diff --git a/Documentation/blockdev/drbd/DRBD-8.3-data-packets.svg b/Documentation/blockdev/drbd/DRBD-8.3-data-packets.svg new file mode 100644 index 000000000000..f87cfa0dc2fb --- /dev/null +++ b/Documentation/blockdev/drbd/DRBD-8.3-data-packets.svg @@ -0,0 +1,588 @@ + + + + + + Master slide + + + + + + + + + + RSDataReply + + + + + + + CsumRSRequest + + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + + WriteAck + + + + got_BlockAck() + + + Checksum based Resync, case not in sync + + + DRBD-8.3 data flow + + + w_e_send_csum() + + + + + + + + RSIsInSync + + + + + + + CsumRSRequest + + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + got_IsInSync() + + + Checksum based Resync, case in sync + + + + + + + + + + OVReply + + + + + + + OVRequest + + + + receive_OVRequest() + + + drbd_endio_read_sec() + + + w_e_end_ov_req() + + + receive_OVReply() + + + drbd_endio_read_sec() + + + w_e_end_ov_reply() + + + + + + OVResult + + + + got_OVResult() + + + Online verify + + + w_make_ov_request() + + + + + + + + drbd_endio_read_sec() + + + w_make_resync_request() + + + w_e_send_csum() + + + + + drbd_endio_read_sec() + + + + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + diff --git a/Documentation/blockdev/drbd/DRBD-data-packets.svg b/Documentation/blockdev/drbd/DRBD-data-packets.svg new file mode 100644 index 000000000000..48a1e2165fec --- /dev/null +++ b/Documentation/blockdev/drbd/DRBD-data-packets.svg @@ -0,0 +1,459 @@ + + + + + + Master slide + + + + + + + + + RSDataReply + + + + + RSDataRequest + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_rsdata_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + WriteAck + + + got_BlockAck() + + + Resync blocks, 4-32K + + + + + + + WriteAck + + + + + Data + + + drbd_make_request() + + + receive_Data() + + + drbd_endio_write_sec() + + + e_end_block() + + + got_BlockAck() + + + Regular mirrored write, 512-32K + + + w_send_dblock() + + + + + drbd_endio_write_pri() + + + + + + + DataReply + + + + + DataRequest + + + drbd_make_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_data_req() + + + Drawing + + receive_DataReply() + + + + Diskless read, 512-32K + + + w_send_read_req() + + + DRBD 8 data flow + + + + + + al_begin_io() + + + al_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + diff --git a/Documentation/blockdev/drbd/README.txt b/Documentation/blockdev/drbd/README.txt new file mode 100644 index 000000000000..627b0a1bf35e --- /dev/null +++ b/Documentation/blockdev/drbd/README.txt @@ -0,0 +1,16 @@ +Description + + DRBD is a shared-nothing, synchronously replicated block device. It + is designed to serve as a building block for high availability + clusters and in this context, is a "drop-in" replacement for shared + storage. Simplistically, you could see it as a network RAID 1. + + Please visit http://www.drbd.org to find out more. + +The here included files are intended to help understand the implementation + +DRBD-8.3-data-packets.svg, DRBD-data-packets.svg + relates some functions, and write packets. + +conn-states-8.dot, disk-states-8.dot, node-states-8.dot + The sub graphs of DRBD's state transitions diff --git a/Documentation/blockdev/drbd/conn-states-8.dot b/Documentation/blockdev/drbd/conn-states-8.dot new file mode 100644 index 000000000000..025e8cf5e64a --- /dev/null +++ b/Documentation/blockdev/drbd/conn-states-8.dot @@ -0,0 +1,18 @@ +digraph conn_states { + StandAllone -> WFConnection [ label = "ioctl_set_net()" ] + WFConnection -> Unconnected [ label = "unable to bind()" ] + WFConnection -> WFReportParams [ label = "in connect() after accept" ] + WFReportParams -> StandAllone [ label = "checks in receive_param()" ] + WFReportParams -> Connected [ label = "in receive_param()" ] + WFReportParams -> WFBitMapS [ label = "sync_handshake()" ] + WFReportParams -> WFBitMapT [ label = "sync_handshake()" ] + WFBitMapS -> SyncSource [ label = "receive_bitmap()" ] + WFBitMapT -> SyncTarget [ label = "receive_bitmap()" ] + SyncSource -> Connected + SyncTarget -> Connected + SyncSource -> PausedSyncS + SyncTarget -> PausedSyncT + PausedSyncS -> SyncSource + PausedSyncT -> SyncTarget + Connected -> WFConnection [ label = "* on network error" ] +} diff --git a/Documentation/blockdev/drbd/disk-states-8.dot b/Documentation/blockdev/drbd/disk-states-8.dot new file mode 100644 index 000000000000..d06cfb46fb98 --- /dev/null +++ b/Documentation/blockdev/drbd/disk-states-8.dot @@ -0,0 +1,16 @@ +digraph disk_states { + Diskless -> Inconsistent [ label = "ioctl_set_disk()" ] + Diskless -> Consistent [ label = "ioctl_set_disk()" ] + Diskless -> Outdated [ label = "ioctl_set_disk()" ] + Consistent -> Outdated [ label = "receive_param()" ] + Consistent -> UpToDate [ label = "receive_param()" ] + Consistent -> Inconsistent [ label = "start resync" ] + Outdated -> Inconsistent [ label = "start resync" ] + UpToDate -> Inconsistent [ label = "ioctl_replicate" ] + Inconsistent -> UpToDate [ label = "resync completed" ] + Consistent -> Failed [ label = "io completion error" ] + Outdated -> Failed [ label = "io completion error" ] + UpToDate -> Failed [ label = "io completion error" ] + Inconsistent -> Failed [ label = "io completion error" ] + Failed -> Diskless [ label = "sending notify to peer" ] +} diff --git a/Documentation/blockdev/drbd/drbd-connection-state-overview.dot b/Documentation/blockdev/drbd/drbd-connection-state-overview.dot new file mode 100644 index 000000000000..6d9cf0a7b11d --- /dev/null +++ b/Documentation/blockdev/drbd/drbd-connection-state-overview.dot @@ -0,0 +1,85 @@ +// vim: set sw=2 sts=2 : +digraph { + rankdir=BT + bgcolor=white + + node [shape=plaintext] + node [fontcolor=black] + + StandAlone [ style=filled,fillcolor=gray,label=StandAlone ] + + node [fontcolor=lightgray] + + Unconnected [ label=Unconnected ] + + CommTrouble [ shape=record, + label="{communication loss|{Timeout|BrokenPipe|NetworkFailure}}" ] + + node [fontcolor=gray] + + subgraph cluster_try_connect { + label="try to connect, handshake" + rank=max + WFConnection [ label=WFConnection ] + WFReportParams [ label=WFReportParams ] + } + + TearDown [ label=TearDown ] + + Connected [ label=Connected,style=filled,fillcolor=green,fontcolor=black ] + + node [fontcolor=lightblue] + + StartingSyncS [ label=StartingSyncS ] + StartingSyncT [ label=StartingSyncT ] + + subgraph cluster_bitmap_exchange { + node [fontcolor=red] + fontcolor=red + label="new application (WRITE?) requests blocked\lwhile bitmap is exchanged" + + WFBitMapT [ label=WFBitMapT ] + WFSyncUUID [ label=WFSyncUUID ] + WFBitMapS [ label=WFBitMapS ] + } + + node [fontcolor=blue] + + cluster_resync [ shape=record,label="{resynchronisation process running\l'concurrent' application requests allowed|{{PausedSyncT\nSyncTarget}|{PausedSyncS\nSyncSource}}}" ] + + node [shape=box,fontcolor=black] + + // drbdadm [label="drbdadm connect"] + // handshake [label="drbd_connect()\ndrbd_do_handshake\ndrbd_sync_handshake() etc."] + // comm_error [label="communication trouble"] + + // + // edges + // -------------------------------------- + + StandAlone -> Unconnected [ label="drbdadm connect" ] + Unconnected -> StandAlone [ label="drbdadm disconnect\lor serious communication trouble" ] + Unconnected -> WFConnection [ label="receiver thread is started" ] + WFConnection -> WFReportParams [ headlabel="accept()\land/or \lconnect()\l" ] + + WFReportParams -> StandAlone [ label="during handshake\lpeers do not agree\labout something essential" ] + WFReportParams -> Connected [ label="data identical\lno sync needed",color=green,fontcolor=green ] + + WFReportParams -> WFBitMapS + WFReportParams -> WFBitMapT + WFBitMapT -> WFSyncUUID [minlen=0.1,constraint=false] + + WFBitMapS -> cluster_resync:S + WFSyncUUID -> cluster_resync:T + + edge [color=green] + cluster_resync:any -> Connected [ label="resnyc done",fontcolor=green ] + + edge [color=red] + WFReportParams -> CommTrouble + Connected -> CommTrouble + cluster_resync:any -> CommTrouble + edge [color=black] + CommTrouble -> Unconnected [label="receiver thread is stopped" ] + +} diff --git a/Documentation/blockdev/drbd/node-states-8.dot b/Documentation/blockdev/drbd/node-states-8.dot new file mode 100644 index 000000000000..4a2b00c23547 --- /dev/null +++ b/Documentation/blockdev/drbd/node-states-8.dot @@ -0,0 +1,14 @@ +digraph node_states { + Secondary -> Primary [ label = "ioctl_set_state()" ] + Primary -> Secondary [ label = "ioctl_set_state()" ] +} + +digraph peer_states { + Secondary -> Primary [ label = "recv state packet" ] + Primary -> Secondary [ label = "recv state packet" ] + Primary -> Unknown [ label = "connection lost" ] + Secondary -> Unknown [ label = "connection lost" ] + Unknown -> Primary [ label = "connected" ] + Unknown -> Secondary [ label = "connected" ] +} + diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt new file mode 100644 index 000000000000..630879cd9a42 --- /dev/null +++ b/Documentation/cgroups/blkio-controller.txt @@ -0,0 +1,135 @@ + Block IO Controller + =================== +Overview +======== +cgroup subsys "blkio" implements the block io controller. There seems to be +a need of various kinds of IO control policies (like proportional BW, max BW) +both at leaf nodes as well as at intermediate nodes in a storage hierarchy. +Plan is to use the same cgroup based management interface for blkio controller +and based on user options switch IO policies in the background. + +In the first phase, this patchset implements proportional weight time based +division of disk policy. It is implemented in CFQ. Hence this policy takes +effect only on leaf nodes when CFQ is being used. + +HOWTO +===== +You can do a very simple testing of running two dd threads in two different +cgroups. Here is what you can do. + +- Enable group scheduling in CFQ + CONFIG_CFQ_GROUP_IOSCHED=y + +- Compile and boot into kernel and mount IO controller (blkio). + + mount -t cgroup -o blkio none /cgroup + +- Create two cgroups + mkdir -p /cgroup/test1/ /cgroup/test2 + +- Set weights of group test1 and test2 + echo 1000 > /cgroup/test1/blkio.weight + echo 500 > /cgroup/test2/blkio.weight + +- Create two same size files (say 512MB each) on same disk (file1, file2) and + launch two dd threads in different cgroup to read those files. + + sync + echo 3 > /proc/sys/vm/drop_caches + + dd if=/mnt/sdb/zerofile1 of=/dev/null & + echo $! > /cgroup/test1/tasks + cat /cgroup/test1/tasks + + dd if=/mnt/sdb/zerofile2 of=/dev/null & + echo $! > /cgroup/test2/tasks + cat /cgroup/test2/tasks + +- At macro level, first dd should finish first. To get more precise data, keep + on looking at (with the help of script), at blkio.disk_time and + blkio.disk_sectors files of both test1 and test2 groups. This will tell how + much disk time (in milli seconds), each group got and how many secotors each + group dispatched to the disk. We provide fairness in terms of disk time, so + ideally io.disk_time of cgroups should be in proportion to the weight. + +Various user visible config options +=================================== +CONFIG_CFQ_GROUP_IOSCHED + - Enables group scheduling in CFQ. Currently only 1 level of group + creation is allowed. + +CONFIG_DEBUG_CFQ_IOSCHED + - Enables some debugging messages in blktrace. Also creates extra + cgroup file blkio.dequeue. + +Config options selected automatically +===================================== +These config options are not user visible and are selected/deselected +automatically based on IO scheduler configuration. + +CONFIG_BLK_CGROUP + - Block IO controller. Selected by CONFIG_CFQ_GROUP_IOSCHED. + +CONFIG_DEBUG_BLK_CGROUP + - Debug help. Selected by CONFIG_DEBUG_CFQ_IOSCHED. + +Details of cgroup files +======================= +- blkio.weight + - Specifies per cgroup weight. + + Currently allowed range of weights is from 100 to 1000. + +- blkio.time + - disk time allocated to cgroup per device in milliseconds. First + two fields specify the major and minor number of the device and + third field specifies the disk time allocated to group in + milliseconds. + +- blkio.sectors + - number of sectors transferred to/from disk by the group. First + two fields specify the major and minor number of the device and + third field specifies the number of sectors transferred by the + group to/from the device. + +- blkio.dequeue + - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This + gives the statistics about how many a times a group was dequeued + from service tree of the device. First two fields specify the major + and minor number of the device and third field specifies the number + of times a group was dequeued from a particular device. + +CFQ sysfs tunable +================= +/sys/block//queue/iosched/group_isolation + +If group_isolation=1, it provides stronger isolation between groups at the +expense of throughput. By default group_isolation is 0. In general that +means that if group_isolation=0, expect fairness for sequential workload +only. Set group_isolation=1 to see fairness for random IO workload also. + +Generally CFQ will put random seeky workload in sync-noidle category. CFQ +will disable idling on these queues and it does a collective idling on group +of such queues. Generally these are slow moving queues and if there is a +sync-noidle service tree in each group, that group gets exclusive access to +disk for certain period. That means it will bring the throughput down if +group does not have enough IO to drive deeper queue depths and utilize disk +capacity to the fullest in the slice allocated to it. But the flip side is +that even a random reader should get better latencies and overall throughput +if there are lots of sequential readers/sync-idle workload running in the +system. + +If group_isolation=0, then CFQ automatically moves all the random seeky queues +in the root group. That means there will be no service differentiation for +that kind of workload. This leads to better throughput as we do collective +idling on root sync-noidle tree. + +By default one should run with group_isolation=0. If that is not sufficient +and one wants stronger isolation between groups, then set group_isolation=1 +but this will come at cost of reduced throughput. + +What works +========== +- Currently only sync IO queues are support. All the buffered writes are + still system wide and not per group. Hence we will not see service + differentiation between buffered writes between groups. diff --git a/MAINTAINERS b/MAINTAINERS index 4a5d67620a51..ea781c1cfb5a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1848,6 +1848,19 @@ S: Maintained F: drivers/scsi/dpt* F: drivers/scsi/dpt/ +DRBD DRIVER +P: Philipp Reisner +P: Lars Ellenberg +M: drbd-dev@lists.linbit.com +L: drbd-user@lists.linbit.com +W: http://www.drbd.org +T: git git://git.drbd.org/linux-2.6-drbd.git drbd +T: git git://git.drbd.org/drbd-8.3.git +S: Supported +F: drivers/block/drbd/ +F: lib/lru_cache.c +F: Documentation/blockdev/drbd/ + DRIVER CORE, KOBJECTS, AND SYSFS M: Greg Kroah-Hartman T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ diff --git a/arch/alpha/include/asm/cacheflush.h b/arch/alpha/include/asm/cacheflush.h index b686cc7fc44e..01d71e1c8a9e 100644 --- a/arch/alpha/include/asm/cacheflush.h +++ b/arch/alpha/include/asm/cacheflush.h @@ -9,6 +9,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 9fd6d3ab68c0..73eceb87e588 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -418,6 +418,7 @@ extern void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, * about to change to user space. This is the same method as used on SPARC64. * See update_mmu_cache for the user space part. */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); static inline void __flush_icache_all(void) diff --git a/arch/avr32/include/asm/cacheflush.h b/arch/avr32/include/asm/cacheflush.h index 670674749b20..96e53820bbbd 100644 --- a/arch/avr32/include/asm/cacheflush.h +++ b/arch/avr32/include/asm/cacheflush.h @@ -107,6 +107,7 @@ extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); * do something here, but only for certain configurations. No such * configurations exist at this time. */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(page) do { } while (0) #define flush_dcache_mmap_unlock(page) do { } while (0) diff --git a/arch/blackfin/include/asm/cacheflush.h b/arch/blackfin/include/asm/cacheflush.h index af03a36c7a4e..417eaac7fe99 100644 --- a/arch/blackfin/include/asm/cacheflush.h +++ b/arch/blackfin/include/asm/cacheflush.h @@ -68,9 +68,11 @@ do { memcpy(dst, src, len); \ #endif #if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK) # define flush_dcache_range(start,end) blackfin_dcache_flush_range((start), (end)) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 # define flush_dcache_page(page) blackfin_dflush_page(page_address(page)) #else # define flush_dcache_range(start,end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 # define flush_dcache_page(page) do { } while (0) #endif diff --git a/arch/cris/include/asm/cacheflush.h b/arch/cris/include/asm/cacheflush.h index cf60e3f69f8d..36795bca605e 100644 --- a/arch/cris/include/asm/cacheflush.h +++ b/arch/cris/include/asm/cacheflush.h @@ -12,6 +12,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/frv/include/asm/cacheflush.h b/arch/frv/include/asm/cacheflush.h index 432a69e7f3d4..edbac54ae015 100644 --- a/arch/frv/include/asm/cacheflush.h +++ b/arch/frv/include/asm/cacheflush.h @@ -47,6 +47,7 @@ static inline void __flush_cache_all(void) } /* dcache/icache coherency... */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #ifdef CONFIG_MMU extern void flush_dcache_page(struct page *page); #else diff --git a/arch/h8300/include/asm/cacheflush.h b/arch/h8300/include/asm/cacheflush.h index 5ffdca217b95..4cf2df20c1ce 100644 --- a/arch/h8300/include/asm/cacheflush.h +++ b/arch/h8300/include/asm/cacheflush.h @@ -15,6 +15,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma,a,b) #define flush_cache_page(vma,p,pfn) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) #define flush_dcache_mmap_lock(mapping) #define flush_dcache_mmap_unlock(mapping) diff --git a/arch/ia64/include/asm/cacheflush.h b/arch/ia64/include/asm/cacheflush.h index c8ce2719fee8..429eefc93ee7 100644 --- a/arch/ia64/include/asm/cacheflush.h +++ b/arch/ia64/include/asm/cacheflush.h @@ -25,6 +25,7 @@ #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) \ do { \ clear_bit(PG_arch_1, &(page)->flags); \ diff --git a/arch/m32r/include/asm/cacheflush.h b/arch/m32r/include/asm/cacheflush.h index 78587c958146..8e8e04516c39 100644 --- a/arch/m32r/include/asm/cacheflush.h +++ b/arch/m32r/include/asm/cacheflush.h @@ -12,6 +12,7 @@ extern void _flush_cache_copyback_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) @@ -33,6 +34,7 @@ extern void smp_flush_cache_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) @@ -46,6 +48,7 @@ extern void smp_flush_cache_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 16bf375fdbe1..73de7c89d8e0 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -128,6 +128,7 @@ static inline void __flush_page_to_ram(void *vaddr) } } +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/m68k/include/asm/cacheflush_no.h b/arch/m68k/include/asm/cacheflush_no.h index c65f00a94553..89f195656be7 100644 --- a/arch/m68k/include/asm/cacheflush_no.h +++ b/arch/m68k/include/asm/cacheflush_no.h @@ -12,6 +12,7 @@ #define flush_cache_range(vma, start, end) __flush_cache_all() #define flush_cache_page(vma, vmaddr) do { } while (0) #define flush_dcache_range(start,len) __flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/microblaze/include/asm/cacheflush.h b/arch/microblaze/include/asm/cacheflush.h index f989d6aad648..088076e657b3 100644 --- a/arch/microblaze/include/asm/cacheflush.h +++ b/arch/microblaze/include/asm/cacheflush.h @@ -37,6 +37,7 @@ #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) #define flush_dcache_range(start, end) __invalidate_dcache_range(start, end) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index 03b1d69b142f..40bb9fde205f 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -38,6 +38,7 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma, extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn); extern void __flush_dcache_page(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 static inline void flush_dcache_page(struct page *page) { if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) diff --git a/arch/mn10300/include/asm/cacheflush.h b/arch/mn10300/include/asm/cacheflush.h index 1a55d61f0d06..29e692f7f030 100644 --- a/arch/mn10300/include/asm/cacheflush.h +++ b/arch/mn10300/include/asm/cacheflush.h @@ -26,6 +26,7 @@ #define flush_cache_page(vma, vmaddr, pfn) do {} while (0) #define flush_cache_vmap(start, end) do {} while (0) #define flush_cache_vunmap(start, end) do {} while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do {} while (0) #define flush_dcache_mmap_lock(mapping) do {} while (0) #define flush_dcache_mmap_unlock(mapping) do {} while (0) diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 724395143f26..7a73b615c23d 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -42,6 +42,7 @@ void flush_cache_mm(struct mm_struct *mm); #define flush_cache_vmap(start, end) flush_cache_all() #define flush_cache_vunmap(start, end) flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) \ diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index ba667a383b8c..ab9e402518e8 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -25,6 +25,7 @@ #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 49d5af916d01..405cc97c6249 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -10,6 +10,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/score/include/asm/cacheflush.h b/arch/score/include/asm/cacheflush.h index 07cc8fc457cd..caaba24036e3 100644 --- a/arch/score/include/asm/cacheflush.h +++ b/arch/score/include/asm/cacheflush.h @@ -16,6 +16,7 @@ extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_dcache_range(unsigned long start, unsigned long end); #define flush_cache_dup_mm(mm) do {} while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do {} while (0) #define flush_dcache_mmap_lock(mapping) do {} while (0) #define flush_dcache_mmap_unlock(mapping) do {} while (0) diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c29918f3c819..dda96eb3e7c0 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -42,6 +42,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 68ac10910271..2e468773f250 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -75,6 +75,7 @@ BTFIXUPDEF_CALL(void, flush_sig_insns, struct mm_struct *, unsigned long) extern void sparc_flush_page_to_ram(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) sparc_flush_page_to_ram(page) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h index c43321729b3b..b95384033e89 100644 --- a/arch/sparc/include/asm/cacheflush_64.h +++ b/arch/sparc/include/asm/cacheflush_64.h @@ -37,6 +37,7 @@ extern void flush_dcache_page_all(struct mm_struct *mm, struct page *page); #endif extern void __flush_dcache_range(unsigned long start, unsigned long end); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_icache_page(vma, pg) do { } while(0) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index b54f6afe7ec4..9076add593a8 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -12,6 +12,7 @@ static inline void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } static inline void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { } +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 static inline void flush_dcache_page(struct page *page) { } static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index b7b8fbe47c77..a508f2f73bd7 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -101,6 +101,7 @@ static inline void __invalidate_icache_page_alias(unsigned long virt, #define flush_cache_vmap(start,end) flush_cache_all() #define flush_cache_vunmap(start,end) flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page*); extern void flush_cache_range(struct vm_area_struct*, ulong, ulong); extern void flush_cache_page(struct vm_area_struct*, unsigned long, unsigned long); diff --git a/block/Kconfig b/block/Kconfig index 9be0b56eaee1..e20fbde0875c 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -77,6 +77,28 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_CGROUP + bool + depends on CGROUPS + default n + ---help--- + Generic block IO controller cgroup interface. This is the common + cgroup interface which should be used by various IO controlling + policies. + + Currently, CFQ IO scheduler uses it to recognize task groups and + control disk bandwidth allocation (proportional time slice allocation) + to such task groups. + +config DEBUG_BLK_CGROUP + bool + depends on BLK_CGROUP + default n + ---help--- + Enable some debugging help. Currently it stores the cgroup path + in the blk group which can be used by cfq for tracing various + group related activity. + endif # BLOCK config BLOCK_COMPAT diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 7e803fc88770..b71abfb0d726 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -12,24 +12,14 @@ config IOSCHED_NOOP that do their own scheduling and require only minimal assistance from the kernel. -config IOSCHED_AS - tristate "Anticipatory I/O scheduler" - default y - ---help--- - The anticipatory I/O scheduler is generally a good choice for most - environments, but is quite large and complex when compared to the - deadline I/O scheduler, it can also be slower in some cases - especially some database loads. - config IOSCHED_DEADLINE tristate "Deadline I/O scheduler" default y ---help--- - The deadline I/O scheduler is simple and compact, and is often as - good as the anticipatory I/O scheduler, and in some database - workloads, better. In the case of a single process performing I/O to - a disk at any one time, its behaviour is almost identical to the - anticipatory I/O scheduler and so is a good choice. + The deadline I/O scheduler is simple and compact. It will provide + CSCAN service with FIFO expiration of requests, switching to + a new point in the service tree and doing a batch of IO from there + in case of expiry. config IOSCHED_CFQ tristate "CFQ I/O scheduler" @@ -37,9 +27,28 @@ config IOSCHED_CFQ ---help--- The CFQ I/O scheduler tries to distribute bandwidth equally among all processes in the system. It should provide a fair - working environment, suitable for desktop systems. + and low latency working environment, suitable for both desktop + and server systems. + This is the default I/O scheduler. +config CFQ_GROUP_IOSCHED + bool "CFQ Group Scheduling support" + depends on IOSCHED_CFQ && CGROUPS + select BLK_CGROUP + default n + ---help--- + Enable group IO scheduling in CFQ. + +config DEBUG_CFQ_IOSCHED + bool "Debug CFQ Scheduling" + depends on CFQ_GROUP_IOSCHED + select DEBUG_BLK_CGROUP + default n + ---help--- + Enable CFQ IO scheduling debugging in CFQ. Currently it makes + blktrace output more verbose. + choice prompt "Default I/O scheduler" default DEFAULT_CFQ @@ -47,9 +56,6 @@ choice Select the I/O scheduler which will be used by default for all block devices. - config DEFAULT_AS - bool "Anticipatory" if IOSCHED_AS=y - config DEFAULT_DEADLINE bool "Deadline" if IOSCHED_DEADLINE=y @@ -63,7 +69,6 @@ endchoice config DEFAULT_IOSCHED string - default "anticipatory" if DEFAULT_AS default "deadline" if DEFAULT_DEADLINE default "cfq" if DEFAULT_CFQ default "noop" if DEFAULT_NOOP diff --git a/block/Makefile b/block/Makefile index ba74ca6bfa14..cb2d515ebd6e 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,8 +8,8 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o +obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o -obj-$(CONFIG_IOSCHED_AS) += as-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o diff --git a/block/as-iosched.c b/block/as-iosched.c deleted file mode 100644 index ce8ba57c6557..000000000000 --- a/block/as-iosched.c +++ /dev/null @@ -1,1520 +0,0 @@ -/* - * Anticipatory & deadline i/o scheduler. - * - * Copyright (C) 2002 Jens Axboe - * Nick Piggin - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * See Documentation/block/as-iosched.txt - */ - -/* - * max time before a read is submitted. - */ -#define default_read_expire (HZ / 8) - -/* - * ditto for writes, these limits are not hard, even - * if the disk is capable of satisfying them. - */ -#define default_write_expire (HZ / 4) - -/* - * read_batch_expire describes how long we will allow a stream of reads to - * persist before looking to see whether it is time to switch over to writes. - */ -#define default_read_batch_expire (HZ / 2) - -/* - * write_batch_expire describes how long we want a stream of writes to run for. - * This is not a hard limit, but a target we set for the auto-tuning thingy. - * See, the problem is: we can send a lot of writes to disk cache / TCQ in - * a short amount of time... - */ -#define default_write_batch_expire (HZ / 8) - -/* - * max time we may wait to anticipate a read (default around 6ms) - */ -#define default_antic_expire ((HZ / 150) ? HZ / 150 : 1) - -/* - * Keep track of up to 20ms thinktimes. We can go as big as we like here, - * however huge values tend to interfere and not decay fast enough. A program - * might be in a non-io phase of operation. Waiting on user input for example, - * or doing a lengthy computation. A small penalty can be justified there, and - * will still catch out those processes that constantly have large thinktimes. - */ -#define MAX_THINKTIME (HZ/50UL) - -/* Bits in as_io_context.state */ -enum as_io_states { - AS_TASK_RUNNING=0, /* Process has not exited */ - AS_TASK_IOSTARTED, /* Process has started some IO */ - AS_TASK_IORUNNING, /* Process has completed some IO */ -}; - -enum anticipation_status { - ANTIC_OFF=0, /* Not anticipating (normal operation) */ - ANTIC_WAIT_REQ, /* The last read has not yet completed */ - ANTIC_WAIT_NEXT, /* Currently anticipating a request vs - last read (which has completed) */ - ANTIC_FINISHED, /* Anticipating but have found a candidate - * or timed out */ -}; - -struct as_data { - /* - * run time data - */ - - struct request_queue *q; /* the "owner" queue */ - - /* - * requests (as_rq s) are present on both sort_list and fifo_list - */ - struct rb_root sort_list[2]; - struct list_head fifo_list[2]; - - struct request *next_rq[2]; /* next in sort order */ - sector_t last_sector[2]; /* last SYNC & ASYNC sectors */ - - unsigned long exit_prob; /* probability a task will exit while - being waited on */ - unsigned long exit_no_coop; /* probablility an exited task will - not be part of a later cooperating - request */ - unsigned long new_ttime_total; /* mean thinktime on new proc */ - unsigned long new_ttime_mean; - u64 new_seek_total; /* mean seek on new proc */ - sector_t new_seek_mean; - - unsigned long current_batch_expires; - unsigned long last_check_fifo[2]; - int changed_batch; /* 1: waiting for old batch to end */ - int new_batch; /* 1: waiting on first read complete */ - int batch_data_dir; /* current batch SYNC / ASYNC */ - int write_batch_count; /* max # of reqs in a write batch */ - int current_write_count; /* how many requests left this batch */ - int write_batch_idled; /* has the write batch gone idle? */ - - enum anticipation_status antic_status; - unsigned long antic_start; /* jiffies: when it started */ - struct timer_list antic_timer; /* anticipatory scheduling timer */ - struct work_struct antic_work; /* Deferred unplugging */ - struct io_context *io_context; /* Identify the expected process */ - int ioc_finished; /* IO associated with io_context is finished */ - int nr_dispatched; - - /* - * settings that change how the i/o scheduler behaves - */ - unsigned long fifo_expire[2]; - unsigned long batch_expire[2]; - unsigned long antic_expire; -}; - -/* - * per-request data. - */ -enum arq_state { - AS_RQ_NEW=0, /* New - not referenced and not on any lists */ - AS_RQ_QUEUED, /* In the request queue. It belongs to the - scheduler */ - AS_RQ_DISPATCHED, /* On the dispatch list. It belongs to the - driver now */ - AS_RQ_PRESCHED, /* Debug poisoning for requests being used */ - AS_RQ_REMOVED, - AS_RQ_MERGED, - AS_RQ_POSTSCHED, /* when they shouldn't be */ -}; - -#define RQ_IOC(rq) ((struct io_context *) (rq)->elevator_private) -#define RQ_STATE(rq) ((enum arq_state)(rq)->elevator_private2) -#define RQ_SET_STATE(rq, state) ((rq)->elevator_private2 = (void *) state) - -static DEFINE_PER_CPU(unsigned long, as_ioc_count); -static struct completion *ioc_gone; -static DEFINE_SPINLOCK(ioc_gone_lock); - -static void as_move_to_dispatch(struct as_data *ad, struct request *rq); -static void as_antic_stop(struct as_data *ad); - -/* - * IO Context helper functions - */ - -/* Called to deallocate the as_io_context */ -static void free_as_io_context(struct as_io_context *aic) -{ - kfree(aic); - elv_ioc_count_dec(as_ioc_count); - if (ioc_gone) { - /* - * AS scheduler is exiting, grab exit lock and check - * the pending io context count. If it hits zero, - * complete ioc_gone and set it back to NULL. - */ - spin_lock(&ioc_gone_lock); - if (ioc_gone && !elv_ioc_count_read(as_ioc_count)) { - complete(ioc_gone); - ioc_gone = NULL; - } - spin_unlock(&ioc_gone_lock); - } -} - -static void as_trim(struct io_context *ioc) -{ - spin_lock_irq(&ioc->lock); - if (ioc->aic) - free_as_io_context(ioc->aic); - ioc->aic = NULL; - spin_unlock_irq(&ioc->lock); -} - -/* Called when the task exits */ -static void exit_as_io_context(struct as_io_context *aic) -{ - WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state)); - clear_bit(AS_TASK_RUNNING, &aic->state); -} - -static struct as_io_context *alloc_as_io_context(void) -{ - struct as_io_context *ret; - - ret = kmalloc(sizeof(*ret), GFP_ATOMIC); - if (ret) { - ret->dtor = free_as_io_context; - ret->exit = exit_as_io_context; - ret->state = 1 << AS_TASK_RUNNING; - atomic_set(&ret->nr_queued, 0); - atomic_set(&ret->nr_dispatched, 0); - spin_lock_init(&ret->lock); - ret->ttime_total = 0; - ret->ttime_samples = 0; - ret->ttime_mean = 0; - ret->seek_total = 0; - ret->seek_samples = 0; - ret->seek_mean = 0; - elv_ioc_count_inc(as_ioc_count); - } - - return ret; -} - -/* - * If the current task has no AS IO context then create one and initialise it. - * Then take a ref on the task's io context and return it. - */ -static struct io_context *as_get_io_context(int node) -{ - struct io_context *ioc = get_io_context(GFP_ATOMIC, node); - if (ioc && !ioc->aic) { - ioc->aic = alloc_as_io_context(); - if (!ioc->aic) { - put_io_context(ioc); - ioc = NULL; - } - } - return ioc; -} - -static void as_put_io_context(struct request *rq) -{ - struct as_io_context *aic; - - if (unlikely(!RQ_IOC(rq))) - return; - - aic = RQ_IOC(rq)->aic; - - if (rq_is_sync(rq) && aic) { - unsigned long flags; - - spin_lock_irqsave(&aic->lock, flags); - set_bit(AS_TASK_IORUNNING, &aic->state); - aic->last_end_request = jiffies; - spin_unlock_irqrestore(&aic->lock, flags); - } - - put_io_context(RQ_IOC(rq)); -} - -/* - * rb tree support functions - */ -#define RQ_RB_ROOT(ad, rq) (&(ad)->sort_list[rq_is_sync((rq))]) - -static void as_add_rq_rb(struct as_data *ad, struct request *rq) -{ - struct request *alias; - - while ((unlikely(alias = elv_rb_add(RQ_RB_ROOT(ad, rq), rq)))) { - as_move_to_dispatch(ad, alias); - as_antic_stop(ad); - } -} - -static inline void as_del_rq_rb(struct as_data *ad, struct request *rq) -{ - elv_rb_del(RQ_RB_ROOT(ad, rq), rq); -} - -/* - * IO Scheduler proper - */ - -#define MAXBACK (1024 * 1024) /* - * Maximum distance the disk will go backward - * for a request. - */ - -#define BACK_PENALTY 2 - -/* - * as_choose_req selects the preferred one of two requests of the same data_dir - * ignoring time - eg. timeouts, which is the job of as_dispatch_request - */ -static struct request * -as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2) -{ - int data_dir; - sector_t last, s1, s2, d1, d2; - int r1_wrap=0, r2_wrap=0; /* requests are behind the disk head */ - const sector_t maxback = MAXBACK; - - if (rq1 == NULL || rq1 == rq2) - return rq2; - if (rq2 == NULL) - return rq1; - - data_dir = rq_is_sync(rq1); - - last = ad->last_sector[data_dir]; - s1 = blk_rq_pos(rq1); - s2 = blk_rq_pos(rq2); - - BUG_ON(data_dir != rq_is_sync(rq2)); - - /* - * Strict one way elevator _except_ in the case where we allow - * short backward seeks which are biased as twice the cost of a - * similar forward seek. - */ - if (s1 >= last) - d1 = s1 - last; - else if (s1+maxback >= last) - d1 = (last - s1)*BACK_PENALTY; - else { - r1_wrap = 1; - d1 = 0; /* shut up, gcc */ - } - - if (s2 >= last) - d2 = s2 - last; - else if (s2+maxback >= last) - d2 = (last - s2)*BACK_PENALTY; - else { - r2_wrap = 1; - d2 = 0; - } - - /* Found required data */ - if (!r1_wrap && r2_wrap) - return rq1; - else if (!r2_wrap && r1_wrap) - return rq2; - else if (r1_wrap && r2_wrap) { - /* both behind the head */ - if (s1 <= s2) - return rq1; - else - return rq2; - } - - /* Both requests in front of the head */ - if (d1 < d2) - return rq1; - else if (d2 < d1) - return rq2; - else { - if (s1 >= s2) - return rq1; - else - return rq2; - } -} - -/* - * as_find_next_rq finds the next request after @prev in elevator order. - * this with as_choose_req form the basis for how the scheduler chooses - * what request to process next. Anticipation works on top of this. - */ -static struct request * -as_find_next_rq(struct as_data *ad, struct request *last) -{ - struct rb_node *rbnext = rb_next(&last->rb_node); - struct rb_node *rbprev = rb_prev(&last->rb_node); - struct request *next = NULL, *prev = NULL; - - BUG_ON(RB_EMPTY_NODE(&last->rb_node)); - - if (rbprev) - prev = rb_entry_rq(rbprev); - - if (rbnext) - next = rb_entry_rq(rbnext); - else { - const int data_dir = rq_is_sync(last); - - rbnext = rb_first(&ad->sort_list[data_dir]); - if (rbnext && rbnext != &last->rb_node) - next = rb_entry_rq(rbnext); - } - - return as_choose_req(ad, next, prev); -} - -/* - * anticipatory scheduling functions follow - */ - -/* - * as_antic_expired tells us when we have anticipated too long. - * The funny "absolute difference" math on the elapsed time is to handle - * jiffy wraps, and disks which have been idle for 0x80000000 jiffies. - */ -static int as_antic_expired(struct as_data *ad) -{ - long delta_jif; - - delta_jif = jiffies - ad->antic_start; - if (unlikely(delta_jif < 0)) - delta_jif = -delta_jif; - if (delta_jif < ad->antic_expire) - return 0; - - return 1; -} - -/* - * as_antic_waitnext starts anticipating that a nice request will soon be - * submitted. See also as_antic_waitreq - */ -static void as_antic_waitnext(struct as_data *ad) -{ - unsigned long timeout; - - BUG_ON(ad->antic_status != ANTIC_OFF - && ad->antic_status != ANTIC_WAIT_REQ); - - timeout = ad->antic_start + ad->antic_expire; - - mod_timer(&ad->antic_timer, timeout); - - ad->antic_status = ANTIC_WAIT_NEXT; -} - -/* - * as_antic_waitreq starts anticipating. We don't start timing the anticipation - * until the request that we're anticipating on has finished. This means we - * are timing from when the candidate process wakes up hopefully. - */ -static void as_antic_waitreq(struct as_data *ad) -{ - BUG_ON(ad->antic_status == ANTIC_FINISHED); - if (ad->antic_status == ANTIC_OFF) { - if (!ad->io_context || ad->ioc_finished) - as_antic_waitnext(ad); - else - ad->antic_status = ANTIC_WAIT_REQ; - } -} - -/* - * This is called directly by the functions in this file to stop anticipation. - * We kill the timer and schedule a call to the request_fn asap. - */ -static void as_antic_stop(struct as_data *ad) -{ - int status = ad->antic_status; - - if (status == ANTIC_WAIT_REQ || status == ANTIC_WAIT_NEXT) { - if (status == ANTIC_WAIT_NEXT) - del_timer(&ad->antic_timer); - ad->antic_status = ANTIC_FINISHED; - /* see as_work_handler */ - kblockd_schedule_work(ad->q, &ad->antic_work); - } -} - -/* - * as_antic_timeout is the timer function set by as_antic_waitnext. - */ -static void as_antic_timeout(unsigned long data) -{ - struct request_queue *q = (struct request_queue *)data; - struct as_data *ad = q->elevator->elevator_data; - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - if (ad->antic_status == ANTIC_WAIT_REQ - || ad->antic_status == ANTIC_WAIT_NEXT) { - struct as_io_context *aic; - spin_lock(&ad->io_context->lock); - aic = ad->io_context->aic; - - ad->antic_status = ANTIC_FINISHED; - kblockd_schedule_work(q, &ad->antic_work); - - if (aic->ttime_samples == 0) { - /* process anticipated on has exited or timed out*/ - ad->exit_prob = (7*ad->exit_prob + 256)/8; - } - if (!test_bit(AS_TASK_RUNNING, &aic->state)) { - /* process not "saved" by a cooperating request */ - ad->exit_no_coop = (7*ad->exit_no_coop + 256)/8; - } - spin_unlock(&ad->io_context->lock); - } - spin_unlock_irqrestore(q->queue_lock, flags); -} - -static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic, - unsigned long ttime) -{ - /* fixed point: 1.0 == 1<<8 */ - if (aic->ttime_samples == 0) { - ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8; - ad->new_ttime_mean = ad->new_ttime_total / 256; - - ad->exit_prob = (7*ad->exit_prob)/8; - } - aic->ttime_samples = (7*aic->ttime_samples + 256) / 8; - aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8; - aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples; -} - -static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic, - sector_t sdist) -{ - u64 total; - - if (aic->seek_samples == 0) { - ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8; - ad->new_seek_mean = ad->new_seek_total / 256; - } - - /* - * Don't allow the seek distance to get too large from the - * odd fragment, pagein, etc - */ - if (aic->seek_samples <= 60) /* second&third seek */ - sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024); - else - sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*64); - - aic->seek_samples = (7*aic->seek_samples + 256) / 8; - aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8; - total = aic->seek_total + (aic->seek_samples/2); - do_div(total, aic->seek_samples); - aic->seek_mean = (sector_t)total; -} - -/* - * as_update_iohist keeps a decaying histogram of IO thinktimes, and - * updates @aic->ttime_mean based on that. It is called when a new - * request is queued. - */ -static void as_update_iohist(struct as_data *ad, struct as_io_context *aic, - struct request *rq) -{ - int data_dir = rq_is_sync(rq); - unsigned long thinktime = 0; - sector_t seek_dist; - - if (aic == NULL) - return; - - if (data_dir == BLK_RW_SYNC) { - unsigned long in_flight = atomic_read(&aic->nr_queued) - + atomic_read(&aic->nr_dispatched); - spin_lock(&aic->lock); - if (test_bit(AS_TASK_IORUNNING, &aic->state) || - test_bit(AS_TASK_IOSTARTED, &aic->state)) { - /* Calculate read -> read thinktime */ - if (test_bit(AS_TASK_IORUNNING, &aic->state) - && in_flight == 0) { - thinktime = jiffies - aic->last_end_request; - thinktime = min(thinktime, MAX_THINKTIME-1); - } - as_update_thinktime(ad, aic, thinktime); - - /* Calculate read -> read seek distance */ - if (aic->last_request_pos < blk_rq_pos(rq)) - seek_dist = blk_rq_pos(rq) - - aic->last_request_pos; - else - seek_dist = aic->last_request_pos - - blk_rq_pos(rq); - as_update_seekdist(ad, aic, seek_dist); - } - aic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); - set_bit(AS_TASK_IOSTARTED, &aic->state); - spin_unlock(&aic->lock); - } -} - -/* - * as_close_req decides if one request is considered "close" to the - * previous one issued. - */ -static int as_close_req(struct as_data *ad, struct as_io_context *aic, - struct request *rq) -{ - unsigned long delay; /* jiffies */ - sector_t last = ad->last_sector[ad->batch_data_dir]; - sector_t next = blk_rq_pos(rq); - sector_t delta; /* acceptable close offset (in sectors) */ - sector_t s; - - if (ad->antic_status == ANTIC_OFF || !ad->ioc_finished) - delay = 0; - else - delay = jiffies - ad->antic_start; - - if (delay == 0) - delta = 8192; - else if (delay <= (20 * HZ / 1000) && delay <= ad->antic_expire) - delta = 8192 << delay; - else - return 1; - - if ((last <= next + (delta>>1)) && (next <= last + delta)) - return 1; - - if (last < next) - s = next - last; - else - s = last - next; - - if (aic->seek_samples == 0) { - /* - * Process has just started IO. Use past statistics to - * gauge success possibility - */ - if (ad->new_seek_mean > s) { - /* this request is better than what we're expecting */ - return 1; - } - - } else { - if (aic->seek_mean > s) { - /* this request is better than what we're expecting */ - return 1; - } - } - - return 0; -} - -/* - * as_can_break_anticipation returns true if we have been anticipating this - * request. - * - * It also returns true if the process against which we are anticipating - * submits a write - that's presumably an fsync, O_SYNC write, etc. We want to - * dispatch it ASAP, because we know that application will not be submitting - * any new reads. - * - * If the task which has submitted the request has exited, break anticipation. - * - * If this task has queued some other IO, do not enter enticipation. - */ -static int as_can_break_anticipation(struct as_data *ad, struct request *rq) -{ - struct io_context *ioc; - struct as_io_context *aic; - - ioc = ad->io_context; - BUG_ON(!ioc); - spin_lock(&ioc->lock); - - if (rq && ioc == RQ_IOC(rq)) { - /* request from same process */ - spin_unlock(&ioc->lock); - return 1; - } - - if (ad->ioc_finished && as_antic_expired(ad)) { - /* - * In this situation status should really be FINISHED, - * however the timer hasn't had the chance to run yet. - */ - spin_unlock(&ioc->lock); - return 1; - } - - aic = ioc->aic; - if (!aic) { - spin_unlock(&ioc->lock); - return 0; - } - - if (atomic_read(&aic->nr_queued) > 0) { - /* process has more requests queued */ - spin_unlock(&ioc->lock); - return 1; - } - - if (atomic_read(&aic->nr_dispatched) > 0) { - /* process has more requests dispatched */ - spin_unlock(&ioc->lock); - return 1; - } - - if (rq && rq_is_sync(rq) && as_close_req(ad, aic, rq)) { - /* - * Found a close request that is not one of ours. - * - * This makes close requests from another process update - * our IO history. Is generally useful when there are - * two or more cooperating processes working in the same - * area. - */ - if (!test_bit(AS_TASK_RUNNING, &aic->state)) { - if (aic->ttime_samples == 0) - ad->exit_prob = (7*ad->exit_prob + 256)/8; - - ad->exit_no_coop = (7*ad->exit_no_coop)/8; - } - - as_update_iohist(ad, aic, rq); - spin_unlock(&ioc->lock); - return 1; - } - - if (!test_bit(AS_TASK_RUNNING, &aic->state)) { - /* process anticipated on has exited */ - if (aic->ttime_samples == 0) - ad->exit_prob = (7*ad->exit_prob + 256)/8; - - if (ad->exit_no_coop > 128) { - spin_unlock(&ioc->lock); - return 1; - } - } - - if (aic->ttime_samples == 0) { - if (ad->new_ttime_mean > ad->antic_expire) { - spin_unlock(&ioc->lock); - return 1; - } - if (ad->exit_prob * ad->exit_no_coop > 128*256) { - spin_unlock(&ioc->lock); - return 1; - } - } else if (aic->ttime_mean > ad->antic_expire) { - /* the process thinks too much between requests */ - spin_unlock(&ioc->lock); - return 1; - } - spin_unlock(&ioc->lock); - return 0; -} - -/* - * as_can_anticipate indicates whether we should either run rq - * or keep anticipating a better request. - */ -static int as_can_anticipate(struct as_data *ad, struct request *rq) -{ -#if 0 /* disable for now, we need to check tag level as well */ - /* - * SSD device without seek penalty, disable idling - */ - if (blk_queue_nonrot(ad->q)) axman - return 0; -#endif - - if (!ad->io_context) - /* - * Last request submitted was a write - */ - return 0; - - if (ad->antic_status == ANTIC_FINISHED) - /* - * Don't restart if we have just finished. Run the next request - */ - return 0; - - if (as_can_break_anticipation(ad, rq)) - /* - * This request is a good candidate. Don't keep anticipating, - * run it. - */ - return 0; - - /* - * OK from here, we haven't finished, and don't have a decent request! - * Status is either ANTIC_OFF so start waiting, - * ANTIC_WAIT_REQ so continue waiting for request to finish - * or ANTIC_WAIT_NEXT so continue waiting for an acceptable request. - */ - - return 1; -} - -/* - * as_update_rq must be called whenever a request (rq) is added to - * the sort_list. This function keeps caches up to date, and checks if the - * request might be one we are "anticipating" - */ -static void as_update_rq(struct as_data *ad, struct request *rq) -{ - const int data_dir = rq_is_sync(rq); - - /* keep the next_rq cache up to date */ - ad->next_rq[data_dir] = as_choose_req(ad, rq, ad->next_rq[data_dir]); - - /* - * have we been anticipating this request? - * or does it come from the same process as the one we are anticipating - * for? - */ - if (ad->antic_status == ANTIC_WAIT_REQ - || ad->antic_status == ANTIC_WAIT_NEXT) { - if (as_can_break_anticipation(ad, rq)) - as_antic_stop(ad); - } -} - -/* - * Gathers timings and resizes the write batch automatically - */ -static void update_write_batch(struct as_data *ad) -{ - unsigned long batch = ad->batch_expire[BLK_RW_ASYNC]; - long write_time; - - write_time = (jiffies - ad->current_batch_expires) + batch; - if (write_time < 0) - write_time = 0; - - if (write_time > batch && !ad->write_batch_idled) { - if (write_time > batch * 3) - ad->write_batch_count /= 2; - else - ad->write_batch_count--; - } else if (write_time < batch && ad->current_write_count == 0) { - if (batch > write_time * 3) - ad->write_batch_count *= 2; - else - ad->write_batch_count++; - } - - if (ad->write_batch_count < 1) - ad->write_batch_count = 1; -} - -/* - * as_completed_request is to be called when a request has completed and - * returned something to the requesting process, be it an error or data. - */ -static void as_completed_request(struct request_queue *q, struct request *rq) -{ - struct as_data *ad = q->elevator->elevator_data; - - WARN_ON(!list_empty(&rq->queuelist)); - - if (RQ_STATE(rq) != AS_RQ_REMOVED) { - WARN(1, "rq->state %d\n", RQ_STATE(rq)); - goto out; - } - - if (ad->changed_batch && ad->nr_dispatched == 1) { - ad->current_batch_expires = jiffies + - ad->batch_expire[ad->batch_data_dir]; - kblockd_schedule_work(q, &ad->antic_work); - ad->changed_batch = 0; - - if (ad->batch_data_dir == BLK_RW_SYNC) - ad->new_batch = 1; - } - WARN_ON(ad->nr_dispatched == 0); - ad->nr_dispatched--; - - /* - * Start counting the batch from when a request of that direction is - * actually serviced. This should help devices with big TCQ windows - * and writeback caches - */ - if (ad->new_batch && ad->batch_data_dir == rq_is_sync(rq)) { - update_write_batch(ad); - ad->current_batch_expires = jiffies + - ad->batch_expire[BLK_RW_SYNC]; - ad->new_batch = 0; - } - - if (ad->io_context == RQ_IOC(rq) && ad->io_context) { - ad->antic_start = jiffies; - ad->ioc_finished = 1; - if (ad->antic_status == ANTIC_WAIT_REQ) { - /* - * We were waiting on this request, now anticipate - * the next one - */ - as_antic_waitnext(ad); - } - } - - as_put_io_context(rq); -out: - RQ_SET_STATE(rq, AS_RQ_POSTSCHED); -} - -/* - * as_remove_queued_request removes a request from the pre dispatch queue - * without updating refcounts. It is expected the caller will drop the - * reference unless it replaces the request at somepart of the elevator - * (ie. the dispatch queue) - */ -static void as_remove_queued_request(struct request_queue *q, - struct request *rq) -{ - const int data_dir = rq_is_sync(rq); - struct as_data *ad = q->elevator->elevator_data; - struct io_context *ioc; - - WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED); - - ioc = RQ_IOC(rq); - if (ioc && ioc->aic) { - BUG_ON(!atomic_read(&ioc->aic->nr_queued)); - atomic_dec(&ioc->aic->nr_queued); - } - - /* - * Update the "next_rq" cache if we are about to remove its - * entry - */ - if (ad->next_rq[data_dir] == rq) - ad->next_rq[data_dir] = as_find_next_rq(ad, rq); - - rq_fifo_clear(rq); - as_del_rq_rb(ad, rq); -} - -/* - * as_fifo_expired returns 0 if there are no expired requests on the fifo, - * 1 otherwise. It is ratelimited so that we only perform the check once per - * `fifo_expire' interval. Otherwise a large number of expired requests - * would create a hopeless seekstorm. - * - * See as_antic_expired comment. - */ -static int as_fifo_expired(struct as_data *ad, int adir) -{ - struct request *rq; - long delta_jif; - - delta_jif = jiffies - ad->last_check_fifo[adir]; - if (unlikely(delta_jif < 0)) - delta_jif = -delta_jif; - if (delta_jif < ad->fifo_expire[adir]) - return 0; - - ad->last_check_fifo[adir] = jiffies; - - if (list_empty(&ad->fifo_list[adir])) - return 0; - - rq = rq_entry_fifo(ad->fifo_list[adir].next); - - return time_after(jiffies, rq_fifo_time(rq)); -} - -/* - * as_batch_expired returns true if the current batch has expired. A batch - * is a set of reads or a set of writes. - */ -static inline int as_batch_expired(struct as_data *ad) -{ - if (ad->changed_batch || ad->new_batch) - return 0; - - if (ad->batch_data_dir == BLK_RW_SYNC) - /* TODO! add a check so a complete fifo gets written? */ - return time_after(jiffies, ad->current_batch_expires); - - return time_after(jiffies, ad->current_batch_expires) - || ad->current_write_count == 0; -} - -/* - * move an entry to dispatch queue - */ -static void as_move_to_dispatch(struct as_data *ad, struct request *rq) -{ - const int data_dir = rq_is_sync(rq); - - BUG_ON(RB_EMPTY_NODE(&rq->rb_node)); - - as_antic_stop(ad); - ad->antic_status = ANTIC_OFF; - - /* - * This has to be set in order to be correctly updated by - * as_find_next_rq - */ - ad->last_sector[data_dir] = blk_rq_pos(rq) + blk_rq_sectors(rq); - - if (data_dir == BLK_RW_SYNC) { - struct io_context *ioc = RQ_IOC(rq); - /* In case we have to anticipate after this */ - copy_io_context(&ad->io_context, &ioc); - } else { - if (ad->io_context) { - put_io_context(ad->io_context); - ad->io_context = NULL; - } - - if (ad->current_write_count != 0) - ad->current_write_count--; - } - ad->ioc_finished = 0; - - ad->next_rq[data_dir] = as_find_next_rq(ad, rq); - - /* - * take it off the sort and fifo list, add to dispatch queue - */ - as_remove_queued_request(ad->q, rq); - WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED); - - elv_dispatch_sort(ad->q, rq); - - RQ_SET_STATE(rq, AS_RQ_DISPATCHED); - if (RQ_IOC(rq) && RQ_IOC(rq)->aic) - atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched); - ad->nr_dispatched++; -} - -/* - * as_dispatch_request selects the best request according to - * read/write expire, batch expire, etc, and moves it to the dispatch - * queue. Returns 1 if a request was found, 0 otherwise. - */ -static int as_dispatch_request(struct request_queue *q, int force) -{ - struct as_data *ad = q->elevator->elevator_data; - const int reads = !list_empty(&ad->fifo_list[BLK_RW_SYNC]); - const int writes = !list_empty(&ad->fifo_list[BLK_RW_ASYNC]); - struct request *rq; - - if (unlikely(force)) { - /* - * Forced dispatch, accounting is useless. Reset - * accounting states and dump fifo_lists. Note that - * batch_data_dir is reset to BLK_RW_SYNC to avoid - * screwing write batch accounting as write batch - * accounting occurs on W->R transition. - */ - int dispatched = 0; - - ad->batch_data_dir = BLK_RW_SYNC; - ad->changed_batch = 0; - ad->new_batch = 0; - - while (ad->next_rq[BLK_RW_SYNC]) { - as_move_to_dispatch(ad, ad->next_rq[BLK_RW_SYNC]); - dispatched++; - } - ad->last_check_fifo[BLK_RW_SYNC] = jiffies; - - while (ad->next_rq[BLK_RW_ASYNC]) { - as_move_to_dispatch(ad, ad->next_rq[BLK_RW_ASYNC]); - dispatched++; - } - ad->last_check_fifo[BLK_RW_ASYNC] = jiffies; - - return dispatched; - } - - /* Signal that the write batch was uncontended, so we can't time it */ - if (ad->batch_data_dir == BLK_RW_ASYNC && !reads) { - if (ad->current_write_count == 0 || !writes) - ad->write_batch_idled = 1; - } - - if (!(reads || writes) - || ad->antic_status == ANTIC_WAIT_REQ - || ad->antic_status == ANTIC_WAIT_NEXT - || ad->changed_batch) - return 0; - - if (!(reads && writes && as_batch_expired(ad))) { - /* - * batch is still running or no reads or no writes - */ - rq = ad->next_rq[ad->batch_data_dir]; - - if (ad->batch_data_dir == BLK_RW_SYNC && ad->antic_expire) { - if (as_fifo_expired(ad, BLK_RW_SYNC)) - goto fifo_expired; - - if (as_can_anticipate(ad, rq)) { - as_antic_waitreq(ad); - return 0; - } - } - - if (rq) { - /* we have a "next request" */ - if (reads && !writes) - ad->current_batch_expires = - jiffies + ad->batch_expire[BLK_RW_SYNC]; - goto dispatch_request; - } - } - - /* - * at this point we are not running a batch. select the appropriate - * data direction (read / write) - */ - - if (reads) { - BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_SYNC])); - - if (writes && ad->batch_data_dir == BLK_RW_SYNC) - /* - * Last batch was a read, switch to writes - */ - goto dispatch_writes; - - if (ad->batch_data_dir == BLK_RW_ASYNC) { - WARN_ON(ad->new_batch); - ad->changed_batch = 1; - } - ad->batch_data_dir = BLK_RW_SYNC; - rq = rq_entry_fifo(ad->fifo_list[BLK_RW_SYNC].next); - ad->last_check_fifo[ad->batch_data_dir] = jiffies; - goto dispatch_request; - } - - /* - * the last batch was a read - */ - - if (writes) { -dispatch_writes: - BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_ASYNC])); - - if (ad->batch_data_dir == BLK_RW_SYNC) { - ad->changed_batch = 1; - - /* - * new_batch might be 1 when the queue runs out of - * reads. A subsequent submission of a write might - * cause a change of batch before the read is finished. - */ - ad->new_batch = 0; - } - ad->batch_data_dir = BLK_RW_ASYNC; - ad->current_write_count = ad->write_batch_count; - ad->write_batch_idled = 0; - rq = rq_entry_fifo(ad->fifo_list[BLK_RW_ASYNC].next); - ad->last_check_fifo[BLK_RW_ASYNC] = jiffies; - goto dispatch_request; - } - - BUG(); - return 0; - -dispatch_request: - /* - * If a request has expired, service it. - */ - - if (as_fifo_expired(ad, ad->batch_data_dir)) { -fifo_expired: - rq = rq_entry_fifo(ad->fifo_list[ad->batch_data_dir].next); - } - - if (ad->changed_batch) { - WARN_ON(ad->new_batch); - - if (ad->nr_dispatched) - return 0; - - if (ad->batch_data_dir == BLK_RW_ASYNC) - ad->current_batch_expires = jiffies + - ad->batch_expire[BLK_RW_ASYNC]; - else - ad->new_batch = 1; - - ad->changed_batch = 0; - } - - /* - * rq is the selected appropriate request. - */ - as_move_to_dispatch(ad, rq); - - return 1; -} - -/* - * add rq to rbtree and fifo - */ -static void as_add_request(struct request_queue *q, struct request *rq) -{ - struct as_data *ad = q->elevator->elevator_data; - int data_dir; - - RQ_SET_STATE(rq, AS_RQ_NEW); - - data_dir = rq_is_sync(rq); - - rq->elevator_private = as_get_io_context(q->node); - - if (RQ_IOC(rq)) { - as_update_iohist(ad, RQ_IOC(rq)->aic, rq); - atomic_inc(&RQ_IOC(rq)->aic->nr_queued); - } - - as_add_rq_rb(ad, rq); - - /* - * set expire time and add to fifo list - */ - rq_set_fifo_time(rq, jiffies + ad->fifo_expire[data_dir]); - list_add_tail(&rq->queuelist, &ad->fifo_list[data_dir]); - - as_update_rq(ad, rq); /* keep state machine up to date */ - RQ_SET_STATE(rq, AS_RQ_QUEUED); -} - -static void as_activate_request(struct request_queue *q, struct request *rq) -{ - WARN_ON(RQ_STATE(rq) != AS_RQ_DISPATCHED); - RQ_SET_STATE(rq, AS_RQ_REMOVED); - if (RQ_IOC(rq) && RQ_IOC(rq)->aic) - atomic_dec(&RQ_IOC(rq)->aic->nr_dispatched); -} - -static void as_deactivate_request(struct request_queue *q, struct request *rq) -{ - WARN_ON(RQ_STATE(rq) != AS_RQ_REMOVED); - RQ_SET_STATE(rq, AS_RQ_DISPATCHED); - if (RQ_IOC(rq) && RQ_IOC(rq)->aic) - atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched); -} - -/* - * as_queue_empty tells us if there are requests left in the device. It may - * not be the case that a driver can get the next request even if the queue - * is not empty - it is used in the block layer to check for plugging and - * merging opportunities - */ -static int as_queue_empty(struct request_queue *q) -{ - struct as_data *ad = q->elevator->elevator_data; - - return list_empty(&ad->fifo_list[BLK_RW_ASYNC]) - && list_empty(&ad->fifo_list[BLK_RW_SYNC]); -} - -static int -as_merge(struct request_queue *q, struct request **req, struct bio *bio) -{ - struct as_data *ad = q->elevator->elevator_data; - sector_t rb_key = bio->bi_sector + bio_sectors(bio); - struct request *__rq; - - /* - * check for front merge - */ - __rq = elv_rb_find(&ad->sort_list[bio_data_dir(bio)], rb_key); - if (__rq && elv_rq_merge_ok(__rq, bio)) { - *req = __rq; - return ELEVATOR_FRONT_MERGE; - } - - return ELEVATOR_NO_MERGE; -} - -static void as_merged_request(struct request_queue *q, struct request *req, - int type) -{ - struct as_data *ad = q->elevator->elevator_data; - - /* - * if the merge was a front merge, we need to reposition request - */ - if (type == ELEVATOR_FRONT_MERGE) { - as_del_rq_rb(ad, req); - as_add_rq_rb(ad, req); - /* - * Note! At this stage of this and the next function, our next - * request may not be optimal - eg the request may have "grown" - * behind the disk head. We currently don't bother adjusting. - */ - } -} - -static void as_merged_requests(struct request_queue *q, struct request *req, - struct request *next) -{ - /* - * if next expires before rq, assign its expire time to arq - * and move into next position (next will be deleted) in fifo - */ - if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { - if (time_before(rq_fifo_time(next), rq_fifo_time(req))) { - list_move(&req->queuelist, &next->queuelist); - rq_set_fifo_time(req, rq_fifo_time(next)); - } - } - - /* - * kill knowledge of next, this one is a goner - */ - as_remove_queued_request(q, next); - as_put_io_context(next); - - RQ_SET_STATE(next, AS_RQ_MERGED); -} - -/* - * This is executed in a "deferred" process context, by kblockd. It calls the - * driver's request_fn so the driver can submit that request. - * - * IMPORTANT! This guy will reenter the elevator, so set up all queue global - * state before calling, and don't rely on any state over calls. - * - * FIXME! dispatch queue is not a queue at all! - */ -static void as_work_handler(struct work_struct *work) -{ - struct as_data *ad = container_of(work, struct as_data, antic_work); - - blk_run_queue(ad->q); -} - -static int as_may_queue(struct request_queue *q, int rw) -{ - int ret = ELV_MQUEUE_MAY; - struct as_data *ad = q->elevator->elevator_data; - struct io_context *ioc; - if (ad->antic_status == ANTIC_WAIT_REQ || - ad->antic_status == ANTIC_WAIT_NEXT) { - ioc = as_get_io_context(q->node); - if (ad->io_context == ioc) - ret = ELV_MQUEUE_MUST; - put_io_context(ioc); - } - - return ret; -} - -static void as_exit_queue(struct elevator_queue *e) -{ - struct as_data *ad = e->elevator_data; - - del_timer_sync(&ad->antic_timer); - cancel_work_sync(&ad->antic_work); - - BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_SYNC])); - BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_ASYNC])); - - put_io_context(ad->io_context); - kfree(ad); -} - -/* - * initialize elevator private data (as_data). - */ -static void *as_init_queue(struct request_queue *q) -{ - struct as_data *ad; - - ad = kmalloc_node(sizeof(*ad), GFP_KERNEL | __GFP_ZERO, q->node); - if (!ad) - return NULL; - - ad->q = q; /* Identify what queue the data belongs to */ - - /* anticipatory scheduling helpers */ - ad->antic_timer.function = as_antic_timeout; - ad->antic_timer.data = (unsigned long)q; - init_timer(&ad->antic_timer); - INIT_WORK(&ad->antic_work, as_work_handler); - - INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_SYNC]); - INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_ASYNC]); - ad->sort_list[BLK_RW_SYNC] = RB_ROOT; - ad->sort_list[BLK_RW_ASYNC] = RB_ROOT; - ad->fifo_expire[BLK_RW_SYNC] = default_read_expire; - ad->fifo_expire[BLK_RW_ASYNC] = default_write_expire; - ad->antic_expire = default_antic_expire; - ad->batch_expire[BLK_RW_SYNC] = default_read_batch_expire; - ad->batch_expire[BLK_RW_ASYNC] = default_write_batch_expire; - - ad->current_batch_expires = jiffies + ad->batch_expire[BLK_RW_SYNC]; - ad->write_batch_count = ad->batch_expire[BLK_RW_ASYNC] / 10; - if (ad->write_batch_count < 2) - ad->write_batch_count = 2; - - return ad; -} - -/* - * sysfs parts below - */ - -static ssize_t -as_var_show(unsigned int var, char *page) -{ - return sprintf(page, "%d\n", var); -} - -static ssize_t -as_var_store(unsigned long *var, const char *page, size_t count) -{ - char *p = (char *) page; - - *var = simple_strtoul(p, &p, 10); - return count; -} - -static ssize_t est_time_show(struct elevator_queue *e, char *page) -{ - struct as_data *ad = e->elevator_data; - int pos = 0; - - pos += sprintf(page+pos, "%lu %% exit probability\n", - 100*ad->exit_prob/256); - pos += sprintf(page+pos, "%lu %% probability of exiting without a " - "cooperating process submitting IO\n", - 100*ad->exit_no_coop/256); - pos += sprintf(page+pos, "%lu ms new thinktime\n", ad->new_ttime_mean); - pos += sprintf(page+pos, "%llu sectors new seek distance\n", - (unsigned long long)ad->new_seek_mean); - - return pos; -} - -#define SHOW_FUNCTION(__FUNC, __VAR) \ -static ssize_t __FUNC(struct elevator_queue *e, char *page) \ -{ \ - struct as_data *ad = e->elevator_data; \ - return as_var_show(jiffies_to_msecs((__VAR)), (page)); \ -} -SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[BLK_RW_SYNC]); -SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[BLK_RW_ASYNC]); -SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire); -SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[BLK_RW_SYNC]); -SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[BLK_RW_ASYNC]); -#undef SHOW_FUNCTION - -#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \ -static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ -{ \ - struct as_data *ad = e->elevator_data; \ - int ret = as_var_store(__PTR, (page), count); \ - if (*(__PTR) < (MIN)) \ - *(__PTR) = (MIN); \ - else if (*(__PTR) > (MAX)) \ - *(__PTR) = (MAX); \ - *(__PTR) = msecs_to_jiffies(*(__PTR)); \ - return ret; \ -} -STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[BLK_RW_SYNC], 0, INT_MAX); -STORE_FUNCTION(as_write_expire_store, - &ad->fifo_expire[BLK_RW_ASYNC], 0, INT_MAX); -STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX); -STORE_FUNCTION(as_read_batch_expire_store, - &ad->batch_expire[BLK_RW_SYNC], 0, INT_MAX); -STORE_FUNCTION(as_write_batch_expire_store, - &ad->batch_expire[BLK_RW_ASYNC], 0, INT_MAX); -#undef STORE_FUNCTION - -#define AS_ATTR(name) \ - __ATTR(name, S_IRUGO|S_IWUSR, as_##name##_show, as_##name##_store) - -static struct elv_fs_entry as_attrs[] = { - __ATTR_RO(est_time), - AS_ATTR(read_expire), - AS_ATTR(write_expire), - AS_ATTR(antic_expire), - AS_ATTR(read_batch_expire), - AS_ATTR(write_batch_expire), - __ATTR_NULL -}; - -static struct elevator_type iosched_as = { - .ops = { - .elevator_merge_fn = as_merge, - .elevator_merged_fn = as_merged_request, - .elevator_merge_req_fn = as_merged_requests, - .elevator_dispatch_fn = as_dispatch_request, - .elevator_add_req_fn = as_add_request, - .elevator_activate_req_fn = as_activate_request, - .elevator_deactivate_req_fn = as_deactivate_request, - .elevator_queue_empty_fn = as_queue_empty, - .elevator_completed_req_fn = as_completed_request, - .elevator_former_req_fn = elv_rb_former_request, - .elevator_latter_req_fn = elv_rb_latter_request, - .elevator_may_queue_fn = as_may_queue, - .elevator_init_fn = as_init_queue, - .elevator_exit_fn = as_exit_queue, - .trim = as_trim, - }, - - .elevator_attrs = as_attrs, - .elevator_name = "anticipatory", - .elevator_owner = THIS_MODULE, -}; - -static int __init as_init(void) -{ - elv_register(&iosched_as); - - return 0; -} - -static void __exit as_exit(void) -{ - DECLARE_COMPLETION_ONSTACK(all_gone); - elv_unregister(&iosched_as); - ioc_gone = &all_gone; - /* ioc_gone's update must be visible before reading ioc_count */ - smp_wmb(); - if (elv_ioc_count_read(as_ioc_count)) - wait_for_completion(&all_gone); - synchronize_rcu(); -} - -module_init(as_init); -module_exit(as_exit); - -MODULE_AUTHOR("Nick Piggin"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("anticipatory IO scheduler"); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c new file mode 100644 index 000000000000..1fa2654db0a6 --- /dev/null +++ b/block/blk-cgroup.c @@ -0,0 +1,361 @@ +/* + * Common Block IO controller cgroup interface + * + * Based on ideas and code from CFQ, CFS and BFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2009 Vivek Goyal + * Nauman Rafique + */ +#include +#include +#include +#include +#include +#include "blk-cgroup.h" + +static DEFINE_SPINLOCK(blkio_list_lock); +static LIST_HEAD(blkio_list); + +struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT }; +EXPORT_SYMBOL_GPL(blkio_root_cgroup); + +bool blkiocg_css_tryget(struct blkio_cgroup *blkcg) +{ + if (!css_tryget(&blkcg->css)) + return false; + return true; +} +EXPORT_SYMBOL_GPL(blkiocg_css_tryget); + +void blkiocg_css_put(struct blkio_cgroup *blkcg) +{ + css_put(&blkcg->css); +} +EXPORT_SYMBOL_GPL(blkiocg_css_put); + +struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) +{ + return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id), + struct blkio_cgroup, css); +} +EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); + +void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, + unsigned long time, unsigned long sectors) +{ + blkg->time += time; + blkg->sectors += sectors; +} +EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats); + +void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, + struct blkio_group *blkg, void *key, dev_t dev) +{ + unsigned long flags; + + spin_lock_irqsave(&blkcg->lock, flags); + rcu_assign_pointer(blkg->key, key); + blkg->blkcg_id = css_id(&blkcg->css); + hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); + spin_unlock_irqrestore(&blkcg->lock, flags); +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* Need to take css reference ? */ + cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path)); +#endif + blkg->dev = dev; +} +EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group); + +static void __blkiocg_del_blkio_group(struct blkio_group *blkg) +{ + hlist_del_init_rcu(&blkg->blkcg_node); + blkg->blkcg_id = 0; +} + +/* + * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1 + * indicating that blk_group was unhashed by the time we got to it. + */ +int blkiocg_del_blkio_group(struct blkio_group *blkg) +{ + struct blkio_cgroup *blkcg; + unsigned long flags; + struct cgroup_subsys_state *css; + int ret = 1; + + rcu_read_lock(); + css = css_lookup(&blkio_subsys, blkg->blkcg_id); + if (!css) + goto out; + + blkcg = container_of(css, struct blkio_cgroup, css); + spin_lock_irqsave(&blkcg->lock, flags); + if (!hlist_unhashed(&blkg->blkcg_node)) { + __blkiocg_del_blkio_group(blkg); + ret = 0; + } + spin_unlock_irqrestore(&blkcg->lock, flags); +out: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group); + +/* called under rcu_read_lock(). */ +struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) +{ + struct blkio_group *blkg; + struct hlist_node *n; + void *__key; + + hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) { + __key = blkg->key; + if (__key == key) + return blkg; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(blkiocg_lookup_group); + +#define SHOW_FUNCTION(__VAR) \ +static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup, \ + struct cftype *cftype) \ +{ \ + struct blkio_cgroup *blkcg; \ + \ + blkcg = cgroup_to_blkio_cgroup(cgroup); \ + return (u64)blkcg->__VAR; \ +} + +SHOW_FUNCTION(weight); +#undef SHOW_FUNCTION + +static int +blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) +{ + struct blkio_cgroup *blkcg; + struct blkio_group *blkg; + struct hlist_node *n; + struct blkio_policy_type *blkiop; + + if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX) + return -EINVAL; + + blkcg = cgroup_to_blkio_cgroup(cgroup); + spin_lock_irq(&blkcg->lock); + blkcg->weight = (unsigned int)val; + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + spin_lock(&blkio_list_lock); + list_for_each_entry(blkiop, &blkio_list, list) + blkiop->ops.blkio_update_group_weight_fn(blkg, + blkcg->weight); + spin_unlock(&blkio_list_lock); + } + spin_unlock_irq(&blkcg->lock); + return 0; +} + +#define SHOW_FUNCTION_PER_GROUP(__VAR) \ +static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ + struct cftype *cftype, struct seq_file *m) \ +{ \ + struct blkio_cgroup *blkcg; \ + struct blkio_group *blkg; \ + struct hlist_node *n; \ + \ + if (!cgroup_lock_live_group(cgroup)) \ + return -ENODEV; \ + \ + blkcg = cgroup_to_blkio_cgroup(cgroup); \ + rcu_read_lock(); \ + hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\ + if (blkg->dev) \ + seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev), \ + MINOR(blkg->dev), blkg->__VAR); \ + } \ + rcu_read_unlock(); \ + cgroup_unlock(); \ + return 0; \ +} + +SHOW_FUNCTION_PER_GROUP(time); +SHOW_FUNCTION_PER_GROUP(sectors); +#ifdef CONFIG_DEBUG_BLK_CGROUP +SHOW_FUNCTION_PER_GROUP(dequeue); +#endif +#undef SHOW_FUNCTION_PER_GROUP + +#ifdef CONFIG_DEBUG_BLK_CGROUP +void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) +{ + blkg->dequeue += dequeue; +} +EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats); +#endif + +struct cftype blkio_files[] = { + { + .name = "weight", + .read_u64 = blkiocg_weight_read, + .write_u64 = blkiocg_weight_write, + }, + { + .name = "time", + .read_seq_string = blkiocg_time_read, + }, + { + .name = "sectors", + .read_seq_string = blkiocg_sectors_read, + }, +#ifdef CONFIG_DEBUG_BLK_CGROUP + { + .name = "dequeue", + .read_seq_string = blkiocg_dequeue_read, + }, +#endif +}; + +static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup) +{ + return cgroup_add_files(cgroup, subsys, blkio_files, + ARRAY_SIZE(blkio_files)); +} + +static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup) +{ + struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); + unsigned long flags; + struct blkio_group *blkg; + void *key; + struct blkio_policy_type *blkiop; + + rcu_read_lock(); +remove_entry: + spin_lock_irqsave(&blkcg->lock, flags); + + if (hlist_empty(&blkcg->blkg_list)) { + spin_unlock_irqrestore(&blkcg->lock, flags); + goto done; + } + + blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group, + blkcg_node); + key = rcu_dereference(blkg->key); + __blkiocg_del_blkio_group(blkg); + + spin_unlock_irqrestore(&blkcg->lock, flags); + + /* + * This blkio_group is being unlinked as associated cgroup is going + * away. Let all the IO controlling policies know about this event. + * + * Currently this is static call to one io controlling policy. Once + * we have more policies in place, we need some dynamic registration + * of callback function. + */ + spin_lock(&blkio_list_lock); + list_for_each_entry(blkiop, &blkio_list, list) + blkiop->ops.blkio_unlink_group_fn(key, blkg); + spin_unlock(&blkio_list_lock); + goto remove_entry; +done: + free_css_id(&blkio_subsys, &blkcg->css); + rcu_read_unlock(); + kfree(blkcg); +} + +static struct cgroup_subsys_state * +blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup) +{ + struct blkio_cgroup *blkcg, *parent_blkcg; + + if (!cgroup->parent) { + blkcg = &blkio_root_cgroup; + goto done; + } + + /* Currently we do not support hierarchy deeper than two level (0,1) */ + parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent); + if (css_depth(&parent_blkcg->css) > 0) + return ERR_PTR(-EINVAL); + + blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); + if (!blkcg) + return ERR_PTR(-ENOMEM); + + blkcg->weight = BLKIO_WEIGHT_DEFAULT; +done: + spin_lock_init(&blkcg->lock); + INIT_HLIST_HEAD(&blkcg->blkg_list); + + return &blkcg->css; +} + +/* + * We cannot support shared io contexts, as we have no mean to support + * two tasks with the same ioc in two different groups without major rework + * of the main cic data structures. For now we allow a task to change + * its cgroup only if it's the only owner of its ioc. + */ +static int blkiocg_can_attach(struct cgroup_subsys *subsys, + struct cgroup *cgroup, struct task_struct *tsk, + bool threadgroup) +{ + struct io_context *ioc; + int ret = 0; + + /* task_lock() is needed to avoid races with exit_io_context() */ + task_lock(tsk); + ioc = tsk->io_context; + if (ioc && atomic_read(&ioc->nr_tasks) > 1) + ret = -EINVAL; + task_unlock(tsk); + + return ret; +} + +static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup, + struct cgroup *prev, struct task_struct *tsk, + bool threadgroup) +{ + struct io_context *ioc; + + task_lock(tsk); + ioc = tsk->io_context; + if (ioc) + ioc->cgroup_changed = 1; + task_unlock(tsk); +} + +struct cgroup_subsys blkio_subsys = { + .name = "blkio", + .create = blkiocg_create, + .can_attach = blkiocg_can_attach, + .attach = blkiocg_attach, + .destroy = blkiocg_destroy, + .populate = blkiocg_populate, + .subsys_id = blkio_subsys_id, + .use_id = 1, +}; + +void blkio_policy_register(struct blkio_policy_type *blkiop) +{ + spin_lock(&blkio_list_lock); + list_add_tail(&blkiop->list, &blkio_list); + spin_unlock(&blkio_list_lock); +} +EXPORT_SYMBOL_GPL(blkio_policy_register); + +void blkio_policy_unregister(struct blkio_policy_type *blkiop) +{ + spin_lock(&blkio_list_lock); + list_del_init(&blkiop->list); + spin_unlock(&blkio_list_lock); +} +EXPORT_SYMBOL_GPL(blkio_policy_unregister); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h new file mode 100644 index 000000000000..4d316df863b4 --- /dev/null +++ b/block/blk-cgroup.h @@ -0,0 +1,127 @@ +#ifndef _BLK_CGROUP_H +#define _BLK_CGROUP_H +/* + * Common Block IO controller cgroup interface + * + * Based on ideas and code from CFQ, CFS and BFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2009 Vivek Goyal + * Nauman Rafique + */ + +#include + +#ifdef CONFIG_BLK_CGROUP + +struct blkio_cgroup { + struct cgroup_subsys_state css; + unsigned int weight; + spinlock_t lock; + struct hlist_head blkg_list; +}; + +struct blkio_group { + /* An rcu protected unique identifier for the group */ + void *key; + struct hlist_node blkcg_node; + unsigned short blkcg_id; +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* Store cgroup path */ + char path[128]; + /* How many times this group has been removed from service tree */ + unsigned long dequeue; +#endif + /* The device MKDEV(major, minor), this group has been created for */ + dev_t dev; + + /* total disk time and nr sectors dispatched by this group */ + unsigned long time; + unsigned long sectors; +}; + +extern bool blkiocg_css_tryget(struct blkio_cgroup *blkcg); +extern void blkiocg_css_put(struct blkio_cgroup *blkcg); + +typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg); +typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg, + unsigned int weight); + +struct blkio_policy_ops { + blkio_unlink_group_fn *blkio_unlink_group_fn; + blkio_update_group_weight_fn *blkio_update_group_weight_fn; +}; + +struct blkio_policy_type { + struct list_head list; + struct blkio_policy_ops ops; +}; + +/* Blkio controller policy registration */ +extern void blkio_policy_register(struct blkio_policy_type *); +extern void blkio_policy_unregister(struct blkio_policy_type *); + +#else + +struct blkio_group { +}; + +struct blkio_policy_type { +}; + +static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { } +static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { } + +#endif + +#define BLKIO_WEIGHT_MIN 100 +#define BLKIO_WEIGHT_MAX 1000 +#define BLKIO_WEIGHT_DEFAULT 500 + +#ifdef CONFIG_DEBUG_BLK_CGROUP +static inline char *blkg_path(struct blkio_group *blkg) +{ + return blkg->path; +} +void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue); +#else +static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } +static inline void blkiocg_update_blkio_group_dequeue_stats( + struct blkio_group *blkg, unsigned long dequeue) {} +#endif + +#ifdef CONFIG_BLK_CGROUP +extern struct blkio_cgroup blkio_root_cgroup; +extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup); +extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, + struct blkio_group *blkg, void *key, dev_t dev); +extern int blkiocg_del_blkio_group(struct blkio_group *blkg); +extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, + void *key); +void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, + unsigned long time, unsigned long sectors); +#else +struct cgroup; +static inline struct blkio_cgroup * +cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } + +static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, + struct blkio_group *blkg, void *key, dev_t dev) +{ +} + +static inline int +blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; } + +static inline struct blkio_group * +blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } +static inline void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, + unsigned long time, unsigned long sectors) +{ +} +#endif +#endif /* _BLK_CGROUP_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 71da5111120c..718897e6d37f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2358,6 +2358,25 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, rq->rq_disk = bio->bi_bdev->bd_disk; } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +/** + * rq_flush_dcache_pages - Helper function to flush all pages in a request + * @rq: the request to be flushed + * + * Description: + * Flush all pages in @rq. + */ +void rq_flush_dcache_pages(struct request *rq) +{ + struct req_iterator iter; + struct bio_vec *bvec; + + rq_for_each_segment(bvec, rq, iter) + flush_dcache_page(bvec->bv_page); +} +EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); +#endif + /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked diff --git a/block/blk-ioc.c b/block/blk-ioc.c index d4ed6000147d..cbdabb0dd6d7 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -66,22 +66,22 @@ static void cfq_exit(struct io_context *ioc) } /* Called by the exitting task */ -void exit_io_context(void) +void exit_io_context(struct task_struct *task) { struct io_context *ioc; - task_lock(current); - ioc = current->io_context; - current->io_context = NULL; - task_unlock(current); + task_lock(task); + ioc = task->io_context; + task->io_context = NULL; + task_unlock(task); if (atomic_dec_and_test(&ioc->nr_tasks)) { if (ioc->aic && ioc->aic->exit) ioc->aic->exit(ioc->aic); cfq_exit(ioc); - put_io_context(ioc); } + put_io_context(ioc); } struct io_context *alloc_io_context(gfp_t gfp_flags, int node) diff --git a/block/blk-settings.c b/block/blk-settings.c index 66d4aa8799b7..dd1f1e0e196f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -8,6 +8,7 @@ #include #include /* for max_pfn/max_low_pfn */ #include +#include #include "blk.h" @@ -96,7 +97,11 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_segment_size = MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; - lim->max_discard_sectors = SAFE_MAX_SECTORS; + lim->max_discard_sectors = 0; + lim->discard_granularity = 0; + lim->discard_alignment = 0; + lim->discard_misaligned = 0; + lim->discard_zeroes_data = -1; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -141,7 +146,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->nr_batching = BLK_BATCH_REQ; q->unplug_thresh = 4; /* hmm */ - q->unplug_delay = (3 * HZ) / 1000; /* 3 milliseconds */ + q->unplug_delay = msecs_to_jiffies(3); /* 3 milliseconds */ if (q->unplug_delay == 0) q->unplug_delay = 1; @@ -488,6 +493,16 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) } EXPORT_SYMBOL(blk_queue_stack_limits); +static unsigned int lcm(unsigned int a, unsigned int b) +{ + if (a && b) + return (a * b) / gcd(a, b); + else if (b) + return b; + + return a; +} + /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top) @@ -502,6 +517,10 @@ EXPORT_SYMBOL(blk_queue_stack_limits); int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset) { + int ret; + + ret = 0; + t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); @@ -526,12 +545,19 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->no_cluster |= b->no_cluster; + t->discard_zeroes_data &= b->discard_zeroes_data; /* Bottom device offset aligned? */ if (offset && (offset & (b->physical_block_size - 1)) != b->alignment_offset) { t->misaligned = 1; - return -1; + ret = -1; + } + + if (offset && + (offset & (b->discard_granularity - 1)) != b->discard_alignment) { + t->discard_misaligned = 1; + ret = -1; } /* If top has no alignment offset, inherit from bottom */ @@ -539,23 +565,26 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->alignment_offset = b->alignment_offset & (b->physical_block_size - 1); + if (!t->discard_alignment) + t->discard_alignment = + b->discard_alignment & (b->discard_granularity - 1); + /* Top device aligned on logical block boundary? */ if (t->alignment_offset & (t->logical_block_size - 1)) { t->misaligned = 1; - return -1; + ret = -1; } - /* Find lcm() of optimal I/O size */ - if (t->io_opt && b->io_opt) - t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt); - else if (b->io_opt) - t->io_opt = b->io_opt; + /* Find lcm() of optimal I/O size and granularity */ + t->io_opt = lcm(t->io_opt, b->io_opt); + t->discard_granularity = lcm(t->discard_granularity, + b->discard_granularity); /* Verify that optimal I/O size is a multiple of io_min */ if (t->io_min && t->io_opt % t->io_min) - return -1; + ret = -1; - return 0; + return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 8a6d81afb284..8606c9543fdd 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -126,6 +126,21 @@ static ssize_t queue_io_opt_show(struct request_queue *q, char *page) return queue_var_show(queue_io_opt(q), page); } +static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.discard_granularity, page); +} + +static ssize_t queue_discard_max_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.max_discard_sectors << 9, page); +} + +static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page) +{ + return queue_var_show(queue_discard_zeroes_data(q), page); +} + static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { @@ -293,6 +308,21 @@ static struct queue_sysfs_entry queue_io_opt_entry = { .show = queue_io_opt_show, }; +static struct queue_sysfs_entry queue_discard_granularity_entry = { + .attr = {.name = "discard_granularity", .mode = S_IRUGO }, + .show = queue_discard_granularity_show, +}; + +static struct queue_sysfs_entry queue_discard_max_entry = { + .attr = {.name = "discard_max_bytes", .mode = S_IRUGO }, + .show = queue_discard_max_show, +}; + +static struct queue_sysfs_entry queue_discard_zeroes_data_entry = { + .attr = {.name = "discard_zeroes_data", .mode = S_IRUGO }, + .show = queue_discard_zeroes_data_show, +}; + static struct queue_sysfs_entry queue_nonrot_entry = { .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR }, .show = queue_nonrot_show, @@ -328,6 +358,9 @@ static struct attribute *default_attrs[] = { &queue_physical_block_size_entry.attr, &queue_io_min_entry.attr, &queue_io_opt_entry.attr, + &queue_discard_granularity_entry.attr, + &queue_discard_max_entry.attr, + &queue_discard_zeroes_data_entry.attr, &queue_nonrot_entry.attr, &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, diff --git a/block/bsg.c b/block/bsg.c index 0676301f16d0..a9fd2d84b53a 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -197,7 +198,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, rq->cmd_len = hdr->request_len; rq->cmd_type = REQ_TYPE_BLOCK_PC; - rq->timeout = (hdr->timeout * HZ) / 1000; + rq->timeout = msecs_to_jiffies(hdr->timeout); if (!rq->timeout) rq->timeout = q->sg_timeout; if (!rq->timeout) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index aa1e9535e358..cfb0b2f5f63d 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -9,9 +9,11 @@ #include #include #include +#include #include #include #include +#include "blk-cgroup.h" /* * tunables @@ -27,6 +29,8 @@ static const int cfq_slice_sync = HZ / 10; static int cfq_slice_async = HZ / 25; static const int cfq_slice_async_rq = 2; static int cfq_slice_idle = HZ / 125; +static const int cfq_target_latency = HZ * 3/10; /* 300 ms */ +static const int cfq_hist_divisor = 4; /* * offset from end of service tree @@ -38,8 +42,15 @@ static int cfq_slice_idle = HZ / 125; */ #define CFQ_MIN_TT (2) +/* + * Allow merged cfqqs to perform this amount of seeky I/O before + * deciding to break the queues up again. + */ +#define CFQQ_COOP_TOUT (HZ) + #define CFQ_SLICE_SCALE (5) #define CFQ_HW_QUEUE_MIN (5) +#define CFQ_SERVICE_SHIFT 12 #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) @@ -57,6 +68,7 @@ static DEFINE_SPINLOCK(ioc_gone_lock); #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) #define sample_valid(samples) ((samples) > 80) +#define rb_entry_cfqg(node) rb_entry((node), struct cfq_group, rb_node) /* * Most of our rbtree usage is for sorting with min extraction, so @@ -67,8 +79,12 @@ static DEFINE_SPINLOCK(ioc_gone_lock); struct cfq_rb_root { struct rb_root rb; struct rb_node *left; + unsigned count; + u64 min_vdisktime; + struct rb_node *active; + unsigned total_weight; }; -#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, } +#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, } /* * Per process-grouping structure @@ -99,6 +115,11 @@ struct cfq_queue { /* fifo list of requests in sort_list */ struct list_head fifo; + /* time when queue got scheduled in to dispatch first request. */ + unsigned long dispatch_start; + unsigned int allocated_slice; + /* time when first request from queue completed and slice started. */ + unsigned long slice_start; unsigned long slice_end; long slice_resid; unsigned int slice_dispatch; @@ -112,7 +133,71 @@ struct cfq_queue { unsigned short ioprio, org_ioprio; unsigned short ioprio_class, org_ioprio_class; + unsigned int seek_samples; + u64 seek_total; + sector_t seek_mean; + sector_t last_request_pos; + unsigned long seeky_start; + pid_t pid; + + struct cfq_rb_root *service_tree; + struct cfq_queue *new_cfqq; + struct cfq_group *cfqg; + struct cfq_group *orig_cfqg; + /* Sectors dispatched in current dispatch round */ + unsigned long nr_sectors; +}; + +/* + * First index in the service_trees. + * IDLE is handled separately, so it has negative index + */ +enum wl_prio_t { + BE_WORKLOAD = 0, + RT_WORKLOAD = 1, + IDLE_WORKLOAD = 2, +}; + +/* + * Second index in the service_trees. + */ +enum wl_type_t { + ASYNC_WORKLOAD = 0, + SYNC_NOIDLE_WORKLOAD = 1, + SYNC_WORKLOAD = 2 +}; + +/* This is per cgroup per device grouping structure */ +struct cfq_group { + /* group service_tree member */ + struct rb_node rb_node; + + /* group service_tree key */ + u64 vdisktime; + unsigned int weight; + bool on_st; + + /* number of cfqq currently on this group */ + int nr_cfqq; + + /* Per group busy queus average. Useful for workload slice calc. */ + unsigned int busy_queues_avg[2]; + /* + * rr lists of queues with requests, onle rr for each priority class. + * Counts are embedded in the cfq_rb_root + */ + struct cfq_rb_root service_trees[2][3]; + struct cfq_rb_root service_tree_idle; + + unsigned long saved_workload_slice; + enum wl_type_t saved_workload; + enum wl_prio_t saved_serving_prio; + struct blkio_group blkg; +#ifdef CONFIG_CFQ_GROUP_IOSCHED + struct hlist_node cfqd_node; + atomic_t ref; +#endif }; /* @@ -120,11 +205,20 @@ struct cfq_queue { */ struct cfq_data { struct request_queue *queue; + /* Root service tree for cfq_groups */ + struct cfq_rb_root grp_service_tree; + struct cfq_group root_group; + /* Number of active cfq groups on group service tree */ + int nr_groups; /* - * rr list of queues with requests and the count of them + * The priority currently being served */ - struct cfq_rb_root service_tree; + enum wl_prio_t serving_prio; + enum wl_type_t serving_type; + unsigned long workload_expires; + struct cfq_group *serving_group; + bool noidle_tree_requires_idle; /* * Each priority tree is sorted by next_request position. These @@ -143,8 +237,14 @@ struct cfq_data { */ int rq_queued; int hw_tag; - int hw_tag_samples; - int rq_in_driver_peak; + /* + * hw_tag can be + * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection) + * 1 => NCQ is present (hw_tag_est_depth is the estimated max depth) + * 0 => no NCQ + */ + int hw_tag_est_depth; + unsigned int hw_tag_samples; /* * idle window management @@ -174,6 +274,7 @@ struct cfq_data { unsigned int cfq_slice_async_rq; unsigned int cfq_slice_idle; unsigned int cfq_latency; + unsigned int cfq_group_isolation; struct list_head cic_list; @@ -183,8 +284,28 @@ struct cfq_data { struct cfq_queue oom_cfqq; unsigned long last_end_sync_rq; + + /* List of cfq groups being managed on this device*/ + struct hlist_head cfqg_list; + struct rcu_head rcu; }; +static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd); + +static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg, + enum wl_prio_t prio, + enum wl_type_t type, + struct cfq_data *cfqd) +{ + if (!cfqg) + return NULL; + + if (prio == IDLE_WORKLOAD) + return &cfqg->service_tree_idle; + + return &cfqg->service_trees[prio][type]; +} + enum cfqq_state_flags { CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */ CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */ @@ -195,8 +316,10 @@ enum cfqq_state_flags { CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */ CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */ CFQ_CFQQ_FLAG_sync, /* synchronous queue */ - CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */ - CFQ_CFQQ_FLAG_coop_preempt, /* coop preempt */ + CFQ_CFQQ_FLAG_coop, /* cfqq is shared */ + CFQ_CFQQ_FLAG_deep, /* sync cfqq experienced large depth */ + CFQ_CFQQ_FLAG_wait_busy, /* Waiting for next request */ + CFQ_CFQQ_FLAG_wait_busy_done, /* Got new request. Expire the queue */ }; #define CFQ_CFQQ_FNS(name) \ @@ -223,14 +346,78 @@ CFQ_CFQQ_FNS(prio_changed); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); CFQ_CFQQ_FNS(coop); -CFQ_CFQQ_FNS(coop_preempt); +CFQ_CFQQ_FNS(deep); +CFQ_CFQQ_FNS(wait_busy); +CFQ_CFQQ_FNS(wait_busy_done); #undef CFQ_CFQQ_FNS +#ifdef CONFIG_DEBUG_CFQ_IOSCHED +#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ + blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \ + cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \ + blkg_path(&(cfqq)->cfqg->blkg), ##args); + +#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) \ + blk_add_trace_msg((cfqd)->queue, "%s " fmt, \ + blkg_path(&(cfqg)->blkg), ##args); \ + +#else #define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args) +#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do {} while (0); +#endif #define cfq_log(cfqd, fmt, args...) \ blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args) +/* Traverses through cfq group service trees */ +#define for_each_cfqg_st(cfqg, i, j, st) \ + for (i = 0; i <= IDLE_WORKLOAD; i++) \ + for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\ + : &cfqg->service_tree_idle; \ + (i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \ + (i == IDLE_WORKLOAD && j == 0); \ + j++, st = i < IDLE_WORKLOAD ? \ + &cfqg->service_trees[i][j]: NULL) \ + + +static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq) +{ + if (cfq_class_idle(cfqq)) + return IDLE_WORKLOAD; + if (cfq_class_rt(cfqq)) + return RT_WORKLOAD; + return BE_WORKLOAD; +} + + +static enum wl_type_t cfqq_type(struct cfq_queue *cfqq) +{ + if (!cfq_cfqq_sync(cfqq)) + return ASYNC_WORKLOAD; + if (!cfq_cfqq_idle_window(cfqq)) + return SYNC_NOIDLE_WORKLOAD; + return SYNC_WORKLOAD; +} + +static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl, + struct cfq_data *cfqd, + struct cfq_group *cfqg) +{ + if (wl == IDLE_WORKLOAD) + return cfqg->service_tree_idle.count; + + return cfqg->service_trees[wl][ASYNC_WORKLOAD].count + + cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count + + cfqg->service_trees[wl][SYNC_WORKLOAD].count; +} + +static inline int cfqg_busy_async_queues(struct cfq_data *cfqd, + struct cfq_group *cfqg) +{ + return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count + + cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count; +} + static void cfq_dispatch_insert(struct request_queue *, struct request *); static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool, struct io_context *, gfp_t); @@ -279,7 +466,7 @@ static int cfq_queue_empty(struct request_queue *q) { struct cfq_data *cfqd = q->elevator->elevator_data; - return !cfqd->busy_queues; + return !cfqd->rq_queued; } /* @@ -303,10 +490,110 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio); } +static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg) +{ + u64 d = delta << CFQ_SERVICE_SHIFT; + + d = d * BLKIO_WEIGHT_DEFAULT; + do_div(d, cfqg->weight); + return d; +} + +static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta > 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta < 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static void update_min_vdisktime(struct cfq_rb_root *st) +{ + u64 vdisktime = st->min_vdisktime; + struct cfq_group *cfqg; + + if (st->active) { + cfqg = rb_entry_cfqg(st->active); + vdisktime = cfqg->vdisktime; + } + + if (st->left) { + cfqg = rb_entry_cfqg(st->left); + vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime); + } + + st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime); +} + +/* + * get averaged number of queues of RT/BE priority. + * average is updated, with a formula that gives more weight to higher numbers, + * to quickly follows sudden increases and decrease slowly + */ + +static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd, + struct cfq_group *cfqg, bool rt) +{ + unsigned min_q, max_q; + unsigned mult = cfq_hist_divisor - 1; + unsigned round = cfq_hist_divisor / 2; + unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg); + + min_q = min(cfqg->busy_queues_avg[rt], busy); + max_q = max(cfqg->busy_queues_avg[rt], busy); + cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) / + cfq_hist_divisor; + return cfqg->busy_queues_avg[rt]; +} + +static