diff options
Diffstat (limited to 'include/linux')
236 files changed, 6234 insertions, 3304 deletions
diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 818cc3a..6a65231 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -46,8 +46,8 @@ header-y += chio.h header-y += coda_psdev.h header-y += coff.h header-y += comstats.h -header-y += consolemap.h header-y += const.h +header-y += cgroupstats.h header-y += cycx_cfm.h header-y += dlm_device.h header-y += dlm_netlink.h @@ -78,7 +78,6 @@ header-y += if_arcnet.h header-y += if_bonding.h header-y += if_cablemodem.h header-y += if_fc.h -header-y += if_fddi.h header-y += if.h header-y += if_hippi.h header-y += if_infiniband.h @@ -121,7 +120,6 @@ header-y += nl80211.h header-y += oom.h header-y += param.h header-y += pci_regs.h -header-y += personality.h header-y += pfkeyv2.h header-y += pg.h header-y += phantom.h @@ -159,7 +157,6 @@ header-y += video_decoder.h header-y += video_encoder.h header-y += videotext.h header-y += vt.h -header-y += wireless.h header-y += x25.h unifdef-y += acct.h @@ -189,6 +186,7 @@ unifdef-y += cyclades.h unifdef-y += dccp.h unifdef-y += dirent.h unifdef-y += dlm.h +unifdef-y += edd.h unifdef-y += elfcore.h unifdef-y += errno.h unifdef-y += errqueue.h @@ -286,6 +284,7 @@ unifdef-y += nfs_idmap.h unifdef-y += n_r3964.h unifdef-y += nubus.h unifdef-y += nvram.h +unifdef-y += oom.h unifdef-y += parport.h unifdef-y += patchkey.h unifdef-y += pci.h @@ -308,6 +307,7 @@ unifdef-y += rtc.h unifdef-y += rtnetlink.h unifdef-y += scc.h unifdef-y += sched.h +unifdef-y += screen_info.h unifdef-y += sdla.h unifdef-y += selinux_netlink.h unifdef-y += sem.h @@ -343,6 +343,9 @@ unifdef-y += user.h unifdef-y += utsname.h unifdef-y += videodev2.h unifdef-y += videodev.h +unifdef-y += virtio_config.h +unifdef-y += virtio_blk.h +unifdef-y += virtio_net.h unifdef-y += wait.h unifdef-y += wanrouter.h unifdef-y += watchdog.h diff --git a/include/linux/acpi.h b/include/linux/acpi.h index bf5e000..8ccedf7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -189,32 +189,6 @@ extern int ec_transaction(u8 command, extern int acpi_blacklisted(void); extern void acpi_bios_year(char *s); -#define ACPI_CSTATE_LIMIT_DEFINED /* for driver builds */ -#ifdef CONFIG_ACPI - -/* - * Set highest legal C-state - * 0: C0 okay, but not C1 - * 1: C1 okay, but not C2 - * 2: C2 okay, but not C3 etc. - */ - -extern unsigned int max_cstate; - -static inline unsigned int acpi_get_cstate_limit(void) -{ - return max_cstate; -} -static inline void acpi_set_cstate_limit(unsigned int new_limit) -{ - max_cstate = new_limit; - return; -} -#else -static inline unsigned int acpi_get_cstate_limit(void) { return 0; } -static inline void acpi_set_cstate_limit(unsigned int new_limit) { return; } -#endif - #ifdef CONFIG_ACPI_NUMA int acpi_get_pxm(acpi_handle handle); int acpi_get_node(acpi_handle *handle); diff --git a/include/linux/aio.h b/include/linux/aio.h index d10e608..7ef8de6 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -232,18 +232,6 @@ int FASTCALL(io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, __put_ioctx(kioctx); \ } while (0) -#define in_aio() (unlikely(!is_sync_wait(current->io_wait))) - -/* may be used for debugging */ -#define warn_if_async() \ -do { \ - if (in_aio()) { \ - printk(KERN_ERR "%s(%s:%d) called in async context!\n", \ - __FUNCTION__, __FILE__, __LINE__); \ - dump_stack(); \ - } \ -} while (0) - #define io_wait_to_kiocb(wait) container_of(wait, struct kiocb, ki_wait) #include <linux/aio_abi.h> diff --git a/include/linux/apm_bios.h b/include/linux/apm_bios.h index 5f921c8..9754baa 100644 --- a/include/linux/apm_bios.h +++ b/include/linux/apm_bios.h @@ -16,29 +16,29 @@ * General Public License for more details. */ -typedef unsigned short apm_event_t; -typedef unsigned short apm_eventinfo_t; +#include <linux/types.h> + +struct apm_bios_info { + __u16 version; + __u16 cseg; + __u32 offset; + __u16 cseg_16; + __u16 dseg; + __u16 flags; + __u16 cseg_len; + __u16 cseg_16_len; + __u16 dseg_len; +}; #ifdef __KERNEL__ -#include <linux/types.h> +typedef unsigned short apm_event_t; +typedef unsigned short apm_eventinfo_t; #define APM_CS (GDT_ENTRY_APMBIOS_BASE * 8) #define APM_CS_16 (APM_CS + 8) #define APM_DS (APM_CS_16 + 8) -struct apm_bios_info { - u16 version; - u16 cseg; - u32 offset; - u16 cseg_16; - u16 dseg; - u16 flags; - u16 cseg_len; - u16 cseg_16_len; - u16 dseg_len; -}; - /* Results of APM Installation Check */ #define APM_16_BIT_SUPPORT 0x0001 #define APM_32_BIT_SUPPORT 0x0002 diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h new file mode 100644 index 0000000..0602339 --- /dev/null +++ b/include/linux/atmel-ssc.h @@ -0,0 +1,312 @@ +#ifndef __INCLUDE_ATMEL_SSC_H +#define __INCLUDE_ATMEL_SSC_H + +#include <linux/platform_device.h> +#include <linux/list.h> + +struct ssc_device { + struct list_head list; + void __iomem *regs; + struct platform_device *pdev; + struct clk *clk; + int user; + int irq; +}; + +struct ssc_device * __must_check ssc_request(unsigned int ssc_num); +void ssc_free(struct ssc_device *ssc); + +/* SSC register offsets */ + +/* SSC Control Register */ +#define SSC_CR 0x00000000 +#define SSC_CR_RXDIS_SIZE 1 +#define SSC_CR_RXDIS_OFFSET 1 +#define SSC_CR_RXEN_SIZE 1 +#define SSC_CR_RXEN_OFFSET 0 +#define SSC_CR_SWRST_SIZE 1 +#define SSC_CR_SWRST_OFFSET 15 +#define SSC_CR_TXDIS_SIZE 1 +#define SSC_CR_TXDIS_OFFSET 9 +#define SSC_CR_TXEN_SIZE 1 +#define SSC_CR_TXEN_OFFSET 8 + +/* SSC Clock Mode Register */ +#define SSC_CMR 0x00000004 +#define SSC_CMR_DIV_SIZE 12 +#define SSC_CMR_DIV_OFFSET 0 + +/* SSC Receive Clock Mode Register */ +#define SSC_RCMR 0x00000010 +#define SSC_RCMR_CKG_SIZE 2 +#define SSC_RCMR_CKG_OFFSET 6 +#define SSC_RCMR_CKI_SIZE 1 +#define SSC_RCMR_CKI_OFFSET 5 +#define SSC_RCMR_CKO_SIZE 3 +#define SSC_RCMR_CKO_OFFSET 2 +#define SSC_RCMR_CKS_SIZE 2 +#define SSC_RCMR_CKS_OFFSET 0 +#define SSC_RCMR_PERIOD_SIZE 8 +#define SSC_RCMR_PERIOD_OFFSET 24 +#define SSC_RCMR_START_SIZE 4 +#define SSC_RCMR_START_OFFSET 8 +#define SSC_RCMR_STOP_SIZE 1 +#define SSC_RCMR_STOP_OFFSET 12 +#define SSC_RCMR_STTDLY_SIZE 8 +#define SSC_RCMR_STTDLY_OFFSET 16 + +/* SSC Receive Frame Mode Register */ +#define SSC_RFMR 0x00000014 +#define SSC_RFMR_DATLEN_SIZE 5 +#define SSC_RFMR_DATLEN_OFFSET 0 +#define SSC_RFMR_DATNB_SIZE 4 +#define SSC_RFMR_DATNB_OFFSET 8 +#define SSC_RFMR_FSEDGE_SIZE 1 +#define SSC_RFMR_FSEDGE_OFFSET 24 +#define SSC_RFMR_FSLEN_SIZE 4 +#define SSC_RFMR_FSLEN_OFFSET 16 +#define SSC_RFMR_FSOS_SIZE 4 +#define SSC_RFMR_FSOS_OFFSET 20 +#define SSC_RFMR_LOOP_SIZE 1 +#define SSC_RFMR_LOOP_OFFSET 5 +#define SSC_RFMR_MSBF_SIZE 1 +#define SSC_RFMR_MSBF_OFFSET 7 + +/* SSC Transmit Clock Mode Register */ +#define SSC_TCMR 0x00000018 +#define SSC_TCMR_CKG_SIZE 2 +#define SSC_TCMR_CKG_OFFSET 6 +#define SSC_TCMR_CKI_SIZE 1 +#define SSC_TCMR_CKI_OFFSET 5 +#define SSC_TCMR_CKO_SIZE 3 +#define SSC_TCMR_CKO_OFFSET 2 +#define SSC_TCMR_CKS_SIZE 2 +#define SSC_TCMR_CKS_OFFSET 0 +#define SSC_TCMR_PERIOD_SIZE 8 +#define SSC_TCMR_PERIOD_OFFSET 24 +#define SSC_TCMR_START_SIZE 4 +#define SSC_TCMR_START_OFFSET 8 +#define SSC_TCMR_STTDLY_SIZE 8 +#define SSC_TCMR_STTDLY_OFFSET 16 + +/* SSC Transmit Frame Mode Register */ +#define SSC_TFMR 0x0000001c +#define SSC_TFMR_DATDEF_SIZE 1 +#define SSC_TFMR_DATDEF_OFFSET 5 +#define SSC_TFMR_DATLEN_SIZE 5 +#define SSC_TFMR_DATLEN_OFFSET 0 +#define SSC_TFMR_DATNB_SIZE 4 +#define SSC_TFMR_DATNB_OFFSET 8 +#define SSC_TFMR_FSDEN_SIZE 1 +#define SSC_TFMR_FSDEN_OFFSET 23 +#define SSC_TFMR_FSEDGE_SIZE 1 +#define SSC_TFMR_FSEDGE_OFFSET 24 +#define SSC_TFMR_FSLEN_SIZE 4 +#define SSC_TFMR_FSLEN_OFFSET 16 +#define SSC_TFMR_FSOS_SIZE 3 +#define SSC_TFMR_FSOS_OFFSET 20 +#define SSC_TFMR_MSBF_SIZE 1 +#define SSC_TFMR_MSBF_OFFSET 7 + +/* SSC Receive Hold Register */ +#define SSC_RHR 0x00000020 +#define SSC_RHR_RDAT_SIZE 32 +#define SSC_RHR_RDAT_OFFSET 0 + +/* SSC Transmit Hold Register */ +#define SSC_THR 0x00000024 +#define SSC_THR_TDAT_SIZE 32 +#define SSC_THR_TDAT_OFFSET 0 + +/* SSC Receive Sync. Holding Register */ +#define SSC_RSHR 0x00000030 +#define SSC_RSHR_RSDAT_SIZE 16 +#define SSC_RSHR_RSDAT_OFFSET 0 + +/* SSC Transmit Sync. Holding Register */ +#define SSC_TSHR 0x00000034 +#define SSC_TSHR_TSDAT_SIZE 16 +#define SSC_TSHR_RSDAT_OFFSET 0 + +/* SSC Receive Compare 0 Register */ +#define SSC_RC0R 0x00000038 +#define SSC_RC0R_CP0_SIZE 16 +#define SSC_RC0R_CP0_OFFSET 0 + +/* SSC Receive Compare 1 Register */ +#define SSC_RC1R 0x0000003c +#define SSC_RC1R_CP1_SIZE 16 +#define SSC_RC1R_CP1_OFFSET 0 + +/* SSC Status Register */ +#define SSC_SR 0x00000040 +#define SSC_SR_CP0_SIZE 1 +#define SSC_SR_CP0_OFFSET 8 +#define SSC_SR_CP1_SIZE 1 +#define SSC_SR_CP1_OFFSET 9 +#define SSC_SR_ENDRX_SIZE 1 +#define SSC_SR_ENDRX_OFFSET 6 +#define SSC_SR_ENDTX_SIZE 1 +#define SSC_SR_ENDTX_OFFSET 2 +#define SSC_SR_OVRUN_SIZE 1 +#define SSC_SR_OVRUN_OFFSET 5 +#define SSC_SR_RXBUFF_SIZE 1 +#define SSC_SR_RXBUFF_OFFSET 7 +#define SSC_SR_RXEN_SIZE 1 +#define SSC_SR_RXEN_OFFSET 17 +#define SSC_SR_RXRDY_SIZE 1 +#define SSC_SR_RXRDY_OFFSET 4 +#define SSC_SR_RXSYN_SIZE 1 +#define SSC_SR_RXSYN_OFFSET 11 +#define SSC_SR_TXBUFE_SIZE 1 +#define SSC_SR_TXBUFE_OFFSET 3 +#define SSC_SR_TXEMPTY_SIZE 1 +#define SSC_SR_TXEMPTY_OFFSET 1 +#define SSC_SR_TXEN_SIZE 1 +#define SSC_SR_TXEN_OFFSET 16 +#define SSC_SR_TXRDY_SIZE 1 +#define SSC_SR_TXRDY_OFFSET 0 +#define SSC_SR_TXSYN_SIZE 1 +#define SSC_SR_TXSYN_OFFSET 10 + +/* SSC Interrupt Enable Register */ +#define SSC_IER 0x00000044 +#define SSC_IER_CP0_SIZE 1 +#define SSC_IER_CP0_OFFSET 8 +#define SSC_IER_CP1_SIZE 1 +#define SSC_IER_CP1_OFFSET 9 +#define SSC_IER_ENDRX_SIZE 1 +#define SSC_IER_ENDRX_OFFSET 6 +#define SSC_IER_ENDTX_SIZE 1 +#define SSC_IER_ENDTX_OFFSET 2 +#define SSC_IER_OVRUN_SIZE 1 +#define SSC_IER_OVRUN_OFFSET 5 +#define SSC_IER_RXBUFF_SIZE 1 +#define SSC_IER_RXBUFF_OFFSET 7 +#define SSC_IER_RXRDY_SIZE 1 +#define SSC_IER_RXRDY_OFFSET 4 +#define SSC_IER_RXSYN_SIZE 1 +#define SSC_IER_RXSYN_OFFSET 11 +#define SSC_IER_TXBUFE_SIZE 1 +#define SSC_IER_TXBUFE_OFFSET 3 +#define SSC_IER_TXEMPTY_SIZE 1 +#define SSC_IER_TXEMPTY_OFFSET 1 +#define SSC_IER_TXRDY_SIZE 1 +#define SSC_IER_TXRDY_OFFSET 0 +#define SSC_IER_TXSYN_SIZE 1 +#define SSC_IER_TXSYN_OFFSET 10 + +/* SSC Interrupt Disable Register */ +#define SSC_IDR 0x00000048 +#define SSC_IDR_CP0_SIZE 1 +#define SSC_IDR_CP0_OFFSET 8 +#define SSC_IDR_CP1_SIZE 1 +#define SSC_IDR_CP1_OFFSET 9 +#define SSC_IDR_ENDRX_SIZE 1 +#define SSC_IDR_ENDRX_OFFSET 6 +#define SSC_IDR_ENDTX_SIZE 1 +#define SSC_IDR_ENDTX_OFFSET 2 +#define SSC_IDR_OVRUN_SIZE 1 +#define SSC_IDR_OVRUN_OFFSET 5 +#define SSC_IDR_RXBUFF_SIZE 1 +#define SSC_IDR_RXBUFF_OFFSET 7 +#define SSC_IDR_RXRDY_SIZE 1 +#define SSC_IDR_RXRDY_OFFSET 4 +#define SSC_IDR_RXSYN_SIZE 1 +#define SSC_IDR_RXSYN_OFFSET 11 +#define SSC_IDR_TXBUFE_SIZE 1 +#define SSC_IDR_TXBUFE_OFFSET 3 +#define SSC_IDR_TXEMPTY_SIZE 1 +#define SSC_IDR_TXEMPTY_OFFSET 1 +#define SSC_IDR_TXRDY_SIZE 1 +#define SSC_IDR_TXRDY_OFFSET 0 +#define SSC_IDR_TXSYN_SIZE 1 +#define SSC_IDR_TXSYN_OFFSET 10 + +/* SSC Interrupt Mask Register */ +#define SSC_IMR 0x0000004c +#define SSC_IMR_CP0_SIZE 1 +#define SSC_IMR_CP0_OFFSET 8 +#define SSC_IMR_CP1_SIZE 1 +#define SSC_IMR_CP1_OFFSET 9 +#define SSC_IMR_ENDRX_SIZE 1 +#define SSC_IMR_ENDRX_OFFSET 6 +#define SSC_IMR_ENDTX_SIZE 1 +#define SSC_IMR_ENDTX_OFFSET 2 +#define SSC_IMR_OVRUN_SIZE 1 +#define SSC_IMR_OVRUN_OFFSET 5 +#define SSC_IMR_RXBUFF_SIZE 1 +#define SSC_IMR_RXBUFF_OFFSET 7 +#define SSC_IMR_RXRDY_SIZE 1 +#define SSC_IMR_RXRDY_OFFSET 4 +#define SSC_IMR_RXSYN_SIZE 1 +#define SSC_IMR_RXSYN_OFFSET 11 +#define SSC_IMR_TXBUFE_SIZE 1 +#define SSC_IMR_TXBUFE_OFFSET 3 +#define SSC_IMR_TXEMPTY_SIZE 1 +#define SSC_IMR_TXEMPTY_OFFSET 1 +#define SSC_IMR_TXRDY_SIZE 1 +#define SSC_IMR_TXRDY_OFFSET 0 +#define SSC_IMR_TXSYN_SIZE 1 +#define SSC_IMR_TXSYN_OFFSET 10 + +/* SSC PDC Receive Pointer Register */ +#define SSC_PDC_RPR 0x00000100 + +/* SSC PDC Receive Counter Register */ +#define SSC_PDC_RCR 0x00000104 + +/* SSC PDC Transmit Pointer Register */ +#define SSC_PDC_TPR 0x00000108 + +/* SSC PDC Receive Next Pointer Register */ +#define SSC_PDC_RNPR 0x00000110 + +/* SSC PDC Receive Next Counter Register */ +#define SSC_PDC_RNCR 0x00000114 + +/* SSC PDC Transmit Counter Register */ +#define SSC_PDC_TCR 0x0000010c + +/* SSC PDC Transmit Next Pointer Register */ +#define SSC_PDC_TNPR 0x00000118 + +/* SSC PDC Transmit Next Counter Register */ +#define SSC_PDC_TNCR 0x0000011c + +/* SSC PDC Transfer Control Register */ +#define SSC_PDC_PTCR 0x00000120 +#define SSC_PDC_PTCR_RXTDIS_SIZE 1 +#define SSC_PDC_PTCR_RXTDIS_OFFSET 1 +#define SSC_PDC_PTCR_RXTEN_SIZE 1 +#define SSC_PDC_PTCR_RXTEN_OFFSET 0 +#define SSC_PDC_PTCR_TXTDIS_SIZE 1 +#define SSC_PDC_PTCR_TXTDIS_OFFSET 9 +#define SSC_PDC_PTCR_TXTEN_SIZE 1 +#define SSC_PDC_PTCR_TXTEN_OFFSET 8 + +/* SSC PDC Transfer Status Register */ +#define SSC_PDC_PTSR 0x00000124 +#define SSC_PDC_PTSR_RXTEN_SIZE 1 +#define SSC_PDC_PTSR_RXTEN_OFFSET 0 +#define SSC_PDC_PTSR_TXTEN_SIZE 1 +#define SSC_PDC_PTSR_TXTEN_OFFSET 8 + +/* Bit manipulation macros */ +#define SSC_BIT(name) \ + (1 << SSC_##name##_OFFSET) +#define SSC_BF(name, value) \ + (((value) & ((1 << SSC_##name##_SIZE) - 1)) \ + << SSC_##name##_OFFSET) +#define SSC_BFEXT(name, value) \ + (((value) >> SSC_##name##_OFFSET) \ + & ((1 << SSC_##name##_SIZE) - 1)) +#define SSC_BFINS(name, value, old) \ + (((old) & ~(((1 << SSC_##name##_SIZE) - 1) \ + << SSC_##name##_OFFSET)) | SSC_BF(name, value)) + +/* Register access macros */ +#define ssc_readl(base, reg) __raw_readl(base + SSC_##reg) +#define ssc_writel(base, reg, value) __raw_writel((value), base + SSC_##reg) + +#endif /* __INCLUDE_ATMEL_SSC_H */ diff --git a/include/linux/audit.h b/include/linux/audit.h index 9ae7409..c687816 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -63,6 +63,8 @@ #define AUDIT_ADD_RULE 1011 /* Add syscall filtering rule */ #define AUDIT_DEL_RULE 1012 /* Delete syscall filtering rule */ #define AUDIT_LIST_RULES 1013 /* List syscall filtering rules */ +#define AUDIT_TRIM 1014 /* Trim junk from watched tree */ +#define AUDIT_MAKE_EQUIV 1015 /* Append to watched tree */ #define AUDIT_TTY_GET 1016 /* Get TTY auditing status */ #define AUDIT_TTY_SET 1017 /* Set TTY auditing status */ @@ -203,6 +205,7 @@ #define AUDIT_SUCCESS 104 /* exit >= 0; value ignored */ #define AUDIT_WATCH 105 #define AUDIT_PERM 106 +#define AUDIT_DIR 107 #define AUDIT_ARG0 200 #define AUDIT_ARG1 (AUDIT_ARG0+1) @@ -366,8 +369,8 @@ extern void audit_syscall_entry(int arch, extern void audit_syscall_exit(int failed, long return_code); extern void __audit_getname(const char *name); extern void audit_putname(const char *name); -extern void __audit_inode(const char *name, const struct inode *inode); -extern void __audit_inode_child(const char *dname, const struct inode *inode, +extern void __audit_inode(const char *name, const struct dentry *dentry); +extern void __audit_inode_child(const char *dname, const struct dentry *dentry, const struct inode *parent); extern void __audit_ptrace(struct task_struct *t); @@ -381,15 +384,15 @@ static inline void audit_getname(const char *name) if (unlikely(!audit_dummy_context())) __audit_getname(name); } -static inline void audit_inode(const char *name, const struct inode *inode) { +static inline void audit_inode(const char *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) - __audit_inode(name, inode); + __audit_inode(name, dentry); } static inline void audit_inode_child(const char *dname, - const struct inode *inode, + const struct dentry *dentry, const struct inode *parent) { if (unlikely(!audit_dummy_context())) - __audit_inode_child(dname, inode, parent); + __audit_inode_child(dname, dentry, parent); } void audit_core_dumps(long signr); @@ -477,9 +480,9 @@ extern int audit_signals; #define audit_dummy_context() 1 #define audit_getname(n) do { ; } while (0) #define audit_putname(n) do { ; } while (0) -#define __audit_inode(n,i) do { ; } while (0) +#define __audit_inode(n,d) do { ; } while (0) #define __audit_inode_child(d,i,p) do { ; } while (0) -#define audit_inode(n,i) do { ; } while (0) +#define audit_inode(n,d) do { ; } while (0) #define audit_inode_child(d,i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index d2bc0d6..ad89545 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -26,6 +26,8 @@ #define AT_SECURE 23 /* secure mode boolean */ -#define AT_VECTOR_SIZE 44 /* Size of auxiliary table. */ +#ifdef __KERNEL__ +#define AT_VECTOR_SIZE_BASE (14 + 2) /* NEW_AUX_ENT entries in auxiliary table */ +#endif #endif /* _LINUX_AUXVEC_H */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 7011d625..48a62ba 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -8,6 +8,9 @@ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H +#include <linux/percpu_counter.h> +#include <linux/log2.h> +#include <linux/proportions.h> #include <asm/atomic.h> struct page; @@ -24,6 +27,14 @@ enum bdi_state { typedef int (congested_fn)(void *, int); +enum bdi_stat_item { + BDI_RECLAIMABLE, + BDI_WRITEBACK, + NR_BDI_STAT_ITEMS +}; + +#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) + struct backing_dev_info { unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ unsigned long state; /* Always use atomic bitops on this */ @@ -32,8 +43,90 @@ struct backing_dev_info { void *congested_data; /* Pointer to aux data for congested func */ void (*unplug_io_fn)(struct backing_dev_info *, struct page *); void *unplug_io_data; + + struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; + + struct prop_local_percpu completions; + int dirty_exceeded; }; +int bdi_init(struct backing_dev_info *bdi); +void bdi_destroy(struct backing_dev_info *bdi); + +static inline void __add_bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item, s64 amount) +{ + __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); +} + +static inline void __inc_bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + __add_bdi_stat(bdi, item, 1); +} + +static inline void inc_bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __inc_bdi_stat(bdi, item); + local_irq_restore(flags); +} + +static inline void __dec_bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + __add_bdi_stat(bdi, item, -1); +} + +static inline void dec_bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __dec_bdi_stat(bdi, item); + local_irq_restore(flags); +} + +static inline s64 bdi_stat(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + return percpu_counter_read_positive(&bdi->bdi_stat[item]); +} + +static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + return percpu_counter_sum_positive(&bdi->bdi_stat[item]); +} + +static inline s64 bdi_stat_sum(struct backing_dev_info *bdi, + enum bdi_stat_item item) +{ + s64 sum; + unsigned long flags; + + local_irq_save(flags); + sum = __bdi_stat_sum(bdi, item); + local_irq_restore(flags); + + return sum; +} + +/* + * maximal error of a stat counter. + */ +static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi) +{ +#ifdef CONFIG_SMP + return nr_cpu_ids * BDI_STAT_BATCH; +#else + return 1; +#endif +} /* * Flags in backing_dev_info::capability @@ -93,7 +186,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) void clear_bdi_congested(struct backing_dev_info *bdi, int rw); void set_bdi_congested(struct backing_dev_info *bdi, int rw); long congestion_wait(int rw, long timeout); -void congestion_end(int rw); #define bdi_cap_writeback_dirty(bdi) \ (!((bdi)->capabilities & BDI_CAP_NO_WRITEBACK)) diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 91c8c07..b7fc55e 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -37,7 +37,8 @@ struct linux_binprm{ int sh_bang; struct file * file; int e_uid, e_gid; - kernel_cap_t cap_inheritable, cap_permitted, cap_effective; + kernel_cap_t cap_inheritable, cap_permitted; + bool cap_effective; void *security; int argc, envc; char * filename; /* Name of binary as seen by procps */ @@ -63,17 +64,17 @@ struct linux_binprm{ * linux accepts. */ struct linux_binfmt { - struct linux_binfmt * next; + struct list_head lh; struct module *module; int (*load_binary)(struct linux_binprm *, struct pt_regs * regs); int (*load_shlib)(struct file *); - int (*core_dump)(long signr, struct pt_regs * regs, struct file * file); + int (*core_dump)(long signr, struct pt_regs *regs, struct file *file, unsigned long limit); unsigned long min_coredump; /* minimal dump size */ int hasvdso; }; extern int register_binfmt(struct linux_binfmt *); -extern int unregister_binfmt(struct linux_binfmt *); +extern void unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); diff --git a/include/linux/bio.h b/include/linux/bio.h index 089a8bc..4da4413 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -176,13 +176,28 @@ struct bio { #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_cur_sectors(bio) (bio_iovec(bio)->bv_len >> 9) -#define bio_data(bio) (page_address(bio_page((bio))) + bio_offset((bio))) #define bio_barrier(bio) ((bio)->bi_rw & (1 << BIO_RW_BARRIER)) #define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC)) #define bio_failfast(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST)) #define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD)) #define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META)) +#define bio_empty_barrier(bio) (bio_barrier(bio) && !(bio)->bi_size) + +static inline unsigned int bio_cur_sectors(struct bio *bio) +{ + if (bio->bi_vcnt) + return bio_iovec(bio)->bv_len >> 9; + + return 0; +} + +static inline void *bio_data(struct bio *bio) +{ + if (bio->bi_vcnt) + return page_address(bio_page(bio)) + bio_offset(bio); + + return NULL; +} /* * will die diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h index 6b20af0..7113a32 100644 --- a/include/linux/bit_spinlock.h +++ b/include/linux/bit_spinlock.h @@ -18,7 +18,7 @@ static inline void bit_spin_lock(int bitnum, unsigned long *addr) */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - while (test_and_set_bit(bitnum, addr)) { + while (unlikely(test_and_set_bit_lock(bitnum, addr))) { while (test_bit(bitnum, addr)) { preempt_enable(); cpu_relax(); @@ -36,7 +36,7 @@ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - if (test_and_set_bit(bitnum, addr)) { + if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } @@ -50,10 +50,28 @@ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(!test_bit(bitnum, addr)); +#endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + clear_bit_unlock(bitnum, addr); +#endif + preempt_enable(); + __release(bitlock); +} + +/* + * bit-based spin_unlock() + * non-atomic version, which can be used eg. if the bit lock itself is + * protecting the rest of the flags in the word. + */ +static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) +{ +#ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); - smp_mb__before_clear_bit(); - clear_bit(bitnum, addr); +#endif +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 64b4641..acad110 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/string.h> +#include <linux/kernel.h> /* * bitmaps provide bit arrays that consume one or more unsigned diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 638165f..69c1edb 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -2,12 +2,26 @@ #define _LINUX_BITOPS_H #include <asm/types.h> +#ifdef __KERNEL__ +#define BIT(nr) (1UL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG) +#define BITS_PER_BYTE 8 +#endif + /* * Include this here because some architectures need generic_ffs/fls in * scope */ #include <asm/bitops.h> +#define for_each_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + + static __inline__ int get_bitmask_order(unsigned int count) { int order; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5ed888b..bbf906a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -330,7 +330,6 @@ typedef void (unplug_fn) (struct request_queue *); struct bio_vec; typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *); -typedef int (issue_flush_fn) (struct request_queue *, struct gendisk *, sector_t *); typedef void (prepare_flush_fn) (struct request_queue *, struct request *); typedef void (softirq_done_fn)(struct request *); @@ -368,7 +367,6 @@ struct request_queue prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; - issue_flush_fn *issue_flush_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -540,6 +538,7 @@ enum { #define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) #define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) +#define blk_empty_barrier(rq) (blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) @@ -729,7 +728,9 @@ static inline void blk_run_address_space(struct address_space *mapping) extern int end_that_request_first(struct request *, int, int); extern int end_that_request_chunk(struct request *, int, int); extern void end_that_request_last(struct request *, int); -extern void end_request(struct request *req, int uptodate); +extern void end_request(struct request *, int); +extern void end_queued_request(struct request *, int); +extern void end_dequeued_request(struct request *, int); extern void blk_complete_request(struct request *); /* @@ -767,7 +768,6 @@ extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *); -extern void blk_queue_issue_flush_fn(struct request_queue *, issue_flush_fn *); extern int blk_do_ordered(struct request_queue *, struct request **); extern unsigned blk_ordered_cur_seq(struct request_queue *); extern unsigned blk_ordered_req_seq(struct request *); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 35cadad..da0d83f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -203,10 +203,20 @@ void block_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); +int block_write_begin(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); +int block_write_end(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page *, void *); +int generic_write_end(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page *, void *); +void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*); -int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*, - loff_t *); -int generic_cont_expand(struct inode *inode, loff_t size); +int cont_write_begin(struct file *, struct address_space *, loff_t, + unsigned, unsigned, struct page **, void **, + get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct page *page, @@ -216,9 +226,13 @@ sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int generic_commit_write(struct file *, struct page *, unsigned, unsigned); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int file_fsync(struct file *, struct dentry *, int); -int nobh_prepare_write(struct page*, unsigned, unsigned, get_block_t*); -int nobh_commit_write(struct file *, struct page *, unsigned, unsigned); -int nobh_truncate_page(struct address_space *, loff_t); +int nobh_write_begin(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); +int nobh_write_end(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page *, void *); +int nobh_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); diff --git a/include/linux/capability.h b/include/linux/capability.h index 2dfa585..bb017ed 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -1,14 +1,14 @@ /* * This is <linux/capability.h> * - * Andrew G. Morgan <morgan@transmeta.com> + * Andrew G. Morgan <morgan@kernel.org> * Alexander Kjeldaas <astor@guardian.no> * with help from Aleph1, Roland Buresund and Andrew Main. * * See here for the libcap library ("POSIX draft" compliance): * - * ftp://linux.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.2/ - */ + * ftp://linux.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/ + */ #ifndef _LINUX_CAPABILITY_H #define _LINUX_CAPABILITY_H @@ -28,23 +28,39 @@ struct task_struct; following structure to such a composite is better handled in a user library since the draft standard requires the use of malloc/free etc.. */ - + #define _LINUX_CAPABILITY_VERSION 0x19980330 typedef struct __user_cap_header_struct { __u32 version; int pid; } __user *cap_user_header_t; - + typedef struct __user_cap_data_struct { __u32 effective; __u32 permitted; __u32 inheritable; } __user *cap_user_data_t; - -#ifdef __KERNEL__ -#include <asm/current.h> +#define XATTR_CAPS_SUFFIX "capability" +#define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX + +#define XATTR_CAPS_SZ (3*sizeof(__le32)) +#define VFS_CAP_REVISION_MASK 0xFF000000 +#define VFS_CAP_REVISION_1 0x01000000 + +#define VFS_CAP_REVISION VFS_CAP_REVISION_1 + +#define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK +#define VFS_CAP_FLAGS_EFFECTIVE 0x000001 + +struct vfs_cap_data { + __u32 magic_etc; /* Little endian */ + __u32 permitted; /* Little endian */ + __u32 inheritable; /* Little endian */ +}; + +#ifdef __KERNEL__ /* #define STRICT_CAP_T_TYPECHECKS */ @@ -59,7 +75,7 @@ typedef struct kernel_cap_struct { typedef __u32 kernel_cap_t; #endif - + #define _USER_CAP_HEADER_SIZE (2*sizeof(__u32)) #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) @@ -67,7 +83,7 @@ typedef __u32 kernel_cap_t; /** - ** POSIX-draft defined capabilities. + ** POSIX-draft defined capabilities. **/ /* In a system with the [_POSIX_CHOWN_RESTRICTED] option defined, this @@ -87,7 +103,7 @@ typedef __u32 kernel_cap_t; defined. Excluding DAC access covered by CAP_LINUX_IMMUTABLE. */ #define CAP_DAC_READ_SEARCH 2 - + /* Overrides all restrictions about allowed operations on files, where file owner ID must be equal to the user ID, except where CAP_FSETID is applicable. It doesn't override MAC and DAC restrictions. */ @@ -257,7 +273,7 @@ typedef __u32 kernel_cap_t; /* Override reserved space on ext2 filesystem */ /* Modify data journaling mode on ext3 filesystem (uses journaling resources) */ -/* NOTE: ext2 honors fsuid when checking for resource overrides, so +/* NOTE: ext2 honors fsuid when checking for resource overrides, so you can override using fsuid too */ /* Override size restrictions on IPC message queues */ /* Allow more than 64hz interrupts from the real-time clock */ @@ -289,16 +305,14 @@ typedef __u32 kernel_cap_t; #define CAP_AUDIT_CONTROL 30 +#define CAP_SETFCAP 31 + #ifdef __KERNEL__ -/* - * Bounding set - */ -extern kernel_cap_t cap_bset; /* * Internal kernel functions only */ - + #ifdef STRICT_CAP_T_TYPECHECKS #define to_cap_t(x) { x } diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 2b641b1..c6d3e22 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -2,7 +2,7 @@ * -- <linux/cdrom.h> * General header file for linux CD-ROM drivers * Copyright (C) 1992 David Giller, rafetmad@oxy.edu - * 1994, 1995 Eberhard Moenkeberg, emoenke@gwdg.de + * 1994, 1995 Eberhard Mönkeberg, emoenke@gwdg.de * 1996 David van Leeuwen, david@tm.tno.nl * 1997, 1998 Erik Andersen, andersee@debian.org * 1998-2002 Jens Axboe, axboe@suse.de @@ -76,7 +76,7 @@ (struct cdrom_multisession) */ #define CDROM_GET_MCN 0x5311 /* Obtain the "Universal Product Code" if available (struct cdrom_mcn) */ -#define CDROM_GET_UPC CDROM_GET_MCN /* This one is depricated, +#define CDROM_GET_UPC CDROM_GET_MCN /* This one is deprecated, but here anyway for compatibility */ #define CDROMRESET 0x5312 /* hard-reset the drive */ #define CDROMVOLREAD 0x5313 /* Get the drive's volume setting @@ -506,7 +506,7 @@ struct cdrom_generic_command #define GPMODE_TO_PROTECT_PAGE 0x1d #define GPMODE_CAPABILITIES_PAGE 0x2a #define GPMODE_ALL_PAGES 0x3f -/* Not in Mt. Fuji, but in ATAPI 2.6 -- depricated now in favor +/* Not in Mt. Fuji, but in ATAPI 2.6 -- deprecated now in favor * of MODE_SENSE_POWER_PAGE */ #define GPMODE_CDROM_PAGE 0x0d diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h new file mode 100644 index 0000000..8747932 --- /dev/null +++ b/include/linux/cgroup.h @@ -0,0 +1,327 @@ +#ifndef _LINUX_CGROUP_H +#define _LINUX_CGROUP_H +/* + * cgroup interface + * + * Copyright (C) 2003 BULL SA + * Copyright (C) 2004-2006 Silicon Graphics, Inc. + * + */ + +#include <linux/sched.h> +#include <linux/kref.h> +#include <linux/cpumask.h> +#include <linux/nodemask.h> +#include <linux/rcupdate.h> +#include <linux/cgroupstats.h> + +#ifdef CONFIG_CGROUPS + +struct cgroupfs_root; +struct cgroup_subsys; +struct inode; + +extern int cgroup_init_early(void); +extern int cgroup_init(void); +extern void cgroup_init_smp(void); +extern void cgroup_lock(void); +extern void cgroup_unlock(void); +extern void cgroup_fork(struct task_struct *p); +extern void cgroup_fork_callbacks(struct task_struct *p); +extern void cgroup_post_fork(struct task_struct *p); +extern void cgroup_exit(struct task_struct *p, int run_callbacks); +extern int cgroupstats_build(struct cgroupstats *stats, + struct dentry *dentry); + +extern struct file_operations proc_cgroup_operations; + +/* Define the enumeration of all cgroup subsystems */ +#define SUBSYS(_x) _x ## _subsys_id, +enum cgroup_subsys_id { +#include <linux/cgroup_subsys.h> + CGROUP_SUBSYS_COUNT +}; +#undef SUBSYS + +/* Per-subsystem/per-cgroup state maintained by the system. */ +struct cgroup_subsys_state { + /* The cgroup that this subsystem is attached to. Useful + * for subsystems that want to know about the cgroup + * hierarchy structure */ + struct cgroup *cgroup; + + /* State maintained by the cgroup system to allow + * subsystems to be "busy". Should be accessed via css_get() + * and css_put() */ + + atomic_t refcnt; + + unsigned long flags; +}; + +/* bits in struct cgroup_subsys_state flags field */ +enum { + CSS_ROOT, /* This CSS is the root of the subsystem */ +}; + +/* + * Call css_get() to hold a reference on the cgroup; + * + */ + +static inline void css_get(struct cgroup_subsys_state *css) +{ + /* We don't need to reference count the root state */ + if (!test_bit(CSS_ROOT, &css->flags)) + atomic_inc(&css->refcnt); +} +/* + * css_put() should be called to release a reference taken by + * css_get() + */ + +extern void __css_put(struct cgroup_subsys_state *css); +static inline void css_put(struct cgroup_subsys_state *css) +{ + if (!test_bit(CSS_ROOT, &css->flags)) + __css_put(css); +} + +struct cgroup { + unsigned long flags; /* "unsigned long" so bitops work */ + + /* count users of this cgroup. >0 means busy, but doesn't + * necessarily indicate the number of tasks in the + * cgroup */ + atomic_t count; + + /* + * We link our 'sibling' struct into our parent's 'children'. + * Our children link their 'sibling' into our 'children'. + */ + struct list_head sibling; /* my parent's children */ + struct list_head children; /* my children */ + + struct cgroup *parent; /* my parent */ + struct dentry *dentry; /* cgroup fs entry */ + + /* Private pointers for each registered subsystem */ + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + struct cgroupfs_root *root; + struct cgroup *top_cgroup; + + /* + * List of cg_cgroup_links pointing at css_sets with + * tasks in this cgroup. Protected by css_set_lock + */ + struct list_head css_sets; + + /* + * Linked list running through all cgroups that can + * potentially be reaped by the release agent. Protected by + * release_list_lock + */ + struct list_head release_list; +}; + +/* A css_set is a structure holding pointers to a set of + * cgroup_subsys_state objects. This saves space in the task struct + * object and speeds up fork()/exit(), since a single inc/dec and a + * list_add()/del() can bump the reference count on the entire + * cgroup set for a task. + */ + +struct css_set { + + /* Reference count */ + struct kref ref; + + /* + * List running through all cgroup groups. Protected by + * css_set_lock + */ + struct list_head list; + + /* + * List running through all tasks using this cgroup + * group. Protected by css_set_lock + */ + struct list_head tasks; + + /* + * List of cg_cgroup_link objects on link chains from + * cgroups referenced from this css_set. Protected by + * css_set_lock + */ + struct list_head cg_links; + + /* + * Set of subsystem states, one for each subsystem. This array + * is immutable after creation apart from the init_css_set + * during subsystem registration (at boot time). + */ + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + +}; + +/* struct cftype: + * + * The files in the cgroup filesystem mostly have a very simple read/write + * handling, some common function will take care of it. Nevertheless some cases + * (read tasks) are special and therefore I define this structure for every + * kind of file. + * + * + * When reading/writing to a file: + * - the cgroup to use in file->f_dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_dentry->d_fsdata + */ + +#define MAX_CFTYPE_NAME 64 +struct cftype { + /* By convention, the name should begin with the name of the + * subsystem, followed by a period */ + char name[MAX_CFTYPE_NAME]; + int private; + int (*open) (struct inode *inode, struct file *file); + ssize_t (*read) (struct cgroup *cont, struct cftype *cft, + struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos); + /* + * read_uint() is a shortcut for the common case of returning a + * single integer. Use it in place of read() + */ + u64 (*read_uint) (struct cgroup *cont, struct cftype *cft); + ssize_t (*write) (struct cgroup *cont, struct cftype *cft, + struct file *file, + const char __user *buf, size_t nbytes, loff_t *ppos); + + /* + * write_uint() is a shortcut for the common case of accepting + * a single integer (as parsed by simple_strtoull) from + * userspace. Use in place of write(); return 0 or error. + */ + int (*write_uint) (struct cgroup *cont, struct cftype *cft, u64 val); + + int (*release) (struct inode *inode, struct file *file); +}; + +/* Add a new file to the given cgroup directory. Should only be + * called by subsystems from within a populate() method */ +int cgroup_add_file(struct cgroup *cont, struct cgroup_subsys *subsys, + const struct cftype *cft); + +/* Add a set of new files to the given cgroup directory. Should + * only be called by subsystems from within a populate() method */ +int cgroup_add_files(struct cgroup *cont, + struct cgroup_subsys *subsys, + const struct cftype cft[], + int count); + +int cgroup_is_removed(const struct cgroup *cont); + +int cgroup_path(const struct cgroup *cont, char *buf, int buflen); + +int cgroup_task_count(const struct cgroup *cont); + +/* Return true if the cgroup is a descendant of the current cgroup */ +int cgroup_is_descendant(const struct cgroup *cont); + +/* Control Group subsystem type. See Documentation/cgroups.txt for details */ + +struct cgroup_subsys { + struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, + struct cgroup *cont); + void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cont); + int (*can_attach)(struct cgroup_subsys *ss, + struct cgroup *cont, struct task_struct *tsk); + void (*attach)(struct cgroup_subsys *ss, struct cgroup *cont, + struct cgroup *old_cont, struct task_struct *tsk); + void (*fork)(struct cgroup_subsys *ss, struct task_struct *task); + void (*exit)(struct cgroup_subsys *ss, struct task_struct *task); + int (*populate)(struct cgroup_subsys *ss, + struct cgroup *cont); + void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cont); + void (*bind)(struct cgroup_subsys *ss, struct cgroup *root); + int subsys_id; + int active; + int early_init; +#define MAX_CGROUP_TYPE_NAMELEN 32 + const char *name; + + /* Protected by RCU */ + struct cgroupfs_root *root; + + struct list_head sibling; + + void *private; +}; + +#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; +#include <linux/cgroup_subsys.h> +#undef SUBSYS + +static inline struct cgroup_subsys_state *cgroup_subsys_state( + struct cgroup *cont, int subsys_id) +{ + return cont->subsys[subsys_id]; +} + +static inline struct cgroup_subsys_state *task_subsys_state( + struct task_struct *task, int subsys_id) +{ + return rcu_dereference(task->cgroups->subsys[subsys_id]); +} + +static inline struct cgroup* task_cgroup(struct task_struct *task, + int subsys_id) +{ + return task_subsys_state(task, subsys_id)->cgroup; +} + +int cgroup_path(const struct cgroup *cont, char *buf, int buflen); + +int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss); + +/* A cgroup_iter should be treated as an opaque object */ +struct cgroup_iter { + struct list_head *cg_link; + struct list_head *task; +}; + +/* To iterate across the tasks in a cgroup: + * + * 1) call cgroup_iter_start to intialize an iterator + * + * 2) call cgroup_iter_next() to retrieve member tasks until it + * returns NULL or until you want to end the iteration + * + * 3) call cgroup_iter_end() to destroy the iterator. + */ +void cgroup_iter_start(struct cgroup *cont, struct cgroup_iter *it); +struct task_struct *cgroup_iter_next(struct cgroup *cont, + struct cgroup_iter *it); +void cgroup_iter_end(struct cgroup *cont, struct cgroup_iter *it); + +#else /* !CONFIG_CGROUPS */ + +static inline int cgroup_init_early(void) { return 0; } +static inline int cgroup_init(void) { return 0; } +static inline void cgroup_init_smp(void) {} +static inline void cgroup_fork(struct task_struct *p) {} +static inline void cgroup_fork_callbacks(struct task_struct *p) {} +static inline void cgroup_post_fork(struct task_struct *p) {} +static inline void cgroup_exit(struct task_struct *p, int callbacks) {} + +static inline void cgroup_lock(void) {} +static inline void cgroup_unlock(void) {} +static inline int cgroupstats_build(struct cgroupstats *stats, + struct dentry *dentry) +{ + return -EINVAL; +} + +#endif /* !CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h new file mode 100644 index 0000000..0b9bfbd --- /dev/null +++ b/include/linux/cgroup_subsys.h @@ -0,0 +1,38 @@ +/* Add subsystem definitions of the form SUBSYS(<name>) in this + * file. Surround each one by a line of comment markers so that + * patches don't collide + */ + +/* */ + +/* */ + +#ifdef CONFIG_CPUSETS +SUBSYS(cpuset) +#endif + +/* */ + +#ifdef CONFIG_CGROUP_CPUACCT +SUBSYS(cpuacct) +#endif + +/* */ + +#ifdef CONFIG_CGROUP_DEBUG +SUBSYS(debug) +#endif + +/* */ + +#ifdef CONFIG_CGROUP_NS +SUBSYS(ns) +#endif + +/* */ + +#ifdef CONFIG_FAIR_CGROUP_SCHED +SUBSYS(cpu_cgroup) +#endif + +/* */ diff --git a/include/linux/cgroupstats.h b/include/linux/cgroupstats.h new file mode 100644 index 0000000..4f53abf --- /dev/null +++ b/include/linux/cgroupstats.h @@ -0,0 +1,70 @@ +/* cgroupstats.h - exporting per-cgroup statistics + * + * Copyright IBM Corporation, 2007 + * Author Balbir Singh <balbir@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + */ + +#ifndef _LINUX_CGROUPSTATS_H +#define _LINUX_CGROUPSTATS_H + +#include <linux/taskstats.h> + +/* + * Data shared between user space and kernel space on a per cgroup + * basis. This data is shared using taskstats. + * + * Most of these states are derived by looking at the task->state value + * For the nr_io_wait state, a flag in the delay accounting structure + * indicates that the task is waiting on IO + * + * Each member is aligned to a 8 byte boundary. + */ +struct cgroupstats { + __u64 nr_sleeping; /* Number of tasks sleeping */ + __u64 nr_running; /* Number of tasks running */ + __u64 nr_stopped; /* Number of tasks in stopped state */ + __u64 nr_uninterruptible; /* Number of tasks in uninterruptible */ + /* state */ + __u64 nr_io_wait; /* Number of tasks waiting on IO */ +}; + +/* + * Commands sent from userspace + * Not versioned. New commands should only be inserted at the enum's end + * prior to __CGROUPSTATS_CMD_MAX + */ + +enum { + CGROUPSTATS_CMD_UNSPEC = __TASKSTATS_CMD_MAX, /* Reserved */ + CGROUPSTATS_CMD_GET, /* user->kernel request/get-response */ + CGROUPSTATS_CMD_NEW, /* kernel->user event */ + __CGROUPSTATS_CMD_MAX, +}; + +#define CGROUPSTATS_CMD_MAX (__CGROUPSTATS_CMD_MAX - 1) + +enum { + CGROUPSTATS_TYPE_UNSPEC = 0, /* Reserved */ + CGROUPSTATS_TYPE_CGROUP_STATS, /* contains name + stats */ + __CGROUPSTATS_TYPE_MAX, +}; + +#define CGROUPSTATS_TYPE_MAX (__CGROUPSTATS_TYPE_MAX - 1) + +enum { + CGROUPSTATS_CMD_ATTR_UNSPEC = 0, + CGROUPSTATS_CMD_ATTR_FD, + __CGROUPSTATS_CMD_ATTR_MAX, +}; + +#define CGROUPSTATS_CMD_ATTR_MAX (__CGROUPSTATS_CMD_ATTR_MAX - 1) + +#endif /* _LINUX_CGROUPSTATS_H */ diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index d2ddea9..c33b0dc 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -31,6 +31,7 @@ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_ADD, CLOCK_EVT_NOTIFY_BROADCAST_ON, CLOCK_EVT_NOTIFY_BROADCAST_OFF, + CLOCK_EVT_NOTIFY_BROADCAST_FORCE, CLOCK_EVT_NOTIFY_BROADCAST_ENTER, CLOCK_EVT_NOTIFY_BROADCAST_EXIT, CLOCK_EVT_NOTIFY_SUSPEND, diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 16ea337..107787a 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -221,10 +221,15 @@ extern void clocksource_resume(void); #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct clocksource *c); +extern void update_vsyscall_tz(void); #else static inline void update_vsyscall(struct timespec *ts, struct clocksource *c) { } + +static inline void update_vsyscall_tz(void) +{ +} #endif #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 03ec231..fe23792 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -1,4 +1,6 @@ -/* Never include this file directly. Include <linux/compiler.h> instead. */ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead." +#endif /* * Common definitions for all gcc versions go here. @@ -34,10 +36,20 @@ #define __weak __attribute__((weak)) #define __naked __attribute__((naked)) #define __noreturn __attribute__((noreturn)) + +/* + * From the GCC manual: + * + * Many functions have no effects except the return value and their + * return value depends only on the parameters and/or global + * variables. Such a function can be subject to common subexpression + * elimination and loop optimization just as an arithmetic operator + * would be. + * [...] + */ #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) #define __printf(a,b) __attribute__((format(printf,a,b))) #define noinline __attribute__((noinline)) -#define __attribute_pure__ __attribute__((pure)) #define __attribute_const__ __attribute__((__const__)) #define __maybe_unused __attribute__((unused)) diff --git a/include/linux/compiler-gcc3.h b/include/linux/compiler-gcc3.h index a9e2863..2d8c0f4 100644 --- a/include/linux/compiler-gcc3.h +++ b/include/linux/compiler-gcc3.h @@ -1,4 +1,6 @@ -/* Never include this file directly. Include <linux/compiler.h> instead. */ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead." +#endif /* These definitions are for GCC v3.x. */ #include <linux/compiler-gcc.h> diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 14f7494..ee7ca5d 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -1,4 +1,6 @@ -/* Never include this file directly. Include <linux/compiler.h> instead. */ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc4.h> directly, include <linux/compiler.h> instead." +#endif /* These definitions are for GCC v4.x. */ #include <linux/compiler-gcc.h> diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index b769961..d8e636e 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -1,4 +1,6 @@ -/* Never include this file directly. Include <linux/compiler.h> instead. */ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-intel.h> directly, include <linux/compiler.h> instead." +#endif #ifdef __ECC diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 86f9a3a..c811c8b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -132,20 +132,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __maybe_unused /* unimplemented */ #endif -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#ifndef __attribute_pure__ -# define __attribute_pure__ /* unimplemented */ -#endif - #ifndef noinline #define noinline #endif diff --git a/include/linux/connector.h b/include/linux/connector.h index b62f823..13fc454 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -36,14 +36,15 @@ #define CN_VAL_CIFS 0x1 #define CN_W1_IDX 0x3 /* w1 communication */ #define CN_W1_VAL 0x1 +#define CN_IDX_V86D 0x4 +#define CN_VAL_V86D_UVESAFB 0x1 - -#define CN_NETLINK_USERS 4 +#define CN_NETLINK_USERS 5 /* * Maximum connector's message size. */ -#define CONNECTOR_MAX_MSG_SIZE 1024 +#define CONNECTOR_MAX_MSG_SIZE 16384 /* * idx and val are unique identifiers which diff --git a/include/linux/console.h b/include/linux/console.h index 56a7bcd..a5f88a6 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -45,7 +45,8 @@ struct consw { int (*con_font_get)(struct vc_data *, struct console_font *); int (*con_font_default)(struct vc_data *, struct console_font *, char *); int (*con_font_copy)(struct vc_data *, int); - int (*con_resize)(struct vc_data *, unsigned int, unsigned int); + int (*con_resize)(struct vc_data *, unsigned int, unsigned int, + unsigned int); int (*con_set_palette)(struct vc_data *, unsigned char *); int (*con_scrolldelta)(struct vc_data *, int); int (*con_set_origin)(struct vc_data *); @@ -121,14 +122,11 @@ extern void console_stop(struct console *); extern void console_start(struct console *); extern int is_console_locked(void); -#ifndef CONFIG_DISABLE_CONSOLE_SUSPEND +extern int console_suspend_enabled; + /* Suspend and resume console messages over PM events */ extern void suspend_console(void); extern void resume_console(void); -#else -static inline void suspend_console(void) {} -static inline void resume_console(void) {} -#endif /* CONFIG_DISABLE_CONSOLE_SUSPEND */ int mda_console_init(void); void prom_con_init(void); diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index dc77fed..d71f7c0 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -100,6 +100,7 @@ struct vc_data { unsigned char vc_G1_charset; unsigned char vc_saved_G0; unsigned char vc_saved_G1; + unsigned int vc_resize_user; /* resize request from user */ unsigned int vc_bell_pitch; /* Console bell pitch */ unsigned int vc_bell_duration; /* Console bell duration */ struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index 06b2768..e2bf7e5 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -16,4 +16,5 @@ extern u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode); extern unsigned short *set_translate(int m, struct vc_data *vc); extern int conv_uni_to_pc(struct vc_data *conp, long ucs); extern u32 conv_8bit_to_uni(unsigned char c); +extern int conv_uni_to_8bit(u32 uni); void console_map_init(void); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 0ad72c4..b79c575 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -119,8 +119,9 @@ static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) #define lock_cpu_hotplug() do { } while (0) #define unlock_cpu_hotplug() do { } while (0) #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) -#define register_hotcpu_notifier(nb) do { (void)(nb); } while (0) -#define unregister_hotcpu_notifier(nb) do { (void)(nb); } while (0) +/* These aren't inline functions due to a GCC bug. */ +#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotcpu_notifier(nb) ({ (void)(nb); }) /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */ static inline int cpu_is_offline(int cpu) { return 0; } diff --git a/include/linux/cpu_acct.h b/include/linux/cpu_acct.h new file mode 100644 index 0000000..6b5fd8a --- /dev/null +++ b/include/linux/cpu_acct.h @@ -0,0 +1,14 @@ + +#ifndef _LINUX_CPU_ACCT_H +#define _LINUX_CPU_ACCT_H + +#include <linux/cgroup.h> +#include <asm/cputime.h> + +#ifdef CONFIG_CGROUP_CPUACCT +extern void cpuacct_charge(struct task_struct *, cputime_t cputime); +#else +static void inline cpuacct_charge(struct task_struct *p, cputime_t cputime) {} +#endif + +#endif diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h new file mode 100644 index 0000000..16a5154 --- /dev/null +++ b/include/linux/cpuidle.h @@ -0,0 +1,180 @@ +/* + * cpuidle.h - a generic framework for CPU idle power management + * + * (C) 2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#ifndef _LINUX_CPUIDLE_H +#define _LINUX_CPUIDLE_H + +#include <linux/percpu.