: Ralf Baechle --- include/asm-mips/mipsregs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/asm-mips/mipsregs.h b/include/asm-mips/mipsregs.h index aa17f658f73c..a46f8e258e6b 100644 --- a/include/asm-mips/mipsregs.h +++ b/include/asm-mips/mipsregs.h @@ -765,6 +765,9 @@ do { \ #define read_c0_index() __read_32bit_c0_register($0, 0) #define write_c0_index(val) __write_32bit_c0_register($0, 0, val) +#define read_c0_random() __read_32bit_c0_register($1, 0) +#define write_c0_random(val) __write_32bit_c0_register($1, 0, val) + #define read_c0_entrylo0() __read_ulong_c0_register($2, 0) #define write_c0_entrylo0(val) __write_ulong_c0_register($2, 0, val) -- cgit v1.2.3 From 2cc3c0b67bdde7263f6eb16c16709e0b84047646 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 27 May 2008 17:27:28 +0200 Subject: [MIPS] Fix typo in header guard Signed-off-by: Vegard Nossum Signed-off-by: Ralf Baechle --- include/asm-mips/rtlx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mips/rtlx.h b/include/asm-mips/rtlx.h index 20b666022dcb..4ca3063ed2ce 100644 --- a/include/asm-mips/rtlx.h +++ b/include/asm-mips/rtlx.h @@ -3,7 +3,7 @@ * */ -#ifndef __ASM_RTLX_H +#ifndef __ASM_RTLX_H_ #define __ASM_RTLX_H_ #include -- cgit v1.2.3 From 609a70ac927b72da647ccee7873d928d45055eae Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Jun 2008 17:07:35 +0100 Subject: FRV: ip_fast_csum() requires a memory clobber on its inline asm ip_fast_csum() requires a memory clobber on its inline asm as it accesses memory in a fashion that gcc can't predict. The GCC manual says: If your assembler instructions access memory in an unpredictable fashion, add `memory' to the list of clobbered registers. This will cause GCC to not keep memory values cached in registers across the assembler instruction and not optimize stores or loads to that memory. The bug hasn't been noticed in FRV, but it has been seen in PA-RISC. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/asm-frv/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-frv/checksum.h b/include/asm-frv/checksum.h index 9b1689850187..269da09ff637 100644 --- a/include/asm-frv/checksum.h +++ b/include/asm-frv/checksum.h @@ -75,7 +75,7 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl) : "=r" (sum), "=r" (iph), "=r" (ihl), "=r" (inc), "=&r"(tmp) : "0" (sum), "1" (iph), "2" (ihl), "3" (4), "m"(*(volatile struct { int _[100]; } *)iph) - : "icc0", "icc1" + : "icc0", "icc1", "memory" ); return (__force __sum16)~sum; -- cgit v1.2.3 From ce263d70e509287ee761f9bba519342f57b121ca Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Wed, 21 May 2008 18:22:51 -0500 Subject: KVM: ppc: Remove duplicate function This was left behind from some code movement. Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/kvm/booke_guest.c | 33 --------------------------------- include/asm-powerpc/kvm_ppc.h | 1 + 2 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kvm/booke_guest.c b/arch/powerpc/kvm/booke_guest.c index 712d89a28c46..9c8ad850c6e3 100644 --- a/arch/powerpc/kvm/booke_guest.c +++ b/arch/powerpc/kvm/booke_guest.c @@ -227,39 +227,6 @@ void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu) } } -static int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) -{ - enum emulation_result er; - int r; - - er = kvmppc_emulate_instruction(run, vcpu); - switch (er) { - case EMULATE_DONE: - /* Future optimization: only reload non-volatiles if they were - * actually modified. */ - r = RESUME_GUEST_NV; - break; - case EMULATE_DO_MMIO: - run->exit_reason = KVM_EXIT_MMIO; - /* We must reload nonvolatiles because "update" load/store - * instructions modify register state. */ - /* Future optimization: only reload non-volatiles if they were - * actually modified. */ - r = RESUME_HOST_NV; - break; - case EMULATE_FAIL: - /* XXX Deliver Program interrupt to guest. */ - printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__, - vcpu->arch.last_inst); - r = RESUME_HOST; - break; - default: - BUG(); - } - - return r; -} - /** * kvmppc_handle_exit * diff --git a/include/asm-powerpc/kvm_ppc.h b/include/asm-powerpc/kvm_ppc.h index b35a7e3ef978..5a21115228af 100644 --- a/include/asm-powerpc/kvm_ppc.h +++ b/include/asm-powerpc/kvm_ppc.h @@ -57,6 +57,7 @@ extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, extern int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu); +extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu); extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid, u32 flags); -- cgit v1.2.3 From 2f5997140f22f68f6390c49941150d3fa8a95cb7 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 May 2008 12:10:20 -0300 Subject: KVM: migrate PIT timer Migrate the PIT timer to the physical CPU which vcpu0 is scheduled on, similarly to what is done for the LAPIC timers, otherwise PIT interrupts will be delayed until an unrelated event causes an exit. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/i8254.c | 14 +++++++++++++- arch/x86/kvm/irq.c | 6 ++++++ arch/x86/kvm/irq.h | 2 ++ arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 2 +- 7 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 7c077a9d9777..f2f5d260874e 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -200,7 +200,6 @@ int __pit_timer_fn(struct kvm_kpit_state *ps) atomic_inc(&pt->pending); smp_mb__after_atomic_inc(); - /* FIXME: handle case where the guest is in guest mode */ if (vcpu0 && waitqueue_active(&vcpu0->wq)) { vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE; wake_up_interruptible(&vcpu0->wq); @@ -237,6 +236,19 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_pit *pit = vcpu->kvm->arch.vpit; + struct hrtimer *timer; + + if (vcpu->vcpu_id != 0 || !pit) + return; + + timer = &pit->pit_state.pit_timer.timer; + if (hrtimer_cancel(timer)) + hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); +} + static void destroy_pit_timer(struct kvm_kpit_timer *pt) { pr_debug("pit: execute del timer!\n"); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index ce1f583459b1..76d736b5f664 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -94,3 +94,9 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_timer_intr_post); + +void __kvm_migrate_timers(struct kvm_vcpu *vcpu) +{ + __kvm_migrate_apic_timer(vcpu); + __kvm_migrate_pit_timer(vcpu); +} diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 1802134b836f..2a15be2275c0 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -84,6 +84,8 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_timers(struct kvm_vcpu *vcpu); int pit_has_pending_timer(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ab22615eee89..6b0d5fa5bab3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -688,7 +688,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) delta = vcpu->arch.host_tsc - tsc_this; svm->vmcb->control.tsc_offset += delta; vcpu->cpu = cpu; - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); } for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bfe4db11989c..96445f341519 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -608,7 +608,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (vcpu->cpu != cpu) { vcpu_clear(vmx); - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); vpid_sync_vcpu_all(vmx); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 21338bdb28ff..00acf1301a15 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2758,7 +2758,7 @@ again: if (vcpu->requests) { if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) - __kvm_migrate_apic_timer(vcpu); + __kvm_migrate_timers(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 398978972b7a..092b1b25291d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -297,7 +297,7 @@ static inline gpa_t gfn_to_gpa(gfn_t gfn) return (gpa_t)gfn << PAGE_SHIFT; } -static inline void kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) +static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu) { set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); } -- cgit v1.2.3 From 44d1b980c72db0faf35adb082fb2208351803028 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 5 Jun 2008 22:46:18 -0700 Subject: Fix various old email addresses for dwmw2 Although if people have questions about ARCnet, perhaps it's _better_ for them to be mailing dwmw2@cam.ac.uk about it... Signed-off-by: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/networking/arcnet.txt | 2 +- arch/frv/kernel/cmode.S | 2 +- arch/frv/kernel/sleep.S | 2 +- arch/frv/mb93090-mb00/pci-dma-nommu.c | 2 +- drivers/mtd/redboot.c | 2 +- fs/afs/callback.c | 2 +- fs/afs/inode.c | 2 +- fs/afs/super.c | 2 +- include/linux/mtd/nand.h | 2 +- include/linux/tty.h | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/Documentation/networking/arcnet.txt b/Documentation/networking/arcnet.txt index 770fc41a78e8..796012540386 100644 --- a/Documentation/networking/arcnet.txt +++ b/Documentation/networking/arcnet.txt @@ -46,7 +46,7 @@ These are the ARCnet drivers for Linux. This new release (2.91) has been put together by David Woodhouse -, in an attempt to tidy up the driver after adding support +, in an attempt to tidy up the driver after adding support for yet another chipset. Now the generic support has been separated from the individual chipset drivers, and the source files aren't quite so packed with #ifdefs! I've changed this file a bit, but kept it in the first person from diff --git a/arch/frv/kernel/cmode.S b/arch/frv/kernel/cmode.S index 81ba28ad2207..53deeb5d7e87 100644 --- a/arch/frv/kernel/cmode.S +++ b/arch/frv/kernel/cmode.S @@ -1,7 +1,7 @@ /* cmode.S: clock mode management * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Woodhouse (dwmw2@redhat.com) + * Written by David Woodhouse (dwmw2@infradead.org) * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/frv/kernel/sleep.S b/arch/frv/kernel/sleep.S index c9b2d51ab9ad..f67bf73cd2cc 100644 --- a/arch/frv/kernel/sleep.S +++ b/arch/frv/kernel/sleep.S @@ -1,7 +1,7 @@ /* sleep.S: power saving mode entry * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Woodhouse (dwmw2@redhat.com) + * Written by David Woodhouse (dwmw2@infradead.org) * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c index 4985466b1a7c..64ee58d748be 100644 --- a/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -1,7 +1,7 @@ /* pci-dma-nommu.c: Dynamic DMA mapping support for the FRV * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Woodhouse (dwmw2@redhat.com) + * Written by David Woodhouse (dwmw2@infradead.org) * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/drivers/mtd/redboot.c b/drivers/mtd/redboot.c index 47474903263c..c5030f94f04e 100644 --- a/drivers/mtd/redboot.c +++ b/drivers/mtd/redboot.c @@ -295,5 +295,5 @@ module_init(redboot_parser_init); module_exit(redboot_parser_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Red Hat, Inc. - David Woodhouse "); +MODULE_AUTHOR("David Woodhouse "); MODULE_DESCRIPTION("Parsing code for RedBoot Flash Image System (FIS) tables"); diff --git a/fs/afs/callback.c b/fs/afs/callback.c index a78d5b236bb1..587ef5123cd8 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -8,7 +8,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * - * Authors: David Woodhouse + * Authors: David Woodhouse * David Howells * */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 08db82e1343a..bb47217f6a18 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -8,7 +8,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * - * Authors: David Woodhouse + * Authors: David Woodhouse * David Howells * */ diff --git a/fs/afs/super.c b/fs/afs/super.c index 4b572b801d8d..7e3faeef6818 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -10,7 +10,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Authors: David Howells - * David Woodhouse + * David Woodhouse * */ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c42bc7f533a5..53ea3dc8b0e8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -1,7 +1,7 @@ /* * linux/include/linux/mtd/nand.h * - * Copyright (c) 2000 David Woodhouse + * Copyright (c) 2000 David Woodhouse * Steven J. Hill * Thomas Gleixner * diff --git a/include/linux/tty.h b/include/linux/tty.h index 7f7121f9c968..324a3b231d40 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -36,7 +36,7 @@ #define N_6PACK 7 #define N_MASC 8 /* Reserved for Mobitex module */ #define N_R3964 9 /* Reserved for Simatic R3964 module */ -#define N_PROFIBUS_FDL 10 /* Reserved for Profibus */ +#define N_PROFIBUS_FDL 10 /* Reserved for Profibus */ #define N_IRDA 11 /* Linux IrDa - http://irda.sourceforge.net/ */ #define N_SMSBLOCK 12 /* SMS block mode - for talking to GSM data */ /* cards about SMS messages */ -- cgit v1.2.3 From 3527fb326f07bc8e85cf66d4f987ebeea24e8e4a Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Thu, 5 Jun 2008 22:46:19 -0700 Subject: lib: export bitrev16 Bluetooth will be able to use this. Signed-off-by: Harvey Harrison Cc: Marcel Holtmann Cc: Dave Young Cc: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitrev.h | 1 + lib/bitrev.