inline unsigned +cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + + return cfq_target_latency * cfqg->weight / st->total_weight; +} + static inline void cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies; + unsigned slice = cfq_prio_to_slice(cfqd, cfqq); + if (cfqd->cfq_latency) { + /* + * interested queues (we consider only the ones with the same + * priority class in the cfq group) + */ + unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg, + cfq_class_rt(cfqq)); + unsigned sync_slice = cfqd->cfq_slice[1]; + unsigned expect_latency = sync_slice * iq; + unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg); + + if (expect_latency > group_slice) { + unsigned base_low_slice = 2 * cfqd->cfq_slice_idle; + /* scale low_slice according to IO priority + * and sync vs async */ + unsigned low_slice = + min(slice, base_low_slice * slice / sync_slice); + /* the adapted slice value is scaled to fit all iqs + * into the target latency */ + slice = max(slice * group_slice / expect_latency, + low_slice); + } + } + cfqq->slice_start = jiffies; + cfqq->slice_end = jiffies + slice; + cfqq->allocated_slice = slice; cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies); } @@ -331,9 +618,9 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq) * behind the head is penalized and only allowed to a certain extent. */ static struct request * -cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) +cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last) { - sector_t last, s1, s2, d1 = 0, d2 = 0; + sector_t s1, s2, d1 = 0, d2 = 0; unsigned long back_max; #define CFQ_RQ1_WRAP 0x01 /* request 1 wraps */ #define CFQ_RQ2_WRAP 0x02 /* request 2 wraps */ @@ -356,8 +643,6 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) s1 = blk_rq_pos(rq1); s2 = blk_rq_pos(rq2); - last = cfqd->last_position; - /* * by definition, 1KiB is 2 sectors */ @@ -425,6 +710,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) */ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) { + /* Service tree is empty */ + if (!root->count) + return NULL; + if (!root->left) root->left = rb_first(&root->rb); @@ -434,6 +723,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) return NULL; } +static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root) +{ + if (!root->left) + root->left = rb_first(&root->rb); + + if (root->left) + return rb_entry_cfqg(root->left); + + return NULL; +} + static void rb_erase_init(struct rb_node *n, struct rb_root *root) { rb_erase(n, root); @@ -445,6 +745,7 @@ static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) if (root->left == n) root->left = NULL; rb_erase_init(n, &root->rb); + --root->count; } /* @@ -471,7 +772,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq, next = rb_entry_rq(rbnext); } - return cfq_choose_req(cfqd, next, prev); + return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last)); } static unsigned long cfq_slice_offset(struct cfq_data *cfqd, @@ -480,12 +781,336 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd, /* * just an approximation, should be ok. */ - return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) - + return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) - cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio)); } +static inline s64 +cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg) +{ + return cfqg->vdisktime - st->min_vdisktime; +} + +static void +__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) +{ + struct rb_node **node = &st->rb.rb_node; + struct rb_node *parent = NULL; + struct cfq_group *__cfqg; + s64 key = cfqg_key(st, cfqg); + int left = 1; + + while (*node != NULL) { + parent = *node; + __cfqg = rb_entry_cfqg(parent); + + if (key < cfqg_key(st, __cfqg)) + node = &parent->rb_left; + else { + node = &parent->rb_right; + left = 0; + } + } + + if (left) + st->left = &cfqg->rb_node; + + rb_link_node(&cfqg->rb_node, parent, node); + rb_insert_color(&cfqg->rb_node, &st->rb); +} + +static void +cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + struct cfq_group *__cfqg; + struct rb_node *n; + + cfqg->nr_cfqq++; + if (cfqg->on_st) + return; + + /* + * Currently put the group at the end. Later implement something + * so that groups get lesser vtime based on their weights, so that + * if group does not loose all if it was not continously backlogged. + */ + n = rb_last(&st->rb); + if (n) { + __cfqg = rb_entry_cfqg(n); + cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY; + } else + cfqg->vdisktime = st->min_vdisktime; + + __cfq_group_service_tree_add(st, cfqg); + cfqg->on_st = true; + cfqd->nr_groups++; + st->total_weight += cfqg->weight; +} + +static void +cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + + if (st->active == &cfqg->rb_node) + st->active = NULL; + + BUG_ON(cfqg->nr_cfqq < 1); + cfqg->nr_cfqq--; + + /* If there are other cfq queues under this group, don't delete it */ + if (cfqg->nr_cfqq) + return; + + cfq_log_cfqg(cfqd, cfqg, "del_from_rr group"); + cfqg->on_st = false; + cfqd->nr_groups--; + st->total_weight -= cfqg->weight; + if (!RB_EMPTY_NODE(&cfqg->rb_node)) + cfq_rb_erase(&cfqg->rb_node, st); + cfqg->saved_workload_slice = 0; + blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1); +} + +static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) +{ + unsigned int slice_used; + + /* + * Queue got expired before even a single request completed or + * got expired immediately after first request completion. + */ + if (!cfqq->slice_start || cfqq->slice_start == jiffies) { + /* + * Also charge the seek time incurred to the group, otherwise + * if there are mutiple queues in the group, each can dispatch + * a single request on seeky media and cause lots of seek time + * and group will never know it. + */ + slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start), + 1); + } else { + slice_used = jiffies - cfqq->slice_start; + if (slice_used > cfqq->allocated_slice) + slice_used = cfqq->allocated_slice; + } + + cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used, + cfqq->nr_sectors); + return slice_used; +} + +static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, + struct cfq_queue *cfqq) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + unsigned int used_sl, charge_sl; + int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg) + - cfqg->service_tree_idle.count; + + BUG_ON(nr_sync < 0); + used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq); + + if (!cfq_cfqq_sync(cfqq) && !nr_sync) + charge_sl = cfqq->allocated_slice; + + /* Can't update vdisktime while group is on service tree */ + cfq_rb_erase(&cfqg->rb_node, st); + cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg); + __cfq_group_service_tree_add(st, cfqg); + + /* This group is being expired. Save the context */ + if (time_after(cfqd->workload_expires, jiffies)) { + cfqg->saved_workload_slice = cfqd->workload_expires + - jiffies; + cfqg->saved_workload = cfqd->serving_type; + cfqg->saved_serving_prio = cfqd->serving_prio; + } else + cfqg->saved_workload_slice = 0; + + cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, + st->min_vdisktime); + blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl, + cfqq->nr_sectors); +} + +#ifdef CONFIG_CFQ_GROUP_IOSCHED +static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg) +{ + if (blkg) + return container_of(blkg, struct cfq_group, blkg); + return NULL; +} + +void +cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight) +{ + cfqg_of_blkg(blkg)->weight = weight; +} + +static struct cfq_group * +cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) +{ + struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); + struct cfq_group *cfqg = NULL; + void *key = cfqd; + int i, j; + struct cfq_rb_root *st; + struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info; + unsigned int major, minor; + + /* Do we need to take this reference */ + if (!blkiocg_css_tryget(blkcg)) + return NULL;; + + cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key)); + if (cfqg || !create) + goto done; + + cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node); + if (!cfqg) + goto done; + + cfqg->weight = blkcg->weight; + for_each_cfqg_st(cfqg, i, j, st) + *st = CFQ_RB_ROOT; + RB_CLEAR_NODE(&cfqg->rb_node); + + /* + * Take the initial reference that will be released on destroy + * This can be thought of a joint reference by cgroup and + * elevator which will be dropped by either elevator exit + * or cgroup deletion path depending on who is exiting first. + */ + atomic_set(&cfqg->ref, 1); + + /* Add group onto cgroup list */ + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, + MKDEV(major, minor)); + + /* Add group on cfqd list */ + hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list); + +done: + blkiocg_css_put(blkcg); + return cfqg; +} + /* - * The cfqd->service_tree holds all pending cfq_queue's that have + * Search for the cfq group current task belongs to. If create = 1, then also + * create the cfq group if it does not exist. request_queue lock must be held. + */ +static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) +{ + struct cgroup *cgroup; + struct cfq_group *cfqg = NULL; + + rcu_read_lock(); + cgroup = task_cgroup(current, blkio_subsys_id); + cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create); + if (!cfqg && create) + cfqg = &cfqd->root_group; + rcu_read_unlock(); + return cfqg; +} + +static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) +{ + /* Currently, all async queues are mapped to root group */ + if (!cfq_cfqq_sync(cfqq)) + cfqg = &cfqq->cfqd->root_group; + + cfqq->cfqg = cfqg; + /* cfqq reference on cfqg */ + atomic_inc(&cfqq->cfqg->ref); +} + +static void cfq_put_cfqg(struct cfq_group *cfqg) +{ + struct cfq_rb_root *st; + int i, j; + + BUG_ON(atomic_read(&cfqg->ref) <= 0); + if (!atomic_dec_and_test(&cfqg->ref)) + return; + for_each_cfqg_st(cfqg, i, j, st) + BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL); + kfree(cfqg); +} + +static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + /* Something wrong if we are trying to remove same group twice */ + BUG_ON(hlist_unhashed(&cfqg->cfqd_node)); + + hlist_del_init(&cfqg->cfqd_node); + + /* + * Put the reference taken at the time of creation so that when all + * queues are gone, group can be destroyed. + */ + cfq_put_cfqg(cfqg); +} + +static void cfq_release_cfq_groups(struct cfq_data *cfqd) +{ + struct hlist_node *pos, *n; + struct cfq_group *cfqg; + + hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) { + /* + * If cgroup removal path got to blk_group first and removed + * it from cgroup list, then it will take care of destroying + * cfqg also. + */ + if (!blkiocg_del_blkio_group(&cfqg->blkg)) + cfq_destroy_cfqg(cfqd, cfqg); + } +} + +/* + * Blk cgroup controller notification saying that blkio_group object is being + * delinked as associated cgroup object is going away. That also means that + * no new IO will come in this group. So get rid of this group as soon as + * any pending IO in the group is finished. + * + * This function is called under rcu_read_lock(). key is the rcu protected + * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu + * read lock. + * + * "key" was fetched from blkio_group under blkio_cgroup->lock. That means + * it should not be NULL as even if elevator was exiting, cgroup deltion + * path got to it first. + */ +void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg) +{ + unsigned long flags; + struct cfq_data *cfqd = key; + + spin_lock_irqsave(cfqd->queue->queue_lock, flags); + cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg)); + spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); +} + +#else /* GROUP_IOSCHED */ +static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) +{ + return &cfqd->root_group; +} +static inline void +cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { + cfqq->cfqg = cfqg; +} + +static void cfq_release_cfq_groups(struct cfq_data *cfqd) {} +static inline void cfq_put_cfqg(struct cfq_group *cfqg) {} + +#endif /* GROUP_IOSCHED */ + +/* + * The cfqd->service_trees holds all pending cfq_queue's that have * requests waiting to be processed. It is sorted in the order that * we will service the queues. */ @@ -495,11 +1120,42 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct rb_node **p, *parent; struct cfq_queue *__cfqq; unsigned long rb_key; + struct cfq_rb_root *service_tree; int left; + int new_cfqq = 1; + int group_changed = 0; +#ifdef CONFIG_CFQ_GROUP_IOSCHED + if (!cfqd->cfq_group_isolation + && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD + && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) { + /* Move this cfq to root group */ + cfq_log_cfqq(cfqd, cfqq, "moving to root group"); + if (!RB_EMPTY_NODE(&cfqq->rb_node)) + cfq_group_service_tree_del(cfqd, cfqq->cfqg); + cfqq->orig_cfqg = cfqq->cfqg; + cfqq->cfqg = &cfqd->root_group; + atomic_inc(&cfqd->root_group.ref); + group_changed = 1; + } else if (!cfqd->cfq_group_isolation + && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) { + /* cfqq is sequential now needs to go to its original group */ + BUG_ON(cfqq->cfqg != &cfqd->root_group); + if (!RB_EMPTY_NODE(&cfqq->rb_node)) + cfq_group_service_tree_del(cfqd, cfqq->cfqg); + cfq_put_cfqg(cfqq->cfqg); + cfqq->cfqg = cfqq->orig_cfqg; + cfqq->orig_cfqg = NULL; + group_changed = 1; + cfq_log_cfqq(cfqd, cfqq, "moved to origin group"); + } +#endif + + service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq), + cfqq_type(cfqq), cfqd); if (cfq_class_idle(cfqq)) { rb_key = CFQ_IDLE_DELAY; - parent = rb_last(&cfqd->service_tree.rb); + parent = rb_last(&service_tree->rb); if (parent && parent != &cfqq->rb_node) { __cfqq = rb_entry(parent, struct cfq_queue, rb_node); rb_key += __cfqq->rb_key; @@ -517,23 +1173,27 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->slice_resid = 0; } else { rb_key = -HZ; - __cfqq = cfq_rb_first(&cfqd->service_tree); + __cfqq = cfq_rb_first(service_tree); rb_key += __cfqq ? __cfqq->rb_key : jiffies; } if (!RB_EMPTY_NODE(&cfqq->rb_node)) { + new_cfqq = 0; /* * same position, nothing more to do */ - if (rb_key == cfqq->rb_key) + if (rb_key == cfqq->rb_key && + cfqq->service_tree == service_tree) return; - cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree); + cfqq->service_tree = NULL; } left = 1; parent = NULL; - p = &cfqd->service_tree.rb.rb_node; + cfqq->service_tree = service_tree; + p = &service_tree->rb.rb_node; while (*p) { struct rb_node **n; @@ -541,35 +1201,28 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, __cfqq = rb_entry(parent, struct cfq_queue, rb_node); /* - * sort RT queues first, we always want to give - * preference to them. IDLE queues goes to the back. - * after that, sort on the next service time. + * sort by key, that represents service time. */ - if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq)) + if (time_before(rb_key, __cfqq->rb_key)) n = &(*p)->rb_left; - else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq)) + else { n = &(*p)->rb_right; - else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq)) - n = &(*p)->rb_left; - else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq)) - n = &(*p)->rb_right; - else if (time_before(rb_key, __cfqq->rb_key)) - n = &(*p)->rb_left; - else - n = &(*p)->rb_right; - - if (n == &(*p)->rb_right) left = 0; + } p = n; } if (left) - cfqd->service_tree.left = &cfqq->rb_node; + service_tree->left = &cfqq->rb_node; cfqq->rb_key = rb_key; rb_link_node(&cfqq->rb_node, parent, p); - rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb); + rb_insert_color(&cfqq->rb_node, &service_tree->rb); + service_tree->count++; + if ((add_front || !new_cfqq) && !group_changed) + return; + cfq_group_service_tree_add(cfqd, cfqq->cfqg); } static struct cfq_queue * @@ -671,13 +1324,16 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) BUG_ON(!cfq_cfqq_on_rr(cfqq)); cfq_clear_cfqq_on_rr(cfqq); - if (!RB_EMPTY_NODE(&cfqq->rb_node)) - cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + if (!RB_EMPTY_NODE(&cfqq->rb_node)) { + cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree); + cfqq->service_tree = NULL; + } if (cfqq->p_root) { rb_erase(&cfqq->p_node, cfqq->p_root); cfqq->p_root = NULL; } + cfq_group_service_tree_del(cfqd, cfqq->cfqg); BUG_ON(!cfqd->busy_queues); cfqd->busy_queues--; } @@ -688,7 +1344,6 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) static void cfq_del_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); - struct cfq_data *cfqd = cfqq->cfqd; const int sync = rq_is_sync(rq); BUG_ON(!cfqq->queued[sync]); @@ -696,8 +1351,17 @@ static void cfq_del_rq_rb(struct request *rq) elv_rb_del(&cfqq->sort_list, rq); - if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) - cfq_del_cfqq_rr(cfqd, cfqq); + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) { + /* + * Queue will be deleted from service tree when we actually + * expire it later. Right now just remove it from prio tree + * as it is empty. + */ + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } + } } static void cfq_add_rq_rb(struct request *rq) @@ -722,7 +1386,7 @@ static void cfq_add_rq_rb(struct request *rq) * check if this request is a better next-serve candidate */ prev = cfqq->next_rq; - cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq); + cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position); /* * adjust priority tree position, if ->next_rq changes @@ -829,6 +1493,7 @@ static void cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) { + struct cfq_queue *cfqq = RQ_CFQQ(rq); /* * reposition in fifo if next is older than rq */ @@ -838,6 +1503,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, rq_set_fifo_time(rq, rq_fifo_time(next)); } + if (cfqq->next_rq == next) + cfqq->next_rq = rq; cfq_remove_request(next); } @@ -848,6 +1515,9 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, struct cfq_io_context *cic; struct cfq_queue *cfqq; + /* Deny merge if bio and rq don't belong to same cfq group */ + if ((RQ_CFQQ(rq))->cfqg != cfq_get_cfqg(cfqd, 0)) + return false; /* * Disallow merge of a sync bio into an async request. */ @@ -871,8 +1541,12 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, { if (cfqq) { cfq_log_cfqq(cfqd, cfqq, "set_active"); + cfqq->slice_start = 0; + cfqq->dispatch_start = jiffies; + cfqq->allocated_slice = 0; cfqq->slice_end = 0; cfqq->slice_dispatch = 0; + cfqq->nr_sectors = 0; cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_must_dispatch(cfqq); @@ -899,6 +1573,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, del_timer(&cfqd->idle_slice_timer); cfq_clear_cfqq_wait_request(cfqq); + cfq_clear_cfqq_wait_busy(cfqq); + cfq_clear_cfqq_wait_busy_done(cfqq); /* * store what was left of this slice, if the queue idled/timed out @@ -908,11 +1584,19 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid); } + cfq_group_served(cfqd, cfqq->cfqg, cfqq); + + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) + cfq_del_cfqq_rr(cfqd, cfqq); + cfq_resort_rr_list(cfqd, cfqq); if (cfqq == cfqd->active_queue) cfqd->active_queue = NULL; + if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active) + cfqd->grp_service_tree.active = NULL; + if (cfqd->active_cic) { put_io_context(cfqd->active_cic->ioc); cfqd->active_cic = NULL; @@ -933,10 +1617,39 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out) */ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) { - if (RB_EMPTY_ROOT(&cfqd->service_tree.rb)) + struct cfq_rb_root *service_tree = + service_tree_for(cfqd->serving_group, cfqd->serving_prio, + cfqd->serving_type, cfqd); + + if (!cfqd->rq_queued) return NULL; - return cfq_rb_first(&cfqd->service_tree); + /* There is nothing to dispatch */ + if (!service_tree) + return NULL; + if (RB_EMPTY_ROOT(&service_tree->rb)) + return NULL; + return cfq_rb_first(service_tree); +} + +static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd) +{ + struct cfq_group *cfqg; + struct cfq_queue *cfqq; + int i, j; + struct cfq_rb_root *st; + + if (!cfqd->rq_queued) + return NULL; + + cfqg = cfq_get_next_cfqg(cfqd); + if (!cfqg) + return NULL; + + for_each_cfqg_st(cfqg, i, j, st) + if ((cfqq = cfq_rb_first(st)) != NULL) + return cfqq; + return NULL; } /* @@ -945,14 +1658,8 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - if (!cfqq) { + if (!cfqq) cfqq = cfq_get_next_queue(cfqd); - if (cfqq && !cfq_cfqq_coop_preempt(cfqq)) - cfq_clear_cfqq_coop(cfqq); - } - - if (cfqq) - cfq_clear_cfqq_coop_preempt(cfqq); __cfq_set_active_queue(cfqd, cfqq); return cfqq; @@ -967,16 +1674,16 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd, return cfqd->last_position - blk_rq_pos(rq); } -#define CIC_SEEK_THR 8 * 1024 -#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR) +#define CFQQ_SEEK_THR 8 * 1024 +#define CFQQ_SEEKY(cfqq) ((cfqq)->seek_mean > CFQQ_SEEK_THR) -static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq) +static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq, + struct request *rq) { - struct cfq_io_context *cic = cfqd->active_cic; - sector_t sdist = cic->seek_mean; + sector_t sdist = cfqq->seek_mean; - if (!sample_valid(cic->seek_samples)) - sdist = CIC_SEEK_THR; + if (!sample_valid(cfqq->seek_samples)) + sdist = CFQQ_SEEK_THR; return cfq_dist_from_last(cfqd, rq) <= sdist; } @@ -1005,7 +1712,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, * will contain the closest sector. */ __cfqq = rb_entry(parent, struct cfq_queue, p_node); - if (cfq_rq_close(cfqd, __cfqq->next_rq)) + if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq)) return __cfqq; if (blk_rq_pos(__cfqq->next_rq) < sector) @@ -1016,7 +1723,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, return NULL; __cfqq = rb_entry(node, struct cfq_queue, p_node); - if (cfq_rq_close(cfqd, __cfqq->next_rq)) + if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq)) return __cfqq; return NULL; @@ -1033,16 +1740,13 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, * assumption. */ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, - struct cfq_queue *cur_cfqq, - bool probe) + struct cfq_queue *cur_cfqq) { struct cfq_queue *cfqq; - /* - * A valid cfq_io_context is necessary to compare requests against - * the seek_mean of the current cfqq. - */ - if (!cfqd->active_cic) + if (!cfq_cfqq_sync(cur_cfqq)) + return NULL; + if (CFQQ_SEEKY(cur_cfqq)) return NULL; /* @@ -1054,14 +1758,55 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, if (!cfqq) return NULL; - if (cfq_cfqq_coop(cfqq)) + /* If new queue belongs to different cfq_group, don't choose it */ + if (cur_cfqq->cfqg != cfqq->cfqg) + return NULL; + + /* + * It only makes sense to merge sync queues. + */ + if (!cfq_cfqq_sync(cfqq)) + return NULL; + if (CFQQ_SEEKY(cfqq)) + return NULL; + + /* + * Do not merge queues of different priority classes + */ + if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq)) return NULL; - if (!probe) - cfq_mark_cfqq_coop(cfqq); return cfqq; } +/* + * Determine whether we should enforce idle window for this queue. + */ + +static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + enum wl_prio_t prio = cfqq_prio(cfqq); + struct cfq_rb_root *service_tree = cfqq->service_tree; + + BUG_ON(!service_tree); + BUG_ON(!service_tree->count); + + /* We never do for idle class queues. */ + if (prio == IDLE_WORKLOAD) + return false; + + /* We do for queues that were marked with idle window flag. */ + if (cfq_cfqq_idle_window(cfqq) && + !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)) + return true; + + /* + * Otherwise, we do only if they are the last ones + * in their service tree. + */ + return service_tree->count == 1; +} + static void cfq_arm_slice_timer(struct cfq_data *cfqd) { struct cfq_queue *cfqq = cfqd->active_queue; @@ -1082,13 +1827,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) /* * idle is disabled, either manually or by past process history */ - if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq)) + if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq)) return; /* - * still requests with the driver, don't idle + * still active requests from this queue, don't idle */ - if (rq_in_driver(cfqd)) + if (cfqq->dispatched) return; /* @@ -1109,14 +1854,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) cfq_mark_cfqq_wait_request(cfqq); - /* - * we don't want to idle for seeks, but we do want to allow - * fair distribution of slice time for a process doing back-to-back - * seeks. so allow a little bit of time for him to submit a new rq - */ sl = cfqd->cfq_slice_idle; - if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic)) - sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT)); mod_timer(&cfqd->idle_slice_timer, jiffies + sl); cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); @@ -1139,6 +1877,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) if (cfq_cfqq_sync(cfqq)) cfqd->sync_flight++; + cfqq->nr_sectors += blk_rq_sectors(rq); } /* @@ -1174,6 +1913,207 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio)); } +/* + * Must be called with the queue_lock held. + */ +static int cfqq_process_refs(struct cfq_queue *cfqq) +{ + int process_refs, io_refs; + + io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE]; + process_refs = atomic_read(&cfqq->ref) - io_refs; + BUG_ON(process_refs < 0); + return process_refs; +} + +static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq) +{ + int process_refs, new_process_refs; + struct cfq_queue *__cfqq; + + /* Avoid a circular list and skip interim queue merges */ + while ((__cfqq = new_cfqq->new_cfqq)) { + if (__cfqq == cfqq) + return; + new_cfqq = __cfqq; + } + + process_refs = cfqq_process_refs(cfqq); + /* + * If the process for the cfqq has gone away, there is no + * sense in merging the queues. + */ + if (process_refs == 0) + return; + + /* + * Merge in the direction of the lesser amount of work. + */ + new_process_refs = cfqq_process_refs(new_cfqq); + if (new_process_refs >= process_refs) { + cfqq->new_cfqq = new_cfqq; + atomic_add(process_refs, &new_cfqq->ref); + } else { + new_cfqq->new_cfqq = cfqq; + atomic_add(new_process_refs, &cfqq->ref); + } +} + +static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd, + struct cfq_group *cfqg, enum wl_prio_t prio, + bool prio_changed) +{ + struct cfq_queue *queue; + int i; + bool key_valid = false; + unsigned long lowest_key = 0; + enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD; + + if (prio_changed) { + /* + * When priorities switched, we prefer starting + * from SYNC_NOIDLE (first choice), or just SYNC + * over ASYNC + */ + if (service_tree_for(cfqg, prio, cur_best, cfqd)->count) + return cur_best; + cur_best = SYNC_WORKLOAD; + if (service_tree_for(cfqg, prio, cur_best, cfqd)->count) + return cur_best; + + return ASYNC_WORKLOAD; + } + + for (i = 0; i < 3; ++i) { + /* otherwise, select the one with lowest rb_key */ + queue = cfq_rb_first(service_tree_for(cfqg, prio, i, cfqd)); + if (queue && + (!key_valid || time_before(queue->rb_key, lowest_key))) { + lowest_key = queue->rb_key; + cur_best = i; + key_valid = true; + } + } + + return cur_best; +} + +static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + enum wl_prio_t previous_prio = cfqd->serving_prio; + bool prio_changed; + unsigned slice; + unsigned count; + struct cfq_rb_root *st; + unsigned group_slice; + + if (!cfqg) { + cfqd->serving_prio = IDLE_WORKLOAD; + cfqd->workload_expires = jiffies + 1; + return; + } + + /* Choose next priority. RT > BE > IDLE */ + if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg)) + cfqd->serving_prio = RT_WORKLOAD; + else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg)) + cfqd->serving_prio = BE_WORKLOAD; + else { + cfqd->serving_prio = IDLE_WORKLOAD; + cfqd->workload_expires = jiffies + 1; + return; + } + + /* + * For RT and BE, we have to choose also the type + * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload + * expiration time + */ + prio_changed = (cfqd->serving_prio != previous_prio); + st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type, + cfqd); + count = st->count; + + /* + * If priority didn't change, check workload expiration, + * and that we still have other queues ready + */ + if (!prio_changed && count && + !time_after(jiffies, cfqd->workload_expires)) + return; + + /* otherwise select new workload type */ + cfqd->serving_type = + cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio, prio_changed); + st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type, + cfqd); + count = st->count; + + /* + * the workload slice is computed as a fraction of target latency + * proportional to the number of queues in that workload, over + * all the queues in the same priority class + */ + group_slice = cfq_group_slice(cfqd, cfqg); + + slice = group_slice * count / + max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio], + cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg)); + + if (cfqd->serving_type == ASYNC_WORKLOAD) { + unsigned int tmp; + + /* + * Async queues are currently system wide. Just taking + * proportion of queues with-in same group will lead to higher + * async ratio system wide as generally root group is going + * to have higher weight. A more accurate thing would be to + * calculate system wide asnc/sync ratio. + */ + tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg); + tmp = tmp/cfqd->busy_queues; + slice = min_t(unsigned, slice, tmp); + + /* async workload slice is scaled down according to + * the sync/async slice ratio. */ + slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1]; + } else + /* sync workload slice is at least 2 * cfq_slice_idle */ + slice = max(slice, 2 * cfqd->cfq_slice_idle); + + slice = max_t(unsigned, slice, CFQ_MIN_TT); + cfqd->workload_expires = jiffies + slice; + cfqd->noidle_tree_requires_idle = false; +} + +static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + struct cfq_group *cfqg; + + if (RB_EMPTY_ROOT(&st->rb)) + return NULL; + cfqg = cfq_rb_first_group(st); + st->active = &cfqg->rb_node; + update_min_vdisktime(st); + return cfqg; +} + +static void cfq_choose_cfqg(struct cfq_data *cfqd) +{ + struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd); + + cfqd->serving_group = cfqg; + + /* Restore the workload type data */ + if (cfqg->saved_workload_slice) { + cfqd->workload_expires = jiffies + cfqg->saved_workload_slice; + cfqd->serving_type = cfqg->saved_workload; + cfqd->serving_prio = cfqg->saved_serving_prio; + } + choose_service_tree(cfqd, cfqg); +} + /* * Select a queue for service. If we have a current active queue, * check whether to continue servicing it, or retrieve and set a new one. @@ -1186,10 +2126,13 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) if (!cfqq) goto new_queue; + if (!cfqd->rq_queued) + return NULL; /* * The active queue has run out of time, expire it and select new. */ - if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) + if ((cfq_slice_used(cfqq) || cfq_cfqq_wait_busy_done(cfqq)) + && !cfq_cfqq_must_dispatch(cfqq)) goto expire; /* @@ -1203,11 +2146,14 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) * If another queue has a request waiting within our mean seek * distance, let it run. The expire code will check for close * cooperators and put the close queue at the front of the service - * tree. + * tree. If possible, merge the expiring queue with the new cfqq. */ - new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0); - if (new_cfqq) + new_cfqq = cfq_close_cooperator(cfqd, cfqq); + if (new_cfqq) { + if (!cfqq->new_cfqq) + cfq_setup_merge(cfqq, new_cfqq); goto expire; + } /* * No requests pending. If the active queue still has requests in @@ -1215,7 +2161,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) * conditions to happen (or time out) before selecting a new queue. */ if (timer_pending(&cfqd->idle_slice_timer) || - (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) { + (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) { cfqq = NULL; goto keep_queue; } @@ -1223,6 +2169,13 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) expire: cfq_slice_expired(cfqd, 0); new_queue: + /* + * Current queue expired. Check if we have to switch to a new + * service tree + */ + if (!new_cfqq) + cfq_choose_cfqg(cfqd); + cfqq = cfq_set_active_queue(cfqd, new_cfqq); keep_queue: return cfqq; @@ -1238,6 +2191,9 @@ static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) } BUG_ON(!list_empty(&cfqq->fifo)); + + /* By default cfqq is not expired if it is empty. Do it explicitly */ + __cfq_slice_expired(cfqq->cfqd, cfqq, 0); return dispatched; } @@ -1250,11 +2206,10 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd) struct cfq_queue *cfqq; int