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/kobject.h> +#include <linux/completion.h> + +#define CPUIDLE_STATE_MAX 8 +#define CPUIDLE_NAME_LEN 16 + +struct cpuidle_device; + + +/**************************** + * CPUIDLE DEVICE INTERFACE * + ****************************/ + +struct cpuidle_state { + char name[CPUIDLE_NAME_LEN]; + void *driver_data; + + unsigned int flags; + unsigned int exit_latency; /* in US */ + unsigned int power_usage; /* in mW */ + unsigned int target_residency; /* in US */ + + unsigned int usage; + unsigned int time; /* in US */ + + int (*enter) (struct cpuidle_device *dev, + struct cpuidle_state *state); +}; + +/* Idle State Flags */ +#define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ +#define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ +#define CPUIDLE_FLAG_SHALLOW (0x10) /* low latency, minimal savings */ +#define CPUIDLE_FLAG_BALANCED (0x20) /* medium latency, moderate savings */ +#define CPUIDLE_FLAG_DEEP (0x40) /* high latency, large savings */ + +#define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) + +/** + * cpuidle_get_statedata - retrieves private driver state data + * @state: the state + */ +static inline void * cpuidle_get_statedata(struct cpuidle_state *state) +{ + return state->driver_data; +} + +/** + * cpuidle_set_statedata - stores private driver state data + * @state: the state + * @data: the private data + */ +static inline void +cpuidle_set_statedata(struct cpuidle_state *state, void *data) +{ + state->driver_data = data; +} + +struct cpuidle_state_kobj { + struct cpuidle_state *state; + struct completion kobj_unregister; + struct kobject kobj; +}; + +struct cpuidle_device { + int enabled:1; + unsigned int cpu; + + int last_residency; + int state_count; + struct cpuidle_state states[CPUIDLE_STATE_MAX]; + struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; + struct cpuidle_state *last_state; + + struct list_head device_list; + struct kobject kobj; + struct completion kobj_unregister; + void *governor_data; +}; + +DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); + +/** + * cpuidle_get_last_residency - retrieves the last state's residency time + * @dev: the target CPU + * + * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_VALID isn't set + */ +static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) +{ + return dev->last_residency; +} + + +/**************************** + * CPUIDLE DRIVER INTERFACE * + ****************************/ + +struct cpuidle_driver { + char name[CPUIDLE_NAME_LEN]; + struct module *owner; +}; + +#ifdef CONFIG_CPU_IDLE + +extern int cpuidle_register_driver(struct cpuidle_driver *drv); +extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); +extern int cpuidle_register_device(struct cpuidle_device *dev); +extern void cpuidle_unregister_device(struct cpuidle_device *dev); + +extern void cpuidle_pause_and_lock(void); +extern void cpuidle_resume_and_unlock(void); +extern int cpuidle_enable_device(struct cpuidle_device *dev); +extern void cpuidle_disable_device(struct cpuidle_device *dev); + +#else + +static inline int cpuidle_register_driver(struct cpuidle_driver *drv) +{return 0;} +static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } +static inline int cpuidle_register_device(struct cpuidle_device *dev) +{return 0;} +static inline void cpuidle_unregister_device(struct cpuidle_device *dev) { } + +static inline void cpuidle_pause_and_lock(void) { } +static inline void cpuidle_resume_and_unlock(void) { } +static inline int cpuidle_enable_device(struct cpuidle_device *dev) +{return 0;} +static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } + +#endif + +/****************************** + * CPUIDLE GOVERNOR INTERFACE * + ******************************/ + +struct cpuidle_governor { + char name[CPUIDLE_NAME_LEN]; + struct list_head governor_list; + unsigned int rating; + + int (*enable) (struct cpuidle_device *dev); + void (*disable) (struct cpuidle_device *dev); + + int (*select) (struct cpuidle_device *dev); + void (*reflect) (struct cpuidle_device *dev); + + struct module *owner; +}; + +#ifdef CONFIG_CPU_IDLE + +extern int cpuidle_register_governor(struct cpuidle_governor *gov); +extern void cpuidle_unregister_governor(struct cpuidle_governor *gov); + +#else + +static inline int cpuidle_register_governor(struct cpuidle_governor *gov) +{return 0;} +static inline void cpuidle_unregister_governor(struct cpuidle_governor *gov) { } + +#endif + +#endif /* _LINUX_CPUIDLE_H */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 826b15e..ecae585 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> +#include <linux/cgroup.h> #ifdef CONFIG_CPUSETS @@ -19,9 +20,8 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init_early(void); extern int cpuset_init(void); extern void cpuset_init_smp(void); -extern void cpuset_fork(struct task_struct *p); -extern void cpuset_exit(struct task_struct *p); extern cpumask_t cpuset_cpus_allowed(struct task_struct *p); +extern cpumask_t cpuset_cpus_allowed_locked(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -45,7 +45,8 @@ static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) __cpuset_zone_allowed_hardwall(z, gfp_mask); } -extern int cpuset_excl_nodes_overlap(const struct task_struct *p); +extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, + const struct task_struct *tsk2); #define cpuset_memory_pressure_bump() \ do { \ @@ -75,25 +76,29 @@ static inline int cpuset_do_slab_mem_spread(void) extern void cpuset_track_online_nodes(void); +extern int current_cpuset_is_being_rebound(void); + #else /* !CONFIG_CPUSETS */ static inline int cpuset_init_early(void) { return 0; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} -static inline void cpuset_fork(struct task_struct *p) {} -static inline void cpuset_exit(struct task_struct *p) {} static inline cpumask_t cpuset_cpus_allowed(struct task_struct *p) { return cpu_possible_map; } +static inline cpumask_t cpuset_cpus_allowed_locked(struct task_struct *p) +{ + return cpu_possible_map; +} static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } -#define cpuset_current_mems_allowed (node_online_map) +#define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline void cpuset_update_task_memory_state(void) {} #define cpuset_nodes_subset_current_mems_allowed(nodes) (1) @@ -113,7 +118,8 @@ static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) return 1; } -static inline int cpuset_excl_nodes_overlap(const struct task_struct *p) +static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, + const struct task_struct *tsk2) { return 1; } @@ -146,6 +152,11 @@ static inline int cpuset_do_slab_mem_spread(void) static inline void cpuset_track_online_nodes(void) {} +static inline int current_cpuset_is_being_rebound(void) +{ + return 0; +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h index 1dba681..3be4e5a 100644 --- a/include/linux/cramfs_fs.h +++ b/include/linux/cramfs_fs.h @@ -4,6 +4,7 @@ #include <linux/types.h> #define CRAMFS_MAGIC 0x28cd3d45 /* some random number */ +#define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */ #define CRAMFS_SIGNATURE "Compressed ROMFS" /* diff --git a/include/linux/crypto.h b/include/linux/crypto.h index fc32694..f3110eb 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -6,7 +6,7 @@ * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> - * and Nettle, by Niels Möller. + * and Nettle, by Niels Möller. * * 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 diff --git a/include/linux/cyclades.h b/include/linux/cyclades.h index 72aa00c..8f3dcd3 100644 --- a/include/linux/cyclades.h +++ b/include/linux/cyclades.h @@ -512,11 +512,11 @@ struct cyclades_card { void __iomem *base_addr; void __iomem *ctl_addr; int irq; - int num_chips; /* 0 if card absent, -1 if Z/PCI, else Y */ - int first_line; /* minor number of first channel on card */ - int nports; /* Number of ports in the card */ - int bus_index; /* address shift - 0 for ISA, 1 for PCI */ - int intr_enabled; /* FW Interrupt flag - 0 disabled, 1 enabled */ + unsigned int num_chips; /* 0 if card absent, -1 if Z/PCI, else Y */ + unsigned int first_line; /* minor number of first channel on card */ + unsigned int nports; /* Number of ports in the card */ + int bus_index; /* address shift - 0 for ISA, 1 for PCI */ + int intr_enabled; /* FW Interrupt flag - 0 disabled, 1 enabled */ spinlock_t card_lock; struct cyclades_port *ports; }; @@ -566,10 +566,9 @@ struct cyclades_port { int rtsdtr_inv; int chip_rev; int custom_divisor; - int x_char; /* to be pushed out ASAP */ + u8 x_char; /* to be pushed out ASAP */ int close_delay; unsigned short closing_wait; - unsigned long event; int count; /* # of fd on device */ int breakon; int breakoff; @@ -584,7 +583,6 @@ struct cyclades_port { struct cyclades_monitor mon; struct cyclades_idle_stats idle_stats; struct cyclades_icount icount; - struct work_struct tqueue; wait_queue_head_t open_wait; wait_queue_head_t close_wait; struct completion shutdown_wait; @@ -592,19 +590,6 @@ struct cyclades_port { int throttle; }; -/* - * Events are used to schedule things to happen at timer-interrupt - * time, instead of at cy interrupt time. - */ -#define Cy_EVENT_READ_PROCESS 0 -#define Cy_EVENT_WRITE_WAKEUP 1 -#define Cy_EVENT_HANGUP 2 -#define Cy_EVENT_BREAK 3 -#define Cy_EVENT_OPEN_WAKEUP 4 -#define Cy_EVENT_SHUTDOWN_WAKEUP 5 -#define Cy_EVENT_DELTA_WAKEUP 6 -#define Cy_EVENT_Z_RX_FULL 7 - #define CLOSING_WAIT_DELAY 30*HZ #define CY_CLOSING_WAIT_NONE 65535 #define CY_CLOSING_WAIT_INF 0 diff --git a/include/linux/dca.h b/include/linux/dca.h new file mode 100644 index 0000000..83eaecc --- /dev/null +++ b/include/linux/dca.h @@ -0,0 +1,47 @@ +#ifndef DCA_H +#define DCA_H +/* DCA Provider API */ + +/* DCA Notifier Interface */ +void dca_register_notify(struct notifier_block *nb); +void dca_unregister_notify(struct notifier_block *nb); + +#define DCA_PROVIDER_ADD 0x0001 +#define DCA_PROVIDER_REMOVE 0x0002 + +struct dca_provider { + struct dca_ops *ops; + struct class_device *cd; + int id; +}; + +struct dca_ops { + int (*add_requester) (struct dca_provider *, struct device *); + int (*remove_requester) (struct dca_provider *, struct device *); + u8 (*get_tag) (struct dca_provider *, int cpu); +}; + +struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size); +void free_dca_provider(struct dca_provider *dca); +int register_dca_provider(struct dca_provider *dca, struct device *dev); +void unregister_dca_provider(struct dca_provider *dca); + +static inline void *dca_priv(struct dca_provider *dca) +{ + return (void *)dca + sizeof(struct dca_provider); +} + +/* Requester API */ +int dca_add_requester(struct device *dev); +int dca_remove_requester(struct device *dev); +u8 dca_get_tag(int cpu); + +/* internal stuff */ +int __init dca_sysfs_init(void); +void __exit dca_sysfs_exit(void); +int dca_sysfs_add_provider(struct dca_provider *dca, struct device *dev); +void dca_sysfs_remove_provider(struct dca_provider *dca); +int dca_sysfs_add_req(struct dca_provider *dca, struct device *dev, int slot); +void dca_sysfs_remove_req(struct dca_provider *dca, int slot); + +#endif /* DCA_H */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index aab53df..c2c153f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -178,6 +178,7 @@ d_iput: no no no yes #define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 /* Parent inode is watched */ extern spinlock_t dcache_lock; +extern seqlock_t rename_lock; /** * d_drop - drop a dentry diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 55d1ca5..ab94bc0 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -26,6 +26,7 @@ * Used to set current->delays->flags */ #define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ +#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ #ifdef CONFIG_TASK_DELAY_ACCT @@ -39,6 +40,14 @@ extern void __delayacct_blkio_end(void); extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); +static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) +{ + if (p->delays) + return (p->delays->flags & DELAYACCT_PF_BLKIO); + else + return 0; +} + static inline void delayacct_set_flag(int flag) { if (current->delays) @@ -71,6 +80,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk) static inline void delayacct_blkio_start(void) { + delayacct_set_flag(DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -79,6 +89,7 @@ static inline void delayacct_blkio_end(void) { if (current->delays) __delayacct_blkio_end(); + delayacct_clear_flag(DELAYACCT_PF_BLKIO); } static inline int delayacct_add_tsk(struct taskstats *d, @@ -116,6 +127,8 @@ static inline int delayacct_add_tsk(struct taskstats *d, { return 0; } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { return 0; } +static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) +{ return 0; } #endif /* CONFIG_TASK_DELAY_ACCT */ #endif diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 499f537..37c66d1 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -183,11 +183,14 @@ int dm_resume(struct mapped_device *md); */ uint32_t dm_get_event_nr(struct mapped_device *md); int dm_wait_event(struct mapped_device *md, int event_nr); +uint32_t dm_next_uevent_seq(struct mapped_device *md); +void dm_uevent_add(struct mapped_device *md, struct list_head *elist); /* * Info functions. */ const char *dm_device_name(struct mapped_device *md); +int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid); struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct mapped_device *md); int dm_noflush_suspending(struct dm_target *ti); diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index b934861..523281c 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -131,6 +131,7 @@ struct dm_ioctl { char name[DM_NAME_LEN]; /* device name */ char uuid[DM_UUID_LEN]; /* unique identifier for * the block device */ + char data[7]; /* padding or data */ }; /* @@ -285,9 +286,9 @@ typedef char ioctl_struct[308]; #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 11 +#define DM_VERSION_MINOR 12 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2006-10-12)" +#define DM_VERSION_EXTRA "-ioctl (2007-10-02)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2dc21cb..101a2d4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -13,16 +13,28 @@ enum dma_data_direction { DMA_NONE = 3, }; -#define DMA_64BIT_MASK 0xffffffffffffffffULL -#define DMA_48BIT_MASK 0x0000ffffffffffffULL -#define DMA_40BIT_MASK 0x000000ffffffffffULL -#define DMA_39BIT_MASK 0x0000007fffffffffULL -#define DMA_32BIT_MASK 0x00000000ffffffffULL -#define DMA_31BIT_MASK 0x000000007fffffffULL -#define DMA_30BIT_MASK 0x000000003fffffffULL -#define DMA_29BIT_MASK 0x000000001fffffffULL -#define DMA_28BIT_MASK 0x000000000fffffffULL -#define DMA_24BIT_MASK 0x0000000000ffffffULL +#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) + +/* + * NOTE: do not use the below macros in new code and do not add new definitions + * here. + * + * Instead, just open-code DMA_BIT_MASK(n) within your driver + */ +#define DMA_64BIT_MASK DMA_BIT_MASK(64) +#define DMA_48BIT_MASK DMA_BIT_MASK(48) +#define DMA_47BIT_MASK DMA_BIT_MASK(47) +#define DMA_40BIT_MASK DMA_BIT_MASK(40) +#define DMA_39BIT_MASK DMA_BIT_MASK(39) +#define DMA_35BIT_MASK DMA_BIT_MASK(35) +#define DMA_32BIT_MASK DMA_BIT_MASK(32) +#define DMA_31BIT_MASK DMA_BIT_MASK(31) +#define DMA_30BIT_MASK DMA_BIT_MASK(30) +#define DMA_29BIT_MASK DMA_BIT_MASK(29) +#define DMA_28BIT_MASK DMA_BIT_MASK(28) +#define DMA_24BIT_MASK DMA_BIT_MASK(24) + +#define DMA_MASK_NONE 0x0ULL static inline int valid_dma_direction(int dma_direction) { @@ -31,6 +43,11 @@ static inline int valid_dma_direction(int dma_direction) (dma_direction == DMA_FROM_DEVICE)); } +static inline int is_device_dma_capable(struct device *dev) +{ + return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE; +} + #ifdef CONFIG_HAS_DMA #include <asm/dma-mapping.h> #else diff --git a/include/linux/dmar.h b/include/linux/dmar.h new file mode 100644 index 0000000..ffb6439 --- /dev/null +++ b/include/linux/dmar.h @@ -0,0 +1,86 @@ +/* + * Copyright (c) 2006, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + * Copyright (C) Ashok Raj <ashok.raj@intel.com> + * Copyright (C) Shaohua Li <shaohua.li@intel.com> + */ + +#ifndef __DMAR_H__ +#define __DMAR_H__ + +#include <linux/acpi.h> +#include <linux/types.h> +#include <linux/msi.h> + +#ifdef CONFIG_DMAR +struct intel_iommu; + +extern char *dmar_get_fault_reason(u8 fault_reason); + +/* Can't use the common MSI interrupt functions + * since DMAR is not a pci device + */ +extern void dmar_msi_unmask(unsigned int irq); +extern void dmar_msi_mask(unsigned int irq); +extern void dmar_msi_read(int irq, struct msi_msg *msg); +extern void dmar_msi_write(int irq, struct msi_msg *msg); +extern int dmar_set_interrupt(struct intel_iommu *iommu); +extern int arch_setup_dmar_msi(unsigned int irq); + +/* Intel IOMMU detection and initialization functions */ +extern void detect_intel_iommu(void); +extern int intel_iommu_init(void); + +extern int dmar_table_init(void); +extern int early_dmar_detect(void); + +extern struct list_head dmar_drhd_units; +extern struct list_head dmar_rmrr_units; + +struct dmar_drhd_unit { + struct list_head list; /* list of drhd units */ + u64 reg_base_addr; /* register base address*/ + struct pci_dev **devices; /* target device array */ + int devices_cnt; /* target device count */ + u8 ignored:1; /* ignore drhd */ + u8 include_all:1; + struct intel_iommu *iommu; +}; + +struct dmar_rmrr_unit { + struct list_head list; /* list of rmrr units */ + u64 base_address; /* reserved base address*/ + u64 end_address; /* reserved end address */ + struct pci_dev **devices; /* target devices */ + int devices_cnt; /* target device count */ +}; + +#define for_each_drhd_unit(drhd) \ + list_for_each_entry(drhd, &dmar_drhd_units, list) +#define for_each_rmrr_units(rmrr) \ + list_for_each_entry(rmrr, &dmar_rmrr_units, list) +#else +static inline void detect_intel_iommu(void) +{ + return; +} +static inline int intel_iommu_init(void) +{ + return -ENODEV; +} + +#endif /* !CONFIG_DMAR */ +#endif /* __DMAR_H__ */ diff --git a/include/linux/edd.h b/include/linux/edd.h index 7b64782..5d747c5 100644 --- a/include/linux/edd.h +++ b/include/linux/edd.h @@ -67,113 +67,113 @@ #define EDD_INFO_USE_INT13_FN50 (1 << 7) struct edd_device_params { - u16 length; - u16 info_flags; - u32 num_default_cylinders; - u32 num_default_heads; - u32 sectors_per_track; - u64 number_of_sectors; - u16 bytes_per_sector; - u32 dpte_ptr; /* 0xFFFFFFFF for our purposes */ - u16 key; /* = 0xBEDD */ - u8 device_path_info_length; /* = 44 */ - u8 reserved2; - u16 reserved3; - u8 host_bus_type[4]; - u8 interface_type[8]; + __u16 length; + __u16 info_flags; + __u32 num_default_cylinders; + __u32 num_default_heads; + __u32 sectors_per_track; + __u64 number_of_sectors; + __u16 bytes_per_sector; + __u32 dpte_ptr; /* 0xFFFFFFFF for our purposes */ + __u16 key; /* = 0xBEDD */ + __u8 device_path_info_length; /* = 44 */ + __u8 reserved2; + __u16 reserved3; + __u8 host_bus_type[4]; + __u8 interface_type[8]; union { struct { - u16 base_address; - u16 reserved1; - u32 reserved2; + __u16 base_address; + __u16 reserved1; + __u32 reserved2; } __attribute__ ((packed)) isa; struct { - u8 bus; - u8 slot; - u8 function; - u8 channel; - u32 reserved; + __u8 bus; + __u8 slot; + __u8 function; + __u8 channel; + __u32 reserved; } __attribute__ ((packed)) pci; /* pcix is same as pci */ struct { - u64 reserved; + __u64 reserved; } __attribute__ ((packed)) ibnd; struct { - u64 reserved; + __u64 reserved; } __attribute__ ((packed)) xprs; struct { - u64 reserved; + __u64 reserved; } __attribute__ ((packed)) htpt; struct { - u64 reserved; + __u64 reserved; } __attribute__ ((packed)) unknown; } interface_path; union { struct { - u8 device; - u8 reserved1; - u16 reserved2; - u32 reserved3; - u64 reserved4; + __u8 device; + __u8 reserved1; + __u16 reserved2; + __u32 reserved3; + __u64 reserved4; } __attribute__ ((packed)) ata; struct { - u8 device; - u8 lun; - u8 reserved1; - u8 reserved2; - u32 reserved3; - u64 reserved4; + __u8 device; + __u8 lun; + __u8 reserved1; + __u8 reserved2; + __u32 reserved3; + __u64 reserved4; } __attribute__ ((packed)) atapi; struct { - u16 id; - u64 lun; - u16 reserved1; - u32 reserved2; + __u16 id; + __u64 lun; + __u16 reserved1; + __u32 reserved2; } __attribute__ ((packed)) scsi; struct { - u64 serial_number; - u64 reserved; + __u64 serial_number; + __u64 reserved; } __attribute__ ((packed)) usb; struct { - u64 eui; - u64 reserved; + __u64 eui; + __u64 reserved; } __attribute__ ((packed)) i1394; struct { - u64 wwid; - u64 lun; + __u64 wwid; + __u64 lun; } __attribute__ ((packed)) fibre; struct { - u64 identity_tag; - u64 reserved; + __u64 identity_tag; + __u64 reserved; } __attribute__ ((packed)) i2o; struct { - u32 array_number; - u32 reserved1; - u64 reserved2; + __u32 array_number; + __u32 reserved1; + __u64 reserved2; } __attribute__ ((packed)) raid; struct { - u8 device; - u8 reserved1; - u16 reserved2; - u32 reserved3; - u64 reserved4; + __u8 device; + __u8 reserved1; + __u16 reserved2; + __u32 reserved3; + __u64 reserved4; } __attribute__ ((packed)) sata; struct { - u64 reserved1; - u64 reserved2; + __u64 reserved1; + __u64 reserved2; } __attribute__ ((packed)) unknown; } device_path; - u8 reserved4; - u8 checksum; + __u8 reserved4; + __u8 checksum; } __attribute__ ((packed)); struct edd_info { - u8 device; - u8 version; - u16 interface_support; - u16 legacy_max_cylinder; - u8 legacy_max_head; - u8 legacy_sectors_per_track; + __u8 device; + __u8 version; + __u16 interface_support; + __u16 legacy_max_cylinder; + __u8 legacy_max_head; + __u8 legacy_sectors_per_track; struct edd_device_params params; } __attribute__ ((packed)); @@ -184,8 +184,9 @@ struct edd { unsigned char edd_info_nr; }; +#ifdef __KERNEL__ extern struct edd edd; - +#endif /* __KERNEL__ */ #endif /*!__ASSEMBLY__ */ #endif /* _LINUX_EDD_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 0b9579a..14813b5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -298,7 +298,7 @@ extern int efi_mem_attribute_range (unsigned long phys_addr, unsigned long size, u64 attr); extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, - struct resource *data_resource); + struct resource *data_resource, struct resource *bss_resource); extern unsigned long efi_get_time(void); extern int efi_set_rtc_mmss(unsigned long nowtime); extern int is_available_memory(efi_memory_desc_t * md); diff --git a/include/linux/efs_fs.h b/include/linux/efs_fs.h index 16cb25c..dd57fe5 100644 --- a/include/linux/efs_fs.h +++ b/include/linux/efs_fs.h @@ -35,6 +35,7 @@ static inline struct efs_sb_info *SUPER_INFO(struct super_block *sb) } struct statfs; +struct fid; extern const struct inode_operations efs_dir_inode_operations; extern const struct file_operations efs_dir_operations; @@ -45,7 +46,10 @@ extern efs_block_t efs_map_block(struct inode *, efs_block_t); extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int); extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *); -extern struct dentry *efs_get_dentry(struct super_block *sb, void *vobjp); +extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); extern struct dentry *efs_get_parent(struct dentry *); extern int efs_bmap(struct inode *, int); diff --git a/include/linux/elf.h b/include/linux/elf.h index d2da84a..576e83b 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -2,7 +2,6 @@ #define _LINUX_ELF_H #include <linux/types.h> -#include <linux/auxvec.h> #include <linux/elf-em.h> #include <asm/elf.h> @@ -355,6 +354,7 @@ typedef struct elf64_shdr { #define NT_TASKSTRUCT 4 #define NT_AUXV 6 #define NT_PRXFPREG 0x46e62b7f /* copied from gdb5.1/include/elf/common.h */ +#define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ /* Note header in a PT_NOTE section */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h new file mode 100644 index 0000000..532d13a --- /dev/null +++ b/include/linux/elfcore-compat.h @@ -0,0 +1,55 @@ +#ifndef _LINUX_ELFCORE_COMPAT_H +#define _LINUX_ELFCORE_COMPAT_H + +#include <linux/elf.h> +#include <linux/elfcore.h> +#include <linux/compat.h> + +/* + * Make sure these layouts match the linux/elfcore.h native definitions. + */ + +struct compat_elf_siginfo +{ + compat_int_t si_signo; + compat_int_t si_code; + compat_int_t si_errno; +}; + +struct compat_elf_prstatus +{ + struct compat_elf_siginfo pr_info; + short pr_cursig; + compat_ulong_t pr_sigpend; + compat_ulong_t pr_sighold; + compat_pid_t pr_pid; + compat_pid_t pr_ppid; + compat_pid_t pr_pgrp; + compat_pid_t pr_sid; + struct compat_timeval pr_utime; + struct compat_timeval pr_stime; + struct compat_timeval pr_cutime; + struct compat_timeval pr_cstime; + compat_elf_gregset_t pr_reg; +#ifdef CONFIG_BINFMT_ELF_FDPIC + compat_ulong_t pr_exec_fdpic_loadmap; + compat_ulong_t pr_interp_fdpic_loadmap; +#endif + compat_int_t pr_fpvalid; +}; + +struct compat_elf_prpsinfo +{ + char pr_state; + char pr_sname; + char pr_zomb; + char pr_nice; + compat_ulong_t pr_flag; + compat_uid_t pr_uid; + compat_gid_t pr_gid; + compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + char pr_fname[16]; + char pr_psargs[ELF_PRARGSZ]; +}; + +#endif /* _LINUX_ELFCORE_COMPAT_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 8872fe8..51d2141 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -4,9 +4,48 @@ #include <linux/types.h> struct dentry; +struct inode; struct super_block; struct vfsmount; +/* + * The fileid_type identifies how the file within the filesystem is encoded. + * In theory this is freely set and parsed by the filesystem, but we try to + * stick to conventions so we can share some generic code and don't confuse + * sniffers like ethereal/wireshark. + * + * The filesystem must not use the value '0' or '0xff'. + */ +enum fid_type { + /* + * The root, or export point, of the filesystem. + * (Never actually passed down to the filesystem. + */ + FILEID_ROOT = 0, + + /* + * 32bit inode number, 32 bit generation number. + */ + FILEID_INO32_GEN = 1, + + /* + * 32bit inode number, 32 bit generation number, + * 32 bit parent directory inode number. + */ + FILEID_INO32_GEN_PARENT = 2, +}; + +struct fid { + union { + struct { + u32 ino; + u32 gen; + u32 parent_ino; + u32 parent_gen; + } i32; + __u32 raw[6]; + }; +}; /** * struct export_operations - for nfsd to communicate with file systems @@ -15,43 +54,9 @@ struct vfsmount; * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory * @get_dentry: find a dentry for the inode given a file handle sub-fragment - * @find_exported_dentry: - * set by the exporting module to a standard helper function. - * - * Description: - * The export_operations structure provides a means for nfsd to communicate - * with a particular exported file system - particularly enabling nfsd and - * the filesystem to co-operate when dealing with file handles. - * - * export_operations contains two basic operation for dealing with file - * handles, decode_fh() and encode_fh(), and allows for some other - * operations to be defined which standard helper routines use to get - * specific information from the filesystem. - * - * nfsd encodes information use to determine which filesystem a filehandle - * applies to in the initial part of the file handle. The remainder, termed - * a file handle fragment, is controlled completely by the filesystem. The - * standard helper routines assume that this fragment will contain one or - * two sub-fragments, one which identifies the file, and one which may be - * used to identify the (a) directory containing the file. * - * In some situations, nfsd needs to get a dentry which is connected into a - * specific part of the file tree. To allow for this, it passes the - * function acceptable() together with a @context which can be used to see - * if the dentry is acceptable. As there can be multiple dentrys for a - * given file, the filesystem should check each one for acceptability before - * looking for the next. As soon as an acceptable one is found, it should - * be returned. - * - * decode_fh: - * @decode_fh is given a &struct super_block (@sb), a file handle fragment - * (@fh, @fh_len) and an acceptability testing function (@acceptable, - * @context). It should return a &struct dentry which refers to the same - * file that the file handle fragment refers to, and which passes the - * acceptability test. If it cannot, it should return a %NULL pointer if - * the file was found but no acceptable &dentries were available, or a - * %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or - * %ENOMEM). + * See Documentation/filesystems/Exporting for details on how to use + * this interface correctly. * * encode_fh: * @encode_fh should store in the file handle fragment @fh (using at most @@ -63,6 +68,21 @@ struct vfsmount; * the filehandle fragment. encode_fh() should return the number of bytes * stored or a negative error code such as %-ENOSPC * + * fh_to_dentry: + * @fh_to_dentry is given a &struct super_block (@sb) and a file handle + * fragment (@fh, @fh_len). It should return a &struct dentry which refers + * to the same file that the file handle fragment refers to. If it cannot, + * it should return a %NULL pointer if the file was found but no acceptable + * &dentries were available, or an %ERR_PTR error code indicating why it + * couldn't be found (e.g. %ENOENT or %ENOMEM). Any suitable dentry can be + * returned including, if necessary, a new dentry created with d_alloc_root. + * The caller can then find any other extant dentries by following the + * d_alias links. + * + * fh_to_parent: + * Same as @fh_to_dentry, except that it returns a pointer to the parent + * dentry if it was encoded into the filehandle fragment by @encode_fh. + * * get_name: * @get_name should find a name for the given @child in the given @parent * directory. The name should be stored in the @name (with the @@ -75,52 +95,37 @@ struct vfsmount; * is also a directory. In the event that it cannot be found, or storage * space cannot be allocated, a %ERR_PTR should be returned. * - * get_dentry: - * Given a &super_block (@sb) and a pointer to a file-system specific inode - * identifier, possibly an inode number, (@inump) get_dentry() should find - * the identified inode and return a dentry for that inode. Any suitable - * dentry can be returned including, if necessary, a new dentry created with - * d_alloc_root. The caller can then find any other extant dentrys by - * following the d_alias links. If a new dentry was created using - * d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry - * should be d_rehash()ed. - * - * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code - * can be returned. The @inump will be whatever was passed to - * nfsd_find_fh_dentry() in either the @obj or @parent parameters. - * * Locking rules: * get_parent is called with child->d_inode->i_mutex down * get_name is not (which is possibly inconsistent) */ struct export_operations { - struct dentry *(*decode_fh)(struct super_block *sb, __u32 *fh, - int fh_len, int fh_type, - int (*acceptable)(void *context, struct dentry *de), - void *context); int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len, int connectable); + struct dentry * (*fh_to_dentry)(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); + struct dentry * (*fh_to_parent)(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); int (*get_name)(struct dentry *parent, char *name, struct dentry *child); struct dentry * (*get_parent)(struct dentry *child); - struct dentry * (*get_dentry)(struct super_block *sb, void *inump); - - /* This is set by the exporting module to a standard helper */ - struct dentry * (*find_exported_dentry)( - struct super_block *sb, void *obj, void *parent, - int (*acceptable)(void *context, struct dentry *de), - void *context); }; -extern struct dentry *find_exported_dentry(struct super_block *sb, void *obj, - void *parent, int (*acceptable)(void *context, struct dentry *de), - void *context); - -extern int exportfs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len, - int connectable); -extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, __u32 *fh, +extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, + int *max_len, int connectable); +extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *), void *context); +/* + * Generic helpers for filesystems. + */ +extern struct dentry *generic_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type, + struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); +extern struct dentry *generic_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type, + struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); + #endif /* LINUX_EXPORTFS_H */ diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 153d755..0f6c86c 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -29,11 +29,12 @@ #undef EXT2FS_DEBUG /* - * Define EXT2_PREALLOCATE to preallocate data blocks for expanding files + * Define EXT2_RESERVATION to reserve data blocks for expanding files */ -#define EXT2_PREALLOCATE -#define EXT2_DEFAULT_PREALLOC_BLOCKS 8 - +#define EXT2_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT2_MAX_RESERVE_BLOCKS 1027 +#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0 /* * The second extended file system version */ @@ -200,6 +201,8 @@ struct ext2_group_desc #define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT2_IOC_GETVERSION FS_IOC_GETVERSION #define EXT2_IOC_SETVERSION FS_IOC_SETVERSION +#define EXT2_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT2_IOC_SETRSVSZ _IOW('f', 6, long) /* * ioctl commands in 32 bit emulation @@ -317,8 +320,9 @@ struct ext2_inode { #define EXT2_MOUNT_XATTR_USER 0x004000 /* Extended user attributes */ #define EXT2_MOUNT_POSIX_ACL 0x008000 /* POSIX Access Control Lists */ #define EXT2_MOUNT_XIP 0x010000 /* Execute in place */ -#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */ -#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */ +#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */ +#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */ +#define EXT2_MOUNT_RESERVATION 0x080000 /* Preallocation */ #define clear_opt(o, opt) o &= ~EXT2_MOUNT_##opt @@ -557,5 +561,13 @@ enum { #define EXT2_DIR_ROUND (EXT2_DIR_PAD - 1) #define EXT2_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT2_DIR_ROUND) & \ ~EXT2_DIR_ROUND) +#define EXT2_MAX_REC_LEN ((1<<16)-1) + +static inline ext2_fsblk_t +ext2_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block); +} #endif /* _LINUX_EXT2_FS_H */ diff --git a/include/linux/ext2_fs_sb.h b/include/linux/ext2_fs_sb.h index d149f29..f273415 100644 --- a/include/linux/ext2_fs_sb.h +++ b/include/linux/ext2_fs_sb.h @@ -18,6 +18,52 @@ #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> +#include <linux/rbtree.h> + +/* XXX Here for now... not interested in restructing headers JUST now */ + +/* data type for block offset of block group */ +typedef int ext2_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long ext2_fsblk_t; + +#define E2FSBLK "%lu" + +struct ext2_reserve_window { + ext2_fsblk_t _rsv_start; /* First byte reserved */ + ext2_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext2_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext2_reserve_window rsv_window; +}; + +struct ext2_block_alloc_info { + /* information about reservation window */ + struct ext2_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext2_inode_info + * is the logical (file-relative) number of the + * most-recently-allocated block in this file. + * We use this for detecting linearly ascending allocation requests. + */ + __u32 last_alloc_logical_block; + /* + * Was i_next_alloc_goal in ext2_inode_info + * is the *physical* companion to i_next_alloc_block. + * it the the physical block number of the block which was most-recentl + * allocated to this file. This give us the goal (target) for the next + * allocation when we detect linearly ascending requests. + */ + ext2_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end /* * second extended-fs super-block data in memory @@ -39,6 +85,7 @@ struct ext2_sb_info { struct ext2_super_block * s_es; /* Pointer to the super block in the buffer */ struct buffer_head ** s_group_desc; unsigned long s_mount_opt; + unsigned long s_sb_block; uid_t s_resuid; gid_t s_resgid; unsigned short s_mount_state; @@ -55,6 +102,10 @@ struct ext2_sb_info { struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; struct blockgroup_lock s_blockgroup_lock; + /* root of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct rb_root s_rsv_window_root; + struct ext2_reserve_window_node s_rsv_window_head; }; #endif /* _LINUX_EXT2_FS_SB */ diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index ece49a8..6413445 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -35,10 +35,6 @@ /*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ #define EXT3_MAX_RESERVE_BLOCKS 1027 #define EXT3_RESERVE_WINDOW_NOT_ALLOCATED 0 -/* - * Always enable hashed directories - */ -#define CONFIG_EXT3_INDEX /* * Debug code @@ -76,8 +72,8 @@ * Macro-instructions used to manage several block sizes */ #define EXT3_MIN_BLOCK_SIZE 1024 -#define EXT3_MAX_BLOCK_SIZE 4096 -#define EXT3_MIN_BLOCK_LOG_SIZE 10 +#define EXT3_MAX_BLOCK_SIZE 65536 +#define EXT3_MIN_BLOCK_LOG_SIZE 10 #ifdef __KERNEL__ # define EXT3_BLOCK_SIZE(s) ((s)->s_blocksize) #else @@ -665,17 +661,11 @@ struct ext3_dir_entry_2 { * (c) Daniel Phillips, 2001 */ -#ifdef CONFIG_EXT3_INDEX - #define is_dx(dir) (EXT3_HAS_COMPAT_FEATURE(dir->i_sb, \ - EXT3_FEATURE_COMPAT_DIR_INDEX) && \ +#define is_dx(dir) (EXT3_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT3_FEATURE_COMPAT_DIR_INDEX) && \ (EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) #define EXT3_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT3_LINK_MAX) #define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) -#else - #define is_dx(dir) 0 -#define EXT3_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT3_LINK_MAX) -#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) -#endif /* Legal values for the dx_root hash_version field: */ diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h index d3c0835..b65f028 100644 --- a/include/linux/ext3_fs_sb.h +++ b/include/linux/ext3_fs_sb.h @@ -44,6 +44,7 @@ struct ext3_sb_info { struct ext3_super_block * s_es; /* Pointer to the super block in the buffer */ struct buffer_head ** s_group_desc; unsigned long s_mount_opt; + ext3_fsblk_t s_sb_block; uid_t s_resuid; gid_t s_resgid; unsigned short s_mount_state; diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index cdee7aa..97dd409 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -36,10 +36,6 @@ /*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ #define EXT4_MAX_RESERVE_BLOCKS 1027 #define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0 -/* - * Always enable hashed directories - */ -#define CONFIG_EXT4_INDEX /* * Debug code @@ -105,37 +101,29 @@ #define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) /* - * Macro-instructions used to manage fragments - */ -#define EXT4_MIN_FRAG_SIZE 1024 -#define EXT4_MAX_FRAG_SIZE 4096 -#define EXT4_MIN_FRAG_LOG_SIZE 10 -#ifdef __KERNEL__ -# define EXT4_FRAG_SIZE(s) (EXT4_SB(s)->s_frag_size) -# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_SB(s)->s_frags_per_block) -#else -# define EXT4_FRAG_SIZE(s) (EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size) -# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s)) -#endif - -/* * Structure of a blocks group descriptor */ struct ext4_group_desc { - __le32 bg_block_bitmap; /* Blocks bitmap block */ - __le32 bg_inode_bitmap; /* Inodes bitmap block */ - __le32 bg_inode_table; /* Inodes table block */ + __le32 bg_block_bitmap_lo; /* Blocks bitmap block */ + __le32 bg_inode_bitmap_lo; /* Inodes bitmap block */ + __le32 bg_inode_table_lo; /* Inodes table block */ __le16 bg_free_blocks_count; /* Free blocks count */ __le16 bg_free_inodes_count; /* Free inodes count */ __le16 bg_used_dirs_count; /* Directories count */ - __u16 bg_flags; - __u32 bg_reserved[3]; + __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */ + __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */ + __le16 bg_itable_unused; /* Unused inodes count */ + __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ __le32 bg_inode_table_hi; /* Inodes table block MSB */ }; +#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ +#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */ +#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */ + #ifdef __KERNEL__ #include <linux/ext4_fs_i.h> #include <linux/ext4_fs_sb.h> @@ -311,27 +299,24 @@ struct ext4_inode { __le32 i_generation; /* File version (for NFS) */ __le32 i_file_acl; /* File ACL */ __le32 i_dir_acl; /* Directory ACL */ - __le32 i_faddr; /* Fragment address */ + __le32 i_obso_faddr; /* Obsoleted fragment address */ union { struct { - __u8 l_i_frag; /* Fragment number */ - __u8 l_i_fsize; /* Fragment size */ + __le16 l_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ __u32 l_i_reserved2; } linux2; struct { - __u8 h_i_frag; /* Fragment number */ - __u8 h_i_fsize; /* Fragment size */ + __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __u16 h_i_mode_high; __u16 h_i_uid_high; __u16 h_i_gid_high; __u32 h_i_author; } hurd2; struct { - __u8 m_i_frag; /* Fragment number */ - __u8 m_i_fsize; /* Fragment size */ + __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __le16 m_i_file_acl_high; __u32 m_i_reserved2[2]; } masix2; @@ -419,8 +404,6 @@ do { \ #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 -#define i_frag osd2.linux2.l_i_frag -#define i_fsize osd2.linux2.l_i_fsize #define i_file_acl_high osd2.linux2.l_i_file_acl_high #define i_uid_low i_uid #define i_gid_low i_gid @@ -431,8 +414,6 @@ do { \ #elif defined(__GNU__) #define i_translator osd1.hurd1.h_i_translator -#define i_frag osd2.hurd2.h_i_frag; -#define i_fsize osd2.hurd2.h_i_fsize; #define i_uid_high osd2.hurd2.h_i_uid_high #define i_gid_high osd2.hurd2.h_i_gid_high #define i_author osd2.hurd2.h_i_author @@ -440,8 +421,6 @@ do { \ #elif defined(__masix__) #define i_reserved1 osd1.masix1.m_i_reserved1 -#define i_frag osd2.masix2.m_i_frag -#define i_fsize osd2.masix2.m_i_fsize #define i_file_acl_high osd2.masix2.m_i_file_acl_high #define i_reserved2 osd2.masix2.m_i_reserved2 @@ -522,15 +501,15 @@ do { \ */ struct ext4_super_block { /*00*/ __le32 s_inodes_count; /* Inodes count */ - __le32 s_blocks_count; /* Blocks count */ - __le32 s_r_blocks_count; /* Reserved blocks count */ - __le32 s_free_blocks_count; /* Free blocks count */ + __le32 s_blocks_count_lo; /* Blocks count */ + __le32 s_r_blocks_count_lo; /* Reserved blocks count */ + __le32 s_free_blocks_count_lo; /* Free blocks count */ /*10*/ __le32 s_free_inodes_count; /* Free inodes count */ __le32 s_first_data_block; /* First Data Block */ __le32 s_log_block_size; /* Block size */ - __le32 s_log_frag_size; /* Fragment size */ + __le32 s_obso_log_frag_size; /* Obsoleted fragment size */ /*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ - __le32 s_frags_per_group; /* # Fragments per group */ + __le32 s_obso_frags_per_group; /* Obsoleted fragments per group */ __le32 s_inodes_per_group; /* # Inodes per group */ __le32 s_mtime; /* Mount time */ /*30*/ __le32 s_wtime; /* Write time */ @@ -595,13 +574,13 @@ struct ext4_super_block { /*150*/ __le32 s_blocks_count_hi; /* Blocks count */ __le32 s_r_blocks_count_hi; /* Reserved blocks count */ __le32 s_free_blocks_count_hi; /* Free blocks count */ - __u16 s_min_extra_isize; /* All inodes have at least # bytes */ - __u16 s_want_extra_isize; /* New inodes should reserve # bytes */ - __u32 s_flags; /* Miscellaneous flags */ - __u16 s_raid_stride; /* RAID stride */ - __u16 s_mmp_interval; /* # seconds to wait in MMP checking */ - __u64 s_mmp_block; /* Block for multi-mount protection */ - __u32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ + __le16 s_min_extra_isize; /* All inodes have at least # bytes */ + __le16 s_want_extra_isize; /* New inodes should reserve # bytes */ + __le32 s_flags; /* Miscellaneous flags */ + __le16 s_raid_stride; /* RAID stride */ + __le16 s_mmp_interval; /* # seconds to wait in MMP checking */ + __le64 s_mmp_block; /* Block for multi-mount protection */ + __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u32 s_reserved[163]; /* Padding to the end of the block */ }; @@ -692,6 +671,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 +#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 @@ -702,15 +682,18 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 #define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ #define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 +#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG| \ EXT4_FEATURE_INCOMPAT_EXTENTS| \ - EXT4_FEATURE_INCOMPAT_64BIT) + EXT4_FEATURE_INCOMPAT_64BIT| \ + EXT4_FEATURE_INCOMPAT_FLEX_BG) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) @@ -789,17 +772,11 @@ struct ext4_dir_entry_2 { * (c) Daniel Phillips, 2001 */ -#ifdef CONFIG_EXT4_INDEX - #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ - EXT4_FEATURE_COMPAT_DIR_INDEX) && \ +#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT4_FEATURE_COMPAT_DIR_INDEX) && \ (EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) #define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) -#else - #define is_dx(dir) 0 -#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX) -#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) -#endif /* Legal values for the dx_root hash_version field: */ @@ -1004,39 +981,39 @@ extern void ext4_inode_table_set(struct super_block *sb, static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | - le32_to_cpu(es->s_blocks_count); + le32_to_cpu(es->s_blocks_count_lo); } static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) | - le32_to_cpu(es->s_r_blocks_count); + le32_to_cpu(es->s_r_blocks_count_lo); } static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) | - le32_to_cpu(es->s_free_blocks_count); + le32_to_cpu(es->s_free_blocks_count_lo); } static inline void ext4_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { - es->s_blocks_count = cpu_to_le32((u32)blk); + es->s_blocks_count_lo = cpu_to_le32((u32)blk); es->s_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { - es->s_free_blocks_count = cpu_to_le32((u32)blk); + es->s_free_blocks_count_lo = cpu_to_le32((u32)blk); es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { - es->s_r_blocks_count = cpu_to_le32((u32)blk); + es->s_r_blocks_count_lo = cpu_to_le32((u32)blk); es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index 81406f3..d2045a2 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -74,7 +74,7 @@ struct ext4_extent { __le32 ee_block; /* first logical block extent covers */ __le16 ee_len; /* number of blocks covered by extent */ __le16 ee_start_hi; /* high 16 bits of physical block */ - __le32 ee_start; /* low 32 bits of physical block */ + __le32 ee_start_lo; /* low 32 bits of physical block */ }; /* @@ -83,7 +83,7 @@ struct ext4_extent { */ struct ext4_extent_idx { __le32 ei_block; /* index covers logical blocks from 'block' */ - __le32 ei_leaf; /* pointer to the physical block of the next * + __le32 ei_leaf_lo; /* pointer to the physical block of the next * * level. leaf or next index could be there */ __le16 ei_leaf_hi; /* high 16 bits of physical block */ __u16 ei_unused; diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 1a511e99..86ddfe2 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -78,11 +78,6 @@ struct ext4_ext_cache { struct ext4_inode_info { __le32 i_data[15]; /* unconverted */ __u32 i_flags; -#ifdef EXT4_FRAGMENTS - __u32 i_faddr; - __u8 i_frag_no; - __u8 i_frag_size; -#endif ext4_fsblk_t i_file_acl; __u32 i_dir_acl; __u32 i_dtime; diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index 1b2ffee..b40e827 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -28,11 +28,8 @@ * third extended-fs super-block data in memory */ struct ext4_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ unsigned long s_desc_size; /* Size of a group descriptor in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -45,6 +42,7 @@ struct ext4_sb_info { struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */ struct buffer_head ** s_group_desc; unsigned long s_mount_opt; + ext4_fsblk_t s_sb_block; uid_t s_resuid; gid_t s_resgid; unsigned short s_mount_state; diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index d716e63..38c71d3 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -12,8 +12,8 @@ * Ext4-specific journaling extensions. */ -#ifndef _LINUX_EXT4_JBD_H -#define _LINUX_EXT4_JBD_H +#ifndef _LINUX_EXT4_JBD2_H +#define _LINUX_EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> @@ -228,4 +228,4 @@ static inline int ext4_should_writeback_data(struct inode *inode) return 0; } -#endif /* _LINUX_EXT4_JBD_H */ +#endif /* _LINUX_EXT4_JBD2_H */ diff --git a/include/linux/fb.h b/include/linux/fb.h index cec5410..58c57a3 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -180,6 +180,7 @@ struct fb_bitfield { }; #define FB_NONSTD_HAM 1 /* Hold-And-Modify (HAM) */ +#define FB_NONSTD_REV_PIX_IN_B 2 /* order of pixels in each byte is reversed */ #define FB_ACTIVATE_NOW 0 /* set values immediately (or vbl)*/ #define FB_ACTIVATE_NXTOPEN 1 /* activate on next open */ @@ -206,6 +207,7 @@ struct fb_bitfield { #define FB_VMODE_NONINTERLACED 0 /* non interlaced */ #define FB_VMODE_INTERLACED 1 /* interlaced */ #define FB_VMODE_DOUBLE 2 /* double scan */ +#define FB_VMODE_ODD_FLD_FIRST 4 /* interlaced: top line first */ #define FB_VMODE_MASK 255 #define FB_VMODE_YWRAP 256 /* ywrap instead of panning */ @@ -1054,6 +1056,7 @@ struct fb_videomode { u32 flag; }; +extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; struct fb_modelist { diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 40b9326..8603740 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -3,12 +3,17 @@ #include <asm/fcntl.h> -/* Cancel a blocking posix lock; internal use only until we expose an - * asynchronous lock api to userspace: */ -#define F_CANCELLK (F_LINUX_SPECIFIC_BASE+5) +#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) +#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) -#define F_SETLEASE (F_LINUX_SPECIFIC_BASE+0) -#define F_GETLEASE (F_LINUX_SPECIFIC_BASE+1) +/* + * Cancel a blocking posix lock; internal use only until we expose an + * asynchronous lock api to userspace: + */ +#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5) + +/* Create a file descriptor with FD_CLOEXEC set. */ +#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) /* * Request nofications on a directory. diff --git a/include/linux/file.h b/include/linux/file.h index 0114fbc..56023c7 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -62,6 +62,15 @@ extern struct kmem_cache *filp_cachep; extern void FASTCALL(__fput(struct file *)); extern void FASTCALL(fput(struct file *)); +struct file_operations; +struct vfsmount; +struct dentry; +extern int init_file(struct file *, struct vfsmount *mnt, + struct dentry *dentry, mode_t mode, + const struct file_operations *fop); +extern struct file *alloc_file(struct vfsmount *, struct dentry *dentry, + mode_t mode, const struct file_operations *fop); + static inline void fput_light(struct file *file, int fput_needed) { if (unlikely(fput_needed)) diff --git a/include/linux/filter.h b/include/linux/filter.h index 91b2e3b..ddfa037 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -146,6 +146,7 @@ struct sock; extern unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +extern int sk_detach_filter(struct sock *sk); extern int sk_chk_filter(struct sock_filter *filter, int flen); #endif /* __KERNEL__ */ diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 1a45d6f..0f0e271 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -178,6 +178,7 @@ union fw_cdev_event { #define FW_CDEV_IOC_QUEUE_ISO _IOWR('#', 0x09, struct fw_cdev_queue_iso) #define FW_CDEV_IOC_START_ISO _IOW('#', 0x0a, struct fw_cdev_start_iso) #define FW_CDEV_IOC_STOP_ISO _IOW('#', 0x0b, struct fw_cdev_stop_iso) +#define FW_CDEV_IOC_GET_CYCLE_TIMER _IOR('#', 0x0c, struct fw_cdev_get_cycle_timer) /* FW_CDEV_VERSION History * @@ -459,4 +460,18 @@ struct fw_cdev_stop_iso { __u32 handle; }; +/** + * struct fw_cdev_get_cycle_timer - read cycle timer register + * @local_time: system time, in microseconds since the Epoch + * @cycle_timer: isochronous cycle timer, as per OHCI 1.1 clause 5.13 + * + * The %FW_CDEV_IOC_GET_CYCLE_TIMER ioctl reads the isochronous cycle timer + * and also the system clock. This allows to express the receive time of an + * isochronous packet as a system time with microsecond accuracy. + */ +struct fw_cdev_get_cycle_timer { + __u64 local_time; + __u32 cycle_timer; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ diff --git a/include/linux/freezer.h b/include/linux/freezer.h index efded00..0893499 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -4,6 +4,7 @@ #define FREEZER_H_INCLUDED #include <linux/sched.h> +#include <linux/wait.h> #ifdef CONFIG_PM_SLEEP /* @@ -126,6 +127,36 @@ static inline void set_freezable(void) current->flags &= ~PF_NOFREEZE; } +/* + * Freezer-friendly wrappers around wait_event_interruptible() and + * wait_event_interruptible_timeout(), originally defined in <linux/wait.h> + */ + +#define wait_event_freezable(wq, condition) \ +({ \ + int __retval; \ + do { \ + __retval = wait_event_interruptible(wq, \ + (condition) || freezing(current)); \ + if (__retval && !freezing(current)) \ + break; \ + else if (!(condition)) \ + __retval = -ERESTARTSYS; \ + } while (try_to_freeze()); \ + __retval; \ +}) + + +#define wait_event_freezable_timeout(wq, condition, timeout) \ +({ \ + long __retval = timeout; \ + do { \ + __retval = wait_event_interruptible_timeout(wq, \ + (condition) || freezing(current), \ + __retval); \ + } while (try_to_freeze()); \ + __retval; \ +}) #else /* !CONFIG_PM_SLEEP */ static inline int frozen(struct task_struct *p) { return 0; } static inline int freezing(struct task_struct *p) { return 0; } @@ -143,6 +174,13 @@ static inline void freezer_do_not_count(void) {} static inline void freezer_count(void) {} static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} + +#define wait_event_freezable(wq, condition) \ + wait_event_interruptible(wq, condition) + +#define wait_event_freezable_timeout(wq, condition, timeout) \ + wait_event_interruptible_timeout(wq, condition, timeout) + #endif /* !CONFIG_PM_SLEEP */ #endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 16421f6..b3ec4a4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -123,6 +123,7 @@ extern int dir_notify_enable; #define MS_SLAVE (1<<19) /* change to slave */ #define MS_SHARED (1<<20) /* change to shared */ #define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ +#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -283,7 +284,6 @@ extern int dir_notify_enable; #include <linux/init.h> #include <linux/pid.h> #include <linux/mutex.h> -#include <linux/sysctl.h> #include <linux/capability.h> #include <asm/atomic.h> @@ -301,9 +301,9 @@ struct kstatfs; struct vm_area_struct; struct vfsmount; -extern void __init inode_init(unsigned long); +extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init mnt_init(unsigned long); +extern void __init mnt_init(void); extern void __init files_init(unsigned long); struct buffer_head; @@ -330,6 +330,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_KILL_SUID 2048 #define ATTR_KILL_SGID 4096 #define ATTR_FILE 8192 +#define ATTR_KILL_PRIV 16384 +#define ATTR_OPEN 32768 /* Truncating from open(O_TRUNC) */ /* * This is the Inode Attributes structure, used for notify_change(). It @@ -381,7 +383,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(), prepare_write(), and commit_write(). + * by readpage(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -394,6 +396,9 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; +#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */ +#define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */ + /* * oh the beauties of C type declarations. */ @@ -401,6 +406,39 @@ struct page; struct address_space; struct writeback_control; +struct iov_iter { + const struct iovec *iov; + unsigned long nr_segs; + size_t iov_offset; + size_t count; +}; + +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes); +size_t iov_iter_copy_from_user(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes); +void iov_iter_advance(struct iov_iter *i, size_t bytes); +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); +size_t iov_iter_single_seg_count(struct iov_iter *i); + +static inline void iov_iter_init(struct iov_iter *i, + const struct iovec *iov, unsigned long nr_segs, + size_t count, size_t written) +{ + i->iov = iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count + written; + + iov_iter_advance(i, written); +} + +static inline size_t iov_iter_count(struct iov_iter *i) +{ + return i->count; +} + + struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); @@ -421,6 +459,14 @@ struct address_space_operations { */ int (*prepare_write)(struct file *, struct page *, unsigned, unsigned); int (*commit_write)(struct file *, struct page *, unsigned, unsigned); + + int (*write_begin)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); + int (*write_end)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); + /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned long); @@ -435,6 +481,18 @@ struct address_space_operations { int (*launder_page) (struct page *); }; +/* + * pagecache_write_begin/pagecache_write_end must be used by general code + * to write into the pagecache. + */ +int pagecache_write_begin(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); + +int pagecache_write_end(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); + struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ @@ -697,16 +755,14 @@ struct fown_struct { * Track a single file's readahead state */ struct file_ra_state { - pgoff_t start; /* where readahead started */ - unsigned long size; /* # of readahead pages */ - unsigned long async_size; /* do asynchronous readahead when + pgoff_t start; /* where readahead started */ + unsigned int size; /* # of readahead pages */ + unsigned int async_size; /* do asynchronous readahead when there are only # of pages ahead */ - unsigned long ra_pages; /* Maximum readahead window */ - unsigned long mmap_hit; /* Cache hit stat for mmap accesses */ - unsigned long mmap_miss; /* Cache miss stat for mmap accesses */ - unsigned long prev_index; /* Cache last read() position */ - unsigned int prev_offset; /* Offset where last read() ended in a page */ + unsigned int ra_pages; /* Maximum readahead window */ + int mmap_miss; /* Cache miss stat for mmap accesses */ + loff_t prev_pos; /* Cache last read() position */ }; /* @@ -739,7 +795,7 @@ struct file { unsigned int f_uid, f_gid; struct file_ra_state f_ra; - unsigned long f_version; + u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif @@ -883,6 +939,7 @@ extern int vfs_setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); +extern struct seq_operations locks_seq_operations; struct fasync_struct { int magic; @@ -930,7 +987,7 @@ struct super_block { const struct super_operations *s_op; struct dquot_operations *dq_op; struct quotactl_ops *s_qcop; - struct export_operations *s_export_op; + const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_magic; struct dentry *s_root; @@ -948,6 +1005,7 @@ struct super_block { struct list_head s_inodes; /* all inodes */ struct list_head s_dirty; /* dirty inodes */ struct list_head s_io; /* parked for writeback */ + struct list_head s_more_io; /* parked for more writeback */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_files; @@ -1206,16 +1264,68 @@ struct super_operations { #endif }; -/* Inode state bits. Protected by inode_lock. */ -#define I_DIRTY_SYNC 1 /* Not dirty enough for O_DATASYNC */ -#define I_DIRTY_DATASYNC 2 /* Data-related inode changes pending */ -#define I_DIRTY_PAGES 4 /* Data-related inode changes pending */ -#define __I_LOCK 3 +/* + * Inode state bits. Protected by inode_lock. + * + * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, + * I_DIRTY_DATASYNC and I_DIRTY_PAGES. + * + * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, + * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at + * various stages of removing an inode. + * + * Two bits are used for locking and completion notification, I_LOCK and I_SYNC. + * + * I_DIRTY_SYNC Inode itself is dirty. + * I_DIRTY_DATASYNC Data-related inode changes pending + * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_NEW get_new_inode() sets i_state to I_LOCK|I_NEW. Both + * are cleared by unlock_new_inode(), called from iget(). + * I_WILL_FREE Must be set when calling write_inode_now() if i_count + * is zero. I_FREEING must be set when I_WILL_FREE is + * cleared. + * I_FREEING Set when inode is about to be freed but still has dirty + * pages or buffers attached or the inode itself is still + * dirty. + * I_CLEAR Set by clear_inode(). In this state the inode is clean + * and can be destroyed. + * + * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are + * prohibited for many purposes. iget() must wait for + * the inode to be completely released, then create it + * anew. Other functions will just ignore such inodes, + * if appropriate. I_LOCK is used for waiting. + * + * I_LOCK Serves as both a mutex and completion notification. + * New inodes set I_LOCK. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_LOCK to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_LOCK, without I_LOCK actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. + * I_SYNC Similar to I_LOCK, but limited in scope to writeback + * of inode dirty data. Having a seperate lock for this + * purpose reduces latency and prevents some filesystem- + * specific deadlocks. + * + * Q: Why does I_DIRTY_DATASYNC exist? It appears as if it could be replaced + * by (I_DIRTY_SYNC|I_DIRTY_PAGES). + * Q: What is the difference between I_WILL_FREE and I_FREEING? + * Q: igrab() only checks on (I_FREEING|I_WILL_FREE). Should it also check on + * I_CLEAR? If not, why? + */ +#define I_DIRTY_SYNC 1 +#define I_DIRTY_DATASYNC 2 +#define I_DIRTY_PAGES 4 +#define I_NEW 8 +#define I_WILL_FREE 16 +#define I_FREEING 32 +#define I_CLEAR 64 +#define __I_LOCK 7 #define I_LOCK (1 << __I_LOCK) -#define I_FREEING 16 -#define I_CLEAR 32 -#define I_NEW 64 -#define I_WILL_FREE 128 +#define __I_SYNC 8 +#define I_SYNC (1 << __I_SYNC) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) @@ -1302,8 +1412,14 @@ struct file_system_type { struct module *owner; struct file_system_type * next; struct list_head fs_supers; + struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; + + struct lock_class_key i_lock_key; + struct lock_class_key i_mutex_key; + struct lock_class_key i_mutex_dir_key; + struct lock_class_key i_alloc_sem_key; }; extern int get_sb_bdev(struct file_system_type *fs_type, @@ -1344,7 +1460,8 @@ void unnamed_dev_init(void); extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount(struct file_system_type *); +extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data); +#define kern_mount(type) kern_mount_data(type, NULL) extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern void umount_tree(struct vfsmount *, int, struct list_head *); @@ -1353,6 +1470,8 @@ extern long do_mount(char *, char *, char *, unsigned long, void *); extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *, struct vfsmount *); +extern struct vfsmount *collect_mounts(struct vfsmount *, struct dentry *); +extern void drop_collected_mounts(struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); @@ -1369,12 +1488,25 @@ extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size * Candidates for mandatory locking have the setgid bit set * but no group execute bit - an otherwise meaningless combination. */ -#define MANDATORY_LOCK(inode) \ - (IS_MANDLOCK(inode) && ((inode)->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID) + +static inline int __mandatory_lock(struct inode *ino) +{ + return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; +} + +/* + * ... and these candidates should be on MS_MANDLOCK mounted fs, + * otherwise these will be advisory locks + */ + +static inline int mandatory_lock(struct inode *ino) +{ + return IS_MANDLOCK(ino) && __mandatory_lock(ino); +} static inline int locks_verify_locked(struct inode *inode) { - if (MANDATORY_LOCK(inode)) + if (mandatory_lock(inode)) return locks_mandatory_locked(inode); return 0; } @@ -1385,7 +1517,7 @@ static inline int locks_verify_truncate(struct inode *inode, struct file *filp, loff_t size) { - if (inode->i_flock && MANDATORY_LOCK(inode)) + if (inode->i_flock && mandatory_lock(inode)) return locks_mandatory_area( FLOCK_VERIFY_WRITE, inode, filp, size < inode->i_size ? size : inode->i_size, @@ -1406,7 +1538,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode) extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); -extern long do_sys_open(int fdf, const char __user *filename, int flags, +extern long do_sys_open(int dfd, const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int); @@ -1655,6 +1787,7 @@ extern int bdev_read_only(struct block_device *); extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); +extern int sb_has_dirty_inodes(struct super_block *); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); @@ -1793,6 +1926,8 @@ extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long); +extern void get_filesystem(struct file_system_type *fs); +extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); extern struct super_block *user_get_super(dev_t); @@ -1813,8 +1948,12 @@ extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to); -extern int simple_commit_write(struct file *file, struct page *page, - unsigned offset, unsigned to); +extern int simple_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); +extern int simple_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); @@ -1952,7 +2091,8 @@ static inline void free_secdata(void *secdata) { } #endif /* CONFIG_SECURITY */ -int proc_nr_files(ctl_table *table, int write, struct file *filp, +struct ctl_table; +int proc_nr_files(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index dfc4e4f..2bd31fa 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -41,8 +41,9 @@ static inline void fsnotify_d_move(struct dentry *entry) */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const char *old_name, const char *new_name, - int isdir, struct inode *target, struct inode *source) + int isdir, struct inode *target, struct dentry *moved) { + struct inode *source = moved->d_inode; u32 cookie = inotify_get_cookie(); if (old_dir == new_dir) @@ -67,7 +68,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, if (source) { inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL); } - audit_inode_child(new_name, source, new_dir); + audit_inode_child(new_name, moved, new_dir); } /* @@ -98,7 +99,7 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) inode_dir_notify(inode, DN_CREATE); inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name, dentry->d_inode); - audit_inode_child(dentry->d_name.name, dentry->d_inode, inode); + audit_inode_child(dentry->d_name.name, dentry, inode); } /* @@ -109,7 +110,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) inode_dir_notify(inode, DN_CREATE); inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, dentry->d_name.name, dentry->d_inode); - audit_inode_child(dentry->d_name.name, dentry->d_inode, inode); + audit_inode_child(dentry->d_name.name, dentry, inode); } /* diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 9fbe9d2..d0c4370 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -6,7 +6,17 @@ See the file COPYING. */ -/* This file defines the kernel interface of FUSE */ +/* + * This file defines the kernel interface of FUSE + * + * Protocol changelog: + * + * 7.9: + * - new fuse_getattr_in input argument of GETATTR + * - add lk_flags in fuse_lk_in + * - add lock_owner field to fuse_setattr_in, fuse_read_in and fuse_write_in + * - add blksize field to fuse_attr + */ #include <asm/types.h> #include <linux/major.h> @@ -15,7 +25,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 8 +#define FUSE_KERNEL_MINOR_VERSION 9 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -44,6 +54,8 @@ struct fuse_attr { __u32 uid; __u32 gid; __u32 rdev; + __u32 blksize; + __u32 padding; }; struct fuse_kstatfs { @@ -76,6 +88,9 @@ struct fuse_file_lock { #define FATTR_ATIME (1 << 4) #define FATTR_MTIME (1 << 5) #define FATTR_FH (1 << 6) +#define FATTR_ATIME_NOW (1 << 7) +#define FATTR_MTIME_NOW (1 << 8) +#define FATTR_LOCKOWNER (1 << 9) /** * Flags returned by the OPEN request @@ -91,12 +106,38 @@ struct fuse_file_lock { */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) +#define FUSE_FILE_OPS (1 << 2) +#define FUSE_ATOMIC_O_TRUNC (1 << 3) /** * Release flags */ #define FUSE_RELEASE_FLUSH (1 << 0) +/** + * Getattr flags + */ +#define FUSE_GETATTR_FH (1 << 0) + +/** + * Lock flags + */ +#define FUSE_LK_FLOCK (1 << 0) + +/** + * WRITE flags + * + * FUSE_WRITE_CACHE: delayed write from page cache, file handle is guessed + * FUSE_WRITE_LOCKOWNER: lock_owner field is valid + */ +#define FUSE_WRITE_CACHE (1 << 0) +#define FUSE_WRITE_LOCKOWNER (1 << 1) + +/** + * Read flags + */ +#define FUSE_READ_LOCKOWNER (1 << 1) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -139,6 +180,8 @@ enum fuse_opcode { /* The read buffer is required to be at least 8k, but may be much larger */ #define FUSE_MIN_READ_BUFFER 8192 +#define FUSE_COMPAT_ENTRY_OUT_SIZE 120 + struct fuse_entry_out { __u64 nodeid; /* Inode ID */ __u64 generation; /* Inode generation: nodeid:gen must @@ -154,6 +197,14 @@ struct fuse_forget_in { __u64 nlookup; }; +struct fuse_getattr_in { + __u32 getattr_flags; + __u32 dummy; + __u64 fh; +}; + +#define FUSE_COMPAT_ATTR_OUT_SIZE 96 + struct fuse_attr_out { __u64 attr_valid; /* Cache timeout for the attributes */ __u32 attr_valid_nsec; @@ -184,7 +235,7 @@ struct fuse_setattr_in { __u32 padding; __u64 fh; __u64 size; - __u64 unused1; + __u64 lock_owner; __u64 atime; __u64 mtime; __u64 unused2; @@ -227,14 +278,18 @@ struct fuse_read_in { __u64 fh; __u64 offset; __u32 size; - __u32 padding; + __u32 read_flags; + __u64 lock_owner; }; +#define FUSE_COMPAT_WRITE_IN_SIZE 24 + struct fuse_write_in { __u64 fh; __u64 offset; __u32 size; __u32 write_flags; + __u64 lock_owner; }; struct fuse_write_out { @@ -273,6 +328,8 @@ struct fuse_lk_in { __u64 fh; __u64 owner; struct fuse_file_lock lk; + __u32 lk_flags; + __u32 padding; }; struct fuse_lk_out { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bc68dd9..7e93a9a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -48,18 +48,12 @@ struct vm_area_struct; #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */ #define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */ -#define __GFP_MOVABLE ((__force gfp_t)0x80000u) /* Page is movable */ +#define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */ +#define __GFP_MOVABLE ((__force gfp_t)0x100000u) /* Page is movable */ -#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 21 /* Room for 21 __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -/* if you forget to add the bitmask here kernel will crash, period */ -#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ - __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \ - __GFP_NOFAIL|__GFP_NORETRY|__GFP_COMP| \ - __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE| \ - __GFP_MOVABLE) - /* This equals 0, but use constants in case they ever change */ #define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) /* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */ @@ -67,6 +61,8 @@ struct vm_area_struct; #define GFP_NOIO (__GFP_WAIT) #define GFP_NOFS (__GFP_WAIT | __GFP_IO) #define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) +#define GFP_TEMPORARY (__GFP_WAIT | __GFP_IO | __GFP_FS | \ + __GFP_RECLAIMABLE) #define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \ __GFP_HIGHMEM) @@ -86,6 +82,19 @@ struct vm_area_struct; #define GFP_THISNODE ((__force gfp_t)0) #endif +/* This mask makes up all the page movable related flags */ +#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) + +/* Control page allocator reclaim behavior */ +#define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\ + __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ + __GFP_NORETRY|__GFP_NOMEMALLOC) + +/* Control allocation constraints */ +#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) + +/* Do not use these with a slab allocator */ +#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* Flag - indicates that the buffer will be suitable for DMA. Ignored on some platforms, used as appropriate on others */ @@ -95,25 +104,50 @@ struct vm_area_struct; /* 4GB DMA on some platforms */ #define GFP_DMA32 __GFP_DMA32 +/* Convert GFP flags to their corresponding migrate type */ +static inline int allocflags_to_migratetype(gfp_t gfp_flags) +{ + WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); + + if (unlikely(page_group_by_mobility_disabled)) + return MIGRATE_UNMOVABLE; + + /* Group based on mobility */ + return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) | + ((gfp_flags & __GFP_RECLAIMABLE) != 0); +} static inline enum zone_type gfp_zone(gfp_t flags) { + int base = 0; + +#ifdef CONFIG_NUMA + if (flags & __GFP_THISNODE) + base = MAX_NR_ZONES; +#endif + #ifdef CONFIG_ZONE_DMA if (flags & __GFP_DMA) - return ZONE_DMA; + return base + ZONE_DMA; #endif #ifdef CONFIG_ZONE_DMA32 if (flags & __GFP_DMA32) - return ZONE_DMA32; + return base + ZONE_DMA32; #endif if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) == (__GFP_HIGHMEM | __GFP_MOVABLE)) - return ZONE_MOVABLE; + return base + ZONE_MOVABLE; #ifdef CONFIG_HIGHMEM if (flags & __GFP_HIGHMEM) - return ZONE_HIGHMEM; + return base + ZONE_HIGHMEM; #endif - return ZONE_NORMAL; + return base + ZONE_NORMAL; +} + +static inline gfp_t set_migrateflags(gfp_t gfp, gfp_t migrate_flags) +{ + BUG_ON((gfp & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); + return (gfp & ~(GFP_MOVABLE_MASK)) | migrate_flags; } /* diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index 265d178..c6d3a9d 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -8,6 +8,7 @@ struct gpio_keys_button { int active_low; char *desc; int type; /* input event type (EV_KEY, EV_SW) */ + int wakeup; /* configure the button as a wake-up source */ }; struct gpio_keys_platform_data { diff --git a/include/linux/hid.h b/include/linux/hid.h index 55e51f9..6e35b92 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -29,13 +29,6 @@ * Vojtech Pavlik, Simunkova 1594, Prague 8, 182 00 Czech Republic */ -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/list.h> -#include <linux/timer.h> -#include <linux/workqueue.h> -#include <linux/input.h> - /* * USB HID (Human Interface Device) interface class code */ @@ -69,6 +62,17 @@ #define HID_DT_REPORT (USB_TYPE_CLASS | 0x02) #define HID_DT_PHYSICAL (USB_TYPE_CLASS | 0x03) +#define HID_MAX_DESCRIPTOR_SIZE 4096 + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/timer.h> +#include <linux/workqueue.h> +#include <linux/input.h> + /* * We parse each description item into this structure. Short items data * values are expanded to 32-bit signed int, long items contain a pointer @@ -311,7 +315,6 @@ struct hid_global { * This is the local environment. It is persistent up the next main-item. */ -#define HID_MAX_DESCRIPTOR_SIZE 4096 #define HID_MAX_USAGES 8192 #define HID_DEFAULT_NUM_COLLECTIONS 16 @@ -466,8 +469,8 @@ struct hid_device { /* device report descriptor */ /* handler for raw output data, used by hidraw */ int (*hid_output_raw_report) (struct hid_device *, __u8 *, size_t); #ifdef CONFIG_USB_HIDINPUT_POWERBOOK - unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; - unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; + unsigned long pb_pressed_fn[BITS_TO_LONGS(KEY_CNT)]; + unsigned long pb_pressed_numlock[BITS_TO_LONGS(KEY_CNT)]; #endif }; @@ -560,4 +563,5 @@ static inline int hid_ff_init(struct hid_device *hid) { return -1; } #define err_hid(format, arg...) printk(KERN_ERR "%s: " format "\n" , \ __FILE__ , ## arg) #endif +#endif diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h index 6676cd5..0536f29 100644 --- a/include/linux/hidraw.h +++ b/include/linux/hidraw.h @@ -15,9 +15,11 @@ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/hid.h> + struct hidraw_report_descriptor { __u32 size; - __u8 *value; + __u8 value[HID_MAX_DESCRIPTOR_SIZE]; }; struct hidraw_devinfo { @@ -40,8 +42,6 @@ struct hidraw_devinfo { /* kernel-only API declarations */ #ifdef __KERNEL__ -#include <linux/hid.h> - struct hidraw { unsigned int minor; int exist; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 540799b..7a9398e 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -300,7 +300,7 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /* Precise sleep: */ extern long hrtimer_nanosleep(struct timespec *rqtp, - struct timespec __user *rmtp, + struct timespec *rmtp, const enum hrtimer_mode mode, const clockid_t clockid); extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a19b03..ea0f50b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -33,6 +33,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; extern unsigned long hugepages_treat_as_movable; +extern int hugetlb_dynamic_pool; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index a271b67..88c8140 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -120,6 +120,7 @@ #define I2C_DRIVERID_WM8753 91 /* Wolfson WM8753 audio codec */ #define I2C_DRIVERID_LM4857 92 /* LM4857 Audio Amplifier */ #define I2C_DRIVERID_VP27SMPX 93 /* Panasonic VP27s tuner internal MPX */ +#define I2C_DRIVERID_CS4270 94 /* Cirrus Logic 4270 audio codec */ #define I2C_DRIVERID_I2CDEV 900 #define I2C_DRIVERID_ARP 902 /* SMBus ARP Client */ diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 9752307..7da5b98 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -32,6 +32,7 @@ #include <linux/workqueue.h> /* work_struct */ #include <linux/mempool.h> #include <linux/mutex.h> +#include <linux/scatterlist.h> #include <asm/io.h> #include <asm/semaphore.h> /* Needed for MUTEX init macros */ @@ -837,7 +838,7 @@ static inline int i2o_dma_map_sg(struct i2o_controller *c, if ((sizeof(dma_addr_t) > 4) && c->pae_support) *mptr++ = cpu_to_le32(i2o_dma_high(sg_dma_address(sg))); #endif - sg++; + sg = sg_next(sg); } *sg_ptr = mptr; diff --git a/include/linux/i8042.h b/include/linux/i8042.h new file mode 100644 index 0000000..7907a72 --- /dev/null +++ b/include/linux/i8042.h @@ -0,0 +1,35 @@ +#ifndef _LINUX_I8042_H +#define _LINUX_I8042_H + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + + +/* + * Standard commands. + */ + +#define I8042_CMD_CTL_RCTR 0x0120 +#define I8042_CMD_CTL_WCTR 0x1060 +#define I8042_CMD_CTL_TEST 0x01aa + +#define I8042_CMD_KBD_DISABLE 0x00ad +#define I8042_CMD_KBD_ENABLE 0x00ae +#define I8042_CMD_KBD_TEST 0x01ab +#define I8042_CMD_KBD_LOOP 0x11d2 + +#define I8042_CMD_AUX_DISABLE 0x00a7 +#define I8042_CMD_AUX_ENABLE 0x00a8 +#define I8042_CMD_AUX_TEST 0x01a9 +#define I8042_CMD_AUX_SEND 0x10d4 +#define I8042_CMD_AUX_LOOP 0x11d3 + +#define I8042_CMD_MUX_PFX 0x0090 +#define I8042_CMD_MUX_SEND 0x1090 + +int i8042_command(unsigned char *param, int command); + +#endif diff --git a/include/linux/ide.h b/include/linux/ide.h index 02a27e8..4ed4777 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -192,22 +192,20 @@ typedef unsigned char byte; /* used everywhere */ struct hwif_s; typedef int (ide_ack_intr_t)(struct hwif_s *); -#ifndef NO_DMA -#define NO_DMA 255 -#endif - /* * hwif_chipset_t is used to keep track of the specific hardware * chipset used by each IDE interface, if known. */ -typedef enum { ide_unknown, ide_generic, ide_pci, +enum { ide_unknown, ide_generic, ide_pci, ide_cmd640, ide_dtc2278, ide_ali14xx, ide_qd65xx, ide_umc8672, ide_ht6560b, ide_rz1000, ide_trm290, ide_cmd646, ide_cy82c693, ide_4drives, ide_pmac, ide_etrax100, ide_acorn, ide_au1xxx, ide_forced -} hwif_chipset_t; +}; + +typedef u8 hwif_chipset_t; /* * Structure to hold all information about the location of this port @@ -215,22 +213,16 @@ typedef enum { ide_unknown, ide_generic, ide_pci, typedef struct hw_regs_s { unsigned long io_ports[IDE_NR_PORTS]; /* task file registers */ int irq; /* our irq number */ - int dma; /* our dma entry */ ide_ack_intr_t *ack_intr; /* acknowledge interrupt */ hwif_chipset_t chipset; struct device *dev; } hw_regs_t; -/* - * Register new hardware with ide - */ -int ide_register_hw(hw_regs_t *, int, struct hwif_s **); -int ide_register_hw_with_fixup(hw_regs_t *, int, struct hwif_s **, - void (*)(struct hwif_s *)); +struct hwif_s * ide_find_port(unsigned long); + +int ide_register_hw(hw_regs_t *, void (*)(struct hwif_s *), int, + struct hwif_s **); -/* - * Set up hw_regs_t structure before calling ide_register_hw (optional) - */ void ide_setup_ports( hw_regs_t *hw, unsigned long base, int *offsets, @@ -268,11 +260,7 @@ static inline void ide_std_init_ports(hw_regs_t *hw, # define ide_init_default_irq(base) (0) #endif -/* - * ide_init_hwif_ports() is OBSOLETE and will be removed in 2.7 series. - * New ports shouldn't define IDE_ARCH_OBSOLETE_INIT in <asm/ide.h>. - */ -#ifdef IDE_ARCH_OBSOLETE_INIT +#ifdef CONFIG_IDE_ARCH_OBSOLETE_INIT static inline void ide_init_hwif_ports(hw_regs_t *hw, unsigned long io_addr, unsigned long ctl_addr, @@ -302,7 +290,7 @@ static inline void ide_init_hwif_ports(hw_regs_t *hw, if (io_addr || ctl_addr) printk(KERN_WARNING "%s: must not be called\n", __FUNCTION__); } -#endif /* IDE_ARCH_OBSOLETE_INIT */ +#endif /* CONFIG_IDE_ARCH_OBSOLETE_INIT */ /* Currently only m68k, apus and m8xx need it */ #ifndef IDE_ARCH_ACK_INTR @@ -363,7 +351,6 @@ typedef union { * ATA DATA Register Special. * ATA NSECTOR Count Register(). * ATAPI Byte Count Register. - * Channel index ordering pairs. */ typedef union { unsigned all :16; @@ -378,7 +365,7 @@ typedef union { #error "Please fix <asm/byteorder.h>" #endif } b; -} ata_nsector_t, ata_data_t, atapi_bcount_t, ata_index_t; +} ata_nsector_t, ata_data_t, atapi_bcount_t; /* * ATA-IDE Select Register, aka Device-Head @@ -576,7 +563,6 @@ typedef struct ide_drive_s { select_t select; /* basic drive/head select reg value */ u8 keep_settings; /* restore settings after drive reset */ - u8 autodma; /* device can safely use dma on host */ u8 using_dma; /* disk is using dma for read/write */ u8 retry_pio; /* retrying dma capable host in pio */ u8 state; /* retry state */ @@ -600,6 +586,7 @@ typedef struct ide_drive_s { unsigned nice0 : 1; /* give obvious excess bandwidth */ unsigned nice2 : 1; /* give a share in our own bandwidth */ unsigned doorlocking : 1; /* for removable only: door lock/unlock works */ + unsigned nodma : 1; /* disallow DMA */ unsigned autotune : 2; /* 0=default, 1=autotune, 2=noautotune */ unsigned remap_0_to_1 : 1; /* 0=noremap, 1=remap 0->1 (for EZDrive) */ unsigned blocked : 1; /* 1=powermanagment told us not to do anything, so sleep nicely */ @@ -657,7 +644,7 @@ typedef struct ide_drive_s { ((1<<ide_pci)|(1<<ide_cmd646)|(1<<ide_ali14xx)) #define IDE_CHIPSET_IS_PCI(c) ((IDE_CHIPSET_PCI_MASK >> (c)) & 1) -struct ide_pci_device_s; +struct ide_port_info; typedef struct hwif_s { struct hwif_s *next; /* for linked-list in ide_hwgroup_t */ @@ -672,7 +659,6 @@ typedef struct hwif_s { unsigned long sata_scr[SATA_NR_PORTS]; unsigned long sata_misc[SATA_NR_PORTS]; - hw_regs_t hw; /* Hardware info */ ide_drive_t drives[MAX_DRIVES]; /* drive info */ u8 major; /* our major number */ @@ -681,11 +667,10 @@ typedef struct hwif_s { u8 straight8; /* Alan's straight 8 check */ u8 bus_state; /* power state of the IDE bus */ - u16 host_flags; + u32 host_flags; u8 pio_mask; - u8 atapi_dma; /* host supports atapi_dma */ u8 ultra_mask; u8 mwdma_mask; u8 swdma_mask; @@ -695,7 +680,9 @@ typedef struct hwif_s { hwif_chipset_t chipset; /* sub-module for tuning.. */ struct pci_dev *pci_dev; /* for pci chipsets */ - struct ide_pci_device_s *cds; /* chipset device struct */ + const struct ide_port_info *cds; /* chipset device struct */ + + ide_ack_intr_t *ack_intr; void (*rw_disk)(ide_drive_t *, struct request *); @@ -726,6 +713,8 @@ typedef struct hwif_s { u8 (*mdma_filter)(ide_drive_t *); u8 (*udma_filter)(ide_drive_t *); + void (*fixup)(struct hwif_s *); + void (*ata_input_data)(ide_drive_t *, void *, u32); void (*ata_output_data)(ide_drive_t *, void *, u32); @@ -736,7 +725,6 @@ typedef struct hwif_s { void (*dma_exec_cmd)(ide_drive_t *, u8); void (*dma_start)(ide_drive_t *); int (*ide_dma_end)(ide_drive_t *drive); - int (*ide_dma_check)(ide_drive_t *drive); int (*ide_dma_on)(ide_drive_t *drive); void (*dma_off_quietly)(ide_drive_t *drive); int (*ide_dma_test_irq)(ide_drive_t *drive); @@ -772,7 +760,7 @@ typedef struct hwif_s { unsigned int nsect; unsigned int nleft; - unsigned int cursg; + struct scatterlist *cursg; unsigned int cursg_ofs; int rqsize; /* max sectors per request */ @@ -798,13 +786,9 @@ typedef struct hwif_s { unsigned serialized : 1; /* serialized all channel operation */ unsigned sharing_irq: 1; /* 1 = sharing irq with another hwif */ unsigned reset : 1; /* reset after probe */ - unsigned autodma : 1; /* auto-attempt using DMA at boot */ - unsigned no_lba48 : 1; /* 1 = cannot do LBA48 */ - unsigned no_lba48_dma : 1; /* 1 = cannot do LBA48 DMA */ unsigned auto_poll : 1; /* supports nop auto-poll */ unsigned sg_mapped : 1; /* sg_table and sg_nents are ready */ unsigned no_io_32bit : 1; /* 1 = can not do 32-bit IO ops */ - unsigned err_stops_fifo : 1; /* 1=data FIFO is cleared by an error */ unsigned mmio : 1; /* host uses MMIO */ struct device gendev; @@ -847,8 +831,6 @@ typedef struct hwgroup_s { /* for pci chipsets */ struct pci_dev *pci_dev; - /* chipset device struct */ - struct ide_pci_device_s *cds; /* current request */ struct request *rq; @@ -1036,36 +1018,16 @@ extern int ide_end_request (ide_drive_t *drive, int uptodate, int nrsecs); int ide_end_dequeued_request(ide_drive_t *drive, struct request *rq, int uptodate, int nr_sectors); -/* - * This is used on exit from the driver to designate the next irq handler - * and also to start the safety timer. - */ extern void ide_set_handler (ide_drive_t *drive, ide_handler_t *handler, unsigned int timeout, ide_expiry_t *expiry); -/* - * This is used on exit from the driver to designate the next irq handler - * and start the safety time safely and atomically from the IRQ handler - * with respect to the command issue (which it also does) - */ extern void ide_execute_command(ide_drive_t *, task_ioreg_t cmd, ide_handler_t *, unsigned int, ide_expiry_t *); ide_startstop_t __ide_error(ide_drive_t *, struct request *, u8, u8); -/* - * ide_error() takes action based on the error returned by the controller. - * The caller should return immediately after invoking this. - * - * (drive, msg, status) - */ ide_startstop_t ide_error (ide_drive_t *drive, const char *msg, byte stat); ide_startstop_t __ide_abort(ide_drive_t *, struct request *); -/* - * Abort a running command on the controller triggering the abort - * from a host side, non error situation - * (drive, msg) - */ extern ide_startstop_t ide_abort(ide_drive_t *, const char *); extern void ide_fix_driveid(struct hd_driveid *); @@ -1081,23 +1043,11 @@ extern void ide_fixstring(u8 *, const int, const int); int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); -/* - * Start a reset operation for an IDE interface. - * The caller should return immediately after invoking this. - */ extern ide_startstop_t ide_do_reset (ide_drive_t *); -/* - * This function is intended to be used prior to invoking ide_do_drive_cmd(). - */ extern void ide_init_drive_cmd (struct request *rq); /* - * this function returns error location sector offset in case of a write error - */ -extern u64 ide_get_error_location(ide_drive_t *, char *); - -/* * "action" parameter type for ide_do_drive_cmd() below. */ typedef enum { @@ -1109,13 +1059,6 @@ typedef enum { extern int ide_do_drive_cmd(ide_drive_t *, struct request *, ide_action_t); -/* - * Clean up after success/failure of an explicit drive cmd. - * stat/err are used only when (HWGROUP(drive)->rq->cmd == IDE_DRIVE_CMD). - * stat/err are used only when (HWGROUP(drive)->rq->cmd == IDE_DRIVE_TASK_MASK). - * - * (ide_drive_t *drive, u8 stat, u8 err) - */ extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); /* @@ -1188,10 +1131,6 @@ extern int taskfile_lib_get_identify(ide_drive_t *drive, u8 *); extern int ide_wait_not_busy(ide_hwif_t *hwif, unsigned long timeout); -/* - * ide_stall_queue() can be used by a drive to give excess bandwidth back - * to the hwgroup by sleeping for timeout jiffies. - */ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern int ide_spin_wait_hwgroup(ide_drive_t *); @@ -1211,26 +1150,13 @@ extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *o #define ide_pci_register_driver(d) pci_register_driver(d) #endif -void ide_pci_setup_ports(struct pci_dev *, struct ide_pci_device_s *, int, ata_index_t *); -extern void ide_setup_pci_noise (struct pci_dev *dev, struct ide_pci_device_s *d); +void ide_pci_setup_ports(struct pci_dev *, const struct ide_port_info *, int, u8 *); +void ide_setup_pci_noise(struct pci_dev *, const struct ide_port_info *); extern void default_hwif_iops(ide_hwif_t *); extern void default_hwif_mmiops(ide_hwif_t *); extern void default_hwif_transport(ide_hwif_t *); -#define ON_BOARD 1 -#define NEVER_BOARD 0 - -#ifdef CONFIG_BLK_DEV_OFFBOARD -# define OFF_BOARD ON_BOARD -#else /* CONFIG_BLK_DEV_OFFBOARD */ -# define OFF_BOARD NEVER_BOARD -#endif /* CONFIG_BLK_DEV_OFFBOARD */ - -#define NODMA 0 -#define NOAUTODMA 1 -#define AUTODMA 2 - typedef struct ide_pci_enablebit_s { u8 reg; /* byte pci reg holding the enable-bit */ u8 mask; /* mask to isolate the enable-bit */ @@ -1261,29 +1187,65 @@ enum { IDE_HFLAG_POST_SET_MODE = (1 << 8), /* don't program host/device for the transfer mode ("smart" hosts) */ IDE_HFLAG_NO_SET_MODE = (1 << 9), + /* trust BIOS for programming chipset/device for DMA */ + IDE_HFLAG_TRUST_BIOS_FOR_DMA = (1 << 10), + /* host uses VDMA */ + IDE_HFLAG_VDMA = (1 << 11), + /* ATAPI DMA is unsupported */ + IDE_HFLAG_NO_ATAPI_DMA = (1 << 12), + /* set if host is a "bootable" controller */ + IDE_HFLAG_BOOTABLE = (1 << 13), + /* host doesn't support DMA */ + IDE_HFLAG_NO_DMA = (1 << 14), + /* check if host is PCI IDE device before allowing DMA */ + IDE_HFLAG_NO_AUTODMA = (1 << 15), + /* host is CS5510/CS5520 */ + IDE_HFLAG_CS5520 = (1 << 16), + /* no LBA48 */ + IDE_HFLAG_NO_LBA48 = (1 << 17), + /* no LBA48 DMA */ + IDE_HFLAG_NO_LBA48_DMA = (1 << 18), + /* data FIFO is cleared by an error */ + IDE_HFLAG_ERROR_STOPS_FIFO = (1 << 19), + /* serialize ports */ + IDE_HFLAG_SERIALIZE = (1 << 20), + /* use legacy IRQs */ + IDE_HFLAG_LEGACY_IRQS = (1 << 21), + /* force use of legacy IRQs */ + IDE_HFLAG_FORCE_LEGACY_IRQS = (1 << 22), + /* limit LBA48 requests to 256 sectors */ + IDE_HFLAG_RQSIZE_256 = (1 << 23), + /* use 32-bit I/O ops */ + IDE_HFLAG_IO_32BIT = (1 << 24), + /* unmask IRQs */ + IDE_HFLAG_UNMASK_IRQS = (1 << 25), }; -typedef struct ide_pci_device_s { +#ifdef CONFIG_BLK_DEV_OFFBOARD +# define IDE_HFLAG_OFF_BOARD IDE_HFLAG_BOOTABLE +#else +# define IDE_HFLAG_OFF_BOARD 0 +#endif + +struct ide_port_info { char *name; - int (*init_setup)(struct pci_dev *, struct ide_pci_device_s *); - void (*init_setup_dma)(struct pci_dev *, struct ide_pci_device_s *, ide_hwif_t *); unsigned int (*init_chipset)(struct pci_dev *, const char *); void (*init_iops)(ide_hwif_t *); void (*init_hwif)(ide_hwif_t *); void (*init_dma)(ide_hwif_t *, unsigned long); void (*fixup)(ide_hwif_t *); - u8 autodma; ide_pci_enablebit_t enablebits[2]; - u8 bootable; + hwif_chipset_t chipset; unsigned int extra; - struct ide_pci_device_s *next; - u16 host_flags; + u32 host_flags; u8 pio_mask; + u8 swdma_mask; + u8 mwdma_mask; u8 udma_mask; -} ide_pci_device_t; +}; -extern int ide_setup_pci_device(struct pci_dev *, ide_pci_device_t *); -extern int ide_setup_pci_devices(struct pci_dev *, struct pci_dev *, ide_pci_device_t *); +int ide_setup_pci_device(struct pci_dev *, const struct ide_port_info *); +int ide_setup_pci_devices(struct pci_dev *, struct pci_dev *, const struct ide_port_info *); void ide_map_sg(ide_drive_t *, struct request *); void ide_init_sg_cmd(ide_drive_t *, struct request *); @@ -1308,7 +1270,6 @@ static inline u8 ide_max_dma_mode(ide_drive_t *drive) return ide_find_dma_mode(drive, XFER_UDMA_6); } -int ide_tune_dma(ide_drive_t *); void ide_dma_off(ide_drive_t *); void ide_dma_verbose(ide_drive_t *); int ide_set_dma(ide_drive_t *); @@ -1335,7 +1296,6 @@ extern void ide_dma_timeout(ide_drive_t *); #else static inline u8 ide_find_dma_mode(ide_drive_t *drive, u8 speed) { return 0; } static inline u8 ide_max_dma_mode(ide_drive_t *drive) { return 0; } -static inline int ide_tune_dma(ide_drive_t *drive) { return 0; } static inline void ide_dma_off(ide_drive_t *drive) { ; } static inline void ide_dma_verbose(ide_drive_t *drive) { ; } static inline int ide_set_dma(ide_drive_t *drive) { return 1; } @@ -1368,8 +1328,7 @@ void ide_unregister_region(struct gendisk *); void ide_undecoded_slave(ide_hwif_t *); -int probe_hwif_init_with_fixup(ide_hwif_t *, void (*)(ide_hwif_t *)); -extern int probe_hwif_init(ide_hwif_t *); +int ide_device_add(u8 idx[4]); static inline void *ide_get_hwifdata (ide_hwif_t * hwif) { @@ -1385,7 +1344,6 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data) extern char *ide_xfer_verbose(u8 xfer_rate); extern void ide_toggle_bounce(ide_drive_t *drive, int on); extern int ide_set_xfer_rate(ide_drive_t *drive, u8 rate); -int ide_use_fast_pio(ide_drive_t *); static inline int ide_dev_has_iordy(struct hd_driveid *id) { @@ -1460,4 +1418,11 @@ static inline int hwif_to_node(ide_hwif_t *hwif) return dev ? pcibus_to_node(dev->bus) : -1; } +static inline ide_drive_t *ide_get_paired_drive(ide_drive_t *drive) +{ + ide_hwif_t *hwif = HWIF(drive); + + return &hwif->drives[(drive->dn ^ 1) & 1]; +} + #endif /* _IDE_H */ diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 99e3a1a..58e43e5 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -107,7 +107,7 @@ struct __fdb_entry extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb); -extern int (*br_should_route_hook)(struct sk_buff **pskb); +extern int (*br_should_route_hook)(struct sk_buff *skb); #endif diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h index 4aba6b0..ae77dae 100644 --- a/include/linux/if_fddi.h +++ b/include/linux/if_fddi.h @@ -24,6 +24,8 @@ #ifndef _LINUX_IF_FDDI_H #define _LINUX_IF_FDDI_H +#include <linux/types.h> + /* * Define max and min legal sizes. The frame sizes do not include * 4 byte FCS/CRC (frame check sequence). diff --git a/include/linux/init.h b/include/linux/init.h index f8d9d0b..5141381 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -67,8 +67,10 @@ /* For assembly routines */ #define __INIT .section ".init.text","ax" +#define __INIT_REFOK .section ".text.init.refok","ax" #define __FINIT .previous #define __INITDATA .section ".init.data","aw" +#define __INITDATA_REFOK .section ".data.init.refok","aw" #ifndef __ASSEMBLY__ /* @@ -159,7 +161,7 @@ struct obs_kernel_param { * obs_kernel_param "array" too far apart in .init.setup. */ #define __setup_param(str, unique_id, fn, early) \ - static char __setup_str_##unique_id[] __initdata = str; \ + static char __setup_str_##unique_id[] __initdata __aligned(1) = str; \ static struct obs_kernel_param __setup_##unique_id \ __attribute_used__ \ __attribute__((__section__(".init.setup"))) \ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 513bc3e..cae35b6 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -67,16 +67,12 @@ .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ - .pgrp = 0, \ - .tty_old_pgrp = NULL, \ - { .__session = 0}, \ } extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ .pid_ns = &init_pid_ns, \ .count = ATOMIC_INIT(1), \ - .nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \ .uts_ns = &init_uts_ns, \ .mnt_ns = NULL, \ INIT_NET_NS(net_ns) \ @@ -95,15 +91,18 @@ extern struct group_info init_groups; #define INIT_STRUCT_PID { \ .count = ATOMIC_INIT(1), \ - .nr = 0, \ - /* Don't put this struct pid in pid_hash */ \ - .pid_chain = { .next = NULL, .pprev = NULL }, \ .tasks = { \ { .first = &init_task.pids[PIDTYPE_PID].node }, \ { .first = &init_task.pids[PIDTYPE_PGID].node }, \ { .first = &init_task.pids[PIDTYPE_SID].node }, \ }, \ .rcu = RCU_HEAD_INIT, \ + .level = 0, \ + .numbers = { { \ + .nr = 0, \ + .ns = &init_pid_ns, \ + .pid_chain = { .next = NULL, .pprev = NULL }, \ + }, } \ } #define INIT_PID_LINK(type) \ @@ -171,6 +170,7 @@ extern struct group_info init_groups; [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ }, \ + .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ INIT_TRACE_IRQFLAGS \ INIT_LOCKDEP \ } diff --git a/include/linux/inotify.h b/include/linux/inotify.h index d4f48c6..742b917 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -120,6 +120,8 @@ extern __s32 inotify_find_update_watch(struct inotify_handle *, struct inode *, u32); extern __s32 inotify_add_watch(struct inotify_handle *, struct inotify_watch *, struct inode *, __u32); +extern __s32 inotify_clone_watch(struct inotify_watch *, struct inotify_watch *); +extern void inotify_evict_watch(struct inotify_watch *); extern int inotify_rm_watch(struct inotify_handle *, struct inotify_watch *); extern int inotify_rm_wd(struct inotify_handle *, __u32); extern void inotify_remove_watch_locked(struct inotify_handle *, diff --git a/include/linux/input.h b/include/linux/input.h index 52d1bd4..6226892 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -98,6 +98,7 @@ struct input_absinfo { #define EV_PWR 0x16 #define EV_FF_STATUS 0x17 #define EV_MAX 0x1f +#define EV_CNT (EV_MAX+1) /* * Synchronization events. @@ -567,6 +568,7 @@ struct input_absinfo { /* We avoid low common keys in module aliases so they don't get huge. */ #define KEY_MIN_INTERESTING KEY_MUTE #define KEY_MAX 0x1ff +#define KEY_CNT (KEY_MAX+1) /* * Relative axes @@ -583,6 +585,7 @@ struct input_absinfo { #define REL_WHEEL 0x08 #define REL_MISC 0x09 #define REL_MAX 0x0f +#define REL_CNT (REL_MAX+1) /* * Absolute axes @@ -615,6 +618,7 @@ struct input_absinfo { #define ABS_VOLUME 0x20 #define ABS_MISC 0x28 #define ABS_MAX 0x3f +#define ABS_CNT (ABS_MAX+1) /* * Switch events @@ -625,6 +629,7 @@ struct input_absinfo { #define SW_HEADPHONE_INSERT 0x02 /* set = inserted */ #define SW_RADIO 0x03 /* set = radio enabled */ #define SW_MAX 0x0f +#define SW_CNT (SW_MAX+1) /* * Misc events @@ -636,6 +641,7 @@ struct input_absinfo { #define MSC_RAW 0x03 #define MSC_SCAN 0x04 #define MSC_MAX 0x07 +#define MSC_CNT (MSC_MAX+1) /* * LEDs @@ -653,6 +659,7 @@ struct input_absinfo { #define LED_MAIL 0x09 #define LED_CHARGING 0x0a #define LED_MAX 0x0f +#define LED_CNT (LED_MAX+1) /* * Autorepeat values @@ -670,6 +677,7 @@ struct input_absinfo { #define SND_BELL 0x01 #define SND_TONE 0x02 #define SND_MAX 0x07 +#define SND_CNT (SND_MAX+1) /* * IDs. @@ -856,7 +864,7 @@ struct ff_rumble_effect { * defining effect parameters * * This structure is sent through ioctl from the application to the driver. - * To create a new effect aplication should set its @id to -1; the kernel + * To create a new effect application should set its @id to -1; the kernel * will return assigned @id which can later be used to update or delete * this effect. * @@ -920,6 +928,7 @@ struct ff_effect { #define FF_AUTOCENTER 0x61 #define FF_MAX 0x7f +#define FF_CNT (FF_MAX+1) #ifdef __KERNEL__ @@ -932,28 +941,99 @@ struct ff_effect { #include <linux/timer.h> #include <linux/mod_devicetable.h> -#define NBITS(x) (((x)/BITS_PER_LONG)+1) -#define BIT(x) (1UL<<((x)%BITS_PER_LONG)) -#define LONG(x) ((x)/BITS_PER_LONG) - +/** + * struct input_dev - represents an input device + * @name: name of the device + * @phys: physical path to the device in the system hierarchy + * @uniq: unique identification code for the device (if device has it) + * @id: id of the device (struct input_id) + * @evbit: bitmap of types of events supported by the device (EV_KEY, + * EV_REL, etc.) + * @keybit: bitmap of keys/buttons this device has + * @relbit: bitmap of relative axes for the device + * @absbit: bitmap of absolute axes for the device + * @mscbit: bitmap of miscellaneous events supported by the device + * @ledbit: bitmap of leds present on the device + * @sndbit: bitmap of sound effects supported by the device + * @ffbit: bitmap of force feedback effects supported by the device + * @swbit: bitmap of switches present on the device + * @keycodemax: size of keycode table + * @keycodesize: size of elements in keycode table + * @keycode: map of scancodes to keycodes for this device + * @setkeycode: optional method to alter current keymap, used to implement + * sparse keymaps. If not supplied default mechanism will be used + * @getkeycode: optional method to retrieve current keymap. If not supplied + * default mechanism will be used + * @ff: force feedback structure associated with the device if device + * supports force feedback effects + * @repeat_key: stores key code of the last key pressed; used to implement + * software autorepeat + * @timer: timer for software autorepeat + * @sync: set to 1 when there were no new events since last EV_SYNC + * @abs: current values for reports from absolute axes + * @rep: current values for autorepeat parameters (delay, rate) + * @key: reflects current state of device's keys/buttons + * @led: reflects current state of device's LEDs + * @snd: reflects current state of sound effects + * @sw: reflects current state of device's switches + * @absmax: maximum values for events coming from absolute axes + * @absmin: minimum values for events coming from absolute axes + * @absfuzz: describes noisiness for axes + * @absflat: size of the center flat position (used by joydev) + * @open: this method is called when the very first user calls + * input_open_device(). The driver must prepare the device + * to start generating events (start polling thread, + * request an IRQ, submit URB, etc.) + * @close: this method is called when the very last user calls + * input_close_device(). + * @flush: purges the device. Most commonly used to get rid of force + * feedback effects loaded into the device when disconnecting + * from it + * @event: event handler for events sent _to_ the device, like EV_LED + * or EV_SND. The device is expected to carry out the requested + * action (turn on a LED, play sound, etc.) The call is protected + * by @event_lock and must not sleep + * @grab: input handle that currently has the device grabbed (via + * EVIOCGRAB ioctl). When a handle grabs a device it becomes sole + * recipient for all input events coming from the device + * @event_lock: this spinlock is is taken when input core receives + * and processes a new event for the device (in input_event()). + * Code that accesses and/or modifies parameters of a device + * (such as keymap or absmin, absmax, absfuzz, etc.) after device + * has been registered with input core must take this lock. + * @mutex: serializes calls to open(), close() and flush() methods + * @users: stores number of users (input handlers) that opened this + * device. It is used by input_open_device() and input_close_device() + * to make sure that dev->open() is only called when the first + * user opens device and dev->close() is called when the very + * last user closes the device + * @going_away: marks devices that are in a middle of unregistering and + * causes input_open_device*() fail with -ENODEV. + * @dev: driver model's view of this device + * @cdev: union for struct device pointer + * @h_list: list of input handles associated with the device. When + * accessing the list dev->mutex must be held + * @node: used to place the device onto input_dev_list + */ struct input_dev { - - void *private; + /* private: */ + void *private; /* do not use */ + /* public: */ const char *name; const char *phys; const char *uniq; struct input_id id; - unsigned long evbit[NBITS(EV_MAX)]; - unsigned long keybit[NBITS(KEY_MAX)]; - unsigned long relbit[NBITS(REL_MAX)]; - unsigned long absbit[NBITS(ABS_MAX)]; - unsigned long mscbit[NBITS(MSC_MAX)]; - unsigned long ledbit[NBITS(LED_MAX)]; - unsigned long sndbit[NBITS(SND_MAX)]; - unsigned long ffbit[NBITS(FF_MAX)]; - unsigned long swbit[NBITS(SW_MAX)]; + unsigned long evbit[BITS_TO_LONGS(EV_CNT)]; + unsigned long keybit[BITS_TO_LONGS(KEY_CNT)]; + unsigned long relbit[BITS_TO_LONGS(REL_CNT)]; + unsigned long absbit[BITS_TO_LONGS(ABS_CNT)]; + unsigned long mscbit[BITS_TO_LONGS(MSC_CNT)]; + unsigned long ledbit[BITS_TO_LONGS(LED_CNT)]; + unsigned long sndbit[BITS_TO_LONGS(SND_CNT)]; + unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; + unsigned long swbit[BITS_TO_LONGS(SW_CNT)]; unsigned int keycodemax; unsigned int keycodesize; @@ -966,17 +1046,15 @@ struct input_dev { unsigned int repeat_key; struct timer_list timer; - int state; - int sync; int abs[ABS_MAX + 1]; int rep[REP_MAX + 1]; - unsigned long key[NBITS(KEY_MAX)]; - unsigned long led[NBITS(LED_MAX)]; - unsigned long snd[NBITS(SND_MAX)]; - unsigned long sw[NBITS(SW_MAX)]; + unsigned long key[BITS_TO_LONGS(KEY_CNT)]; + unsigned long led[BITS_TO_LONGS(LED_CNT)]; + unsigned long snd[BITS_TO_LONGS(SND_CNT)]; + unsigned long sw[BITS_TO_LONGS(SW_CNT)]; int absmax[ABS_MAX + 1]; int absmin[ABS_MAX + 1]; @@ -990,8 +1068,11 @@ struct input_dev { struct input_handle *grab; - struct mutex mutex; /* serializes open and close operations */ + spinlock_t event_lock; + struct mutex mutex; + unsigned int users; + int going_away; struct device dev; union { /* temporarily so while we switching to struct device */ @@ -1057,7 +1138,9 @@ struct input_handle; /** * struct input_handler - implements one of interfaces for input devices * @private: driver-specific data - * @event: event handler + * @event: event handler. This method is being called by input core with + * interrupts disabled and dev->event_lock spinlock held and so + * it may not sleep * @connect: called when attaching a handler to an input device * @disconnect: disconnects a handler from input device * @start: starts handler for given handle. This function is called by @@ -1069,10 +1152,18 @@ struct input_handle; * @name: name of the handler, to be shown in /proc/bus/input/handlers * @id_table: pointer to a table of input_device_ids this driver can * handle - * @blacklist: prointer to a table of input_device_ids this driver should + * @blacklist: pointer to a table of input_device_ids this driver should * ignore even if they match @id_table * @h_list: list of input handles associated with the handler * @node: for placing the driver onto input_handler_list + * + * Input handlers attach to input devices and create input handles. There + * are likely several handlers attached to any given input device at the + * same time. All of them will get their copy of input event generated by + * the device. + * + * Note that input core serializes calls to connect() and disconnect() + * methods. */ struct input_handler { @@ -1094,6 +1185,18 @@ struct input_handler { struct list_head node; }; +/** + * struct input_handle - links input device with an input handler + * @private: handler-specific data + * @open: counter showing whether the handle is 'open', i.e. should deliver + * events from its device + * @name: name given to the handle by handler that created it + * @dev: input device the handle is attached to + * @handler: handler that works with the device through this handle + * @d_node: used to put the handle on device's list of attached handles + * @h_node: used to put the handle on handler's list of handles from which + * it gets events + */ struct input_handle { void *private; @@ -1136,10 +1239,10 @@ static inline void input_set_drvdata(struct input_dev *dev, void *data) dev->private = data; } -int input_register_device(struct input_dev *); +int __must_check input_register_device(struct input_dev *); void input_unregister_device(struct input_dev *); -int input_register_handler(struct input_handler *); +int __must_check input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); int input_register_handle(struct input_handle *); @@ -1195,7 +1298,7 @@ static inline void input_set_abs_params(struct input_dev *dev, int axis, int min dev->absfuzz[axis] = fuzz; dev->absflat[axis] = flat; - dev->absbit[LONG(axis)] |= BIT(axis); + dev->absbit[BIT_WORD(axis)] |= BIT_MASK(axis); } extern struct class input_class; @@ -1216,7 +1319,7 @@ extern struct class input_class; * @max_effects: maximum number of effects supported by device * @effects: pointer to an array of effects currently loaded into device * @effect_owners: array of effect owners; when file handle owning - * an effect gets closed the effcet is automatically erased + * an effect gets closed the effect is automatically erased * * Every force-feedback device must implement upload() and playback() * methods; erase() is optional. set_gain() and set_autocenter() need @@ -1236,7 +1339,7 @@ struct ff_device { void *private; - unsigned long ffbit[NBITS(FF_MAX)]; + unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; struct mutex mutex; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5523f19..2306920 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -55,28 +55,6 @@ #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 -/* - * Migration helpers. Scheduled for removal in 9/2007 - * Do not use for new code ! - */ -static inline -unsigned long __deprecated deprecated_irq_flag(unsigned long flag) -{ - return flag; -} - -#define SA_INTERRUPT deprecated_irq_flag(IRQF_DISABLED) -#define SA_SAMPLE_RANDOM deprecated_irq_flag(IRQF_SAMPLE_RANDOM) -#define SA_SHIRQ deprecated_irq_flag(IRQF_SHARED) -#define SA_PROBEIRQ deprecated_irq_flag(IRQF_PROBE_SHARED) -#define SA_PERCPU deprecated_irq_flag(IRQF_PERCPU) - -#define SA_TRIGGER_LOW deprecated_irq_flag(IRQF_TRIGGER_LOW) -#define SA_TRIGGER_HIGH deprecated_irq_flag(IRQF_TRIGGER_HIGH) -#define SA_TRIGGER_FALLING deprecated_irq_flag(IRQF_TRIGGER_FALLING) -#define SA_TRIGGER_RISING deprecated_irq_flag(IRQF_TRIGGER_RISING) -#define SA_TRIGGER_MASK deprecated_irq_flag(IRQF_TRIGGER_MASK) - typedef irqreturn_t (*irq_handler_t)(int, void *); struct irqaction { @@ -205,6 +183,15 @@ static inline int disable_irq_wake(unsigned int irq) enable_irq(irq) # endif +static inline int enable_irq_wake(unsigned int irq) +{ + return 0; +} + +static inline int disable_irq_wake(unsigned int irq) +{ + return 0; +} #endif /* CONFIG_GENERIC_HARDIRQS */ #ifndef __ARCH_SET_SOFTIRQ_PENDING diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 71ea923..6187a85 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -110,9 +110,6 @@ extern int allocate_resource(struct resource *root, struct resource *new, int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size); -/* get registered SYSTEM_RAM resources in specified area */ -extern int find_next_system_ram(struct resource *res); - /* Convenience shorthand with allocation */ #define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name)) #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name)) diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 3fd3ddd..408696e 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -49,6 +49,34 @@ struct ipc_perm #define IPC_64 0x0100 /* New version (support 32-bit UIDs, bigger message sizes, etc. */ +/* + * These are used to wrap system calls. + * + * See architecture code for ugly details.. + */ +struct ipc_kludge { + struct msgbuf __user *msgp; + long msgtyp; +}; + +#define SEMOP 1 +#define SEMGET 2 +#define SEMCTL 3 +#define SEMTIMEDOP 4 +#define MSGSND 11 +#define MSGRCV 12 +#define MSGGET 13 +#define MSGCTL 14 +#define SHMAT 21 +#define SHMDT 22 +#define SHMGET 23 +#define SHMCTL 24 + +/* Used by the DIPC package, try and avoid reusing it */ +#define DIPC 25 + +#define IPCCALL(version,op) ((version)<<16 | (op)) + #ifdef __KERNEL__ #include <linux/kref.h> @@ -61,6 +89,7 @@ struct kern_ipc_perm { spinlock_t lock; int deleted; + int id; key_t key; uid_t uid; gid_t gid; @@ -82,6 +111,8 @@ struct ipc_namespace { int msg_ctlmax; int msg_ctlmnb; int msg_ctlmni; + atomic_t msg_bytes; + atomic_t msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 7a9db390..c5bd28b 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -365,6 +365,16 @@ int ipmi_request_supply_msgs(ipmi_user_t user, int priority); /* + * Poll the IPMI interface for the user. This causes the IPMI code to + * do an immediate check for information from the driver and handle + * anything that is immediately pending. This will not block in any + * way. This is useful if you need to implement polling from the user + * for things like modifying the watchdog timeout when a panic occurs + * or disabling the watchdog timer on a reboot. + */ +void ipmi_poll_interface(ipmi_user_t user); + +/* * When commands come in to the SMS, the user can register to receive * them. Only one user can be listening on a specific netfn/cmd/chan tuple * at a time, you will get an EBUSY error if the command is already diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index c063310..56ae438 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -118,7 +118,7 @@ struct ipmi_smi_handlers /* Enable/disable firmware maintenance mode. Note that this is *not* the modes defined, this is simply an on/off setting. The message handler does the mode handling. Note - that this is called from interupt context, so it cannot + that this is called from interrupt context, so it cannot block. */ void (*set_maintenance_mode)(void *send_info, int enable); @@ -148,26 +148,46 @@ struct ipmi_device_id { /* Take a pointer to a raw data buffer and a length and extract device id information from it. The first byte of data must point to the - byte from the get device id response after the completion code. - The caller is responsible for making sure the length is at least - 11 and the command completed without error. */ -static inline void ipmi_demangle_device_id(unsigned char *data, - unsigned int data_len, - struct ipmi_device_id *id) + netfn << 2, the data should be of the format: + netfn << 2, cmd, completion code, data + as normally comes from a device interface. */ +static inline int ipmi_demangle_device_id(const unsigned char *data, + unsigned int data_len, + struct ipmi_device_id *id) { + if (data_len < 9) + return -EINVAL; + if (data[0] != IPMI_NETFN_APP_RESPONSE << 2 || + data[1] != IPMI_GET_DEVICE_ID_CMD) + /* Strange, didn't get the response we expected. */ + return -EINVAL; + if (data[2] != 0) + /* That's odd, it shouldn't be able to fail. */ + return -EINVAL; + + data += 3; + data_len -= 3; id->device_id = data[0]; id->device_revision = data[1]; id->firmware_revision_1 = data[2]; id->firmware_revision_2 = data[3]; id->ipmi_version = data[4]; id->additional_device_support = data[5]; - id->manufacturer_id = data[6] | (data[7] << 8) | (data[8] << 16); - id->product_id = data[9] | (data[10] << 8); + if (data_len >= 6) { + id->manufacturer_id = (data[6] | (data[7] << 8) | + (data[8] << 16)); + id->product_id = data[9] | (data[10] << 8); + } else { + id->manufacturer_id = 0; + id->product_id = 0; + } if (data_len >= 15) { memcpy(id->aux_firmware_revision, data+11, 4); id->aux_firmware_revision_set = 1; } else id->aux_firmware_revision_set = 0; + + return 0; } /* Add a low-level interface to the IPMI driver. Note that if the diff --git a/include/linux/isdn.h b/include/linux/isdn.h index ad09506..d0ecc8e 100644 --- a/include/linux/isdn.h +++ b/include/linux/isdn.h @@ -167,6 +167,7 @@ typedef struct { #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/tcp.h> +#include <linux/mutex.h> #define ISDN_TTY_MAJOR 43 #define ISDN_TTYAUX_MAJOR 44 @@ -286,7 +287,6 @@ typedef struct { /* Local interface-data */ typedef struct isdn_net_local_s { ulong magic; - char name[10]; /* Name of device */ struct net_device_stats stats; /* Ethernet Statistics */ int isdn_device; /* Index to isdn-device */ int isdn_channel; /* Index to isdn-channel */ @@ -617,7 +617,7 @@ typedef struct isdn_devt { int v110emu[ISDN_MAX_CHANNELS]; /* V.110 emulator-mode 0=none */ atomic_t v110use[ISDN_MAX_CHANNELS]; /* Usage-Semaphore for stream */ isdn_v110_stream *v110[ISDN_MAX_CHANNELS]; /* V.110 private data */ - struct semaphore sem; /* serialize list access*/ + struct mutex mtx; /* serialize list access*/ unsigned long global_features; } isdn_dev; diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 4527375..16e7ed8 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -30,6 +30,7 @@ #include <linux/bit_spinlock.h> #include <linux/mutex.h> #include <linux/timer.h> +#include <linux/lockdep.h> #include <asm/semaphore.h> #endif @@ -57,7 +58,7 @@ * CONFIG_JBD_DEBUG is on. */ #define JBD_EXPENSIVE_CHECKING -extern int journal_enable_debug; +extern u8 journal_enable_debug; #define jbd_debug(n, f, a...) \ do { \ @@ -71,14 +72,15 @@ extern int journal_enable_debug; #define jbd_debug(f, a...) /**/ #endif -extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry); -extern void * jbd_slab_alloc(size_t size, gfp_t flags); -extern void jbd_slab_free(void *ptr, size_t size); +static inline void *jbd_alloc(size_t size, gfp_t flags) +{ + return (void *)__get_free_pages(flags, get_order(size)); +} -#define jbd_kmalloc(size, flags) \ - __jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) -#define jbd_rep_kmalloc(size, flags) \ - __jbd_kmalloc(__FUNCTION__, (size), (flags), 1) +static inline void jbd_free(void *ptr, size_t size) +{ + free_pages((unsigned long)ptr, get_order(size)); +}; #define JFS_MIN_JOURNAL_BLOCKS 1024 @@ -246,17 +248,7 @@ typedef struct journal_superblock_s #include <linux/fs.h> #include <linux/sched.h> -#define JBD_ASSERTIONS -#ifdef JBD_ASSERTIONS -#define J_ASSERT(assert) \ -do { \ - if (!(assert)) { \ - printk (KERN_EMERG \ - "Assertion failure in %s() at %s:%d: \"%s\"\n", \ - __FUNCTION__, __FILE__, __LINE__, # assert); \ - BUG(); \ - } \ -} while (0) +#define J_ASSERT(assert) BUG_ON(!(assert)) #if defined(CONFIG_BUFFER_DEBUG) void buffer_assertion_failure(struct buffer_head *bh); @@ -272,10 +264,6 @@ void buffer_assertion_failure(struct buffer_head *bh); #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #endif -#else -#define J_ASSERT(assert) do { } while (0) -#endif /* JBD_ASSERTIONS */ - #if defined(JBD_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) @@ -371,6 +359,7 @@ struct jbd_revoke_table_s; * @h_sync: flag for sync-on-close * @h_jdata: flag to force data journaling * @h_aborted: flag indicating fatal error on handle + * @h_lockdep_map: lockdep info for debugging lock problems **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation @@ -396,6 +385,10 @@ struct handle_s unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ unsigned int h_aborted: 1; /* fatal error on handle */ + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map h_lockdep_map; +#endif }; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 260d6d7..06ef114 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -13,8 +13,8 @@ * filesystem journaling support. */ -#ifndef _LINUX_JBD_H -#define _LINUX_JBD_H +#ifndef _LINUX_JBD2_H +#define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ @@ -37,26 +37,26 @@ #define journal_oom_retry 1 /* - * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under - * normal use we want ext3 to continue after such errors, because + * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ -#undef JBD_PARANOID_IOFAIL +#undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ -#define JBD_DEFAULT_MAX_COMMIT_AGE 5 +#define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* - * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal + * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ -#define JBD_EXPENSIVE_CHECKING +#define JBD2_EXPENSIVE_CHECKING extern u8 jbd2_journal_enable_debug; #define jbd_debug(n, f, a...) \ @@ -71,14 +71,15 @@ extern u8 jbd2_journal_enable_debug; #define jbd_debug(f, a...) /**/ #endif -extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry); -extern void * jbd2_slab_alloc(size_t size, gfp_t flags); -extern void jbd2_slab_free(void *ptr, size_t size); +static inline void *jbd2_alloc(size_t size, gfp_t flags) +{ + return (void *)__get_free_pages(flags, get_order(size)); +} -#define jbd_kmalloc(size, flags) \ - __jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) -#define jbd_rep_kmalloc(size, flags) \ - __jbd2_kmalloc(__FUNCTION__, (size), (flags), 1) +static inline void jbd2_free(void *ptr, size_t size) +{ + free_pages((unsigned long)ptr, get_order(size)); +}; #define JBD2_MIN_JOURNAL_BLOCKS 1024 @@ -162,8 +163,8 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD_TAG_SIZE64 (sizeof(journal_block_tag_t)) +#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) +#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) /* * The revoke descriptor: used on disk to describe a series of blocks to @@ -255,8 +256,8 @@ typedef struct journal_superblock_s #include <linux/fs.h> #include <linux/sched.h> -#define JBD_ASSERTIONS -#ifdef JBD_ASSERTIONS +#define JBD2_ASSERTIONS +#ifdef JBD2_ASSERTIONS #define J_ASSERT(assert) \ do { \ if (!