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 05e540d6963a..7ffe03f4693d 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -10,6 +10,7 @@ static inline u8 bitrev8(u8 byte) return byte_rev_table[byte]; } +extern u16 bitrev16(u16 in); extern u32 bitrev32(u32 in); #endif /* _LINUX_BITREV_H */ diff --git a/lib/bitrev.c b/lib/bitrev.c index 989aff73f881..3956203456d4 100644 --- a/lib/bitrev.c +++ b/lib/bitrev.c @@ -42,10 +42,11 @@ const u8 byte_rev_table[256] = { }; EXPORT_SYMBOL_GPL(byte_rev_table); -static __always_inline u16 bitrev16(u16 x) +u16 bitrev16(u16 x) { return (bitrev8(x & 0xff) << 8) | bitrev8(x >> 8); } +EXPORT_SYMBOL(bitrev16); /** * bitrev32 - reverse the order of bits in a u32 value -- cgit v1.2.3 From 93b071139a956e51c98cdefd50a47981a4eb852e Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 5 Jun 2008 22:46:21 -0700 Subject: introduce memory_read_from_buffer() This patch introduces memory_read_from_buffer(). The only difference between memory_read_from_buffer() and simple_read_from_buffer() is which address space the function copies to. simple_read_from_buffer copies to user space memory. memory_read_from_buffer copies to normal memory. Signed-off-by: Akinobu Mita Cc: Al Viro Cc: Doug Warzecha Cc: Zhang Rui Cc: Matt Domsch Cc: Abhay Salunke Cc: Greg Kroah-Hartman Cc: Markus Rechberger Cc: Kay Sievers Cc: Bob Moore Cc: Thomas Renninger Cc: Len Brown Cc: Benjamin Herrenschmidt Cc: "Antonino A. Daplas" Cc: Krzysztof Helt Cc: Geert Uytterhoeven Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Peter Oberparleiter Cc: Michael Holzheu Cc: Brian King Cc: James E.J. Bottomley Cc: Andrew Vasquez Cc: Seokmann Ju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/libfs.c | 18 ++++++++++++++++++ include/linux/fs.h | 5 ++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/libfs.c b/fs/libfs.c index b004dfadd891..892d41cb3382 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -528,6 +528,23 @@ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, return count; } +ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, + const void *from, size_t available) +{ + loff_t pos = *ppos; + + if (pos < 0) + return -EINVAL; + if (pos >= available) + return 0; + if (count > available - pos) + count = available - pos; + memcpy(to, from + pos, count); + *ppos = pos + count; + + return count; +} + /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then @@ -800,6 +817,7 @@ EXPORT_SYMBOL(simple_statfs); EXPORT_SYMBOL(simple_sync_file); EXPORT_SYMBOL(simple_unlink); EXPORT_SYMBOL(simple_read_from_buffer); +EXPORT_SYMBOL(memory_read_from_buffer); EXPORT_SYMBOL(simple_transaction_get); EXPORT_SYMBOL(simple_transaction_read); EXPORT_SYMBOL(simple_transaction_release); diff --git a/include/linux/fs.h b/include/linux/fs.h index f413085f748e..d490779f18d9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2000,7 +2000,10 @@ extern int simple_fill_super(struct super_block *, int, struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); -extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t); +extern ssize_t simple_read_from_buffer(void __user *to, size_t count, + loff_t *ppos, const void *from, size_t available); +extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, + const void *from, size_t available); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, -- cgit v1.2.3 From 68aa0a206a7a2dd8655a50b36e8274eb87b84544 Mon Sep 17 00:00:00 2001 From: Nadia Derbey Date: Thu, 5 Jun 2008 22:46:36 -0700 Subject: ipc: restore MSGPOOL original value When posting: [PATCH 1/8] Scaling msgmni to the amount of lowmem (see http://article.gmane.org/gmane.linux.kernel/637849/) I changed the MSGPOOL value to make it fit what is said in the man pages (i.e. a size in bytes). But Michael Kerrisk rightly complained that this change could affect the ABI. So I'm posting this patch to make MSGPOOL expressed back in Kbytes. Michael, on his side, has fixed the man page. Signed-off-by: Nadia Derbey Cc: Pierre Peiffer Cc: Manfred Spraul Acked-by: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/msg.h b/include/linux/msg.h index 6f3b8e79a991..56abf1558fdd 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -64,11 +64,11 @@ struct msginfo { #define MSGMNB 16384 /* <= INT_MAX */ /* default max size of a message queue */ /* unused */ -#define MSGPOOL (MSGMNI * MSGMNB) /* size in bytes of message pool */ +#define MSGPOOL (MSGMNI * MSGMNB / 1024) /* size in kbytes of message pool */ #define MSGTQL MSGMNB /* number of system message headers */ #define MSGMAP MSGMNB /* number of entries in message map */ #define MSGSSZ 16 /* message segment size */ -#define __MSGSEG (MSGPOOL / MSGSSZ) /* max no. of segments */ +#define __MSGSEG ((MSGPOOL * 1024) / MSGSSZ) /* max no. of segments */ #define MSGSEG (__MSGSEG <= 0xffff ? __MSGSEG : 0xffff) #ifdef __KERNEL__ -- cgit v1.2.3 From 3b2d38b48b5abb6921ac6ad2d080ce82887cdbc7 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Thu, 5 Jun 2008 22:46:41 -0700 Subject: h8300: fix typo in header guard Signed-off-by: Vegard Nossum Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-h8300/cacheflush.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-h8300/cacheflush.h b/include/asm-h8300/cacheflush.h index 71210d141b64..5ffdca217b95 100644 --- a/include/asm-h8300/cacheflush.h +++ b/include/asm-h8300/cacheflush.h @@ -3,7 +3,7 @@ */ #ifndef _ASM_H8300_CACHEFLUSH_H -#define _AMS_H8300_CACHEFLUSH_H +#define _ASM_H8300_CACHEFLUSH_H /* * Cache handling functions -- cgit v1.2.3 From 4fd5a433d4887f0a6c766c258ca335100ffe208a Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Thu, 5 Jun 2008 22:46:42 -0700 Subject: v850: fix typo in header guard Signed-off-by: Vegard Nossum Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-v850/clinkage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-v850/clinkage.h b/include/asm-v850/clinkage.h index 2b622adccae5..c389691d6f86 100644 --- a/include/asm-v850/clinkage.h +++ b/include/asm-v850/clinkage.h @@ -11,7 +11,7 @@ * Written by Miles Bader */ -#ifndef __CLINKAGE_H__ +#ifndef __V850_CLINKAGE_H__ #define __V850_CLINKAGE_H__ #include -- cgit v1.2.3 From ec0ced156f930aba24e7527905de294ad929ef65 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 5 Jun 2008 22:46:48 -0700 Subject: asm-m32r/uaccess.h must #include This patch fixes the following compile error caused by commit 4016a1390d07f15b267eecb20e76a48fd5c524ef (mm/nommu.c: return 0 from kobjsize with invalid objects): /home/bunk/linux/kernel-2.6/git/linux-2.6/mm/nommu.c: In function 'kobjsize': /home/bunk/linux/kernel-2.6/git/linux-2.6/mm/nommu.c:112: error: 'memory_end' undeclared (first use in this function) /home/bunk/linux/kernel-2.6/git/linux-2.6/mm/nommu.c:112: error: (Each undeclared identifier is reported only once /home/bunk/linux/kernel-2.6/git/linux-2.6/mm/nommu.c:112: error: for each function it appears in.) The patch also removes now no longer required memory_{start,end} declarations inside access_ok(). Reported-by: Adrian Bunk Signed-off-by: Adrian Bunk Cc: Hirokazu Takata Cc: Michael Hennerich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-m32r/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-m32r/uaccess.h b/include/asm-m32r/uaccess.h index bd8c83765a5c..1c7047bea200 100644 --- a/include/asm-m32r/uaccess.h +++ b/include/asm-m32r/uaccess.h @@ -14,6 +14,7 @@ #include #include #include +#include #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -106,7 +107,6 @@ static inline void set_fs(mm_segment_t s) #else static inline int access_ok(int type, const void *addr, unsigned long size) { - extern unsigned long memory_start, memory_end; unsigned long val = (unsigned long)addr; return ((val >= memory_start) && ((val + size) < memory_end)); -- cgit v1.2.3 From 979b0fea2d9ae5d57237a368d571cbc84655fba6 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Jun 2008 22:47:00 -0700 Subject: vm: add kzalloc_node() inline To get zeroed out memory from a particular NUMA node. To be used by sunrpc. Signed-off-by: Jeff Layton Cc: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 805ed4b92f9a..c2ad35016599 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -276,6 +276,17 @@ static inline void *kzalloc(size_t size, gfp_t flags) return kmalloc(size, flags | __GFP_ZERO); } +/** + * kzalloc_node - allocate zeroed memory from a particular memory node. + * @size: how many bytes of memory are required. + * @flags: the type of memory to allocate (see kmalloc). + * @node: memory node from which to allocate + */ +static inline void *kzalloc_node(size_t size, gfp_t flags, int node) +{ + return kmalloc_node(size, flags | __GFP_ZERO, node); +} + #ifdef CONFIG_SLABINFO extern const struct seq_operations slabinfo_op; ssize_t slabinfo_write(struct file *, const char __user *, size_t, loff_t *); -- cgit v1.2.3 From aab2545fdd6641b76af0ae96456c4ca9d1e50dad Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Jun 2008 11:31:39 -0700 Subject: uml: activate_mm: remove the dead PF_BORROWED_MM check use_mm() was changed to use switch_mm() instead of activate_mm(), since then nobody calls (and nobody should call) activate_mm() with PF_BORROWED_MM bit set. As Jeff Dike pointed out, we can also remove the "old != new" check, it is always true. Signed-off-by: Oleg Nesterov Cc: Jeff Dike Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/aio.c | 4 ---- include/asm-um/mmu_context.h | 12 +++--------- 2 files changed, 3 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/aio.c b/fs/aio.c index b5253e77eb2f..0fb3117ddd93 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -591,10 +591,6 @@ static void use_mm(struct mm_struct *mm) atomic_inc(&mm->mm_count); tsk->mm = mm; tsk->active_mm = mm; - /* - * Note that on UML this *requires* PF_BORROWED_MM to be set, otherwise - * it won't work. Update it accordingly if you change it here - */ switch_mm(active_mm, mm, tsk); task_unlock(tsk); diff --git a/include/asm-um/mmu_context.h b/include/asm-um/mmu_context.h index 6686fc524ca1..54f42e8b0105 100644 --- a/include/asm-um/mmu_context.h +++ b/include/asm-um/mmu_context.h @@ -22,16 +22,10 @@ extern void force_flush_all(void); static inline void activate_mm(struct mm_struct *old, struct mm_struct *new) { /* - * This is called by fs/exec.c and fs/aio.c. In the first case, for an - * exec, we don't need to do anything as we're called from userspace - * and thus going to use a new host PID. In the second, we're called - * from a kernel thread, and thus need to go doing the mmap's on the - * host. Since they're very expensive, we want to avoid that as far as - * possible. + * This is called by fs/exec.c and sys_unshare() + * when the new ->mm is used for the first time. */ - if (old != new && (current->flags & PF_BORROWED_MM)) - __switch_mm(&new->context.id); - + __switch_mm(&new->context.id); arch_dup_mmap(old, new); } -- cgit v1.2.3 From f751aa125d1843ea4a9a264b451fd5b1639fab20 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 8 Jun 2008 21:43:10 +0300 Subject: fat_valid_media() isn't for userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 73f20e58b1d586e9f6d3ddc3aad872829aca7743 ("FAT_VALID_MEDIA(): remove pointless test") wrongly added the new fat_valid_media() function to the userspace-visible part of include/linux/msdos_fs.h Move it to the part of include/linux/msdos_fs.h that is not exported to userspace. Reported-by: Onur Küçük Reported-by: S.