dispatched = 0; - while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL) + while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) dispatched += __cfq_forced_dispatch_cfqq(cfqq); cfq_slice_expired(cfqd, 0); - BUG_ON(cfqd->busy_queues); cfq_log(cfqd, "forced_dispatch=%d", dispatched); @@ -1268,7 +2223,7 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq) /* * Drain async requests before we start sync IO */ - if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC]) + if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC]) return false; /* @@ -1298,9 +2253,9 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq) return false; /* - * Sole queue user, allow bigger slice + * Sole queue user, no limit */ - max_dispatch *= 4; + max_dispatch = -1; } /* @@ -1407,11 +2362,13 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) * task holds one reference to the queue, dropped when task exits. each rq * in-flight on this queue also holds a reference, dropped when rq is freed. * + * Each cfq queue took a reference on the parent group. Drop it now. * queue lock must be held here. */ static void cfq_put_queue(struct cfq_queue *cfqq) { struct cfq_data *cfqd = cfqq->cfqd; + struct cfq_group *cfqg, *orig_cfqg; BUG_ON(atomic_read(&cfqq->ref) <= 0); @@ -1421,14 +2378,19 @@ static void cfq_put_queue(struct cfq_queue *cfqq) cfq_log_cfqq(cfqd, cfqq, "put_queue"); BUG_ON(rb_first(&cfqq->sort_list)); BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]); - BUG_ON(cfq_cfqq_on_rr(cfqq)); + cfqg = cfqq->cfqg; + orig_cfqg = cfqq->orig_cfqg; if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); cfq_schedule_dispatch(cfqd); } + BUG_ON(cfq_cfqq_on_rr(cfqq)); kmem_cache_free(cfq_pool, cfqq); + cfq_put_cfqg(cfqg); + if (orig_cfqg) + cfq_put_cfqg(orig_cfqg); } /* @@ -1518,11 +2480,29 @@ static void cfq_free_io_context(struct io_context *ioc) static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { + struct cfq_queue *__cfqq, *next; + if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); cfq_schedule_dispatch(cfqd); } + /* + * If this queue was scheduled to merge with another queue, be + * sure to drop the reference taken on that queue (and others in + * the merge chain). See cfq_setup_merge and cfq_merge_cfqqs. + */ + __cfqq = cfqq->new_cfqq; + while (__cfqq) { + if (__cfqq == cfqq) { + WARN(1, "cfqq->new_cfqq loop detected\n"); + break; + } + next = __cfqq->new_cfqq; + cfq_put_queue(__cfqq); + __cfqq = next; + } + cfq_put_queue(cfqq); } @@ -1703,14 +2683,51 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->pid = pid; } +#ifdef CONFIG_CFQ_GROUP_IOSCHED +static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic) +{ + struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1); + struct cfq_data *cfqd = cic->key; + unsigned long flags; + struct request_queue *q; + + if (unlikely(!cfqd)) + return; + + q = cfqd->queue; + + spin_lock_irqsave(q->queue_lock, flags); + + if (sync_cfqq) { + /* + * Drop reference to sync queue. A new sync queue will be + * assigned in new group upon arrival of a fresh request. + */ + cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup"); + cic_set_cfqq(cic, NULL, 1); + cfq_put_queue(sync_cfqq); + } + + spin_unlock_irqrestore(q->queue_lock, flags); +} + +static void cfq_ioc_set_cgroup(struct io_context *ioc) +{ + call_for_each_cic(ioc, changed_cgroup); + ioc->cgroup_changed = 0; +} +#endif /* CONFIG_CFQ_GROUP_IOSCHED */ + static struct cfq_queue * cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc, gfp_t gfp_mask) { struct cfq_queue *cfqq, *new_cfqq = NULL; struct cfq_io_context *cic; + struct cfq_group *cfqg; retry: + cfqg = cfq_get_cfqg(cfqd, 1); cic = cfq_cic_lookup(cfqd, ioc); /* cic always exists here */ cfqq = cic_to_cfqq(cic, is_sync); @@ -1741,6 +2758,7 @@ retry: if (cfqq) { cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); cfq_init_prio_data(cfqq, ioc); + cfq_link_cfqq_cfqg(cfqq, cfqg); cfq_log_cfqq(cfqd, cfqq, "alloced"); } else cfqq = &cfqd->oom_cfqq; @@ -1932,6 +2950,10 @@ out: if (unlikely(ioc->ioprio_changed)) cfq_ioc_set_ioprio(ioc); +#ifdef CONFIG_CFQ_GROUP_IOSCHED + if (unlikely(ioc->cgroup_changed)) + cfq_ioc_set_cgroup(ioc); +#endif return cic; err_free: cfq_cic_free(cic); @@ -1952,33 +2974,46 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic) } static void -cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, +cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct request *rq) { sector_t sdist; u64 total; - if (!cic->last_request_pos) + if (!cfqq->last_request_pos) sdist = 0; - else if (cic->last_request_pos < blk_rq_pos(rq)) - sdist = blk_rq_pos(rq) - cic->last_request_pos; + else if (cfqq->last_request_pos < blk_rq_pos(rq)) + sdist = blk_rq_pos(rq) - cfqq->last_request_pos; else - sdist = cic->last_request_pos - blk_rq_pos(rq); + sdist = cfqq->last_request_pos - blk_rq_pos(rq); /* * Don't allow the seek distance to get too large from the * odd fragment, pagein, etc */ - if (cic->seek_samples <= 60) /* second&third seek */ - sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024); + if (cfqq->seek_samples <= 60) /* second&third seek */ + sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024); else - sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*64); + sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64); - cic->seek_samples = (7*cic->seek_samples + 256) / 8; - cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8; - total = cic->seek_total + (cic->seek_samples/2); - do_div(total, cic->seek_samples); - cic->seek_mean = (sector_t)total; + cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8; + cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8; + total = cfqq->seek_total + (cfqq->seek_samples/2); + do_div(total, cfqq->seek_samples); + cfqq->seek_mean = (sector_t)total; + + /* + * If this cfqq is shared between multiple processes, check to + * make sure that those processes are still issuing I/Os within + * the mean seek distance. If not, it may be time to break the + * queues apart again. + */ + if (cfq_cfqq_coop(cfqq)) { + if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start) + cfqq->seeky_start = jiffies; + else if (!CFQQ_SEEKY(cfqq)) + cfqq->seeky_start = 0; + } } /* @@ -1999,14 +3034,15 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, enable_idle = old_idle = cfq_cfqq_idle_window(cfqq); + if (cfqq->queued[0] + cfqq->queued[1] >= 4) + cfq_mark_cfqq_deep(cfqq); + if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle || - (!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic))) + (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples) + && CFQQ_SEEKY(cfqq))) enable_idle = 0; else if (sample_valid(cic->ttime_samples)) { - unsigned int slice_idle = cfqd->cfq_slice_idle; - if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic)) - slice_idle = msecs_to_jiffies(CFQ_MIN_TT); - if (cic->ttime_mean > slice_idle) + if (cic->ttime_mean > cfqd->cfq_slice_idle) enable_idle = 0; else enable_idle = 1; @@ -2035,9 +3071,6 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, if (!cfqq) return false; - if (cfq_slice_used(cfqq)) - return true; - if (cfq_class_idle(new_cfqq)) return false; @@ -2051,6 +3084,19 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq)) return true; + if (new_cfqq->cfqg != cfqq->cfqg) + return false; + + if (cfq_slice_used(cfqq)) + return true; + + /* Allow preemption only if we are idling on sync-noidle tree */ + if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD && + cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD && + new_cfqq->service_tree->count == 2 && + RB_EMPTY_ROOT(&cfqq->sort_list)) + return true; + /* * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. @@ -2071,16 +3117,8 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * if this request is as-good as one we would expect from the * current cfqq, let it preempt */ - if (cfq_rq_close(cfqd, rq) && (!cfq_cfqq_coop(new_cfqq) || - cfqd->busy_queues == 1)) { - /* - * Mark new queue coop_preempt, so its coop flag will not be - * cleared when new queue gets scheduled at the very first time - */ - cfq_mark_cfqq_coop_preempt(new_cfqq); - cfq_mark_cfqq_coop(new_cfqq); + if (cfq_rq_close(cfqd, cfqq, rq)) return true; - } return false; } @@ -2121,12 +3159,16 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->meta_pending++; cfq_update_io_thinktime(cfqd, cic); - cfq_update_io_seektime(cfqd, cic, rq); + cfq_update_io_seektime(cfqd, cfqq, rq); cfq_update_idle_window(cfqd, cfqq, cic); - cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); + cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); if (cfqq == cfqd->active_queue) { + if (cfq_cfqq_wait_busy(cfqq)) { + cfq_clear_cfqq_wait_busy(cfqq); + cfq_mark_cfqq_wait_busy_done(cfqq); + } /* * Remember that we saw a request from this process, but * don't start queuing just yet. Otherwise we risk seeing lots @@ -2141,9 +3183,9 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || cfqd->busy_queues > 1) { del_timer(&cfqd->idle_slice_timer); - __blk_run_queue(cfqd->queue); - } - cfq_mark_cfqq_must_dispatch(cfqq); + __blk_run_queue(cfqd->queue); + } else + cfq_mark_cfqq_must_dispatch(cfqq); } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* @@ -2165,10 +3207,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) cfq_log_cfqq(cfqd, cfqq, "insert_request"); cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc); - cfq_add_rq_rb(rq); - rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]); list_add_tail(&rq->queuelist, &cfqq->fifo); + cfq_add_rq_rb(rq); cfq_rq_enqueued(cfqd, cfqq, rq); } @@ -2179,23 +3220,35 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) */ static void cfq_update_hw_tag(struct cfq_data *cfqd) { - if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak) - cfqd->rq_in_driver_peak = rq_in_driver(cfqd); + struct cfq_queue *cfqq = cfqd->active_queue; + + if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth) + cfqd->hw_tag_est_depth = rq_in_driver(cfqd); + + if (cfqd->hw_tag == 1) + return; if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN) return; + /* + * If active queue hasn't enough requests and can idle, cfq might not + * dispatch sufficient requests to hardware. Don't zero hw_tag in this + * case + */ + if (cfqq && cfq_cfqq_idle_window(cfqq) && + cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] < + CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN) + return; + if (cfqd->hw_tag_samples++ < 50) return; - if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN) + if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN) cfqd->hw_tag = 1; else cfqd->hw_tag = 0; - - cfqd->hw_tag_samples = 0; - cfqd->rq_in_driver_peak = 0; } static void cfq_completed_request(struct request_queue *q, struct request *rq) @@ -2206,7 +3259,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) unsigned long now; now = jiffies; - cfq_log_cfqq(cfqd, cfqq, "complete"); + cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq)); cfq_update_hw_tag(cfqd); @@ -2234,18 +3287,40 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfq_set_prio_slice(cfqd, cfqq); cfq_clear_cfqq_slice_new(cfqq); } + /* - * If there are no requests waiting in this queue, and - * there are other queues ready to issue requests, AND - * those other queues are issuing requests within our - * mean seek distance, give them a chance to run instead - * of idling. + * If this queue consumed its slice and this is last queue + * in the group, wait for next request before we expire + * the queue + */ + if (cfq_slice_used(cfqq) && cfqq->cfqg->nr_cfqq == 1) { + cfqq->slice_end = jiffies + cfqd->cfq_slice_idle; + cfq_mark_cfqq_wait_busy(cfqq); + } + + /* + * Idling is not enabled on: + * - expired queues + * - idle-priority queues + * - async queues + * - queues with still some requests queued + * - when there is a close cooperator */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) cfq_slice_expired(cfqd, 1); - else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) && - sync && !rq_noidle(rq)) - cfq_arm_slice_timer(cfqd); + else if (sync && cfqq_empty && + !cfq_close_cooperator(cfqd, cfqq)) { + cfqd->noidle_tree_requires_idle |= !rq_noidle(rq); + /* + * Idling is enabled for SYNC_WORKLOAD. + * SYNC_NOIDLE_WORKLOAD idles at the end of the tree + * only if we processed at least one !rq_noidle request + */ + if (cfqd->serving_type == SYNC_WORKLOAD + || cfqd->noidle_tree_requires_idle + || cfqq->cfqg->nr_cfqq == 1) + cfq_arm_slice_timer(cfqd); + } } if (!rq_in_driver(cfqd)) @@ -2269,12 +3344,10 @@ static void cfq_prio_boost(struct cfq_queue *cfqq) cfqq->ioprio = IOPRIO_NORM; } else { /* - * check if we need to unboost the queue + * unboost the queue (if needed) */ - if (cfqq->ioprio_class != cfqq->org_ioprio_class) - cfqq->ioprio_class = cfqq->org_ioprio_class; - if (cfqq->ioprio != cfqq->org_ioprio) - cfqq->ioprio = cfqq->org_ioprio; + cfqq->ioprio_class = cfqq->org_ioprio_class; + cfqq->ioprio = cfqq->org_ioprio; } } @@ -2338,6 +3411,43 @@ static void cfq_put_request(struct request *rq) } } +static struct cfq_queue * +cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic, + struct cfq_queue *cfqq) +{ + cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq); + cic_set_cfqq(cic, cfqq->new_cfqq, 1); + cfq_mark_cfqq_coop(cfqq->new_cfqq); + cfq_put_queue(cfqq); + return cic_to_cfqq(cic, 1); +} + +static int should_split_cfqq(struct cfq_queue *cfqq) +{ + if (cfqq->seeky_start && + time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT)) + return 1; + return 0; +} + +/* + * Returns NULL if a new cfqq should be allocated, or the old cfqq if this + * was the last process referring to said cfqq. + */ +static struct cfq_queue * +split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq) +{ + if (cfqq_process_refs(cfqq) == 1) { + cfqq->seeky_start = 0; + cfqq->pid = current->pid; + cfq_clear_cfqq_coop(cfqq); + return cfqq; + } + + cic_set_cfqq(cic, NULL, 1); + cfq_put_queue(cfqq); + return NULL; +} /* * Allocate cfq data structures associated with this request. */ @@ -2360,10 +3470,30 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) if (!cic) goto queue_fail; +new_queue: cfqq = cic_to_cfqq(cic, is_sync); if (!cfqq || cfqq == &cfqd->oom_cfqq) { cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask); cic_set_cfqq(cic, cfqq, is_sync); + } else { + /* + * If the queue was seeky for too long, break it apart. + */ + if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) { + cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq"); + cfqq = split_cfqq(cic, cfqq); + if (!cfqq) + goto new_queue; + } + + /* + * Check to see if this queue is scheduled to merge with + * another, closely cooperating queue. The merging of + * queues happens here as it must be done in process context. + * The reference on new_cfqq was taken in merge_cfqqs. + */ + if (cfqq->new_cfqq) + cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq); } cfqq->allocated[rw]++; @@ -2438,6 +3568,11 @@ static void cfq_idle_slice_timer(unsigned long data) */ if (!RB_EMPTY_ROOT(&cfqq->sort_list)) goto out_kick; + + /* + * Queue depth flag is reset only when the idle didn't succeed + */ + cfq_clear_cfqq_deep(cfqq); } expire: cfq_slice_expired(cfqd, timed_out); @@ -2468,6 +3603,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd) cfq_put_queue(cfqd->async_idle_cfqq); } +static void cfq_cfqd_free(struct rcu_head *head) +{ + kfree(container_of(head, struct cfq_data, rcu)); +} + static void cfq_exit_queue(struct elevator_queue *e) { struct cfq_data *cfqd = e->elevator_data; @@ -2489,25 +3629,49 @@ static void cfq_exit_queue(struct elevator_queue *e) } cfq_put_async_queues(cfqd); + cfq_release_cfq_groups(cfqd); + blkiocg_del_blkio_group(&cfqd->root_group.blkg); spin_unlock_irq(q->queue_lock); cfq_shutdown_timer_wq(cfqd); - kfree(cfqd); + /* Wait for cfqg->blkg->key accessors to exit their grace periods. */ + call_rcu(&cfqd->rcu, cfq_cfqd_free); } static void *cfq_init_queue(struct request_queue *q) { struct cfq_data *cfqd; - int i; + int i, j; + struct cfq_group *cfqg; + struct cfq_rb_root *st; cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); if (!cfqd) return NULL; - cfqd->service_tree = CFQ_RB_ROOT; + /* Init root service tree */ + cfqd->grp_service_tree = CFQ_RB_ROOT; + /* Init root group */ + cfqg = &cfqd->root_group; + for_each_cfqg_st(cfqg, i, j, st) + *st = CFQ_RB_ROOT; + RB_CLEAR_NODE(&cfqg->rb_node); + + /* Give preference to root group over other groups */ + cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT; + +#ifdef CONFIG_CFQ_GROUP_IOSCHED + /* + * Take a reference to root group which we never drop. This is just + * to make sure that cfq_put_cfqg() does not try to kfree root group + */ + atomic_set(&cfqg->ref, 1); + blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd, + 0); +#endif /* * Not strictly needed (since RB_ROOT just clears the node and we * zeroed cfqd on alloc), but better be safe in case someone decides @@ -2523,6 +3687,7 @@ static void *cfq_init_queue(struct request_queue *q) */ cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0); atomic_inc(&cfqd->oom_cfqq.ref); + cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group); INIT_LIST_HEAD(&cfqd->cic_list); @@ -2544,8 +3709,10 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; cfqd->cfq_latency = 1; - cfqd->hw_tag = 1; + cfqd->cfq_group_isolation = 0; + cfqd->hw_tag = -1; cfqd->last_end_sync_rq = jiffies; + INIT_RCU_HEAD(&cfqd->rcu); return cfqd; } @@ -2614,6 +3781,7 @@ SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1); SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1); SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0); SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0); +SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ @@ -2646,6 +3814,7 @@ STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0); STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0); +STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0); #undef STORE_FUNCTION #define CFQ_ATTR(name) \ @@ -2662,6 +3831,7 @@ static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(slice_async_rq), CFQ_ATTR(slice_idle), CFQ_ATTR(low_latency), + CFQ_ATTR(group_isolation), __ATTR_NULL }; @@ -2691,6 +3861,17 @@ static struct elevator_type iosched_cfq = { .elevator_owner = THIS_MODULE, }; +#ifdef CONFIG_CFQ_GROUP_IOSCHED +static struct blkio_policy_type blkio_policy_cfq = { + .ops = { + .blkio_unlink_group_fn = cfq_unlink_blkio_group, + .blkio_update_group_weight_fn = cfq_update_blkio_group_weight, + }, +}; +#else +static struct blkio_policy_type blkio_policy_cfq; +#endif + static int __init cfq_init(void) { /* @@ -2705,6 +3886,7 @@ static int __init cfq_init(void) return -ENOMEM; elv_register(&iosched_cfq); + blkio_policy_register(&blkio_policy_cfq); return 0; } @@ -2712,6 +3894,7 @@ static int __init cfq_init(void) static void __exit cfq_exit(void) { DECLARE_COMPLETION_ONSTACK(all_gone); + blkio_policy_unregister(&blkio_policy_cfq); elv_unregister(&iosched_cfq); ioc_gone = &all_gone; /* ioc_gone's update must be visible before reading ioc_count */ diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 9bd086c1a4d5..4eb8e9ea4af5 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -747,6 +747,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_uint(arg, bdev_io_opt(bdev)); case BLKALIGNOFF: return compat_put_int(arg, bdev_alignment_offset(bdev)); + case BLKDISCARDZEROES: + return compat_put_uint(arg, bdev_discard_zeroes_data(bdev)); case BLKFLSBUF: case BLKROSET: case BLKDISCARD: diff --git a/block/elevator.c b/block/elevator.c index a847046c6e53..9ad5ccc4c5ee 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -154,10 +154,7 @@ static struct elevator_type *elevator_get(const char *name) spin_unlock(&elv_list_lock); - if (!strcmp(name, "anticipatory")) - sprintf(elv, "as-iosched"); - else - sprintf(elv, "%s-iosched", name); + sprintf(elv, "%s-iosched", name); request_module("%s", elv); spin_lock(&elv_list_lock); @@ -193,10 +190,7 @@ static int __init elevator_setup(char *str) * Be backwards-compatible with previous kernels, so users * won't get the wrong elevator. */ - if (!strcmp(str, "as")) - strcpy(chosen_elevator, "anticipatory"); - else - strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1); + strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1); return 1; } diff --git a/block/genhd.c b/block/genhd.c index 517e4332cb37..b11a4ad7d571 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -861,12 +861,23 @@ static ssize_t disk_alignment_offset_show(struct device *dev, return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); } +static ssize_t disk_discard_alignment_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + return sprintf(buf, "%u\n", queue_discard_alignment(disk->queue)); +} + static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL); static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); +static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, + NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); @@ -887,6 +898,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_ro.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, + &dev_attr_discard_alignment.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, diff --git a/block/ioctl.c b/block/ioctl.c index 1f4d1de12b09..be48ea51faee 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -280,6 +280,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_uint(arg, bdev_io_opt(bdev)); case BLKALIGNOFF: return put_int(arg, bdev_alignment_offset(bdev)); + case BLKDISCARDZEROES: + return put_uint(arg, bdev_discard_zeroes_data(bdev)); case BLKSECTGET: return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); case BLKRASET: diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index e5b10017a50b..a8b5a10eb5b0 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -35,7 +35,9 @@ struct blk_cmd_filter { unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; -} blk_default_cmd_filter; +}; + +static struct blk_cmd_filter blk_default_cmd_filter; /* Command group 3 is reserved and should never be used. */ const unsigned char scsi_command_size_tbl[8] = @@ -675,7 +677,7 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod } EXPORT_SYMBOL(scsi_cmd_ioctl); -int __init blk_scsi_ioctl_init(void) +static int __init blk_scsi_ioctl_init(void) { blk_set_cmd_filter_defaults(&blk_default_cmd_filter); return 0; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 1d886e079c58..77bfce52e9ca 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -271,6 +271,8 @@ config BLK_DEV_CRYPTOLOOP instead, which can be configured to be on-disk compatible with the cryptoloop device. +source "drivers/block/drbd/Kconfig" + config BLK_DEV_NBD tristate "Network block device support" depends on NET diff --git a/drivers/block/Makefile b/drivers/block/Makefile index cdaa3f8fddf0..aff5ac925c34 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -36,5 +36,6 @@ obj-$(CONFIG_BLK_DEV_UB) += ub.o obj-$(CONFIG_BLK_DEV_HD) += hd.o obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o +obj-$(CONFIG_BLK_DEV_DRBD) += drbd/ swim_mod-objs := swim.o swim_asm.o diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 92b126394fa1..873e594860d3 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -179,19 +179,17 @@ static int rebuild_lun_table(ctlr_info_t *h, int first_time, int via_ioctl); static int deregister_disk(ctlr_info_t *h, int drv_index, int clear_all, int via_ioctl); -static void cciss_read_capacity(int ctlr, int logvol, int withirq, +static void cciss_read_capacity(int ctlr, int logvol, sector_t *total_size, unsigned int *block_size); -static void cciss_read_capacity_16(int ctlr, int logvol, int withirq, +static void cciss_read_capacity_16(int ctlr, int logvol, sector_t *total_size, unsigned int *block_size); static void cciss_geometry_inquiry(int ctlr, int logvol, - int withirq, sector_t total_size, + sector_t total_size, unsigned int block_size, InquiryData_struct *inq_buff, drive_info_struct *drv); static void __devinit cciss_interrupt_mode(ctlr_info_t *, struct pci_dev *, __u32); static void start_io(ctlr_info_t *h); -static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, - __u8 page_code, unsigned char *scsi3addr, int cmd_type); static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size, __u8 page_code, unsigned char scsi3addr[], int cmd_type); @@ -424,12 +422,9 @@ cciss_proc_write(struct file *file, const char __user *buf, if (strncmp(ENGAGE_SCSI, buffer, sizeof ENGAGE_SCSI - 1) == 0) { struct seq_file *seq = file->private_data; ctlr_info_t *h = seq->private; - int rc; - rc = cciss_engage_scsi(h->ctlr); - if (rc != 0) - err = -rc; - else + err = cciss_engage_scsi(h->ctlr); + if (err == 0) err = length; } else #endif /* CONFIG_CISS_SCSI_TAPE */ @@ -1657,9 +1652,11 @@ static void cciss_softirq_done(struct request *rq) { CommandList_struct *cmd = rq->completion_data; ctlr_info_t *h = hba[cmd->ctlr]; + SGDescriptor_struct *curr_sg = cmd->SG; unsigned long flags; u64bit temp64; int i, ddir; + int sg_index = 0; if (cmd->Request.Type.Direction == XFER_READ) ddir = PCI_DMA_FROMDEVICE; @@ -1669,9 +1666,22 @@ static void cciss_softirq_done(struct request *rq) /* command did not need to be retried */ /* unmap the DMA mapping for all the scatter gather elements */ for (i = 0; i < cmd->Header.SGList; i++) { - temp64.val32.lower = cmd->SG[i].Addr.lower; - temp64.val32.upper = cmd->SG[i].Addr.upper; - pci_unmap_page(h->pdev, temp64.val, cmd->SG[i].Len, ddir); + if (curr_sg[sg_index].Ext == CCISS_SG_CHAIN) { + temp64.val32.lower = cmd->SG[i].Addr.lower; + temp64.val32.upper = cmd->SG[i].Addr.upper; + pci_dma_sync_single_for_cpu(h->pdev, temp64.val, + cmd->SG[i].Len, ddir); + pci_unmap_single(h->pdev, temp64.val, + cmd->SG[i].Len, ddir); + /* Point to the next block */ + curr_sg = h->cmd_sg_list[cmd->cmdindex]->sgchain; + sg_index = 0; + } + temp64.val32.lower = curr_sg[sg_index].Addr.lower; + temp64.val32.upper = curr_sg[sg_index].Addr.upper; + pci_unmap_page(h->pdev, temp64.val, curr_sg[sg_index].Len, + ddir); + ++sg_index; } #ifdef CCISS_DEBUG @@ -1701,7 +1711,7 @@ static inline void log_unit_to_scsi3addr(ctlr_info_t *h, * via the inquiry page 0. Model, vendor, and rev are set to empty strings if * they cannot be read. */ -static void cciss_get_device_descr(int ctlr, int logvol, int withirq, +static void cciss_get_device_descr(int ctlr, int logvol, char *vendor, char *model, char *rev) { int rc; @@ -1717,14 +1727,8 @@ static void cciss_get_device_descr(int ctlr, int logvol, int withirq, return; log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol); - if (withirq) - rc = sendcmd_withirq(CISS_INQUIRY, ctlr, inq_buf, - sizeof(InquiryData_struct), 0, - scsi3addr, TYPE_CMD); - else - rc = sendcmd(CISS_INQUIRY, ctlr, inq_buf, - sizeof(InquiryData_struct), 0, - scsi3addr, TYPE_CMD); + rc = sendcmd_withirq(CISS_INQUIRY, ctlr, inq_buf, sizeof(*inq_buf), 0, + scsi3addr, TYPE_CMD); if (rc == IO_OK) { memcpy(vendor, &inq_buf->data_byte[8], VENDOR_LEN); vendor[VENDOR_LEN] = '\0'; @@ -1743,7 +1747,7 @@ static void cciss_get_device_descr(int ctlr, int logvol, int withirq, * number cannot be had, for whatever reason, 16 bytes of 0xff * are returned instead. */ -static void cciss_get_serial_no(int ctlr, int logvol, int withirq, +static void cciss_get_serial_no(int ctlr, int logvol, unsigned char *serial_no, int buflen) { #define PAGE_83_INQ_BYTES 64 @@ -1759,12 +1763,8 @@ static void cciss_get_serial_no(int ctlr, int logvol, int withirq, return; memset(serial_no, 0, buflen); log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol); - if (withirq) - rc = sendcmd_withirq(CISS_INQUIRY, ctlr, buf, - PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD); - else - rc = sendcmd(CISS_INQUIRY, ctlr, buf, - PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD); + rc = sendcmd_withirq(CISS_INQUIRY, ctlr, buf, + PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD); if (rc == IO_OK) memcpy(serial_no, &buf[8], buflen); kfree(buf); @@ -1793,10 +1793,10 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask); /* This is a hardware imposed limit. */ - blk_queue_max_hw_segments(disk->queue, MAXSGENTRIES); + blk_queue_max_hw_segments(disk->queue, h->maxsgentries); /* This is a limit in the driver and could be eliminated. */ - blk_queue_max_phys_segments(disk->queue, MAXSGENTRIES); + blk_queue_max_phys_segments(disk->queue, h->maxsgentries); blk_queue_max_sectors(disk->queue, h->cciss_max_sectors); @@ -1852,18 +1852,16 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time, /* testing to see if 16-byte CDBs are already being used */ if (h->cciss_read == CCISS_READ_16) { - cciss_read_capacity_16(h->ctlr, drv_index, 1, + cciss_read_capacity_16(h->ctlr, drv_index, &total_size, &block_size); } else { - cciss_read_capacity(ctlr, drv_index, 1, - &total_size, &block_size); - + cciss_read_capacity(ctlr, drv_index, &total_size, &block_size); /* if read_capacity returns all F's this volume is >2TB */ /* in size so we switch to 16-byte CDB's for all */ /* read/write ops */ if (total_size == 0xFFFFFFFFULL) { - cciss_read_capacity_16(ctlr, drv_index, 1, + cciss_read_capacity_16(ctlr, drv_index, &total_size, &block_size); h->cciss_read = CCISS_READ_16; h->cciss_write = CCISS_WRITE_16; @@ -1873,14 +1871,14 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time, } } - cciss_geometry_inquiry(ctlr, drv_index, 1, total_size, block_size, + cciss_geometry_inquiry(ctlr, drv_index, total_size, block_size, inq_buff, drvinfo); drvinfo->block_size = block_size; drvinfo->nr_blocks = total_size + 1; - cciss_get_device_descr(ctlr, drv_index, 1, drvinfo->vendor, + cciss_get_device_descr(ctlr, drv_index, drvinfo->vendor, drvinfo->model, drvinfo->rev); - cciss_get_serial_no(ctlr, drv_index, 1, drvinfo->serial_no, + cciss_get_serial_no(ctlr, drv_index, drvinfo->serial_no, sizeof(drvinfo->serial_no)); /* Save the lunid in case we deregister the disk, below. */ memcpy(drvinfo->LunID, h->drv[drv_index]->LunID, @@ -2531,6 +2529,8 @@ static int check_target_status(ctlr_info_t *h, CommandList_struct *c) case 0: return IO_OK; /* no sense */ case 1: return IO_OK; /* recovered error */ default: + if (check_for_unit_attention(h, c)) + return IO_NEEDS_RETRY; printk(KERN_WARNING "cciss%d: cmd 0x%02x " "check condition, sense key = 0x%02x\n", h->ctlr, c->Request.CDB[0], @@ -2672,7 +2672,7 @@ static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size, } static void cciss_geometry_inquiry(int ctlr, int logvol, - int withirq, sector_t total_size, + sector_t total_size, unsigned int block_size, InquiryData_struct *inq_buff, drive_info_struct *drv) @@ -2683,14 +2683,8 @@ static void cciss_geometry_inquiry(int ctlr, int logvol, memset(inq_buff, 0, sizeof(InquiryData_struct)); log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol); - if (withirq) - return_code = sendcmd_withirq(CISS_INQUIRY, ctlr, - inq_buff, sizeof(*inq_buff), - 0xC1, scsi3addr, TYPE_CMD); - else - return_code = sendcmd(CISS_INQUIRY, ctlr, inq_buff, - sizeof(*inq_buff), 0xC1, scsi3addr, - TYPE_CMD); + return_code = sendcmd_withirq(CISS_INQUIRY, ctlr, inq_buff, + sizeof(*inq_buff), 0xC1, scsi3addr, TYPE_CMD); if (return_code == IO_OK) { if (inq_buff->data_byte[8] == 0xFF) { printk(KERN_WARNING @@ -2723,7 +2717,7 @@ static void cciss_geometry_inquiry(int ctlr, int logvol, } static void -cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size, +cciss_read_capacity(int ctlr, int logvol, sector_t *total_size, unsigned int *block_size) { ReadCapdata_struct *buf; @@ -2737,14 +2731,8 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size, } log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol); - if (withirq) - return_code = sendcmd_withirq(CCISS_READ_CAPACITY, - ctlr, buf, sizeof(ReadCapdata_struct), - 0, scsi3addr, TYPE_CMD); - else - return_code = sendcmd(CCISS_READ_CAPACITY, - ctlr, buf, sizeof(ReadCapdata_struct), - 0, scsi3addr, TYPE_CMD); + return_code = sendcmd_withirq(CCISS_READ_CAPACITY, ctlr, buf, + sizeof(ReadCapdata_struct), 0, scsi3addr, TYPE_CMD); if (return_code == IO_OK) { *total_size = be32_to_cpu(*(__be32 *) buf->total_size); *block_size = be32_to_cpu(*(__be32 *) buf->block_size); @@ -2756,8 +2744,8 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size, kfree(buf); } -static void -cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size, unsigned int *block_size) +static void cciss_read_capacity_16(int ctlr, int logvol, + sector_t *total_size, unsigned int *block_size) { ReadCapdata_struct_16 *buf; int return_code; @@ -2770,16 +2758,9 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size, } log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol); - if (withirq) { - return_code = sendcmd_withirq(CCISS_READ_CAPACITY_16, - ctlr, buf, sizeof(ReadCapdata_struct_16), - 0, scsi3addr, TYPE_CMD); - } - else { - return_code = sendcmd(CCISS_READ_CAPACITY_16, - ctlr, buf, sizeof(ReadCapdata_struct_16), - 0, scsi3addr, TYPE_CMD); - } + return_code = sendcmd_withirq(CCISS_READ_CAPACITY_16, + ctlr, buf, sizeof(ReadCapdata_struct_16), + 0, scsi3addr, TYPE_CMD); if (return_code == IO_OK) { *total_size = be64_to_cpu(*(__be64 *) buf->total_size); *block_size = be32_to_cpu(*(__be32 *) buf->block_size); @@ -2820,13 +2801,13 @@ static int cciss_revalidate(struct gendisk *disk) return 1; } if (h->cciss_read == CCISS_READ_10) { - cciss_read_capacity(h->ctlr, logvol, 1, + cciss_read_capacity(h->ctlr, logvol, &total_size, &block_size); } else { - cciss_read_capacity_16(h->ctlr, logvol, 1, + cciss_read_capacity_16(h->ctlr, logvol, &total_size, &block_size); } - cciss_geometry_inquiry(h->ctlr, logvol, 1, total_size, block_size, + cciss_geometry_inquiry(h->ctlr, logvol, total_size, block_size, inq_buff, drv); blk_queue_logical_block_size(drv->queue, drv->block_size); @@ -2836,167 +2817,6 @@ static int cciss_revalidate(struct gendisk *disk) return 0; } -/* - * Wait polling for a command to complete. - * The memory mapped FIFO is polled for the completion. - * Used only at init time, interrupts from the HBA are disabled. - */ -static unsigned long pollcomplete(int ctlr) -{ - unsigned long done; - int i; - - /* Wait (up to 20 seconds) for a command to complete */ - - for (i = 20 * HZ; i > 0; i--) { - done = hba[ctlr]->access.command_completed(hba[ctlr]); - if (done == FIFO_EMPTY) - schedule_timeout_uninterruptible(1); - else - return done; - } - /* Invalid address to tell caller we ran out of time */ - return 1; -} - -/* Send command c to controller h and poll for it to complete. - * Turns interrupts off on the board. Used at driver init time - * and during SCSI error recovery. - */ -static int sendcmd_core(ctlr_info_t *h, CommandList_struct *c) -{ - int i; - unsigned long complete; - int status = IO_ERROR; - u64bit buff_dma_handle; - -resend_cmd1: - - /* Disable interrupt on the board. */ - h->access.set_intr_mask(h, CCISS_INTR_OFF); - - /* Make sure there is room in the command FIFO */ - /* Actually it should be completely empty at this time */ - /* unless we are in here doing error handling for the scsi */ - /* tape side of the driver. */ - for (i = 200000; i > 0; i--) { - /* if fifo isn't full go */ - if (!