(assert)) { \ @@ -283,9 +284,9 @@ void buffer_assertion_failure(struct buffer_head *bh); #else #define J_ASSERT(assert) do { } while (0) -#endif /* JBD_ASSERTIONS */ +#endif /* JBD2_ASSERTIONS */ -#if defined(JBD_PARANOID_IOFAIL) +#if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) @@ -959,12 +960,12 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; -static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) +static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); } -static inline void jbd_free_handle(handle_t *handle) +static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } @@ -1103,4 +1104,4 @@ extern int jbd_blocks_per_page(struct inode *inode); #endif /* __KERNEL__ */ -#endif /* _LINUX_JBD_H */ +#endif /* _LINUX_JBD2_H */ diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d7a5e03..8b08002 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -109,6 +109,10 @@ static inline u64 get_jiffies_64(void) ((long)(a) - (long)(b) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) +#define time_in_range(a,b,c) \ + (time_after_eq(a,b) && \ + time_before_eq(a,c)) + /* Same as above, but does so with platform independent 64bit types. * These must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64() */ @@ -144,6 +148,8 @@ static inline u64 get_jiffies_64(void) */ #define MAX_JIFFY_OFFSET ((LONG_MAX >> 1)-1) +extern unsigned long preset_lpj; + /* * We want to do realistic conversions of time so we need to use the same * values the update wall clock code uses as the jiffies size. This value diff --git a/include/linux/kbd_diacr.h b/include/linux/kbd_diacr.h index 1c1a3ff..7274ec6 100644 --- a/include/linux/kbd_diacr.h +++ b/include/linux/kbd_diacr.h @@ -2,7 +2,7 @@ #define _DIACR_H #include <linux/kd.h> -extern struct kbdiacr accent_table[]; +extern struct kbdiacruc accent_table[]; extern unsigned int accent_table_size; #endif /* _DIACR_H */ diff --git a/include/linux/kd.h b/include/linux/kd.h index 28be4fb..c91fc0c 100644 --- a/include/linux/kd.h +++ b/include/linux/kd.h @@ -125,6 +125,16 @@ struct kbdiacrs { #define KDGKBDIACR 0x4B4A /* read kernel accent table */ #define KDSKBDIACR 0x4B4B /* write kernel accent table */ +struct kbdiacruc { + __u32 diacr, base, result; +}; +struct kbdiacrsuc { + unsigned int kb_cnt; /* number of entries in following array */ + struct kbdiacruc kbdiacruc[256]; /* MAX_DIACR from keyboard.h */ +}; +#define KDGKBDIACRUC 0x4BFA /* read kernel accent table - UCS */ +#define KDSKBDIACRUC 0x4BFB /* write kernel accent table - UCS */ + struct kbkeycode { unsigned int scancode, keycode; }; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d9725a2..94bc996 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -35,6 +35,7 @@ extern const char linux_proc_banner[]; #define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) #define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) +#define IS_ALIGNED(x,a) (((x) % ((typeof(x))(a))) == 0) #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) @@ -75,6 +76,13 @@ extern const char linux_proc_banner[]; #define KERN_INFO "<6>" /* informational */ #define KERN_DEBUG "<7>" /* debug-level messages */ +/* + * Annotation for a "continued" line of log printout (only done after a + * line that had no enclosing \n). Only to be used by core/arch code + * during early bootup (a continued line is not SMP-safe otherwise). + */ +#define KERN_CONT "" + extern int console_printk[]; #define console_loglevel (console_printk[0]) @@ -171,6 +179,9 @@ asmlinkage int vprintk(const char *fmt, va_list args) __attribute__ ((format (printf, 1, 0))); asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; +extern int log_buf_get_len(void); +extern int log_buf_read(int idx); +extern int log_buf_copy(char *dest, int idx, int len); #else static inline int vprintk(const char *s, va_list args) __attribute__ ((format (printf, 1, 0))); @@ -178,6 +189,9 @@ static inline int vprintk(const char *s, va_list args) { return 0; } static inline int printk(const char *s, ...) __attribute__ ((format (printf, 1, 2))); static inline int __cold printk(const char *s, ...) { return 0; } +static inline int log_buf_get_len(void) { return 0; } +static inline int log_buf_read(int idx) { return 0; } +static inline int log_buf_copy(char *dest, int idx, int len) { return 0; } #endif unsigned long int_sqrt(unsigned long); @@ -244,10 +258,25 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, const void *buf, size_t len); #define hex_asc(x) "0123456789abcdef"[x] +#define pr_emerg(fmt, arg...) \ + printk(KERN_EMERG fmt, ##arg) +#define pr_alert(fmt, arg...) \ + printk(KERN_ALERT fmt, ##arg) +#define pr_crit(fmt, arg...) \ + printk(KERN_CRIT fmt, ##arg) +#define pr_err(fmt, arg...) \ + printk(KERN_ERR fmt, ##arg) +#define pr_warning(fmt, arg...) \ + printk(KERN_WARNING fmt, ##arg) +#define pr_notice(fmt, arg...) \ + printk(KERN_NOTICE fmt, ##arg) +#define pr_info(fmt, arg...) \ + printk(KERN_INFO fmt, ##arg) + #ifdef DEBUG /* If you are writing a driver, please use dev_dbg instead */ -#define pr_debug(fmt,arg...) \ - printk(KERN_DEBUG fmt,##arg) +#define pr_debug(fmt, arg...) \ + printk(KERN_DEBUG fmt, ##arg) #else static inline int __attribute__ ((format (printf, 1, 2))) pr_debug(const char * fmt, ...) { @@ -255,9 +284,6 @@ static inline int __attribute__ ((format (printf, 1, 2))) pr_debug(const char * } #endif -#define pr_info(fmt,arg...) \ - printk(KERN_INFO fmt,##arg) - /* * Display an IP address in readable format. */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 43e895f..e8ffce8 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -23,6 +23,7 @@ struct cpu_usage_stat { cputime64_t idle; cputime64_t iowait; cputime64_t steal; + cputime64_t guest; }; struct kernel_stat { @@ -52,7 +53,9 @@ static inline int kstat_irqs(int irq) } extern void account_user_time(struct task_struct *, cputime_t); +extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); +extern void account_system_time_scaled(struct task_struct *, cputime_t); extern void account_steal_time(struct task_struct *, cputime_t); #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 8c2c7fc..2d9c448 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -121,6 +121,30 @@ extern struct page *kimage_alloc_control_pages(struct kimage *image, extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); +void crash_save_vmcoreinfo(void); +void arch_crash_save_vmcoreinfo(void); +void vmcoreinfo_append_str(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); +unsigned long paddr_vmcoreinfo_note(void); + +#define VMCOREINFO_SYMBOL(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(struct name)) +#define VMCOREINFO_TYPEDEF_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(name)) +#define VMCOREINFO_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)&(((struct name *)0)->field)) +#define VMCOREINFO_LENGTH(name, value) \ + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) +#define VMCOREINFO_NUMBER(name) \ + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) +#define VMCOREINFO_CONFIG(name) \ + vmcoreinfo_append_str("CONFIG_%s=y\n", #name) + extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -148,12 +172,23 @@ extern struct kimage *kexec_crash_image; #define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ +#define VMCOREINFO_BYTES (4096) +#define VMCOREINFO_NOTE_NAME "VMCOREINFO" +#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) +#define VMCOREINFO_NOTE_SIZE (KEXEC_NOTE_HEAD_BYTES*2 + VMCOREINFO_BYTES \ + + VMCOREINFO_NOTE_NAME_BYTES) + /* Location of a reserved region to hold the crash kernel. */ extern struct resource crashk_res; typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4]; extern note_buf_t *crash_notes; +extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; +extern size_t vmcoreinfo_size; +extern size_t vmcoreinfo_max_size; +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); #else /* !CONFIG_KEXEC */ struct pt_regs; diff --git a/include/linux/key-type.h b/include/linux/key-type.h new file mode 100644 index 0000000..65833d4 --- /dev/null +++ b/include/linux/key-type.h @@ -0,0 +1,112 @@ +/* Definitions for key type implementations + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_KEY_TYPE_H +#define _LINUX_KEY_TYPE_H + +#include <linux/key.h> + +#ifdef CONFIG_KEYS + +/* + * key under-construction record + * - passed to the request_key actor if supplied + */ +struct key_construction { + struct key *key; /* key being constructed */ + struct key *authkey;/* authorisation for key being constructed */ +}; + +typedef int (*request_key_actor_t)(struct key_construction *key, + const char *op, void *aux); + +/* + * kernel managed key type definition + */ +struct key_type { + /* name of the type */ + const char *name; + + /* default payload length for quota precalculation (optional) + * - this can be used instead of calling key_payload_reserve(), that + * function only needs to be called if the real datalen is different + */ + size_t def_datalen; + + /* instantiate a key of this type + * - this method should call key_payload_reserve() to determine if the + * user's quota will hold the payload + */ + int (*instantiate)(struct key *key, const void *data, size_t datalen); + + /* update a key of this type (optional) + * - this method should call key_payload_reserve() to recalculate the + * quota consumption + * - the key must be locked against read when modifying + */ + int (*update)(struct key *key, const void *data, size_t datalen); + + /* match a key against a description */ + int (*match)(const struct key *key, const void *desc); + + /* clear some of the data from a key on revokation (optional) + * - the key's semaphore will be write-locked by the caller + */ + void (*revoke)(struct key *key); + + /* clear the data from a key (optional) */ + void (*destroy)(struct key *key); + + /* describe a key */ + void (*describe)(const struct key *key, struct seq_file *p); + + /* read a key's data (optional) + * - permission checks will be done by the caller + * - the key's semaphore will be readlocked by the caller + * - should return the amount of data that could be read, no matter how + * much is copied into the buffer + * - shouldn't do the copy if the buffer is NULL + */ + long (*read)(const struct key *key, char __user *buffer, size_t buflen); + + /* handle request_key() for this type instead of invoking + * /sbin/request-key (optional) + * - key is the key to instantiate + * - authkey is the authority to assume when instantiating this key + * - op is the operation to be done, usually "create" + * - the call must not return until the instantiation process has run + * its course + */ + request_key_actor_t request_key; + + /* internal fields */ + struct list_head link; /* link in types list */ +}; + +extern struct key_type key_type_keyring; + +extern int register_key_type(struct key_type *ktype); +extern void unregister_key_type(struct key_type *ktype); + +extern int key_payload_reserve(struct key *key, size_t datalen); +extern int key_instantiate_and_link(struct key *key, + const void *data, + size_t datalen, + struct key *keyring, + struct key *instkey); +extern int key_negate_and_link(struct key *key, + unsigned timeout, + struct key *keyring, + struct key *instkey); +extern void complete_request_key(struct key_construction *cons, int error); + +#endif /* CONFIG_KEYS */ +#endif /* _LINUX_KEY_TYPE_H */ diff --git a/include/linux/key.h b/include/linux/key.h index a9220e7..fcdbd5e 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -1,6 +1,6 @@ -/* key.h: authentication token and access key management +/* Authentication token and access key management * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2004, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -175,78 +175,6 @@ struct key { } payload; }; -/*****************************************************************************/ -/* - * kernel managed key type definition - */ -typedef int (*request_key_actor_t)(struct key *key, struct key *authkey, - const char *op, void *aux); - -struct key_type { - /* name of the type */ - const char *name; - - /* default payload length for quota precalculation (optional) - * - this can be used instead of calling key_payload_reserve(), that - * function only needs to be called if the real datalen is different - */ - size_t def_datalen; - - /* instantiate a key of this type - * - this method should call key_payload_reserve() to determine if the - * user's quota will hold the payload - */ - int (*instantiate)(struct key *key, const void *data, size_t datalen); - - /* update a key of this type (optional) - * - this method should call key_payload_reserve() to recalculate the - * quota consumption - * - the key must be locked against read when modifying - */ - int (*update)(struct key *key, const void *data, size_t datalen); - - /* match a key against a description */ - int (*match)(const struct key *key, const void *desc); - - /* clear some of the data from a key on revokation (optional) - * - the key's semaphore will be write-locked by the caller - */ - void (*revoke)(struct key *key); - - /* clear the data from a key (optional) */ - void (*destroy)(struct key *key); - - /* describe a key */ - void (*describe)(const struct key *key, struct seq_file *p); - - /* read a key's data (optional) - * - permission checks will be done by the caller - * - the key's semaphore will be readlocked by the caller - * - should return the amount of data that could be read, no matter how - * much is copied into the buffer - * - shouldn't do the copy if the buffer is NULL - */ - long (*read)(const struct key *key, char __user *buffer, size_t buflen); - - /* handle request_key() for this type instead of invoking - * /sbin/request-key (optional) - * - key is the key to instantiate - * - authkey is the authority to assume when instantiating this key - * - op is the operation to be done, usually "create" - * - the call must not return until the instantiation process has run - * its course - */ - request_key_actor_t request_key; - - /* internal fields */ - struct list_head link; /* link in types list */ -}; - -extern struct key_type key_type_keyring; - -extern int register_key_type(struct key_type *ktype); -extern void unregister_key_type(struct key_type *ktype); - extern struct key *key_alloc(struct key_type *type, const char *desc, uid_t uid, gid_t gid, @@ -259,16 +187,6 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ -extern int key_payload_reserve(struct key *key, size_t datalen); -extern int key_instantiate_and_link(struct key *key, - const void *data, - size_t datalen, - struct key *keyring, - struct key *instkey); -extern int key_negate_and_link(struct key *key, - unsigned timeout, - struct key *keyring, - struct key *instkey); extern void key_revoke(struct key *key); extern void key_put(struct key *key); @@ -293,6 +211,17 @@ extern struct key *request_key_with_auxdata(struct key_type *type, const char *callout_info, void *aux); +extern struct key *request_key_async(struct key_type *type, + const char *description, + const char *callout_info); + +extern struct key *request_key_async_with_auxdata(struct key_type *type, + const char *description, + const char *callout_info, + void *aux); + +extern int wait_for_key_construction(struct key *key, bool intr); + extern int key_validate(struct key *key); extern key_ref_t key_create_or_update(key_ref_t keyring, @@ -328,8 +257,6 @@ extern int keyring_add_key(struct key *keyring, extern struct key *key_lookup(key_serial_t id); -extern void keyring_replace_payload(struct key *key, void *replacement); - #define key_serial(key) ((key) ? (key)->serial : 0) /* diff --git a/include/linux/keyboard.h b/include/linux/keyboard.h index 7ddbc30..65c2d70 100644 --- a/include/linux/keyboard.h +++ b/include/linux/keyboard.h @@ -23,10 +23,21 @@ #define MAX_NR_OF_USER_KEYMAPS 256 /* should be at least 7 */ #ifdef __KERNEL__ +struct notifier_block; extern const int NR_TYPES; extern const int max_vals[]; extern unsigned short *key_maps[MAX_NR_KEYMAPS]; extern unsigned short plain_map[NR_KEYS]; + +struct keyboard_notifier_param { + struct vc_data *vc; /* VC on which the keyboard press was done */ + int down; /* Pressure of the key? */ + int shift; /* Current shift mask */ + unsigned int value; /* keycode, unicode value or keysym */ +}; + +extern int register_keyboard_notifier(struct notifier_block *nb); +extern int unregister_keyboard_notifier(struct notifier_block *nb); #endif #define MAX_NR_FUNC 256 /* max nr of strings assigned to keys */ @@ -416,6 +427,7 @@ extern unsigned short plain_map[NR_KEYS]; #define K_SHIFTRLOCK K(KT_LOCK,KG_SHIFTR) #define K_CTRLLLOCK K(KT_LOCK,KG_CTRLL) #define K_CTRLRLOCK K(KT_LOCK,KG_CTRLR) +#define K_CAPSSHIFTLOCK K(KT_LOCK,KG_CAPSSHIFT) #define K_SHIFT_SLOCK K(KT_SLOCK,KG_SHIFT) #define K_CTRL_SLOCK K(KT_SLOCK,KG_CTRL) @@ -425,8 +437,9 @@ extern unsigned short plain_map[NR_KEYS]; #define K_SHIFTR_SLOCK K(KT_SLOCK,KG_SHIFTR) #define K_CTRLL_SLOCK K(KT_SLOCK,KG_CTRLL) #define K_CTRLR_SLOCK K(KT_SLOCK,KG_CTRLR) +#define K_CAPSSHIFT_SLOCK K(KT_SLOCK,KG_CAPSSHIFT) -#define NR_LOCK 8 +#define NR_LOCK 9 #define K_BRL_BLANK K(KT_BRL, 0) #define K_BRL_DOT1 K(KT_BRL, 1) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 51464d1..8189158 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -166,6 +166,12 @@ struct kretprobe_instance { struct task_struct *task; }; +struct kretprobe_blackpoint { + const char *name; + void *addr; +}; +extern struct kretprobe_blackpoint kretprobe_blacklist[]; + static inline void kretprobe_assert(struct kretprobe_instance *ri, unsigned long orig_ret_address, unsigned long trampoline_address) { diff --git a/include/linux/lguest.h b/include/linux/lguest.h index 157ad64..8beb291 100644 --- a/include/linux/lguest.h +++ b/include/linux/lguest.h @@ -1,76 +1,16 @@ /* Things the lguest guest needs to know. Note: like all lguest interfaces, * this is subject to wild and random change between versions. */ -#ifndef _ASM_LGUEST_H -#define _ASM_LGUEST_H +#ifndef _LINUX_LGUEST_H +#define _LINUX_LGUEST_H #ifndef __ASSEMBLY__ +#include <linux/time.h> #include <asm/irq.h> - -#define LHCALL_FLUSH_ASYNC 0 -#define LHCALL_LGUEST_INIT 1 -#define LHCALL_CRASH 2 -#define LHCALL_LOAD_GDT 3 -#define LHCALL_NEW_PGTABLE 4 -#define LHCALL_FLUSH_TLB 5 -#define LHCALL_LOAD_IDT_ENTRY 6 -#define LHCALL_SET_STACK 7 -#define LHCALL_TS 8 -#define LHCALL_SET_CLOCKEVENT 9 -#define LHCALL_HALT 10 -#define LHCALL_BIND_DMA 12 -#define LHCALL_SEND_DMA 13 -#define LHCALL_SET_PTE 14 -#define LHCALL_SET_PMD 15 -#define LHCALL_LOAD_TLS 16 +#include <asm/lguest_hcall.h> #define LG_CLOCK_MIN_DELTA 100UL #define LG_CLOCK_MAX_DELTA ULONG_MAX -/*G:031 First, how does our Guest contact the Host to ask for privileged - * operations? There are two ways: the direct way is to make a "hypercall", - * to make requests of the Host Itself. - * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Seventeen hypercalls are - * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %edx, %ebx and %ecx. If a return - * value makes sense, it's returned in %eax. - * - * Grossly invalid calls result in Sudden Death at the hands of the vengeful - * Host, rather than returning failure. This reflects Winston Churchill's - * definition of a gentleman: "someone who is only rude intentionally". */ -#define LGUEST_TRAP_ENTRY 0x1F - -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call is in %eax (aka "a"), and can be replaced */ - : "=a"(call) - /* The other arguments are in %eax, %edx, %ebx & %ecx */ - : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} -/*:*/ - -void async_hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3); - -/* Can't use our min() macro here: needs to be a constant */ -#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) - -#define LHCALL_RING_SIZE 64 -struct hcall_ring -{ - u32 eax, edx, ebx, ecx; -}; - /*G:032 The second method of communicating with the Host is to via "struct * lguest_data". The Guest's very first hypercall is to tell the Host where * this is, and then the Guest and Host both publish information in it. :*/ @@ -97,20 +37,24 @@ struct lguest_data /* 0xFF == done (set by Host), 0 == pending (set by Guest). */ u8 hcall_status[LHCALL_RING_SIZE]; /* The actual registers for the hypercalls. */ - struct hcall_ring hcalls[LHCALL_RING_SIZE]; + struct hcall_args hcalls[LHCALL_RING_SIZE]; /* Fields initialized by the Host at boot: */ /* Memory not to try to access */ unsigned long reserve_mem; - /* ID of this Guest (used by network driver to set ethernet address) */ - u16 guestid; /* KHz for the TSC clock. */ u32 tsc_khz; + /* Page where the top-level pagetable is */ + unsigned long pgdir; /* Fields initialized by the Guest at boot: */ /* Instruction range to suppress interrupts even if enabled */ unsigned long noirq_start, noirq_end; + /* Address above which page tables are all identical. */ + unsigned long kernel_address; + /* The vector to try to use for system calls (0x40 or 0x80). */ + unsigned int syscall_vec; }; extern struct lguest_data lguest_data; #endif /* __ASSEMBLY__ */ -#endif /* _ASM_LGUEST_H */ +#endif /* _LINUX_LGUEST_H */ diff --git a/include/linux/lguest_bus.h b/include/linux/lguest_bus.h deleted file mode 100644 index d27853d..0000000 --- a/include/linux/lguest_bus.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef _ASM_LGUEST_DEVICE_H -#define _ASM_LGUEST_DEVICE_H -/* Everything you need to know about lguest devices. */ -#include <linux/device.h> -#include <linux/lguest.h> -#include <linux/lguest_launcher.h> - -struct lguest_device { - /* Unique busid, and index into lguest_page->devices[] */ - unsigned int index; - - struct device dev; - - /* Driver can hang data off here. */ - void *private; -}; - -/*D:380 Since interrupt numbers are arbitrary, we use a convention: each device - * can use the interrupt number corresponding to its index. The +1 is because - * interrupt 0 is not usable (it's actually the timer interrupt). */ -static inline int lgdev_irq(const struct lguest_device *dev) -{ - return dev->index + 1; -} -/*:*/ - -/* dma args must not be vmalloced! */ -void lguest_send_dma(unsigned long key, struct lguest_dma *dma); -int lguest_bind_dma(unsigned long key, struct lguest_dma *dmas, - unsigned int num, u8 irq); -void lguest_unbind_dma(unsigned long key, struct lguest_dma *dmas); - -/* Map the virtual device space */ -void *lguest_map(unsigned long phys_addr, unsigned long pages); -void lguest_unmap(void *); - -struct lguest_driver { - const char *name; - struct module *owner; - u16 device_type; - int (*probe)(struct lguest_device *dev); - void (*remove)(struct lguest_device *dev); - - struct device_driver drv; -}; - -extern int register_lguest_driver(struct lguest_driver *drv); -extern void unregister_lguest_driver(struct lguest_driver *drv); - -extern struct lguest_device_desc *lguest_devices; /* Just past max_pfn */ -#endif /* _ASM_LGUEST_DEVICE_H */ diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 6416705..61e1e3e 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -1,6 +1,7 @@ #ifndef _ASM_LGUEST_USER #define _ASM_LGUEST_USER /* Everything the "lguest" userspace program needs to know. */ +#include <linux/types.h> /* They can register up to 32 arrays of lguest_dma. */ #define LGUEST_MAX_DMA 32 /* At most we can dma 16 lguest_dma in one op. */ @@ -9,66 +10,6 @@ /* How many devices? Assume each one wants up to two dma arrays per device. */ #define LGUEST_MAX_DEVICES (LGUEST_MAX_DMA/2) -/*D:200 - * Lguest I/O - * - * The lguest I/O mechanism is the only way Guests can talk to devices. There - * are two hypercalls involved: SEND_DMA for output and BIND_DMA for input. In - * each case, "struct lguest_dma" describes the buffer: this contains 16 - * addr/len pairs, and if there are fewer buffer elements the len array is - * terminated with a 0. - * - * I/O is organized by keys: BIND_DMA attaches buffers to a particular key, and - * SEND_DMA transfers to buffers bound to particular key. By convention, keys - * correspond to a physical address within the device's page. This means that - * devices will never accidentally end up with the same keys, and allows the - * Host use The Futex Trick (as we'll see later in our journey). - * - * SEND_DMA simply indicates a key to send to, and the physical address of the - * "struct lguest_dma" to send. The Host will write the number of bytes - * transferred into the "struct lguest_dma"'s used_len member. - * - * BIND_DMA indicates a key to bind to, a pointer to an array of "struct - * lguest_dma"s ready for receiving, the size of that array, and an interrupt - * to trigger when data is received. The Host will only allow transfers into - * buffers with a used_len of zero: it then sets used_len to the number of - * bytes transferred and triggers the interrupt for the Guest to process the - * new input. */ -struct lguest_dma -{ - /* 0 if free to be used, filled by the Host. */ - u32 used_len; - unsigned long addr[LGUEST_MAX_DMA_SECTIONS]; - u16 len[LGUEST_MAX_DMA_SECTIONS]; -}; -/*:*/ - -/*D:460 This is the layout of a block device memory page. The Launcher sets up - * the num_sectors initially to tell the Guest the size of the disk. The Guest - * puts the type, sector and length of the request in the first three fields, - * then DMAs to the Host. The Host processes the request, sets up the result, - * then DMAs back to the Guest. */ -struct lguest_block_page -{ - /* 0 is a read, 1 is a write. */ - int type; - u32 sector; /* Offset in device = sector * 512. */ - u32 bytes; /* Length expected to be read/written in bytes */ - /* 0 = pending, 1 = done, 2 = done, error */ - int result; - u32 num_sectors; /* Disk length = num_sectors * 512 */ -}; - -/*D:520 The network device is basically a memory page where all the Guests on - * the network publish their MAC (ethernet) addresses: it's an array of "struct - * lguest_net": */ -struct lguest_net -{ - /* Simply the mac address (with multicast bit meaning promisc). */ - unsigned char mac[6]; -}; -/*:*/ - /* Where the Host expects the Guest to SEND_DMA console output to. */ #define LGUEST_CONSOLE_DMA_KEY 0 @@ -81,38 +22,29 @@ struct lguest_net * complex burden for the Host and suboptimal for the Guest, so we have our own * "lguest" bus and simple drivers. * - * Devices are described by an array of LGUEST_MAX_DEVICES of these structs, - * placed by the Launcher just above the top of physical memory: + * Devices are described by a simplified ID, a status byte, and some "config" + * bytes which describe this device's configuration. This is placed by the + * Launcher just above the top of physical memory: */ struct lguest_device_desc { - /* The device type: console, network, disk etc. */ - u16 type; -#define LGUEST_DEVICE_T_CONSOLE 1 -#define LGUEST_DEVICE_T_NET 2 -#define LGUEST_DEVICE_T_BLOCK 3 - - /* The specific features of this device: these depends on device type - * except for LGUEST_DEVICE_F_RANDOMNESS. */ - u16 features; -#define LGUEST_NET_F_NOCSUM 0x4000 /* Don't bother checksumming */ -#define LGUEST_DEVICE_F_RANDOMNESS 0x8000 /* IRQ is fairly random */ - - /* This is how the Guest reports status of the device: the Host can set - * LGUEST_DEVICE_S_REMOVED to indicate removal, but the rest are only - * ever manipulated by the Guest, and only ever set. */ - u16 status; -/* 256 and above are device specific. */ -#define LGUEST_DEVICE_S_ACKNOWLEDGE 1 /* We have seen device. */ -#define LGUEST_DEVICE_S_DRIVER 2 /* We have found a driver */ -#define LGUEST_DEVICE_S_DRIVER_OK 4 /* Driver says OK! */ -#define LGUEST_DEVICE_S_REMOVED 8 /* Device has gone away. */ -#define LGUEST_DEVICE_S_REMOVED_ACK 16 /* Driver has been told. */ -#define LGUEST_DEVICE_S_FAILED 128 /* Something actually failed */ + /* The device type: console, network, disk etc. Type 0 terminates. */ + __u8 type; + /* The number of bytes of the config array. */ + __u8 config_len; + /* A status byte, written by the Guest. */ + __u8 status; + __u8 config[0]; +}; - /* Each device exists somewhere in Guest physical memory, over some - * number of pages. */ - u16 num_pages; - u32 pfn; +/*D:135 This is how we expect the device configuration field for a virtqueue + * (type VIRTIO_CONFIG_F_VIRTQUEUE) to be laid out: */ +struct lguest_vqconfig { + /* The number of entries in the virtio_ring */ + __u16 num; + /* The interrupt we get when something happens. */ + __u16 irq; + /* The page number of the virtio ring for this device. */ + __u32 pfn; }; /*:*/ @@ -120,7 +52,7 @@ struct lguest_device_desc { enum lguest_req { LHREQ_INITIALIZE, /* + pfnlimit, pgdir, start, pageoffset */ - LHREQ_GETDMA, /* + addr (returns &lguest_dma, irq in ->used_len) */ + LHREQ_GETDMA, /* No longer used */ LHREQ_IRQ, /* + irq */ LHREQ_BREAK, /* + on/off flag (on blocks until someone does off) */ }; diff --git a/include/linux/libata.h b/include/linux/libata.h index 229a9ff..bc3b6fc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -29,7 +29,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/dma-mapping.h> -#include <asm/scatterlist.h> +#include <linux/scatterlist.h> #include <linux/io.h> #include <linux/ata.h> #include <linux/workqueue.h> @@ -416,6 +416,7 @@ struct ata_queued_cmd { unsigned long flags; /* ATA_QCFLAG_xxx */ unsigned int tag; unsigned int n_elem; + unsigned int n_iter; unsigned int orig_n_elem; int dma_dir; @@ -426,7 +427,7 @@ struct ata_queued_cmd { unsigned int nbytes; unsigned int curbytes; - unsigned int cursg; + struct scatterlist *cursg; unsigned int cursg_ofs; struct scatterlist sgent; @@ -1036,21 +1037,10 @@ extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset, /* * qc helpers */ -static inline int -ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc) -{ - if (sg == &qc->pad_sgent) - return 1; - if (qc->pad_len) - return 0; - if (((sg - qc->__sg) + 1) == qc->n_elem) - return 1; - return 0; -} - static inline struct scatterlist * ata_qc_first_sg(struct ata_queued_cmd *qc) { + qc->n_iter = 0; if (qc->n_elem) return qc->__sg; if (qc->pad_len) @@ -1063,8 +1053,8 @@ ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc) { if (sg == &qc->pad_sgent) return NULL; - if (++sg - qc->__sg < qc->n_elem) - return sg; + if (++qc->n_iter < qc->n_elem) + return sg_next(sg); if (qc->pad_len) return &qc->pad_sgent; return NULL; @@ -1309,9 +1299,11 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) qc->dma_dir = DMA_NONE; qc->__sg = NULL; qc->flags = 0; - qc->cursg = qc->cursg_ofs = 0; + qc->cursg = NULL; + qc->cursg_ofs = 0; qc->nbytes = qc->curbytes = 0; qc->n_elem = 0; + qc->n_iter = 0; qc->err_mask = 0; qc->pad_len = 0; qc->sect_size = ATA_SECT_SIZE; diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 6c9873f..ff203dd 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -34,6 +34,12 @@ name: #endif +#ifndef WEAK +#define WEAK(name) \ + .weak name; \ + name: +#endif + #define KPROBE_ENTRY(name) \ .pushsection .kprobes.text, "ax"; \ ENTRY(name) diff --git a/include/linux/list.h b/include/linux/list.h index ad9dcb9..75ce2cb 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -478,6 +478,17 @@ static inline void list_splice_init_rcu(struct list_head *list, pos = n, n = pos->next) /** + * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_prev_safe(pos, n, head) \ + for (pos = (head)->prev, n = pos->prev; \ + prefetch(pos->prev), pos != (head); \ + pos = n, n = pos->prev) + +/** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 0e843bf..4c4d236 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -238,6 +238,7 @@ extern void lockdep_info(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); +extern void lockdep_sys_exit(void); extern void lockdep_off(void); extern void lockdep_on(void); @@ -252,6 +253,13 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass); /* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), } + +/* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope * of dependencies wrong: they are either too broad (they need a class-split) @@ -268,6 +276,14 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, (lock)->dep_map.key, sub) /* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), } + + +/* * Acquire a lock. * * Values for "read": @@ -317,6 +333,7 @@ static inline void lockdep_on(void) # define INIT_LOCKDEP # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) +# define lockdep_sys_exit() do { } while (0) /* * The class key takes no space if lockdep is disabled: */ diff --git a/include/linux/log2.h b/include/linux/log2.h index 1b8a2c1..c8cf5e8 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -63,6 +63,15 @@ unsigned long __roundup_pow_of_two(unsigned long n) return 1UL << fls_long(n - 1); } +/* + * round down to nearest power of two + */ +static inline __attribute__((const)) +unsigned long __rounddown_pow_of_two(unsigned long n) +{ + return 1UL << (fls_long(n) - 1); +} + /** * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value * @n - parameter @@ -165,4 +174,20 @@ unsigned long __roundup_pow_of_two(unsigned long n) __roundup_pow_of_two(n) \ ) +/** + * rounddown_pow_of_two - round the given value down to nearest power of two + * @n - parameter + * + * round the given value down to the nearest power of two + * - the result is undefined when n == 0 + * - this can be used to initialise global variables from constant data + */ +#define rounddown_pow_of_two(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n == 1) ? 0 : \ + (1UL << ilog2(n))) : \ + __rounddown_pow_of_two(n) \ + ) + #endif /* _LINUX_LOG2_H */ diff --git a/include/linux/magic.h b/include/linux/magic.h index 36cc20d..1fa0c2c 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -37,5 +37,9 @@ #define SMB_SUPER_MAGIC 0x517B #define USBDEVICE_SUPER_MAGIC 0x9fa2 +#define CGROUP_SUPER_MAGIC 0x27e0eb + +#define FUTEXFS_SUPER_MAGIC 0xBAD1DEA +#define INOTIFYFS_SUPER_MAGIC 0x2BAD1DEA #endif /* __LINUX_MAGIC_H__ */ diff --git a/include/linux/marker.h b/include/linux/marker.h new file mode 100644 index 0000000..5f36cf9 --- /dev/null +++ b/include/linux/marker.h @@ -0,0 +1,129 @@ +#ifndef _LINUX_MARKER_H +#define _LINUX_MARKER_H + +/* + * Code markup for dynamic and static tracing. + * + * See Documentation/marker.txt. + * + * (C) Copyright 2006 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> + * + * This file is released under the GPLv2. + * See the file COPYING for more details. + */ + +#include <linux/types.h> + +struct module; +struct marker; + +/** + * marker_probe_func - Type of a marker probe function + * @mdata: pointer of type struct marker + * @private_data: caller site private data + * @fmt: format string + * @...: variable argument list + * + * Type of marker probe functions. They receive the mdata and need to parse the + * format string to recover the variable argument list. + */ +typedef void marker_probe_func(const struct marker *mdata, + void *private_data, const char *fmt, ...); + +struct marker { + const char *name; /* Marker name */ + const char *format; /* Marker format string, describing the + * variable argument list. + */ + char state; /* Marker state. */ + marker_probe_func *call;/* Probe handler function pointer */ + void *private; /* Private probe data */ +} __attribute__((aligned(8))); + +#ifdef CONFIG_MARKERS + +/* + * Note : the empty asm volatile with read constraint is used here instead of a + * "used" attribute to fix a gcc 4.1.x bug. + * Make sure the alignment of the structure in the __markers section will + * not add unwanted padding between the beginning of the section and the + * structure. Force alignment to the same alignment as the section start. + */ +#define __trace_mark(name, call_data, format, args...) \ + do { \ + static const char __mstrtab_name_##name[] \ + __attribute__((section("__markers_strings"))) \ + = #name; \ + static const char __mstrtab_format_##name[] \ + __attribute__((section("__markers_strings"))) \ + = format; \ + static struct marker __mark_##name \ + __attribute__((section("__markers"), aligned(8))) = \ + { __mstrtab_name_##name, __mstrtab_format_##name, \ + 0, __mark_empty_function, NULL }; \ + __mark_check_format(format, ## args); \ + if (unlikely(__mark_##name.state)) { \ + preempt_disable(); \ + (*__mark_##name.call) \ + (&__mark_##name, call_data, \ + format, ## args); \ + preempt_enable(); \ + } \ + } while (0) + +extern void marker_update_probe_range(struct marker *begin, + struct marker *end, struct module *probe_module, int *refcount); +#else /* !CONFIG_MARKERS */ +#define __trace_mark(name, call_data, format, args...) \ + __mark_check_format(format, ## args) +static inline void marker_update_probe_range(struct marker *begin, + struct marker *end, struct module *probe_module, int *refcount) +{ } +#endif /* CONFIG_MARKERS */ + +/** + * trace_mark - Marker + * @name: marker name, not quoted. + * @format: format string + * @args...: variable argument list + * + * Places a marker. + */ +#define trace_mark(name, format, args...) \ + __trace_mark(name, NULL, format, ## args) + +#define MARK_MAX_FORMAT_LEN 1024 + +/** + * MARK_NOARGS - Format string for a marker with no argument. + */ +#define MARK_NOARGS " " + +/* To be used for string format validity checking with gcc */ +static inline void __printf(1, 2) __mark_check_format(const char *fmt, ...) +{ +} + +extern marker_probe_func __mark_empty_function; + +/* + * Connect a probe to a marker. + * private data pointer must be a valid allocated memory address, or NULL. + */ +extern int marker_probe_register(const char *name, const char *format, + marker_probe_func *probe, void *private); + +/* + * Returns the private data given to marker_probe_register. + */ +extern void *marker_probe_unregister(const char *name); +/* + * Unregister a marker by providing the registered private data. + */ +extern void *marker_probe_unregister_private_data(void *private); + +extern int marker_arm(const char *name); +extern int marker_disarm(const char *name); +extern void *marker_get_private_data(const char *name); + +#endif diff --git a/include/linux/memory.h b/include/linux/memory.h index 654ef55..33f0ff0 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -41,18 +41,15 @@ struct memory_block { #define MEM_ONLINE (1<<0) /* exposed to userspace */ #define MEM_GOING_OFFLINE (1<<1) /* exposed to userspace */ #define MEM_OFFLINE (1<<2) /* exposed to userspace */ +#define MEM_GOING_ONLINE (1<<3) +#define MEM_CANCEL_ONLINE (1<<4) +#define MEM_CANCEL_OFFLINE (1<<5) -/* - * All of these states are currently kernel-internal for notifying - * kernel components and architectures. - * - * For MEM_MAPPING_INVALID, all notifier chains with priority >0 - * are called before pfn_to_page() becomes invalid. The priority=0 - * entry is reserved for the function that actually makes - * pfn_to_page() stop working. Any notifiers that want to be called - * after that should have priority <0. - */ -#define MEM_MAPPING_INVALID (1<<3) +struct memory_notify { + unsigned long start_pfn; + unsigned long nr_pages; + int status_change_nid; +}; struct notifier_block; struct mem_section; @@ -69,21 +66,31 @@ static inline int register_memory_notifier(struct notifier_block *nb) static inline void unregister_memory_notifier(struct notifier_block *nb) { } +static inline int memory_notify(unsigned long val, void *v) +{ + return 0; +} #else +extern int register_memory_notifier(struct notifier_block *nb); +extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_new_memory(struct mem_section *); extern int unregister_memory_section(struct mem_section *); extern int memory_dev_init(void); extern int remove_memory_block(unsigned long, struct mem_section *, int); - +extern int memory_notify(unsigned long val, void *v); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) { \ static struct notifier_block fn##_mem_nb = \ { .notifier_call = fn, .priority = pri }; \ register_memory_notifier(&fn##_mem_nb); \ } +#else +#define hotplug_memory_notifier(fn, pri) do { } while (0) +#endif #endif /* _LINUX_MEMORY_H_ */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7b54666..8fee7a4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -3,7 +3,6 @@ #include <linux/mmzone.h> #include <linux/spinlock.h> -#include <linux/mmzone.h> #include <linux/notifier.h> struct page; @@ -59,11 +58,21 @@ extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void online_page(struct page *page); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long, unsigned long); +extern void __offline_isolated_pages(unsigned long, unsigned long); +extern int offline_pages(unsigned long, unsigned long, unsigned long); /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); +/* + * Walk thorugh 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 @@ -161,13 +170,6 @@ static inline int mhp_notimplemented(const char *func) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) -{ - printk(KERN_WARNING "%s() called, not yet supported\n", __FUNCTION__); - dump_stack(); - return -ENOSYS; -} extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index a020eb2..59c4865 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -19,6 +19,7 @@ /* Flags for get_mem_policy */ #define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */ #define MPOL_F_ADDR (1<<1) /* look up vma using address */ +#define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */ /* Flags for mbind */ #define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */ @@ -143,19 +144,10 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, extern void numa_default_policy(void); extern void numa_policy_init(void); -extern void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *new); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern void mpol_fix_fork_child_flag(struct task_struct *p); -#define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x)) - -#ifdef CONFIG_CPUSETS -#define current_cpuset_is_being_rebound() \ - (cpuset_being_rebound == current->cpuset) -#else -#define current_cpuset_is_being_rebound() 0 -#endif extern struct mempolicy default_policy; extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, @@ -173,8 +165,6 @@ static inline void check_highest_zone(enum zone_type k) int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags); -extern void *cpuset_being_rebound; /* Trigger mpol_copy vma rebind */ - #else struct mempolicy {}; @@ -235,11 +225,6 @@ static inline void numa_default_policy(void) { } -static inline void mpol_rebind_policy(struct mempolicy *pol, - const nodemask_t *new) -{ -} - static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { @@ -253,8 +238,6 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p) { } -#define set_cpuset_being_rebound(x) do {} while (0) - static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 1692dd6..520238c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -10,9 +10,7 @@ #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/prio_tree.h> -#include <linux/mutex.h> #include <linux/debug_locks.h> -#include <linux/backing-dev.h> #include <linux/mm_types.h> struct mempolicy; @@ -50,69 +48,6 @@ extern int sysctl_legacy_va_layout; * mmap() functions). */ -/* - * This struct defines a memory VMM memory area. There is one of these - * per VM-area/task. A VM area is any part of the process virtual memory - * space that has a special rule for the page-fault handlers (ie a shared - * library, the executable area etc). - */ -struct vm_area_struct { - struct mm_struct * vm_mm; /* The address space we belong to. */ - unsigned long vm_start; /* Our start address within vm_mm. */ - unsigned long vm_end; /* The first byte after our end address - within vm_mm. */ - - /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next; - - pgprot_t vm_page_prot; /* Access permissions of this VMA. */ - unsigned long vm_flags; /* Flags, listed below. */ - - struct rb_node vm_rb; - - /* - * For areas with an address space and backing store, - * linkage into the address_space->i_mmap prio tree, or - * linkage to the list of like vmas hanging off its node, or - * linkage of vma in the address_space->i_mmap_nonlinear list. - */ - union { - struct { - struct list_head list; - void *parent; /* aligns with prio_tree_node parent */ - struct vm_area_struct *head; - } vm_set; - - struct raw_prio_tree_node prio_tree_node; - } shared; - - /* - * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma - * list, after a COW of one of the file pages. A MAP_SHARED vma - * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack - * or brk vma (with NULL file) can only be in an anon_vma list. - */ - struct list_head anon_vma_node; /* Serialized by anon_vma->lock */ - struct anon_vma *anon_vma; /* Serialized by page_table_lock */ - - /* Function pointers to deal with this struct. */ - struct vm_operations_struct * vm_ops; - - /* Information about our backing store: */ - unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE - units, *not* PAGE_CACHE_SIZE */ - struct file * vm_file; /* File we map to (can be NULL). */ - void * vm_private_data; /* was vm_pte (shared mem) */ - unsigned long vm_truncate_count;/* truncate_count or restart_addr */ - -#ifndef CONFIG_MMU - atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */ -#endif -#ifdef CONFIG_NUMA - struct mempolicy *vm_policy; /* NUMA policy for the VMA */ -#endif -}; - extern struct kmem_cache *vm_area_cachep; /* @@ -631,10 +566,6 @@ static inline struct address_space *page_mapping(struct page *page) VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; -#ifdef CONFIG_SLUB - else if (unlikely(PageSlab(page))) - mapping = NULL; -#endif else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) mapping = NULL; return mapping; @@ -715,9 +646,6 @@ static inline int page_mapped(struct page *page) extern void show_free_areas(void); #ifdef CONFIG_SHMEM -int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new); -struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, - unsigned long addr); int shmem_lock(struct file *file, int lock, struct user_struct *user); #else static inline int shmem_lock(struct file *file, int lock, @@ -725,18 +653,6 @@ static inline int shmem_lock(struct file *file, int lock, { return 0; } - -static inline int shmem_set_policy(struct vm_area_struct *vma, - struct mempolicy *new) -{ - return 0; -} - -static inline struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, - unsigned long addr) -{ - return NULL; -} #endif struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags); @@ -779,8 +695,6 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); -int zeromap_page_range(struct vm_area_struct *vma, unsigned long from, - unsigned long size, pgprot_t prot); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); @@ -1106,8 +1020,6 @@ int write_one_page(struct page *page, int wait); /* readahead.c */ #define VM_MAX_READAHEAD 128 /* kbytes */ #define VM_MIN_READAHEAD 16 /* kbytes (includes current page) */ -#define VM_MAX_CACHE_HIT 256 /* max pages in a row in cache before - * turning readahead off */ int do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); @@ -1218,5 +1130,16 @@ extern int randomize_va_space; const char * arch_vma_name(struct vm_area_struct *vma); +struct page *sparse_mem_map_populate(unsigned long pnum, int nid); +pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); +pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); +pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); +pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); +void *vmemmap_alloc_block(unsigned long size, int node); +void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); +int vmemmap_populate_basepages(struct page *start_page, + unsigned long pages, int node); +int vmemmap_populate(struct page *start_page, unsigned long pages, int node); + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d5bb179..f4c03e0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1,13 +1,31 @@ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H +#include <linux/auxvec.h> #include <linux/types.h> #include <linux/threads.h> #include <linux/list.h> #include <linux/spinlock.h> +#include <linux/prio_tree.h> +#include <linux/rbtree.h> +#include <linux/rwsem.h> +#include <linux/completion.h> +#include <asm/page.h> +#include <asm/mmu.h> + +#ifndef AT_VECTOR_SIZE_ARCH +#define AT_VECTOR_SIZE_ARCH 0 +#endif +#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) struct address_space; +#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS +typedef atomic_long_t mm_counter_t; +#else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ +typedef unsigned long mm_counter_t; +#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ + /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -24,10 +42,7 @@ struct page { * to show when page is mapped * & limit reverse map searches. */ - struct { /* SLUB uses */ - short unsigned int inuse; - short unsigned int offset; - }; + unsigned int inuse; /* SLUB: Nr of objects */ }; union { struct { @@ -49,13 +64,8 @@ struct page { #if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS spinlock_t ptl; #endif - struct { /* SLUB uses */ - void **lockless_freelist; - struct kmem_cache *slab; /* Pointer to slab */ - }; - struct { - struct page *first_page; /* Compound pages */ - }; + struct kmem_cache *slab; /* SLUB: Pointer to slab */ + struct page *first_page; /* Compound tail pages */ }; union { pgoff_t index; /* Our offset within mapping. */ @@ -80,4 +90,135 @@ struct page { #endif /* WANT_PAGE_VIRTUAL */ }; +/* + * This struct defines a memory VMM memory area. There is one of these + * per VM-area/task. A VM area is any part of the process virtual memory + * space that has a special rule for the page-fault handlers (ie a shared + * library, the executable area etc). + */ +struct vm_area_struct { + struct mm_struct * vm_mm; /* The address space we belong to. */ + unsigned long vm_start; /* Our start address within vm_mm. */ + unsigned long vm_end; /* The first byte after our end address + within vm_mm. */ + + /* linked list of VM areas per task, sorted by address */ + struct vm_area_struct *vm_next; + + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ + unsigned long vm_flags; /* Flags, listed below. */ + + struct rb_node vm_rb; + + /* + * For areas with an address space and backing store, + * linkage into the address_space->i_mmap prio tree, or + * linkage to the list of like vmas hanging off its node, or + * linkage of vma in the address_space->i_mmap_nonlinear list. + */ + union { + struct { + struct list_head list; + void *parent; /* aligns with prio_tree_node parent */ + struct vm_area_struct *head; + } vm_set; + + struct raw_prio_tree_node prio_tree_node; + } shared; + + /* + * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma + * list, after a COW of one of the file pages. A MAP_SHARED vma + * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack + * or brk vma (with NULL file) can only be in an anon_vma list. + */ + struct list_head anon_vma_node; /* Serialized by anon_vma->lock */ + struct anon_vma *anon_vma; /* Serialized by page_table_lock */ + + /* Function pointers to deal with this struct. */ + struct vm_operations_struct * vm_ops; + + /* Information about our backing store: */ + unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE + units, *not* PAGE_CACHE_SIZE */ + struct file * vm_file; /* File we map to (can be NULL). */ + void * vm_private_data; /* was vm_pte (shared mem) */ + unsigned long vm_truncate_count;/* truncate_count or restart_addr */ + +#ifndef CONFIG_MMU + atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */ +#endif +#ifdef CONFIG_NUMA + struct mempolicy *vm_policy; /* NUMA policy for the VMA */ +#endif +}; + +struct mm_struct { + struct vm_area_struct * mmap; /* list of VMAs */ + struct rb_root mm_rb; + struct vm_area_struct * mmap_cache; /* last find_vma result */ + unsigned long (*get_unmapped_area) (struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags); + void (*unmap_area) (struct mm_struct *mm, unsigned long addr); + unsigned long mmap_base; /* base of mmap area */ + unsigned long task_size; /* size of task vm space */ + unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ + unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ + pgd_t * pgd; + atomic_t mm_users; /* How many users with user space? */ + atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ + int map_count; /* number of VMAs */ + struct rw_semaphore mmap_sem; + spinlock_t page_table_lock; /* Protects page tables and some counters */ + + struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung + * together off init_mm.mmlist, and are protected + * by mmlist_lock + */ + + /* Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + mm_counter_t _file_rss; + mm_counter_t _anon_rss; + + unsigned long hiwater_rss; /* High-watermark of RSS usage */ + unsigned long hiwater_vm; /* High-water virtual memory usage */ + + unsigned long total_vm, locked_vm, shared_vm, exec_vm; + unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; + unsigned long start_code, end_code, start_data, end_data; + unsigned long start_brk, brk, start_stack; + unsigned long arg_start, arg_end, env_start, env_end; + + unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + + cpumask_t cpu_vm_mask; + + /* Architecture-specific MM context */ + mm_context_t context; + + /* Swap token stuff */ + /* + * Last value of global fault stamp as seen by this process. + * In other words, this value gives an indication of how long + * it has been since this task got the token. + * Look at mm/thrash.c + */ + unsigned int faultstamp; + unsigned int token_priority; + unsigned int last_interval; + + unsigned long flags; /* Must use atomic bitops to access the bits */ + + /* coredumping support */ + int core_waiters; + struct completion *core_startup_done, core_done; + + /* aio bits */ + rwlock_t ioctx_list_lock; + struct kioctx *ioctx_list; +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 09306d4..ea1bf5b 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -19,5 +19,11 @@ #define SDIO_CLASS_WLAN 0x07 /* WLAN interface */ #define SDIO_CLASS_ATA 0x08 /* Embedded SDIO-ATA std interface */ +/* + * Vendors and devices. Sort key: vendor first, device next. + */ + +#define SDIO_VENDOR_ID_MARVELL 0x02df +#define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4e56273..4c4522a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -7,12 +7,14 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/wait.h> +#include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> +#include <linux/pageblock-flags.h> #include <asm/atomic.h> #include <asm/page.h> @@ -32,8 +34,29 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3 +#define MIGRATE_UNMOVABLE 0 +#define MIGRATE_RECLAIMABLE 1 +#define MIGRATE_MOVABLE 2 +#define MIGRATE_RESERVE 3 +#define MIGRATE_ISOLATE 4 /* can't allocate from here */ +#define MIGRATE_TYPES 5 + +#define for_each_migratetype_order(order, type) \ + for (order = 0; order < MAX_ORDER; order++) \ + for (type = 0; type < MIGRATE_TYPES; type++) + +extern int page_group_by_mobility_disabled; + +static inline int get_pageblock_migratetype(struct page *page) +{ + if (unlikely(page_group_by_mobility_disabled)) + return MIGRATE_UNMOVABLE; + + return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); +} + struct free_area { - struct list_head free_list; + struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; @@ -222,6 +245,14 @@ struct zone { #endif struct free_area free_area[MAX_ORDER]; +#ifndef CONFIG_SPARSEMEM + /* + * Flags for a pageblock_nr_pages block. See pageblock-flags.h. + * In SPARSEMEM, this map is stored in struct mem_section + */ + unsigned long *pageblock_flags; +#endif /* CONFIG_SPARSEMEM */ + ZONE_PADDING(_pad1_) @@ -232,10 +263,7 @@ struct zone { unsigned long nr_scan_active; unsigned long nr_scan_inactive; unsigned long pages_scanned; /* since last reclaim */ - int all_unreclaimable; /* All pages pinned */ - - /* A count of how many reclaimers are scanning this zone */ - atomic_t reclaim_in_progress; + unsigned long flags; /* zone flags, see below */ /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; @@ -313,6 +341,42 @@ struct zone { const char *name; } ____cacheline_internodealigned_in_smp; +typedef enum { + ZONE_ALL_UNRECLAIMABLE, /* all pages pinned */ + ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ + ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */ +} zone_flags_t; + +static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) +{ + set_bit(flag, &zone->flags); +} + +static inline int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag) +{ + return test_and_set_bit(flag, &zone->flags); +} + +static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag) +{ + clear_bit(flag, &zone->flags); +} + +static inline int zone_is_all_unreclaimable(const struct zone *zone) +{ + return test_bit(ZONE_ALL_UNRECLAIMABLE, &zone->flags); +} + +static inline int zone_is_reclaim_locked(const struct zone *zone) +{ + return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); +} + +static inline int zone_is_oom_locked(const struct zone *zone) +{ + return test_bit(ZONE_OOM_LOCKED, &zone->flags); +} + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -324,6 +388,17 @@ struct zone { #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) #ifdef CONFIG_NUMA + +/* + * The NUMA zonelists are doubled becausse we need zonelists that restrict the + * allocations to a single node for GFP_THISNODE. + * + * [0 .. MAX_NR_ZONES -1] : Zonelists with fallback + * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1] : No fallback (GFP_THISNODE) + */ +#define MAX_ZONELISTS (2 * MAX_NR_ZONES) + + /* * We cache key information from each zonelist for smaller cache * footprint when scanning for free pages in get_page_from_freelist(). @@ -389,6 +464,7 @@ struct zonelist_cache { unsigned long last_full_zap; /* when last zap'd (jiffies) */ }; #else +#define MAX_ZONELISTS MAX_NR_ZONES struct zonelist_cache; #endif @@ -455,7 +531,7 @@ extern struct page *mem_map; struct bootmem_data; typedef struct pglist_data { struct zone node_zones[MAX_NR_ZONES]; - struct zonelist node_zonelists[MAX_NR_ZONES]; + struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; #ifdef CONFIG_FLAT_NODE_MEM_MAP struct page *node_mem_map; @@ -708,6 +784,9 @@ extern struct zone *next_zone(struct zone *zone); #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) +#define SECTION_BLOCKFLAGS_BITS \ + ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) + #if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif @@ -727,6 +806,9 @@ struct mem_section { * before using it wrong. */ unsigned long section_mem_map; + + /* See declaration of similar field in struct zone */ + unsigned long *pageblock_flags; }; #ifdef CONFIG_SPARSEMEM_EXTREME @@ -771,12 +853,17 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section) return (struct page *)map; } -static inline int valid_section(struct mem_section *section) +static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } -static inline int section_has_mem_map(struct mem_section *section) +static inline int present_section_nr(unsigned long nr) +{ + return present_section(__nr_to_section(nr)); +} + +static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } @@ -798,6 +885,13 @@ static inline int pfn_valid(unsigned long pfn) return valid_section(__nr_to_section(pfn_to_section_nr(pfn))); } +static inline int pfn_present(unsigned long pfn) +{ + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) + return 0; + return present_section(__nr_to_section(pfn_to_section_nr(pfn))); +} + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 522b0dd..e9fddb4 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -361,4 +361,10 @@ struct ssb_device_id { #define SSB_ANY_ID 0xFFFF #define SSB_ANY_REV 0xFF +struct virtio_device_id { + __u32 device; + __u32 vendor; +}; +#define VIRTIO_DEV_ANY_ID 0xffffffff + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index b6a646c..2cbc0b8 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -15,6 +15,7 @@ #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> +#include <linux/marker.h> #include <asm/local.h> #include <asm/module.h> @@ -312,9 +313,6 @@ struct module /* Arch-specific module values */ struct mod_arch_specific arch; - /* Am I unsafe to unload? */ - int unsafe; - unsigned int taints; /* same bits as kernel:tainted */ #ifdef CONFIG_GENERIC_BUG @@ -346,6 +344,9 @@ struct module /* Section attributes */ struct module_sect_attrs *sect_attrs; + + /* Notes attributes */ + struct module_notes_attrs *notes_attrs; #endif /* Per-cpu data. */ @@ -354,6 +355,10 @@ struct module /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ char *args; +#ifdef CONFIG_MARKERS + struct marker *markers; + unsigned int num_markers; +#endif }; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} @@ -441,16 +446,6 @@ static inline void __module_get(struct module *module) __mod ? __mod->name : "kernel"; \ }) -#define __unsafe(mod) \ -do { \ - if (mod && !