Çağlar Onur Signed-off-by: Adrian Bunk Acked-by: OGAWA Hirofumi Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index b03b27457413..81cd36b735b0 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -57,12 +57,6 @@ #define MSDOS_DOT ". " /* ".", padded to MSDOS_NAME chars */ #define MSDOS_DOTDOT ".. " /* "..", padded to MSDOS_NAME chars */ -/* media of boot sector */ -static inline int fat_valid_media(u8 media) -{ - return 0xf8 <= media || media == 0xf0; -} - #define FAT_FIRST_ENT(s, x) ((MSDOS_SB(s)->fat_bits == 32 ? 0x0FFFFF00 : \ MSDOS_SB(s)->fat_bits == 16 ? 0xFF00 : 0xF00) | (x)) @@ -334,6 +328,12 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len) #endif } +/* media of boot sector */ +static inline int fat_valid_media(u8 media) +{ + return 0xf8 <= media || media == 0xf0; +} + /* fat/cache.c */ extern void fat_cache_inval_inode(struct inode *inode); extern int fat_get_cluster(struct inode *inode, int cluster, -- cgit v1.2.3 From 0d5799449f0f373ca12681d86c941ae464146a37 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 4 Jun 2008 08:30:54 +1000 Subject: [POWERPC] Make walk_memory_resource available with MEMORY_HOTPLUG=n The ehea driver was recently changed[1] to use walk_memory_resource() to detect the system's memory layout. However, walk_memory_resource() is available only when memory hotplug is enabled. So CONFIG_EHEA was made to depend on MEMORY_HOTPLUG [2], but it is inappropriate for a network driver to have such a dependency. Make the declaration of walk_memory_resource() and its powerpc implementation (ehea is powerpc-specific) unconditionally available. [1] 48cfb14f8b89d4d5b3df6c16f08b258686fb12ad "ehea: Add DLPAR memory remove support" [2] fb7b6ca2b6b7c23b52be143bdd5f55a23b9780c8 "ehea: Add dependency to Kconfig" Signed-off-by: Nathan Lynch Acked-by: Badari Pulavarty Signed-off-by: Paul Mackerras --- arch/powerpc/mm/mem.c | 3 +-- include/linux/memory_hotplug.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f67e118116fa..51f82d83bf14 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -151,6 +151,7 @@ out: return ret; } #endif /* CONFIG_MEMORY_HOTREMOVE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * walk_memory_resource() needs to make sure there is no holes in a given @@ -184,8 +185,6 @@ walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg, } EXPORT_SYMBOL_GPL(walk_memory_resource); -#endif /* CONFIG_MEMORY_HOTPLUG */ - void show_mem(void) { unsigned long total = 0, reserved = 0; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 73e358612eaf..ea9f5ad9ec8e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -77,14 +77,6 @@ extern int __add_pages(struct zone *zone, unsigned long start_pfn, extern int __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -/* - * Walk through all memory which is registered as resource. - * arg is (start_pfn, nr_pages, private_arg_pointer) - */ -extern int walk_memory_resource(unsigned long start_pfn, - unsigned long nr_pages, void *arg, - int (*func)(unsigned long, unsigned long, void *)); - #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); #else @@ -199,6 +191,14 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) #endif /* ! CONFIG_MEMORY_HOTPLUG */ +/* + * Walk through all memory which is registered as resource. + * arg is (start_pfn, nr_pages, private_arg_pointer) + */ +extern int walk_memory_resource(unsigned long start_pfn, + unsigned long nr_pages, void *arg, + int (*func)(unsigned long, unsigned long, void *)); + extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); -- cgit v1.2.3 From 4c0283fc561d79a4f94ab48ec37282e15273d1f8 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Mon, 9 Jun 2008 09:58:42 -0700 Subject: IB/core: Remove IB_DEVICE_SEND_W_INV capability flag In 2.6.26, we added some support for send with invalidate work requests, including a device capability flag to indicate whether a device supports such requests. However, the support was incomplete: the completion structure was not extended with a field for the key contained in incoming send with invalidate requests. Full support for memory management extensions (send with invalidate, local invalidate, fast register through a send queue, etc) is planned for 2.6.27. Since send with invalidate is not very useful by itself, just remove the IB_DEVICE_SEND_W_INV bit before the 2.6.26 final release; we will add an IB_DEVICE_MEM_MGT_EXTENSIONS bit in 2.6.27, which makes things simpler for applications, since they will not have quite as confusing an array of fine-grained bits to check. Signed-off-by: Roland Dreier --- drivers/infiniband/hw/amso1100/c2_rnic.c | 3 +-- include/rdma/ib_verbs.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c index 9a054c6941a4..b1441aeb60c2 100644 --- a/drivers/infiniband/hw/amso1100/c2_rnic.c +++ b/drivers/infiniband/hw/amso1100/c2_rnic.c @@ -455,8 +455,7 @@ int __devinit c2_rnic_init(struct c2_dev *c2dev) IB_DEVICE_CURR_QP_STATE_MOD | IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_ZERO_STAG | - IB_DEVICE_MEM_WINDOW | - IB_DEVICE_SEND_W_INV); + IB_DEVICE_MEM_WINDOW); /* Allocate the qptr_array */ c2dev->qptr_array = vmalloc(C2_MAX_CQS * sizeof(void *)); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 911a661b7278..31d30b1852e8 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -105,7 +105,6 @@ enum ib_device_cap_flags { */ IB_DEVICE_UD_IP_CSUM = (1<<18), IB_DEVICE_UD_TSO = (1<<19), - IB_DEVICE_SEND_W_INV = (1<<21), }; enum ib_atomic_cap { -- cgit v1.2.3 From dfa7e20cc0d1a7a620def4dce97de1ae5375f99b Mon Sep 17 00:00:00 2001 From: Russ Anderson Date: Mon, 9 Jun 2008 11:18:45 -0500 Subject: mm: Minor clean-up of page flags in mm/page_alloc.c Minor source code cleanup of page flags in mm/page_alloc.c. Move the definition of the groups of bits to page-flags.h. The purpose of this clean up is that the next patch will conditionally add a page flag to the groups. Doing that in a header file is cleaner than adding #ifdefs to the C code. Signed-off-by: Russ Anderson Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 24 ++++++++++++++++++++++++ mm/page_alloc.c | 34 +++------------------------------- 2 files changed, 27 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 590cff32415d..f31debfac926 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -306,5 +306,29 @@ static inline void __ClearPageTail(struct page *page) } #endif /* !PAGEFLAGS_EXTENDED */ + +#define PAGE_FLAGS (1 << PG_lru | 1 << PG_private | 1 << PG_locked | \ + 1 << PG_buddy | 1 << PG_writeback | \ + 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active) + +/* + * Flags checked in bad_page(). Pages on the free list should not have + * these flags set. It they are, there is a problem. + */ +#define PAGE_FLAGS_CLEAR_WHEN_BAD (PAGE_FLAGS | 1 << PG_reclaim | 1 << PG_dirty) + +/* + * Flags checked when a page is freed. Pages being freed should not have + * these flags set. It they are, there is a problem. + */ +#define PAGE_FLAGS_CHECK_AT_FREE (PAGE_FLAGS | 1 << PG_reserved) + +/* + * Flags checked when a page is prepped for return by the page allocator. + * Pages being prepped should not have these flags set. It they are, there + * is a problem. + */ +#define PAGE_FLAGS_CHECK_AT_PREP (PAGE_FLAGS | 1 << PG_reserved | 1 << PG_dirty) + #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8e83f02cd2d3..2f552955a02f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -237,16 +237,7 @@ static void bad_page(struct page *page) printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n" KERN_EMERG "Backtrace:\n"); dump_stack(); - page->flags &= ~(1 << PG_lru | - 1 << PG_private | - 1 << PG_locked | - 1 << PG_active | - 1 << PG_dirty | - 1 << PG_reclaim | - 1 << PG_slab | - 1 << PG_swapcache | - 1 << PG_writeback | - 1 << PG_buddy ); + page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD; set_page_count(page, 0); reset_page_mapcount(page); page->mapping = NULL; @@ -463,16 +454,7 @@ static inline int free_pages_check(struct page *page) (page->mapping != NULL) | (page_get_page_cgroup(page) != NULL) | (page_count(page) != 0) | - (page->flags & ( - 1 << PG_lru | - 1 << PG_private | - 1 << PG_locked | - 1 << PG_active | - 1 << PG_slab | - 1 << PG_swapcache | - 1 << PG_writeback | - 1 << PG_reserved | - 1 << PG_buddy )))) + (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) bad_page(page); if (PageDirty(page)) __ClearPageDirty(page); @@ -616,17 +598,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) (page->mapping != NULL) | (page_get_page_cgroup(page) != NULL) | (page_count(page) != 0) | - (page->flags & ( - 1 << PG_lru | - 1 << PG_private | - 1 << PG_locked | - 1 << PG_active | - 1 << PG_dirty | - 1 << PG_slab | - 1 << PG_swapcache | - 1 << PG_writeback | - 1 << PG_reserved | - 1 << PG_buddy )))) + (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) bad_page(page); /* -- cgit v1.2.3 From 585c5434f0e02ff0ffc567ec223af61e2d8e2e88 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 5 Jun 2008 21:29:49 +0300 Subject: include/linux/ssb/ssb_driver_gige.h typo fix This patch fixes a typo in the name of a config variable. Reported-by: Robert P. J. Day Signed-off-by: Adrian Bunk Reviewed-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb_driver_gige.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 01fbdf5fef22..942e38736901 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -100,7 +100,7 @@ extern char * nvram_get(const char *name); /* Get the device MAC address */ static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -#ifdef CONFIG_BCM947XX +#ifdef CONFIG_BCM47XX char *res = nvram_get("et0macaddr"); if (res) memcpy(macaddr, res, 6); -- cgit v1.2.3 From b57838ea3f860c97e4726ab93abdf83a3d079a66 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Tue, 10 Jun 2008 10:03:24 +0200 Subject: [S390] Fix __ctl_load/__ctl_store inline assembly constraints __ctl_load/__ctl_store are called with either an array of unsigned long or a single unsigned long value. Add an address operator to the "m"/"=m" contraints to make them work for unsigned long arguments as well. Signed-off-by: Martin Schwidefsky --- include/asm-s390/system.