(h->access.fifo_full(h))) - break; - udelay(10); - printk(KERN_WARNING "cciss cciss%d: SendCmd FIFO full," - " waiting!\n", h->ctlr); - } - h->access.submit_command(h, c); /* Send the cmd */ - do { - complete = pollcomplete(h->ctlr); - -#ifdef CCISS_DEBUG - printk(KERN_DEBUG "cciss: command completed\n"); -#endif /* CCISS_DEBUG */ - - if (complete == 1) { - printk(KERN_WARNING - "cciss cciss%d: SendCmd Timeout out, " - "No command list address returned!\n", h->ctlr); - status = IO_ERROR; - break; - } - - /* Make sure it's the command we're expecting. */ - if ((complete & ~CISS_ERROR_BIT) != c->busaddr) { - printk(KERN_WARNING "cciss%d: Unexpected command " - "completion.\n", h->ctlr); - continue; - } - - /* It is our command. If no error, we're done. */ - if (!(complete & CISS_ERROR_BIT)) { - status = IO_OK; - break; - } - - /* There is an error... */ - - /* if data overrun or underun on Report command ignore it */ - if (((c->Request.CDB[0] == CISS_REPORT_LOG) || - (c->Request.CDB[0] == CISS_REPORT_PHYS) || - (c->Request.CDB[0] == CISS_INQUIRY)) && - ((c->err_info->CommandStatus == CMD_DATA_OVERRUN) || - (c->err_info->CommandStatus == CMD_DATA_UNDERRUN))) { - complete = c->busaddr; - status = IO_OK; - break; - } - - if (c->err_info->CommandStatus == CMD_UNSOLICITED_ABORT) { - printk(KERN_WARNING "cciss%d: unsolicited abort %p\n", - h->ctlr, c); - if (c->retry_count < MAX_CMD_RETRIES) { - printk(KERN_WARNING "cciss%d: retrying %p\n", - h->ctlr, c); - c->retry_count++; - /* erase the old error information */ - memset(c->err_info, 0, sizeof(c->err_info)); - goto resend_cmd1; - } - printk(KERN_WARNING "cciss%d: retried %p too many " - "times\n", h->ctlr, c); - status = IO_ERROR; - break; - } - - if (c->err_info->CommandStatus == CMD_UNABORTABLE) { - printk(KERN_WARNING "cciss%d: command could not be " - "aborted.\n", h->ctlr); - status = IO_ERROR; - break; - } - - if (c->err_info->CommandStatus == CMD_TARGET_STATUS) { - status = check_target_status(h, c); - break; - } - - printk(KERN_WARNING "cciss%d: sendcmd error\n", h->ctlr); - printk(KERN_WARNING "cmd = 0x%02x, CommandStatus = 0x%02x\n", - c->Request.CDB[0], c->err_info->CommandStatus); - status = IO_ERROR; - break; - - } while (1); - - /* unlock the data buffer from DMA */ - buff_dma_handle.val32.lower = c->SG[0].Addr.lower; - buff_dma_handle.val32.upper = c->SG[0].Addr.upper; - pci_unmap_single(h->pdev, (dma_addr_t) buff_dma_handle.val, - c->SG[0].Len, PCI_DMA_BIDIRECTIONAL); - return status; -} - -/* - * Send a command to the controller, and wait for it to complete. - * Used at init time, and during SCSI error recovery. - */ -static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, - __u8 page_code, unsigned char *scsi3addr, int cmd_type) -{ - CommandList_struct *c; - int status; - - c = cmd_alloc(hba[ctlr], 1); - if (!c) { - printk(KERN_WARNING "cciss: unable to get memory"); - return IO_ERROR; - } - status = fill_cmd(c, cmd, ctlr, buff, size, page_code, - scsi3addr, cmd_type); - if (status == IO_OK) - status = sendcmd_core(hba[ctlr], c); - cmd_free(hba[ctlr], c, 1); - return status; -} - /* * Map (physical) PCI mem into (virtual) kernel space */ @@ -3255,9 +3075,13 @@ static void do_cciss_request(struct request_queue *q) int seg; struct request *creq; u64bit temp64; - struct scatterlist tmp_sg[MAXSGENTRIES]; + struct scatterlist *tmp_sg; + SGDescriptor_struct *curr_sg; drive_info_struct *drv; int i, dir; + int nseg = 0; + int sg_index = 0; + int chained = 0; /* We call start_io here in case there is a command waiting on the * queue that has not been sent. @@ -3270,13 +3094,14 @@ static void do_cciss_request(struct request_queue *q) if (!creq) goto startio; - BUG_ON(creq->nr_phys_segments > MAXSGENTRIES); + BUG_ON(creq->nr_phys_segments > h->maxsgentries); if ((c = cmd_alloc(h, 1)) == NULL) goto full; blk_start_request(creq); + tmp_sg = h->scatter_list[c->cmdindex]; spin_unlock_irq(q->queue_lock); c->cmd_type = CMD_RWREQ; @@ -3305,7 +3130,7 @@ static void do_cciss_request(struct request_queue *q) (int)blk_rq_pos(creq), (int)blk_rq_sectors(creq)); #endif /* CCISS_DEBUG */ - sg_init_table(tmp_sg, MAXSGENTRIES); + sg_init_table(tmp_sg, h->maxsgentries); seg = blk_rq_map_sg(q, creq, tmp_sg); /* get the DMA records for the setup */ @@ -3314,25 +3139,70 @@ static void do_cciss_request(struct request_queue *q) else dir = PCI_DMA_TODEVICE; + curr_sg = c->SG; + sg_index = 0; + chained = 0; + for (i = 0; i < seg; i++) { - c->SG[i].Len = tmp_sg[i].length; + if (((sg_index+1) == (h->max_cmd_sgentries)) && + !chained && ((seg - i) > 1)) { + nseg = seg - i; + curr_sg[sg_index].Len = (nseg) * + sizeof(SGDescriptor_struct); + curr_sg[sg_index].Ext = CCISS_SG_CHAIN; + + /* Point to next chain block. */ + curr_sg = h->cmd_sg_list[c->cmdindex]->sgchain; + sg_index = 0; + chained = 1; + } + curr_sg[sg_index].Len = tmp_sg[i].length; temp64.val = (__u64) pci_map_page(h->pdev, sg_page(&tmp_sg[i]), - tmp_sg[i].offset, - tmp_sg[i].length, dir); - c->SG[i].Addr.lower = temp64.val32.lower; - c->SG[i].Addr.upper = temp64.val32.upper; - c->SG[i].Ext = 0; // we are not chaining + tmp_sg[i].offset, + tmp_sg[i].length, dir); + curr_sg[sg_index].Addr.lower = temp64.val32.lower; + curr_sg[sg_index].Addr.upper = temp64.val32.upper; + curr_sg[sg_index].Ext = 0; /* we are not chaining */ + + ++sg_index; } + + if (chained) { + int len; + curr_sg = c->SG; + sg_index = h->max_cmd_sgentries - 1; + len = curr_sg[sg_index].Len; + /* Setup pointer to next chain block. + * Fill out last element in current chain + * block with address of next chain block. + */ + temp64.val = pci_map_single(h->pdev, + h->cmd_sg_list[c->cmdindex]->sgchain, + len, dir); + + h->cmd_sg_list[c->cmdindex]->sg_chain_dma = temp64.val; + curr_sg[sg_index].Addr.lower = temp64.val32.lower; + curr_sg[sg_index].Addr.upper = temp64.val32.upper; + + pci_dma_sync_single_for_device(h->pdev, + h->cmd_sg_list[c->cmdindex]->sg_chain_dma, + len, dir); + } + /* track how many SG entries we are using */ if (seg > h->maxSG) h->maxSG = seg; #ifdef CCISS_DEBUG - printk(KERN_DEBUG "cciss: Submitting %u sectors in %d segments\n", - blk_rq_sectors(creq), seg); + printk(KERN_DEBUG "cciss: Submitting %ld sectors in %d segments " + "chained[%d]\n", + blk_rq_sectors(creq), seg, chained); #endif /* CCISS_DEBUG */ - c->Header.SGList = c->Header.SGTotal = seg; + c->Header.SGList = c->Header.SGTotal = seg + chained; + if (seg > h->max_cmd_sgentries) + c->Header.SGList = h->max_cmd_sgentries; + if (likely(blk_fs_request(creq))) { if(h->cciss_read == CCISS_READ_10) { c->Request.CDB[1] = 0; @@ -3513,28 +3383,33 @@ static int add_to_scan_list(struct ctlr_info *h) * @h: Pointer to the controller. * * Removes the controller from the rescan queue if present. Blocks if - * the controller is currently conducting a rescan. + * the controller is currently conducting a rescan. The controller + * can be in one of three states: + * 1. Doesn't need a scan + * 2. On the scan list, but not scanning yet (we remove it) + * 3. Busy scanning (and not on the list). In this case we want to wait for + * the scan to complete to make sure the scanning thread for this + * controller is completely idle. **/ static void remove_from_scan_list(struct ctlr_info *h) { struct ctlr_info *test_h, *tmp_h; - int scanning = 0; mutex_lock(&scan_mutex); list_for_each_entry_safe(test_h, tmp_h, &scan_q, scan_list) { - if (test_h == h) { + if (test_h == h) { /* state 2. */ list_del(&h->scan_list); complete_all(&h->scan_wait); mutex_unlock(&scan_mutex); return; } } - if (&h->busy_scanning) - scanning = 0; - mutex_unlock(&scan_mutex); - - if (scanning) + if (h->busy_scanning) { /* state 3. */ + mutex_unlock(&scan_mutex); wait_for_completion(&h->scan_wait); + } else { /* state 1, nothing to do. */ + mutex_unlock(&scan_mutex); + } } /** @@ -3573,13 +3448,11 @@ static int scan_thread(void *data) h->busy_scanning = 1; mutex_unlock(&scan_mutex); - if (h) { - rebuild_lun_table(h, 0, 0); - complete_all(&h->scan_wait); - mutex_lock(&scan_mutex); - h->busy_scanning = 0; - mutex_unlock(&scan_mutex); - } + rebuild_lun_table(h, 0, 0); + complete_all(&h->scan_wait); + mutex_lock(&scan_mutex); + h->busy_scanning = 0; + mutex_unlock(&scan_mutex); } } @@ -3605,8 +3478,22 @@ static int check_for_unit_attention(ctlr_info_t *h, CommandList_struct *c) case REPORT_LUNS_CHANGED: printk(KERN_WARNING "cciss%d: report LUN data " "changed\n", h->ctlr); - add_to_scan_list(h); - wake_up_process(cciss_scan_thread); + /* + * Here, we could call add_to_scan_list and wake up the scan thread, + * except that it's quite likely that we will get more than one + * REPORT_LUNS_CHANGED condition in quick succession, which means + * that those which occur after the first one will likely happen + * *during* the scan_thread's rescan. And the rescan code is not + * robust enough to restart in the middle, undoing what it has already + * done, and it's not clear that it's even possible to do this, since + * part of what it does is notify the block layer, which starts + * doing it's own i/o to read partition tables and so on, and the + * driver doesn't have visibility to know what might need undoing. + * In any event, if possible, it is horribly complicated to get right + * so we just don't do it for now. + * + * Note: this REPORT_LUNS_CHANGED condition only occurs on the MSA2012. + */ return 1; break; case POWER_OR_RESET: @@ -3888,6 +3775,23 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev) * leave a little room for ioctl calls. */ c->max_commands = readl(&(c->cfgtable->CmdsOutMax)); + c->maxsgentries = readl(&(c->cfgtable->MaxSGElements)); + + /* + * Limit native command to 32 s/g elements to save dma'able memory. + * Howvever spec says if 0, use 31 + */ + + c->max_cmd_sgentries = 31; + if (c->maxsgentries > 512) { + c->max_cmd_sgentries = 32; + c->chainsize = c->maxsgentries - c->max_cmd_sgentries + 1; + c->maxsgentries -= 1; /* account for chain pointer */ + } else { + c->maxsgentries = 31; /* Default to traditional value */ + c->chainsize = 0; /* traditional */ + } + c->product_name = products[prod_index].product_name; c->access = *(products[prod_index].access); c->nr_cmds = c->max_commands - 4; @@ -4214,6 +4118,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, { int i; int j = 0; + int k = 0; int rc; int dac, return_code; InquiryData_struct *inq_buff; @@ -4317,6 +4222,53 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, printk(KERN_ERR "cciss: out of memory"); goto clean4; } + + /* Need space for temp scatter list */ + hba[i]->scatter_list = kmalloc(hba[i]->max_commands * + sizeof(struct scatterlist *), + GFP_KERNEL); + for (k = 0; k < hba[i]->nr_cmds; k++) { + hba[i]->scatter_list[k] = kmalloc(sizeof(struct scatterlist) * + hba[i]->maxsgentries, + GFP_KERNEL); + if (hba[i]->scatter_list[k] == NULL) { + printk(KERN_ERR "cciss%d: could not allocate " + "s/g lists\n", i); + goto clean4; + } + } + hba[i]->cmd_sg_list = kmalloc(sizeof(struct Cmd_sg_list *) * + hba[i]->nr_cmds, + GFP_KERNEL); + if (!hba[i]->cmd_sg_list) { + printk(KERN_ERR "cciss%d: Cannot get memory for " + "s/g chaining.\n", i); + goto clean4; + } + /* Build up chain blocks for each command */ + if (hba[i]->chainsize > 0) { + for (j = 0; j < hba[i]->nr_cmds; j++) { + hba[i]->cmd_sg_list[j] = + kmalloc(sizeof(struct Cmd_sg_list), + GFP_KERNEL); + if (!hba[i]->cmd_sg_list[j]) { + printk(KERN_ERR "cciss%d: Cannot get memory " + "for chain block.\n", i); + goto clean4; + } + /* Need a block of chainsized s/g elements. */ + hba[i]->cmd_sg_list[j]->sgchain = + kmalloc((hba[i]->chainsize * + sizeof(SGDescriptor_struct)), + GFP_KERNEL); + if (!hba[i]->cmd_sg_list[j]->sgchain) { + printk(KERN_ERR "cciss%d: Cannot get memory " + "for s/g chains\n", i); + goto clean4; + } + } + } + spin_lock_init(&hba[i]->lock); /* Initialize the pdev driver private data. @@ -4362,7 +4314,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, cciss_procinit(i); - hba[i]->cciss_max_sectors = 2048; + hba[i]->cciss_max_sectors = 8192; rebuild_lun_table(hba[i], 1, 0); hba[i]->busy_initializing = 0; @@ -4370,6 +4322,20 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, clean4: kfree(hba[i]->cmd_pool_bits); + /* Free up sg elements */ + for (k = 0; k < hba[i]->nr_cmds; k++) + kfree(hba[i]->scatter_list[k]); + kfree(hba[i]->scatter_list); + /* Only free up extra s/g lists if controller supports them */ + if (hba[i]->chainsize > 0) { + for (j = 0; j < hba[i]->nr_cmds; j++) { + if (hba[i]->cmd_sg_list[j]) { + kfree(hba[i]->cmd_sg_list[j]->sgchain); + kfree(hba[i]->cmd_sg_list[j]); + } + } + kfree(hba[i]->cmd_sg_list); + } if (hba[i]->cmd_pool) pci_free_consistent(hba[i]->pdev, hba[i]->nr_cmds * sizeof(CommandList_struct), @@ -4400,30 +4366,28 @@ clean_no_release_regions: static void cciss_shutdown(struct pci_dev *pdev) { - ctlr_info_t *tmp_ptr; - int i; - char flush_buf[4]; + ctlr_info_t *h; + char *flush_buf; int return_code; - tmp_ptr = pci_get_drvdata(pdev); - if (tmp_ptr == NULL) + h = pci_get_drvdata(pdev); + flush_buf = kzalloc(4, GFP_KERNEL); + if (!flush_buf) { + printk(KERN_WARNING + "cciss:%d cache not flushed, out of memory.\n", + h->ctlr); return; - i = tmp_ptr->ctlr; - if (hba[i] == NULL) - return; - - /* Turn board interrupts off and send the flush cache command */ - /* sendcmd will turn off interrupt, and send the flush... - * To write all data in the battery backed cache to disks */ - memset(flush_buf, 0, 4); - return_code = sendcmd(CCISS_CACHE_FLUSH, i, flush_buf, 4, 0, - CTLR_LUNID, TYPE_CMD); - if (return_code == IO_OK) { - printk(KERN_INFO "Completed flushing cache on controller %d\n", i); - } else { - printk(KERN_WARNING "Error flushing cache on controller %d\n", i); } - free_irq(hba[i]->intr[2], hba[i]); + /* write all data in the battery backed cache to disk */ + memset(flush_buf, 0, 4); + return_code = sendcmd_withirq(CCISS_CACHE_FLUSH, h->ctlr, flush_buf, + 4, 0, CTLR_LUNID, TYPE_CMD); + kfree(flush_buf); + if (return_code != IO_OK) + printk(KERN_WARNING "cciss%d: Error flushing cache\n", + h->ctlr); + h->access.set_intr_mask(h, CCISS_INTR_OFF); + free_irq(h->intr[2], h); } static void __devexit cciss_remove_one(struct pci_dev *pdev) @@ -4485,6 +4449,20 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev) pci_free_consistent(hba[i]->pdev, hba[i]->nr_cmds * sizeof(ErrorInfo_struct), hba[i]->errinfo_pool, hba[i]->errinfo_pool_dhandle); kfree(hba[i]->cmd_pool_bits); + /* Free up sg elements */ + for (j = 0; j < hba[i]->nr_cmds; j++) + kfree(hba[i]->scatter_list[j]); + kfree(hba[i]->scatter_list); + /* Only free up extra s/g lists if controller supports them */ + if (hba[i]->chainsize > 0) { + for (j = 0; j < hba[i]->nr_cmds; j++) { + if (hba[i]->cmd_sg_list[j]) { + kfree(hba[i]->cmd_sg_list[j]->sgchain); + kfree(hba[i]->cmd_sg_list[j]); + } + } + kfree(hba[i]->cmd_sg_list); + } /* * Deliberately omit pci_disable_device(): it does something nasty to * Smart Array controllers that pci_enable_device does not undo diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h index 31524cf42c77..1d95db254069 100644 --- a/drivers/block/cciss.h +++ b/drivers/block/cciss.h @@ -55,7 +55,13 @@ typedef struct _drive_info_struct char device_initialized; /* indicates whether dev is initialized */ } drive_info_struct; -struct ctlr_info +struct Cmd_sg_list { + SGDescriptor_struct *sgchain; + dma_addr_t sg_chain_dma; + int chain_block_size; +}; + +struct ctlr_info { int ctlr; char devname[8]; @@ -75,6 +81,16 @@ struct ctlr_info int num_luns; int highest_lun; int usage_count; /* number of opens all all minor devices */ + /* Need space for temp sg list + * number of scatter/gathers supported + * number of scatter/gathers in chained block + */ + struct scatterlist **scatter_list; + int maxsgentries; + int chainsize; + int max_cmd_sgentries; + struct Cmd_sg_list **cmd_sg_list; + # define DOORBELL_INT 0 # define PERF_MODE_INT 1 # define SIMPLE_MODE_INT 2 diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h index dbaed1ea0da3..b50a9b261b85 100644 --- a/drivers/block/cciss_cmd.h +++ b/drivers/block/cciss_cmd.h @@ -7,7 +7,8 @@ //general boundary defintions #define SENSEINFOBYTES 32//note that this value may vary between host implementations -#define MAXSGENTRIES 31 +#define MAXSGENTRIES 32 +#define CCISS_SG_CHAIN 0x80000000 #define MAXREPLYQS 256 //Command Status value @@ -319,6 +320,10 @@ typedef struct _CfgTable_struct { BYTE ServerName[16]; DWORD HeartBeat; DWORD SCSI_Prefetch; + DWORD MaxSGElements; + DWORD MaxLogicalUnits; + DWORD MaxPhysicalDrives; + DWORD MaxPhysicalDrivesPerLogicalUnit; } CfgTable_struct; #pragma pack() #endif // CCISS_CMD_H diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c index 3315268b4ec7..5d0e46dc3632 100644 --- a/drivers/block/cciss_scsi.c +++ b/drivers/block/cciss_scsi.c @@ -755,7 +755,7 @@ complete_scsi_command( CommandList_struct *cp, int timeout, __u32 tag) cp, ei->ScsiStatus); #endif - cmd->result |= (ei->ScsiStatus < 1); + cmd->result |= (ei->ScsiStatus << 1); } else { /* scsi status is zero??? How??? */ @@ -1547,7 +1547,7 @@ cciss_engage_scsi(int ctlr) if (sa->registered) { printk("cciss%d: SCSI subsystem already engaged.\n", ctlr); spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags); - return ENXIO; + return -ENXIO; } sa->registered = 1; spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags); diff --git a/drivers/block/drbd/Kconfig b/drivers/block/drbd/Kconfig new file mode 100644 index 000000000000..f4acd04ebeef --- /dev/null +++ b/drivers/block/drbd/Kconfig @@ -0,0 +1,71 @@ +# +# DRBD device driver configuration +# + +comment "DRBD disabled because PROC_FS, INET or CONNECTOR not selected" + depends on !PROC_FS || !INET || !CONNECTOR + +config BLK_DEV_DRBD + tristate "DRBD Distributed Replicated Block Device support" + depends on PROC_FS && INET && CONNECTOR + select LRU_CACHE + default n + help + + NOTE: In order to authenticate connections you have to select + CRYPTO_HMAC and a hash function as well. + + DRBD is a shared-nothing, synchronously replicated block device. It + is designed to serve as a building block for high availability + clusters and in this context, is a "drop-in" replacement for shared + storage. Simplistically, you could see it as a network RAID 1. + + Each minor device has a role, which can be 'primary' or 'secondary'. + On the node with the primary device the application is supposed to + run and to access the device (/dev/drbdX). Every write is sent to + the local 'lower level block device' and, across the network, to the + node with the device in 'secondary' state. The secondary device + simply writes the data to its lower level block device. + + DRBD can also be used in dual-Primary mode (device writable on both + nodes), which means it can exhibit shared disk semantics in a + shared-nothing cluster. Needless to say, on top of dual-Primary + DRBD utilizing a cluster file system is necessary to maintain for + cache coherency. + + For automatic failover you need a cluster manager (e.g. heartbeat). + See also: http://www.drbd.org/, http://www.linux-ha.org + + If unsure, say N. + +config DRBD_FAULT_INJECTION + bool "DRBD fault injection" + depends on BLK_DEV_DRBD + help + + Say Y here if you want to simulate IO errors, in order to test DRBD's + behavior. + + The actual simulation of IO errors is done by writing 3 values to + /sys/module/drbd/parameters/ + + enable_faults: bitmask of... + 1 meta data write + 2 read + 4 resync data write + 8 read + 16 data write + 32 data read + 64 read ahead + 128 kmalloc of bitmap + 256 allocation of EE (epoch_entries) + + fault_devs: bitmask of minor numbers + fault_rate: frequency in percent + + Example: Simulate data write errors on /dev/drbd0 with a probability of 5%. + echo 16 > /sys/module/drbd/parameters/enable_faults + echo 1 > /sys/module/drbd/parameters/fault_devs + echo 5 > /sys/module/drbd/parameters/fault_rate + + If unsure, say N. diff --git a/drivers/block/drbd/Makefile b/drivers/block/drbd/Makefile new file mode 100644 index 000000000000..0d3f337ff5ff --- /dev/null +++ b/drivers/block/drbd/Makefile @@ -0,0 +1,5 @@ +drbd-y := drbd_bitmap.o drbd_proc.o +drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o +drbd-y += drbd_main.o drbd_strings.o drbd_nl.o + +obj-$(CONFIG_BLK_DEV_DRBD) += drbd.o diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c new file mode 100644 index 000000000000..17956ff6a08d --- /dev/null +++ b/drivers/block/drbd/drbd_actlog.c @@ -0,0 +1,1424 @@ +/* + drbd_actlog.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2003-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2003-2008, Philipp Reisner . + Copyright (C) 2003-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include +#include +#include "drbd_int.h" +#include "drbd_wrappers.h" + +/* We maintain a trivial check sum in our on disk activity log. + * With that we can ensure correct operation even when the storage + * device might do a partial (last) sector write while loosing power. + */ +struct __packed al_transaction { + u32 magic; + u32 tr_number; + struct __packed { + u32 pos; + u32 extent; } updates[1 + AL_EXTENTS_PT]; + u32 xor_sum; +}; + +struct update_odbm_work { + struct drbd_work w; + unsigned int enr; +}; + +struct update_al_work { + struct drbd_work w; + struct lc_element *al_ext; + struct completion event; + unsigned int enr; + /* if old_enr != LC_FREE, write corresponding bitmap sector, too */ + unsigned int old_enr; +}; + +struct drbd_atodb_wait { + atomic_t count; + struct completion io_done; + struct drbd_conf *mdev; + int error; +}; + + +int w_al_write_transaction(struct drbd_conf *, struct drbd_work *, int); + +static int _drbd_md_sync_page_io(struct drbd_conf *mdev, + struct drbd_backing_dev *bdev, + struct page *page, sector_t sector, + int rw, int size) +{ + struct bio *bio; + struct drbd_md_io md_io; + int ok; + + md_io.mdev = mdev; + init_completion(&md_io.event); + md_io.error = 0; + + if ((rw & WRITE) && !test_bit(MD_NO_BARRIER, &mdev->flags)) + rw |= (1 << BIO_RW_BARRIER); + rw |= ((1<bi_bdev = bdev->md_bdev; + bio->bi_sector = sector; + ok = (bio_add_page(bio, page, size, 0) == size); + if (!ok) + goto out; + bio->bi_private = &md_io; + bio->bi_end_io = drbd_md_io_complete; + bio->bi_rw = rw; + + if (FAULT_ACTIVE(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) + bio_endio(bio, -EIO); + else + submit_bio(rw, bio); + wait_for_completion(&md_io.event); + ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0; + + /* check for unsupported barrier op. + * would rather check on EOPNOTSUPP, but that is not reliable. + * don't try again for ANY return value != 0 */ + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER) && !ok)) { + /* Try again with no barrier */ + dev_warn(DEV, "Barriers not supported on meta data device - disabling\n"); + set_bit(MD_NO_BARRIER, &mdev->flags); + rw &= ~(1 << BIO_RW_BARRIER); + bio_put(bio); + goto retry; + } + out: + bio_put(bio); + return ok; +} + +int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev, + sector_t sector, int rw) +{ + int logical_block_size, mask, ok; + int offset = 0; + struct page *iop = mdev->md_io_page; + + D_ASSERT(mutex_is_locked(&mdev->md_io_mutex)); + + BUG_ON(!bdev->md_bdev); + + logical_block_size = bdev_logical_block_size(bdev->md_bdev); + if (logical_block_size == 0) + logical_block_size = MD_SECTOR_SIZE; + + /* in case logical_block_size != 512 [ s390 only? ] */ + if (logical_block_size != MD_SECTOR_SIZE) { + mask = (logical_block_size / MD_SECTOR_SIZE) - 1; + D_ASSERT(mask == 1 || mask == 3 || mask == 7); + D_ASSERT(logical_block_size == (mask+1) * MD_SECTOR_SIZE); + offset = sector & mask; + sector = sector & ~mask; + iop = mdev->md_io_tmpp; + + if (rw & WRITE) { + /* these are GFP_KERNEL pages, pre-allocated + * on device initialization */ + void *p = page_address(mdev->md_io_page); + void *hp = page_address(mdev->md_io_tmpp); + + ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, + READ, logical_block_size); + + if (unlikely(!ok)) { + dev_err(DEV, "drbd_md_sync_page_io(,%llus," + "READ [logical_block_size!=512]) failed!\n", + (unsigned long long)sector); + return 0; + } + + memcpy(hp + offset*MD_SECTOR_SIZE, p, MD_SECTOR_SIZE); + } + } + + if (sector < drbd_md_first_sector(bdev) || + sector > drbd_md_last_sector(bdev)) + dev_alert(DEV, "%s [%d]:%s(,%llus,%s) out of range md access!\n", + current->comm, current->pid, __func__, + (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ"); + + ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, logical_block_size); + if (unlikely(!ok)) { + dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed!\n", + (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ"); + return 0; + } + + if (logical_block_size != MD_SECTOR_SIZE && !(rw & WRITE)) { + void *p = page_address(mdev->md_io_page); + void *hp = page_address(mdev->md_io_tmpp); + + memcpy(p, hp + offset*MD_SECTOR_SIZE, MD_SECTOR_SIZE); + } + + return ok; +} + +static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr) +{ + struct lc_element *al_ext; + struct lc_element *tmp; + unsigned long al_flags = 0; + + spin_lock_irq(&mdev->al_lock); + tmp = lc_find(mdev->resync, enr/AL_EXT_PER_BM_SECT); + if (unlikely(tmp != NULL)) { + struct bm_extent *bm_ext = lc_entry(tmp, struct bm_extent, lce); + if (test_bit(BME_NO_WRITES, &bm_ext->flags)) { + spin_unlock_irq(&mdev->al_lock); + return NULL; + } + } + al_ext = lc_get(mdev->act_log, enr); + al_flags = mdev->act_log->flags; + spin_unlock_irq(&mdev->al_lock); + + /* + if (!al_ext) { + if (al_flags & LC_STARVING) + dev_warn(DEV, "Have to wait for LRU element (AL too small?)\n"); + if (al_flags & LC_DIRTY) + dev_warn(DEV, "Ongoing AL update (AL device too slow?)\n"); + } + */ + + return al_ext; +} + +void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector) +{ + unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9)); + struct lc_element *al_ext; + struct update_al_work al_work; + + D_ASSERT(atomic_read(&mdev->local_cnt) > 0); + + wait_event(mdev->al_wait, (al_ext = _al_get(mdev, enr))); + + if (al_ext->lc_number != enr) { + /* drbd_al_write_transaction(mdev,al_ext,enr); + * recurses into generic_make_request(), which + * disallows recursion, bios being serialized on the + * current->bio_tail list now. + * we have to delegate updates to the activity log + * to the worker thread. */ + init_completion(&al_work.event); + al_work.al_ext = al_ext; + al_work.enr = enr; + al_work.old_enr = al_ext->lc_number; + al_work.w.cb = w_al_write_transaction; + drbd_queue_work_front(&mdev->data.work, &al_work.w); + wait_for_completion(&al_work.event); + + mdev->al_writ_cnt++; + + spin_lock_irq(&mdev->al_lock); + lc_changed(mdev->act_log, al_ext); + spin_unlock_irq(&mdev->al_lock); + wake_up(&mdev->al_wait); + } +} + +void drbd_al_complete_io(struct drbd_conf *mdev, sector_t sector) +{ + unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9)); + struct lc_element *extent; + unsigned long flags; + + spin_lock_irqsave(&mdev->al_lock, flags); + + extent = lc_find(mdev->act_log, enr); + + if (!extent) { + spin_unlock_irqrestore(&mdev->al_lock, flags); + dev_err(DEV, "al_complete_io() called on inactive extent %u\n", enr); + return; + } + + if (lc_put(mdev->act_log, extent) == 0) + wake_up(&mdev->al_wait); + + spin_unlock_irqrestore(&mdev->al_lock, flags); +} + +int +w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct update_al_work *aw = container_of(w, struct update_al_work, w); + struct lc_element *updated = aw->al_ext; + const unsigned int new_enr = aw->enr; + const unsigned int evicted = aw->old_enr; + struct al_transaction *buffer; + sector_t sector; + int i, n, mx; + unsigned int extent_nr; + u32 xor_sum = 0; + + if (!get_ldev(mdev)) { + dev_err(DEV, "get_ldev() failed in w_al_write_transaction\n"); + complete(&((struct update_al_work *)w)->event); + return 1; + } + /* do we have to do a bitmap write, first? + * TODO reduce maximum latency: + * submit both bios, then wait for both, + * instead of doing two synchronous sector writes. */ + if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE) + drbd_bm_write_sect(mdev, evicted/AL_EXT_PER_BM_SECT); + + mutex_lock(&mdev->md_io_mutex); /* protects md_io_page, al_tr_cycle, ... */ + buffer = (struct al_transaction *)page_address(mdev->md_io_page); + + buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC); + buffer->tr_number = cpu_to_be32(mdev->al_tr_number); + + n = lc_index_of(mdev->act_log, updated); + + buffer->updates[0].pos = cpu_to_be32(n); + buffer->updates[0].extent = cpu_to_be32(new_enr); + + xor_sum ^= new_enr; + + mx = min_t(int, AL_EXTENTS_PT, + mdev->act_log->nr_elements - mdev->al_tr_cycle); + for (i = 0; i < mx; i++) { + unsigned idx = mdev->al_tr_cycle + i; + extent_nr = lc_element_by_index(mdev->act_log, idx)->lc_number; + buffer->updates[i+1].pos = cpu_to_be32(idx); + buffer->updates[i+1].extent = cpu_to_be32(extent_nr); + xor_sum ^= extent_nr; + } + for (; i < AL_EXTENTS_PT; i++) { + buffer->updates[i+1].pos = __constant_cpu_to_be32(-1); + buffer->updates[i+1].extent = __constant_cpu_to_be32(LC_FREE); + xor_sum ^= LC_FREE; + } + mdev->al_tr_cycle += AL_EXTENTS_PT; + if (mdev->al_tr_cycle >= mdev->act_log->nr_elements) + mdev->al_tr_cycle = 0; + + buffer->xor_sum = cpu_to_be32(xor_sum); + + sector = mdev->ldev->md.md_offset + + mdev->ldev->md.al_offset + mdev->al_tr_pos; + + if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) + drbd_chk_io_error(mdev, 1, TRUE); + + if (++mdev->al_tr_pos > + div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT)) + mdev->al_tr_pos = 0; + + D_ASSERT(mdev->al_tr_pos < MD_AL_MAX_SIZE); + mdev->al_tr_number++; + + mutex_unlock(&mdev->md_io_mutex); + + complete(&((struct update_al_work *)w)->event); + put_ldev(mdev); + + return 1; +} + +/** + * drbd_al_read_tr() - Read a single transaction from the on disk activity log + * @mdev: DRBD device. + * @bdev: Block device to read form. + * @b: pointer to an al_transaction. + * @index: On disk slot of the transaction to read. + * + * Returns -1 on IO error, 0 on checksum error and 1 upon success. + */ +static int drbd_al_read_tr(struct drbd_conf *mdev, + struct drbd_backing_dev *bdev, + struct al_transaction *b, + int index) +{ + sector_t sector; + int rv, i; + u32 xor_sum = 0; + + sector = bdev->md.md_offset + bdev->md.al_offset + index; + + /* Dont process error normally, + * as this is done before disk is attached! */ + if (!drbd_md_sync_page_io(mdev, bdev, sector, READ)) + return -1; + + rv = (be32_to_cpu(b->magic) == DRBD_MAGIC); + + for (i = 0; i < AL_EXTENTS_PT + 1; i++) + xor_sum ^= be32_to_cpu(b->updates[i].extent); + rv &= (xor_sum == be32_to_cpu(b->xor_sum)); + + return rv; +} + +/** + * drbd_al_read_log() - Restores the activity log from its on disk representation. + * @mdev: DRBD device. + * @bdev: Block device to read form. + * + * Returns 1 on success, returns 0 when reading the log failed due to IO errors. + */ +int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev) +{ + struct al_transaction *buffer; + int i; + int rv; + int mx; + int active_extents = 0; + int transactions = 0; + int found_valid = 0; + int from = 0; + int to = 0; + u32 from_tnr = 0; + u32 to_tnr = 0; + u32 cnr; + + mx = div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT); + + /* lock out all other meta data io for now, + * and make sure the page is mapped. + */ + mutex_lock(&mdev->md_io_mutex); + buffer = page_address(mdev->md_io_page); + + /* Find the valid transaction in the log */ + for (i = 0; i <= mx; i++) { + rv = drbd_al_read_tr(mdev, bdev, buffer, i); + if (rv == 0) + continue; + if (rv == -1) { + mutex_unlock(&mdev->md_io_mutex); + return 0; + } + cnr = be32_to_cpu(buffer->tr_number); + + if (++found_valid == 1) { + from = i; + to = i; + from_tnr = cnr; + to_tnr = cnr; + continue; + } + if ((int)cnr - (int)from_tnr < 0) { + D_ASSERT(from_tnr - cnr + i - from == mx+1); + from = i; + from_tnr = cnr; + } + if ((int)cnr - (int)to_tnr > 0) { + D_ASSERT(cnr - to_tnr == i - to); + to = i; + to_tnr = cnr; + } + } + + if (!found_valid) { + dev_warn(DEV, "No usable activity log found.