(mod)->unsafe) { \ - printk(KERN_WARNING \ - "Module %s cannot be unloaded due to unsafe usage in" \ - " %s:%u\n", (mod)->name, __FILE__, __LINE__); \ - (mod)->unsafe = 1; \ - } \ -} while(0) - /* For kallsyms to ask for address resolution. NULL means not found. */ const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, @@ -467,6 +462,8 @@ int unregister_module_notifier(struct notifier_block * nb); extern void print_modules(void); +extern void module_update_markers(struct module *probe_module, int *refcount); + #else /* !CONFIG_MODULES... */ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) @@ -518,8 +515,6 @@ static inline void module_put(struct module *module) #define module_name(mod) "kernel" -#define __unsafe(mod) - /* For kallsyms to ask for address resolution. NULL means not found. */ static inline const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, @@ -568,6 +563,11 @@ static inline void print_modules(void) { } +static inline void module_update_markers(struct module *probe_module, + int *refcount) +{ +} + #endif /* CONFIG_MODULES */ struct device_driver; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index c83588c..13410b2 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -38,7 +38,11 @@ struct kernel_param { unsigned int perm; param_set_fn set; param_get_fn get; - void *arg; + union { + void *arg; + const struct kparam_string *str; + const struct kparam_array *arr; + }; }; /* Special one for strings we want to copy into */ @@ -66,11 +70,11 @@ struct kparam_array /* Default value instead of permissions? */ \ static int __param_perm_check_##name __attribute__((unused)) = \ BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2)); \ - static char __param_str_##name[] = prefix #name; \ + static const char __param_str_##name[] = prefix #name; \ static struct kernel_param const __param_##name \ __attribute_used__ \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ - = { __param_str_##name, perm, set, get, arg } + = { __param_str_##name, perm, set, get, { arg } } #define module_param_call(name, set, get, arg, perm) \ __module_param_call(MODULE_PARAM_PREFIX, name, set, get, arg, perm) @@ -88,10 +92,10 @@ struct kparam_array /* Actually copy string: maxlen param is usually sizeof(string). */ #define module_param_string(name, string, len, perm) \ - static struct kparam_string __param_string_##name \ + static const struct kparam_string __param_string_##name \ = { len, string }; \ module_param_call(name, param_set_copystring, param_get_string, \ - &__param_string_##name, perm); \ + .str = &__param_string_##name, perm); \ __MODULE_PARM_TYPE(name, "string") /* Called on module insert or kernel boot */ @@ -149,11 +153,11 @@ extern int param_get_invbool(char *buffer, struct kernel_param *kp); /* Comma-separated array: *nump is set to number they actually specified. */ #define module_param_array_named(name, array, type, nump, perm) \ - static struct kparam_array __param_arr_##name \ + static const struct kparam_array __param_arr_##name \ = { ARRAY_SIZE(array), nump, param_set_##type, param_get_##type,\ sizeof(array[0]), array }; \ module_param_call(name, param_array_set, param_array_get, \ - &__param_arr_##name, perm); \ + .arr = &__param_arr_##name, perm); \ __MODULE_PARM_TYPE(name, "array of " #type) #define module_param_array(name, type, nump, perm) \ diff --git a/include/linux/msg.h b/include/linux/msg.h index f1b6074..10a3d5a 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -77,7 +77,6 @@ struct msg_msg { /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; - int q_id; time_t q_stime; /* last msgsnd time */ time_t q_rtime; /* last msgrcv time */ time_t q_ctime; /* last change time */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 0d50ea3..6014797 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -29,7 +29,8 @@ * - task may not exit with mutex held * - memory areas where held locks reside must not be freed * - held mutexes must not be reinitialized - * - mutexes may not be used in irq contexts + * - mutexes may not be used in hardware or software interrupt + * contexts such as tasklets and timers * * These semantics are fully enforced when DEBUG_MUTEXES is * enabled. Furthermore, besides enforcing the above rules, the mutex @@ -120,14 +121,17 @@ static inline int fastcall mutex_is_locked(struct mutex *lock) * See kernel/mutex.c for detailed documentation of these APIs. * Also see Documentation/mutex-design.txt. */ -extern void fastcall mutex_lock(struct mutex *lock); -extern int __must_check fastcall mutex_lock_interruptible(struct mutex *lock); - #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass); extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); + +#define mutex_lock(lock) mutex_lock_nested(lock, 0) +#define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0) #else +extern void fastcall mutex_lock(struct mutex *lock); +extern int __must_check fastcall mutex_lock_interruptible(struct mutex *lock); + # define mutex_lock_nested(lock, subclass) mutex_lock(lock) # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) #endif diff --git a/include/linux/namei.h b/include/linux/namei.h index 6c38efb..4cb4f8d 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -81,8 +81,8 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry extern struct file *nameidata_to_filp(struct nameidata *nd, int flags); extern void release_open_intent(struct nameidata *); -extern struct dentry * lookup_one_len(const char *, struct dentry *, int); -extern struct dentry *lookup_one_len_kern(const char *, struct dentry *, int); +extern struct dentry *lookup_one_len(const char *, struct dentry *, int); +extern struct dentry *lookup_one_noperm(const char *, struct dentry *); extern int follow_down(struct vfsmount **, struct dentry **); extern int follow_up(struct vfsmount **, struct dentry **); diff --git a/include/linux/nbd.h b/include/linux/nbd.h index 0f3e693..cc2b472 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -26,6 +26,7 @@ #define NBD_PRINT_DEBUG _IO( 0xab, 6 ) #define NBD_SET_SIZE_BLOCKS _IO( 0xab, 7 ) #define NBD_DISCONNECT _IO( 0xab, 8 ) +#define NBD_SET_TIMEOUT _IO( 0xab, 9 ) enum { NBD_CMD_READ = 0, @@ -65,6 +66,7 @@ struct nbd_device { int blksize; u64 bytesize; pid_t pid; /* pid of nbd-client, if attached */ + int xmit_timeout; }; #endif diff --git a/include/linux/net.h b/include/linux/net.h index c136abc..dd79cdb 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -313,6 +313,10 @@ static const struct proto_ops name##_ops = { \ #define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) +#define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \ + MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ + "-type-" __stringify(type)) + #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> extern ctl_table net_table[]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39dd83b..4a3f54e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -407,6 +407,24 @@ static inline void napi_enable(struct napi_struct *n) clear_bit(NAPI_STATE_SCHED, &n->state); } +#ifdef CONFIG_SMP +/** + * napi_synchronize - wait until NAPI is not running + * @n: napi context + * + * Wait until NAPI is done being scheduled on this context. + * Waits till any outstanding processing completes but + * does not disable future activations. + */ +static inline void napi_synchronize(const struct napi_struct *n) +{ + while (test_bit(NAPI_STATE_SCHED, &n->state)) + msleep(1); +} +#else +# define napi_synchronize(n) barrier() +#endif + /* * The DEVICE structure. * Actually, this whole structure is a big mistake. It mixes I/O @@ -827,7 +845,7 @@ static inline int dev_parse_header(const struct sk_buff *skb, { const struct net_device *dev = skb->dev; - if (!dev->header_ops->parse) + if (!dev->header_ops || !dev->header_ops->parse) return 0; return dev->header_ops->parse(skb, haddr); } @@ -978,7 +996,7 @@ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) * * Check individual transmit queue of a device with multiple transmit queues. */ -static inline int netif_subqueue_stopped(const struct net_device *dev, +static inline int __netif_subqueue_stopped(const struct net_device *dev, u16 queue_index) { #ifdef CONFIG_NETDEVICES_MULTIQUEUE @@ -989,6 +1007,11 @@ static inline int netif_subqueue_stopped(const struct net_device *dev, #endif } +static inline int netif_subqueue_stopped(const struct net_device *dev, + struct sk_buff *skb) +{ + return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); +} /** * netif_wake_subqueue - allow sending packets on subqueue diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1dd075e..16adac6 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -51,7 +51,7 @@ struct sk_buff; struct net_device; typedef unsigned int nf_hookfn(unsigned int hooknum, - struct sk_buff **skb, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)); @@ -183,7 +183,7 @@ void nf_log_packet(int pf, struct nf_loginfo *li, const char *fmt, ...); -int nf_hook_slow(int pf, unsigned int hook, struct sk_buff **pskb, +int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *), int thresh); @@ -195,7 +195,7 @@ int nf_hook_slow(int pf, unsigned int hook, struct sk_buff **pskb, * value indicates the packet has been consumed by the hook. */ static inline int nf_hook_thresh(int pf, unsigned int hook, - struct sk_buff **pskb, + struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *), int thresh, @@ -207,14 +207,14 @@ static inline int nf_hook_thresh(int pf, unsigned int hook, if (list_empty(&nf_hooks[pf][hook])) return 1; #endif - return nf_hook_slow(pf, hook, pskb, indev, outdev, okfn, thresh); + return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh); } -static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, +static inline int nf_hook(int pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return nf_hook_thresh(pf, hook, pskb, indev, outdev, okfn, INT_MIN, 1); + return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN, 1); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -241,13 +241,13 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, #define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, thresh, 1)) == 1)\ +if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, thresh, 1)) == 1)\ __ret = (okfn)(skb); \ __ret;}) #define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, INT_MIN, cond)) == 1)\ +if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, INT_MIN, cond)) == 1)\ __ret = (okfn)(skb); \ __ret;}) @@ -287,7 +287,7 @@ extern void nf_invalidate_cache(int pf); /* Call this before modifying an existing packet: ensures it is modifiable and linear to the point you care about (writable_len). Returns true or false. */ -extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); +extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); static inline void nf_csum_replace4(__sum16 *sum, __be32 from, __be32 to) { @@ -317,7 +317,7 @@ struct nf_afinfo { unsigned int dataoff, u_int8_t protocol); void (*saveroute)(const struct sk_buff *skb, struct nf_info *info); - int (*reroute)(struct sk_buff **skb, + int (*reroute)(struct sk_buff *skb, const struct nf_info *info); int route_key_size; }; @@ -371,15 +371,15 @@ extern struct proc_dir_entry *proc_net_netfilter; #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) #define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) static inline int nf_hook_thresh(int pf, unsigned int hook, - struct sk_buff **pskb, + struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *), int thresh, int cond) { - return okfn(*pskb); + return okfn(skb); } -static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, +static inline int nf_hook(int pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 26c2235..0bb5a69 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -2,7 +2,7 @@ #define _NF_CONNTRACK_AMANDA_H /* AMANDA tracking. */ -extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int matchoff, unsigned int matchlen, diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index b7c360f..47727d7 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -32,7 +32,7 @@ struct nf_conntrack_expect; /* For NAT to hook in when we find a packet which describes what other * connection we should expect. */ -extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, unsigned int matchoff, diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 08e2f49..aabd24a 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -36,27 +36,27 @@ extern void nf_conntrack_h245_expect(struct nf_conn *new, struct nf_conntrack_expect *this); extern void nf_conntrack_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this); -extern int (*set_h245_addr_hook) (struct sk_buff **pskb, +extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_conntrack_address *addr, __be16 port); -extern int (*set_h225_addr_hook) (struct sk_buff **pskb, +extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_conntrack_address *addr, __be16 port); -extern int (*set_sig_addr_hook) (struct sk_buff **pskb, +extern int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, TransportAddress *taddr, int count); -extern int (*set_ras_addr_hook) (struct sk_buff **pskb, +extern int (*set_ras_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, TransportAddress *taddr, int count); -extern int (*nat_rtp_rtcp_hook) (struct sk_buff **pskb, +extern int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int dataoff, @@ -64,24 +64,24 @@ extern int (*nat_rtp_rtcp_hook) (struct sk_buff **pskb, __be16 port, __be16 rtp_port, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp); -extern int (*nat_t120_hook) (struct sk_buff **pskb, struct nf_conn *ct, +extern int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); -extern int (*nat_h245_hook) (struct sk_buff **pskb, struct nf_conn *ct, +extern int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); -extern int (*nat_callforwarding_hook) (struct sk_buff **pskb, +extern int (*nat_callforwarding_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); -extern int (*nat_q931_hook) (struct sk_buff **pskb, struct nf_conn *ct, +extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index 2ab6b82..36282bf 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -5,7 +5,7 @@ #define IRC_PORT 6667 -extern unsigned int (*nf_nat_irc_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int matchoff, unsigned int matchlen, diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index c93061f..2343549 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -301,13 +301,13 @@ struct nf_conn; struct nf_conntrack_expect; extern int -(*nf_nat_pptp_hook_outbound)(struct sk_buff **pskb, +(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); extern int -(*nf_nat_pptp_hook_inbound)(struct sk_buff **pskb, +(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index bb7f204..9fff197 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -21,11 +21,11 @@ enum sip_header_pos { POS_SDP_HEADER, }; -extern unsigned int (*nf_nat_sip_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, struct nf_conn *ct, const char **dptr); -extern unsigned int (*nf_nat_sdp_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_sdp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, struct nf_conntrack_expect *exp, const char *dptr); diff --git a/include/linux/netfilter/nf_conntrack_tftp.h b/include/linux/netfilter/nf_conntrack_tftp.h index 0d79b7a..c78d38f 100644 --- a/include/linux/netfilter/nf_conntrack_tftp.h +++ b/include/linux/netfilter/nf_conntrack_tftp.h @@ -13,7 +13,7 @@ struct tftphdr { #define TFTP_OPCODE_ACK 4 #define TFTP_OPCODE_ERROR 5 -extern unsigned int (*nf_nat_tftp_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_tftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 64f425a8..03e6ce9 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -191,7 +191,7 @@ struct xt_target /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ - unsigned int (*target)(struct sk_buff **pskb, + unsigned int (*target)(struct sk_buff *skb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, diff --git a/include/linux/netfilter/xt_sctp.h b/include/linux/netfilter/xt_sctp.h index b157897..dd5a4fd 100644 --- a/include/linux/netfilter/xt_sctp.h +++ b/include/linux/netfilter/xt_sctp.h @@ -7,9 +7,6 @@ #define XT_SCTP_VALID_FLAGS 0x07 -#define ELEMCOUNT(x) (sizeof(x)/sizeof(x[0])) - - struct xt_sctp_flag_info { u_int8_t chunktype; u_int8_t flag; @@ -59,21 +56,21 @@ struct xt_sctp_info { #define SCTP_CHUNKMAP_RESET(chunkmap) \ do { \ int i; \ - for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + for (i = 0; i < ARRAY_SIZE(chunkmap); i++) \ chunkmap[i] = 0; \ } while (0) #define SCTP_CHUNKMAP_SET_ALL(chunkmap) \ do { \ int i; \ - for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + for (i = 0; i < ARRAY_SIZE(chunkmap); i++) \ chunkmap[i] = ~0; \ } while (0) #define SCTP_CHUNKMAP_COPY(destmap, srcmap) \ do { \ int i; \ - for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + for (i = 0; i < ARRAY_SIZE(srcmap); i++) \ destmap[i] = srcmap[i]; \ } while (0) @@ -81,7 +78,7 @@ struct xt_sctp_info { ({ \ int i; \ int flag = 1; \ - for (i = 0; i < ELEMCOUNT(chunkmap); i++) { \ + for (i = 0; i < ARRAY_SIZE(chunkmap); i++) { \ if (chunkmap[i]) { \ flag = 0; \ break; \ @@ -94,7 +91,7 @@ struct xt_sctp_info { ({ \ int i; \ int flag = 1; \ - for (i = 0; i < ELEMCOUNT(chunkmap); i++) { \ + for (i = 0; i < ARRAY_SIZE(chunkmap); i++) { \ if (chunkmap[i] != ~0) { \ flag = 0; \ break; \ diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 584cd1b..2fc73fa 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -287,7 +287,7 @@ struct arpt_error extern int arpt_register_table(struct arpt_table *table, const struct arpt_replace *repl); extern void arpt_unregister_table(struct arpt_table *table); -extern unsigned int arpt_do_table(struct sk_buff **pskb, +extern unsigned int arpt_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 94e0a7d..892f5b7 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -237,7 +237,7 @@ struct ebt_target struct list_head list; const char name[EBT_FUNCTION_MAXNAMELEN]; /* returns one of the standard verdicts */ - int (*target)(struct sk_buff **pskb, unsigned int hooknr, + int (*target)(struct sk_buff *skb, unsigned int hooknr, const struct net_device *in, const struct net_device *out, const void *targetdata, unsigned int datalen); /* 0 == let it in */ @@ -294,7 +294,7 @@ extern int ebt_register_watcher(struct ebt_watcher *watcher); extern void ebt_unregister_watcher(struct ebt_watcher *watcher); extern int ebt_register_target(struct ebt_target *target); extern void ebt_unregister_target(struct ebt_target *target); -extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff **pskb, +extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, struct ebt_table *table); diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index ceae87a..1a63adf 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -75,8 +75,8 @@ enum nf_ip_hook_priorities { #define SO_ORIGINAL_DST 80 #ifdef __KERNEL__ -extern int ip_route_me_harder(struct sk_buff **pskb, unsigned addr_type); -extern int ip_xfrm_me_harder(struct sk_buff **pskb); +extern int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); +extern int ip_xfrm_me_harder(struct sk_buff *skb); extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__KERNEL__*/ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index e992cd6..d79ed69 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -337,7 +337,7 @@ struct ipt_error .target.errorname = "ERROR", \ } -extern unsigned int ipt_do_table(struct sk_buff **pskb, +extern unsigned int ipt_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 9a720f0..7dc481c 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -336,7 +336,7 @@ extern void ip6t_init(void) __init; extern int ip6t_register_table(struct xt_table *table, const struct ip6t_replace *repl); extern void ip6t_unregister_table(struct xt_table *table); -extern unsigned int ip6t_do_table(struct sk_buff **pskb, +extern unsigned int ip6t_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7250eea..e82a6eb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -47,10 +47,8 @@ #include <linux/nfs3.h> #include <linux/nfs4.h> #include <linux/nfs_xdr.h> - #include <linux/nfs_fs_sb.h> -#include <linux/rwsem.h> #include <linux/mempool.h> /* @@ -77,6 +75,9 @@ struct nfs_open_context { struct nfs4_state *state; fl_owner_t lockowner; int mode; + + unsigned long flags; +#define NFS_CONTEXT_ERROR_WRITE (0) int error; struct list_head list; @@ -133,11 +134,6 @@ struct nfs_inode { * server. */ unsigned long cache_change_attribute; - /* - * Counter indicating the number of outstanding requests that - * will cause a file data update. - */ - atomic_t data_updates; struct rb_root access_cache; struct list_head access_cache_entry_lru; @@ -164,6 +160,12 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Number of in-flight sillydelete RPC calls */ + atomic_t silly_count; + /* List of deferred sillydelete requests */ + struct hlist_head silly_list; + wait_queue_head_t waitqueue; + #ifdef CONFIG_NFS_V4 struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -205,27 +207,18 @@ static inline struct nfs_inode *NFS_I(struct inode *inode) #define NFS_CLIENT(inode) (NFS_SERVER(inode)->client) #define NFS_PROTO(inode) (NFS_SERVER(inode)->nfs_client->rpc_ops) #define NFS_COOKIEVERF(inode) (NFS_I(inode)->cookieverf) -#define NFS_READTIME(inode) (NFS_I(inode)->read_cache_jiffies) -#define NFS_CHANGE_ATTR(inode) (NFS_I(inode)->change_attr) -#define NFS_ATTRTIMEO(inode) (NFS_I(inode)->attrtimeo) #define NFS_MINATTRTIMEO(inode) \ (S_ISDIR(inode->i_mode)? NFS_SERVER(inode)->acdirmin \ : NFS_SERVER(inode)->acregmin) #define NFS_MAXATTRTIMEO(inode) \ (S_ISDIR(inode->i_mode)? NFS_SERVER(inode)->acdirmax \ : NFS_SERVER(inode)->acregmax) -#define NFS_ATTRTIMEO_UPDATE(inode) (NFS_I(inode)->attrtimeo_timestamp) #define NFS_FLAGS(inode) (NFS_I(inode)->flags) #define NFS_STALE(inode) (test_bit(NFS_INO_STALE, &NFS_FLAGS(inode))) #define NFS_FILEID(inode) (NFS_I(inode)->fileid) -static inline int nfs_caches_unstable(struct inode *inode) -{ - return atomic_read(&NFS_I(inode)->data_updates) != 0; -} - static inline void nfs_mark_for_revalidate(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); @@ -237,12 +230,6 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) spin_unlock(&inode->i_lock); } -static inline void NFS_CACHEINV(struct inode *inode) -{ - if (!nfs_caches_unstable(inode)) - nfs_mark_for_revalidate(inode); -} - static inline int nfs_server_capable(struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; @@ -253,28 +240,33 @@ static inline int NFS_USE_READDIRPLUS(struct inode *inode) return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode)); } +static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) +{ + dentry->d_time = verf; +} + /** * nfs_save_change_attribute - Returns the inode attribute change cookie - * @inode - pointer to inode + * @dir - pointer to parent directory inode * The "change attribute" is updated every time we finish an operation * that will result in a metadata change on the server. */ -static inline long nfs_save_change_attribute(struct inode *inode) +static inline unsigned long nfs_save_change_attribute(struct inode *dir) { - return NFS_I(inode)->cache_change_attribute; + return NFS_I(dir)->cache_change_attribute; } /** - * nfs_verify_change_attribute - Detects NFS inode cache updates - * @inode - pointer to inode + * nfs_verify_change_attribute - Detects NFS remote directory changes + * @dir - pointer to parent directory inode * @chattr - previously saved change attribute - * Return "false" if metadata has been updated (or is in the process of - * being updated) since the change attribute was saved. + * Return "false" if the verifiers doesn't match the change attribute. + * This would usually indicate that the directory contents have changed on + * the server, and that any dentries need revalidating. */ -static inline int nfs_verify_change_attribute(struct inode *inode, unsigned long chattr) +static inline int nfs_verify_change_attribute(struct inode *dir, unsigned long chattr) { - return !nfs_caches_unstable(inode) - && time_after_eq(chattr, NFS_I(inode)->cache_change_attribute); + return chattr == NFS_I(dir)->cache_change_attribute; } /* @@ -283,15 +275,14 @@ static inline int nfs_verify_change_attribute(struct inode *inode, unsigned long extern int nfs_sync_mapping(struct address_space *mapping); extern void nfs_zap_mapping(struct inode *inode, struct address_space *mapping); extern void nfs_zap_caches(struct inode *); +extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); +extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); extern int nfs_permission(struct inode *, int, struct nameidata *); -extern int nfs_access_get_cached(struct inode *, struct rpc_cred *, struct nfs_access_entry *); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); -extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); @@ -301,13 +292,10 @@ extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *map extern int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); -extern void nfs_begin_attr_update(struct inode *); -extern void nfs_end_attr_update(struct inode *); -extern void nfs_begin_data_update(struct inode *); -extern void nfs_end_data_update(struct inode *); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode); +extern u64 nfs_compat_user_ino64(u64 fileid); /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern __be32 root_nfs_parse_addr(char *name); /*__init*/ @@ -328,14 +316,15 @@ extern const struct inode_operations nfs3_file_inode_operations; extern const struct file_operations nfs_file_operations; extern const struct address_space_operations nfs_file_aops; -static inline struct rpc_cred *nfs_file_cred(struct file *file) +static inline struct nfs_open_context *nfs_file_open_context(struct file *filp) { - if (file != NULL) { - struct nfs_open_context *ctx; + return filp->private_data; +} - ctx = (struct nfs_open_context*)file->private_data; - return ctx->cred; - } +static inline struct rpc_cred *nfs_file_cred(struct file *file) +{ + if (file != NULL) + return nfs_file_open_context(file)->cred; return NULL; } @@ -378,6 +367,8 @@ extern const struct file_operations nfs_dir_operations; extern struct dentry_operations nfs_dentry_operations; extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); +extern int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags); +extern void nfs_access_zap_cache(struct inode *inode); /* * linux/fs/nfs/symlink.c @@ -409,6 +400,8 @@ extern void nfs_release_automount_timer(void); */ extern int nfs_async_unlink(struct inode *dir, struct dentry *dentry); extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); +extern void nfs_block_sillyrename(struct dentry *dentry); +extern void nfs_unblock_sillyrename(struct dentry *dentry); /* * linux/fs/nfs/write.c @@ -420,15 +413,14 @@ extern int nfs_flush_incompatible(struct file *file, struct page *page); extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); extern void nfs_writedata_release(void *); -extern int nfs_set_page_dirty(struct page *); /* * Try to write back everything synchronously (but check the * return value!) */ extern long nfs_sync_mapping_wait(struct address_space *, struct writeback_control *, int); -extern int nfs_sync_mapping_range(struct address_space *, loff_t, loff_t, int); extern int nfs_wb_all(struct inode *inode); +extern int nfs_wb_nocommit(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page* page); extern int nfs_wb_page_priority(struct inode *inode, struct page* page, int how); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 78e6079..30dbcc1 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -30,7 +30,6 @@ #define PG_BUSY 0 #define PG_NEED_COMMIT 1 #define PG_NEED_RESCHED 2 -#define PG_NEED_FLUSH 3 struct nfs_inode; struct nfs_page { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index cf74a4d..daab252 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -62,7 +62,8 @@ struct nfs_fattr { #define NFS_ATTR_FATTR 0x0002 /* post-op attributes */ #define NFS_ATTR_FATTR_V3 0x0004 /* NFSv3 attributes */ #define NFS_ATTR_FATTR_V4 0x0008 /* NFSv4 change attribute */ -#define NFS_ATTR_FATTR_V4_REFERRAL 0x0010 /* NFSv4 referral */ +#define NFS_ATTR_WCC_V4 0x0010 /* pre-op change attribute */ +#define NFS_ATTR_FATTR_V4_REFERRAL 0x0020 /* NFSv4 referral */ /* * Info on the file system @@ -538,10 +539,13 @@ typedef u64 clientid4; struct nfs4_accessargs { const struct nfs_fh * fh; + const u32 * bitmask; u32 access; }; struct nfs4_accessres { + const struct nfs_server * server; + struct nfs_fattr * fattr; u32 supported; u32 access; }; diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 5cd1924..bcb7aba 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -127,17 +127,9 @@ void nfsd_export_shutdown(void); void nfsd_export_flush(void); void exp_readlock(void); void exp_readunlock(void); -struct svc_export * exp_get_by_name(struct auth_domain *clp, - struct vfsmount *mnt, - struct dentry *dentry, - struct cache_req *reqp); struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, struct vfsmount *, struct dentry *); -struct svc_export * exp_parent(struct auth_domain *clp, - struct vfsmount *mnt, - struct dentry *dentry, - struct cache_req *reqp); struct svc_export * rqst_exp_parent(struct svc_rqst *, struct vfsmount *mnt, struct dentry *dentry); @@ -157,9 +149,6 @@ static inline void exp_get(struct svc_export *exp) { cache_get(&exp->h); } -extern struct svc_export * -exp_find(struct auth_domain *clp, int fsid_type, u32 *fsidv, - struct cache_req *reqp); struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *); #endif /* __KERNEL__ */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index e452256..604a0d7 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -153,19 +153,21 @@ extern int nfsd_max_blksize; */ #ifdef CONFIG_NFSD_V4 extern unsigned int max_delegations; -void nfs4_state_init(void); -int nfs4_state_start(void); +int nfs4_state_init(void); +void nfsd4_free_slabs(void); +void nfs4_state_start(void); void nfs4_state_shutdown(void); time_t nfs4_lease_time(void); void nfs4_reset_lease(time_t leasetime); int nfs4_reset_recoverydir(char *recdir); #else -static inline void nfs4_state_init(void){}; -static inline int nfs4_state_start(void){return 0;} -static inline void nfs4_state_shutdown(void){} -static inline time_t nfs4_lease_time(void){return 0;} -static inline void nfs4_reset_lease(time_t leasetime){} -static inline int nfs4_reset_recoverydir(char *recdir) {return 0;} +static inline int nfs4_state_init(void) { return 0; } +static inline void nfsd4_free_slabs(void) { } +static inline void nfs4_state_start(void) { } +static inline void nfs4_state_shutdown(void) { } +static inline time_t nfs4_lease_time(void) { return 0; } +static inline void nfs4_reset_lease(time_t leasetime) { } +static inline int nfs4_reset_recoverydir(char *recdir) { return 0; } #endif /* diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 11e568e..d1941cb 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -150,17 +150,7 @@ typedef struct svc_fh { struct timespec fh_pre_ctime; /* ctime before oper */ /* Post-op attributes saved in fh_unlock */ - umode_t fh_post_mode; /* i_mode */ - nlink_t fh_post_nlink; /* i_nlink */ - uid_t fh_post_uid; /* i_uid */ - gid_t fh_post_gid; /* i_gid */ - __u64 fh_post_size; /* i_size */ - unsigned long fh_post_blocks; /* i_blocks */ - unsigned long fh_post_blksize;/* i_blksize */ - __be32 fh_post_rdev[2];/* i_rdev */ - struct timespec fh_post_atime; /* i_atime */ - struct timespec fh_post_mtime; /* i_mtime */ - struct timespec fh_post_ctime; /* i_ctime */ + struct kstat fh_post_attr; /* full attrs after operation */ #endif /* CONFIG_NFSD_V3 */ } svc_fh; @@ -297,36 +287,12 @@ fill_pre_wcc(struct svc_fh *fhp) if (!fhp->fh_pre_saved) { fhp->fh_pre_mtime = inode->i_mtime; fhp->fh_pre_ctime = inode->i_ctime; - fhp->fh_pre_size = inode->i_size; - fhp->fh_pre_saved = 1; + fhp->fh_pre_size = inode->i_size; + fhp->fh_pre_saved = 1; } } -/* - * Fill in the post_op attr for the wcc data - */ -static inline void -fill_post_wcc(struct svc_fh *fhp) -{ - struct inode *inode = fhp->fh_dentry->d_inode; - - if (fhp->fh_post_saved) - printk("nfsd: inode locked twice during operation.\n"); - - fhp->fh_post_mode = inode->i_mode; - fhp->fh_post_nlink = inode->i_nlink; - fhp->fh_post_uid = inode->i_uid; - fhp->fh_post_gid = inode->i_gid; - fhp->fh_post_size = inode->i_size; - fhp->fh_post_blksize = BLOCK_SIZE; - fhp->fh_post_blocks = inode->i_blocks; - fhp->fh_post_rdev[0] = htonl((u32)imajor(inode)); - fhp->fh_post_rdev[1] = htonl((u32)iminor(inode)); - fhp->fh_post_atime = inode->i_atime; - fhp->fh_post_mtime = inode->i_mtime; - fhp->fh_post_ctime = inode->i_ctime; - fhp->fh_post_saved = 1; -} +extern void fill_post_wcc(struct svc_fh *); #else #define fill_pre_wcc(ignored) #define fill_post_wcc(notused) diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 1b65326..b0ddfb4 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -428,8 +428,8 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) cinfo->atomic = 1; cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec; cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec; - cinfo->after_ctime_sec = fhp->fh_post_ctime.tv_sec; - cinfo->after_ctime_nsec = fhp->fh_post_ctime.tv_nsec; + cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec; + cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec; } int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); diff --git a/include/linux/nls.h b/include/linux/nls.h index 816c04a..6a88220 100644 --- a/include/linux/nls.h +++ b/include/linux/nls.h @@ -7,13 +7,13 @@ typedef __u16 wchar_t; struct nls_table { - char *charset; - char *alias; + const char *charset; + const char *alias; int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen); int (*char2uni) (const unsigned char *rawstring, int boundlen, wchar_t *uni); - unsigned char *charset2lower; - unsigned char *charset2upper; + const unsigned char *charset2lower; + const unsigned char *charset2upper; struct module *owner; struct nls_table *next; }; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 52c54a5..905e18f 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -338,31 +338,88 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, #endif /* MAX_NUMNODES */ /* + * Bitmasks that are kept for all the nodes. + */ +enum node_states { + N_POSSIBLE, /* The node could become online at some point */ + N_ONLINE, /* The node is online */ + N_NORMAL_MEMORY, /* The node has regular memory */ +#ifdef CONFIG_HIGHMEM + N_HIGH_MEMORY, /* The node has regular or high memory */ +#else + N_HIGH_MEMORY = N_NORMAL_MEMORY, +#endif + N_CPU, /* The node has one or more cpus */ + NR_NODE_STATES +}; + +/* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ -extern nodemask_t node_online_map; -extern nodemask_t node_possible_map; +extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -#define num_online_nodes() nodes_weight(node_online_map) -#define num_possible_nodes() nodes_weight(node_possible_map) -#define node_online(node) node_isset((node), node_online_map) -#define node_possible(node) node_isset((node), node_possible_map) -#define first_online_node first_node(node_online_map) -#define next_online_node(nid) next_node((nid), node_online_map) +static inline int node_state(int node, enum node_states state) +{ + return node_isset(node, node_states[state]); +} + +static inline void node_set_state(int node, enum node_states state) +{ + __node_set(node, &node_states[state]); +} + +static inline void node_clear_state(int node, enum node_states state) +{ + __node_clear(node, &node_states[state]); +} + +static inline int num_node_state(enum node_states state) +{ + return nodes_weight(node_states[state]); +} + +#define for_each_node_state(__node, __state) \ + for_each_node_mask((__node), node_states[__state]) + +#define first_online_node first_node(node_states[N_ONLINE]) +#define next_online_node(nid) next_node((nid), node_states[N_ONLINE]) + extern int nr_node_ids; #else -#define num_online_nodes() 1 -#define num_possible_nodes() 1 -#define node_online(node) ((node) == 0) -#define node_possible(node) ((node) == 0) + +static inline int node_state(int node, enum node_states state) +{ + return node == 0; +} + +static inline void node_set_state(int node, enum node_states state) +{ +} + +static inline void node_clear_state(int node, enum node_states state) +{ +} + +static inline int num_node_state(enum node_states state) +{ + return 1; +} + +#define for_each_node_state(node, __state) \ + for ( (node) = 0; (node) == 0; (node) = 1) + #define first_online_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1 + #endif +#define node_online_map node_states[N_ONLINE] +#define node_possible_map node_states[N_POSSIBLE] + #define any_online_node(mask) \ ({ \ int node; \ @@ -372,10 +429,15 @@ extern int nr_node_ids; node; \ }) -#define node_set_online(node) set_bit((node), node_online_map.bits) -#define node_set_offline(node) clear_bit((node), node_online_map.bits) +#define num_online_nodes() num_node_state(N_ONLINE) +#define num_possible_nodes() num_node_state(N_POSSIBLE) +#define node_online(node) node_state((node), N_ONLINE) +#define node_possible(node) node_state((node), N_POSSIBLE) + +#define node_set_online(node) node_set_state((node), N_ONLINE) +#define node_set_offline(node) node_clear_state((node), N_ONLINE) -#define for_each_node(node) for_each_node_mask((node), node_possible_map) -#define for_each_online_node(node) for_each_node_mask((node), node_online_map) +#define for_each_node(node) for_each_node_state(node, N_POSSIBLE) +#define for_each_online_node(node) for_each_node_state(node, N_ONLINE) #endif /* __LINUX_NODEMASK_H */ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index fad7ff1..0c40cc0 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -231,5 +231,22 @@ static inline int notifier_to_errno(int ret) #define PM_SUSPEND_PREPARE 0x0003 /* Going to suspend the system */ #define PM_POST_SUSPEND 0x0004 /* Suspend finished */ +/* Console keyboard events. + * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and + * KBD_KEYSYM. */ +#define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ +#define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ +#define KBD_UNICODE 0x0003 /* Keyboard unicode */ +#define KBD_KEYSYM 0x0004 /* Keyboard keysym */ +#define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ + +extern struct blocking_notifier_head reboot_notifier_list; + +/* Virtual Terminal events. */ +#define VT_ALLOCATE 0x0001 /* Console got allocated */ +#define VT_DEALLOCATE 0x0002 /* Console will be deallocated */ +#define VT_WRITE 0x0003 /* A char got output */ +#define VT_UPDATE 0x0004 /* A bigger update occurred */ + #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index bec4485..0e66b57 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -23,7 +23,6 @@ struct pid_namespace; */ struct nsproxy { atomic_t count; - spinlock_t nslock; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; @@ -33,8 +32,39 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; +/* + * the namespaces access rules are: + * + * 1. only current task is allowed to change tsk->nsproxy pointer or + * any pointer on the nsproxy itself + * + * 2. when accessing (i.e. reading) current task's namespaces - no + * precautions should be taken - just dereference the pointers + * + * 3. the access to other task namespaces is performed like this + * rcu_read_lock(); + * nsproxy = task_nsproxy(tsk); + * if (nsproxy != NULL) { + * / * + * * work with the namespaces here + * * e.g. get the reference on one of them + * * / + * } / * + * * NULL task_nsproxy() means that this task is + * * almost dead (zombie) + * * / + * rcu_read_unlock(); + * + */ + +static inline struct nsproxy *task_nsproxy(struct task_struct *tsk) +{ + return rcu_dereference(tsk->nsproxy); +} + int copy_namespaces(unsigned long flags, struct task_struct *tsk); -void get_task_namespaces(struct task_struct *tsk); +void exit_task_namespaces(struct task_struct *tsk); +void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct fs_struct *); @@ -46,14 +76,15 @@ static inline void put_nsproxy(struct nsproxy *ns) } } -static inline void exit_task_namespaces(struct task_struct *p) +static inline void get_nsproxy(struct nsproxy *ns) { - struct nsproxy *ns = p->nsproxy; - if (ns) { - task_lock(p); - p->nsproxy = NULL; - task_unlock(p); - put_nsproxy(ns); - } + atomic_inc(&ns->count); } + +#ifdef CONFIG_CGROUP_NS +int ns_cgroup_clone(struct task_struct *tsk); +#else +static inline int ns_cgroup_clone(struct task_struct *tsk) { return 0; } +#endif + #endif diff --git a/include/linux/of.h b/include/linux/of.h index 6df80e9..5c39b92 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -16,8 +16,8 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/types.h> +#include <linux/bitops.h> -#include <asm/bitops.h> #include <asm/prom.h> /* flag descriptions */ diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 91bf84b..212bffb 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -22,5 +22,10 @@ extern int of_device_register(struct of_device *ofdev); extern void of_device_unregister(struct of_device *ofdev); extern void of_release_dev(struct device *dev); +static inline void of_device_free(struct of_device *dev) +{ + of_release_dev(&dev->dev); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_OF_DEVICE_H */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 448f70b..a8efcfe 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -48,6 +48,10 @@ struct of_platform_driver #define to_of_platform_driver(drv) \ container_of(drv,struct of_platform_driver, driver) +extern int of_register_driver(struct of_platform_driver *drv, + struct bus_type *bus); +extern void of_unregister_driver(struct of_platform_driver *drv); + #include <asm/of_platform.h> extern struct of_device *of_find_device_by_node(struct device_node *np); diff --git a/include/linux/oom.h b/include/linux/oom.h index ad76463..3852436 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -7,4 +7,28 @@ #define OOM_ADJUST_MIN (-16) #define OOM_ADJUST_MAX 15 -#endif +#ifdef __KERNEL__ + +#include <linux/types.h> + +struct zonelist; +struct notifier_block; + +/* + * Types of limitations to the nodes from which allocations may occur + */ +enum oom_constraint { + CONSTRAINT_NONE, + CONSTRAINT_CPUSET, + CONSTRAINT_MEMORY_POLICY, +}; + +extern int try_set_zone_oom(struct zonelist *zonelist); +extern void clear_zonelist_oom(struct zonelist *zonelist); + +extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order); +extern int register_oom_notifier(struct notifier_block *nb); +extern int unregister_oom_notifier(struct notifier_block *nb); + +#endif /* __KERNEL__*/ +#endif /* _INCLUDE_LINUX_OOM_H */ diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h new file mode 100644 index 0000000..051c1b1 --- /dev/null +++ b/include/linux/page-isolation.h @@ -0,0 +1,37 @@ +#ifndef __LINUX_PAGEISOLATION_H +#define __LINUX_PAGEISOLATION_H + +/* + * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. + * If specified range includes migrate types other than MOVABLE, + * this will fail with -EBUSY. + * + * For isolating all pages in the range finally, the caller have to + * free all pages in the range. test_page_isolated() can be used for + * test it. + */ +extern int +start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); + +/* + * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. + * target range is [start_pfn, end_pfn) + */ +extern int +undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); + +/* + * test all pages in [start_pfn, end_pfn)are isolated or not. + */ +extern int +test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); + +/* + * Internal funcs.Changes pageblock's migrate type. + * Please use make_pagetype_isolated()/make_pagetype_movable(). + */ +extern int set_migratetype_isolate(struct page *page); +extern void unset_migratetype_isolate(struct page *page); + + +#endif diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h new file mode 100644 index 0000000..e875905 --- /dev/null +++ b/include/linux/pageblock-flags.h @@ -0,0 +1,75 @@ +/* + * Macros for manipulating and testing flags related to a + * pageblock_nr_pages number of pages. + * + * 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 version 2 of the License + * + * 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2006 + * + * Original author, Mel Gorman + * Major cleanups and reduction of bit operations, Andy Whitcroft + */ +#ifndef PAGEBLOCK_FLAGS_H +#define PAGEBLOCK_FLAGS_H + +#include <linux/types.h> + +/* Macro to aid the definition of ranges of bits */ +#define PB_range(name, required_bits) \ + name, name ## _end = (name + required_bits) - 1 + +/* Bit indices that affect a whole block of pages */ +enum pageblock_bits { + PB_range(PB_migrate, 3), /* 3 bits required for migrate types */ + NR_PAGEBLOCK_BITS +}; + +#ifdef CONFIG_HUGETLB_PAGE + +#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE + +/* Huge page sizes are variable */ +extern int pageblock_order; + +#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +/* Huge pages are a constant size */ +#define pageblock_order HUGETLB_PAGE_ORDER + +#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +#else /* CONFIG_HUGETLB_PAGE */ + +/* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ +#define pageblock_order (MAX_ORDER-1) + +#endif /* CONFIG_HUGETLB_PAGE */ + +#define pageblock_nr_pages (1UL << pageblock_order) + +/* Forward declaration */ +struct page; + +/* Declarations for getting and setting flags. See mm/page_alloc.c */ +unsigned long get_pageblock_flags_group(struct page *page, + int start_bitidx, int end_bitidx); +void set_pageblock_flags_group(struct page *page, unsigned long flags, + int start_bitidx, int end_bitidx); + +#define get_pageblock_flags(page) \ + get_pageblock_flags_group(page, 0, NR_PAGEBLOCK_BITS-1) +#define set_pageblock_flags(page) \ + set_pageblock_flags_group(page, 0, NR_PAGEBLOCK_BITS-1) + +#endif /* PAGEBLOCK_FLAGS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8a83537..db8a410 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -84,11 +84,11 @@ static inline struct page *page_cache_alloc_cold(struct address_space *x) typedef int filler_t(void *, struct page *); extern struct page * find_get_page(struct address_space *mapping, - unsigned long index); + pgoff_t index); extern struct page * find_lock_page(struct address_space *mapping, - unsigned long index); + pgoff_t index); extern struct page * find_or_create_page(struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp_mask); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, @@ -96,44 +96,47 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages); +struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index); + /* * Returns locked page at given index in given cache, creating it if needed. */ -static inline struct page *grab_cache_page(struct address_space *mapping, unsigned long index) +static inline struct page *grab_cache_page(struct address_space *mapping, + pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } extern struct page * grab_cache_page_nowait(struct address_space *mapping, - unsigned long index); + pgoff_t index); extern struct page * read_cache_page_async(struct address_space *mapping, - unsigned long index, filler_t *filler, + pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, - unsigned long index, filler_t *filler, + pgoff_t index, filler_t *filler, void *data); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page_async( struct address_space *mapping, - unsigned long index, void *data) + pgoff_t index, void *data) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return read_cache_page_async(mapping, index, filler, data); } static inline struct page *read_mapping_page(struct address_space *mapping, - unsigned long index, void *data) + pgoff_t index, void *data) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return read_cache_page(mapping, index, filler, data); } int add_to_page_cache(struct page *page, struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp_mask); extern void remove_from_page_cache(struct page *page); extern void __remove_from_page_cache(struct page *page); @@ -218,6 +221,9 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size) { int ret; + if (unlikely(size == 0)) + return 0; + /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. @@ -237,19 +243,23 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size) return ret; } -static inline void fault_in_pages_readable(const char __user *uaddr, int size) +static inline int fault_in_pages_readable(const char __user *uaddr, int size) { volatile char c; int ret; + if (unlikely(size == 0)) + return 0; + ret = __get_user(c, uaddr); if (ret == 0) { const char __user *end = uaddr + size - 1; if (((unsigned long)uaddr & PAGE_MASK) != ((unsigned long)end & PAGE_MASK)) - __get_user(c, end); + ret = __get_user(c, end); } + return ret; } #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/parport.h b/include/linux/parport.h index 9cdd694..ec3f765 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -510,7 +510,6 @@ extern struct pardevice *parport_open (int devnum, const char *name, int flags, void *handle); extern void parport_close (struct pardevice *dev); extern ssize_t parport_device_id (int devnum, char *buffer, size_t len); -extern int parport_device_num (int parport, int mux, int daisy); extern void parport_daisy_deselect_all (struct parport *port); extern int parport_daisy_select (struct parport *port, int daisy, int mode); diff --git a/include/linux/pci.h b/include/linux/pci.h index 768b933..5d2281f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -141,6 +141,7 @@ struct pci_dev { unsigned int class; /* 3 bytes: (base,sub,prog-if) */ u8 revision; /* PCI revision, low byte of class word */ u8 hdr_type; /* PCI header type (`multi' flag masked out) */ + u8 pcie_type; /* PCI-E device/port type */ u8 rom_base_reg; /* which config register controls the ROM */ u8 pin; /* which interrupt pin this device uses */ @@ -183,6 +184,7 @@ struct pci_dev { unsigned int msi_enabled:1; unsigned int msix_enabled:1; unsigned int is_managed:1; + unsigned int is_pcie:1; atomic_t enable_cnt; /* pci_enable_device has been called */ u32 saved_config_space[16]; /* config space saved at suspend time */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 87439ad..4e10a07 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1467,6 +1467,8 @@ #define PCI_DEVICE_ID_TOSHIBA_TC86C001_MISC 0x0108 #define PCI_DEVICE_ID_TOSHIBA_SPIDER_NET 0x01b3 +#define PCI_VENDOR_ID_ATTO 0x117c + #define PCI_VENDOR_ID_RICOH 0x1180 #define PCI_DEVICE_ID_RICOH_RL5C465 0x0465 #define PCI_DEVICE_ID_RICOH_RL5C466 0x0466 @@ -1634,6 +1636,7 @@ #define PCI_DEVICE_ID_ITE_8211 0x8211 #define PCI_DEVICE_ID_ITE_8212 0x8212 #define PCI_DEVICE_ID_ITE_8213 0x8213 +#define PCI_DEVICE_ID_ITE_8152 0x8152 #define PCI_DEVICE_ID_ITE_8872 0x8872 #define PCI_DEVICE_ID_ITE_IT8330G_0 0xe886 @@ -1940,6 +1943,7 @@ #define PCI_DEVICE_ID_TIGON3_5720 0x1658 #define PCI_DEVICE_ID_TIGON3_5721 0x1659 #define PCI_DEVICE_ID_TIGON3_5722 0x165a +#define PCI_DEVICE_ID_TIGON3_5723 0x165b #define PCI_DEVICE_ID_TIGON3_5705M 0x165d #define PCI_DEVICE_ID_TIGON3_5705M_2 0x165e #define PCI_DEVICE_ID_TIGON3_5714 0x1668 @@ -1992,6 +1996,8 @@ #define PCI_VENDOR_ID_TOPIC 0x151f #define PCI_DEVICE_ID_TOPIC_TP560 0x0000 +#define PCI_VENDOR_ID_MAINPINE 0x1522 +#define PCI_DEVICE_ID_MAINPINE_PBRIDGE 0x0100 #define PCI_VENDOR_ID_ENE 0x1524 #define PCI_DEVICE_ID_ENE_CB712_SD 0x0550 #define PCI_DEVICE_ID_ENE_CB712_SD_2 0x0551 @@ -2075,6 +2081,9 @@ #define PCI_DEVICE_ID_ARECA_1130 0x1130 #define PCI_DEVICE_ID_ARECA_1160 0x1160 #define PCI_DEVICE_ID_ARECA_1170 0x1170 +#define PCI_DEVICE_ID_ARECA_1200 0x1200 +#define PCI_DEVICE_ID_ARECA_1201 0x1201 +#define PCI_DEVICE_ID_ARECA_1202 0x1202 #define PCI_DEVICE_ID_ARECA_1210 0x1210 #define PCI_DEVICE_ID_ARECA_1220 0x1220 #define PCI_DEVICE_ID_ARECA_1230 0x1230 @@ -2318,6 +2327,8 @@ #define PCI_DEVICE_ID_INTEL_MCH_PC 0x3599 #define PCI_DEVICE_ID_INTEL_MCH_PC1 0x359a #define PCI_DEVICE_ID_INTEL_E7525_MCH 0x359e +#define PCI_DEVICE_ID_INTEL_IOAT_CNB 0x360b +#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_TOLAPAI_0 0x5031 #define PCI_DEVICE_ID_INTEL_TOLAPAI_1 0x5032 #define PCI_DEVICE_ID_INTEL_82371SB_0 0x7000 diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 3d9f709..9007ccd 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -30,10 +30,28 @@ struct percpu_counter { #define FBC_BATCH (NR_CPUS*4) #endif -void percpu_counter_init(struct percpu_counter *fbc, s64 amount); +int percpu_counter_init(struct percpu_counter *fbc, s64 amount); +int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); -void percpu_counter_mod(struct percpu_counter *fbc, s32 amount); -s64 percpu_counter_sum(struct percpu_counter *fbc); +void percpu_counter_set(struct percpu_counter *fbc, s64 amount); +void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); +s64 __percpu_counter_sum(struct percpu_counter *fbc); + +static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) +{ + __percpu_counter_add(fbc, amount, FBC_BATCH); +} + +static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) +{ + s64 ret = __percpu_counter_sum(fbc); + return ret < 0 ? 0 : ret; +} + +static inline s64 percpu_counter_sum(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc); +} static inline s64 percpu_counter_read(struct percpu_counter *fbc) { @@ -61,17 +79,28 @@ struct percpu_counter { s64 count; }; -static inline void percpu_counter_init(struct percpu_counter *fbc, s64 amount) +static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; + return 0; } +#define percpu_counter_init_irq percpu_counter_init + static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } +static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) +{ + fbc->count = amount; +} + +#define __percpu_counter_add(fbc, amount, batch) \ + percpu_counter_add(fbc, amount) + static inline void -percpu_counter_mod(struct percpu_counter *fbc, s32 amount) +percpu_counter_add(struct percpu_counter *fbc, s64 amount) { preempt_disable(); fbc->count += amount; @@ -88,21 +117,31 @@ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) return fbc->count; } -static inline s64 percpu_counter_sum(struct percpu_counter *fbc) +static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } +static inline s64 percpu_counter_sum(struct percpu_counter *fbc) +{ + return percpu_counter_read(fbc); +} + #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { - percpu_counter_mod(fbc, 1); + percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { - percpu_counter_mod(fbc, -1); + percpu_counter_add(fbc, -1); +} + +static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ diff --git a/include/linux/phantom.h b/include/linux/phantom.h index d3ebbfa..96f4048 100644 --- a/include/linux/phantom.h +++ b/include/linux/phantom.h @@ -30,7 +30,11 @@ struct phm_regs { #define PHN_SET_REG _IOW (PH_IOC_MAGIC, 1, struct phm_reg *) #define PHN_GET_REGS _IOWR(PH_IOC_MAGIC, 2, struct phm_regs *) #define PHN_SET_REGS _IOW (PH_IOC_MAGIC, 3, struct phm_regs *) -#define PH_IOC_MAXNR 3 +/* this ioctl tells the driver, that the caller is not OpenHaptics and might + * use improved registers update (no more phantom switchoffs when using + * libphantom) */ +#define PHN_NOT_OH _IO (PH_IOC_MAGIC, 4) +#define PH_IOC_MAXNR 4 #define PHN_CONTROL 0x6 /* control byte in iaddr space */ #define PHN_CTL_AMP 0x1 /* switch after torques change */ diff --git a/include/linux/pid.h b/include/linux/pid.h index 1e0e4e3..e29a900 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -40,15 +40,28 @@ enum pid_type * processes. */ -struct pid -{ - atomic_t count; + +/* + * struct upid is used to get the id of the struct pid, as it is + * seen in particular namespace. Later the struct pid is found with + * find_pid_ns() using the int nr and struct pid_namespace *ns. + */ + +struct upid { /* Try to keep pid_chain in the same cacheline as nr for find_pid */ int nr; + struct pid_namespace *ns; struct hlist_node pid_chain; +}; + +struct pid +{ + atomic_t count; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct rcu_head rcu; + int level; + struct upid numbers[1]; }; extern struct pid init_struct_pid; @@ -83,26 +96,60 @@ extern void FASTCALL(detach_pid(struct task_struct *task, enum pid_type)); extern void FASTCALL(transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type)); +struct pid_namespace; +extern struct pid_namespace init_pid_ns; + /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. + * + * find_pid_ns() finds the pid in the namespace specified + * find_pid() find the pid by its global id, i.e. in the init namespace + * find_vpid() finr the pid by its virtual id, i.e. in the current namespace + * + * see also find_task_by_pid() set in include/linux/sched.h */ -extern struct pid *FASTCALL(find_pid(int nr)); +extern struct pid *FASTCALL(find_pid_ns(int nr, struct pid_namespace *ns)); +extern struct pid *find_vpid(int nr); +extern struct pid *find_pid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); -extern struct pid *find_ge_pid(int nr); +extern struct pid *find_ge_pid(int nr, struct pid_namespace *); -extern struct pid *alloc_pid(void); +extern struct pid *alloc_pid(struct pid_namespace *ns); extern void FASTCALL(free_pid(struct pid *pid)); +extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); + +/* + * the helpers to get the pid's id seen from different namespaces + * + * pid_nr() : global id, i.e. the id seen from the init namespace; + * pid_vnr() : virtual id, i.e. the id seen from the namespace this pid + * belongs to. this only makes sence when called in the + * context of the task that belongs to the same namespace; + * pid_nr_ns() : id seen from the ns specified. + * + * see also task_xid_nr() etc in include/linux/sched.h + */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) - nr = pid->nr; + nr = pid->numbers[0].nr; + return nr; +} + +pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); + +static inline pid_t pid_vnr(struct pid *pid) +{ + pid_t nr = 0; + if (pid) + nr = pid->numbers[pid->level].nr; return nr; } diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index b9a17e0..0135c76 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -4,7 +4,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/threads.h> -#include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/kref.h> @@ -20,13 +19,21 @@ struct pid_namespace { struct pidmap pidmap[PIDMAP_ENTRIES]; int last_pid; struct task_struct *child_reaper; + struct kmem_cache *pid_cachep; + int level; + struct pid_namespace *parent; +#ifdef CONFIG_PROC_FS + struct vfsmount *proc_mnt; +#endif }; extern struct pid_namespace init_pid_ns; -static inline void get_pid_ns(struct pid_namespace *ns) +static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { - kref_get(&ns->kref); + if (ns != &init_pid_ns) + kref_get(&ns->kref); + return ns; } extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns); @@ -34,12 +41,19 @@ extern void free_pid_ns(struct kref *kref); static inline void put_pid_ns(struct pid_namespace *ns) { - kref_put(&ns->kref, free_pid_ns); + if (ns != &init_pid_ns) + kref_put(&ns->kref, free_pid_ns); } -static inline struct task_struct *child_reaper(struct task_struct *tsk) +static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { - return init_pid_ns.child_reaper; + return tsk->nsproxy->pid_ns; +} + +static inline struct task_struct *task_child_reaper(struct task_struct *tsk) +{ + BUG_ON(tsk != current); + return tsk->nsproxy->pid_ns->child_reaper; } #endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 48b71ba..09a309b 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -104,104 +104,6 @@ extern void (*pm_idle)(void); extern void (*pm_power_off)(void); extern void (*pm_power_off_prepare)(void); -typedef int __bitwise suspend_state_t; - -#define PM_SUSPEND_ON ((__force suspend_state_t) 0) -#define PM_SUSPEND_STANDBY ((__force suspend_state_t) 1) -#define PM_SUSPEND_MEM ((__force suspend_state_t) 3) -#define PM_SUSPEND_MAX ((__force suspend_state_t) 4) - -/** - * struct pm_ops - Callbacks for managing platform dependent system sleep - * states. - * - * @valid: Callback to determine if given system sleep state is supported by - * the platform. - * Valid (ie. supported) states are advertised in /sys/power/state. Note - * that it still may be impossible to enter given system sleep state if the - * conditions aren't right. - * There is the %pm_valid_only_mem function available that can be assigned - * to this if the platform only supports mem sleep. - * - * @set_target: Tell the platform which system sleep state is going to be - * entered. - * @set_target() is executed right prior to suspending devices. The - * information conveyed to the platform code by @set_target() should be - * disregarded by the platform as soon as @finish() is executed and if - * @prepare() fails. If @set_target() fails (ie. returns nonzero), - * @prepare(), @enter() and @finish() will not be called by the PM core. - * This callback is optional. However, if it is implemented, the argument - * passed to @prepare(), @enter() and @finish() is meaningless and should - * be ignored. - * - * @prepare: Prepare the platform for entering the system sleep state indicated - * by @set_target() or represented by the argument if @set_target() is not - * implemented. - * @prepare() is called right after devices have been suspended (ie. the - * appropriate .suspend() method has been executed for each device) and - * before the nonboot CPUs are disabled (it is executed with IRQs enabled). - * This callback is optional. It returns 0 on success or a negative - * error code otherwise, in which case the system cannot enter the desired - * sleep state (@enter() and @finish() will not be called in that case). - * - * @enter: Enter the system sleep state indicated by @set_target() or - * represented by the argument if @set_target() is not implemented. - * This callback is mandatory. It returns 0 on success or a negative - * error code otherwise, in which case the system cannot enter the desired - * sleep state. - * - * @finish: Called when the system has just left a sleep state, right after - * the nonboot CPUs have been enabled and before devices are resumed (it is - * executed with IRQs enabled). If @set_target() is not implemented, the - * argument represents the sleep state being left. - * This callback is optional, but should be implemented by the platforms - * that implement @prepare(). If implemented, it is always called after - * @enter() (even if @enter() fails). - */ -struct pm_ops { - int (*valid)(suspend_state_t state); - int (*set_target)(suspend_state_t state); - int (*prepare)(suspend_state_t state); - int (*enter)(suspend_state_t state); - int (*finish)(suspend_state_t state); -}; - -#ifdef CONFIG_SUSPEND -extern struct pm_ops *pm_ops; - -/** - * pm_set_ops - set platform dependent power management ops - * @pm_ops: The new power management operations to set. - */ -extern void pm_set_ops(struct pm_ops *pm_ops); -extern int pm_valid_only_mem(suspend_state_t state); - -/** - * arch_suspend_disable_irqs - disable IRQs for suspend - * - * Disables IRQs (in the default case). This is a weak symbol in the common - * code and thus allows architectures to override it if more needs to be - * done. Not called for suspend to disk. - */ -extern void arch_suspend_disable_irqs(void); - -/** - * arch_suspend_enable_irqs - enable IRQs after suspend - * - * Enables IRQs (in the default case). This is a weak symbol in the common - * code and thus allows architectures to override it if more needs to be - * done. Not called for suspend to disk. - */ -extern void arch_suspend_enable_irqs(void); - -extern int pm_suspend(suspend_state_t state); -#else /* !CONFIG_SUSPEND */ -#define suspend_valid_only_mem NULL - -static inline void pm_set_ops(struct pm_ops *pm_ops) {} -static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } -#endif /* !CONFIG_SUSPEND */ - /* * Device power management */ diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 16b46aa..664d68c 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -243,11 +243,11 @@ struct pnp_fixup { #define PNP_CONFIGURABLE 0x0008 #define PNP_REMOVABLE 0x0010 -#define pnp_can_read(dev) (((dev)->protocol) && ((dev)->protocol->get) && \ +#define pnp_can_read(dev) (((dev)->protocol->get) && \ ((dev)->capabilities & PNP_READ)) -#define pnp_can_write(dev) (((dev)->protocol) && ((dev)->protocol->set) && \ +#define pnp_can_write(dev) (((dev)->protocol->set) && \ ((dev)->capabilities & PNP_WRITE)) -#define pnp_can_disable(dev) (((dev)->protocol) && ((dev)->protocol->disable) && \ +#define pnp_can_disable(dev) (((dev)->protocol->disable) && \ ((dev)->capabilities & PNP_DISABLE)) #define pnp_can_configure(dev) ((!