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/asm-s390/system.h b/include/asm-s390/system.h index e0d4500d5f95..819e7d99ca0c 100644 --- a/include/asm-s390/system.h +++ b/include/asm-s390/system.h @@ -315,14 +315,14 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) asm volatile( \ " lctlg %1,%2,0(%0)\n" \ : : "a" (&array), "i" (low), "i" (high), \ - "m" (*(addrtype *)(array))); \ + "m" (*(addrtype *)(&array))); \ }) #define __ctl_store(array, low, high) ({ \ typedef struct { char _[sizeof(array)]; } addrtype; \ asm volatile( \ " stctg %2,%3,0(%1)\n" \ - : "=m" (*(addrtype *)(array)) \ + : "=m" (*(addrtype *)(&array)) \ : "a" (&array), "i" (low), "i" (high)); \ }) @@ -333,14 +333,14 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) asm volatile( \ " lctl %1,%2,0(%0)\n" \ : : "a" (&array), "i" (low), "i" (high), \ - "m" (*(addrtype *)(array))); \ + "m" (*(addrtype *)(&array))); \ }) #define __ctl_store(array, low, high) ({ \ typedef struct { char _[sizeof(array)]; } addrtype; \ asm volatile( \ " stctl %2,%3,0(%1)\n" \ - : "=m" (*(addrtype *)(array)) \ + : "=m" (*(addrtype *)(&array)) \ : "a" (&array), "i" (low), "i" (high)); \ }) -- cgit v1.2.3 From 16882c1e962b4be5122fc05aaf2afc10fd9e2d15 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 8 Jun 2008 21:20:41 +0400 Subject: sched: fix TASK_WAKEKILL vs SIGKILL race schedule() has the special "TASK_INTERRUPTIBLE && signal_pending()" case, this allows us to do current->state = TASK_INTERRUPTIBLE; schedule(); without fear to sleep with pending signal. However, the code like current->state = TASK_KILLABLE; schedule(); is not right, schedule() doesn't take TASK_WAKEKILL into account. This means that mutex_lock_killable(), wait_for_completion_killable(), down_killable(), schedule_timeout_killable() can miss SIGKILL (and btw the second SIGKILL has no effect). Introduce the new helper, signal_pending_state(), and change schedule() to use it. Hopefully it will have more users, that is why the task's state is passed separately. Note this "__TASK_STOPPED | __TASK_TRACED" check in signal_pending_state(). This is needed to preserve the current behaviour (ptrace_notify). I hope this check will be removed soon, but this (afaics good) change needs the separate discussion. The fast path is "(state & (INTERRUPTIBLE | WAKEKILL)) + signal_pending(p)", basically the same that schedule() does now. However, this patch of course bloats schedule(). Signed-off-by: Oleg Nesterov Signed-off-by: Ingo Molnar --- include/linux/sched.h | 13 +++++++++++++ kernel/sched.c | 6 ++---- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index ae0be3c62375..c5d3f847ca8d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2026,6 +2026,19 @@ static inline int fatal_signal_pending(struct task_struct *p) return signal_pending(p) && __fatal_signal_pending(p); } +static inline int signal_pending_state(long state, struct task_struct *p) +{ + if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) + return 0; + if (!signal_pending(p)) + return 0; + + if (state & (__TASK_STOPPED | __TASK_TRACED)) + return 0; + + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); +} + static inline int need_resched(void) { return unlikely(test_thread_flag(TIF_NEED_RESCHED)); diff --git a/kernel/sched.c b/kernel/sched.c index bfb8ad8ed171..2c65bf29d133 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4159,12 +4159,10 @@ need_resched_nonpreemptible: clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely((prev->state & TASK_INTERRUPTIBLE) && - signal_pending(prev))) { + if (unlikely(signal_pending_state(prev->state, prev))) prev->state = TASK_RUNNING; - } else { + else deactivate_task(rq, prev, 1); - } switch_count = &prev->nvcsw; } -- cgit v1.2.3 From b76916462d990751882eaeadc75ac8c487d6de1d Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 10 Jun 2008 20:56:36 +0200 Subject: ide: remove the ide_etrax100 chipset type I forgot to remove the ide_etrax100 chipset type when removing the ETRAX_IDE driver. Reported-by: Bartlomiej Zolnierkiewicz Signed-off-by: Adrian Bunk Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/ide/ide-probe.c | 5 ++--- drivers/ide/ide-proc.c | 1 - include/linux/ide.h | 2 +- 3 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 655ec7ef568a..0bccb63d10a1 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1333,8 +1333,7 @@ static void ide_port_init_devices(ide_hwif_t *hwif) static void ide_init_port(ide_hwif_t *hwif, unsigned int port, const struct ide_port_info *d) { - if (d->chipset != ide_etrax100) - hwif->channel = port; + hwif->channel = port; if (d->chipset) hwif->chipset = d->chipset; @@ -1519,7 +1518,7 @@ int ide_device_add_all(u8 *idx, const struct ide_port_info *d) continue; } - if (d->chipset != ide_etrax100 && (i & 1) && mate) { + if ((i & 1) && mate) { hwif->mate = mate; mate->mate = hwif; } diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c index 8d6ad812a014..55ec7f798772 100644 --- a/drivers/ide/ide-proc.c +++ b/drivers/ide/ide-proc.c @@ -63,7 +63,6 @@ static int proc_ide_read_imodel case ide_pmac: name = "mac-io"; break; case ide_au1xxx: name = "au1xxx"; break; case ide_palm3710: name = "palm3710"; break; - case ide_etrax100: name = "etrax100"; break; case ide_acorn: name = "acorn"; break; default: name = "(unknown)"; break; } diff --git a/include/linux/ide.h b/include/linux/ide.h index f8f195c20da2..9918772bf274 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -153,7 +153,7 @@ enum { ide_unknown, ide_generic, ide_pci, ide_qd65xx, ide_umc8672, ide_ht6560b, ide_rz1000, ide_trm290, ide_cmd646, ide_cy82c693, ide_4drives, - ide_pmac, ide_etrax100, ide_acorn, + ide_pmac, ide_acorn, ide_au1xxx, ide_palm3710 }; -- cgit v1.2.3 From 45d465bc237ab1e1ebb4c65b9b318830dafb7509 Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Tue, 10 Jun 2008 12:37:42 -0700 Subject: ipv4: Remove unused declaration from include/net/tcp.h. - The tcp_unhash() method in /include/net/tcp.h is no more needed, as the unhash method in tcp_prot structure is now inet_unhash (instead of tcp_unhash in the past); see tcp_prot structure in net/ipv4/tcp_ipv4.c. - So, this patch removes tcp_unhash() declaration from include/net/tcp.h Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 633147cb6bbc..d448310c82c1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -433,7 +433,6 @@ extern struct sk_buff * tcp_make_synack(struct sock *sk, extern int tcp_disconnect(struct sock *sk, int flags); -extern void tcp_unhash(struct sock *sk); /* From syncookies.c */ extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; -- cgit v1.2.3 From ce4a7d0d48bbaed78ccbb0bafb9229651a40303a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 10 Jun 2008 12:39:35 -0700 Subject: inet{6}_request_sock: Init ->opt and ->pktopts in the constructor Wei Yongjun noticed that we may call reqsk_free on request sock objects where the opt fields may not be initialized, fix it by introducing inet_reqsk_alloc where we initialize ->opt to NULL and set ->pktopts to NULL in inet6_reqsk_alloc. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 +++- include/net/inet_sock.h | 10 ++++++++++ net/dccp/ipv4.c | 3 +-- net/dccp/ipv6.c | 1 - net/ipv4/syncookies.c | 3 +-- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/syncookies.c | 1 - net/ipv6/tcp_ipv6.c | 1 - 8 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 10b666b61add..cde056e08181 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -396,8 +396,10 @@ static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *op { struct request_sock *req = reqsk_alloc(ops); - if (req != NULL) + if (req != NULL) { inet_rsk(req)->inet6_rsk_offset = inet6_rsk_offset(req); + inet6_rsk(req)->pktopts = NULL; + } return req; } diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a42cd63d241a..9fabe5b38912 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -197,4 +197,14 @@ static inline int inet_iif(const struct sk_buff *skb) return skb->rtable->rt_iif; } +static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops) +{ + struct request_sock *req = reqsk_alloc(ops); + + if (req != NULL) + inet_rsk(req)->opt = NULL; + + return req; +} + #endif /* _INET_SOCK_H */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index c22a3780c14e..37d27bcb361f 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -589,7 +589,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops); if (req == NULL) goto drop; @@ -605,7 +605,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; /* * Step 3: Process LISTEN state diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9b1129bb7ece..f7fe2a572d7b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -421,7 +421,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq6 = inet6_rsk(req); ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); - ireq6->pktopts = NULL; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 73ba98921d64..d182a2a26291 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -285,7 +285,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, cookie_check_timestamp(&tcp_opt); ret = NULL; - req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) goto out; @@ -301,7 +301,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rmt_port = th->source; ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->rcv_wscale = tcp_opt.rcv_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cd601a866c2f..4f8485c67d1a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1285,7 +1285,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&tcp_request_sock_ops); + req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 938ce4ecde55..3ecc1157994e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -198,7 +198,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); - ireq6->pktopts = NULL; if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 715965f0fac0..cb46749d4c32 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1299,7 +1299,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq = inet6_rsk(req); ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); - treq->pktopts = NULL; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); -- cgit v1.2.3 From 2506ece0c0bbd2fc19a4827b96dc52ea47e2ce4a Mon Sep 17 00:00:00 2001 From: Mark McLoughlin Date: Sun, 8 Jun 2008 20:49:59 +1000 Subject: virtio: Fix typo in virtio_net_hdr comments Signed-off-by: Mark McLoughlin Signed-off-by: Rusty Russell Signed-off-by: Jeff Garzik --- include/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 9405aa6cdf26..38c0571820fb 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -38,7 +38,7 @@ struct virtio_net_hdr #define VIRTIO_NET_HDR_GSO_ECN 0x80 // TCP has ECN set __u8 gso_type; __u16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ - __u16 gso_size; /* Bytes to append to gso_hdr_len per frame */ + __u16 gso_size; /* Bytes to append to hdr_len per frame */ __u16 csum_start; /* Position to start checksumming from */ __u16 csum_offset; /* Offset after that to place checksum */ }; -- cgit v1.2.3 From 709772e6e06564ed94ba740de70185ac3d792773 Mon Sep 17 00:00:00 2001 From: Krzysztof Piotr Oledzki Date: Tue, 10 Jun 2008 15:44:49 -0700 Subject: net: Fix routing tables with id > 255 for legacy software Most legacy software do not like tables > 255 as rtm_table is u8 so tb_id is sent &0xff and it is possible to mismatch for example table 510 with table 254 (main). This patch introduces RT_TABLE_COMPAT=252 so the code uses it if tb_id > 255. It makes such old applications happy, new ones are still able to use RTA_TABLE to get a proper table id. Signed-off-by: Krzysztof Piotr Oledzki Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 1 + net/ipv4/fib_semantics.