\n"); + mutex_unlock(&mdev->md_io_mutex); + return 1; + } + + /* Read the valid transactions. + * dev_info(DEV, "Reading from %d to %d.\n",from,to); */ + i = from; + while (1) { + int j, pos; + unsigned int extent_nr; + unsigned int trn; + + rv = drbd_al_read_tr(mdev, bdev, buffer, i); + ERR_IF(rv == 0) goto cancel; + if (rv == -1) { + mutex_unlock(&mdev->md_io_mutex); + return 0; + } + + trn = be32_to_cpu(buffer->tr_number); + + spin_lock_irq(&mdev->al_lock); + + /* This loop runs backwards because in the cyclic + elements there might be an old version of the + updated element (in slot 0). So the element in slot 0 + can overwrite old versions. */ + for (j = AL_EXTENTS_PT; j >= 0; j--) { + pos = be32_to_cpu(buffer->updates[j].pos); + extent_nr = be32_to_cpu(buffer->updates[j].extent); + + if (extent_nr == LC_FREE) + continue; + + lc_set(mdev->act_log, extent_nr, pos); + active_extents++; + } + spin_unlock_irq(&mdev->al_lock); + + transactions++; + +cancel: + if (i == to) + break; + i++; + if (i > mx) + i = 0; + } + + mdev->al_tr_number = to_tnr+1; + mdev->al_tr_pos = to; + if (++mdev->al_tr_pos > + div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT)) + mdev->al_tr_pos = 0; + + /* ok, we are done with it */ + mutex_unlock(&mdev->md_io_mutex); + + dev_info(DEV, "Found %d transactions (%d active extents) in activity log.\n", + transactions, active_extents); + + return 1; +} + +static void atodb_endio(struct bio *bio, int error) +{ + struct drbd_atodb_wait *wc = bio->bi_private; + struct drbd_conf *mdev = wc->mdev; + struct page *page; + int uptodate = bio_flagged(bio, BIO_UPTODATE); + + /* strange behavior of some lower level drivers... + * fail the request by clearing the uptodate flag, + * but do not return any error?! */ + if (!error && !uptodate) + error = -EIO; + + drbd_chk_io_error(mdev, error, TRUE); + if (error && wc->error == 0) + wc->error = error; + + if (atomic_dec_and_test(&wc->count)) + complete(&wc->io_done); + + page = bio->bi_io_vec[0].bv_page; + put_page(page); + bio_put(bio); + mdev->bm_writ_cnt++; + put_ldev(mdev); +} + +#define S2W(s) ((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL)) +/* activity log to on disk bitmap -- prepare bio unless that sector + * is already covered by previously prepared bios */ +static int atodb_prepare_unless_covered(struct drbd_conf *mdev, + struct bio **bios, + unsigned int enr, + struct drbd_atodb_wait *wc) __must_hold(local) +{ + struct bio *bio; + struct page *page; + sector_t on_disk_sector = enr + mdev->ldev->md.md_offset + + mdev->ldev->md.bm_offset; + unsigned int page_offset = PAGE_SIZE; + int offset; + int i = 0; + int err = -ENOMEM; + + /* Check if that enr is already covered by an already created bio. + * Caution, bios[] is not NULL terminated, + * but only initialized to all NULL. + * For completely scattered activity log, + * the last invocation iterates over all bios, + * and finds the last NULL entry. + */ + while ((bio = bios[i])) { + if (bio->bi_sector == on_disk_sector) + return 0; + i++; + } + /* bios[i] == NULL, the next not yet used slot */ + + /* GFP_KERNEL, we are not in the write-out path */ + bio = bio_alloc(GFP_KERNEL, 1); + if (bio == NULL) + return -ENOMEM; + + if (i > 0) { + const struct bio_vec *prev_bv = bios[i-1]->bi_io_vec; + page_offset = prev_bv->bv_offset + prev_bv->bv_len; + page = prev_bv->bv_page; + } + if (page_offset == PAGE_SIZE) { + page = alloc_page(__GFP_HIGHMEM); + if (page == NULL) + goto out_bio_put; + page_offset = 0; + } else { + get_page(page); + } + + offset = S2W(enr); + drbd_bm_get_lel(mdev, offset, + min_t(size_t, S2W(1), drbd_bm_words(mdev) - offset), + kmap(page) + page_offset); + kunmap(page); + + bio->bi_private = wc; + bio->bi_end_io = atodb_endio; + bio->bi_bdev = mdev->ldev->md_bdev; + bio->bi_sector = on_disk_sector; + + if (bio_add_page(bio, page, MD_SECTOR_SIZE, page_offset) != MD_SECTOR_SIZE) + goto out_put_page; + + atomic_inc(&wc->count); + /* we already know that we may do this... + * get_ldev_if_state(mdev,D_ATTACHING); + * just get the extra reference, so that the local_cnt reflects + * the number of pending IO requests DRBD at its backing device. + */ + atomic_inc(&mdev->local_cnt); + + bios[i] = bio; + + return 0; + +out_put_page: + err = -EINVAL; + put_page(page); +out_bio_put: + bio_put(bio); + return err; +} + +/** + * drbd_al_to_on_disk_bm() - * Writes bitmap parts covered by active AL extents + * @mdev: DRBD device. + * + * Called when we detach (unconfigure) local storage, + * or when we go from R_PRIMARY to R_SECONDARY role. + */ +void drbd_al_to_on_disk_bm(struct drbd_conf *mdev) +{ + int i, nr_elements; + unsigned int enr; + struct bio **bios; + struct drbd_atodb_wait wc; + + ERR_IF (!get_ldev_if_state(mdev, D_ATTACHING)) + return; /* sorry, I don't have any act_log etc... */ + + wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); + + nr_elements = mdev->act_log->nr_elements; + + /* GFP_KERNEL, we are not in anyone's write-out path */ + bios = kzalloc(sizeof(struct bio *) * nr_elements, GFP_KERNEL); + if (!bios) + goto submit_one_by_one; + + atomic_set(&wc.count, 0); + init_completion(&wc.io_done); + wc.mdev = mdev; + wc.error = 0; + + for (i = 0; i < nr_elements; i++) { + enr = lc_element_by_index(mdev->act_log, i)->lc_number; + if (enr == LC_FREE) + continue; + /* next statement also does atomic_inc wc.count and local_cnt */ + if (atodb_prepare_unless_covered(mdev, bios, + enr/AL_EXT_PER_BM_SECT, + &wc)) + goto free_bios_submit_one_by_one; + } + + /* unnecessary optimization? */ + lc_unlock(mdev->act_log); + wake_up(&mdev->al_wait); + + /* all prepared, submit them */ + for (i = 0; i < nr_elements; i++) { + if (bios[i] == NULL) + break; + if (FAULT_ACTIVE(mdev, DRBD_FAULT_MD_WR)) { + bios[i]->bi_rw = WRITE; + bio_endio(bios[i], -EIO); + } else { + submit_bio(WRITE, bios[i]); + } + } + + drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev)); + + /* always (try to) flush bitmap to stable storage */ + drbd_md_flush(mdev); + + /* In case we did not submit a single IO do not wait for + * them to complete. ( Because we would wait forever here. ) + * + * In case we had IOs and they are already complete, there + * is not point in waiting anyways. + * Therefore this if () ... */ + if (atomic_read(&wc.count)) + wait_for_completion(&wc.io_done); + + put_ldev(mdev); + + kfree(bios); + return; + + free_bios_submit_one_by_one: + /* free everything by calling the endio callback directly. */ + for (i = 0; i < nr_elements && bios[i]; i++) + bio_endio(bios[i], 0); + + kfree(bios); + + submit_one_by_one: + dev_warn(DEV, "Using the slow drbd_al_to_on_disk_bm()\n"); + + for (i = 0; i < mdev->act_log->nr_elements; i++) { + enr = lc_element_by_index(mdev->act_log, i)->lc_number; + if (enr == LC_FREE) + continue; + /* Really slow: if we have al-extents 16..19 active, + * sector 4 will be written four times! Synchronous! */ + drbd_bm_write_sect(mdev, enr/AL_EXT_PER_BM_SECT); + } + + lc_unlock(mdev->act_log); + wake_up(&mdev->al_wait); + put_ldev(mdev); +} + +/** + * drbd_al_apply_to_bm() - Sets the bitmap to diry(1) where covered ba active AL extents + * @mdev: DRBD device. + */ +void drbd_al_apply_to_bm(struct drbd_conf *mdev) +{ + unsigned int enr; + unsigned long add = 0; + char ppb[10]; + int i; + + wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); + + for (i = 0; i < mdev->act_log->nr_elements; i++) { + enr = lc_element_by_index(mdev->act_log, i)->lc_number; + if (enr == LC_FREE) + continue; + add += drbd_bm_ALe_set_all(mdev, enr); + } + + lc_unlock(mdev->act_log); + wake_up(&mdev->al_wait); + + dev_info(DEV, "Marked additional %s as out-of-sync based on AL.\n", + ppsize(ppb, Bit2KB(add))); +} + +static int _try_lc_del(struct drbd_conf *mdev, struct lc_element *al_ext) +{ + int rv; + + spin_lock_irq(&mdev->al_lock); + rv = (al_ext->refcnt == 0); + if (likely(rv)) + lc_del(mdev->act_log, al_ext); + spin_unlock_irq(&mdev->al_lock); + + return rv; +} + +/** + * drbd_al_shrink() - Removes all active extents form the activity log + * @mdev: DRBD device. + * + * Removes all active extents form the activity log, waiting until + * the reference count of each entry dropped to 0 first, of course. + * + * You need to lock mdev->act_log with lc_try_lock() / lc_unlock() + */ +void drbd_al_shrink(struct drbd_conf *mdev) +{ + struct lc_element *al_ext; + int i; + + D_ASSERT(test_bit(__LC_DIRTY, &mdev->act_log->flags)); + + for (i = 0; i < mdev->act_log->nr_elements; i++) { + al_ext = lc_element_by_index(mdev->act_log, i); + if (al_ext->lc_number == LC_FREE) + continue; + wait_event(mdev->al_wait, _try_lc_del(mdev, al_ext)); + } + + wake_up(&mdev->al_wait); +} + +static int w_update_odbm(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w); + + if (!get_ldev(mdev)) { + if (__ratelimit(&drbd_ratelimit_state)) + dev_warn(DEV, "Can not update on disk bitmap, local IO disabled.\n"); + kfree(udw); + return 1; + } + + drbd_bm_write_sect(mdev, udw->enr); + put_ldev(mdev); + + kfree(udw); + + if (drbd_bm_total_weight(mdev) <= mdev->rs_failed) { + switch (mdev->state.conn) { + case C_SYNC_SOURCE: case C_SYNC_TARGET: + case C_PAUSED_SYNC_S: case C_PAUSED_SYNC_T: + drbd_resync_finished(mdev); + default: + /* nothing to do */ + break; + } + } + drbd_bcast_sync_progress(mdev); + + return 1; +} + + +/* ATTENTION. The AL's extents are 4MB each, while the extents in the + * resync LRU-cache are 16MB each. + * The caller of this function has to hold an get_ldev() reference. + * + * TODO will be obsoleted once we have a caching lru of the on disk bitmap + */ +static void drbd_try_clear_on_disk_bm(struct drbd_conf *mdev, sector_t sector, + int count, int success) +{ + struct lc_element *e; + struct update_odbm_work *udw; + + unsigned int enr; + + D_ASSERT(atomic_read(&mdev->local_cnt)); + + /* I simply assume that a sector/size pair never crosses + * a 16 MB extent border. (Currently this is true...) */ + enr = BM_SECT_TO_EXT(sector); + + e = lc_get(mdev->resync, enr); + if (e) { + struct bm_extent *ext = lc_entry(e, struct bm_extent, lce); + if (ext->lce.lc_number == enr) { + if (success) + ext->rs_left -= count; + else + ext->rs_failed += count; + if (ext->rs_left < ext->rs_failed) { + dev_err(DEV, "BAD! sector=%llus enr=%u rs_left=%d " + "rs_failed=%d count=%d\n", + (unsigned long long)sector, + ext->lce.lc_number, ext->rs_left, + ext->rs_failed, count); + dump_stack(); + + lc_put(mdev->resync, &ext->lce); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return; + } + } else { + /* Normally this element should be in the cache, + * since drbd_rs_begin_io() pulled it already in. + * + * But maybe an application write finished, and we set + * something outside the resync lru_cache in sync. + */ + int rs_left = drbd_bm_e_weight(mdev, enr); + if (ext->flags != 0) { + dev_warn(DEV, "changing resync lce: %d[%u;%02lx]" + " -> %d[%u;00]\n", + ext->lce.lc_number, ext->rs_left, + ext->flags, enr, rs_left); + ext->flags = 0; + } + if (ext->rs_failed) { + dev_warn(DEV, "Kicking resync_lru element enr=%u " + "out with rs_failed=%d\n", + ext->lce.lc_number, ext->rs_failed); + set_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags); + } + ext->rs_left = rs_left; + ext->rs_failed = success ? 0 : count; + lc_changed(mdev->resync, &ext->lce); + } + lc_put(mdev->resync, &ext->lce); + /* no race, we are within the al_lock! */ + + if (ext->rs_left == ext->rs_failed) { + ext->rs_failed = 0; + + udw = kmalloc(sizeof(*udw), GFP_ATOMIC); + if (udw) { + udw->enr = ext->lce.lc_number; + udw->w.cb = w_update_odbm; + drbd_queue_work_front(&mdev->data.work, &udw->w); + } else { + dev_warn(DEV, "Could not kmalloc an udw\n"); + set_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags); + } + } + } else { + dev_err(DEV, "lc_get() failed! locked=%d/%d flags=%lu\n", + mdev->resync_locked, + mdev->resync->nr_elements, + mdev->resync->flags); + } +} + +/* clear the bit corresponding to the piece of storage in question: + * size byte of data starting from sector. Only clear a bits of the affected + * one ore more _aligned_ BM_BLOCK_SIZE blocks. + * + * called by worker on C_SYNC_TARGET and receiver on SyncSource. + * + */ +void __drbd_set_in_sync(struct drbd_conf *mdev, sector_t sector, int size, + const char *file, const unsigned int line) +{ + /* Is called from worker and receiver context _only_ */ + unsigned long sbnr, ebnr, lbnr; + unsigned long count = 0; + sector_t esector, nr_sectors; + int wake_up = 0; + unsigned long flags; + + if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) { + dev_err(DEV, "drbd_set_in_sync: sector=%llus size=%d nonsense!\n", + (unsigned long long)sector, size); + return; + } + nr_sectors = drbd_get_capacity(mdev->this_bdev); + esector = sector + (size >> 9) - 1; + + ERR_IF(sector >= nr_sectors) return; + ERR_IF(esector >= nr_sectors) esector = (nr_sectors-1); + + lbnr = BM_SECT_TO_BIT(nr_sectors-1); + + /* we clear it (in sync). + * round up start sector, round down end sector. we make sure we only + * clear full, aligned, BM_BLOCK_SIZE (4K) blocks */ + if (unlikely(esector < BM_SECT_PER_BIT-1)) + return; + if (unlikely(esector == (nr_sectors-1))) + ebnr = lbnr; + else + ebnr = BM_SECT_TO_BIT(esector - (BM_SECT_PER_BIT-1)); + sbnr = BM_SECT_TO_BIT(sector + BM_SECT_PER_BIT-1); + + if (sbnr > ebnr) + return; + + /* + * ok, (capacity & 7) != 0 sometimes, but who cares... + * we count rs_{total,left} in bits, not sectors. + */ + spin_lock_irqsave(&mdev->al_lock, flags); + count = drbd_bm_clear_bits(mdev, sbnr, ebnr); + if (count) { + /* we need the lock for drbd_try_clear_on_disk_bm */ + if (jiffies - mdev->rs_mark_time > HZ*10) { + /* should be rolling marks, + * but we estimate only anyways. */ + if (mdev->rs_mark_left != drbd_bm_total_weight(mdev) && + mdev->state.conn != C_PAUSED_SYNC_T && + mdev->state.conn != C_PAUSED_SYNC_S) { + mdev->rs_mark_time = jiffies; + mdev->rs_mark_left = drbd_bm_total_weight(mdev); + } + } + if (get_ldev(mdev)) { + drbd_try_clear_on_disk_bm(mdev, sector, count, TRUE); + put_ldev(mdev); + } + /* just wake_up unconditional now, various lc_chaged(), + * lc_put() in drbd_try_clear_on_disk_bm(). */ + wake_up = 1; + } + spin_unlock_irqrestore(&mdev->al_lock, flags); + if (wake_up) + wake_up(&mdev->al_wait); +} + +/* + * this is intended to set one request worth of data out of sync. + * affects at least 1 bit, + * and at most 1+DRBD_MAX_SEGMENT_SIZE/BM_BLOCK_SIZE bits. + * + * called by tl_clear and drbd_send_dblock (==drbd_make_request). + * so this can be _any_ process. + */ +void __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, int size, + const char *file, const unsigned int line) +{ + unsigned long sbnr, ebnr, lbnr, flags; + sector_t esector, nr_sectors; + unsigned int enr, count; + struct lc_element *e; + + if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) { + dev_err(DEV, "sector: %llus, size: %d\n", + (unsigned long long)sector, size); + return; + } + + if (!get_ldev(mdev)) + return; /* no disk, no metadata, no bitmap to set bits in */ + + nr_sectors = drbd_get_capacity(mdev->this_bdev); + esector = sector + (size >> 9) - 1; + + ERR_IF(sector >= nr_sectors) + goto out; + ERR_IF(esector >= nr_sectors) + esector = (nr_sectors-1); + + lbnr = BM_SECT_TO_BIT(nr_sectors-1); + + /* we set it out of sync, + * we do not need to round anything here */ + sbnr = BM_SECT_TO_BIT(sector); + ebnr = BM_SECT_TO_BIT(esector); + + /* ok, (capacity & 7) != 0 sometimes, but who cares... + * we count rs_{total,left} in bits, not sectors. */ + spin_lock_irqsave(&mdev->al_lock, flags); + count = drbd_bm_set_bits(mdev, sbnr, ebnr); + + enr = BM_SECT_TO_EXT(sector); + e = lc_find(mdev->resync, enr); + if (e) + lc_entry(e, struct bm_extent, lce)->rs_left += count; + spin_unlock_irqrestore(&mdev->al_lock, flags); + +out: + put_ldev(mdev); +} + +static +struct bm_extent *_bme_get(struct drbd_conf *mdev, unsigned int enr) +{ + struct lc_element *e; + struct bm_extent *bm_ext; + int wakeup = 0; + unsigned long rs_flags; + + spin_lock_irq(&mdev->al_lock); + if (mdev->resync_locked > mdev->resync->nr_elements/2) { + spin_unlock_irq(&mdev->al_lock); + return NULL; + } + e = lc_get(mdev->resync, enr); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (bm_ext) { + if (bm_ext->lce.lc_number != enr) { + bm_ext->rs_left = drbd_bm_e_weight(mdev, enr); + bm_ext->rs_failed = 0; + lc_changed(mdev->resync, &bm_ext->lce); + wakeup = 1; + } + if (bm_ext->lce.refcnt == 1) + mdev->resync_locked++; + set_bit(BME_NO_WRITES, &bm_ext->flags); + } + rs_flags = mdev->resync->flags; + spin_unlock_irq(&mdev->al_lock); + if (wakeup) + wake_up(&mdev->al_wait); + + if (!bm_ext) { + if (rs_flags & LC_STARVING) + dev_warn(DEV, "Have to wait for element" + " (resync LRU too small?)\n"); + BUG_ON(rs_flags & LC_DIRTY); + } + + return bm_ext; +} + +static int _is_in_al(struct drbd_conf *mdev, unsigned int enr) +{ + struct lc_element *al_ext; + int rv = 0; + + spin_lock_irq(&mdev->al_lock); + if (unlikely(enr == mdev->act_log->new_number)) + rv = 1; + else { + al_ext = lc_find(mdev->act_log, enr); + if (al_ext) { + if (al_ext->refcnt) + rv = 1; + } + } + spin_unlock_irq(&mdev->al_lock); + + /* + if (unlikely(rv)) { + dev_info(DEV, "Delaying sync read until app's write is done\n"); + } + */ + return rv; +} + +/** + * drbd_rs_begin_io() - Gets an extent in the resync LRU cache and sets it to BME_LOCKED + * @mdev: DRBD device. + * @sector: The sector number. + * + * This functions sleeps on al_wait. Returns 1 on success, 0 if interrupted. + */ +int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector) +{ + unsigned int enr = BM_SECT_TO_EXT(sector); + struct bm_extent *bm_ext; + int i, sig; + + sig = wait_event_interruptible(mdev->al_wait, + (bm_ext = _bme_get(mdev, enr))); + if (sig) + return 0; + + if (test_bit(BME_LOCKED, &bm_ext->flags)) + return 1; + + for (i = 0; i < AL_EXT_PER_BM_SECT; i++) { + sig = wait_event_interruptible(mdev->al_wait, + !_is_in_al(mdev, enr * AL_EXT_PER_BM_SECT + i)); + if (sig) { + spin_lock_irq(&mdev->al_lock); + if (lc_put(mdev->resync, &bm_ext->lce) == 0) { + clear_bit(BME_NO_WRITES, &bm_ext->flags); + mdev->resync_locked--; + wake_up(&mdev->al_wait); + } + spin_unlock_irq(&mdev->al_lock); + return 0; + } + } + + set_bit(BME_LOCKED, &bm_ext->flags); + + return 1; +} + +/** + * drbd_try_rs_begin_io() - Gets an extent in the resync LRU cache, does not sleep + * @mdev: DRBD device. + * @sector: The sector number. + * + * Gets an extent in the resync LRU cache, sets it to BME_NO_WRITES, then + * tries to set it to BME_LOCKED. Returns 0 upon success, and -EAGAIN + * if there is still application IO going on in this area. + */ +int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector) +{ + unsigned int enr = BM_SECT_TO_EXT(sector); + const unsigned int al_enr = enr*AL_EXT_PER_BM_SECT; + struct lc_element *e; + struct bm_extent *bm_ext; + int i; + + spin_lock_irq(&mdev->al_lock); + if (mdev->resync_wenr != LC_FREE && mdev->resync_wenr != enr) { + /* in case you have very heavy scattered io, it may + * stall the syncer undefined if we give up the ref count + * when we try again and requeue. + * + * if we don't give up the refcount, but the next time + * we are scheduled this extent has been "synced" by new + * application writes, we'd miss the lc_put on the + * extent we keep the refcount on. + * so we remembered which extent we had to try again, and + * if the next requested one is something else, we do + * the lc_put here... + * we also have to wake_up + */ + e = lc_find(mdev->resync, mdev->resync_wenr); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (bm_ext) { + D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags)); + D_ASSERT(test_bit(BME_NO_WRITES, &bm_ext->flags)); + clear_bit(BME_NO_WRITES, &bm_ext->flags); + mdev->resync_wenr = LC_FREE; + if (lc_put(mdev->resync, &bm_ext->lce) == 0) + mdev->resync_locked--; + wake_up(&mdev->al_wait); + } else { + dev_alert(DEV, "LOGIC BUG\n"); + } + } + /* TRY. */ + e = lc_try_get(mdev->resync, enr); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (bm_ext) { + if (test_bit(BME_LOCKED, &bm_ext->flags)) + goto proceed; + if (!test_and_set_bit(BME_NO_WRITES, &bm_ext->flags)) { + mdev->resync_locked++; + } else { + /* we did set the BME_NO_WRITES, + * but then could not set BME_LOCKED, + * so we tried again. + * drop the extra reference. */ + bm_ext->lce.refcnt--; + D_ASSERT(bm_ext->lce.refcnt > 0); + } + goto check_al; + } else { + /* do we rather want to try later? */ + if (mdev->resync_locked > mdev->resync->nr_elements-3) + goto try_again; + /* Do or do not. There is no try. -- Yoda */ + e = lc_get(mdev->resync, enr); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (!bm_ext) { + const unsigned long rs_flags = mdev->resync->flags; + if (rs_flags & LC_STARVING) + dev_warn(DEV, "Have to wait for element" + " (resync LRU too small?)\n"); + BUG_ON(rs_flags & LC_DIRTY); + goto try_again; + } + if (bm_ext->lce.lc_number != enr) { + bm_ext->rs_left = drbd_bm_e_weight(mdev, enr); + bm_ext->rs_failed = 0; + lc_changed(mdev->resync, &bm_ext->lce); + wake_up(&mdev->al_wait); + D_ASSERT(test_bit(BME_LOCKED, &bm_ext->flags) == 0); + } + set_bit(BME_NO_WRITES, &bm_ext->flags); + D_ASSERT(bm_ext->lce.refcnt == 1); + mdev->resync_locked++; + goto check_al; + } +check_al: + for (i = 0; i < AL_EXT_PER_BM_SECT; i++) { + if (unlikely(al_enr+i == mdev->act_log->new_number)) + goto try_again; + if (lc_is_used(mdev->act_log, al_enr+i)) + goto try_again; + } + set_bit(BME_LOCKED, &bm_ext->flags); +proceed: + mdev->resync_wenr = LC_FREE; + spin_unlock_irq(&mdev->al_lock); + return 0; + +try_again: + if (bm_ext) + mdev->resync_wenr = enr; + spin_unlock_irq(&mdev->al_lock); + return -EAGAIN; +} + +void drbd_rs_complete_io(struct drbd_conf *mdev, sector_t sector) +{ + unsigned int enr = BM_SECT_TO_EXT(sector); + struct lc_element *e; + struct bm_extent *bm_ext; + unsigned long flags; + + spin_lock_irqsave(&mdev->al_lock, flags); + e = lc_find(mdev->resync, enr); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (!bm_ext) { + spin_unlock_irqrestore(&mdev->al_lock, flags); + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "drbd_rs_complete_io() called, but extent not found\n"); + return; + } + + if (bm_ext->lce.refcnt == 0) { + spin_unlock_irqrestore(&mdev->al_lock, flags); + dev_err(DEV, "drbd_rs_complete_io(,%llu [=%u]) called, " + "but refcnt is 0!?\n", + (unsigned long long)sector, enr); + return; + } + + if (lc_put(mdev->resync, &bm_ext->lce) == 0) { + clear_bit(BME_LOCKED, &bm_ext->flags); + clear_bit(BME_NO_WRITES, &bm_ext->flags); + mdev->resync_locked--; + wake_up(&mdev->al_wait); + } + + spin_unlock_irqrestore(&mdev->al_lock, flags); +} + +/** + * drbd_rs_cancel_all() - Removes all extents from the resync LRU (even BME_LOCKED) + * @mdev: DRBD device. + */ +void drbd_rs_cancel_all(struct drbd_conf *mdev) +{ + spin_lock_irq(&mdev->al_lock); + + if (get_ldev_if_state(mdev, D_FAILED)) { /* Makes sure ->resync is there. */ + lc_reset(mdev->resync); + put_ldev(mdev); + } + mdev->resync_locked = 0; + mdev->resync_wenr = LC_FREE; + spin_unlock_irq(&mdev->al_lock); + wake_up(&mdev->al_wait); +} + +/** + * drbd_rs_del_all() - Gracefully remove all extents from the resync LRU + * @mdev: DRBD device. + * + * Returns 0 upon success, -EAGAIN if at least one reference count was + * not zero. + */ +int drbd_rs_del_all(struct drbd_conf *mdev) +{ + struct lc_element *e; + struct bm_extent *bm_ext; + int i; + + spin_lock_irq(&mdev->al_lock); + + if (get_ldev_if_state(mdev, D_FAILED)) { + /* ok, ->resync is there. */ + for (i = 0; i < mdev->resync->nr_elements; i++) { + e = lc_element_by_index(mdev->resync, i); + bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL; + if (bm_ext->lce.lc_number == LC_FREE) + continue; + if (bm_ext->lce.lc_number == mdev->resync_wenr) { + dev_info(DEV, "dropping %u in drbd_rs_del_all, apparently" + " got 'synced' by application io\n", + mdev->resync_wenr); + D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags)); + D_ASSERT(test_bit(BME_NO_WRITES, &bm_ext->flags)); + clear_bit(BME_NO_WRITES, &bm_ext->flags); + mdev->resync_wenr = LC_FREE; + lc_put(mdev->resync, &bm_ext->lce); + } + if (bm_ext->lce.refcnt != 0) { + dev_info(DEV, "Retrying drbd_rs_del_all() later. " + "refcnt=%d\n", bm_ext->lce.refcnt); + put_ldev(mdev); + spin_unlock_irq(&mdev->al_lock); + return -EAGAIN; + } + D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags)); + D_ASSERT(!test_bit(BME_NO_WRITES, &bm_ext->flags)); + lc_del(mdev->resync, &bm_ext->lce); + } + D_ASSERT(mdev->resync->used == 0); + put_ldev(mdev); + } + spin_unlock_irq(&mdev->al_lock); + + return 0; +} + +/** + * drbd_rs_failed_io() - Record information on a failure to resync the specified blocks + * @mdev: DRBD device. + * @sector: The sector number. + * @size: Size of failed IO operation, in byte. + */ +void drbd_rs_failed_io(struct drbd_conf *mdev, sector_t sector, int size) +{ + /* Is called from worker and receiver context _only_ */ + unsigned long sbnr, ebnr, lbnr; + unsigned long count; + sector_t esector, nr_sectors; + int wake_up = 0; + + if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) { + dev_err(DEV, "drbd_rs_failed_io: sector=%llus size=%d nonsense!\n", + (unsigned long long)sector, size); + return; + } + nr_sectors = drbd_get_capacity(mdev->this_bdev); + esector = sector + (size >> 9) - 1; + + ERR_IF(sector >= nr_sectors) return; + ERR_IF(esector >= nr_sectors) esector = (nr_sectors-1); + + lbnr = BM_SECT_TO_BIT(nr_sectors-1); + + /* + * round up start sector, round down end sector. we make sure we only + * handle full, aligned, BM_BLOCK_SIZE (4K) blocks */ + if (unlikely(esector < BM_SECT_PER_BIT-1)) + return; + if (unlikely(esector == (nr_sectors-1))) + ebnr = lbnr; + else + ebnr = BM_SECT_TO_BIT(esector - (BM_SECT_PER_BIT-1)); + sbnr = BM_SECT_TO_BIT(sector + BM_SECT_PER_BIT-1); + + if (sbnr > ebnr) + return; + + /* + * ok, (capacity & 7) != 0 sometimes, but who cares... + * we count rs_{total,left} in bits, not sectors. + */ + spin_lock_irq(&mdev->al_lock); + count = drbd_bm_count_bits(mdev, sbnr, ebnr); + if (count) { + mdev->rs_failed += count; + + if (get_ldev(mdev)) { + drbd_try_clear_on_disk_bm(mdev, sector, count, FALSE); + put_ldev(mdev); + } + + /* just wake_up unconditional now, various lc_chaged(), + * lc_put() in drbd_try_clear_on_disk_bm(). */ + wake_up = 1; + } + spin_unlock_irq(&mdev->al_lock); + if (wake_up) + wake_up(&mdev->al_wait); +} diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c new file mode 100644 index 000000000000..b61057e77882 --- /dev/null +++ b/drivers/block/drbd/drbd_bitmap.c @@ -0,0 +1,1327 @@ +/* + drbd_bitmap.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2004-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2004-2008, Philipp Reisner . + Copyright (C) 2004-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include +#include +#include +#include +#include +#include "drbd_int.h" + +/* OPAQUE outside this file! + * interface defined in drbd_int.h + + * convention: + * function name drbd_bm_... => used elsewhere, "public". + * function name bm_... => internal to implementation, "private". + + * Note that since find_first_bit returns int, at the current granularity of + * the bitmap (4KB per byte), this implementation "only" supports up to + * 1<<(32+12) == 16 TB... + */ + +/* + * NOTE + * Access to the *bm_pages is protected by bm_lock. + * It is safe to read the other members within the lock. + * + * drbd_bm_set_bits is called from bio_endio callbacks, + * We may be called with irq already disabled, + * so we need spin_lock_irqsave(). + * And we need the kmap_atomic. + */ +struct drbd_bitmap { + struct page **bm_pages; + spinlock_t bm_lock; + /* WARNING unsigned long bm_*: + * 32bit number of bit offset is just enough for 512 MB bitmap. + * it will blow up if we make the bitmap bigger... + * not that it makes much sense to have a bitmap that large, + * rather change the granularity to 16k or 64k or something. + * (that implies other problems, however...) + */ + unsigned long bm_set; /* nr of set bits; THINK maybe atomic_t? */ + unsigned long bm_bits; + size_t bm_words; + size_t bm_number_of_pages; + sector_t bm_dev_capacity; + struct semaphore bm_change; /* serializes resize operations */ + + atomic_t bm_async_io; + wait_queue_head_t bm_io_wait; + + unsigned long bm_flags; + + /* debugging aid, in case we are still racy somewhere */ + char *bm_why; + struct task_struct *bm_task; +}; + +/* definition of bits in bm_flags */ +#define BM_LOCKED 0 +#define BM_MD_IO_ERROR 1 +#define BM_P_VMALLOCED 2 + +static int bm_is_locked(struct drbd_bitmap *b) +{ + return test_bit(BM_LOCKED, &b->bm_flags); +} + +#define bm_print_lock_info(m) __bm_print_lock_info(m, __func__) +static void __bm_print_lock_info(struct drbd_conf *mdev, const char *func) +{ + struct drbd_bitmap *b = mdev->bitmap; + if (!__ratelimit(&drbd_ratelimit_state)) + return; + dev_err(DEV, "FIXME %s in %s, bitmap locked for '%s' by %s\n", + current == mdev->receiver.task ? "receiver" : + current == mdev->asender.task ? "asender" : + current == mdev->worker.task ? "worker" : current->comm, + func, b->bm_why ?: "?", + b->bm_task == mdev->receiver.task ? "receiver" : + b->bm_task == mdev->asender.task ? "asender" : + b->bm_task == mdev->worker.task ? "worker" : "?"); +} + +void drbd_bm_lock(struct drbd_conf *mdev, char *why) +{ + struct drbd_bitmap *b = mdev->bitmap; + int trylock_failed; + + if (!b) { + dev_err(DEV, "FIXME no bitmap in drbd_bm_lock!?\n"); + return; + } + + trylock_failed = down_trylock(&b->bm_change); + + if (trylock_failed) { + dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n", + current == mdev->receiver.task ? "receiver" : + current == mdev->asender.task ? "asender" : + current == mdev->worker.task ? "worker" : current->comm, + why, b->bm_why ?: "?", + b->bm_task == mdev->receiver.task ? "receiver" : + b->bm_task == mdev->asender.task ? "asender" : + b->bm_task == mdev->worker.task ? "worker" : "?"); + down(&b->bm_change); + } + if (__test_and_set_bit(BM_LOCKED, &b->bm_flags)) + dev_err(DEV, "FIXME bitmap already locked in bm_lock\n"); + + b->bm_why = why; + b->bm_task = current; +} + +void drbd_bm_unlock(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + if (!b) { + dev_err(DEV, "FIXME no bitmap in drbd_bm_unlock!?\n"); + return; + } + + if (!