(dev)->active) && \ ((dev)->capabilities & PNP_CONFIGURABLE)) diff --git a/include/linux/poison.h b/include/linux/poison.h index d93c300..a9c31be 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -36,7 +36,8 @@ */ /********** fs/jbd/journal.c **********/ -#define JBD_POISON_FREE 0x5b +#define JBD_POISON_FREE 0x5b +#define JBD2_POISON_FREE 0x5c /********** drivers/base/dmapool.c **********/ #define POOL_POISON_FREED 0xa7 /* !inuse */ diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h index 1adfe66..af7c36a 100644 --- a/include/linux/prefetch.h +++ b/include/linux/prefetch.h @@ -34,17 +34,12 @@ */ -/* - * These cannot be do{}while(0) macros. See the mental gymnastics in - * the loop macro. - */ - #ifndef ARCH_HAS_PREFETCH -static inline void prefetch(const void *x) {;} +#define prefetch(x) __builtin_prefetch(x) #endif #ifndef ARCH_HAS_PREFETCHW -static inline void prefetchw(const void *x) {;} +#define prefetchw(x) __builtin_prefetch(x,1) #endif #ifndef ARCH_HAS_SPINLOCK_PREFETCH diff --git a/include/linux/prio_heap.h b/include/linux/prio_heap.h new file mode 100644 index 0000000..0809435 --- /dev/null +++ b/include/linux/prio_heap.h @@ -0,0 +1,58 @@ +#ifndef _LINUX_PRIO_HEAP_H +#define _LINUX_PRIO_HEAP_H + +/* + * Simple insertion-only static-sized priority heap containing + * pointers, based on CLR, chapter 7 + */ + +#include <linux/gfp.h> + +/** + * struct ptr_heap - simple static-sized priority heap + * @ptrs - pointer to data area + * @max - max number of elements that can be stored in @ptrs + * @size - current number of valid elements in @ptrs (in the range 0..@size-1 + * @gt: comparison operator, which should implement "greater than" + */ +struct ptr_heap { + void **ptrs; + int max; + int size; + int (*gt)(void *, void *); +}; + +/** + * heap_init - initialize an empty heap with a given memory size + * @heap: the heap structure to be initialized + * @size: amount of memory to use in bytes + * @gfp_mask: mask to pass to kmalloc() + * @gt: comparison operator, which should implement "greater than" + */ +extern int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask, + int (*gt)(void *, void *)); + +/** + * heap_free - release a heap's storage + * @heap: the heap structure whose data should be released + */ +void heap_free(struct ptr_heap *heap); + +/** + * heap_insert - insert a value into the heap and return any overflowed value + * @heap: the heap to be operated on + * @p: the pointer to be inserted + * + * Attempts to insert the given value into the priority heap. If the + * heap is full prior to the insertion, then the resulting heap will + * consist of the smallest @max elements of the original heap and the + * new element; the greatest element will be removed from the heap and + * returned. Note that the returned element will be the new element + * (i.e. no change to the heap) if the new element is greater than all + * elements currently in the heap. + */ +extern void *heap_insert(struct ptr_heap *heap, void *p); + + + +#endif /* _LINUX_PRIO_HEAP_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 20741f6..1ff4616 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -125,7 +125,8 @@ extern struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); extern struct vfsmount *proc_mnt; -extern int proc_fill_super(struct super_block *,void *,int); +struct pid_namespace; +extern int proc_fill_super(struct super_block *); extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *); /* @@ -142,6 +143,9 @@ extern const struct file_operations proc_kcore_operations; extern const struct file_operations proc_kmsg_operations; extern const struct file_operations ppc_htab_operations; +extern int pid_ns_prepare_proc(struct pid_namespace *ns); +extern void pid_ns_release_proc(struct pid_namespace *ns); + /* * proc_tty.c */ @@ -207,7 +211,9 @@ extern void proc_net_remove(struct net *net, const char *name); #define proc_net_create(net, name, mode, info) ({ (void)(mode), NULL; }) static inline void proc_net_remove(struct net *net, const char *name) {} -static inline void proc_flush_task(struct task_struct *task) { } +static inline void proc_flush_task(struct task_struct *task) +{ +} static inline struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, struct proc_dir_entry *parent) { return NULL; } @@ -232,6 +238,15 @@ static inline void proc_tty_unregister_driver(struct tty_driver *driver) {}; extern struct proc_dir_entry proc_root; +static inline int pid_ns_prepare_proc(struct pid_namespace *ns) +{ + return 0; +} + +static inline void pid_ns_release_proc(struct pid_namespace *ns) +{ +} + #endif /* CONFIG_PROC_FS */ #if !defined(CONFIG_PROC_KCORE) diff --git a/include/linux/profile.h b/include/linux/profile.h index eec48f5..ff576d1 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -78,9 +78,6 @@ int profile_event_unregister(enum profile_type, struct notifier_block * n); int register_timer_hook(int (*hook)(struct pt_regs *)); void unregister_timer_hook(int (*hook)(struct pt_regs *)); -/* Timer based profiling hook */ -extern int (*timer_hook)(struct pt_regs *); - struct pt_regs; #else diff --git a/include/linux/proportions.h b/include/linux/proportions.h new file mode 100644 index 0000000..2c3b3ca --- /dev/null +++ b/include/linux/proportions.h @@ -0,0 +1,119 @@ +/* + * FLoating proportions + * + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * + * This file contains the public data structure and API definitions. + */ + +#ifndef _LINUX_PROPORTIONS_H +#define _LINUX_PROPORTIONS_H + +#include <linux/percpu_counter.h> +#include <linux/spinlock.h> +#include <linux/mutex.h> + +struct prop_global { + /* + * The period over which we differentiate + * + * period = 2^shift + */ + int shift; + /* + * The total event counter aka 'time'. + * + * Treated as an unsigned long; the lower 'shift - 1' bits are the + * counter bits, the remaining upper bits the period counter. + */ + struct percpu_counter events; +}; + +/* + * global proportion descriptor + * + * this is needed to consitently flip prop_global structures. + */ +struct prop_descriptor { + int index; + struct prop_global pg[2]; + struct mutex mutex; /* serialize the prop_global switch */ +}; + +int prop_descriptor_init(struct prop_descriptor *pd, int shift); +void prop_change_shift(struct prop_descriptor *pd, int new_shift); + +/* + * ----- PERCPU ------ + */ + +struct prop_local_percpu { + /* + * the local events counter + */ + struct percpu_counter events; + + /* + * snapshot of the last seen global state + */ + int shift; + unsigned long period; + spinlock_t lock; /* protect the snapshot state */ +}; + +int prop_local_init_percpu(struct prop_local_percpu *pl); +void prop_local_destroy_percpu(struct prop_local_percpu *pl); +void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl); +void prop_fraction_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl, + long *numerator, long *denominator); + +static inline +void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl) +{ + unsigned long flags; + + local_irq_save(flags); + __prop_inc_percpu(pd, pl); + local_irq_restore(flags); +} + +/* + * ----- SINGLE ------ + */ + +struct prop_local_single { + /* + * the local events counter + */ + unsigned long events; + + /* + * snapshot of the last seen global state + * and a lock protecting this state + */ + int shift; + unsigned long period; + spinlock_t lock; /* protect the snapshot state */ +}; + +#define INIT_PROP_LOCAL_SINGLE(name) \ +{ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ +} + +int prop_local_init_single(struct prop_local_single *pl); +void prop_local_destroy_single(struct prop_local_single *pl); +void __prop_inc_single(struct prop_descriptor *pd, struct prop_local_single *pl); +void prop_fraction_single(struct prop_descriptor *pd, struct prop_local_single *pl, + long *numerator, long *denominator); + +static inline +void prop_inc_single(struct prop_descriptor *pd, struct prop_local_single *pl) +{ + unsigned long flags; + + local_irq_save(flags); + __prop_inc_single(pd, pl); + local_irq_restore(flags); +} + +#endif /* _LINUX_PROPORTIONS_H */ diff --git a/include/linux/quota.h b/include/linux/quota.h index 6243982..6e0393a 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -128,6 +128,37 @@ struct if_dqinfo { __u32 dqi_valid; }; +/* + * Definitions for quota netlink interface + */ +#define QUOTA_NL_NOWARN 0 +#define QUOTA_NL_IHARDWARN 1 /* Inode hardlimit reached */ +#define QUOTA_NL_ISOFTLONGWARN 2 /* Inode grace time expired */ +#define QUOTA_NL_ISOFTWARN 3 /* Inode softlimit reached */ +#define QUOTA_NL_BHARDWARN 4 /* Block hardlimit reached */ +#define QUOTA_NL_BSOFTLONGWARN 5 /* Block grace time expired */ +#define QUOTA_NL_BSOFTWARN 6 /* Block softlimit reached */ + +enum { + QUOTA_NL_C_UNSPEC, + QUOTA_NL_C_WARNING, + __QUOTA_NL_C_MAX, +}; +#define QUOTA_NL_C_MAX (__QUOTA_NL_C_MAX - 1) + +enum { + QUOTA_NL_A_UNSPEC, + QUOTA_NL_A_QTYPE, + QUOTA_NL_A_EXCESS_ID, + QUOTA_NL_A_WARNING, + QUOTA_NL_A_DEV_MAJOR, + QUOTA_NL_A_DEV_MINOR, + QUOTA_NL_A_CAUSED_ID, + __QUOTA_NL_A_MAX, +}; +#define QUOTA_NL_A_MAX (__QUOTA_NL_A_MAX - 1) + + #ifdef __KERNEL__ #include <linux/spinlock.h> #include <linux/rwsem.h> diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index f9e77d2..b6116b4 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -26,28 +26,31 @@ #include <linux/rcupdate.h> /* - * A direct pointer (root->rnode pointing directly to a data item, - * rather than another radix_tree_node) is signalled by the low bit - * set in the root->rnode pointer. + * An indirect pointer (root->rnode pointing to a radix_tree_node, rather + * than a data item) is signalled by the low bit set in the root->rnode + * pointer. * - * In this case root->height is also NULL, but the direct pointer tests are - * needed for RCU lookups when root->height is unreliable. + * In this case root->height is > 0, but the indirect pointer tests are + * needed for RCU lookups (because root->height is unreliable). The only + * time callers need worry about this is when doing a lookup_slot under + * RCU. */ -#define RADIX_TREE_DIRECT_PTR 1 +#define RADIX_TREE_INDIRECT_PTR 1 +#define RADIX_TREE_RETRY ((void *)-1UL) -static inline void *radix_tree_ptr_to_direct(void *ptr) +static inline void *radix_tree_ptr_to_indirect(void *ptr) { - return (void *)((unsigned long)ptr | RADIX_TREE_DIRECT_PTR); + return (void *)((unsigned long)ptr | RADIX_TREE_INDIRECT_PTR); } -static inline void *radix_tree_direct_to_ptr(void *ptr) +static inline void *radix_tree_indirect_to_ptr(void *ptr) { - return (void *)((unsigned long)ptr & ~RADIX_TREE_DIRECT_PTR); + return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR); } -static inline int radix_tree_is_direct_ptr(void *ptr) +static inline int radix_tree_is_indirect_ptr(void *ptr) { - return (int)((unsigned long)ptr & RADIX_TREE_DIRECT_PTR); + return (int)((unsigned long)ptr & RADIX_TREE_INDIRECT_PTR); } /*** radix-tree API starts here ***/ @@ -130,7 +133,10 @@ do { \ */ static inline void *radix_tree_deref_slot(void **pslot) { - return radix_tree_direct_to_ptr(*pslot); + void *ret = *pslot; + if (unlikely(radix_tree_is_indirect_ptr(ret))) + ret = RADIX_TREE_RETRY; + return ret; } /** * radix_tree_replace_slot - replace item in a slot @@ -142,10 +148,8 @@ static inline void *radix_tree_deref_slot(void **pslot) */ static inline void radix_tree_replace_slot(void **pslot, void *item) { - BUG_ON(radix_tree_is_direct_ptr(item)); - rcu_assign_pointer(*pslot, - (void *)((unsigned long)item | - ((unsigned long)*pslot & RADIX_TREE_DIRECT_PTR))); + BUG_ON(radix_tree_is_indirect_ptr(item)); + rcu_assign_pointer(*pslot, item); } int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); @@ -155,6 +159,8 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); +unsigned long radix_tree_next_hole(struct radix_tree_root *root, + unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 75e17a0..306a1d1a 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -138,7 +138,6 @@ typedef __u16 bitmap_counter_t; /* use these for bitmap->flags and bitmap->sb->state bit-fields */ enum bitmap_state { - BITMAP_ACTIVE = 0x001, /* the bitmap is in use */ BITMAP_STALE = 0x002, /* the bitmap file is out of date or had -EIO */ BITMAP_WRITE_ERROR = 0x004, /* A write error has occurred */ BITMAP_HOSTENDIAN = 0x8000, @@ -258,7 +257,6 @@ struct bitmap { int bitmap_create(mddev_t *mddev); void bitmap_flush(mddev_t *mddev); void bitmap_destroy(mddev_t *mddev); -int bitmap_active(struct bitmap *bitmap); char *file_path(struct file *file, char *buf, int count); void bitmap_print_sb(struct bitmap *bitmap); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index fe17d7d..cc24a01 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -41,6 +41,7 @@ #include <linux/percpu.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/lockdep.h> /** * struct rcu_head - callback structure for use with RCU @@ -133,6 +134,15 @@ static inline void rcu_bh_qsctr_inc(int cpu) extern int rcu_pending(int cpu); extern int rcu_needs_cpu(int cpu); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern struct lockdep_map rcu_lock_map; +# define rcu_read_acquire() lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_) +# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) +#else +# define rcu_read_acquire() do { } while (0) +# define rcu_read_release() do { } while (0) +#endif + /** * rcu_read_lock - mark the beginning of an RCU read-side critical section. * @@ -166,6 +176,7 @@ extern int rcu_needs_cpu(int cpu); do { \ preempt_disable(); \ __acquire(RCU); \ + rcu_read_acquire(); \ } while(0) /** @@ -175,6 +186,7 @@ extern int rcu_needs_cpu(int cpu); */ #define rcu_read_unlock() \ do { \ + rcu_read_release(); \ __release(RCU); \ preempt_enable(); \ } while(0) @@ -204,6 +216,7 @@ extern int rcu_needs_cpu(int cpu); do { \ local_bh_disable(); \ __acquire(RCU_BH); \ + rcu_read_acquire(); \ } while(0) /* @@ -213,10 +226,23 @@ extern int rcu_needs_cpu(int cpu); */ #define rcu_read_unlock_bh() \ do { \ + rcu_read_release(); \ __release(RCU_BH); \ local_bh_enable(); \ } while(0) +/* + * Prevent the compiler from merging or refetching accesses. The compiler + * is also forbidden from reordering successive instances of ACCESS_ONCE(), + * but only when the compiler is aware of some particular ordering. One way + * to make the compiler aware of ordering is to put the two invocations of + * ACCESS_ONCE() in different C statements. + * + * This macro does absolutely -nothing- to prevent the CPU from reordering, + * merging, or refetching absolutely anything at any time. + */ +#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) + /** * rcu_dereference - fetch an RCU-protected pointer in an * RCU read-side critical section. This pointer may later @@ -228,7 +254,7 @@ extern int rcu_needs_cpu(int cpu); */ #define rcu_dereference(p) ({ \ - typeof(p) _________p1 = p; \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ smp_read_barrier_depends(); \ (_________p1); \ }) diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 180a9d8..422eab4 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -28,6 +28,8 @@ #include <linux/reiserfs_fs_sb.h> #endif +struct fid; + /* * include/linux/reiser_fs.h * @@ -85,7 +87,7 @@ void reiserfs_warning(struct super_block *s, const char *fmt, ...); if( !( cond ) ) \ reiserfs_panic( NULL, "reiserfs[%i]: assertion " scond " failed at " \ __FILE__ ":%i:%s: " format "\n", \ - in_interrupt() ? -1 : current -> pid, __LINE__ , __FUNCTION__ , ##args ) + in_interrupt() ? -1 : task_pid_nr(current), __LINE__ , __FUNCTION__ , ##args ) #define RASSERT(cond, format, args...) __RASSERT(cond, #cond, format, ##args) @@ -283,6 +285,18 @@ static inline struct reiserfs_sb_info *REISERFS_SB(const struct super_block *sb) return sb->s_fs_info; } +/* Don't trust REISERFS_SB(sb)->s_bmap_nr, it's a u16 + * which overflows on large file systems. */ +static inline u32 reiserfs_bmap_count(struct super_block *sb) +{ + return (SB_BLOCK_COUNT(sb) - 1) / (sb->s_blocksize * 8) + 1; +} + +static inline int bmap_would_wrap(unsigned bmap_nr) +{ + return bmap_nr > ((1LL << 16) - 1); +} + /** this says about version of key of all items (but stat data) the object consists of */ #define get_inode_item_key_version( inode ) \ @@ -1703,8 +1717,6 @@ static inline int reiserfs_transaction_free_space(struct reiserfs_transaction_ha return th->t_blocks_allocated - th->t_blocks_logged; } -int reiserfs_async_progress_wait(struct super_block *s); - struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct super_block *, @@ -1736,8 +1748,8 @@ int journal_end_sync(struct reiserfs_transaction_handle *, struct super_block *, int journal_mark_freed(struct reiserfs_transaction_handle *, struct super_block *, b_blocknr_t blocknr); int journal_transaction_should_end(struct reiserfs_transaction_handle *, int); -int reiserfs_in_journal(struct super_block *p_s_sb, int bmap_nr, int bit_nr, - int searchall, b_blocknr_t * next); +int reiserfs_in_journal(struct super_block *p_s_sb, unsigned int bmap_nr, + int bit_nr, int searchall, b_blocknr_t *next); int journal_begin(struct reiserfs_transaction_handle *, struct super_block *p_s_sb, unsigned long); int journal_join_abort(struct reiserfs_transaction_handle *, @@ -1745,7 +1757,7 @@ int journal_join_abort(struct reiserfs_transaction_handle *, void reiserfs_journal_abort(struct super_block *sb, int errno); void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...); int reiserfs_allocate_list_bitmaps(struct super_block *s, - struct reiserfs_list_bitmap *, int); + struct reiserfs_list_bitmap *, unsigned int); void add_save_link(struct reiserfs_transaction_handle *th, struct inode *inode, int truncate); @@ -1859,8 +1871,6 @@ void padd_item(char *item, int total_length, int length); #define GET_BLOCK_NO_IMUX 8 /* i_mutex is not held, don't preallocate */ #define GET_BLOCK_NO_DANGLE 16 /* don't leave any transactions running */ -int restart_transaction(struct reiserfs_transaction_handle *th, - struct inode *inode, struct treepath *path); void reiserfs_read_locked_inode(struct inode *inode, struct reiserfs_iget_args *args); int reiserfs_find_actor(struct inode *inode, void *p); @@ -1869,12 +1879,10 @@ void reiserfs_delete_inode(struct inode *inode); int reiserfs_write_inode(struct inode *inode, int); int reiserfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create); -struct dentry *reiserfs_get_dentry(struct super_block *, void *); -struct dentry *reiserfs_decode_fh(struct super_block *sb, __u32 * data, - int len, int fhtype, - int (*acceptable) (void *contect, - struct dentry * de), - void *context); +struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, int connectable); @@ -2045,7 +2053,7 @@ struct buffer_head *get_FEB(struct tree_balance *); * arguments, such as node, search path, transaction_handle, etc. */ struct __reiserfs_blocknr_hint { struct inode *inode; /* inode passed to allocator, if we allocate unf. nodes */ - long block; /* file offset, in blocks */ + sector_t block; /* file offset, in blocks */ struct in_core_key key; struct treepath *path; /* search path, used by allocator to deternine search_start by * various ways */ @@ -2103,7 +2111,8 @@ static inline int reiserfs_new_form_blocknrs(struct tree_balance *tb, static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, - struct treepath *path, long block) + struct treepath *path, + sector_t block) { reiserfs_blocknr_hint_t hint = { .th = th, @@ -2120,7 +2129,8 @@ static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle static inline int reiserfs_new_unf_blocknrs2(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, - struct treepath *path, long block) + struct treepath *path, + sector_t block) { reiserfs_blocknr_hint_t hint = { .th = th, @@ -2137,9 +2147,6 @@ void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th, struct inode *inode); void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th); #endif -void reiserfs_claim_blocks_to_be_allocated(struct super_block *sb, int blocks); -void reiserfs_release_claimed_blocks(struct super_block *sb, int blocks); -int reiserfs_can_fit_pages(struct super_block *sb); /* hashes.c */ __u32 keyed_hash(const signed char *msg, int len); diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index ff9e923..10fa0c8 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -265,9 +265,7 @@ enum journal_state_bits { typedef __u32(*hashf_t) (const signed char *, int); struct reiserfs_bitmap_info { - // FIXME: Won't work with block sizes > 8K - __u16 first_zero_hint; - __u16 free_count; + __u32 free_count; }; struct proc_dir_entry; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 4efbd9c..42daf5e 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -4,20 +4,252 @@ #include <asm/scatterlist.h> #include <linux/mm.h> #include <linux/string.h> +#include <asm/io.h> +/* + * Notes on SG table design. + * + * Architectures must provide an unsigned long page_link field in the + * scatterlist struct. We use that to place the page pointer AND encode + * information about the sg table as well. The two lower bits are reserved + * for this information. + * + * If bit 0 is set, then the page_link contains a pointer to the next sg + * table list. Otherwise the next entry is at sg + 1. + * + * If bit 1 is set, then this sg entry is the last element in a list. + * + * See sg_next(). + * + */ + +#define SG_MAGIC 0x87654321 + +/** + * sg_set_page - Set sg entry to point at given page + * @sg: SG entry + * @page: The page + * + * Description: + * Use this function to set an sg entry pointing at a page, never assign + * the page directly. We encode sg table information in the lower bits + * of the page pointer. See sg_page() for looking up the page belonging + * to an sg entry. + * + **/ +static inline void sg_set_page(struct scatterlist *sg, struct page *page) +{ + unsigned long page_link = sg->page_link & 0x3; + +#ifdef CONFIG_DEBUG_SG + BUG_ON(sg->sg_magic != SG_MAGIC); +#endif + sg->page_link = page_link | (unsigned long) page; +} + +#define sg_page(sg) ((struct page *) ((sg)->page_link & ~0x3)) + +/** + * sg_set_buf - Set sg entry to point at given data + * @sg: SG entry + * @buf: Data + * @buflen: Data length + * + **/ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { - sg->page = virt_to_page(buf); + sg_set_page(sg, virt_to_page(buf)); sg->offset = offset_in_page(buf); sg->length = buflen; } +/* + * We overload the LSB of the page pointer to indicate whether it's + * a valid sg entry, or whether it points to the start of a new scatterlist. + * Those low bits are there for everyone! (thanks mason :-) + */ +#define sg_is_chain(sg) ((sg)->page_link & 0x01) +#define sg_is_last(sg) ((sg)->page_link & 0x02) +#define sg_chain_ptr(sg) \ + ((struct scatterlist *) ((sg)->page_link & ~0x03)) + +/** + * sg_next - return the next scatterlist entry in a list + * @sg: The current sg entry + * + * Description: + * Usually the next entry will be @sg@ + 1, but if this sg element is part + * of a chained scatterlist, it could jump to the start of a new + * scatterlist array. + * + **/ +static inline struct scatterlist *sg_next(struct scatterlist *sg) +{ +#ifdef CONFIG_DEBUG_SG + BUG_ON(sg->sg_magic != SG_MAGIC); +#endif + if (sg_is_last(sg)) + return NULL; + + sg++; + if (unlikely(sg_is_chain(sg))) + sg = sg_chain_ptr(sg); + + return sg; +} + +/* + * Loop over each sg element, following the pointer to a new list if necessary + */ +#define for_each_sg(sglist, sg, nr, __i) \ + for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) + +/** + * sg_last - return the last scatterlist entry in a list + * @sgl: First entry in the scatterlist + * @nents: Number of entries in the scatterlist + * + * Description: + * Should only be used casually, it (currently) scan the entire list + * to get the last entry. + * + * Note that the @sgl@ pointer passed in need not be the first one, + * the important bit is that @nents@ denotes the number of entries that + * exist from @sgl@. + * + **/ +static inline struct scatterlist *sg_last(struct scatterlist *sgl, + unsigned int nents) +{ +#ifndef ARCH_HAS_SG_CHAIN + struct scatterlist *ret = &sgl[nents - 1]; +#else + struct scatterlist *sg, *ret = NULL; + int i; + + for_each_sg(sgl, sg, nents, i) + ret = sg; + +#endif +#ifdef CONFIG_DEBUG_SG + BUG_ON(sgl[0].sg_magic != SG_MAGIC); + BUG_ON(!sg_is_last(ret)); +#endif + return ret; +} + +/** + * sg_chain - Chain two sglists together + * @prv: First scatterlist + * @prv_nents: Number of entries in prv + * @sgl: Second scatterlist + * + * Description: + * Links @prv@ and @sgl@ together, to form a longer scatterlist. + * + **/ +static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, + struct scatterlist *sgl) +{ +#ifndef ARCH_HAS_SG_CHAIN + BUG(); +#endif + prv[prv_nents - 1].page_link = (unsigned long) sgl | 0x01; +} + +/** + * sg_mark_end - Mark the end of the scatterlist + * @sgl: Scatterlist + * @nents: Number of entries in sgl + * + * Description: + * Marks the last entry as the termination point for sg_next() + * + **/ +static inline void sg_mark_end(struct scatterlist *sgl, unsigned int nents) +{ + sgl[nents - 1].page_link = 0x02; +} + +static inline void __sg_mark_end(struct scatterlist *sg) +{ + sg->page_link |= 0x02; +} + +/** + * sg_init_one - Initialize a single entry sg list + * @sg: SG entry + * @buf: Virtual address for IO + * @buflen: IO length + * + * Notes: + * This should not be used on a single entry that is part of a larger + * table. Use sg_init_table() for that. + * + **/ static inline void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen) { memset(sg, 0, sizeof(*sg)); +#ifdef CONFIG_DEBUG_SG + sg->sg_magic = SG_MAGIC; +#endif + sg_mark_end(sg, 1); sg_set_buf(sg, buf, buflen); } +/** + * sg_init_table - Initialize SG table + * @sgl: The SG table + * @nents: Number of entries in table + * + * Notes: + * If this is part of a chained sg table, sg_mark_end() should be + * used only on the last table part. + * + **/ +static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents) +{ + memset(sgl, 0, sizeof(*sgl) * nents); + sg_mark_end(sgl, nents); +#ifdef CONFIG_DEBUG_SG + { + int i; + for (i = 0; i < nents; i++) + sgl[i].sg_magic = SG_MAGIC; + } +#endif +} + +/** + * sg_phys - Return physical address of an sg entry + * @sg: SG entry + * + * Description: + * This calls page_to_phys() on the page in this sg entry, and adds the + * sg offset. The caller must know that it is legal to call page_to_phys() + * on the sg page. + * + **/ +static inline unsigned long sg_phys(struct scatterlist *sg) +{ + return page_to_phys(sg_page(sg)) + sg->offset; +} + +/** + * sg_virt - Return virtual address of an sg entry + * @sg: SG entry + * + * Description: + * This calls page_address() on the page in this sg entry, and adds the + * sg offset. The caller must know that the sg page has a valid virtual + * mapping. + * + **/ +static inline void *sg_virt(struct scatterlist *sg) +{ + return page_address(sg_page(sg)) + sg->offset; +} + #endif /* _LINUX_SCATTERLIST_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 833f7dc..13df99f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1,8 +1,6 @@ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H -#include <linux/auxvec.h> /* For AT_VECTOR_SIZE */ - /* * cloning flags: */ @@ -27,6 +25,7 @@ #define CLONE_NEWUTS 0x04000000 /* New utsname group? */ #define CLONE_NEWIPC 0x08000000 /* New ipcs */ #define CLONE_NEWUSER 0x10000000 /* New user namespace */ +#define CLONE_NEWPID 0x20000000 /* New pid namespace */ #define CLONE_NEWNET 0x40000000 /* New network namespace */ /* @@ -58,12 +57,12 @@ struct sched_param { #include <linux/cpumask.h> #include <linux/errno.h> #include <linux/nodemask.h> +#include <linux/mm_types.h> #include <asm/system.h> #include <asm/semaphore.h> #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/mmu.h> #include <asm/cputime.h> #include <linux/smp.h> @@ -76,6 +75,7 @@ struct sched_param { #include <linux/pid.h> #include <linux/percpu.h> #include <linux/topology.h> +#include <linux/proportions.h> #include <linux/seccomp.h> #include <linux/rcupdate.h> #include <linux/futex.h> @@ -87,6 +87,7 @@ struct sched_param { #include <linux/timer.h> #include <linux/hrtimer.h> #include <linux/task_io_accounting.h> +#include <linux/kobject.h> #include <asm/processor.h> @@ -136,6 +137,7 @@ extern unsigned long weighted_cpuload(const int cpu); struct seq_file; struct cfs_rq; +struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); @@ -174,8 +176,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #define EXIT_ZOMBIE 16 #define EXIT_DEAD 32 /* in tsk->state again */ -#define TASK_NONINTERACTIVE 64 -#define TASK_DEAD 128 +#define TASK_DEAD 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -261,6 +262,7 @@ extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); +extern int softlockup_thresh; #else static inline void softlockup_tick(void) { @@ -318,7 +320,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member) #define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member) #define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member) -typedef atomic_long_t mm_counter_t; #else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ /* @@ -330,7 +331,6 @@ typedef atomic_long_t mm_counter_t; #define add_mm_counter(mm, member, value) (mm)->_##member += (value) #define inc_mm_counter(mm, member) (mm)->_##member++ #define dec_mm_counter(mm, member) (mm)->_##member-- -typedef unsigned long mm_counter_t; #endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ @@ -360,81 +360,14 @@ extern int get_dumpable(struct mm_struct *mm); #define MMF_DUMP_ANON_SHARED 3 #define MMF_DUMP_MAPPED_PRIVATE 4 #define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 4 +#define MMF_DUMP_FILTER_BITS 5 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED)) -struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ - struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ - unsigned long (*get_unmapped_area) (struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct mm_struct *mm, unsigned long addr); - unsigned long mmap_base; /* base of mmap area */ - unsigned long task_size; /* size of task vm space */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ - unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ - pgd_t * pgd; - atomic_t mm_users; /* How many users with user space? */ - atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - int map_count; /* number of VMAs */ - struct rw_semaphore mmap_sem; - spinlock_t page_table_lock; /* Protects page tables and some counters */ - - struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung - * together off init_mm.mmlist, and are protected - * by mmlist_lock - */ - - /* Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - mm_counter_t _file_rss; - mm_counter_t _anon_rss; - - unsigned long hiwater_rss; /* High-watermark of RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ - - unsigned long total_vm, locked_vm, shared_vm, exec_vm; - unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; - unsigned long start_code, end_code, start_data, end_data; - unsigned long start_brk, brk, start_stack; - unsigned long arg_start, arg_end, env_start, env_end; - - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - - cpumask_t cpu_vm_mask; - - /* Architecture-specific MM context */ - mm_context_t context; - - /* Swap token stuff */ - /* - * Last value of global fault stamp as seen by this process. - * In other words, this value gives an indication of how long - * it has been since this task got the token. - * Look at mm/thrash.c - */ - unsigned int faultstamp; - unsigned int token_priority; - unsigned int last_interval; - - unsigned long flags; /* Must use atomic bitops to access the bits */ - - /* coredumping support */ - int core_waiters; - struct completion *core_startup_done, core_done; - - /* aio bits */ - rwlock_t ioctx_list_lock; - struct kioctx *ioctx_list; -}; - struct sighand_struct { atomic_t count; struct k_sigaction action[_NSIG]; @@ -496,7 +429,17 @@ struct signal_struct { cputime_t it_prof_incr, it_virt_incr; /* job control IDs */ - pid_t pgrp; + + /* + * pgrp and session fields are deprecated. + * use the task_session_Xnr and task_pgrp_Xnr routines below + */ + + union { + pid_t pgrp __deprecated; + pid_t __pgrp; + }; + struct pid *tty_old_pgrp; union { @@ -516,6 +459,8 @@ struct signal_struct { * in __exit_signal, except for the group leader. */ cputime_t utime, stime, cutime, cstime; + cputime_t gtime; + cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -584,8 +529,10 @@ struct user_struct { atomic_t inotify_watches; /* How many inotify watches does this user have? */ atomic_t inotify_devs; /* How many inotify devs does this user have opened? */ #endif +#ifdef CONFIG_POSIX_MQUEUE /* protected by mq_lock */ unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ +#endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ #ifdef CONFIG_KEYS @@ -596,8 +543,23 @@ struct user_struct { /* Hash table maintenance information */ struct hlist_node uidhash_node; uid_t uid; + +#ifdef CONFIG_FAIR_USER_SCHED + struct task_group *tg; +#ifdef CONFIG_SYSFS + struct kset kset; + struct subsys_attribute user_attr; + struct work_struct work; +#endif +#endif }; +#ifdef CONFIG_FAIR_USER_SCHED +extern int uids_kobject_init(void); +#else +static inline int uids_kobject_init(void) { return 0; } +#endif + extern struct user_struct *find_user(uid_t); extern struct user_struct root_user; @@ -609,13 +571,17 @@ struct reclaim_state; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info { /* cumulative counters */ - unsigned long pcnt; /* # of times run on this cpu */ + unsigned long pcount; /* # of times run on this cpu */ unsigned long long cpu_time, /* time spent on the cpu */ run_delay; /* time spent waiting on a runqueue */ /* timestamps */ unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ +#ifdef CONFIG_SCHEDSTATS + /* BKL stats */ + unsigned int bkl_count; +#endif }; #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ @@ -750,39 +716,38 @@ struct sched_domain { #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ - unsigned long lb_cnt[CPU_MAX_IDLE_TYPES]; - unsigned long lb_failed[CPU_MAX_IDLE_TYPES]; - unsigned long lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned long lb_imbalance[CPU_MAX_IDLE_TYPES]; - unsigned long lb_gained[CPU_MAX_IDLE_TYPES]; - unsigned long lb_hot_gained[CPU_MAX_IDLE_TYPES]; - unsigned long lb_nobusyg[CPU_MAX_IDLE_TYPES]; - unsigned long lb_nobusyq[CPU_MAX_IDLE_TYPES]; + unsigned int lb_count[CPU_MAX_IDLE_TYPES]; + unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; + unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES]; /* Active load balancing */ - unsigned long alb_cnt; - unsigned long alb_failed; - unsigned long alb_pushed; + unsigned int alb_count; + unsigned int alb_failed; + unsigned int alb_pushed; /* SD_BALANCE_EXEC stats */ - unsigned long sbe_cnt; - unsigned long sbe_balanced; - unsigned long sbe_pushed; + unsigned int sbe_count; + unsigned int sbe_balanced; + unsigned int sbe_pushed; /* SD_BALANCE_FORK stats */ - unsigned long sbf_cnt; - unsigned long sbf_balanced; - unsigned long sbf_pushed; + unsigned int sbf_count; + unsigned int sbf_balanced; + unsigned int sbf_pushed; /* try_to_wake_up() stats */ - unsigned long ttwu_wake_remote; - unsigned long ttwu_move_affine; - unsigned long ttwu_move_balance; + unsigned int ttwu_wake_remote; + unsigned int ttwu_move_affine; + unsigned int ttwu_move_balance; #endif }; -extern int partition_sched_domains(cpumask_t *partition1, - cpumask_t *partition2); +extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new); #endif /* CONFIG_SMP */ @@ -804,8 +769,6 @@ static inline int above_background_load(void) } struct io_context; /* See blkdev.h */ -struct cpuset; - #define NGROUPS_SMALL 32 #define NGROUPS_PER_BLOCK ((int)(PAGE_SIZE / sizeof(gid_t))) struct group_info { @@ -854,11 +817,11 @@ struct rq; struct sched_domain; struct sched_class { - struct sched_class *next; + const struct sched_class *next; void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); - void (*yield_task) (struct rq *rq, struct task_struct *p); + void (*yield_task) (struct rq *rq); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p); @@ -888,31 +851,22 @@ struct load_weight { * 4 se->block_start * 4 se->run_node * 4 se->sleep_start - * 4 se->sleep_start_fair * 6 se->load.weight - * 7 se->delta_fair - * 15 se->wait_runtime */ struct sched_entity { - long wait_runtime; - unsigned long delta_fair_run; - unsigned long delta_fair_sleep; - unsigned long delta_exec; - s64 fair_key; struct load_weight load; /* for load-balancing */ struct rb_node run_node; unsigned int on_rq; + int peer_preempt; u64 exec_start; u64 sum_exec_runtime; + u64 vruntime; u64 prev_sum_exec_runtime; - u64 wait_start_fair; - u64 sleep_start_fair; #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; - s64 sum_wait_runtime; u64 sleep_start; u64 sleep_max; @@ -921,9 +875,25 @@ struct sched_entity { u64 block_start; u64 block_max; u64 exec_max; - - unsigned long wait_runtime_overruns; - unsigned long wait_runtime_underruns; + u64 slice_max; + + u64 nr_migrations; + u64 nr_migrations_cold; + u64 nr_failed_migrations_affine; + u64 nr_failed_migrations_running; + u64 nr_failed_migrations_hot; + u64 nr_forced_migrations; + u64 nr_forced2_migrations; + + u64 nr_wakeups; + u64 nr_wakeups_sync; + u64 nr_wakeups_migrate; + u64 nr_wakeups_local; + u64 nr_wakeups_remote; + u64 nr_wakeups_affine; + u64 nr_wakeups_affine_attempts; + u64 nr_wakeups_passive; + u64 nr_wakeups_idle; #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -952,7 +922,7 @@ struct task_struct { int prio, static_prio, normal_prio; struct list_head run_list; - struct sched_class *sched_class; + const struct sched_class *sched_class; struct sched_entity se; #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -961,6 +931,16 @@ struct task_struct { #endif unsigned short ioprio; + /* + * fpu_counter contains the number of consecutive context switches + * that the FPU is used. If this is over a threshold, the lazy fpu + * saving becomes unlazy to save the trap. This is an unsigned char + * so that after 256 times the counter wraps and the behavior turns + * lazy again; this to deal with bursty apps that only use FPU for + * a short time + */ + unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif @@ -1022,7 +1002,8 @@ struct task_struct { int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ unsigned int rt_priority; - cputime_t utime, stime; + cputime_t utime, stime, utimescaled, stimescaled; + cputime_t gtime; unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ @@ -1045,16 +1026,6 @@ struct task_struct { struct key *thread_keyring; /* keyring private to this thread */ unsigned char jit_keyring; /* default keyring to attach requested keys to */ #endif - /* - * fpu_counter contains the number of consecutive context switches - * that the FPU is used. If this is over a threshold, the lazy fpu - * saving becomes unlazy to save the trap. This is an unsigned char - * so that after 256 times the counter wraps and the behavior turns - * lazy again; this to deal with bursty apps that only use FPU for - * a short time - */ - unsigned char fpu_counter; - int oomkilladj; /* OOM kill score adjustment (bit shift). */ char comm[TASK_COMM_LEN]; /* executable name excluding path - access with [gs]et_task_comm (which lock it with task_lock()) @@ -1086,8 +1057,9 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; - +#ifdef CONFIG_SECURITY void *security; +#endif struct audit_context *audit_context; seccomp_t seccomp; @@ -1149,13 +1121,6 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ -/* - * current io wait handle: wait queue entry to use for io waits - * If this thread is processing aio, this points at the waitqueue - * inside the currently handled kiocb. It may be NULL (i.e. default - * to a stack based synchronous wait) if its doing sync IO. - */ - wait_queue_t *io_wait; #ifdef CONFIG_TASK_XACCT /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; @@ -1171,18 +1136,24 @@ struct task_struct { short il_next; #endif #ifdef CONFIG_CPUSETS - struct cpuset *cpuset; nodemask_t mems_allowed; int cpuset_mems_generation; int cpuset_mem_spread_rotor; #endif +#ifdef CONFIG_CGROUPS + /* Control Group info protected by css_set_lock */ + struct css_set *cgroups; + /* cg_list protected by css_set_lock and tsk->alloc_lock */ + struct list_head cg_list; +#endif +#ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; - +#endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; @@ -1196,6 +1167,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; #endif + struct prop_local_single dirties; }; /* @@ -1229,24 +1201,14 @@ static inline int rt_task(struct task_struct *p) return rt_prio(p->prio); } -static inline pid_t process_group(struct task_struct *tsk) -{ - return tsk->signal->pgrp; -} - -static inline pid_t signal_session(struct signal_struct *sig) -{ - return sig->__session; -} - -static inline pid_t process_session(struct task_struct *tsk) +static inline void set_task_session(struct task_struct *tsk, pid_t session) { - return signal_session(tsk->signal); + tsk->signal->__session = session; } -static inline void set_signal_session(struct signal_struct *sig, pid_t session) +static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp) { - sig->__session = session; + tsk->signal->__pgrp = pgrp; } static inline struct pid *task_pid(struct task_struct *task) @@ -1269,6 +1231,88 @@ static inline struct pid *task_session(struct task_struct *task) return task->group_leader->pids[PIDTYPE_SID].pid; } +struct pid_namespace; + +/* + * the helpers to get the task's different pids as they are seen + * from various namespaces + * + * task_xid_nr() : global id, i.e. the id seen from the init namespace; + * task_xid_vnr() : virtual id, i.e. the id seen from the namespace the task + * belongs to. this only makes sence when called in the + * context of the task that belongs to the same namespace; + * task_xid_nr_ns() : id seen from the ns specified; + * + * set_task_vxid() : assigns a virtual id to a task; + * + * task_ppid_nr_ns() : the parent's id as seen from the namespace specified. + * the result depends on the namespace and whether the + * task in question is the namespace's init. e.g. for the + * namespace's init this will return 0 when called from + * the namespace of this init, or appropriate id otherwise. + * + * + * see also pid_nr() etc in include/linux/pid.h + */ + +static inline pid_t task_pid_nr(struct task_struct *tsk) +{ + return tsk->pid; +} + +pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); + +static inline pid_t task_pid_vnr(struct task_struct *tsk) +{ + return pid_vnr(task_pid(tsk)); +} + + +static inline pid_t task_tgid_nr(struct task_struct *tsk) +{ + return tsk->tgid; +} + +pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return pid_vnr(task_tgid(tsk)); +} + + +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return tsk->signal->__pgrp; +} + +pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); + +static inline pid_t task_pgrp_vnr(struct task_struct *tsk) +{ + return pid_vnr(task_pgrp(tsk)); +} + + +static inline pid_t task_session_nr(struct task_struct *tsk) +{ + return tsk->signal->__session; +} + +pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); + +static inline pid_t task_session_vnr(struct task_struct *tsk) +{ + return pid_vnr(task_session(tsk)); +} + + +static inline pid_t task_ppid_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return pid_nr_ns(task_pid(rcu_dereference(tsk->real_parent)), ns); +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. @@ -1283,16 +1327,22 @@ static inline int pid_alive(struct task_struct *p) } /** - * is_init - check if a task structure is init + * is_global_init - check if a task structure is init * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. */ -static inline int is_init(struct task_struct *tsk) +static inline int is_global_init(struct task_struct *tsk) { return tsk->pid == 1; } +/* + * is_container_init: + * check whether in the task is init in its own pid namespace. + */ +extern int is_container_init(struct task_struct *tsk); + extern struct pid *cad_pid; extern void free_task(struct task_struct *tsk); @@ -1314,6 +1364,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ +#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ @@ -1401,15 +1452,17 @@ static inline void idle_task_exit(void) {} extern void sched_idle_next(void); +#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_latency; -extern unsigned int sysctl_sched_min_granularity; +extern unsigned int sysctl_sched_nr_latency; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_batch_wakeup_granularity; -extern unsigned int sysctl_sched_stat_granularity; -extern unsigned int sysctl_sched_runtime_limit; -extern unsigned int sysctl_sched_compat_yield; extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; +extern unsigned int sysctl_sched_migration_cost; +#endif + +extern unsigned int sysctl_sched_compat_yield; #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); @@ -1461,8 +1514,32 @@ extern struct task_struct init_task; extern struct mm_struct init_mm; -#define find_task_by_pid(nr) find_task_by_pid_type(PIDTYPE_PID, nr) -extern struct task_struct *find_task_by_pid_type(int type, int pid); +extern struct pid_namespace init_pid_ns; + +/* + * find a task by one of its numerical ids + * + * find_task_by_pid_type_ns(): + * it is the most generic call - it finds a task by all id, + * type and namespace specified + * find_task_by_pid_ns(): + * finds a task by its pid in the specified namespace + * find_task_by_vpid(): + * finds a task by its virtual pid + * find_task_by_pid(): + * finds a task by its global pid + * + * see also find_pid() etc in include/linux/pid.h + */ + +extern struct task_struct *find_task_by_pid_type_ns(int type, int pid, + struct pid_namespace *ns); + +extern struct task_struct *find_task_by_pid(pid_t nr); +extern struct task_struct *find_task_by_vpid(pid_t nr); +extern struct task_struct *find_task_by_pid_ns(pid_t nr, + struct pid_namespace *ns); + extern void __set_special_pids(pid_t session, pid_t pgrp); /* per-UID process charging. */ @@ -1649,6 +1726,12 @@ static inline int has_group_leader_pid(struct task_struct *p) return p->pid == p->tgid; } +static inline +int same_thread_group(struct task_struct *p1, struct task_struct *p2) +{ + return p1->tgid == p2->tgid; +} + static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry(rcu_dereference(p->thread_group.next), @@ -1666,7 +1749,8 @@ static inline int thread_group_empty(struct task_struct *p) /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also - * pins the final release of task.io_context. Also protects ->cpuset. + * pins the final release of task.io_context. Also protects ->cpuset and + * ->cgroup.subsys[]. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), @@ -1843,6 +1927,18 @@ extern int sched_mc_power_savings, sched_smt_power_savings; extern void normalize_rt_tasks(void); +#ifdef CONFIG_FAIR_GROUP_SCHED + +extern struct task_group init_task_group; + +extern struct task_group *sched_create_group(void); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_move_task(struct task_struct *tsk); +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +extern unsigned long sched_group_shares(struct task_group *tg); + +#endif + #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 3ee412b..827b85b 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -8,54 +8,43 @@ */ struct screen_info { - u8 orig_x; /* 0x00 */ - u8 orig_y; /* 0x01 */ - u16 ext_mem_k; /* 0x02 */ - u16 orig_video_page; /* 0x04 */ - u8 orig_video_mode; /* 0x06 */ - u8 orig_video_cols; /* 0x07 */ - u16 unused2; /* 0x08 */ - u16 orig_video_ega_bx; /* 0x0a */ - u16 unused3; /* 0x0c */ - u8 orig_video_lines; /* 0x0e */ - u8 orig_video_isVGA; /* 0x0f */ - u16 orig_video_points; /* 0x10 */ + __u8 orig_x; /* 0x00 */ + __u8 orig_y; /* 0x01 */ + __u16 ext_mem_k; /* 0x02 */ + __u16 orig_video_page; /* 0x04 */ + __u8 orig_video_mode; /* 0x06 */ + __u8 orig_video_cols; /* 0x07 */ + __u16 unused2; /* 0x08 */ + __u16 orig_video_ega_bx;/* 0x0a */ + __u16 unused3; /* 0x0c */ + __u8 orig_video_lines; /* 0x0e */ + __u8 orig_video_isVGA; /* 0x0f */ + __u16 orig_video_points;/* 0x10 */ /* VESA graphic mode -- linear frame buffer */ - u16 lfb_width; /* 0x12 */ - u16 lfb_height; /* 0x14 */ - u16 lfb_depth; /* 0x16 */ - u32 lfb_base; /* 0x18 */ - u32 lfb_size; /* 0x1c */ - u16 cl_magic, cl_offset; /* 0x20 */ - u16 lfb_linelength; /* 0x24 */ - u8 red_size; /* 0x26 */ - u8 red_pos; /* 0x27 */ - u8 green_size; /* 0x28 */ - u8 green_pos; /* 0x29 */ - u8 blue_size; /* 0x2a */ - u8 blue_pos; /* 0x2b */ - u8 rsvd_size; /* 0x2c */ - u8 rsvd_pos; /* 0x2d */ - u16 vesapm_seg; /* 0x2e */ - u16 vesapm_off; /* 0x30 */ - u16 pages; /* 0x32 */ - u16 vesa_attributes; /* 0x34 */ - u32 capabilities; /* 0x36 */ - u8 _reserved[6]; /* 0x3a */ + __u16 lfb_width; /* 0x12 */ + __u16 lfb_height; /* 0x14 */ + __u16 lfb_depth; /* 0x16 */ + __u32 lfb_base; /* 0x18 */ + __u32 lfb_size; /* 0x1c */ + __u16 cl_magic, cl_offset; /* 0x20 */ + __u16 lfb_linelength; /* 0x24 */ + __u8 red_size; /* 0x26 */ + __u8 red_pos; /* 0x27 */ + __u8 green_size; /* 0x28 */ + __u8 green_pos; /* 0x29 */ + __u8 blue_size; /* 0x2a */ + __u8 blue_pos; /* 0x2b */ + __u8 rsvd_size; /* 0x2c */ + __u8 rsvd_pos; /* 0x2d */ + __u16 vesapm_seg; /* 0x2e */ + __u16 vesapm_off; /* 0x30 */ + __u16 pages; /* 0x32 */ + __u16 vesa_attributes; /* 0x34 */ + __u32 capabilities; /* 0x36 */ + __u8 _reserved[6]; /* 0x3a */ } __attribute__((packed)); -extern struct screen_info screen_info; - -#define ORIG_X (screen_info.orig_x) -#define ORIG_Y (screen_info.orig_y) -#define ORIG_VIDEO_MODE (screen_info.orig_video_mode) -#define ORIG_VIDEO_COLS (screen_info.orig_video_cols) -#define ORIG_VIDEO_EGA_BX (screen_info.orig_video_ega_bx) -#define ORIG_VIDEO_LINES (screen_info.orig_video_lines) -#define ORIG_VIDEO_ISVGA (screen_info.orig_video_isVGA) -#define ORIG_VIDEO_POINTS (screen_info.orig_video_points) - #define VIDEO_TYPE_MDA 0x10 /* Monochrome Text Display */ #define VIDEO_TYPE_CGA 0x11 /* CGA Display */ #define VIDEO_TYPE_EGAM 0x20 /* EGA/VGA in Monochrome Mode */ @@ -74,4 +63,17 @@ extern struct screen_info screen_info; #define VIDEO_TYPE_PMAC 0x60 /* PowerMacintosh frame buffer. */ +#ifdef __KERNEL__ +extern struct screen_info screen_info; + +#define ORIG_X (screen_info.orig_x) +#define ORIG_Y (screen_info.orig_y) +#define ORIG_VIDEO_MODE (screen_info.orig_video_mode) +#define ORIG_VIDEO_COLS (screen_info.orig_video_cols) +#define ORIG_VIDEO_EGA_BX (screen_info.orig_video_ega_bx) +#define ORIG_VIDEO_LINES (screen_info.orig_video_lines) +#define ORIG_VIDEO_ISVGA (screen_info.orig_video_isVGA) +#define ORIG_VIDEO_POINTS (screen_info.orig_video_points) +#endif /* __KERNEL__ */ + #endif /* _SCREEN_INFO_H */ diff --git a/include/linux/security.h b/include/linux/security.h index 1a15526..ac05083 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -34,6 +34,13 @@ #include <linux/xfrm.h> #include <net/flow.h> +/* + * Bounding set + */ +extern kernel_cap_t cap_bset; + +extern unsigned securebits; + struct ctl_table; /* @@ -51,10 +58,16 @@ extern void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe); extern int cap_bprm_secureexec(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, char *name, void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, char *name); +extern int cap_inode_need_killpriv(struct dentry *dentry); +extern int cap_inode_killpriv(struct dentry *dentry); extern int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags); extern void cap_task_reparent_to_init (struct task_struct *p); +extern int cap_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid); +extern int cap_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp); +extern int cap_task_setioprio (struct task_struct *p, int ioprio); +extern int cap_task_setnice (struct task_struct *p, int nice); extern int cap_syslog (int type); -extern int cap_vm_enough_memory (struct mm_struct *mm, long pages); +extern int cap_vm_enough_memory(struct mm_struct *mm, long pages); struct msghdr; struct sk_buff; @@ -413,6 +426,18 @@ struct request_sock; * is specified by @buffer_size. @buffer may be NULL to request * the size of the buffer required. * Returns number of bytes used/required on success. + * @inode_need_killpriv: + * Called when an inode has been changed. + * @dentry is the dentry being changed. + * Return <0 on error to abort the inode change operation. + * Return 0 if inode_killpriv does not need to be called. + * Return >0 if inode_killpriv does need to be called. + * @inode_killpriv: + * The setuid bit is being removed. Remove similar security labels. + * Called with the dentry->d_inode->i_mutex held. + * @dentry is the dentry being changed. + * Return 0 on success. If error is returned, then the operation + * causing setuid bit removal is failed. * * Security hooks for file operations * @@ -504,6 +529,13 @@ struct request_sock; * @file contains the file structure being received. * Return 0 if permission is granted. * + * Security hook for dentry + * + * @dentry_open + * Save open-time permission checking state for later use upon + * file_permission, and recheck access if anything has changed + * since inode_permission. + * * Security hooks for task operations. * * @task_create: @@ -800,9 +832,11 @@ struct request_sock; * incoming sk_buff @skb has been associated with a particular socket, @sk. * @sk contains the sock (not socket) associated with the incoming sk_buff. * @skb contains the incoming network data. - * @socket_getpeersec: + * @socket_getpeersec_stream: * This hook allows the security module to provide peer socket security - * state to userspace via getsockopt SO_GETPEERSEC. + * state for unix or connected tcp sockets to userspace via getsockopt + * SO_GETPEERSEC. For tcp sockets this can be meaningful if the + * socket is associated with an ipsec SA. * @sock is the local socket. * @optval userspace memory where the security state is to be copied. * @optlen userspace int where the module should copy the actual length @@ -811,6 +845,17 @@ struct request_sock; * by the caller. * Return 0 if all is well, otherwise, typical getsockopt return * values. + * @socket_getpeersec_dgram: + * This hook allows the security module to provide peer socket security + * state for udp sockets on a per-packet basis to userspace via + * getsockopt SO_GETPEERSEC. The application must first have indicated + * the IP_PASSSEC option via getsockopt. It can then retrieve the + * security state returned by this hook for a packet via the SCM_SECURITY + * ancillary message type. + * @skb is the skbuff for the packet being queried + * @secdata is a pointer to a buffer in which to copy the security data + * @seclen is the maximum length for @secdata + * Return 0 on success, error on failure. * @sk_alloc_security: * Allocate and attach a security structure to the sk->sk_security field, * which is used to copy security attributes between local stream sockets. @@ -1133,10 +1178,6 @@ struct request_sock; * allow module stacking. * @name contains the name of the security module being stacked. * @ops contains a pointer to the struct security_operations of the module to stack. - * @unregister_security: - * remove a stacked module. - * @name contains the name of the security module being unstacked. - * @ops contains a pointer to the struct security_operations of the module to unstack. * * @secid_to_secctx: * Convert secid to security context. @@ -1232,7 +1273,8 @@ struct security_operations { int (*inode_getxattr) (struct dentry *dentry, char *name); int (*inode_listxattr) (struct dentry *dentry); int (*inode_removexattr) (struct dentry *dentry, char *name); - const char *(*inode_xattr_getsuffix) (void); + int (*inode_need_killpriv) (struct dentry *dentry); + int (*inode_killpriv) (struct dentry *dentry); int (*inode_getsecurity)(const struct inode *inode, const char *name, void *buffer, size_t size, int err); int (*inode_setsecurity)(struct inode *inode, const char *name, const void *value, size_t size, int flags); int (*inode_listsecurity)(struct inode *inode, char *buffer, size_t buffer_size); @@ -1256,6 +1298,7 @@ struct security_operations { int (*file_send_sigiotask) (struct task_struct * tsk, struct fown_struct * fown, int sig); int (*file_receive) (struct file * file); + int (*dentry_open) (struct file *file); int (*task_create) (unsigned long clone_flags); int (*task_alloc_security) (struct task_struct * p); @@ -1322,8 +1365,6 @@ struct security_operations { /* allow module stacking */ int (*register_security) (const char *name, struct security_operations *ops); - int (*unregister_security) (const char *name, - struct security_operations *ops); void (*d_instantiate) (struct dentry *dentry, struct inode *inode); @@ -1401,743 +1442,10 @@ struct security_operations { }; -/* global variables */ -extern struct security_operations *security_ops; - -/* inline stuff */ -static inline int security_ptrace (struct task_struct * parent, struct task_struct * child) -{ - return security_ops->ptrace (parent, child); -} - -static inline int security_capget (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - return security_ops->capget (target, effective, inheritable, permitted); -} - -static inline int security_capset_check (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - return security_ops->capset_check (target, effective, inheritable, permitted); -} - -static inline void security_capset_set (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - security_ops->capset_set (target, effective, inheritable, permitted); -} - -static inline int security_capable(struct task_struct *tsk, int cap) -{ - return security_ops->capable(tsk, cap); -} - -static inline int security_acct (struct file *file) -{ - return security_ops->acct (file); -} - -static inline int security_sysctl(struct ctl_table *table, int op) -{ - return security_ops->sysctl(table, op); -} - -static inline int security_quotactl (int cmds, int type, int id, - struct super_block *sb) -{ - return security_ops->quotactl (cmds, type, id, sb); -} - -static inline int security_quota_on (struct dentry * dentry) -{ - return security_ops->quota_on (dentry); -} - -static inline int security_syslog(int type) -{ - return security_ops->syslog(type); -} - -static inline int security_settime(struct timespec *ts, struct timezone *tz) -{ - return security_ops->settime(ts, tz); -} - -static inline int security_vm_enough_memory(long pages) -{ - return security_ops->vm_enough_memory(current->mm, pages); -} - -static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) -{ - return security_ops->vm_enough_memory(mm, pages); -} - -static inline int security_bprm_alloc (struct linux_binprm *bprm) -{ - return security_ops->bprm_alloc_security (bprm); -} -static inline void security_bprm_free (struct linux_binprm *bprm) -{ - security_ops->bprm_free_security (bprm); -} -static inline void security_bprm_apply_creds (struct linux_binprm *bprm, int unsafe) -{ - security_ops->bprm_apply_creds (bprm, unsafe); -} -static inline void security_bprm_post_apply_creds (struct linux_binprm *bprm) -{ - security_ops->bprm_post_apply_creds (bprm); -} -static inline int security_bprm_set (struct linux_binprm *bprm) -{ - return security_ops->bprm_set_security (bprm); -} - -static inline int security_bprm_check (struct linux_binprm *bprm) -{ - return security_ops->bprm_check_security (bprm); -} - -static inline int security_bprm_secureexec (struct linux_binprm *bprm) -{ - return security_ops->bprm_secureexec (bprm); -} - -static inline int security_sb_alloc (struct super_block *sb) -{ - return security_ops->sb_alloc_security (sb); -} - -static inline void security_sb_free (struct super_block *sb) -{ - security_ops->sb_free_security (sb); -} - -static inline int security_sb_copy_data (struct file_system_type *type, - void *orig, void *copy) -{ - return security_ops->sb_copy_data (type, orig, copy); -} - -static inline int security_sb_kern_mount (struct super_block *sb, void *data) -{ - return security_ops->sb_kern_mount (sb, data); -} - -static inline int security_sb_statfs (struct dentry *dentry) -{ - return security_ops->sb_statfs (dentry); -} - -static inline int security_sb_mount (char *dev_name, struct nameidata *nd, - char *type, unsigned long flags, - void *data) -{ - return security_ops->sb_mount (dev_name, nd, type, flags, data); -} - -static inline int security_sb_check_sb (struct vfsmount *mnt, - struct nameidata *nd) -{ - return security_ops->sb_check_sb (mnt, nd); -} - -static inline int security_sb_umount (struct vfsmount *mnt, int flags) -{ - return security_ops->sb_umount (mnt, flags); -} - -static inline void security_sb_umount_close (struct vfsmount *mnt) -{ - security_ops->sb_umount_close (mnt); -} - -static inline void security_sb_umount_busy (struct vfsmount *mnt) -{ - security_ops->sb_umount_busy (mnt); -} - -static inline void security_sb_post_remount (struct vfsmount *mnt, - unsigned long flags, void *data) -{ - security_ops->sb_post_remount (mnt, flags, data); -} - -static inline void security_sb_post_mountroot (void) -{ - security_ops->sb_post_mountroot (); -} - -static inline void security_sb_post_addmount (struct vfsmount *mnt, - struct nameidata *mountpoint_nd) -{ - security_ops->sb_post_addmount (mnt, mountpoint_nd); -} - -static inline int security_sb_pivotroot (struct nameidata *old_nd, - struct nameidata *new_nd) -{ - return security_ops->sb_pivotroot (old_nd, new_nd); -} - -static inline void security_sb_post_pivotroot (struct nameidata *old_nd, - struct nameidata *new_nd) -{ - security_ops->sb_post_pivotroot (old_nd, new_nd); -} - -static inline int security_inode_alloc (struct inode *inode) -{ - inode->i_security = NULL; - return security_ops->inode_alloc_security (inode); -} - -static inline void security_inode_free (struct inode *inode) -{ - security_ops->inode_free_security (inode); -} - -static inline int security_inode_init_security (struct inode *inode, - struct inode *dir, - char **name, - void **value, - size_t *len) -{ - if (unlikely (IS_PRIVATE (inode))) - return -EOPNOTSUPP; - return security_ops->inode_init_security (inode, dir, name, value, len); -} - -static inline int security_inode_create (struct inode *dir, - struct dentry *dentry, - int mode) -{ - if (unlikely (IS_PRIVATE (dir))) - return 0; - return security_ops->inode_create (dir, dentry, mode); -} - -static inline int security_inode_link (struct dentry *old_dentry, - struct inode *dir, - struct dentry *new_dentry) -{ - if (unlikely (IS_PRIVATE (old_dentry->d_inode))) - return 0; - return security_ops->inode_link (old_dentry, dir, new_dentry); -} - -static inline int security_inode_unlink (struct inode *dir, - struct dentry *dentry) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_unlink (dir, dentry); -} - -static inline int security_inode_symlink (struct inode *dir, - struct dentry *dentry, - const char *old_name) -{ - if (unlikely (IS_PRIVATE (dir))) - return 0; - return security_ops->inode_symlink (dir, dentry, old_name); -} - -static inline int security_inode_mkdir (struct inode *dir, - struct dentry *dentry, - int mode) -{ - if (unlikely (IS_PRIVATE (dir))) - return 0; - return security_ops->inode_mkdir (dir, dentry, mode); -} - -static inline int security_inode_rmdir (struct inode *dir, - struct dentry *dentry) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_rmdir (dir, dentry); -} - -static inline int security_inode_mknod (struct inode *dir, - struct dentry *dentry, - int mode, dev_t dev) -{ - if (unlikely (IS_PRIVATE (dir))) - return 0; - return security_ops->inode_mknod (dir, dentry, mode, dev); -} - -static inline int security_inode_rename (struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry) -{ - if (unlikely (IS_PRIVATE (old_dentry->d_inode) || - (new_dentry->d_inode && IS_PRIVATE (new_dentry->d_inode)))) - return 0; - return security_ops->inode_rename (old_dir, old_dentry, - new_dir, new_dentry); -} - -static inline int security_inode_readlink (struct dentry *dentry) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_readlink (dentry); -} - -static inline int security_inode_follow_link (struct dentry *dentry, - struct nameidata *nd) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_follow_link (dentry, nd); -} - -static inline int security_inode_permission (struct inode *inode, int mask, - struct nameidata *nd) -{ - if (unlikely (IS_PRIVATE (inode))) - return 0; - return security_ops->inode_permission (inode, mask, nd); -} - -static inline int security_inode_setattr (struct dentry *dentry, - struct iattr *attr) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_setattr (dentry, attr); -} - -static inline int security_inode_getattr (struct vfsmount *mnt, - struct dentry *dentry) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_getattr (mnt, dentry); -} - -static inline void security_inode_delete (struct inode *inode) -{ - if (unlikely (IS_PRIVATE (inode))) - return; - security_ops->inode_delete (inode); -} - -static inline int security_inode_setxattr (struct dentry *dentry, char *name, - void *value, size_t size, int flags) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_setxattr (dentry, name, value, size, flags); -} - -static inline void security_inode_post_setxattr (struct dentry *dentry, char *name, - void *value, size_t size, int flags) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return; - security_ops->inode_post_setxattr (dentry, name, value, size, flags); -} - -static inline int security_inode_getxattr (struct dentry *dentry, char *name) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_getxattr (dentry, name); -} - -static inline int security_inode_listxattr (struct dentry *dentry) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_listxattr (dentry); -} - -static inline int security_inode_removexattr (struct dentry *dentry, char *name) -{ - if (unlikely (IS_PRIVATE (dentry->d_inode))) - return 0; - return security_ops->inode_removexattr (dentry, name); -} - -static inline const char *security_inode_xattr_getsuffix(void) -{ - return security_ops->inode_xattr_getsuffix(); -} - -static inline int security_inode_getsecurity(const struct inode *inode, const char *name, void *buffer, size_t size, int err) -{ - if (unlikely (IS_PRIVATE (inode))) - return 0; - return security_ops->inode_getsecurity(inode, name, buffer, size, err); -} - -static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) -{ - if (unlikely (IS_PRIVATE (inode))) - return 0; - return security_ops->inode_setsecurity(inode, name, value, size, flags); -} - -static inline int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) -{ - if (unlikely (IS_PRIVATE (inode))) - return 0; - return security_ops->inode_listsecurity(inode, buffer, buffer_size); -} - -static inline int security_file_permission (struct file *file, int mask) -{ - return security_ops->file_permission (file, mask); -} - -static inline int security_file_alloc (struct file *file) -{ - return security_ops->file_alloc_security (file); -} - -static inline void security_file_free (struct file *file) -{ - security_ops->file_free_security (file); -} - -static inline int security_file_ioctl (struct file *file, unsigned int cmd, - unsigned long arg) -{ - return security_ops->file_ioctl (file, cmd, arg); -} - -static inline int security_file_mmap (struct file *file, unsigned long reqprot, - unsigned long prot, - unsigned long flags, - unsigned long addr, - unsigned long addr_only) -{ - return security_ops->file_mmap (file, reqprot, prot, flags, addr, - addr_only); -} - -static inline int security_file_mprotect (struct vm_area_struct *vma, - unsigned long reqprot, - unsigned long prot) -{ - return security_ops->file_mprotect (vma, reqprot, prot); -} - -static inline int security_file_lock (struct file *file, unsigned int cmd) -{ - return security_ops->file_lock (file, cmd); -} - -static inline int security_file_fcntl (struct file *file, unsigned int cmd, - unsigned long arg) -{ - return security_ops->file_fcntl (file, cmd, arg); -} - -static inline int security_file_set_fowner (struct file *file) -{ - return security_ops->file_set_fowner (file); -} - -static inline int security_file_send_sigiotask (struct task_struct *tsk, - struct fown_struct *fown, - int sig) -{ - return security_ops->file_send_sigiotask (tsk, fown, sig); -} - -static inline int security_file_receive (struct file *file) -{ - return security_ops->file_receive (file); -} - -static inline int security_task_create (unsigned long clone_flags) -{ - return security_ops->task_create (clone_flags); -} - -static inline int security_task_alloc (struct task_struct *p) -{ - return security_ops->task_alloc_security (p); -} - -static inline void security_task_free (struct task_struct *p) -{ - security_ops->task_free_security (p); -} - -static inline int security_task_setuid (uid_t id0, uid_t id1, uid_t id2, - int flags) -{ - return security_ops->task_setuid (id0, id1, id2, flags); -} - -static inline int security_task_post_setuid (uid_t old_ruid, uid_t old_euid, - uid_t old_suid, int flags) -{ - return security_ops->task_post_setuid (old_ruid, old_euid, old_suid, flags); -} - -static inline int security_task_setgid (gid_t id0, gid_t id1, gid_t id2, - int flags) -{ - return security_ops->task_setgid (id0, id1, id2, flags); -} - -static inline int security_task_setpgid (struct task_struct *p, pid_t pgid) -{ - return security_ops->task_setpgid (p, pgid); -} - -static inline int security_task_getpgid (struct task_struct *p) -{ - return security_ops->task_getpgid (p); -} - -static inline int security_task_getsid (struct task_struct *p) -{ - return security_ops->task_getsid (p); -} - -static inline void security_task_getsecid (struct task_struct *p, u32 *secid) -{ - security_ops->task_getsecid (p, secid); -} - -static inline int security_task_setgroups (struct group_info *group_info) -{ - return security_ops->task_setgroups (group_info); -} - -static inline int security_task_setnice (struct task_struct *p, int nice) -{ - return security_ops->task_setnice (p, nice); -} - -static inline int security_task_setioprio (struct task_struct *p, int ioprio) -{ - return security_ops->task_setioprio (p, ioprio); -} - -static inline int security_task_getioprio (struct task_struct *p) -{ - return security_ops->task_getioprio (p); -} - -static inline int security_task_setrlimit (unsigned int resource, - struct rlimit *new_rlim) -{ - return security_ops->task_setrlimit (resource, new_rlim); -} - -static inline int security_task_setscheduler (struct task_struct *p, - int policy, - struct sched_param *lp) -{ - return security_ops->task_setscheduler (p, policy, lp); -} - -static inline int security_task_getscheduler (struct task_struct *p) -{ - return security_ops->task_getscheduler (p); -} - -static inline int security_task_movememory (struct task_struct *p) -{ - return security_ops->task_movememory (p); -} - -static inline int security_task_kill (struct task_struct *p, - struct siginfo *info, int sig, - u32 secid) -{ - return security_ops->task_kill (p, info, sig, secid); -} - -static inline int security_task_wait (struct task_struct *p) -{ - return security_ops->task_wait (p); -} - -static inline int security_task_prctl (int option, unsigned long arg2, - unsigned long arg3, - unsigned long arg4, - unsigned long arg5) -{ - return security_ops->task_prctl (option, arg2, arg3, arg4, arg5); -} - -static inline void security_task_reparent_to_init (struct task_struct *p) -{ - security_ops->task_reparent_to_init (p); -} - -static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) -{ - security_ops->task_to_inode(p, inode); -} - -static inline int security_ipc_permission (struct kern_ipc_perm *ipcp, - short flag) -{ - return security_ops->ipc_permission (ipcp, flag); -} - -static inline int security_msg_msg_alloc (struct msg_msg * msg) -{ - return security_ops->msg_msg_alloc_security (msg); -} - -static inline void security_msg_msg_free (struct msg_msg * msg) -{ - security_ops->msg_msg_free_security(msg); -} - -static inline int security_msg_queue_alloc (struct msg_queue *msq) -{ - return security_ops->msg_queue_alloc_security (msq); -} - -static inline void security_msg_queue_free (struct msg_queue *msq) -{ - security_ops->msg_queue_free_security (msq); -} - -static inline int security_msg_queue_associate (struct msg_queue * msq, - int msqflg) -{ - return security_ops->msg_queue_associate (msq, msqflg); -} - -static inline int security_msg_queue_msgctl (struct msg_queue * msq, int cmd) -{ - return security_ops->msg_queue_msgctl (msq, cmd); -} - -static inline int security_msg_queue_msgsnd (struct msg_queue * msq, - struct msg_msg * msg, int msqflg) -{ - return security_ops->msg_queue_msgsnd (msq, msg, msqflg); -} - -static inline int security_msg_queue_msgrcv (struct msg_queue * msq, - struct msg_msg * msg, - struct task_struct * target, - long type, int mode) -{ - return security_ops->msg_queue_msgrcv (msq, msg, target, type, mode); -} - -static inline int security_shm_alloc (struct shmid_kernel *shp) -{ - return security_ops->shm_alloc_security (shp); -} - -static inline void security_shm_free (struct shmid_kernel *shp) -{ - security_ops->shm_free_security (shp); -} - -static inline int security_shm_associate (struct shmid_kernel * shp, - int shmflg) -{ - return security_ops->shm_associate(shp, shmflg); -} - -static inline int security_shm_shmctl (struct shmid_kernel * shp, int cmd) -{ - return security_ops->shm_shmctl (shp, cmd); -} - -static inline int security_shm_shmat (struct shmid_kernel * shp, - char __user *shmaddr, int shmflg) -{ - return security_ops->shm_shmat(shp, shmaddr, shmflg); -} - -static inline int security_sem_alloc (struct sem_array *sma) -{ - return security_ops->sem_alloc_security (sma); -} - -static inline void security_sem_free (struct sem_array *sma) -{ - security_ops->sem_free_security (sma); -} - -static inline int security_sem_associate (struct sem_array * sma, int semflg) -{ - return security_ops->sem_associate (sma, semflg); -} - -static inline int security_sem_semctl (struct sem_array * sma, int cmd) -{ - return security_ops->sem_semctl(sma, cmd); -} - -static inline int security_sem_semop (struct sem_array * sma, - struct sembuf * sops, unsigned nsops, - int alter) -{ - return security_ops->sem_semop(sma, sops, nsops, alter); -} - -static inline void security_d_instantiate (struct dentry *dentry, struct inode *inode) -{ - if (unlikely (inode && IS_PRIVATE (inode))) - return; - security_ops->d_instantiate (dentry, inode); -} - -static inline int security_getprocattr(struct task_struct *p, char *name, char **value) -{ - return security_ops->getprocattr(p, name, value); -} - -static inline int security_setprocattr(struct task_struct *p, char *name, void *value, size_t size) -{ - return security_ops->setprocattr(p, name, value, size); -} - -static inline int security_netlink_send(struct sock *sk, struct sk_buff * skb) -{ - return security_ops->netlink_send(sk, skb); -} - -static inline int security_netlink_recv(struct sk_buff * skb, int cap) -{ - return security_ops->netlink_recv(skb, cap); -} - -static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) -{ - return security_ops->secid_to_secctx(secid, secdata, seclen); -} - -static inline void security_release_secctx(char *secdata, u32 seclen) -{ - return security_ops->release_secctx(secdata, seclen); -} - /* prototypes */ extern int security_init (void); extern int register_security (struct security_operations *ops); -extern int unregister_security (struct security_operations *ops); extern int mod_reg_security (const char *name, struct security_operations *ops); -extern int mod_unreg_security (const char *name, struct security_operations *ops); extern struct dentry *securityfs_create_file(const char *name, mode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); @@ -2145,6 +1453,158 @@ extern struct dentry *securityfs_create_dir(const char *name, struct dentry *par extern void securityfs_remove(struct dentry *dentry); +/* Security operations */ +int security_ptrace(struct task_struct *parent, struct task_struct *child); +int security_capget(struct task_struct *target, + kernel_cap_t *effective, + kernel_cap_t *inheritable, + kernel_cap_t *permitted); +int security_capset_check(struct task_struct *target, + kernel_cap_t *effective, + kernel_cap_t *inheritable, + kernel_cap_t *permitted); +void security_capset_set(struct task_struct *target, + kernel_cap_t *effective, + kernel_cap_t *inheritable, + kernel_cap_t *permitted); +int security_capable(struct task_struct *tsk, int cap); +int security_acct(struct file *file); +int security_sysctl(struct ctl_table *table, int op); +int security_quotactl(int cmds, int type, int id, struct super_block *sb); +int security_quota_on(struct dentry *dentry); +int security_syslog(int type); +int security_settime(struct timespec *ts, struct timezone *tz); +int security_vm_enough_memory(long pages); +int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); +int security_bprm_alloc(struct linux_binprm *bprm); +void security_bprm_free(struct linux_binprm *bprm); +void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe); +void security_bprm_post_apply_creds(struct linux_binprm *bprm); +int security_bprm_set(struct linux_binprm *bprm); +int security_bprm_check(struct linux_binprm *bprm); +int security_bprm_secureexec(struct linux_binprm *bprm); +int security_sb_alloc(struct super_block *sb); +void security_sb_free(struct super_block *sb); +int security_sb_copy_data(struct file_system_type *type, void *orig, void *copy); +int security_sb_kern_mount(struct super_block *sb, void *data); +int security_sb_statfs(struct dentry *dentry); +int security_sb_mount(char *dev_name, struct nameidata *nd, + char *type, unsigned long flags, void *data); +int security_sb_check_sb(struct vfsmount *mnt, struct nameidata *nd); +int security_sb_umount(struct vfsmount *mnt, int flags); +void security_sb_umount_close(struct vfsmount *mnt); +void security_sb_umount_busy(struct vfsmount *mnt); +void security_sb_post_remount(struct vfsmount *mnt, unsigned long flags, void *data); +void security_sb_post_mountroot(void); +void security_sb_post_addmount(struct vfsmount *mnt, struct nameidata *mountpoint_nd); +int security_sb_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); +void security_sb_post_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); +int security_inode_alloc(struct inode *inode); +void security_inode_free(struct inode *inode); +int security_inode_init_security(struct inode *inode, struct inode *dir, + char **name, void **value, size_t *len); +int security_inode_create(struct inode *dir, struct dentry *dentry, int mode); +int security_inode_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry); +int security_inode_unlink(struct inode *dir, struct dentry *dentry); +int security_inode_symlink(struct inode *dir, struct dentry *dentry, + const char *old_name); +int security_inode_mkdir(struct inode *dir, struct dentry *dentry, int mode); +int security_inode_rmdir(struct inode *dir, struct dentry *dentry); +int security_inode_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev); +int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); +int security_inode_readlink(struct dentry *dentry); +int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); +int security_inode_permission(struct inode *inode, int mask, struct nameidata *nd); +int security_inode_setattr(struct dentry *dentry, struct iattr *attr); +int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry); +void security_inode_delete(struct inode *inode); +int security_inode_setxattr(struct dentry *dentry, char *name, + void *value, size_t size, int flags); +void security_inode_post_setxattr(struct dentry *dentry, char *name, + void *value, size_t size, int flags); +int security_inode_getxattr(struct dentry *dentry, char *name); +int security_inode_listxattr(struct dentry *dentry); +int security_inode_removexattr(struct dentry *dentry, char *name); +int security_inode_need_killpriv(struct dentry *dentry); +int security_inode_killpriv(struct dentry *dentry); +int security_inode_getsecurity(const struct inode *inode, const char *name, void *buffer, size_t size, int err); +int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); +int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); +int security_file_permission(struct file *file, int mask); +int security_file_alloc(struct file *file); +void security_file_free(struct file *file); +int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int security_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only); +int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, + unsigned long prot); +int security_file_lock(struct file *file, unsigned int cmd); +int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +int security_file_set_fowner(struct file *file); +int security_file_send_sigiotask(struct task_struct *tsk, + struct fown_struct *fown, int sig); +int security_file_receive(struct file *file); +int security_dentry_open(struct file *file); +int security_task_create(unsigned long clone_flags); +int security_task_alloc(struct task_struct *p); +void security_task_free(struct task_struct *p); +int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags); +int security_task_post_setuid(uid_t old_ruid, uid_t old_euid, + uid_t old_suid, int flags); +int security_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags); +int security_task_setpgid(struct task_struct *p, pid_t pgid); +int security_task_getpgid(struct task_struct *p); +int security_task_getsid(struct task_struct *p); +void security_task_getsecid(struct task_struct *p, u32 *secid); +int security_task_setgroups(struct group_info *group_info); +int security_task_setnice(struct task_struct *p, int nice); +int security_task_setioprio(struct task_struct *p, int ioprio); +int security_task_getioprio(struct task_struct *p); +int security_task_setrlimit(unsigned int resource, struct rlimit *new_rlim); +int security_task_setscheduler(struct task_struct *p, + int policy, struct sched_param *lp); +int security_task_getscheduler(struct task_struct *p); +int security_task_movememory(struct task_struct *p); +int security_task_kill(struct task_struct *p, struct siginfo *info, + int sig, u32 secid); +int security_task_wait(struct task_struct *p); +int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); +void security_task_reparent_to_init(struct task_struct *p); +void security_task_to_inode(struct task_struct *p, struct inode *inode); +int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); +int security_msg_msg_alloc(struct msg_msg *msg); +void security_msg_msg_free(struct msg_msg *msg); +int security_msg_queue_alloc(struct msg_queue *msq); +void security_msg_queue_free(struct msg_queue *msq); +int security_msg_queue_associate(struct msg_queue *msq, int msqflg); +int security_msg_queue_msgctl(struct msg_queue *msq, int cmd); +int security_msg_queue_msgsnd(struct msg_queue *msq, + struct msg_msg *msg, int msqflg); +int security_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg, + struct task_struct *target, long type, int mode); +int security_shm_alloc(struct shmid_kernel *shp); +void security_shm_free(struct shmid_kernel *shp); +int security_shm_associate(struct shmid_kernel *shp, int shmflg); +int security_shm_shmctl(struct shmid_kernel *shp, int cmd); +int security_shm_shmat(struct shmid_kernel *shp, char __user *shmaddr, int shmflg); +int security_sem_alloc(struct sem_array *sma); +void security_sem_free(struct sem_array *sma); +int security_sem_associate(struct sem_array *sma, int semflg); +int security_sem_semctl(struct sem_array *sma, int cmd); +int security_sem_semop(struct sem_array *sma, struct sembuf *sops, + unsigned nsops, int alter); +void security_d_instantiate (struct dentry *dentry, struct inode *inode); +int security_getprocattr(struct task_struct *p, char *name, char **value); +int security_setprocattr(struct task_struct *p, char *name, void *value, size_t size); +int security_netlink_send(struct sock *sk, struct sk_buff *skb); +int security_netlink_recv(struct sk_buff *skb, int cap); +int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +void security_release_secctx(char *secdata, u32 seclen); + #else /* CONFIG_SECURITY */ /* @@ -2463,9 +1923,14 @@ static inline int security_inode_removexattr (struct dentry *dentry, char *name) return cap_inode_removexattr(dentry, name); } -static inline const char *security_inode_xattr_getsuffix (void) +static inline int security_inode_need_killpriv(struct dentry *dentry) +{ + return cap_inode_need_killpriv(dentry); +} + +static inline int security_inode_killpriv(struct dentry *dentry) { - return NULL ; + return cap_inode_killpriv(dentry); } static inline int security_inode_getsecurity(const struct inode *inode, const char *name, void *buffer, size_t size, int err) @@ -2546,6 +2011,11 @@ static inline int security_file_receive (struct file *file) return 0; } +static inline int security_dentry_open (struct file *file) +{ + return 0; +} + static inline int security_task_create (unsigned long clone_flags) { return 0; @@ -2602,12 +2072,12 @@ static inline int security_task_setgroups (struct group_info *group_info) static inline int security_task_setnice (struct task_struct *p, int nice) { - return 0; + return cap_task_setnice(p, nice); } static inline int security_task_setioprio (struct task_struct *p, int ioprio) { - return 0; + return cap_task_setioprio(p, ioprio); } static inline int security_task_getioprio (struct task_struct *p) @@ -2625,7 +2095,7 @@ static inline int security_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp) { - return 0; + return cap_task_setscheduler(p, policy, lp); } static inline int security_task_getscheduler (struct task_struct *p) @@ -2642,7 +2112,7 @@ static inline int security_task_kill (struct task_struct *p, struct siginfo *info, int sig, u32 secid) { - return 0; + return cap_task_kill(p, info, sig, secid); } static inline int security_task_wait (struct task_struct *p) @@ -2816,170 +2286,43 @@ static inline void security_release_secctx(char *secdata, u32 seclen) #endif /* CONFIG_SECURITY */ #ifdef CONFIG_SECURITY_NETWORK -static inline int security_unix_stream_connect(struct socket * sock, - struct socket * other, - struct sock * newsk) -{ - return security_ops->unix_stream_connect(sock, other, newsk); -} +int security_unix_stream_connect(struct socket *sock, struct socket *other, + struct sock *newsk); +int security_unix_may_send(struct socket *sock, struct socket *other); +int security_socket_create(int family, int type, int protocol, int kern); +int security_socket_post_create(struct socket *sock, int family, + int type, int protocol, int kern); +int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen); +int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen); +int security_socket_listen(struct socket *sock, int backlog); +int security_socket_accept(struct socket *sock, struct socket *newsock); +void security_socket_post_accept(struct socket *sock, struct socket *newsock); +int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size); +int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, + int size, int flags); +int security_socket_getsockname(struct socket *sock); +int security_socket_getpeername(struct socket *sock); +int security_socket_getsockopt(struct socket *sock, int level, int optname); +int security_socket_setsockopt(struct socket *sock, int level, int optname); +int security_socket_shutdown(struct socket *sock, int how); +int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb); +int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, + int __user *optlen, unsigned len); +int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid); +int security_sk_alloc(struct sock *sk, int family, gfp_t priority); +void security_sk_free(struct sock *sk); +void security_sk_clone(const struct sock *sk, struct sock *newsk); +void security_sk_classify_flow(struct sock *sk, struct flowi *fl); +void security_req_classify_flow(const struct request_sock *req, struct flowi *fl); +void security_sock_graft(struct sock*sk, struct socket *parent); +int security_inet_conn_request(struct sock *sk, + struct sk_buff *skb, struct request_sock *req); +void security_inet_csk_clone(struct sock *newsk, + const struct request_sock *req); +void security_inet_conn_established(struct sock *sk, + struct sk_buff *skb); -static inline int security_unix_may_send(struct socket * sock, - struct socket * other) -{ - return security_ops->unix_may_send(sock, other); -} - -static inline int security_socket_create (int family, int type, - int protocol, int kern) -{ - return security_ops->socket_create(family, type, protocol, kern); -} - -static inline int security_socket_post_create(struct socket * sock, - int family, - int type, - int protocol, int kern) -{ - return security_ops->socket_post_create(sock, family, type, - protocol, kern); -} - -static inline int security_socket_bind(struct socket * sock, - struct sockaddr * address, - int addrlen) -{ - return security_ops->socket_bind(sock, address, addrlen); -} - -static inline int security_socket_connect(struct socket * sock, - struct sockaddr * address, - int addrlen) -{ - return security_ops->socket_connect(sock, address, addrlen); -} - -static inline int security_socket_listen(struct socket * sock, int backlog) -{ - return security_ops->socket_listen(sock, backlog); -} - -static inline int security_socket_accept(struct socket * sock, - struct socket * newsock) -{ - return security_ops->socket_accept(sock, newsock); -} - -static inline void security_socket_post_accept(struct socket * sock, - struct socket * newsock) -{ - security_ops->socket_post_accept(sock, newsock); -} - -static inline int security_socket_sendmsg(struct socket * sock, - struct msghdr * msg, int size) -{ - return security_ops->socket_sendmsg(sock, msg, size); -} - -static inline int security_socket_recvmsg(struct socket * sock, - struct msghdr * msg, int size, - int flags) -{ - return security_ops->socket_recvmsg(sock, msg, size, flags); -} - -static inline int security_socket_getsockname(struct socket * sock) -{ - return security_ops->socket_getsockname(sock); -} - -static inline int security_socket_getpeername(struct socket * sock) -{ - return security_ops->socket_getpeername(sock); -} - -static inline int security_socket_getsockopt(struct socket * sock, - int level, int optname) -{ - return security_ops->socket_getsockopt(sock, level, optname); -} - -static inline int security_socket_setsockopt(struct socket * sock, - int level, int optname) -{ - return security_ops->socket_setsockopt(sock, level, optname); -} - -static inline int security_socket_shutdown(struct socket * sock, int how) -{ - return security_ops->socket_shutdown(sock, how); -} - -static inline int security_sock_rcv_skb (struct sock * sk, - struct sk_buff * skb) -{ - return security_ops->socket_sock_rcv_skb (sk, skb); -} - -static inline int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) -{ - return security_ops->socket_getpeersec_stream(sock, optval, optlen, len); -} - -static inline int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) -{ - return security_ops->socket_getpeersec_dgram(sock, skb, secid); -} - -static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority) -{ - return security_ops->sk_alloc_security(sk, family, priority); -} - -static inline void security_sk_free(struct sock *sk) -{ - return security_ops->sk_free_security(sk); -} - -static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) -{ - return security_ops->sk_clone_security(sk, newsk); -} - -static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl) -{ - security_ops->sk_getsecid(sk, &fl->secid); -} - -static inline void security_req_classify_flow(const struct request_sock *req, struct flowi *fl) -{ - security_ops->req_classify_flow(req, fl); -} - -static inline void security_sock_graft(struct sock* sk, struct socket *parent) -{ - security_ops->sock_graft(sk, parent); -} - -static inline int security_inet_conn_request(struct sock *sk, - struct sk_buff *skb, struct request_sock *req) -{ - return security_ops->inet_conn_request(sk, skb, req); -} - -static inline void security_inet_csk_clone(struct sock *newsk, - const struct request_sock *req) -{ - security_ops->inet_csk_clone(newsk, req); -} - -static inline void security_inet_conn_established(struct sock *sk, - struct sk_buff *skb) -{ - security_ops->inet_conn_established(sk, skb); -} #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct socket * sock, struct socket * other, @@ -3137,77 +2480,24 @@ static inline void security_inet_conn_established(struct sock *sk, #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) -{ - return security_ops->xfrm_policy_alloc_security(xp, sec_ctx); -} -static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) -{ - return security_ops->xfrm_policy_clone_security(old, new); -} - -static inline void security_xfrm_policy_free(struct xfrm_policy *xp) -{ - security_ops->xfrm_policy_free_security(xp); -} - -static inline int security_xfrm_policy_delete(struct xfrm_policy *xp) -{ - return security_ops->xfrm_policy_delete_security(xp); -} +int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx); +int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new); +void security_xfrm_policy_free(struct xfrm_policy *xp); +int security_xfrm_policy_delete(struct xfrm_policy *xp); +int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx); +int security_xfrm_state_alloc_acquire(struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, u32 secid); +int security_xfrm_state_delete(struct xfrm_state *x); +void security_xfrm_state_free(struct xfrm_state *x); +int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir); +int security_xfrm_state_pol_flow_match(struct xfrm_state *x, + struct xfrm_policy *xp, struct flowi *fl); +int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid); +void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl); -static inline int security_xfrm_state_alloc(struct xfrm_state *x, - struct xfrm_user_sec_ctx *sec_ctx) -{ - return security_ops->xfrm_state_alloc_security(x, sec_ctx, 0); -} - -static inline int security_xfrm_state_alloc_acquire(struct xfrm_state *x, - struct xfrm_sec_ctx *polsec, u32 secid) -{ - if (!polsec) - return 0; - /* - * We want the context to be taken from secid which is usually - * from the sock. - */ - return security_ops->xfrm_state_alloc_security(x, NULL, secid); -} - -static inline int security_xfrm_state_delete(struct xfrm_state *x) -{ - return security_ops->xfrm_state_delete_security(x); -} - -static inline void security_xfrm_state_free(struct xfrm_state *x) -{ - security_ops->xfrm_state_free_security(x); -} - -static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir) -{ - return security_ops->xfrm_policy_lookup(xp, fl_secid, dir); -} - -static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl) -{ - return security_ops->xfrm_state_pol_flow_match(x, xp, fl); -} - -static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) -{ - return security_ops->xfrm_decode_session(skb, secid, 1); -} - -static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl) -{ - int rc = security_ops->xfrm_decode_session(skb, &fl->secid, 0); - - BUG_ON(rc); -} #else /* CONFIG_SECURITY_NETWORK_XFRM */ + static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) { return 0; @@ -3272,24 +2562,11 @@ static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi #ifdef CONFIG_KEYS #ifdef CONFIG_SECURITY -static inline int security_key_alloc(struct key *key, - struct task_struct *tsk, - unsigned long flags) -{ - return security_ops->key_alloc(key, tsk, flags); -} - -static inline void security_key_free(struct key *key) -{ - security_ops->key_free(key); -} -static inline int security_key_permission(key_ref_t key_ref, - struct task_struct *context, - key_perm_t perm) -{ - return security_ops->key_permission(key_ref, context, perm); -} +int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long flags); +void security_key_free(struct key *key); +int security_key_permission(key_ref_t key_ref, + struct task_struct *context, key_perm_t perm); #else diff --git a/include/linux/selection.h b/include/linux/selection.h index f945786..8cdaa11 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -13,6 +13,7 @@ struct tty_struct; extern struct vc_data *sel_cons; +struct tty_struct; extern void clear_selection(void); extern int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *tty); diff --git a/include/linux/sem.h b/include/linux/sem.h index 9aaffb0..c8eaad9 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -90,7 +90,6 @@ struct sem { /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - int sem_id; time_t sem_otime; /* last semop time */ time_t sem_ctime; /* last change time */ struct sem *sem_base; /* ptr to first semaphore in array */ diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 8bf1e05..ebbc02b 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -18,7 +18,7 @@ struct seq_file { size_t from; size_t count; loff_t index; - loff_t version; + u64 version; struct mutex lock; const struct seq_operations *op; void *private; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 09d17b0..4db7724 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -291,7 +291,8 @@ struct uart_port { resource_size_t mapbase; /* for ioremap */ struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ - unsigned char unused[3]; + unsigned char suspended; + unsigned char unused[2]; void *private_data; /* generic platform data pointer */ }; diff --git a/include/linux/shm.h b/include/linux/shm.h index ad2e3af..eeaed92 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,9 @@ #define SHMALL (SHMMAX/PAGE_SIZE*(SHMMNI/16)) /* max shm system wide (pages) */ #define SHMSEG SHMMNI /* max shared segs per process */ +#ifdef __KERNEL__ #include <asm/shmparam.h> +#endif /* Obsolete, used only for backwards compatibility and libc5 compiles */ struct shmid_ds { @@ -77,7 +79,6 @@ struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; struct file * shm_file; - int id; unsigned long shm_nattch; unsigned long shm_segsz; time_t shm_atim; diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index 4c9ff09..86f9b1e 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -10,22 +10,22 @@ struct signalfd_siginfo { - __u32 signo; - __s32 err; - __s32 code; - __u32 pid; - __u32 uid; - __s32 fd; - __u32 tid; - __u32 band; - __u32 overrun; - __u32 trapno; - __s32 status; - __s32 svint; - __u64 svptr; - __u64 utime; - __u64 stime; - __u64 addr; + __u32 ssi_signo; + __s32 ssi_errno; + __s32 ssi_code; + __u32 ssi_pid; + __u32 ssi_uid; + __s32 ssi_fd; + __u32 ssi_tid; + __u32 ssi_band; + __u32 ssi_overrun; + __u32 ssi_trapno; + __s32 ssi_status; + __s32 ssi_int; + __u64 ssi_ptr; + __u64 ssi_utime; + __u64 ssi_stime; + __u64 ssi_addr; /* * Pad strcture to 128 bytes. Remember to update the diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a656cec..fd4e12f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -41,8 +41,7 @@ #define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \ ~(SMP_CACHE_BYTES - 1)) #define SKB_WITH_OVERHEAD(X) \ - (((X) - sizeof(struct skb_shared_info)) & \ - ~(SMP_CACHE_BYTES - 1)) + ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) @@ -301,8 +300,9 @@ struct sk_buff { #endif int iif; +#ifdef CONFIG_NETDEVICES_MULTIQUEUE __u16 queue_mapping; - +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT @@ -357,6 +357,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, } extern void kfree_skbmem(struct sk_buff *skb); +extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); extern struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); extern struct sk_buff *skb_copy(const struct sk_buff *skb, @@ -1769,6 +1770,15 @@ static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) #endif } +static inline u16 skb_get_queue_mapping(struct sk_buff *skb) +{ +#ifdef CONFIG_NETDEVICES_MULTIQUEUE + return skb->queue_mapping; +#else + return 0; +#endif +} + static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_NETDEVICES_MULTIQUEUE @@ -1781,6 +1791,11 @@ static inline int skb_is_gso(const struct sk_buff *skb) return skb_shinfo(skb)->gso_size; } +static inline int skb_is_gso_v6(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; +} + static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ diff --git a/include/linux/slab.h b/include/linux/slab.h index d859354..f3a8eec 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -24,12 +24,14 @@ #define SLAB_HWCACHE_ALIGN 0x00002000UL /* Align objs on cache lines */ #define SLAB_CACHE_DMA 0x00004000UL /* Use GFP_DMA memory */ #define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */ -#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ #define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */ #define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */ #define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */ #define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */ +/* The following flags affect the page allocator grouping pages by mobility */ +#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ +#define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -51,7 +53,7 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, - void (*)(void *, struct kmem_cache *, unsigned long)); + void (*)(struct kmem_cache *, void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 7496207..40801e7 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -11,6 +11,14 @@ #include <linux/workqueue.h> #include <linux/kobject.h> +struct kmem_cache_cpu { + void **freelist; + struct page *page; + int node; + unsigned int offset; + unsigned int objsize; +}; + struct kmem_cache_node { spinlock_t list_lock; /* Protect partial list and nr_partial */ unsigned long nr_partial; @@ -41,7 +49,7 @@ struct kmem_cache { /* Allocation and freeing of slabs */ int objects; /* Number of objects in slab */ int refcount; /* Refcount for slab cache destroy */ - void (*ctor)(void *, struct kmem_cache *, unsigned long); + void (*ctor)(struct kmem_cache *, void *); int inuse; /* Offset to metadata */ int align; /* Alignment */ const char *name; /* Name (only for display!) */ @@ -54,7 +62,11 @@ struct kmem_cache { int defrag_ratio; struct kmem_cache_node *node[MAX_NUMNODES]; #endif - struct page *cpu_slab[NR_CPUS]; +#ifdef CONFIG_SMP + struct kmem_cache_cpu *cpu_slab[NR_CPUS]; +#else + struct kmem_cache_cpu cpu_slab; +#endif }; /* @@ -72,7 +84,7 @@ struct kmem_cache { * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache kmalloc_caches[PAGE_SHIFT]; /* * Sorry that the following has to be that ugly but some versions of GCC @@ -83,9 +95,6 @@ static __always_inline int kmalloc_index(size_t size) if (!size) return 0; - if (size > KMALLOC_MAX_SIZE) - return -1; - if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; @@ -102,6 +111,10 @@ static __always_inline int kmalloc_index(size_t size) if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; +/* + * The following is only needed to support architectures with a larger page + * size than 4k. + */ if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; @@ -109,13 +122,9 @@ static __always_inline int kmalloc_index(size_t size) if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; - if (size <= 512 * 1024) return 19; + if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; - if (size <= 4 * 1024 * 1024) return 22; - if (size <= 8 * 1024 * 1024) return 23; - if (size <= 16 * 1024 * 1024) return 24; - if (size <= 32 * 1024 * 1024) return 25; return -1; /* @@ -140,19 +149,6 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size) if (index == 0) return NULL; - /* - * This function only gets expanded if __builtin_constant_p(size), so - * testing it here shouldn't be needed. But some versions of gcc need - * help. - */ - if (__builtin_constant_p(size) && index < 0) { - /* - * Generate a link failure. Would be great if we could - * do something to stop the compile here. - */ - extern void __kmalloc_size_too_large(void); - __kmalloc_size_too_large(); - } return &kmalloc_caches[index]; } @@ -168,15 +164,21 @@ void *__kmalloc(size_t size, gfp_t flags); static __always_inline void *kmalloc(size_t size, gfp_t flags) { - if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (__builtin_constant_p(size)) { + if (size > PAGE_SIZE / 2) + return (void *)__get_free_pages(flags | __GFP_COMP, + get_order(size)); - if (!s) - return ZERO_SIZE_PTR; + if (!(flags & SLUB_DMA)) { + struct kmem_cache *s = kmalloc_slab(size); - return kmem_cache_alloc(s, flags); - } else - return __kmalloc(size, flags); + if (!s) + return ZERO_SIZE_PTR; + + return kmem_cache_alloc(s, flags); + } + } + return __kmalloc(size, flags); } #ifdef CONFIG_NUMA @@ -185,15 +187,16 @@ void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { - if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (__builtin_constant_p(size) && + size <= PAGE_SIZE / 2 && !(flags & SLUB_DMA)) { + struct kmem_cache *s = kmalloc_slab(size); if (!s) return ZERO_SIZE_PTR; return kmem_cache_alloc_node(s, flags, node); - } else - return __kmalloc_node(size, flags, node); + } + return __kmalloc_node(size, flags, node); } #endif diff --git a/include/linux/sm501-regs.h b/include/linux/sm501-regs.h index 014e73b..df7620d 100644 --- a/include/linux/sm501-regs.h +++ b/include/linux/sm501-regs.h @@ -15,6 +15,24 @@ /* config 1 */ #define SM501_SYSTEM_CONTROL (0x000000) + +#define SM501_SYSCTRL_PANEL_TRISTATE (1<<0) +#define SM501_SYSCTRL_MEM_TRISTATE (1<<1) +#define SM501_SYSCTRL_CRT_TRISTATE (1<<2) + +#define SM501_SYSCTRL_PCI_SLAVE_BURST_MASK (3<<4) +#define SM501_SYSCTRL_PCI_SLAVE_BURST_1 (0<<4) +#define SM501_SYSCTRL_PCI_SLAVE_BURST_2 (1<<4) +#define SM501_SYSCTRL_PCI_SLAVE_BURST_4 (2<<4) +#define SM501_SYSCTRL_PCI_SLAVE_BURST_8 (3<<4) + +#define SM501_SYSCTRL_PCI_CLOCK_RUN_EN (1<<6) +#define SM501_SYSCTRL_PCI_RETRY_DISABLE (1<<7) +#define SM501_SYSCTRL_PCI_SUBSYS_LOCK (1<<11) +#define SM501_SYSCTRL_PCI_BURST_READ_EN (1<<15) + +/* miscellaneous control */ + #define SM501_MISC_CONTROL (0x000004) #define SM501_MISC_BUS_SH (0x0) diff --git a/include/linux/socket.h b/include/linux/socket.h index f852e1a..c22ef1c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -291,6 +291,7 @@ struct ucred { #define SOL_TIPC 271 #define SOL_RXRPC 272 #define SOL_PPPOL2TP 273 +#define SOL_BLUETOOTH 274 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/spi/at73c213.h b/include/linux/spi/at73c213.h new file mode 100644 index 0000000..0f20a70e --- /dev/null +++ b/include/linux/spi/at73c213.h @@ -0,0 +1,25 @@ +/* + * Board-specific data used to set up AT73c213 audio DAC driver. + */ + +#ifndef __LINUX_SPI_AT73C213_H +#define __LINUX_SPI_AT73C213_H + +/** + * at73c213_board_info - how the external DAC is wired to the device. + * + * @ssc_id: SSC platform_driver id the DAC shall use to stream the audio. + * @dac_clk: the external clock used to provide master clock to the DAC. + * @shortname: a short discription for the DAC, seen by userspace tools. + * + * This struct contains the configuration of the hardware connection to the + * external DAC. The DAC needs a master clock and a I2S audio stream. It also + * provides a name which is used to identify it in userspace tools. + */ +struct at73c213_board_info { + int ssc_id; + struct clk *dac_clk; + char shortname[32]; +}; + +#endif /* __LINUX_SPI_AT73C213_H */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 002a3cd..387e428 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -195,7 +195,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) /** * struct spi_master - interface to SPI master controller - * @cdev: class interface to this driver + * @dev: device interface to this driver * @bus_num: board-specific (and often SOC-specific) identifier for a * given SPI controller. * @num_chipselect: chipselects are used to distinguish individual @@ -222,7 +222,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * message's completion function when the transaction completes. */ struct spi_master { - struct class_device cdev; + struct device dev; /* other than negative (== assign one dynamically), bus_num is fully * board-specific. usually that simplifies to being SOC-specific. @@ -268,17 +268,17 @@ struct spi_master { static inline void *spi_master_get_devdata(struct spi_master *master) { - return class_get_devdata(&master->cdev); + return dev_get_drvdata(&master->dev); } static inline void spi_master_set_devdata(struct spi_master *master, void *data) { - class_set_devdata(&master->cdev, data); + dev_set_drvdata(&master->dev, data); } static inline struct spi_master *spi_master_get(struct spi_master *master) { - if (!master || !class_device_get(&master->cdev)) + if (!master || !get_device(&master->dev)) return NULL; return master; } @@ -286,7 +286,7 @@ static inline struct spi_master *spi_master_get(struct spi_master *master) static inline void spi_master_put(struct spi_master *master) { if (master) - class_device_put(&master->cdev); + put_device(&master->dev); } diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 3699dff..bd7a6b0 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -136,16 +136,6 @@ sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); -#define cache_for_each(pos, detail, index, member) \ - for (({read_lock(&(detail)->hash_lock); index = (detail)->hash_size;}) ; \ - ({if (index==0)read_unlock(&(detail)->hash_lock); index--;}); \ - ) \ - for (pos = container_of((detail)->hash_table[index], typeof(*pos), member); \ - &pos->member; \ - pos = container_of(pos->member.next, typeof(*pos), member)) - - - extern void cache_clean_deferred(void *owner); static inline struct cache_head *cache_get(struct cache_head *h) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index c0d9d14..d9d5c5a 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -117,7 +117,7 @@ struct rpc_create_args { struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, - struct rpc_program *, int); + struct rpc_program *, u32); struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 3912cf1..3347c72 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -88,6 +88,11 @@ enum { CTL_SLOTTABLE_TCP, CTL_MIN_RESVPORT, CTL_MAX_RESVPORT, + CTL_SLOTTABLE_RDMA, + CTL_RDMA_MAXINLINEREAD, + CTL_RDMA_MAXINLINEWRITE, + CTL_RDMA_WRITEPADDING, + CTL_RDMA_MEMREG, }; #endif /* _LINUX_SUNRPC_DEBUG_H_ */ diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 784d4c3..c4beb57 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -138,6 +138,19 @@ typedef __be32 rpc_fraghdr; #define RPC_MAX_HEADER_WITH_AUTH \ (RPC_CALLHDRSIZE + 2*(2+RPC_MAX_AUTH_SIZE/4)) +/* + * RFC1833/RFC3530 rpcbind (v3+) well-known netid's. + */ +#define RPCBIND_NETID_UDP "udp" +#define RPCBIND_NETID_TCP "tcp" +#define RPCBIND_NETID_UDP6 "udp6" +#define RPCBIND_NETID_TCP6 "tcp6" + +/* + * Note that RFC 1833 does not put any size restrictions on the + * netid string, but all currently defined netid's fit in 4 bytes. + */ +#define RPCBIND_MAXNETIDLEN (4u) #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h new file mode 100644 index 0000000..0013a0d --- /dev/null +++ b/include/linux/sunrpc/rpc_rdma.h @@ -0,0 +1,116 @@ +/* + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the BSD-type + * license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials provided + * with the distribution. + * + * Neither the name of the Network Appliance, Inc. nor the names of + * its contributors may be used to endorse or promote products + * derived from this software without specific prior written + * permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_SUNRPC_RPC_RDMA_H +#define _LINUX_SUNRPC_RPC_RDMA_H + +struct rpcrdma_segment { + uint32_t rs_handle; /* Registered memory handle */ + uint32_t rs_length; /* Length of the chunk in bytes */ + uint64_t rs_offset; /* Chunk virtual address or offset */ +}; + +/* + * read chunk(s), encoded as a linked list. + */ +struct rpcrdma_read_chunk { + uint32_t rc_discrim; /* 1 indicates presence */ + uint32_t rc_position; /* Position in XDR stream */ + struct rpcrdma_segment rc_target; +}; + +/* + * write chunk, and reply chunk. + */ +struct rpcrdma_write_chunk { + struct rpcrdma_segment wc_target; +}; + +/* + * write chunk(s), encoded as a counted array. + */ +struct rpcrdma_write_array { + uint32_t wc_discrim; /* 1 indicates presence */ + uint32_t wc_nchunks; /* Array count */ + struct rpcrdma_write_chunk wc_array[0]; +}; + +struct rpcrdma_msg { + uint32_t rm_xid; /* Mirrors the RPC header xid */ + uint32_t rm_vers; /* Version of this protocol */ + uint32_t rm_credit; /* Buffers requested/granted */ + uint32_t rm_type; /* Type of message (enum rpcrdma_proc) */ + union { + + struct { /* no chunks */ + uint32_t rm_empty[3]; /* 3 empty chunk lists */ + } rm_nochunks; + + struct { /* no chunks and padded */ + uint32_t rm_align; /* Padding alignment */ + uint32_t rm_thresh; /* Padding threshold */ + uint32_t rm_pempty[3]; /* 3 empty chunk lists */ + } rm_padded; + + uint32_t rm_chunks[0]; /* read, write and reply chunks */ + + } rm_body; +}; + +#define RPCRDMA_HDRLEN_MIN 28 + +enum rpcrdma_errcode { + ERR_VERS = 1, + ERR_CHUNK = 2 +}; + +struct rpcrdma_err_vers { + uint32_t rdma_vers_low; /* Version range supported by peer */ + uint32_t rdma_vers_high; +}; + +enum rpcrdma_proc { + RDMA_MSG = 0, /* An RPC call or reply msg */ + RDMA_NOMSG = 1, /* An RPC call or reply msg - separate body */ + RDMA_MSGP = 2, /* An RPC call or reply msg with padding */ + RDMA_DONE = 3, /* Client signals reply completion */ + RDMA_ERROR = 4 /* An RPC RDMA encoding error */ +}; + +#endif /* _LINUX_SUNRPC_RPC_RDMA_H */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index c6b53d1..0751c94 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -70,7 +70,10 @@ struct xdr_buf { struct page ** pages; /* Array of contiguous pages */ unsigned int page_base, /* Start of page data */ - page_len; /* Length of page data */ + page_len, /* Length of page data */ + flags; /* Flags for data disposition */ +#define XDRBUF_READ 0x01 /* target of file read */ +#define XDRBUF_WRITE 0x02 /* source of file write */ unsigned int buflen, /* Total length of storage buffer */ len; /* Length of XDR encoded message */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d11cedd..30b17b3 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -19,25 +19,11 @@ #ifdef __KERNEL__ -extern unsigned int xprt_udp_slot_table_entries; -extern unsigned int xprt_tcp_slot_table_entries; - #define RPC_MIN_SLOT_TABLE (2U) #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE (128U) /* - * Parameters for choosing a free port - */ -extern unsigned int xprt_min_resvport; -extern unsigned int xprt_max_resvport; - -#define RPC_MIN_RESVPORT (1U) -#define RPC_MAX_RESVPORT (65535U) -#define RPC_DEF_MIN_RESVPORT (665U) -#define