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index a2aec2c0cfb5..b358c704d102 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -246,6 +246,7 @@ enum rt_class_t { RT_TABLE_UNSPEC=0, /* User defined values */ + RT_TABLE_COMPAT=252, RT_TABLE_DEFAULT=253, RT_TABLE_MAIN=254, RT_TABLE_LOCAL=255, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3b83c34019fc..0d4d72827e4b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -960,7 +960,10 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = tos; - rtm->rtm_table = tb_id; + if (tb_id < 256) + rtm->rtm_table = tb_id; + else + rtm->rtm_table = RT_TABLE_COMPAT; NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; -- cgit v1.2.3 From dcb84f335bee9c9a7781cfc5d74492dccaf066d2 Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Mon, 19 May 2008 19:09:27 -0400 Subject: cpuidle acpi driver: fix oops on AC<->DC cpuidle and acpi driver interaction bug with the way cpuidle_register_driver() is called. Due to this bug, there will be oops on AC<->DC on some systems, where they support C-states in one DC and not in AC. The current code does ON BOOT: Look at CST and other C-state info to see whether more than C1 is supported. If it is, then acpi processor_idle does a cpuidle_register_driver() call, which internally enables the device. ON CST change notification (AC<->DC) and on suspend-resume: acpi driver temporarily disables device, updates the device with any new C-states, and reenables the device. The problem is is on boot, there are no C2, C3 states supported and we skip the register. Later on AC<->DC, we may get a CST notification and we try to reevaluate CST and enabled the device, without actually registering it. This causes breakage as we try to create /sys fs sub directory, without the parent directory which is created at register time. Thanks to Sanjeev for reporting the problem here. http://bugzilla.kernel.org/show_bug.cgi?id=10394 Signed-off-by: Venkatesh Pallipadi Signed-off-by: Len Brown --- drivers/acpi/processor_idle.c | 13 +++++++------ drivers/cpuidle/cpuidle.c | 40 +++++++++++++++++++++++++++++++++++----- include/linux/cpuidle.h | 1 + 3 files changed, 43 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 2dd2c1f3a01c..556ee1585192 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1669,6 +1669,7 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr) return -EINVAL; } + dev->cpu = pr->id; for (i = 0; i < CPUIDLE_STATE_MAX; i++) { dev->states[i].name[0] = '\0'; dev->states[i].desc[0] = '\0'; @@ -1738,7 +1739,7 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr) int acpi_processor_cst_has_changed(struct acpi_processor *pr) { - int ret; + int ret = 0; if (boot_option_idle_override) return 0; @@ -1756,8 +1757,10 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) cpuidle_pause_and_lock(); cpuidle_disable_device(&pr->power.dev); acpi_processor_get_power_info(pr); - acpi_processor_setup_cpuidle(pr); - ret = cpuidle_enable_device(&pr->power.dev); + if (pr->flags.power) { + acpi_processor_setup_cpuidle(pr); + ret = cpuidle_enable_device(&pr->power.dev); + } cpuidle_resume_and_unlock(); return ret; @@ -1813,7 +1816,6 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, if (pr->flags.power) { #ifdef CONFIG_CPU_IDLE acpi_processor_setup_cpuidle(pr); - pr->power.dev.cpu = pr->id; if (cpuidle_register_device(&pr->power.dev)) return -EIO; #endif @@ -1850,8 +1852,7 @@ int acpi_processor_power_exit(struct acpi_processor *pr, return 0; #ifdef CONFIG_CPU_IDLE - if (pr->flags.power) - cpuidle_unregister_device(&pr->power.dev); + cpuidle_unregister_device(&pr->power.dev); #endif pr->flags.power_setup_done = 0; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index fc555a90bb21..23554b676d6e 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -38,6 +38,8 @@ static void cpuidle_kick_cpus(void) static void cpuidle_kick_cpus(void) {} #endif +static int __cpuidle_register_device(struct cpuidle_device *dev); + /** * cpuidle_idle_call - the main idle loop * @@ -138,6 +140,12 @@ int cpuidle_enable_device(struct cpuidle_device *dev) if (!dev->state_count) return -EINVAL; + if (dev->registered == 0) { + ret = __cpuidle_register_device(dev); + if (ret) + return ret; + } + if ((ret = cpuidle_add_state_sysfs(dev))) return ret; @@ -232,10 +240,13 @@ static void poll_idle_init(struct cpuidle_device *dev) {} #endif /* CONFIG_ARCH_HAS_CPU_RELAX */ /** - * cpuidle_register_device - registers a CPU's idle PM feature + * __cpuidle_register_device - internal register function called before register + * and enable routines * @dev: the cpu + * + * cpuidle_lock mutex must be held before this is called */ -int cpuidle_register_device(struct cpuidle_device *dev) +static int __cpuidle_register_device(struct cpuidle_device *dev) { int ret; struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); @@ -247,18 +258,34 @@ int cpuidle_register_device(struct cpuidle_device *dev) init_completion(&dev->kobj_unregister); - mutex_lock(&cpuidle_lock); - poll_idle_init(dev); per_cpu(cpuidle_devices, dev->cpu) = dev; list_add(&dev->device_list, &cpuidle_detected_devices); if ((ret = cpuidle_add_sysfs(sys_dev))) { - mutex_unlock(&cpuidle_lock); module_put(cpuidle_curr_driver->owner); return ret; } + dev->registered = 1; + return 0; +} + +/** + * cpuidle_register_device - registers a CPU's idle PM feature + * @dev: the cpu + */ +int cpuidle_register_device(struct cpuidle_device *dev) +{ + int ret; + + mutex_lock(&cpuidle_lock); + + if ((ret = __cpuidle_register_device(dev))) { + mutex_unlock(&cpuidle_lock); + return ret; + } + cpuidle_enable_device(dev); cpuidle_install_idle_handler(); @@ -278,6 +305,9 @@ void cpuidle_unregister_device(struct cpuidle_device *dev) { struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); + if (dev->registered == 0) + return; + cpuidle_pause_and_lock(); cpuidle_disable_device(dev); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 51e6b1e520e6..dcf77fa826b5 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -82,6 +82,7 @@ struct cpuidle_state_kobj { }; struct cpuidle_device { + unsigned int registered:1; unsigned int enabled:1; unsigned int cpu; -- cgit v1.2.3 From e9fe9e188118a0a34c6200d9b10ea6247f53592d Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 9 Jun 2008 16:52:04 -0700 Subject: pnpacpi: fix IRQ flag decoding When decoding IRQ trigger mode and polarity, it is not enough to mask by IORESOURCE_BITS because there are now additional bits defined. For example, if IORESOURCE_IRQ_SHAREABLE was set, we failed to set *triggering and *polarity at all. I can't point to a failure that this patch fixes, but bugs in this area have caused problems when resuming after suspend, for example: http://bugzilla.kernel.org/show_bug.cgi?id=6316 http://bugzilla.kernel.org/show_bug.cgi?id=9487 https://bugs.launchpad.net/ubuntu/+source/linux-source-2.6.22/+bug/152187 This is based on a patch by Tom Jaeger: http://bugzilla.kernel.org/show_bug.cgi?id=9487#c32 [rene.herman@keyaccess.nl: fix comment] Signed-off-by: Bjorn Helgaas Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- drivers/pnp/pnpacpi/rsparser.c | 16 ++++++++++++---- include/linux/ioport.h | 6 +++--- 2 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 0201c8adfda7..ab09fe6fe1e4 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -56,9 +56,11 @@ static int irq_flags(int triggering, int polarity, int shareable) return flags; } -static void decode_irq_flags(int flag, int *triggering, int *polarity) +static void decode_irq_flags(struct pnp_dev *dev, int flags, int *triggering, + int *polarity) { - switch (flag) { + switch (flags & (IORESOURCE_IRQ_LOWLEVEL | IORESOURCE_IRQ_HIGHLEVEL | + IORESOURCE_IRQ_LOWEDGE | IORESOURCE_IRQ_HIGHEDGE)) { case IORESOURCE_IRQ_LOWLEVEL: *triggering = ACPI_LEVEL_SENSITIVE; *polarity = ACPI_ACTIVE_LOW; @@ -75,6 +77,12 @@ static void decode_irq_flags(int flag, int *triggering, int *polarity) *triggering = ACPI_EDGE_SENSITIVE; *polarity = ACPI_ACTIVE_HIGH; break; + default: + dev_err(&dev->dev, "can't encode invalid IRQ mode %#x\n", + flags); + *triggering = ACPI_EDGE_SENSITIVE; + *polarity = ACPI_ACTIVE_HIGH; + break; } } @@ -790,7 +798,7 @@ static void pnpacpi_encode_irq(struct pnp_dev *dev, struct acpi_resource_irq *irq = &resource->data.irq; int triggering, polarity; - decode_irq_flags(p->flags & IORESOURCE_BITS, &triggering, &polarity); + decode_irq_flags(dev, p->flags, &triggering, &polarity); irq->triggering = triggering; irq->polarity = polarity; if (triggering == ACPI_EDGE_SENSITIVE) @@ -813,7 +821,7 @@ static void pnpacpi_encode_ext_irq(struct pnp_dev *dev, struct acpi_resource_extended_irq *extended_irq = &resource->data.extended_irq; int triggering, polarity; - decode_irq_flags(p->flags & IORESOURCE_BITS, &triggering, &polarity); + decode_irq_flags(dev, p->flags, &triggering, &polarity); extended_irq->producer_consumer = ACPI_CONSUMER; extended_irq->triggering = triggering; extended_irq->polarity = polarity; diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d5d40a9f7929..c6801bffe76d 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -53,14 +53,14 @@ struct resource_list { #define IORESOURCE_AUTO 0x40000000 #define IORESOURCE_BUSY 0x80000000 /* Driver has marked this resource busy */ -/* ISA PnP IRQ specific bits (IORESOURCE_BITS) */ +/* PnP IRQ specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IRQ_HIGHEDGE (1<<0) #define IORESOURCE_IRQ_LOWEDGE (1<<1) #define IORESOURCE_IRQ_HIGHLEVEL (1<<2) #define IORESOURCE_IRQ_LOWLEVEL (1<<3) #define IORESOURCE_IRQ_SHAREABLE (1<<4) -/* ISA PnP DMA specific bits (IORESOURCE_BITS) */ +/* PnP DMA specific bits (IORESOURCE_BITS) */ #define IORESOURCE_DMA_TYPE_MASK (3<<0) #define IORESOURCE_DMA_8BIT (0<<0) #define IORESOURCE_DMA_8AND16BIT (1<<0) @@ -76,7 +76,7 @@ struct resource_list { #define IORESOURCE_DMA_TYPEB (2<<6) #define IORESOURCE_DMA_TYPEF (3<<6) -/* ISA PnP memory I/O specific bits (IORESOURCE_BITS) */ +/* PnP memory I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_MEM_WRITEABLE (1<<0) /* dup: IORESOURCE_READONLY */ #define IORESOURCE_MEM_CACHEABLE (1<<1) /* dup: IORESOURCE_CACHEABLE */ #define IORESOURCE_MEM_RANGELENGTH (1<<2) /* dup: IORESOURCE_RANGELENGTH */ -- cgit v1.2.3 From a66b34b26fe1b0983c6d91b6381df806cd98886e Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 9 Jun 2008 16:22:24 -0700 Subject: proper prototype for acpi_processor_tstate_has_changed() This patch adds a proper prototype for acpi_processor_tstate_has_changed() in include/acpi/processor.h Signed-off-by: Adrian Bunk Cc: Len Brown Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- drivers/acpi/processor_core.c | 1 - include/acpi/processor.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 386e5aa48834..9dd0fa93b9e1 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -86,7 +86,6 @@ static int acpi_processor_info_open_fs(struct inode *inode, struct file *file); static void acpi_processor_notify(acpi_handle handle, u32 event, void *data); static acpi_status acpi_processor_hotadd_init(acpi_handle handle, int *p_cpu); static int acpi_processor_handle_eject(struct acpi_processor *pr); -extern int acpi_processor_tstate_has_changed(struct acpi_processor *pr); static const struct acpi_device_id processor_device_ids[] = { diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 06480bcabfdc..06ebb6ef72aa 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -319,6 +319,7 @@ static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr) #endif /* CONFIG_CPU_FREQ */ /* in processor_throttling.c */ +int acpi_processor_tstate_has_changed(struct acpi_processor *pr); int acpi_processor_get_throttling_info(struct acpi_processor *pr); extern int acpi_processor_set_throttling(struct acpi_processor *pr, int state); extern struct file_operations acpi_processor_throttling_fops; -- cgit v1.2.3 From 45aec1ae72fc592f231e9e73ed9ed4d10cfbc0b5 Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Tue, 18 Mar 2008 17:00:22 -0700 Subject: x86: PAT export resource_wc in pci sysfs For the ranges with IORESOURCE_PREFETCH, export a new resource_wc interface in pci /sysfs along with resource (which is uncached). Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Acked-by: Jesse Barnes Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- Documentation/filesystems/sysfs-pci.txt | 1 + drivers/pci/pci-sysfs.c | 84 ++++++++++++++++++++++++--------- include/linux/pci.h | 1 + 3 files changed, 64 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt index 5daa2aaec2c5..68ef48839c04 100644 --- a/Documentation/filesystems/sysfs-pci.txt +++ b/Documentation/filesystems/sysfs-pci.txt @@ -36,6 +36,7 @@ files, each with their own function. local_cpus nearby CPU mask (cpumask, ro) resource PCI resource host addresses (ascii, ro) resource0..N PCI resource N, if present (binary, mmap) + resource0_wc..N_wc PCI WC map resource N, if prefetchable (binary, mmap) rom PCI ROM resource, if present (binary, ro) subsystem_device PCI subsystem device (ascii, ro) subsystem_vendor PCI subsystem vendor (ascii, ro) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 271d41cc05ab..9ec7d3977a82 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -489,13 +489,14 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr, * @kobj: kobject for mapping * @attr: struct bin_attribute for the file being mapped * @vma: struct vm_area_struct passed into the mmap + * @write_combine: 1 for write_combine mapping * * Use the regular PCI mapping routines to map a PCI resource into userspace. * FIXME: write combining? maybe automatic for prefetchable regions? */ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, - struct vm_area_struct *vma) + struct vm_area_struct *vma, int write_combine) { struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj)); @@ -518,7 +519,21 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, vma->vm_pgoff += start >> PAGE_SHIFT; mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io; - return pci_mmap_page_range(pdev, vma, mmap_type, 0); + return pci_mmap_page_range(pdev, vma, mmap_type, write_combine); +} + +static int +pci_mmap_resource_uc(struct kobject *kobj, struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + return pci_mmap_resource(kobj, attr, vma, 0); +} + +static int +pci_mmap_resource_wc(struct kobject *kobj, struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + return pci_mmap_resource(kobj, attr, vma, 1); } /** @@ -541,9 +556,46 @@ pci_remove_resource_files(struct pci_dev *pdev) sysfs_remove_bin_file(&pdev->dev.kobj, res_attr); kfree(res_attr); } + + res_attr = pdev->res_attr_wc[i]; + if (res_attr) { + sysfs_remove_bin_file(&pdev->dev.kobj, res_attr); + kfree(res_attr); + } } } +static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) +{ + /* allocate attribute structure, piggyback attribute name */ + int name_len = write_combine ? 13 : 10; + struct bin_attribute *res_attr; + int retval; + + res_attr = kzalloc(sizeof(*res_attr) + name_len, GFP_ATOMIC); + if (res_attr) { + char *res_attr_name = (char *)(res_attr + 1); + + if (write_combine) { + pdev->res_attr_wc[num] = res_attr; + sprintf(res_attr_name, "resource%d_wc", num); + res_attr->mmap = pci_mmap_resource_wc; + } else { + pdev->res_attr[num] = res_attr; + sprintf(res_attr_name, "resource%d", num); + res_attr->mmap = pci_mmap_resource_uc; + } + res_attr->attr.name = res_attr_name; + res_attr->attr.mode = S_IRUSR | S_IWUSR; + res_attr->size = pci_resource_len(pdev, num); + res_attr->private = &pdev->resource[num]; + retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr); + } else + retval = -ENOMEM; + + return retval; +} + /** * pci_create_resource_files - create resource files in sysfs for @dev * @dev: dev in question @@ -557,31 +609,19 @@ static int pci_create_resource_files(struct pci_dev *pdev) /* Expose the PCI resources from this device as files */ for (i = 0; i < PCI_ROM_RESOURCE; i++) { - struct bin_attribute *res_attr; /* skip empty resources */ if (!pci_resource_len(pdev, i)) continue; - /* allocate attribute structure, piggyback attribute name */ - res_attr = kzalloc(sizeof(*res_attr) + 10, GFP_ATOMIC); - if (res_attr) { - char *res_attr_name = (char *)(res_attr + 1); - - pdev->res_attr[i] = res_attr; - sprintf(res_attr_name, "resource%d", i); - res_attr->attr.name = res_attr_name; - res_attr->attr.mode = S_IRUSR | S_IWUSR; - res_attr->size = pci_resource_len(pdev, i); - res_attr->mmap = pci_mmap_resource; - res_attr->private = &pdev->resource[i]; - retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr); - if (retval) { - pci_remove_resource_files(pdev); - return retval; - } - } else { - return -ENOMEM; + retval = pci_create_attr(pdev, i, 0); + /* for prefetchable resources, create a WC mappable file */ + if (!retval && pdev->resource[i].flags & IORESOURCE_PREFETCH) + retval = pci_create_attr(pdev, i, 1); + + if (retval) { + pci_remove_resource_files(pdev); + return retval; } } return 0; diff --git a/include/linux/pci.h b/include/linux/pci.h index 509159bcd4e7..d18b1dd49fab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -206,6 +206,7 @@ struct pci_dev { struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */ int rom_attr_enabled; /* has display of the rom attribute been enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ + struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ #ifdef CONFIG_PCI_MSI struct list_head msi_list; #endif -- cgit v1.2.3 From f595ec964daf7f99668039d7303ddedd09a75142 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Jun 2008 10:47:56 +0200 Subject: common implementation of iterative div/mod We have a few instances of the open-coded iterative div/mod loop, used when we don't expcet the dividend to be much bigger than the divisor. Unfortunately modern gcc's have the tendency to strength "reduce" this into a full mod operation, which isn't necessarily any faster, and even if it were, doesn't exist if gcc implements it in libgcc. The workaround is to put a dummy asm statement in the loop to prevent gcc from performing the transformation. This patch creates a single implementation of this loop, and uses it to replace the open-coded versions I know about. Signed-off-by: Jeremy Fitzhardinge Cc: Andrew Morton Cc: john stultz Cc: Segher Boessenkool Cc: Christian Kujau Cc: Robert Hancock Signed-off-by: Ingo Molnar --- arch/x86/xen/time.c | 13 +++---------- include/linux/math64.h | 2 ++ include/linux/time.h | 11 ++--------- lib/div64.c | 23 +++++++++++++++++++++++ 4 files changed, 30 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c39e1a5aa241..52b2e3856980 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -150,11 +151,7 @@ static void do_stolen_accounting(void) if (stolen < 0) stolen = 0; - ticks = 0; - while (stolen >= NS_PER_TICK) { - ticks++; - stolen -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __get_cpu_var(residual_stolen) = stolen; account_steal_time(NULL, ticks); @@ -166,11 +163,7 @@ static void do_stolen_accounting(void) if (blocked < 0) blocked = 0; - ticks = 0; - while (blocked >= NS_PER_TICK) { - ticks++; - blocked -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); __get_cpu_var(residual_blocked) = blocked; account_steal_time(idle_task(smp_processor_id()), ticks); } diff --git a/include/linux/math64.h b/include/linux/math64.h index c1a5f81501ff..177785e1e4a3 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -81,4 +81,6 @@ static inline s64 div_s64(s64 dividend, s32 divisor) } #endif +u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); + #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/time.h b/include/linux/time.h index d32ef0ad4c0a..05f9517a8ed1 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -6,6 +6,7 @@ #ifdef __KERNEL__ # include # include +# include #endif #ifndef _STRUCT_TIMESPEC @@ -172,15 +173,7 @@ extern struct timeval ns_to_timeval(const s64 nsec); */ static inline void timespec_add_ns(struct timespec *a, u64 ns) { - ns += a->tv_nsec; - while(unlikely(ns >= NSEC_PER_SEC)) { - /* The following asm() prevents the compiler from - * optimising this loop into a modulo operation. */ - asm("" : "+r"(ns)); - - ns -= NSEC_PER_SEC; - a->tv_sec++; - } + a->tv_sec += iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } #endif /* __KERNEL__ */ diff --git a/lib/div64.c b/lib/div64.c index bb5bd0c0f030..76c01542d3e1 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -98,3 +98,26 @@ EXPORT_SYMBOL(div64_u64); #endif #endif /* BITS_PER_LONG == 32 */ + +/* + * Iterative div/mod for use when dividend is not expected to be much + * bigger than divisor. + */ +u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + u32 ret = 0; + + while (dividend >= divisor) { + /* The following asm() prevents the compiler from + optimising this loop into a modulo operation. */ + asm("" : "+rm"(dividend)); + + dividend -= divisor; + ret++; + } + + *remainder = dividend; + + return ret; +} +EXPORT_SYMBOL(iter_div_u64_rem); -- cgit v1.2.3 From d5e181f78ac753893eb930868a52a4488cd3de0a Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Jun 2008 10:47:58 +0200 Subject: add an inlined version of iter_div_u64_rem iter_div_u64_rem is used in the x86-64 vdso, which cannot call other kernel code. For this case, provide the always_inlined version, __iter_div_u64_rem. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- include/linux/math64.h | 19 +++++++++++++++++++ lib/div64.c | 15 +-------------- 2 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/math64.h b/include/linux/math64.h index 177785e1e4a3..c87f1528703a 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -83,4 +83,23 @@ static inline s64 div_s64(s64 dividend, s32 divisor) u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); +static __always_inline u32 +__iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + u32 ret = 0; + + while (dividend >= divisor) { + /* The following asm() prevents the compiler from + optimising this loop into a modulo operation. */ + asm("" : "+rm"(dividend)); + + dividend -= divisor; + ret++; + } + + *remainder = dividend; + + return ret; +} + #endif /* _LINUX_MATH64_H */ diff --git a/lib/div64.c b/lib/div64.c index 76c01542d3e1..a111eb8de9cf 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -105,19 +105,6 @@ EXPORT_SYMBOL(div64_u64); */ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { - u32 ret = 0; - - while (dividend >= divisor) { - /* The following asm() prevents the compiler from - optimising this loop into a modulo operation. */ - asm("" : "+rm"(dividend)); - - dividend -= divisor; - ret++; - } - - *remainder = dividend; - - return ret; + return __iter_div_u64_rem(dividend, divisor, remainder); } EXPORT_SYMBOL(iter_div_u64_rem); -- cgit v1.2.3 From 9412e28649d0272df5e4af57bb378926fd4df580 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Jun 2008 10:48:00 +0200 Subject: always_inline timespec_add_ns timespec_add_ns is used from the x86-64 vdso, which cannot call out to other kernel code. Make sure that timespec_add_ns is always inlined (and only uses always_inlined functions) to make sure there are no unexpected calls. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- include/linux/time.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index 05f9517a8ed1..e15206a7e82e 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -170,10 +170,13 @@ extern struct timeval ns_to_timeval(const s64 nsec); * timespec_add_ns - Adds nanoseconds to a timespec * @a: pointer to timespec to be incremented * @ns: unsigned nanoseconds value to be added + * + * This must always be inlined because its used from the x86-64 vdso, + * which cannot call other kernel functions. */ -static inline void timespec_add_ns(struct timespec *a, u64 ns) +static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) { - a->tv_sec += iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); + a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 3692fd0aaef489b063518b5999c702bada5b6e22 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 12 Jun 2008 07:07:22 +0100 Subject: [ARM] 5091/1: Add missing bitfield include to regs-lcd.h Macros like Fld() or FShft used in regs-lcd.h are defined in bitfield.h, but the latter is not included. Also fix one whitespace issue while being there. Signed-off-by: Antonio Ospite Signed-off-by: Stefan Schmidt Acked-by: Eric Miao Signed-off-by: Russell King --- include/asm-arm/arch-pxa/regs-lcd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-arm/arch-pxa/regs-lcd.h b/include/asm-arm/arch-pxa/regs-lcd.h index f762493f5141..3ba464c913a5 100644 --- a/include/asm-arm/arch-pxa/regs-lcd.h +++ b/include/asm-arm/arch-pxa/regs-lcd.h @@ -1,5 +1,8 @@ #ifndef __ASM_ARCH_REGS_LCD_H #define __ASM_ARCH_REGS_LCD_H + +#include + /* * LCD Controller Registers and Bits Definitions */ @@ -69,7 +72,7 @@ #define LCCR0_QDM (1 << 11) /* LCD Quick Disable mask */ #define LCCR0_PDD (0xff << 12) /* Palette DMA request delay */ #define LCCR0_PDD_S 12 -#define LCCR0_BM (1 << 20) /* Branch mask */ +#define LCCR0_BM (1 << 20) /* Branch mask */ #define LCCR0_OUM (1 << 21) /* Output FIFO underrun mask */ #define LCCR0_LCDT (1 << 22) /* LCD panel type */ #define LCCR0_RDSTM (1 << 23) /* Read status interrupt mask */ -- cgit v1.2.3 From ec0a196626bd12e0ba108d7daa6d95a4fb25c2c5 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 12 Jun 2008 16:31:35 -0700 Subject: tcp: Revert 'process defer accept as established' changes. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ------- include/net/request_sock.h | 4 ++-- include/net/tcp.h | 1 - net/ipv4/inet_connection_sock.c | 11 +++++++--- net/ipv4/tcp.c | 18 ++++++++++------- net/ipv4/tcp_input.c | 45 ----------------------------------------- net/ipv4/tcp_ipv4.c | 8 -------- net/ipv4/tcp_minisocks.c | 32 +++++++++++------------------ net/ipv4/tcp_timer.c | 5 ----- 9 files changed, 33 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 18e62e3d406f..b31b6b74aa28 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -239,11 +239,6 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } -struct tcp_deferred_accept_info { - struct sock *listen_sk; - struct request_sock *request; -}; - struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; @@ -379,8 +374,6 @@ struct tcp_sock { unsigned int keepalive_intvl; /* time interval between keep alive probes */ int linger2; - struct tcp_deferred_accept_info defer_tcp_accept; - unsigned long last_synq_overflow; u32 tso_deferred; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b220b5f624de..0c96e7bed5db 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -115,8 +115,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; rwlock_t syn_wait_lock; - u16 rskq_defer_accept; - /* 2 bytes hole, try to pack */ + u8 rskq_defer_accept; + /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index d448310c82c1..cf54034019d9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -139,7 +139,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define MAX_TCP_ACCEPT_DEFERRED 65535 #define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 828ea211ff21..045e799d3e1d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, struct inet_connection_sock *icsk = inet_csk(parent); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int thresh = max_retries; unsigned long now = jiffies; struct request_sock **reqp, *req; int i, budget; @@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } } + if (queue->rskq_defer_accept) + max_retries = queue->rskq_defer_accept; + budget = 2 * (lopt->nr_table_entries / (timeout / interval)); i = lopt->clock_hand; @@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, reqp=&lopt->syn_table[i]; while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { - if (req->retrans < thresh && - !req->rsk_ops->rtx_syn_ack(parent, req)) { + if ((req->retrans < (inet_rsk(req)->acked ? max_retries : thresh)) && + (inet_rsk(req)->acked || + !req->rsk_ops->rtx_syn_ack(parent, req))) { unsigned long timeo; if (req->retrans++ == 0) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ab66683b8043..fc54a48fde1e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2112,12 +2112,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - if (val < 0) { - err = -EINVAL; - } else { - if (val > MAX_TCP_ACCEPT_DEFERRED) - val = MAX_TCP_ACCEPT_DEFERRED; - icsk->icsk_accept_queue.rskq_defer_accept = val; + icsk->icsk_accept_queue.rskq_defer_accept = 0; + if (val > 0) { + /* Translate value in seconds to number of + * retransmits */ + while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && + val > ((TCP_TIMEOUT_INIT / HZ) << + icsk->icsk_accept_queue.rskq_defer_accept)) + icsk->icsk_accept_queue.rskq_defer_accept++; + icsk->icsk_accept_queue.rskq_defer_accept++; } break; @@ -2299,7 +2302,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = icsk->icsk_accept_queue.rskq_defer_accept; + val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : + ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eba873e9b560..cad73b7dfef0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4541,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th) } } -static int tcp_defer_accept_check(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->defer_tcp_accept.request) { - int queued_data = tp->rcv_nxt - tp->copied_seq; - int hasfin = !skb_queue_empty(&sk->sk_receive_queue) ? - tcp_hdr((struct sk_buff *) - sk->sk_receive_queue.prev)->fin : 0; - - if (queued_data && hasfin) - queued_data--; - - if (queued_data && - tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) { - if (sock_flag(sk, SOCK_KEEPOPEN)) { - inet_csk_reset_keepalive_timer(sk, - keepalive_time_when(tp)); - } else { - inet_csk_delete_keepalive_timer(sk); - } - - inet_csk_reqsk_queue_add( - tp->defer_tcp_accept.listen_sk, - tp->defer_tcp_accept.request, - sk); - - tp->defer_tcp_accept.listen_sk->sk_data_ready( - tp->defer_tcp_accept.listen_sk, 0); - - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } else if (hasfin || - tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) { - tcp_reset(sk); - return -1; - } - } - return 0; -} - static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); @@ -4944,8 +4901,6 @@ step5: tcp_data_snd_check(sk); tcp_ack_snd_check(sk); - - tcp_defer_accept_check(sk); return 0; csum_error: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4f8485c67d1a..97a230026e13 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1918,14 +1918,6 @@ int tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - if (tp->defer_tcp_accept.request) { - reqsk_free(tp->defer_tcp_accept.request); - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } - atomic_dec(&tcp_sockets_allocated); return 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 019c8c16e5cc..8245247a6ceb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, does sequence test, SYN is truncated, and thus we consider it a bare ACK. - Both ends (listening sockets) accept the new incoming - connection and try to talk to each other. 8-) + If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this + bare ACK. Otherwise, we create an established connection. Both + ends (listening sockets) accept the new incoming connection and try + to talk to each other. 8-) Note: This case is both harmless, and rare. Possibility is about the same as us discovering intelligent life on another plant tomorrow. @@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ + if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; + return NULL; + } + /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all * the tests. THIS SEGMENT MUST MOVE SOCKET TO @@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, inet_csk_reqsk_queue_unlink(sk, req, prev); inet_csk_reqsk_queue_removed(sk, req); - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && - TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { - - /* the accept queue handling is done is est recv slow - * path so lets make sure to start there - */ - tcp_sk(child)->pred_flags = 0; - sock_hold(sk); - sock_hold(child); - tcp_sk(child)->defer_tcp_accept.listen_sk = sk; - tcp_sk(child)->defer_tcp_accept.request = req; - - inet_csk_reset_keepalive_timer(child, - inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ); - } else { - inet_csk_reqsk_queue_add(sk, req, child); - } - + inet_csk_reqsk_queue_add(sk, req, child); return child; listen_overflow: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4de68cf5f2aa..63ed9d6830e7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { - tcp_send_active_reset(sk, GFP_ATOMIC); - goto death; - } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) goto out; -- cgit v1.2.3 From 69c5ddf58a03da3686691ad2f293bc79fd977c10 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Jun 2008 15:21:29 -0700 Subject: m68k: Add ext2_find_{first,next}_bit() for ext4 Add ext2_find_{first,next}_bit(), which are needed for ext4. They're derived out of the ext2_find_next_zero_bit found in the same file. Compile tested with crosstools [Reworked to preserve all symmetry with ext2_find_{first,next}_zero_bit()] This fixes http://bugzilla.kernel.org/show_bug.cgi?id=10393 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-m68k/bitops.h | 45 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 43 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-m68k/bitops.h b/include/asm-m68k/bitops.h index 83d1f286230b..3e8106442d5a 100644 --- a/include/asm-m68k/bitops.h +++ b/include/asm-m68k/bitops.h @@ -410,8 +410,49 @@ static inline int ext2_find_next_zero_bit(const void *vaddr, unsigned size, res = ext2_find_first_zero_bit (p, size - 32 * (p - addr)); return (p - addr) * 32 + res; } -#define ext2_find_next_bit(addr, size, off) \ - generic_find_next_le_bit((unsigned long *)(addr), (size), (off)) + +static inline int ext2_find_first_bit(const void *vaddr, unsigned size) +{ + const unsigned long *p = vaddr, *addr = vaddr; + int res; + + if (!size) + return 0; + + size = (size >> 5) + ((size & 31) > 0); + while (*p++ == 0UL) { + if (--size == 0) + return (p - addr) << 5; + } + + --p; + for (res = 0; res < 32; res++) + if (ext2_test_bit(res, p)) + break; + return (p - addr) * 32 + res; +} + +static inline int ext2_find_next_bit(const void *vaddr, unsigned size, + unsigned offset) +{ + const unsigned long *addr = vaddr; + const unsigned long *p = addr + (offset >> 5); + int bit = offset & 31UL, res; + + if (offset >= size) + return size; + + if (bit) { + /* Look for one in first longword */ + for (res = bit; res < 32; res++) + if (ext2_test_bit(res, p)) + return (p - addr) * 32 + res; + p++; + } + /* No set bit yet, search remaining full bytes for a set bit */ + res = ext2_find_first_bit(p, size - 32 * (p - addr)); + return (p - addr) * 32 + res; +} #endif /* __KERNEL__ */ -- cgit v1.2.3 From 57d3c64fd8130ebdacd85a36c9656ba5e221f3a3 Mon Sep 17 00:00:00 2001 From: Ben Nizette Date: Thu, 12 Jun 2008 15:21:31 -0700 Subject: proc_fs.h: move struct mm_struct forward-declaration Move the forward-declaration of struct mm_struct a little way up proc_fs.h. This fixes a bunch of "'struct mm_struct' declared inside parameter list" warnings with CONFIG_PROC_FS=n Signed-off-by: Ben Nizette Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 9883bc942262..fff1d27ddb4c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -9,6 +9,8 @@ struct net; struct completion; +struct mm_struct; + /* * The proc filesystem constants/structures */ @@ -101,8 +103,6 @@ extern spinlock_t proc_subdir_lock; extern void proc_root_init(void); extern void proc_misc_init(void); -struct mm_struct; - void proc_flush_task(struct task_struct *task); struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *); int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir); -- cgit v1.2.3 From 24aac480e76c6f5d1391ac05c5e9c0eb9b0cd302 Mon Sep 17 00:00:00 2001 From: Mike Miller Date: Thu, 12 Jun 2008 15:21:34 -0700 Subject: cciss: add new hardware support Add support for the next generation of HP Smart Array SAS/SATA controllers. Shipping date is late Fall 2008. Bump the driver version to 3.6.20 to reflect the new hardware support from patch 1 of this set. Signed-off-by: Mike Miller Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cciss.txt | 5 +++++ drivers/block/cciss.c | 21 ++++++++++++++++----- include/linux/pci_ids.h | 1 + 3 files changed, 22 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/Documentation/cciss.txt b/Documentation/cciss.txt index e65736c6b8bc..63e59b8847c5 100644 --- a/Documentation/cciss.txt +++ b/Documentation/cciss.txt @@ -21,6 +21,11 @@ This driver is known to work with the following cards: * SA E200 * SA E200i * SA E500 + * SA P212 + * SA P410 + * SA P410i + * SA P411 + * SA P812 Detecting drive failures: ------------------------- diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index e336b05fe4a7..5f1e1cc6165a 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -53,15 +53,16 @@ #include #define CCISS_DRIVER_VERSION(maj,min,submin) ((maj<<16)|(min<<8)|(submin)) -#define DRIVER_NAME "HP CISS Driver (v 3.6.14)" -#define DRIVER_VERSION CCISS_DRIVER_VERSION(3,6,14) +#define DRIVER_NAME "HP CISS Driver (v 3.6.20)" +#define DRIVER_VERSION CCISS_DRIVER_VERSION(3, 6, 20) /* Embedded module documentation macros - see modules.h */ MODULE_AUTHOR("Hewlett-Packard Company"); -MODULE_DESCRIPTION("Driver for HP Controller SA5xxx SA6xxx version 3.6.14"); +MODULE_DESCRIPTION("Driver for HP Smart Array Controllers"); MODULE_SUPPORTED_DEVICE("HP SA5i SA5i+ SA532 SA5300 SA5312 SA641 SA642 SA6400" - " SA6i P600 P800 P400 P400i E200 E200i E500"); -MODULE_VERSION("3.6.14"); + " SA6i P600 P800 P400 P400i E200 E200i E500 P700m" + " Smart Array G2 Series SAS/SATA Controllers"); +MODULE_VERSION("3.6.20"); MODULE_LICENSE("GPL"); #include "cciss_cmd.h" @@ -90,6 +91,11 @@ static const struct pci_device_id cciss_pci_device_id[] = { {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSD, 0x103C, 0x3215}, {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSC, 0x103C, 0x3237}, {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSC, 0x103C, 0x323D}, + {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSE, 0x103C, 0x3241}, + {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSE, 0x103C, 0x3243}, + {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSE, 0x103C, 0x3245}, + {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSE, 0x103C, 0x3247}, + {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_CISSE, 0x103C, 0x3249}, {PCI_VENDOR_ID_HP, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_STORAGE_RAID << 8, 0xffff << 8, 0}, {0,} @@ -123,6 +129,11 @@ static struct board_type products[] = { {0x3215103C, "Smart Array E200i", &SA5_access, 120}, {0x3237103C, "Smart Array E500", &SA5_access, 512}, {0x323D103C, "Smart Array P700m", &SA5_access, 512}, + {0x3241103C, "Smart Array P212", &SA5_access, 384}, + {0x3243103C, "Smart Array P410", &SA5_access, 384}, + {0x3245103C, "Smart Array P410i", &SA5_access, 384}, + {0x3247103C, "Smart Array P411", &SA5_access, 384}, + {0x3249103C, "Smart Array P812", &SA5_access, 384}, {0xFFFF103C, "Unknown Smart Array", &SA5_access, 120}, }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 9b940e644179..eafc9d6d2b35 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -716,6 +716,7 @@ #define PCI_DEVICE_ID_HP_CISSA 0x3220 #define PCI_DEVICE_ID_HP_CISSC 0x3230 #define PCI_DEVICE_ID_HP_CISSD 0x3238 +#define PCI_DEVICE_ID_HP_CISSE 0x323a #define PCI_DEVICE_ID_HP_ZX2_IOC 0x4031 #define PCI_VENDOR_ID_PCTECH 0x1042 -- cgit v1.2.3 From 2165009bdf63f79716a36ad545df14c3cdf958b7 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 12 Jun 2008 15:21:47 -0700 Subject: pagemap: pass mm into pagewalkers We need this at least for huge page detection for now, because powerpc needs the vm_area_struct to be able to determine whether a virtual address is referring to a huge page (its pmd_huge() doesn't work). It might also come in handy for some of the other users. Signed-off-by: Dave Hansen Acked-by: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 44 +++++++++++++++++++++++++------------------- include/linux/mm.h | 17 +++++++++-------- mm/pagewalk.c | 42 ++++++++++++++++++++++-------------------- 3 files changed, 56 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 17403629e330..f0df3109343d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -315,9 +315,9 @@ struct mem_size_stats { }; static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - void *private) + struct mm_walk *walk) { - struct mem_size_stats *mss = private; + struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; pte_t *pte, ptent; spinlock_t *ptl; @@ -365,19 +365,21 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return 0; } -static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range }; - static int show_smap(struct seq_file *m, void *v) { struct vm_area_struct *vma = v; struct mem_size_stats mss; int ret; + struct mm_walk smaps_walk = { + .pmd_entry = smaps_pte_range, + .mm = vma->vm_mm, + .private = &mss, + }; memset(&mss, 0, sizeof mss); mss.vma = vma; if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end, - &smaps_walk, &mss); + walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); ret = show_map(m, v); if (ret) @@ -426,9 +428,9 @@ const struct file_operations proc_smaps_operations = { }; static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, void *private) + unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma = private; + struct vm_area_struct *vma = walk->private; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; @@ -452,8 +454,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, return 0; } -static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range }; - static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -476,11 +476,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { + static struct mm_walk clear_refs_walk; + memset(&clear_refs_walk, 0, sizeof(clear_refs_walk)); + clear_refs_walk.pmd_entry = clear_refs_pte_range; + clear_refs_walk.mm = mm; down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) + for (vma = mm->mmap; vma; vma = vma->vm_next) { + clear_refs_walk.private = vma; if (!is_vm_hugetlb_page(vma)) - walk_page_range(mm, vma->vm_start, vma->vm_end, - &clear_refs_walk, vma); + walk_page_range(vma->vm_start, vma->vm_end, + &clear_refs_walk); + } flush_tlb_mm(mm); up_read(&mm->mmap_sem); mmput(mm); @@ -528,9 +534,9 @@ static int add_to_pagemap(unsigned long addr, u64 pfn, } static int pagemap_pte_hole(unsigned long start, unsigned long end, - void *private) + struct mm_walk *walk) { - struct pagemapread *pm = private; + struct pagemapread *pm = walk->private; unsigned long addr; int err = 0; for (addr = start; addr < end; addr += PAGE_SIZE) { @@ -548,9 +554,9 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte) } static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - void *private) + struct mm_walk *walk) { - struct pagemapread *pm = private; + struct pagemapread *pm = walk->private; pte_t *pte; int err = 0; @@ -675,8 +681,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, * user buffer is tracked in "pm", and the walk * will stop when we hit the end of the buffer. */ - ret = walk_page_range(mm, start_vaddr, end_vaddr, - &pagemap_walk, &pm); + ret = walk_page_range(start_vaddr, end_vaddr, + &pagemap_walk); if (ret == PM_END_OF_BUFFER) ret = 0; /* don't need mmap_sem for these, but this looks cleaner */ diff --git a/include/linux/mm.h b/include/linux/mm.h index c31a9cd2a30e..586a943cab01 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -760,16 +760,17 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *); - int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *); - int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *); - int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *); - int (*pte_hole)(unsigned long, unsigned long, void *); + int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); + struct mm_struct *mm; + void *private; }; -int walk_page_range(const struct mm_struct *, unsigned long addr, - unsigned long end, const struct mm_walk *walk, - void *private); +int walk_page_range(unsigned long addr, unsigned long end, + struct mm_walk *walk); void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 0afd2387e507..d5878bed7841 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -3,14 +3,14 @@ #include static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - const struct mm_walk *walk, void *private) + struct mm_walk *walk) { pte_t *pte; int err = 0; pte = pte_offset_map(pmd, addr); for (;;) { - err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, private); + err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; addr += PAGE_SIZE; @@ -24,7 +24,7 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, } static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, - const struct mm_walk *walk, void *private) + struct mm_walk *walk) { pmd_t *pmd; unsigned long next; @@ -35,15 +35,15 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) { if (walk->pte_hole) - err = walk->pte_hole(addr, next, private); + err = walk->pte_hole(addr, next, walk); if (err) break; continue; } if (walk->pmd_entry) - err = walk->pmd_entry(pmd, addr, next, private); + err = walk->pmd_entry(pmd, addr, next, walk); if (!err && walk->pte_entry) - err = walk_pte_range(pmd, addr, next, walk, private); + err = walk_pte_range(pmd, addr, next, walk); if (err) break; } while (pmd++, addr = next, addr != end); @@ -52,7 +52,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, } static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, - const struct mm_walk *walk, void *private) + struct mm_walk *walk) { pud_t *pud; unsigned long next; @@ -63,15 +63,15 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) { if (walk->pte_hole) - err = walk->pte_hole(addr, next, private); + err = walk->pte_hole(addr, next, walk); if (err) break; continue; } if (walk->pud_entry) - err = walk->pud_entry(pud, addr, next, private); + err = walk->pud_entry(pud, addr, next, walk); if (!err && (walk->pmd_entry || walk->pte_entry)) - err = walk_pmd_range(pud, addr, next, walk, private); + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -85,15 +85,15 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, * @addr: starting address * @end: ending address * @walk: set of callbacks to invoke for each level of the tree - * @private: private data passed to the callback function * * Recursively walk the page table for the memory area in a VMA, * calling supplied callbacks. Callbacks are called in-order (first * PGD, first PUD, first PMD, first PTE, second PTE... second PMD, * etc.). If lower-level callbacks are omitted, walking depth is reduced. * - * Each callback receives an entry pointer, the start and end of the - * associated range, and a caller-supplied private data pointer. + * Each callback receives an entry pointer and the start and end of the + * associated range, and a copy of the original mm_walk for access to + * the ->private or ->mm fields. * * No locks are taken, but the bottom level iterator will map PTE * directories from highmem if necessary. @@ -101,9 +101,8 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, * If any callback returns a non-zero value, the walk is aborted and * the return value is propagated back to the caller. Otherwise 0 is returned. */ -int walk_page_range(const struct mm_struct *mm, - unsigned long addr, unsigned long end, - const struct mm_walk *walk, void *private) +int walk_page_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) { pgd_t *pgd; unsigned long next; @@ -112,21 +111,24 @@ int walk_page_range(const struct mm_struct *mm, if (addr >= end) return err; - pgd = pgd_offset(mm, addr); + if (!walk->mm) + return -EINVAL; + + pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { if (walk->pte_hole) - err = walk->pte_hole(addr, next, private); + err = walk->pte_hole(addr, next, walk); if (err) break; continue; } if (walk->pgd_entry) - err = walk->pgd_entry(pgd, addr, next, private); + err = walk->pgd_entry(pgd, addr, next, walk); if (!err && (walk->pud_entry || walk->pmd_entry || walk->pte_entry)) - err = walk_pud_range(pgd, addr, next, walk, private); + err = walk_pud_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); -- cgit v1.2.3 From e374d17cd74ec5967f81e2b0c67ec3219a2bbbcc Mon Sep 17 00:00:00 2001 From: Kyle McMartin Date: Sat, 31 May 2008 12:15:42 -0400 Subject: parisc: fix miscompilation of ip_fast_csum with gcc >= 4.3 ip_fast_csum needs an asm "memory" clobber, otherwise the aggressive optimizations in gcc-4.3 cause it to be miscompiled. Signed-off-by: Kyle McMartin --- include/asm-parisc/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-parisc/checksum.h b/include/asm-parisc/checksum.h index cc3ec1bd8919..e9639ccc3fce 100644 --- a/include/asm-parisc/checksum.h +++ b/include/asm-parisc/checksum.h @@ -65,7 +65,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) "2:\n" : "=r" (sum), "=r" (iph), "=r" (ihl) : "1" (iph), "2" (ihl) - : "r19", "r20", "r21" ); + : "r19", "r20", "r21", "memory"); return (__force __sum16)sum; } -- cgit v1.2.3