RPC_DEF_MAX_RESVPORT (1023U) - -/* * This describes a timeout strategy */ struct rpc_timeout { @@ -53,6 +39,10 @@ enum rpc_display_format_t { RPC_DISPLAY_PORT, RPC_DISPLAY_PROTO, RPC_DISPLAY_ALL, + RPC_DISPLAY_HEX_ADDR, + RPC_DISPLAY_HEX_PORT, + RPC_DISPLAY_UNIVERSAL_ADDR, + RPC_DISPLAY_NETID, RPC_DISPLAY_MAX, }; @@ -196,14 +186,22 @@ struct rpc_xprt { char * address_strings[RPC_DISPLAY_MAX]; }; -struct rpc_xprtsock_create { - int proto; /* IPPROTO_UDP or IPPROTO_TCP */ +struct xprt_create { + int ident; /* XPRT_TRANSPORT identifier */ struct sockaddr * srcaddr; /* optional local address */ struct sockaddr * dstaddr; /* remote peer address */ size_t addrlen; struct rpc_timeout * timeout; /* optional timeout parameters */ }; +struct xprt_class { + struct list_head list; + int ident; /* XPRT_TRANSPORT identifier */ + struct rpc_xprt * (*setup)(struct xprt_create *); + struct module *owner; + char name[32]; +}; + /* * Transport operations used by ULPs */ @@ -212,7 +210,7 @@ void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long /* * Generic internal transport functions */ -struct rpc_xprt * xprt_create_transport(struct rpc_xprtsock_create *args); +struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_task *task); @@ -235,6 +233,8 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 * /* * Transport switch helper functions */ +int xprt_register_transport(struct xprt_class *type); +int xprt_unregister_transport(struct xprt_class *type); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); @@ -248,14 +248,6 @@ void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect(struct rpc_xprt *xprt); /* - * Socket transport setup operations - */ -struct rpc_xprt * xs_setup_udp(struct rpc_xprtsock_create *args); -struct rpc_xprt * xs_setup_tcp(struct rpc_xprtsock_create *args); -int init_socket_xprt(void); -void cleanup_socket_xprt(void); - -/* * Reserved bit positions in xprt->state */ #define XPRT_LOCKED (0) diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h new file mode 100644 index 0000000..4de56b1 --- /dev/null +++ b/include/linux/sunrpc/xprtrdma.h @@ -0,0 +1,85 @@ +/* + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the BSD-type + * license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials provided + * with the distribution. + * + * Neither the name of the Network Appliance, Inc. nor the names of + * its contributors may be used to endorse or promote products + * derived from this software without specific prior written + * permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_SUNRPC_XPRTRDMA_H +#define _LINUX_SUNRPC_XPRTRDMA_H + +/* + * RPC transport identifier for RDMA + */ +#define XPRT_TRANSPORT_RDMA 256 + +/* + * rpcbind (v3+) RDMA netid. + */ +#define RPCBIND_NETID_RDMA "rdma" + +/* + * Constants. Max RPC/NFS header is big enough to account for + * additional marshaling buffers passed down by Linux client. + * + * RDMA header is currently fixed max size, and is big enough for a + * fully-chunked NFS message (read chunks are the largest). Note only + * a single chunk type per message is supported currently. + */ +#define RPCRDMA_MIN_SLOT_TABLE (2U) +#define RPCRDMA_DEF_SLOT_TABLE (32U) +#define RPCRDMA_MAX_SLOT_TABLE (256U) + +#define RPCRDMA_DEF_INLINE (1024) /* default inline max */ + +#define RPCRDMA_INLINE_PAD_THRESH (512)/* payload threshold to pad (bytes) */ + +#define RDMA_RESOLVE_TIMEOUT (5*HZ) /* TBD 5 seconds */ +#define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */ + +/* memory registration strategies */ +#define RPCRDMA_PERSISTENT_REGISTRATION (1) + +enum rpcrdma_memreg { + RPCRDMA_BOUNCEBUFFERS = 0, + RPCRDMA_REGISTER, + RPCRDMA_MEMWINDOWS, + RPCRDMA_MEMWINDOWS_ASYNC, + RPCRDMA_MTHCAFMR, + RPCRDMA_ALLPHYSICAL, + RPCRDMA_LAST +}; + +#endif /* _LINUX_SUNRPC_XPRTRDMA_H */ diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h new file mode 100644 index 0000000..2c6c2c2 --- /dev/null +++ b/include/linux/sunrpc/xprtsock.h @@ -0,0 +1,51 @@ +/* + * linux/include/linux/sunrpc/xprtsock.h + * + * Declarations for the RPC transport socket provider. + */ + +#ifndef _LINUX_SUNRPC_XPRTSOCK_H +#define _LINUX_SUNRPC_XPRTSOCK_H + +#ifdef __KERNEL__ + +/* + * Socket transport setup operations + */ +struct rpc_xprt *xs_setup_udp(struct xprt_create *args); +struct rpc_xprt *xs_setup_tcp(struct xprt_create *args); + +int init_socket_xprt(void); +void cleanup_socket_xprt(void); + +/* + * RPC transport identifiers for UDP, TCP + * + * To preserve compatibility with the historical use of raw IP protocol + * id's for transport selection, these are specified with the previous + * values. No such restriction exists for new transports, except that + * they may not collide with these values (17 and 6, respectively). + */ +#define XPRT_TRANSPORT_UDP IPPROTO_UDP +#define XPRT_TRANSPORT_TCP IPPROTO_TCP + +/* + * RPC slot table sizes for UDP, TCP transports + */ +extern unsigned int xprt_udp_slot_table_entries; +extern unsigned int xprt_tcp_slot_table_entries; + +/* + * Parameters for choosing a free port + */ +extern unsigned int xprt_min_resvport; +extern unsigned int xprt_max_resvport; + +#define RPC_MIN_RESVPORT (1U) +#define RPC_MAX_RESVPORT (65535U) +#define RPC_DEF_MIN_RESVPORT (665U) +#define RPC_DEF_MAX_RESVPORT (1023U) + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 388cace..4360e08 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -1,5 +1,5 @@ -#ifndef _LINUX_SWSUSP_H -#define _LINUX_SWSUSP_H +#ifndef _LINUX_SUSPEND_H +#define _LINUX_SUSPEND_H #if defined(CONFIG_X86) || defined(CONFIG_FRV) || defined(CONFIG_PPC32) || defined(CONFIG_PPC64) #include <asm/suspend.h> @@ -9,6 +9,108 @@ #include <linux/init.h> #include <linux/pm.h> #include <linux/mm.h> +#include <asm/errno.h> + +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) +extern int pm_prepare_console(void); +extern void pm_restore_console(void); +#else +static inline int pm_prepare_console(void) { return 0; } +static inline void pm_restore_console(void) {} +#endif + +typedef int __bitwise suspend_state_t; + +#define PM_SUSPEND_ON ((__force suspend_state_t) 0) +#define PM_SUSPEND_STANDBY ((__force suspend_state_t) 1) +#define PM_SUSPEND_MEM ((__force suspend_state_t) 3) +#define PM_SUSPEND_MAX ((__force suspend_state_t) 4) + +/** + * struct platform_suspend_ops - Callbacks for managing platform dependent + * system sleep states. + * + * @valid: Callback to determine if given system sleep state is supported by + * the platform. + * Valid (ie. supported) states are advertised in /sys/power/state. Note + * that it still may be impossible to enter given system sleep state if the + * conditions aren't right. + * There is the %suspend_valid_only_mem function available that can be + * assigned to this if the platform only supports mem sleep. + * + * @set_target: Tell the platform which system sleep state is going to be + * entered. + * @set_target() is executed right prior to suspending devices. The + * information conveyed to the platform code by @set_target() should be + * disregarded by the platform as soon as @finish() is executed and if + * @prepare() fails. If @set_target() fails (ie. returns nonzero), + * @prepare(), @enter() and @finish() will not be called by the PM core. + * This callback is optional. However, if it is implemented, the argument + * passed to @enter() is meaningless and should be ignored. + * + * @prepare: Prepare the platform for entering the system sleep state indicated + * by @set_target(). + * @prepare() is called right after devices have been suspended (ie. the + * appropriate .suspend() method has been executed for each device) and + * before the nonboot CPUs are disabled (it is executed with IRQs enabled). + * This callback is optional. It returns 0 on success or a negative + * error code otherwise, in which case the system cannot enter the desired + * sleep state (@enter() and @finish() will not be called in that case). + * + * @enter: Enter the system sleep state indicated by @set_target() or + * represented by the argument if @set_target() is not implemented. + * This callback is mandatory. It returns 0 on success or a negative + * error code otherwise, in which case the system cannot enter the desired + * sleep state. + * + * @finish: Called when the system has just left a sleep state, right after + * the nonboot CPUs have been enabled and before devices are resumed (it is + * executed with IRQs enabled). + * This callback is optional, but should be implemented by the platforms + * that implement @prepare(). If implemented, it is always called after + * @enter() (even if @enter() fails). + */ +struct platform_suspend_ops { + int (*valid)(suspend_state_t state); + int (*set_target)(suspend_state_t state); + int (*prepare)(void); + int (*enter)(suspend_state_t state); + void (*finish)(void); +}; + +#ifdef CONFIG_SUSPEND +/** + * suspend_set_ops - set platform dependent suspend operations + * @ops: The new suspend operations to set. + */ +extern void suspend_set_ops(struct platform_suspend_ops *ops); +extern int suspend_valid_only_mem(suspend_state_t state); + +/** + * arch_suspend_disable_irqs - disable IRQs for suspend + * + * Disables IRQs (in the default case). This is a weak symbol in the common + * code and thus allows architectures to override it if more needs to be + * done. Not called for suspend to disk. + */ +extern void arch_suspend_disable_irqs(void); + +/** + * arch_suspend_enable_irqs - enable IRQs after suspend + * + * Enables IRQs (in the default case). This is a weak symbol in the common + * code and thus allows architectures to override it if more needs to be + * done. Not called for suspend to disk. + */ +extern void arch_suspend_enable_irqs(void); + +extern int pm_suspend(suspend_state_t state); +#else /* !CONFIG_SUSPEND */ +#define suspend_valid_only_mem NULL + +static inline void suspend_set_ops(struct platform_suspend_ops *ops) {} +static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } +#endif /* !CONFIG_SUSPEND */ /* struct pbe is used for creating lists of pages that should be restored * atomically during the resume from disk, because the page frames they have @@ -24,32 +126,57 @@ struct pbe { extern void drain_local_pages(void); extern void mark_free_pages(struct zone *zone); -#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) -extern int pm_prepare_console(void); -extern void pm_restore_console(void); -#else -static inline int pm_prepare_console(void) { return 0; } -static inline void pm_restore_console(void) {} -#endif - /** - * struct hibernation_ops - hibernation platform support + * struct platform_hibernation_ops - hibernation platform support * * The methods in this structure allow a platform to override the default * mechanism of shutting down the machine during a hibernation transition. * * All three methods must be assigned. * - * @prepare: prepare system for hibernation - * @enter: shut down system after state has been saved to disk - * @finish: finish/clean up after state has been reloaded - * @pre_restore: prepare system for the restoration from a hibernation image - * @restore_cleanup: clean up after a failing image restoration + * @start: Tell the platform driver that we're starting hibernation. + * Called right after shrinking memory and before freezing devices. + * + * @pre_snapshot: Prepare the platform for creating the hibernation image. + * Called right after devices have been frozen and before the nonboot + * CPUs are disabled (runs with IRQs on). + * + * @finish: Restore the previous state of the platform after the hibernation + * image has been created *or* put the platform into the normal operation + * mode after the hibernation (the same method is executed in both cases). + * Called right after the nonboot CPUs have been enabled and before + * thawing devices (runs with IRQs on). + * + * @prepare: Prepare the platform for entering the low power state. + * Called right after the hibernation image has been saved and before + * devices are prepared for entering the low power state. + * + * @enter: Put the system into the low power state after the hibernation image + * has been saved to disk. + * Called after the nonboot CPUs have been disabled and all of the low + * level devices have been shut down (runs with IRQs off). + * + * @leave: Perform the first stage of the cleanup after the system sleep state + * indicated by @set_target() has been left. + * Called right after the control has been passed from the boot kernel to + * the image kernel, before the nonboot CPUs are enabled and before devices + * are resumed. Executed with interrupts disabled. + * + * @pre_restore: Prepare system for the restoration from a hibernation image. + * Called right after devices have been frozen and before the nonboot + * CPUs are disabled (runs with IRQs on). + * + * @restore_cleanup: Clean up after a failing image restoration. + * Called right after the nonboot CPUs have been enabled and before + * thawing devices (runs with IRQs on). */ -struct hibernation_ops { +struct platform_hibernation_ops { + int (*start)(void); + int (*pre_snapshot)(void); + void (*finish)(void); int (*prepare)(void); int (*enter)(void); - void (*finish)(void); + void (*leave)(void); int (*pre_restore)(void); void (*restore_cleanup)(void); }; @@ -70,14 +197,14 @@ extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); extern unsigned long get_safe_page(gfp_t gfp_mask); -extern void hibernation_set_ops(struct hibernation_ops *ops); +extern void hibernation_set_ops(struct platform_hibernation_ops *ops); extern int hibernate(void); #else /* CONFIG_HIBERNATION */ static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} -static inline void hibernation_set_ops(struct hibernation_ops *ops) {} +static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } #endif /* CONFIG_HIBERNATION */ @@ -130,4 +257,4 @@ static inline void register_nosave_region_late(unsigned long b, unsigned long e) } #endif -#endif /* _LINUX_SWSUSP_H */ +#endif /* _LINUX_SUSPEND_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index edf681a..4f3838a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -158,11 +158,6 @@ struct swap_list_t { /* Swap 50% full? Release swapcache more aggressively.. */ #define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) -/* linux/mm/oom_kill.c */ -extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order); -extern int register_oom_notifier(struct notifier_block *nb); -extern int unregister_oom_notifier(struct notifier_block *nb); - /* linux/mm/memory.c */ extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct *); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 483050c..e99171f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -238,6 +238,7 @@ enum NET_LLC=18, NET_NETFILTER=19, NET_DCCP=20, + NET_IRDA=412, }; /* /proc/sys/kernel/random */ @@ -795,6 +796,25 @@ enum { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED = 5, }; +/* proc/sys/net/irda */ +enum { + NET_IRDA_DISCOVERY=1, + NET_IRDA_DEVNAME=2, + NET_IRDA_DEBUG=3, + NET_IRDA_FAST_POLL=4, + NET_IRDA_DISCOVERY_SLOTS=5, + NET_IRDA_DISCOVERY_TIMEOUT=6, + NET_IRDA_SLOT_TIMEOUT=7, + NET_IRDA_MAX_BAUD_RATE=8, + NET_IRDA_MIN_TX_TURN_TIME=9, + NET_IRDA_MAX_TX_DATA_SIZE=10, + NET_IRDA_MAX_TX_WINDOW=11, + NET_IRDA_MAX_NOREPLY_TIME=12, + NET_IRDA_WARN_NOREPLY_TIME=13, + NET_IRDA_LAP_KEEPALIVE_TIME=14, +}; + + /* CTL_FS names: */ enum { @@ -937,41 +957,42 @@ extern int sysctl_perm(struct ctl_table *table, int op); typedef struct ctl_table ctl_table; -typedef int ctl_handler (ctl_table *table, int __user *name, int nlen, +typedef int ctl_handler (struct ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); -typedef int proc_handler (ctl_table *ctl, int write, struct file * filp, +typedef int proc_handler (struct ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dostring(ctl_table *, int, struct file *, +extern int proc_dostring(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec(ctl_table *, int, struct file *, +extern int proc_dointvec(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec_bset(ctl_table *, int, struct file *, +extern int proc_dointvec_bset(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(ctl_table *, int, struct file *, +extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec_jiffies(ctl_table *, int, struct file *, +extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(ctl_table *, int, struct file *, +extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(ctl_table *, int, struct file *, +extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(ctl_table *, int, struct file *, +extern int proc_doulongvec_minmax(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -extern int proc_doulongvec_ms_jiffies_minmax(ctl_table *table, int, +extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, struct file *, void __user *, size_t *, loff_t *); extern int do_sysctl (int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); -extern int do_sysctl_strategy (ctl_table *table, +extern int do_sysctl_strategy (struct ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); +extern ctl_handler sysctl_data; extern ctl_handler sysctl_string; extern ctl_handler sysctl_intvec; extern ctl_handler sysctl_jiffies; @@ -980,7 +1001,7 @@ extern ctl_handler sysctl_ms_jiffies; /* * Register a set of sysctl names by calling register_sysctl_table - * with an initialised array of ctl_table's. An entry with zero + * with an initialised array of struct ctl_table's. An entry with zero * ctl_name and NULL procname terminates the table. table->de will be * set up by the registration and need not be initialised in advance. * @@ -1026,8 +1047,8 @@ struct ctl_table void *data; int maxlen; mode_t mode; - ctl_table *child; - ctl_table *parent; /* Automatically set */ + struct ctl_table *child; + struct ctl_table *parent; /* Automatically set */ proc_handler *proc_handler; /* Callback for text formatting */ ctl_handler *strategy; /* Callback function for all r/w */ void *extra1; @@ -1035,18 +1056,19 @@ struct ctl_table }; /* struct ctl_table_header is used to maintain dynamic lists of - ctl_table trees. */ + struct ctl_table trees. */ struct ctl_table_header { - ctl_table *ctl_table; + struct ctl_table *ctl_table; struct list_head ctl_entry; int used; struct completion *unregistering; }; -struct ctl_table_header * register_sysctl_table(ctl_table * table); +struct ctl_table_header *register_sysctl_table(struct ctl_table * table); void unregister_sysctl_table(struct ctl_table_header * table); +int sysctl_check_table(struct ctl_table *table); #else /* __KERNEL__ */ diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index dce1ed204..5d69c07 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 5 +#define TASKSTATS_VERSION 6 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -152,6 +152,11 @@ struct taskstats { __u64 nvcsw; /* voluntary_ctxt_switches */ __u64 nivcsw; /* nonvoluntary_ctxt_switches */ + + /* time accounting for SMT machines */ + __u64 ac_utimescaled; /* utime scaled on frequency etc */ + __u64 ac_stimescaled; /* stime scaled on frequency etc */ + __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c5b94c1..bac17c5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -315,7 +315,7 @@ struct tcp_sock { */ u32 snd_ssthresh; /* Slow start size threshold */ u32 snd_cwnd; /* Sending congestion window */ - u16 snd_cwnd_cnt; /* Linear increase counter */ + u32 snd_cwnd_cnt; /* Linear increase counter */ u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; diff --git a/include/linux/tick.h b/include/linux/tick.h index 9a7252e..f4a1395 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -40,6 +40,7 @@ enum tick_nohz_mode { * @idle_sleeps: Number of idle calls, where the sched tick was stopped * @idle_entrytime: Time when the idle call was entered * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @sleep_length: Duration of the current idle sleep */ struct tick_sched { struct hrtimer sched_timer; @@ -52,6 +53,7 @@ struct tick_sched { unsigned long idle_sleeps; ktime_t idle_entrytime; ktime_t idle_sleeptime; + ktime_t sleep_length; unsigned long last_jiffies; unsigned long next_jiffies; ktime_t idle_expires; @@ -100,10 +102,17 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } extern void tick_nohz_stop_sched_tick(void); extern void tick_nohz_restart_sched_tick(void); extern void tick_nohz_update_jiffies(void); +extern ktime_t tick_nohz_get_sleep_length(void); # else static inline void tick_nohz_stop_sched_tick(void) { } static inline void tick_nohz_restart_sched_tick(void) { } static inline void tick_nohz_update_jiffies(void) { } +static inline ktime_t tick_nohz_get_sleep_length(void) +{ + ktime_t len = { .tv64 = NSEC_PER_SEC/HZ }; + + return len; +} # endif /* !NO_HZ */ #endif diff --git a/include/linux/time.h b/include/linux/time.h index 6a5f503..b04136d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -92,7 +92,7 @@ static inline struct timespec timespec_sub(struct timespec lhs, extern struct timespec xtime; extern struct timespec wall_to_monotonic; -extern seqlock_t xtime_lock __attribute__((weak)); +extern seqlock_t xtime_lock; extern unsigned long read_persistent_clock(void); extern int update_persistent_clock(struct timespec now); diff --git a/include/linux/topology.h b/include/linux/topology.h index 525d437..47729f1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -159,15 +159,14 @@ .imbalance_pct = 125, \ .cache_nice_tries = 1, \ .busy_idx = 2, \ - .idle_idx = 0, \ - .newidle_idx = 0, \ + .idle_idx = 1, \ + .newidle_idx = 2, \ .wake_idx = 1, \ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | SD_WAKE_IDLE \ | BALANCE_FOR_PKG_POWER,\ .last_balance = jiffies, \ .balance_interval = 1, \ diff --git a/include/linux/tty.h b/include/linux/tty.h index 60478f6..56164d7 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -81,11 +81,6 @@ struct tty_bufhead { int memory_used; /* Buffer space used excluding free queue */ }; /* - * The pty uses char_buf and flag_buf as a contiguous buffer - */ -#define PTY_BUF_SIZE 4*TTY_FLIPBUF_SIZE - -/* * When a break, frame error, or parity error happens, these codes are * stuffed into the flags buffer. */ @@ -321,6 +316,9 @@ extern void tty_flip_buffer_push(struct tty_struct *tty); extern speed_t tty_get_baud_rate(struct tty_struct *tty); extern speed_t tty_termios_baud_rate(struct ktermios *termios); extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); +extern void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud); +extern void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, speed_t obaud); +extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); diff --git a/include/linux/types.h b/include/linux/types.h index 0351bf2..4f0dad2 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -3,12 +3,9 @@ #ifdef __KERNEL__ -#define BITS_TO_LONGS(bits) \ - (((bits)+BITS_PER_LONG-1)/BITS_PER_LONG) #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] -#define BITS_PER_BYTE 8 #endif #include <linux/posix_types.h> diff --git a/include/linux/ufs_fs.h b/include/linux/ufs_fs.h index daeba22..10b854d 100644 --- a/include/linux/ufs_fs.h +++ b/include/linux/ufs_fs.h @@ -46,11 +46,6 @@ typedef __u32 __bitwise __fs32; typedef __u16 __bitwise __fs16; #endif -#ifdef __KERNEL__ -#include <linux/ufs_fs_i.h> -#include <linux/ufs_fs_sb.h> -#endif - #define UFS_BBLOCK 0 #define UFS_BBSIZE 8192 #define UFS_SBLOCK 8192 @@ -170,8 +165,9 @@ typedef __u16 __bitwise __fs16; #define UFS_ST_MASK 0x00000700 /* mask for the following */ #define UFS_ST_OLD 0x00000000 #define UFS_ST_44BSD 0x00000100 -#define UFS_ST_SUN 0x00000200 -#define UFS_ST_SUNx86 0x00000400 +#define UFS_ST_SUN 0x00000200 /* Solaris */ +#define UFS_ST_SUNOS 0x00000300 +#define UFS_ST_SUNx86 0x00000400 /* Solaris x86 */ /*cylinder group encoding */ #define UFS_CG_MASK 0x00003000 /* mask for the following */ #define UFS_CG_OLD 0x00000000 @@ -187,28 +183,6 @@ typedef __u16 __bitwise __fs16; #define UFS_42INODEFMT -1 #define UFS_44INODEFMT 2 -/* mount options */ -#define UFS_MOUNT_ONERROR 0x0000000F -#define UFS_MOUNT_ONERROR_PANIC 0x00000001 -#define UFS_MOUNT_ONERROR_LOCK 0x00000002 -#define UFS_MOUNT_ONERROR_UMOUNT 0x00000004 -#define UFS_MOUNT_ONERROR_REPAIR 0x00000008 - -#define UFS_MOUNT_UFSTYPE 0x0000FFF0 -#define UFS_MOUNT_UFSTYPE_OLD 0x00000010 -#define UFS_MOUNT_UFSTYPE_44BSD 0x00000020 -#define UFS_MOUNT_UFSTYPE_SUN 0x00000040 -#define UFS_MOUNT_UFSTYPE_NEXTSTEP 0x00000080 -#define UFS_MOUNT_UFSTYPE_NEXTSTEP_CD 0x00000100 -#define UFS_MOUNT_UFSTYPE_OPENSTEP 0x00000200 -#define UFS_MOUNT_UFSTYPE_SUNx86 0x00000400 -#define UFS_MOUNT_UFSTYPE_HP 0x00000800 -#define UFS_MOUNT_UFSTYPE_UFS2 0x00001000 - -#define ufs_clear_opt(o,opt) o &= ~UFS_MOUNT_##opt -#define ufs_set_opt(o,opt) o |= UFS_MOUNT_##opt -#define ufs_test_opt(o,opt) ((o) & UFS_MOUNT_##opt) - /* * MINFREE gives the minimum acceptable percentage of file system * blocks which may be free. If the freelist drops below this level @@ -223,19 +197,6 @@ typedef __u16 __bitwise __fs16; */ #define UFS_MINFREE 5 #define UFS_DEFAULTOPT UFS_OPTTIME - -/* - * Debug code - */ -#ifdef CONFIG_UFS_DEBUG -# define UFSD(f, a...) { \ - printk ("UFSD (%s, %d): %s:", \ - __FILE__, __LINE__, __FUNCTION__); \ - printk (f, ## a); \ - } -#else -# define UFSD(f, a...) /**/ -#endif /* * Turn file system block numbers into disk block addresses. @@ -374,7 +335,14 @@ struct ufs_csum_core { * struct ufs_super_block_(first,second,third) instead. */ struct ufs_super_block { - __fs32 fs_link; /* UNUSED */ + union { + struct { + __fs32 fs_link; /* UNUSED */ + } fs_42; + struct { + __fs32 fs_state; /* file system state flag */ + } fs_sun; + } fs_u0; __fs32 fs_rlink; /* UNUSED */ __fs32 fs_sblkno; /* addr of super-block in filesys */ __fs32 fs_cblkno; /* offset of cyl-block in filesys */ @@ -545,6 +513,15 @@ struct ufs_super_block { #define CG_MAGIC 0x090255 #define ufs_cg_chkmagic(sb, ucg) \ (fs32_to_cpu((sb), (ucg)->cg_magic) == CG_MAGIC) +/* + * Macros for access to old cylinder group array structures + */ +#define ufs_ocg_blktot(sb, ucg) fs32_to_cpu((sb), ((struct ufs_old_cylinder_group *)(ucg))->cg_btot) +#define ufs_ocg_blks(sb, ucg, cylno) fs32_to_cpu((sb), ((struct ufs_old_cylinder_group *)(ucg))->cg_b[cylno]) +#define ufs_ocg_inosused(sb, ucg) fs32_to_cpu((sb), ((struct ufs_old_cylinder_group *)(ucg))->cg_iused) +#define ufs_ocg_blksfree(sb, ucg) fs32_to_cpu((sb), ((struct ufs_old_cylinder_group *)(ucg))->cg_free) +#define ufs_ocg_chkmagic(sb, ucg) \ + (fs32_to_cpu((sb), ((struct ufs_old_cylinder_group *)(ucg))->cg_magic) == CG_MAGIC) /* * size of this structure is 172 B @@ -590,6 +567,28 @@ struct ufs_cylinder_group { /* actually longer */ }; +/* Historic Cylinder group info */ +struct ufs_old_cylinder_group { + __fs32 cg_link; /* linked list of cyl groups */ + __fs32 cg_rlink; /* for incore cyl groups */ + __fs32 cg_time; /* time last written */ + __fs32 cg_cgx; /* we are the cgx'th cylinder group */ + __fs16 cg_ncyl; /* number of cyl's this cg */ + __fs16 cg_niblk; /* number of inode blocks this cg */ + __fs32 cg_ndblk; /* number of data blocks this cg */ + struct ufs_csum cg_cs; /* cylinder summary information */ + __fs32 cg_rotor; /* position of last used block */ + __fs32 cg_frotor; /* position of last used frag */ + __fs32 cg_irotor; /* position of last used inode */ + __fs32 cg_frsum[8]; /* counts of available frags */ + __fs32 cg_btot[32]; /* block totals per cylinder */ + __fs16 cg_b[32][8]; /* positions of free blocks */ + __u8 cg_iused[256]; /* used inode map */ + __fs32 cg_magic; /* magic number */ + __u8 cg_free[1]; /* free block map */ +/* actually longer */ +}; + /* * structure of an on-disk inode */ @@ -796,7 +795,14 @@ struct ufs_sb_private_info { * ufs_super_block_third 356 */ struct ufs_super_block_first { - __fs32 fs_link; + union { + struct { + __fs32 fs_link; /* UNUSED */ + } fs_42; + struct { + __fs32 fs_state; /* file system state flag */ + } fs_sun; + } fs_u0; __fs32 fs_rlink; __fs32 fs_sblkno; __fs32 fs_cblkno; @@ -944,89 +950,4 @@ struct ufs_super_block_third { __u8 fs_space[1]; }; -#ifdef __KERNEL__ - -/* balloc.c */ -extern void ufs_free_fragments (struct inode *, u64, unsigned); -extern void ufs_free_blocks (struct inode *, u64, unsigned); -extern u64 ufs_new_fragments(struct inode *, void *, u64, u64, - unsigned, int *, struct page *); - -/* cylinder.c */ -extern struct ufs_cg_private_info * ufs_load_cylinder (struct super_block *, unsigned); -extern void ufs_put_cylinder (struct super_block *, unsigned); - -/* dir.c */ -extern const struct inode_operations ufs_dir_inode_operations; -extern int ufs_add_link (struct dentry *, struct inode *); -extern ino_t ufs_inode_by_name(struct inode *, struct dentry *); -extern int ufs_make_empty(struct inode *, struct inode *); -extern struct ufs_dir_entry *ufs_find_entry(struct inode *, struct dentry *, struct page **); -extern int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct page *); -extern int ufs_empty_dir (struct inode *); -extern struct ufs_dir_entry *ufs_dotdot(struct inode *, struct page **); -extern void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, - struct page *page, struct inode *inode); - -/* file.c */ -extern const struct inode_operations ufs_file_inode_operations; -extern const struct file_operations ufs_file_operations; - -extern const struct address_space_operations ufs_aops; - -/* ialloc.c */ -extern void ufs_free_inode (struct inode *inode); -extern struct inode * ufs_new_inode (struct inode *, int); - -/* inode.c */ -extern void ufs_read_inode (struct inode *); -extern void ufs_put_inode (struct inode *); -extern int ufs_write_inode (struct inode *, int); -extern int ufs_sync_inode (struct inode *); -extern void ufs_delete_inode (struct inode *); -extern struct buffer_head * ufs_bread (struct inode *, unsigned, int, int *); -extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create); - -/* namei.c */ -extern const struct file_operations ufs_dir_operations; - -/* super.c */ -extern void ufs_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ufs_error (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ufs_panic (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); - -/* symlink.c */ -extern const struct inode_operations ufs_fast_symlink_inode_operations; - -/* truncate.c */ -extern int ufs_truncate (struct inode *, loff_t); - -static inline struct ufs_sb_info *UFS_SB(struct super_block *sb) -{ - return sb->s_fs_info; -} - -static inline struct ufs_inode_info *UFS_I(struct inode *inode) -{ - return container_of(inode, struct ufs_inode_info, vfs_inode); -} - -/* - * Give cylinder group number for a file system block. - * Give cylinder group block number for a file system block. - */ -/* #define ufs_dtog(d) ((d) / uspi->s_fpg) */ -static inline u64 ufs_dtog(struct ufs_sb_private_info * uspi, u64 b) -{ - do_div(b, uspi->s_fpg); - return b; -} -/* #define ufs_dtogd(d) ((d) % uspi->s_fpg) */ -static inline u32 ufs_dtogd(struct ufs_sb_private_info * uspi, u64 b) -{ - return do_div(b, uspi->s_fpg); -} - -#endif /* __KERNEL__ */ - #endif /* __LINUX_UFS_FS_H */ diff --git a/include/linux/ufs_fs_i.h b/include/linux/ufs_fs_i.h deleted file mode 100644 index 6496caa..0000000 --- a/include/linux/ufs_fs_i.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * linux/include/linux/ufs_fs_i.h - * - * Copyright (C) 1996 - * Adrian Rodriguez (adrian@franklins-tower.rutgers.edu) - * Laboratory for Computer Science Research Computing Facility - * Rutgers, The State University of New Jersey - * - * NeXTstep support added on February 5th 1998 by - * Niels Kristian Bech Jensen <nkbj@image.dk>. - */ - -#ifndef _LINUX_UFS_FS_I_H -#define _LINUX_UFS_FS_I_H - -struct ufs_inode_info { - union { - __fs32 i_data[15]; - __u8 i_symlink[4*15]; - __fs64 u2_i_data[15]; - } i_u1; - __u32 i_flags; - __u32 i_shadow; - __u32 i_unused1; - __u32 i_unused2; - __u32 i_oeftflag; - __u16 i_osync; - __u64 i_lastfrag; - __u32 i_dir_start_lookup; - struct inode vfs_inode; -}; - -#endif /* _LINUX_UFS_FS_I_H */ diff --git a/include/linux/ufs_fs_sb.h b/include/linux/ufs_fs_sb.h deleted file mode 100644 index e114c93..0000000 --- a/include/linux/ufs_fs_sb.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * linux/include/linux/ufs_fs_sb.h - * - * Copyright (C) 1996 - * Adrian Rodriguez (adrian@franklins-tower.rutgers.edu) - * Laboratory for Computer Science Research Computing Facility - * Rutgers, The State University of New Jersey - * - * $Id: ufs_fs_sb.h,v 1.8 1998/05/06 12:04:40 jj Exp $ - * - * Write support by Daniel Pirkl <daniel.pirkl@email.cz> - */ - -#ifndef __LINUX_UFS_FS_SB_H -#define __LINUX_UFS_FS_SB_H - - -#define UFS_MAX_GROUP_LOADED 8 -#define UFS_CGNO_EMPTY ((unsigned)-1) - -struct ufs_sb_private_info; -struct ufs_cg_private_info; -struct ufs_csum; - -struct ufs_sb_info { - struct ufs_sb_private_info * s_uspi; - struct ufs_csum * s_csp; - unsigned s_bytesex; - unsigned s_flags; - struct buffer_head ** s_ucg; - struct ufs_cg_private_info * s_ucpi[UFS_MAX_GROUP_LOADED]; - unsigned s_cgno[UFS_MAX_GROUP_LOADED]; - unsigned short s_cg_loaded; - unsigned s_mount_opt; -}; - -#endif diff --git a/include/linux/uinput.h b/include/linux/uinput.h index a6c1e8e..15ddd44 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -162,10 +162,6 @@ struct uinput_ff_erase { #define UI_FF_UPLOAD 1 #define UI_FF_ERASE 2 -#ifndef NBITS -#define NBITS(x) ((((x)-1)/(sizeof(long)*8))+1) -#endif /* NBITS */ - #define UINPUT_MAX_NAME_SIZE 80 struct uinput_user_dev { char name[UINPUT_MAX_NAME_SIZE]; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 46705e9..c1527c2 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -481,7 +481,7 @@ static inline void *get_gadget_data (struct usb_gadget *gadget) /** * gadget_is_dualspeed - return true iff the hardware handles high speed - * @gadget: controller that might support both high and full speeds + * @g: controller that might support both high and full speeds */ static inline int gadget_is_dualspeed(struct usb_gadget *g) { @@ -497,7 +497,7 @@ static inline int gadget_is_dualspeed(struct usb_gadget *g) /** * gadget_is_otg - return true iff the hardware is OTG-ready - * @gadget: controller that might have a Mini-AB connector + * @g: controller that might have a Mini-AB connector * * This is a runtime test, since kernels with a USB-OTG stack sometimes * run on boards which only have a Mini-B (or Mini-A) connector. diff --git a/include/linux/videodev.h b/include/linux/videodev.h index 8dba97a..52e3d5f 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -294,48 +294,6 @@ struct video_code #define VID_PLAY_RESET 13 #define VID_PLAY_END_MARK 14 - - -#define VID_HARDWARE_BT848 1 -#define VID_HARDWARE_QCAM_BW 2 -#define VID_HARDWARE_PMS 3 -#define VID_HARDWARE_QCAM_C 4 -#define VID_HARDWARE_PSEUDO 5 -#define VID_HARDWARE_SAA5249 6 -#define VID_HARDWARE_AZTECH 7 -#define VID_HARDWARE_SF16MI 8 -#define VID_HARDWARE_RTRACK 9 -#define VID_HARDWARE_ZOLTRIX 10 -#define VID_HARDWARE_SAA7146 11 -#define VID_HARDWARE_VIDEUM 12 /* Reserved for Winnov videum */ -#define VID_HARDWARE_RTRACK2 13 -#define VID_HARDWARE_PERMEDIA2 14 /* Reserved for Permedia2 */ -#define VID_HARDWARE_RIVA128 15 /* Reserved for RIVA 128 */ -#define VID_HARDWARE_PLANB 16 /* PowerMac motherboard video-in */ -#define VID_HARDWARE_BROADWAY 17 /* Broadway project */ -#define VID_HARDWARE_GEMTEK 18 -#define VID_HARDWARE_TYPHOON 19 -#define VID_HARDWARE_VINO 20 /* SGI Indy Vino */ -#define VID_HARDWARE_CADET 21 /* Cadet radio */ -#define VID_HARDWARE_TRUST 22 /* Trust FM Radio */ -#define VID_HARDWARE_TERRATEC 23 /* TerraTec ActiveRadio */ -#define VID_HARDWARE_CPIA 24 -#define VID_HARDWARE_ZR36120 25 /* Zoran ZR36120/ZR36125 */ -#define VID_HARDWARE_ZR36067 26 /* Zoran ZR36067/36060 */ -#define VID_HARDWARE_OV511 27 -#define VID_HARDWARE_ZR356700 28 /* Zoran 36700 series */ -#define VID_HARDWARE_W9966 29 -#define VID_HARDWARE_SE401 30 /* SE401 USB webcams */ -#define VID_HARDWARE_PWC 31 /* Philips webcams */ -#define VID_HARDWARE_MEYE 32 /* Sony Vaio MotionEye cameras */ -#define VID_HARDWARE_CPIA2 33 -#define VID_HARDWARE_VICAM 34 -#define VID_HARDWARE_SF16FMR2 35 -#define VID_HARDWARE_W9968CF 36 -#define VID_HARDWARE_SAA7114H 37 -#define VID_HARDWARE_SN9C102 38 -#define VID_HARDWARE_ARV 39 - #endif /* CONFIG_VIDEO_V4L1_COMPAT */ #endif /* __LINUX_VIDEODEV_H */ diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 1f503e9..439474f 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -441,94 +441,6 @@ struct v4l2_timecode #define V4L2_TC_USERBITS_8BITCHARS 0x0008 /* The above is based on SMPTE timecodes */ -#ifdef __KERNEL__ -/* - * M P E G C O M P R E S S I O N P A R A M E T E R S - * - * ### WARNING: This experimental MPEG compression API is obsolete. - * ### It is replaced by the MPEG controls API. - * ### This old API will disappear in the near future! - * - */ -enum v4l2_bitrate_mode { - V4L2_BITRATE_NONE = 0, /* not specified */ - V4L2_BITRATE_CBR, /* constant bitrate */ - V4L2_BITRATE_VBR, /* variable bitrate */ -}; -struct v4l2_bitrate { - /* rates are specified in kbit/sec */ - enum v4l2_bitrate_mode mode; - __u32 min; - __u32 target; /* use this one for CBR */ - __u32 max; -}; - -enum v4l2_mpeg_streamtype { - V4L2_MPEG_SS_1, /* MPEG-1 system stream */ - V4L2_MPEG_PS_2, /* MPEG-2 program stream */ - V4L2_MPEG_TS_2, /* MPEG-2 transport stream */ - V4L2_MPEG_PS_DVD, /* MPEG-2 program stream with DVD header fixups */ -}; -enum v4l2_mpeg_audiotype { - V4L2_MPEG_AU_2_I, /* MPEG-2 layer 1 */ - V4L2_MPEG_AU_2_II, /* MPEG-2 layer 2 */ - V4L2_MPEG_AU_2_III, /* MPEG-2 layer 3 */ - V4L2_MPEG_AC3, /* AC3 */ - V4L2_MPEG_LPCM, /* LPCM */ -}; -enum v4l2_mpeg_videotype { - V4L2_MPEG_VI_1, /* MPEG-1 */ - V4L2_MPEG_VI_2, /* MPEG-2 */ -}; -enum v4l2_mpeg_aspectratio { - V4L2_MPEG_ASPECT_SQUARE = 1, /* square pixel */ - V4L2_MPEG_ASPECT_4_3 = 2, /* 4 : 3 */ - V4L2_MPEG_ASPECT_16_9 = 3, /* 16 : 9 */ - V4L2_MPEG_ASPECT_1_221 = 4, /* 1 : 2,21 */ -}; - -struct v4l2_mpeg_compression { - /* general */ - enum v4l2_mpeg_streamtype st_type; - struct v4l2_bitrate st_bitrate; - - /* transport streams */ - __u16 ts_pid_pmt; - __u16 ts_pid_audio; - __u16 ts_pid_video; - __u16 ts_pid_pcr; - - /* program stream */ - __u16 ps_size; - __u16 reserved_1; /* align */ - - /* audio */ - enum v4l2_mpeg_audiotype au_type; - struct v4l2_bitrate au_bitrate; - __u32 au_sample_rate; - __u8 au_pesid; - __u8 reserved_2[3]; /* align */ - - /* video */ - enum v4l2_mpeg_videotype vi_type; - enum v4l2_mpeg_aspectratio vi_aspect_ratio; - struct v4l2_bitrate vi_bitrate; - __u32 vi_frame_rate; - __u16 vi_frames_per_gop; - __u16 vi_bframes_count; - __u8 vi_pesid; - __u8 reserved_3[3]; /* align */ - - /* misc flags */ - __u32 closed_gops:1; - __u32 pulldown:1; - __u32 reserved_4:30; /* align */ - - /* I don't expect the above being perfect yet ;) */ - __u32 reserved_5[8]; -}; -#endif - struct v4l2_jpegcompression { int quality; @@ -1420,10 +1332,6 @@ struct v4l2_chip_ident { #define VIDIOC_ENUM_FMT _IOWR ('V', 2, struct v4l2_fmtdesc) #define VIDIOC_G_FMT _IOWR ('V', 4, struct v4l2_format) #define VIDIOC_S_FMT _IOWR ('V', 5, struct v4l2_format) -#ifdef __KERNEL__ -#define VIDIOC_G_MPEGCOMP _IOR ('V', 6, struct v4l2_mpeg_compression) -#define VIDIOC_S_MPEGCOMP _IOW ('V', 7, struct v4l2_mpeg_compression) -#endif #define VIDIOC_REQBUFS _IOWR ('V', 8, struct v4l2_requestbuffers) #define VIDIOC_QUERYBUF _IOWR ('V', 9, struct v4l2_buffer) #define VIDIOC_G_FBUF _IOR ('V', 10, struct v4l2_framebuffer) diff --git a/include/linux/virtio.h b/include/linux/virtio.h new file mode 100644 index 0000000..14e1379 --- /dev/null +++ b/include/linux/virtio.h @@ -0,0 +1,110 @@ +#ifndef _LINUX_VIRTIO_H +#define _LINUX_VIRTIO_H +/* Everything a virtio driver needs to work with any particular virtio + * implementation. */ +#include <linux/types.h> +#include <linux/scatterlist.h> +#include <linux/spinlock.h> +#include <linux/device.h> +#include <linux/mod_devicetable.h> + +/** + * virtqueue - a queue to register buffers for sending or receiving. + * @callback: the function to call when buffers are consumed (can be NULL). + * If this returns false, callbacks are suppressed until vq_ops->restart + * is called. + * @vdev: the virtio device this queue was created for. + * @vq_ops: the operations for this virtqueue (see below). + * @priv: a pointer for the virtqueue implementation to use. + */ +struct virtqueue +{ + bool (*callback)(struct virtqueue *vq); + struct virtio_device *vdev; + struct virtqueue_ops *vq_ops; + void *priv; +}; + +/** + * virtqueue_ops - operations for virtqueue abstraction layer + * @add_buf: expose buffer to other end + * vq: the struct virtqueue we're talking about. + * sg: the description of the buffer(s). + * out_num: the number of sg readable by other side + * in_num: the number of sg which are writable (after readable ones) + * data: the token identifying the buffer. + * Returns 0 or an error. + * @kick: update after add_buf + * vq: the struct virtqueue + * After one or more add_buf calls, invoke this to kick the other side. + * @get_buf: get the next used buffer + * vq: the struct virtqueue we're talking about. + * len: the length written into the buffer + * Returns NULL or the "data" token handed to add_buf. + * @restart: restart callbacks after callback returned false. + * vq: the struct virtqueue we're talking about. + * This returns "false" (and doesn't re-enable) if there are pending + * buffers in the queue, to avoid a race. + * @shutdown: "unadd" all buffers. + * vq: the struct virtqueue we're talking about. + * Remove everything from the queue. + * + * Locking rules are straightforward: the driver is responsible for + * locking. No two operations may be invoked simultaneously. + * + * All operations can be called in any context. + */ +struct virtqueue_ops { + int (*add_buf)(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data); + + void (*kick)(struct virtqueue *vq); + + void *(*get_buf)(struct virtqueue *vq, unsigned int *len); + + bool (*restart)(struct virtqueue *vq); + + void (*shutdown)(struct virtqueue *vq); +}; + +/** + * virtio_device - representation of a device using virtio + * @index: unique position on the virtio bus + * @dev: underlying device. + * @id: the device type identification (used to match it with a driver). + * @config: the configuration ops for this device. + * @priv: private pointer for the driver's use. + */ +struct virtio_device +{ + int index; + struct device dev; + struct virtio_device_id id; + struct virtio_config_ops *config; + void *priv; +}; + +int register_virtio_device(struct virtio_device *dev); +void unregister_virtio_device(struct virtio_device *dev); + +/** + * virtio_driver - operations for a virtio I/O driver + * @driver: underlying device driver (populate name and owner). + * @id_table: the ids serviced by this driver. + * @probe: the function to call when a device is found. Returns a token for + * remove, or PTR_ERR(). + * @remove: the function when a device is removed. + */ +struct virtio_driver { + struct device_driver driver; + const struct virtio_device_id *id_table; + int (*probe)(struct virtio_device *dev); + void (*remove)(struct virtio_device *dev); +}; + +int register_virtio_driver(struct virtio_driver *drv); +void unregister_virtio_driver(struct virtio_driver *drv); +#endif /* _LINUX_VIRTIO_H */ diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h new file mode 100644 index 0000000..7bd2bce --- /dev/null +++ b/include/linux/virtio_blk.h @@ -0,0 +1,51 @@ +#ifndef _LINUX_VIRTIO_BLK_H +#define _LINUX_VIRTIO_BLK_H +#include <linux/virtio_config.h> + +/* The ID for virtio_block */ +#define VIRTIO_ID_BLOCK 2 + +/* Feature bits */ +#define VIRTIO_CONFIG_BLK_F 0x40 +#define VIRTIO_BLK_F_BARRIER 1 /* Does host support barriers? */ + +/* The capacity (in 512-byte sectors). */ +#define VIRTIO_CONFIG_BLK_F_CAPACITY 0x41 +/* The maximum segment size. */ +#define VIRTIO_CONFIG_BLK_F_SIZE_MAX 0x42 +/* The maximum number of segments. */ +#define VIRTIO_CONFIG_BLK_F_SEG_MAX 0x43 + +/* These two define direction. */ +#define VIRTIO_BLK_T_IN 0 +#define VIRTIO_BLK_T_OUT 1 + +/* This bit says it's a scsi command, not an actual read or write. */ +#define VIRTIO_BLK_T_SCSI_CMD 2 + +/* Barrier before this op. */ +#define VIRTIO_BLK_T_BARRIER 0x80000000 + +/* This is the first element of the read scatter-gather list. */ +struct virtio_blk_outhdr +{ + /* VIRTIO_BLK_T* */ + __u32 type; + /* io priority. */ + __u32 ioprio; + /* Sector (ie. 512 byte offset) */ + __u64 sector; + /* Where to put reply. */ + __u64 id; +}; + +#define VIRTIO_BLK_S_OK 0 +#define VIRTIO_BLK_S_IOERR 1 +#define VIRTIO_BLK_S_UNSUPP 2 + +/* This is the first element of the write scatter-gather list */ +struct virtio_blk_inhdr +{ + unsigned char status; +}; +#endif /* _LINUX_VIRTIO_BLK_H */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h new file mode 100644 index 0000000..bcc0188 --- /dev/null +++ b/include/linux/virtio_config.h @@ -0,0 +1,111 @@ +#ifndef _LINUX_VIRTIO_CONFIG_H +#define _LINUX_VIRTIO_CONFIG_H +/* Virtio devices use a standardized configuration space to define their + * features and pass configuration information, but each implementation can + * store and access that space differently. */ +#include <linux/types.h> + +/* Status byte for guest to report progress, and synchronize config. */ +/* We have seen device and processed generic fields (VIRTIO_CONFIG_F_VIRTIO) */ +#define VIRTIO_CONFIG_S_ACKNOWLEDGE 1 +/* We have found a driver for the device. */ +#define VIRTIO_CONFIG_S_DRIVER 2 +/* Driver has used its parts of the config, and is happy */ +#define VIRTIO_CONFIG_S_DRIVER_OK 4 +/* We've given up on this device. */ +#define VIRTIO_CONFIG_S_FAILED 0x80 + +/* Feature byte (actually 7 bits availabe): */ +/* Requirements/features of the virtio implementation. */ +#define VIRTIO_CONFIG_F_VIRTIO 1 +/* Requirements/features of the virtqueue (may have more than one). */ +#define VIRTIO_CONFIG_F_VIRTQUEUE 2 + +#ifdef __KERNEL__ +struct virtio_device; + +/** + * virtio_config_ops - operations for configuring a virtio device + * @find: search for the next configuration field of the given type. + * vdev: the virtio_device + * type: the feature type + * len: the (returned) length of the field if found. + * Returns a token if found, or NULL. Never returnes the same field twice + * (ie. it's used up). + * @get: read the value of a configuration field after find(). + * vdev: the virtio_device + * token: the token returned from find(). + * buf: the buffer to write the field value into. + * len: the length of the buffer (given by find()). + * Note that contents are conventionally little-endian. + * @set: write the value of a configuration field after find(). + * vdev: the virtio_device + * token: the token returned from find(). + * buf: the buffer to read the field value from. + * len: the length of the buffer (given by find()). + * Note that contents are conventionally little-endian. + * @get_status: read the status byte + * vdev: the virtio_device + * Returns the status byte + * @set_status: write the status byte + * vdev: the virtio_device + * status: the new status byte + * @find_vq: find the first VIRTIO_CONFIG_F_VIRTQUEUE and create a virtqueue. + * vdev: the virtio_device + * callback: the virqtueue callback + * Returns the new virtqueue or ERR_PTR(). + * @del_vq: free a virtqueue found by find_vq(). + */ +struct virtio_config_ops +{ + void *(*find)(struct virtio_device *vdev, u8 type, unsigned *len); + void (*get)(struct virtio_device *vdev, void *token, + void *buf, unsigned len); + void (*set)(struct virtio_device *vdev, void *token, + const void *buf, unsigned len); + u8 (*get_status)(struct virtio_device *vdev); + void (*set_status)(struct virtio_device *vdev, u8 status); + struct virtqueue *(*find_vq)(struct virtio_device *vdev, + bool (*callback)(struct virtqueue *)); + void (*del_vq)(struct virtqueue *vq); +}; + +/** + * virtio_config_val - get a single virtio config and mark it used. + * @config: the virtio config space + * @type: the type to search for. + * @val: a pointer to the value to fill in. + * + * Once used, the config type is marked with VIRTIO_CONFIG_F_USED so it can't + * be found again. This version does endian conversion. */ +#define virtio_config_val(vdev, type, v) ({ \ + int _err = __virtio_config_val((vdev),(type),(v),sizeof(*(v))); \ + \ + BUILD_BUG_ON(sizeof(*(v)) != 1 && sizeof(*(v)) != 2 \ + && sizeof(*(v)) != 4 && sizeof(*(v)) != 8); \ + if (!_err) { \ + switch (sizeof(*(v))) { \ + case 2: le16_to_cpus((__u16 *) v); break; \ + case 4: le32_to_cpus((__u32 *) v); break; \ + case 8: le64_to_cpus((__u64 *) v); break; \ + } \ + } \ + _err; \ +}) + +int __virtio_config_val(struct virtio_device *dev, + u8 type, void *val, size_t size); + +/** + * virtio_use_bit - helper to use a feature bit in a bitfield value. + * @dev: the virtio device + * @token: the token as returned from vdev->config->find(). + * @len: the length of the field. + * @bitnum: the bit to test. + * + * If handed a NULL token, it returns false, otherwise returns bit status. + * If it's one, it sets the mirroring acknowledgement bit. */ +int virtio_use_bit(struct virtio_device *vdev, + void *token, unsigned int len, unsigned int bitnum); +#endif /* __KERNEL__ */ +#endif /* _LINUX_VIRTIO_CONFIG_H */ diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h new file mode 100644 index 0000000..ed2d4ea --- /dev/null +++ b/include/linux/virtio_console.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_VIRTIO_CONSOLE_H +#define _LINUX_VIRTIO_CONSOLE_H +#include <linux/virtio_config.h> + +/* The ID for virtio console */ +#define VIRTIO_ID_CONSOLE 3 + +#ifdef __KERNEL__ +int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); +#endif /* __KERNEL__ */ + +#endif /* _LINUX_VIRTIO_CONSOLE_H */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h new file mode 100644 index 0000000..ae469ae --- /dev/null +++ b/include/linux/virtio_net.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_VIRTIO_NET_H +#define _LINUX_VIRTIO_NET_H +#include <linux/virtio_config.h> + +/* The ID for virtio_net */ +#define VIRTIO_ID_NET 1 + +/* The bitmap of config for virtio net */ +#define VIRTIO_CONFIG_NET_F 0x40 +#define VIRTIO_NET_F_NO_CSUM 0 +#define VIRTIO_NET_F_TSO4 1 +#define VIRTIO_NET_F_UFO 2 +#define VIRTIO_NET_F_TSO4_ECN 3 +#define VIRTIO_NET_F_TSO6 4 + +/* The config defining mac address. */ +#define VIRTIO_CONFIG_NET_MAC_F 0x41 + +/* This is the first element of the scatter-gather list. If you don't + * specify GSO or CSUM features, you can simply ignore the header. */ +struct virtio_net_hdr +{ +#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset + __u8 flags; +#define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame +#define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO) +/* FIXME: Do we need this? If they said they can handle ECN, do they care? */ +#define VIRTIO_NET_HDR_GSO_TCPV4_ECN 2 // GSO frame, IPv4 TCP w/ ECN +#define VIRTIO_NET_HDR_GSO_UDP 3 // GSO frame, IPv4 UDP (UFO) +#define VIRTIO_NET_HDR_GSO_TCPV6 4 // GSO frame, IPv6 TCP + __u8 gso_type; + __u16 gso_size; + __u16 csum_start; + __u16 csum_offset; +}; +#endif /* _LINUX_VIRTIO_NET_H */ diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h new file mode 100644 index 0000000..ac69e7b --- /dev/null +++ b/include/linux/virtio_ring.h @@ -0,0 +1,119 @@ +#ifndef _LINUX_VIRTIO_RING_H +#define _LINUX_VIRTIO_RING_H +/* An interface for efficient virtio implementation, currently for use by KVM + * and lguest, but hopefully others soon. Do NOT change this since it will + * break existing servers and clients. + * + * This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. + * + * Copyright Rusty Russell IBM Corporation 2007. */ +#include <linux/types.h> + +/* This marks a buffer as continuing via the next field. */ +#define VRING_DESC_F_NEXT 1 +/* This marks a buffer as write-only (otherwise read-only). */ +#define VRING_DESC_F_WRITE 2 + +/* This means don't notify other side when buffer added. */ +#define VRING_USED_F_NO_NOTIFY 1 +/* This means don't interrupt guest when buffer consumed. */ +#define VRING_AVAIL_F_NO_INTERRUPT 1 + +/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ +struct vring_desc +{ + /* Address (guest-physical). */ + __u64 addr; + /* Length. */ + __u32 len; + /* The flags as indicated above. */ + __u16 flags; + /* We chain unused descriptors via this, too */ + __u16 next; +}; + +struct vring_avail +{ + __u16 flags; + __u16 idx; + __u16 ring[]; +}; + +/* u32 is used here for ids for padding reasons. */ +struct vring_used_elem +{ + /* Index of start of used descriptor chain. */ + __u32 id; + /* Total length of the descriptor chain which was used (written to) */ + __u32 len; +}; + +struct vring_used +{ + __u16 flags; + __u16 idx; + struct vring_used_elem ring[]; +}; + +struct vring { + unsigned int num; + + struct vring_desc *desc; + + struct vring_avail *avail; + + struct vring_used *used; +}; + +/* The standard layout for the ring is a continuous chunk of memory which looks + * like this. The used fields will be aligned to a "num+1" boundary. + * + * struct vring + * { + * // The actual descriptors (16 bytes each) + * struct vring_desc desc[num]; + * + * // A ring of available descriptor heads with free-running index. + * __u16 avail_flags; + * __u16 avail_idx; + * __u16 available[num]; + * + * // Padding so a correctly-chosen num value will cache-align used_idx. + * char pad[sizeof(struct vring_desc) - sizeof(avail_flags)]; + * + * // A ring of used descriptor heads with free-running index. + * __u16 used_flags; + * __u16 used_idx; + * struct vring_used_elem used[num]; + * }; + */ +static inline void vring_init(struct vring *vr, unsigned int num, void *p) +{ + vr->num = num; + vr->desc = p; + vr->avail = p + num*sizeof(struct vring); + vr->used = p + (num+1)*(sizeof(struct vring) + sizeof(__u16)); +} + +static inline unsigned vring_size(unsigned int num) +{ + return (num + 1) * (sizeof(struct vring_desc) + sizeof(__u16)) + + sizeof(__u32) + num * sizeof(struct vring_used_elem); +} + +#ifdef __KERNEL__ +#include <linux/irqreturn.h> +struct virtio_device; +struct virtqueue; + +struct virtqueue *vring_new_virtqueue(unsigned int num, + struct virtio_device *vdev, + void *pages, + void (*notify)(struct virtqueue *vq), + bool (*callback)(struct virtqueue *vq)); +void vring_del_virtqueue(struct virtqueue *vq); + +irqreturn_t vring_interrupt(int irq, void *_vq); +#endif /* __KERNEL__ */ +#endif /* _LINUX_VIRTIO_RING_H */ diff --git a/include/linux/vt.h b/include/linux/vt.h index ba806e8..02c1c02 100644 --- a/include/linux/vt.h +++ b/include/linux/vt.h @@ -1,6 +1,18 @@ #ifndef _LINUX_VT_H #define _LINUX_VT_H +#ifdef __KERNEL__ +struct notifier_block; + +struct vt_notifier_param { + struct vc_data *vc; /* VC on which the update happened */ + unsigned int c; /* Printed char */ +}; + +extern int register_vt_notifier(struct notifier_block *nb); +extern int unregister_vt_notifier(struct notifier_block *nb); +#endif + /* * These constants are also useful for user-level apps (e.g., VC * resizing). diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 699b7e9..feb5e99 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -87,6 +87,7 @@ extern int unbind_con_driver(const struct consw *csw, int first, int last, extern char con_buf[CON_BUF_SIZE]; extern struct mutex con_buf_mtx; extern char vt_dont_switch; +extern int default_utf8; struct vt_spawn_console { spinlock_t lock; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ce6badc..7daafdc 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -8,6 +8,7 @@ #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> +#include <linux/lockdep.h> #include <asm/atomic.h> struct workqueue_struct; @@ -28,6 +29,9 @@ struct work_struct { #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct list_head entry; work_func_t func; +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT(0) @@ -41,10 +45,23 @@ struct execute_work { struct work_struct work; }; +#ifdef CONFIG_LOCKDEP +/* + * NB: because we have to copy the lockdep_map, setting _key + * here is required, otherwise it could get initialised to the + * copy of the lockdep_map! + */ +#define __WORK_INIT_LOCKDEP_MAP(n, k) \ + .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), +#else +#define __WORK_INIT_LOCKDEP_MAP(n, k) +#endif + #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ + __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f) { \ @@ -76,12 +93,24 @@ struct execute_work { * assignment of the work data initializer allows the compiler * to generate better code. */ +#ifdef CONFIG_LOCKDEP +#define INIT_WORK(_work, _func) \ + do { \ + static struct lock_class_key __key; \ + \ + (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ + lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0);\ + INIT_LIST_HEAD(&(_work)->entry); \ + PREPARE_WORK((_work), (_func)); \ + } while (0) +#else #define INIT_WORK(_work, _func) \ do { \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ PREPARE_WORK((_work), (_func)); \ } while (0) +#endif #define INIT_DELAYED_WORK(_work, _func) \ do { \ @@ -118,9 +147,23 @@ struct execute_work { clear_bit(WORK_STRUCT_PENDING, work_data_bits(work)) -extern struct workqueue_struct *__create_workqueue(const char *name, - int singlethread, - int freezeable); +extern struct workqueue_struct * +__create_workqueue_key(const char *name, int singlethread, + int freezeable, struct lock_class_key *key); + +#ifdef CONFIG_LOCKDEP +#define __create_workqueue(name, singlethread, freezeable) \ +({ \ + static struct lock_class_key __key; \ + \ + __create_workqueue_key((name), (singlethread), \ + (freezeable), &__key); \ +}) +#else +#define __create_workqueue(name, singlethread, freezeable) \ + __create_workqueue_key((name), (singlethread), (freezeable), NULL) +#endif + #define create_workqueue(name) __create_workqueue((name), 0, 0) #define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1) #define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c7c3337..bef7d66 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -62,15 +62,13 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned for_writepages:1; /* This is a writepages() call */ unsigned range_cyclic:1; /* range_start is cyclic */ - - void *fs_private; /* For use by ->writepages() */ + unsigned more_io:1; /* more io to be dispatched */ }; /* * fs/fs-writeback.c */ void writeback_inodes(struct writeback_control *wbc); -void wake_up_inode(struct inode *inode); int inode_wait(void *); void sync_inodes_sb(struct super_block *, int wait); void sync_inodes(int wait); @@ -82,6 +80,13 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_LOCK, inode_wait, TASK_UNINTERRUPTIBLE); } +static inline void inode_sync_wait(struct inode *inode) +{ + might_sleep(); + wait_on_bit(&inode->i_state, __I_SYNC, inode_wait, + TASK_UNINTERRUPTIBLE); +} + /* * mm/page-writeback.c @@ -99,6 +104,10 @@ extern int dirty_expire_interval; extern int block_dump; extern int laptop_mode; +extern int dirty_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); + struct ctl_table; struct file; int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, |