__test_and_clear_bit(BM_LOCKED, &mdev->bitmap->bm_flags)) + dev_err(DEV, "FIXME bitmap not locked in bm_unlock\n"); + + b->bm_why = NULL; + b->bm_task = NULL; + up(&b->bm_change); +} + +/* word offset to long pointer */ +static unsigned long *__bm_map_paddr(struct drbd_bitmap *b, unsigned long offset, const enum km_type km) +{ + struct page *page; + unsigned long page_nr; + + /* page_nr = (word*sizeof(long)) >> PAGE_SHIFT; */ + page_nr = offset >> (PAGE_SHIFT - LN2_BPL + 3); + BUG_ON(page_nr >= b->bm_number_of_pages); + page = b->bm_pages[page_nr]; + + return (unsigned long *) kmap_atomic(page, km); +} + +static unsigned long * bm_map_paddr(struct drbd_bitmap *b, unsigned long offset) +{ + return __bm_map_paddr(b, offset, KM_IRQ1); +} + +static void __bm_unmap(unsigned long *p_addr, const enum km_type km) +{ + kunmap_atomic(p_addr, km); +}; + +static void bm_unmap(unsigned long *p_addr) +{ + return __bm_unmap(p_addr, KM_IRQ1); +} + +/* long word offset of _bitmap_ sector */ +#define S2W(s) ((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL)) +/* word offset from start of bitmap to word number _in_page_ + * modulo longs per page +#define MLPP(X) ((X) % (PAGE_SIZE/sizeof(long)) + hm, well, Philipp thinks gcc might not optimze the % into & (... - 1) + so do it explicitly: + */ +#define MLPP(X) ((X) & ((PAGE_SIZE/sizeof(long))-1)) + +/* Long words per page */ +#define LWPP (PAGE_SIZE/sizeof(long)) + +/* + * actually most functions herein should take a struct drbd_bitmap*, not a + * struct drbd_conf*, but for the debug macros I like to have the mdev around + * to be able to report device specific. + */ + +static void bm_free_pages(struct page **pages, unsigned long number) +{ + unsigned long i; + if (!pages) + return; + + for (i = 0; i < number; i++) { + if (!pages[i]) { + printk(KERN_ALERT "drbd: bm_free_pages tried to free " + "a NULL pointer; i=%lu n=%lu\n", + i, number); + continue; + } + __free_page(pages[i]); + pages[i] = NULL; + } +} + +static void bm_vk_free(void *ptr, int v) +{ + if (v) + vfree(ptr); + else + kfree(ptr); +} + +/* + * "have" and "want" are NUMBER OF PAGES. + */ +static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) +{ + struct page **old_pages = b->bm_pages; + struct page **new_pages, *page; + unsigned int i, bytes, vmalloced = 0; + unsigned long have = b->bm_number_of_pages; + + BUG_ON(have == 0 && old_pages != NULL); + BUG_ON(have != 0 && old_pages == NULL); + + if (have == want) + return old_pages; + + /* Trying kmalloc first, falling back to vmalloc. + * GFP_KERNEL is ok, as this is done when a lower level disk is + * "attached" to the drbd. Context is receiver thread or cqueue + * thread. As we have no disk yet, we are not in the IO path, + * not even the IO path of the peer. */ + bytes = sizeof(struct page *)*want; + new_pages = kmalloc(bytes, GFP_KERNEL); + if (!new_pages) { + new_pages = vmalloc(bytes); + if (!new_pages) + return NULL; + vmalloced = 1; + } + + memset(new_pages, 0, bytes); + if (want >= have) { + for (i = 0; i < have; i++) + new_pages[i] = old_pages[i]; + for (; i < want; i++) { + page = alloc_page(GFP_HIGHUSER); + if (!page) { + bm_free_pages(new_pages + have, i - have); + bm_vk_free(new_pages, vmalloced); + return NULL; + } + new_pages[i] = page; + } + } else { + for (i = 0; i < want; i++) + new_pages[i] = old_pages[i]; + /* NOT HERE, we are outside the spinlock! + bm_free_pages(old_pages + want, have - want); + */ + } + + if (vmalloced) + set_bit(BM_P_VMALLOCED, &b->bm_flags); + else + clear_bit(BM_P_VMALLOCED, &b->bm_flags); + + return new_pages; +} + +/* + * called on driver init only. TODO call when a device is created. + * allocates the drbd_bitmap, and stores it in mdev->bitmap. + */ +int drbd_bm_init(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + WARN_ON(b != NULL); + b = kzalloc(sizeof(struct drbd_bitmap), GFP_KERNEL); + if (!b) + return -ENOMEM; + spin_lock_init(&b->bm_lock); + init_MUTEX(&b->bm_change); + init_waitqueue_head(&b->bm_io_wait); + + mdev->bitmap = b; + + return 0; +} + +sector_t drbd_bm_capacity(struct drbd_conf *mdev) +{ + ERR_IF(!mdev->bitmap) return 0; + return mdev->bitmap->bm_dev_capacity; +} + +/* called on driver unload. TODO: call when a device is destroyed. + */ +void drbd_bm_cleanup(struct drbd_conf *mdev) +{ + ERR_IF (!mdev->bitmap) return; + bm_free_pages(mdev->bitmap->bm_pages, mdev->bitmap->bm_number_of_pages); + bm_vk_free(mdev->bitmap->bm_pages, test_bit(BM_P_VMALLOCED, &mdev->bitmap->bm_flags)); + kfree(mdev->bitmap); + mdev->bitmap = NULL; +} + +/* + * since (b->bm_bits % BITS_PER_LONG) != 0, + * this masks out the remaining bits. + * Returns the number of bits cleared. + */ +static int bm_clear_surplus(struct drbd_bitmap *b) +{ + const unsigned long mask = (1UL << (b->bm_bits & (BITS_PER_LONG-1))) - 1; + size_t w = b->bm_bits >> LN2_BPL; + int cleared = 0; + unsigned long *p_addr, *bm; + + p_addr = bm_map_paddr(b, w); + bm = p_addr + MLPP(w); + if (w < b->bm_words) { + cleared = hweight_long(*bm & ~mask); + *bm &= mask; + w++; bm++; + } + + if (w < b->bm_words) { + cleared += hweight_long(*bm); + *bm = 0; + } + bm_unmap(p_addr); + return cleared; +} + +static void bm_set_surplus(struct drbd_bitmap *b) +{ + const unsigned long mask = (1UL << (b->bm_bits & (BITS_PER_LONG-1))) - 1; + size_t w = b->bm_bits >> LN2_BPL; + unsigned long *p_addr, *bm; + + p_addr = bm_map_paddr(b, w); + bm = p_addr + MLPP(w); + if (w < b->bm_words) { + *bm |= ~mask; + bm++; w++; + } + + if (w < b->bm_words) { + *bm = ~(0UL); + } + bm_unmap(p_addr); +} + +static unsigned long __bm_count_bits(struct drbd_bitmap *b, const int swap_endian) +{ + unsigned long *p_addr, *bm, offset = 0; + unsigned long bits = 0; + unsigned long i, do_now; + + while (offset < b->bm_words) { + i = do_now = min_t(size_t, b->bm_words-offset, LWPP); + p_addr = __bm_map_paddr(b, offset, KM_USER0); + bm = p_addr + MLPP(offset); + while (i--) { +#ifndef __LITTLE_ENDIAN + if (swap_endian) + *bm = lel_to_cpu(*bm); +#endif + bits += hweight_long(*bm++); + } + __bm_unmap(p_addr, KM_USER0); + offset += do_now; + cond_resched(); + } + + return bits; +} + +static unsigned long bm_count_bits(struct drbd_bitmap *b) +{ + return __bm_count_bits(b, 0); +} + +static unsigned long bm_count_bits_swap_endian(struct drbd_bitmap *b) +{ + return __bm_count_bits(b, 1); +} + +/* offset and len in long words.*/ +static void bm_memset(struct drbd_bitmap *b, size_t offset, int c, size_t len) +{ + unsigned long *p_addr, *bm; + size_t do_now, end; + +#define BM_SECTORS_PER_BIT (BM_BLOCK_SIZE/512) + + end = offset + len; + + if (end > b->bm_words) { + printk(KERN_ALERT "drbd: bm_memset end > bm_words\n"); + return; + } + + while (offset < end) { + do_now = min_t(size_t, ALIGN(offset + 1, LWPP), end) - offset; + p_addr = bm_map_paddr(b, offset); + bm = p_addr + MLPP(offset); + if (bm+do_now > p_addr + LWPP) { + printk(KERN_ALERT "drbd: BUG BUG BUG! p_addr:%p bm:%p do_now:%d\n", + p_addr, bm, (int)do_now); + break; /* breaks to after catch_oob_access_end() only! */ + } + memset(bm, c, do_now * sizeof(long)); + bm_unmap(p_addr); + offset += do_now; + } +} + +/* + * make sure the bitmap has enough room for the attached storage, + * if necessary, resize. + * called whenever we may have changed the device size. + * returns -ENOMEM if we could not allocate enough memory, 0 on success. + * In case this is actually a resize, we copy the old bitmap into the new one. + * Otherwise, the bitmap is initialized to all bits set. + */ +int drbd_bm_resize(struct drbd_conf *mdev, sector_t capacity) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long bits, words, owords, obits, *p_addr, *bm; + unsigned long want, have, onpages; /* number of pages */ + struct page **npages, **opages = NULL; + int err = 0, growing; + int opages_vmalloced; + + ERR_IF(!b) return -ENOMEM; + + drbd_bm_lock(mdev, "resize"); + + dev_info(DEV, "drbd_bm_resize called with capacity == %llu\n", + (unsigned long long)capacity); + + if (capacity == b->bm_dev_capacity) + goto out; + + opages_vmalloced = test_bit(BM_P_VMALLOCED, &b->bm_flags); + + if (capacity == 0) { + spin_lock_irq(&b->bm_lock); + opages = b->bm_pages; + onpages = b->bm_number_of_pages; + owords = b->bm_words; + b->bm_pages = NULL; + b->bm_number_of_pages = + b->bm_set = + b->bm_bits = + b->bm_words = + b->bm_dev_capacity = 0; + spin_unlock_irq(&b->bm_lock); + bm_free_pages(opages, onpages); + bm_vk_free(opages, opages_vmalloced); + goto out; + } + bits = BM_SECT_TO_BIT(ALIGN(capacity, BM_SECT_PER_BIT)); + + /* if we would use + words = ALIGN(bits,BITS_PER_LONG) >> LN2_BPL; + a 32bit host could present the wrong number of words + to a 64bit host. + */ + words = ALIGN(bits, 64) >> LN2_BPL; + + if (get_ldev(mdev)) { + D_ASSERT((u64)bits <= (((u64)mdev->ldev->md.md_size_sect-MD_BM_OFFSET) << 12)); + put_ldev(mdev); + } + + /* one extra long to catch off by one errors */ + want = ALIGN((words+1)*sizeof(long), PAGE_SIZE) >> PAGE_SHIFT; + have = b->bm_number_of_pages; + if (want == have) { + D_ASSERT(b->bm_pages != NULL); + npages = b->bm_pages; + } else { + if (FAULT_ACTIVE(mdev, DRBD_FAULT_BM_ALLOC)) + npages = NULL; + else + npages = bm_realloc_pages(b, want); + } + + if (!npages) { + err = -ENOMEM; + goto out; + } + + spin_lock_irq(&b->bm_lock); + opages = b->bm_pages; + owords = b->bm_words; + obits = b->bm_bits; + + growing = bits > obits; + if (opages) + bm_set_surplus(b); + + b->bm_pages = npages; + b->bm_number_of_pages = want; + b->bm_bits = bits; + b->bm_words = words; + b->bm_dev_capacity = capacity; + + if (growing) { + bm_memset(b, owords, 0xff, words-owords); + b->bm_set += bits - obits; + } + + if (want < have) { + /* implicit: (opages != NULL) && (opages != npages) */ + bm_free_pages(opages + want, have - want); + } + + p_addr = bm_map_paddr(b, words); + bm = p_addr + MLPP(words); + *bm = DRBD_MAGIC; + bm_unmap(p_addr); + + (void)bm_clear_surplus(b); + + spin_unlock_irq(&b->bm_lock); + if (opages != npages) + bm_vk_free(opages, opages_vmalloced); + if (!growing) + b->bm_set = bm_count_bits(b); + dev_info(DEV, "resync bitmap: bits=%lu words=%lu\n", bits, words); + + out: + drbd_bm_unlock(mdev); + return err; +} + +/* inherently racy: + * if not protected by other means, return value may be out of date when + * leaving this function... + * we still need to lock it, since it is important that this returns + * bm_set == 0 precisely. + * + * maybe bm_set should be atomic_t ? + */ +static unsigned long _drbd_bm_total_weight(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long s; + unsigned long flags; + + ERR_IF(!b) return 0; + ERR_IF(!b->bm_pages) return 0; + + spin_lock_irqsave(&b->bm_lock, flags); + s = b->bm_set; + spin_unlock_irqrestore(&b->bm_lock, flags); + + return s; +} + +unsigned long drbd_bm_total_weight(struct drbd_conf *mdev) +{ + unsigned long s; + /* if I don't have a disk, I don't know about out-of-sync status */ + if (!get_ldev_if_state(mdev, D_NEGOTIATING)) + return 0; + s = _drbd_bm_total_weight(mdev); + put_ldev(mdev); + return s; +} + +size_t drbd_bm_words(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + ERR_IF(!b) return 0; + ERR_IF(!b->bm_pages) return 0; + + return b->bm_words; +} + +unsigned long drbd_bm_bits(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + ERR_IF(!b) return 0; + + return b->bm_bits; +} + +/* merge number words from buffer into the bitmap starting at offset. + * buffer[i] is expected to be little endian unsigned long. + * bitmap must be locked by drbd_bm_lock. + * currently only used from receive_bitmap. + */ +void drbd_bm_merge_lel(struct drbd_conf *mdev, size_t offset, size_t number, + unsigned long *buffer) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr, *bm; + unsigned long word, bits; + size_t end, do_now; + + end = offset + number; + + ERR_IF(!b) return; + ERR_IF(!b->bm_pages) return; + if (number == 0) + return; + WARN_ON(offset >= b->bm_words); + WARN_ON(end > b->bm_words); + + spin_lock_irq(&b->bm_lock); + while (offset < end) { + do_now = min_t(size_t, ALIGN(offset+1, LWPP), end) - offset; + p_addr = bm_map_paddr(b, offset); + bm = p_addr + MLPP(offset); + offset += do_now; + while (do_now--) { + bits = hweight_long(*bm); + word = *bm | lel_to_cpu(*buffer++); + *bm++ = word; + b->bm_set += hweight_long(word) - bits; + } + bm_unmap(p_addr); + } + /* with 32bit <-> 64bit cross-platform connect + * this is only correct for current usage, + * where we _know_ that we are 64 bit aligned, + * and know that this function is used in this way, too... + */ + if (end == b->bm_words) + b->bm_set -= bm_clear_surplus(b); + + spin_unlock_irq(&b->bm_lock); +} + +/* copy number words from the bitmap starting at offset into the buffer. + * buffer[i] will be little endian unsigned long. + */ +void drbd_bm_get_lel(struct drbd_conf *mdev, size_t offset, size_t number, + unsigned long *buffer) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr, *bm; + size_t end, do_now; + + end = offset + number; + + ERR_IF(!b) return; + ERR_IF(!b->bm_pages) return; + + spin_lock_irq(&b->bm_lock); + if ((offset >= b->bm_words) || + (end > b->bm_words) || + (number <= 0)) + dev_err(DEV, "offset=%lu number=%lu bm_words=%lu\n", + (unsigned long) offset, + (unsigned long) number, + (unsigned long) b->bm_words); + else { + while (offset < end) { + do_now = min_t(size_t, ALIGN(offset+1, LWPP), end) - offset; + p_addr = bm_map_paddr(b, offset); + bm = p_addr + MLPP(offset); + offset += do_now; + while (do_now--) + *buffer++ = cpu_to_lel(*bm++); + bm_unmap(p_addr); + } + } + spin_unlock_irq(&b->bm_lock); +} + +/* set all bits in the bitmap */ +void drbd_bm_set_all(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + ERR_IF(!b) return; + ERR_IF(!b->bm_pages) return; + + spin_lock_irq(&b->bm_lock); + bm_memset(b, 0, 0xff, b->bm_words); + (void)bm_clear_surplus(b); + b->bm_set = b->bm_bits; + spin_unlock_irq(&b->bm_lock); +} + +/* clear all bits in the bitmap */ +void drbd_bm_clear_all(struct drbd_conf *mdev) +{ + struct drbd_bitmap *b = mdev->bitmap; + ERR_IF(!b) return; + ERR_IF(!b->bm_pages) return; + + spin_lock_irq(&b->bm_lock); + bm_memset(b, 0, 0, b->bm_words); + b->bm_set = 0; + spin_unlock_irq(&b->bm_lock); +} + +static void bm_async_io_complete(struct bio *bio, int error) +{ + struct drbd_bitmap *b = bio->bi_private; + int uptodate = bio_flagged(bio, BIO_UPTODATE); + + + /* strange behavior of some lower level drivers... + * fail the request by clearing the uptodate flag, + * but do not return any error?! + * do we want to WARN() on this? */ + if (!error && !uptodate) + error = -EIO; + + if (error) { + /* doh. what now? + * for now, set all bits, and flag MD_IO_ERROR */ + __set_bit(BM_MD_IO_ERROR, &b->bm_flags); + } + if (atomic_dec_and_test(&b->bm_async_io)) + wake_up(&b->bm_io_wait); + + bio_put(bio); +} + +static void bm_page_io_async(struct drbd_conf *mdev, struct drbd_bitmap *b, int page_nr, int rw) __must_hold(local) +{ + /* we are process context. we always get a bio */ + struct bio *bio = bio_alloc(GFP_KERNEL, 1); + unsigned int len; + sector_t on_disk_sector = + mdev->ldev->md.md_offset + mdev->ldev->md.bm_offset; + on_disk_sector += ((sector_t)page_nr) << (PAGE_SHIFT-9); + + /* this might happen with very small + * flexible external meta data device */ + len = min_t(unsigned int, PAGE_SIZE, + (drbd_md_last_sector(mdev->ldev) - on_disk_sector + 1)<<9); + + bio->bi_bdev = mdev->ldev->md_bdev; + bio->bi_sector = on_disk_sector; + bio_add_page(bio, b->bm_pages[page_nr], len, 0); + bio->bi_private = b; + bio->bi_end_io = bm_async_io_complete; + + if (FAULT_ACTIVE(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) { + bio->bi_rw |= rw; + bio_endio(bio, -EIO); + } else { + submit_bio(rw, bio); + } +} + +# if defined(__LITTLE_ENDIAN) + /* nothing to do, on disk == in memory */ +# define bm_cpu_to_lel(x) ((void)0) +# else +void bm_cpu_to_lel(struct drbd_bitmap *b) +{ + /* need to cpu_to_lel all the pages ... + * this may be optimized by using + * cpu_to_lel(-1) == -1 and cpu_to_lel(0) == 0; + * the following is still not optimal, but better than nothing */ + unsigned int i; + unsigned long *p_addr, *bm; + if (b->bm_set == 0) { + /* no page at all; avoid swap if all is 0 */ + i = b->bm_number_of_pages; + } else if (b->bm_set == b->bm_bits) { + /* only the last page */ + i = b->bm_number_of_pages - 1; + } else { + /* all pages */ + i = 0; + } + for (; i < b->bm_number_of_pages; i++) { + p_addr = kmap_atomic(b->bm_pages[i], KM_USER0); + for (bm = p_addr; bm < p_addr + PAGE_SIZE/sizeof(long); bm++) + *bm = cpu_to_lel(*bm); + kunmap_atomic(p_addr, KM_USER0); + } +} +# endif +/* lel_to_cpu == cpu_to_lel */ +# define bm_lel_to_cpu(x) bm_cpu_to_lel(x) + +/* + * bm_rw: read/write the whole bitmap from/to its on disk location. + */ +static int bm_rw(struct drbd_conf *mdev, int rw) __must_hold(local) +{ + struct drbd_bitmap *b = mdev->bitmap; + /* sector_t sector; */ + int bm_words, num_pages, i; + unsigned long now; + char ppb[10]; + int err = 0; + + WARN_ON(!bm_is_locked(b)); + + /* no spinlock here, the drbd_bm_lock should be enough! */ + + bm_words = drbd_bm_words(mdev); + num_pages = (bm_words*sizeof(long) + PAGE_SIZE-1) >> PAGE_SHIFT; + + /* on disk bitmap is little endian */ + if (rw == WRITE) + bm_cpu_to_lel(b); + + now = jiffies; + atomic_set(&b->bm_async_io, num_pages); + __clear_bit(BM_MD_IO_ERROR, &b->bm_flags); + + /* let the layers below us try to merge these bios... */ + for (i = 0; i < num_pages; i++) + bm_page_io_async(mdev, b, i, rw); + + drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev)); + wait_event(b->bm_io_wait, atomic_read(&b->bm_async_io) == 0); + + if (test_bit(BM_MD_IO_ERROR, &b->bm_flags)) { + dev_alert(DEV, "we had at least one MD IO ERROR during bitmap IO\n"); + drbd_chk_io_error(mdev, 1, TRUE); + err = -EIO; + } + + now = jiffies; + if (rw == WRITE) { + /* swap back endianness */ + bm_lel_to_cpu(b); + /* flush bitmap to stable storage */ + drbd_md_flush(mdev); + } else /* rw == READ */ { + /* just read, if necessary adjust endianness */ + b->bm_set = bm_count_bits_swap_endian(b); + dev_info(DEV, "recounting of set bits took additional %lu jiffies\n", + jiffies - now); + } + now = b->bm_set; + + dev_info(DEV, "%s (%lu bits) marked out-of-sync by on disk bit-map.\n", + ppsize(ppb, now << (BM_BLOCK_SHIFT-10)), now); + + return err; +} + +/** + * drbd_bm_read() - Read the whole bitmap from its on disk location. + * @mdev: DRBD device. + */ +int drbd_bm_read(struct drbd_conf *mdev) __must_hold(local) +{ + return bm_rw(mdev, READ); +} + +/** + * drbd_bm_write() - Write the whole bitmap to its on disk location. + * @mdev: DRBD device. + */ +int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local) +{ + return bm_rw(mdev, WRITE); +} + +/** + * drbd_bm_write_sect: Writes a 512 (MD_SECTOR_SIZE) byte piece of the bitmap + * @mdev: DRBD device. + * @enr: Extent number in the resync lru (happens to be sector offset) + * + * The BM_EXT_SIZE is on purpose exactly the amount of the bitmap covered + * by a single sector write. Therefore enr == sector offset from the + * start of the bitmap. + */ +int drbd_bm_write_sect(struct drbd_conf *mdev, unsigned long enr) __must_hold(local) +{ + sector_t on_disk_sector = enr + mdev->ldev->md.md_offset + + mdev->ldev->md.bm_offset; + int bm_words, num_words, offset; + int err = 0; + + mutex_lock(&mdev->md_io_mutex); + bm_words = drbd_bm_words(mdev); + offset = S2W(enr); /* word offset into bitmap */ + num_words = min(S2W(1), bm_words - offset); + if (num_words < S2W(1)) + memset(page_address(mdev->md_io_page), 0, MD_SECTOR_SIZE); + drbd_bm_get_lel(mdev, offset, num_words, + page_address(mdev->md_io_page)); + if (!drbd_md_sync_page_io(mdev, mdev->ldev, on_disk_sector, WRITE)) { + int i; + err = -EIO; + dev_err(DEV, "IO ERROR writing bitmap sector %lu " + "(meta-disk sector %llus)\n", + enr, (unsigned long long)on_disk_sector); + drbd_chk_io_error(mdev, 1, TRUE); + for (i = 0; i < AL_EXT_PER_BM_SECT; i++) + drbd_bm_ALe_set_all(mdev, enr*AL_EXT_PER_BM_SECT+i); + } + mdev->bm_writ_cnt++; + mutex_unlock(&mdev->md_io_mutex); + return err; +} + +/* NOTE + * find_first_bit returns int, we return unsigned long. + * should not make much difference anyways, but ... + * + * this returns a bit number, NOT a sector! + */ +#define BPP_MASK ((1UL << (PAGE_SHIFT+3)) - 1) +static unsigned long __bm_find_next(struct drbd_conf *mdev, unsigned long bm_fo, + const int find_zero_bit, const enum km_type km) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long i = -1UL; + unsigned long *p_addr; + unsigned long bit_offset; /* bit offset of the mapped page. */ + + if (bm_fo > b->bm_bits) { + dev_err(DEV, "bm_fo=%lu bm_bits=%lu\n", bm_fo, b->bm_bits); + } else { + while (bm_fo < b->bm_bits) { + unsigned long offset; + bit_offset = bm_fo & ~BPP_MASK; /* bit offset of the page */ + offset = bit_offset >> LN2_BPL; /* word offset of the page */ + p_addr = __bm_map_paddr(b, offset, km); + + if (find_zero_bit) + i = find_next_zero_bit(p_addr, PAGE_SIZE*8, bm_fo & BPP_MASK); + else + i = find_next_bit(p_addr, PAGE_SIZE*8, bm_fo & BPP_MASK); + + __bm_unmap(p_addr, km); + if (i < PAGE_SIZE*8) { + i = bit_offset + i; + if (i >= b->bm_bits) + break; + goto found; + } + bm_fo = bit_offset + PAGE_SIZE*8; + } + i = -1UL; + } + found: + return i; +} + +static unsigned long bm_find_next(struct drbd_conf *mdev, + unsigned long bm_fo, const int find_zero_bit) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long i = -1UL; + + ERR_IF(!b) return i; + ERR_IF(!b->bm_pages) return i; + + spin_lock_irq(&b->bm_lock); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + + i = __bm_find_next(mdev, bm_fo, find_zero_bit, KM_IRQ1); + + spin_unlock_irq(&b->bm_lock); + return i; +} + +unsigned long drbd_bm_find_next(struct drbd_conf *mdev, unsigned long bm_fo) +{ + return bm_find_next(mdev, bm_fo, 0); +} + +#if 0 +/* not yet needed for anything. */ +unsigned long drbd_bm_find_next_zero(struct drbd_conf *mdev, unsigned long bm_fo) +{ + return bm_find_next(mdev, bm_fo, 1); +} +#endif + +/* does not spin_lock_irqsave. + * you must take drbd_bm_lock() first */ +unsigned long _drbd_bm_find_next(struct drbd_conf *mdev, unsigned long bm_fo) +{ + /* WARN_ON(!bm_is_locked(mdev)); */ + return __bm_find_next(mdev, bm_fo, 0, KM_USER1); +} + +unsigned long _drbd_bm_find_next_zero(struct drbd_conf *mdev, unsigned long bm_fo) +{ + /* WARN_ON(!bm_is_locked(mdev)); */ + return __bm_find_next(mdev, bm_fo, 1, KM_USER1); +} + +/* returns number of bits actually changed. + * for val != 0, we change 0 -> 1, return code positive + * for val == 0, we change 1 -> 0, return code negative + * wants bitnr, not sector. + * expected to be called for only a few bits (e - s about BITS_PER_LONG). + * Must hold bitmap lock already. */ +int __bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, + unsigned long e, int val, const enum km_type km) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr = NULL; + unsigned long bitnr; + unsigned long last_page_nr = -1UL; + int c = 0; + + if (e >= b->bm_bits) { + dev_err(DEV, "ASSERT FAILED: bit_s=%lu bit_e=%lu bm_bits=%lu\n", + s, e, b->bm_bits); + e = b->bm_bits ? b->bm_bits -1 : 0; + } + for (bitnr = s; bitnr <= e; bitnr++) { + unsigned long offset = bitnr>>LN2_BPL; + unsigned long page_nr = offset >> (PAGE_SHIFT - LN2_BPL + 3); + if (page_nr != last_page_nr) { + if (p_addr) + __bm_unmap(p_addr, km); + p_addr = __bm_map_paddr(b, offset, km); + last_page_nr = page_nr; + } + if (val) + c += (0 == __test_and_set_bit(bitnr & BPP_MASK, p_addr)); + else + c -= (0 != __test_and_clear_bit(bitnr & BPP_MASK, p_addr)); + } + if (p_addr) + __bm_unmap(p_addr, km); + b->bm_set += c; + return c; +} + +/* returns number of bits actually changed. + * for val != 0, we change 0 -> 1, return code positive + * for val == 0, we change 1 -> 0, return code negative + * wants bitnr, not sector */ +int bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, + const unsigned long e, int val) +{ + unsigned long flags; + struct drbd_bitmap *b = mdev->bitmap; + int c = 0; + + ERR_IF(!b) return 1; + ERR_IF(!b->bm_pages) return 0; + + spin_lock_irqsave(&b->bm_lock, flags); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + + c = __bm_change_bits_to(mdev, s, e, val, KM_IRQ1); + + spin_unlock_irqrestore(&b->bm_lock, flags); + return c; +} + +/* returns number of bits changed 0 -> 1 */ +int drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsigned long e) +{ + return bm_change_bits_to(mdev, s, e, 1); +} + +/* returns number of bits changed 1 -> 0 */ +int drbd_bm_clear_bits(struct drbd_conf *mdev, const unsigned long s, const unsigned long e) +{ + return -bm_change_bits_to(mdev, s, e, 0); +} + +/* sets all bits in full words, + * from first_word up to, but not including, last_word */ +static inline void bm_set_full_words_within_one_page(struct drbd_bitmap *b, + int page_nr, int first_word, int last_word) +{ + int i; + int bits; + unsigned long *paddr = kmap_atomic(b->bm_pages[page_nr], KM_USER0); + for (i = first_word; i < last_word; i++) { + bits = hweight_long(paddr[i]); + paddr[i] = ~0UL; + b->bm_set += BITS_PER_LONG - bits; + } + kunmap_atomic(paddr, KM_USER0); +} + +/* Same thing as drbd_bm_set_bits, but without taking the spin_lock_irqsave. + * You must first drbd_bm_lock(). + * Can be called to set the whole bitmap in one go. + * Sets bits from s to e _inclusive_. */ +void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsigned long e) +{ + /* First set_bit from the first bit (s) + * up to the next long boundary (sl), + * then assign full words up to the last long boundary (el), + * then set_bit up to and including the last bit (e). + * + * Do not use memset, because we must account for changes, + * so we need to loop over the words with hweight() anyways. + */ + unsigned long sl = ALIGN(s,BITS_PER_LONG); + unsigned long el = (e+1) & ~((unsigned long)BITS_PER_LONG-1); + int first_page; + int last_page; + int page_nr; + int first_word; + int last_word; + + if (e - s <= 3*BITS_PER_LONG) { + /* don't bother; el and sl may even be wrong. */ + __bm_change_bits_to(mdev, s, e, 1, KM_USER0); + return; + } + + /* difference is large enough that we can trust sl and el */ + + /* bits filling the current long */ + if (sl) + __bm_change_bits_to(mdev, s, sl-1, 1, KM_USER0); + + first_page = sl >> (3 + PAGE_SHIFT); + last_page = el >> (3 + PAGE_SHIFT); + + /* MLPP: modulo longs per page */ + /* LWPP: long words per page */ + first_word = MLPP(sl >> LN2_BPL); + last_word = LWPP; + + /* first and full pages, unless first page == last page */ + for (page_nr = first_page; page_nr < last_page; page_nr++) { + bm_set_full_words_within_one_page(mdev->bitmap, page_nr, first_word, last_word); + cond_resched(); + first_word = 0; + } + + /* last page (respectively only page, for first page == last page) */ + last_word = MLPP(el >> LN2_BPL); + bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word); + + /* possibly trailing bits. + * example: (e & 63) == 63, el will be e+1. + * if that even was the very last bit, + * it would trigger an assert in __bm_change_bits_to() + */ + if (el <= e) + __bm_change_bits_to(mdev, el, e, 1, KM_USER0); +} + +/* returns bit state + * wants bitnr, NOT sector. + * inherently racy... area needs to be locked by means of {al,rs}_lru + * 1 ... bit set + * 0 ... bit not set + * -1 ... first out of bounds access, stop testing for bits! + */ +int drbd_bm_test_bit(struct drbd_conf *mdev, const unsigned long bitnr) +{ + unsigned long flags; + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr; + int i; + + ERR_IF(!b) return 0; + ERR_IF(!b->bm_pages) return 0; + + spin_lock_irqsave(&b->bm_lock, flags); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + if (bitnr < b->bm_bits) { + unsigned long offset = bitnr>>LN2_BPL; + p_addr = bm_map_paddr(b, offset); + i = test_bit(bitnr & BPP_MASK, p_addr) ? 1 : 0; + bm_unmap(p_addr); + } else if (bitnr == b->bm_bits) { + i = -1; + } else { /* (bitnr > b->bm_bits) */ + dev_err(DEV, "bitnr=%lu > bm_bits=%lu\n", bitnr, b->bm_bits); + i = 0; + } + + spin_unlock_irqrestore(&b->bm_lock, flags); + return i; +} + +/* returns number of bits set in the range [s, e] */ +int drbd_bm_count_bits(struct drbd_conf *mdev, const unsigned long s, const unsigned long e) +{ + unsigned long flags; + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr = NULL, page_nr = -1; + unsigned long bitnr; + int c = 0; + size_t w; + + /* If this is called without a bitmap, that is a bug. But just to be + * robust in case we screwed up elsewhere, in that case pretend there + * was one dirty bit in the requested area, so we won't try to do a + * local read there (no bitmap probably implies no disk) */ + ERR_IF(!b) return 1; + ERR_IF(!b->bm_pages) return 1; + + spin_lock_irqsave(&b->bm_lock, flags); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + for (bitnr = s; bitnr <= e; bitnr++) { + w = bitnr >> LN2_BPL; + if (page_nr != w >> (PAGE_SHIFT - LN2_BPL + 3)) { + page_nr = w >> (PAGE_SHIFT - LN2_BPL + 3); + if (p_addr) + bm_unmap(p_addr); + p_addr = bm_map_paddr(b, w); + } + ERR_IF (bitnr >= b->bm_bits) { + dev_err(DEV, "bitnr=%lu bm_bits=%lu\n", bitnr, b->bm_bits); + } else { + c += (0 != test_bit(bitnr - (page_nr << (PAGE_SHIFT+3)), p_addr)); + } + } + if (p_addr) + bm_unmap(p_addr); + spin_unlock_irqrestore(&b->bm_lock, flags); + return c; +} + + +/* inherently racy... + * return value may be already out-of-date when this function returns. + * but the general usage is that this is only use during a cstate when bits are + * only cleared, not set, and typically only care for the case when the return + * value is zero, or we already "locked" this "bitmap extent" by other means. + * + * enr is bm-extent number, since we chose to name one sector (512 bytes) + * worth of the bitmap a "bitmap extent". + * + * TODO + * I think since we use it like a reference count, we should use the real + * reference count of some bitmap extent element from some lru instead... + * + */ +int drbd_bm_e_weight(struct drbd_conf *mdev, unsigned long enr) +{ + struct drbd_bitmap *b = mdev->bitmap; + int count, s, e; + unsigned long flags; + unsigned long *p_addr, *bm; + + ERR_IF(!b) return 0; + ERR_IF(!b->bm_pages) return 0; + + spin_lock_irqsave(&b->bm_lock, flags); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + + s = S2W(enr); + e = min((size_t)S2W(enr+1), b->bm_words); + count = 0; + if (s < b->bm_words) { + int n = e-s; + p_addr = bm_map_paddr(b, s); + bm = p_addr + MLPP(s); + while (n--) + count += hweight_long(*bm++); + bm_unmap(p_addr); + } else { + dev_err(DEV, "start offset (%d) too large in drbd_bm_e_weight\n", s); + } + spin_unlock_irqrestore(&b->bm_lock, flags); + return count; +} + +/* set all bits covered by the AL-extent al_enr */ +unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev, unsigned long al_enr) +{ + struct drbd_bitmap *b = mdev->bitmap; + unsigned long *p_addr, *bm; + unsigned long weight; + int count, s, e, i, do_now; + ERR_IF(!b) return 0; + ERR_IF(!b->bm_pages) return 0; + + spin_lock_irq(&b->bm_lock); + if (bm_is_locked(b)) + bm_print_lock_info(mdev); + weight = b->bm_set; + + s = al_enr * BM_WORDS_PER_AL_EXT; + e = min_t(size_t, s + BM_WORDS_PER_AL_EXT, b->bm_words); + /* assert that s and e are on the same page */ + D_ASSERT((e-1) >> (PAGE_SHIFT - LN2_BPL + 3) + == s >> (PAGE_SHIFT - LN2_BPL + 3)); + count = 0; + if (s < b->bm_words) { + i = do_now = e-s; + p_addr = bm_map_paddr(b, s); + bm = p_addr + MLPP(s); + while (i--) { + count += hweight_long(*bm); + *bm = -1UL; + bm++; + } + bm_unmap(p_addr); + b->bm_set += do_now*BITS_PER_LONG - count; + if (e == b->bm_words) + b->bm_set -= bm_clear_surplus(b); + } else { + dev_err(DEV, "start offset (%d) too large in drbd_bm_ALe_set_all\n", s); + } + weight = b->bm_set - weight; + spin_unlock_irq(&b->bm_lock); + return weight; +} diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h new file mode 100644 index 000000000000..2312d782fe99 --- /dev/null +++ b/drivers/block/drbd/drbd_int.h @@ -0,0 +1,2252 @@ +/* + drbd_int.h + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + +*/ + +#ifndef _DRBD_INT_H +#define _DRBD_INT_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef __CHECKER__ +# define __protected_by(x) __attribute__((require_context(x,1,999,"rdwr"))) +# define __protected_read_by(x) __attribute__((require_context(x,1,999,"read"))) +# define __protected_write_by(x) __attribute__((require_context(x,1,999,"write"))) +# define __must_hold(x) __attribute__((context(x,1,1), require_context(x,1,999,"call"))) +#else +# define __protected_by(x) +# define __protected_read_by(x) +# define __protected_write_by(x) +# define __must_hold(x) +#endif + +#define __no_warn(lock, stmt) do { __acquire(lock); stmt; __release(lock); } while (0) + +/* module parameter, defined in drbd_main.c */ +extern unsigned int minor_count; +extern int disable_sendpage; +extern int allow_oos; +extern unsigned int cn_idx; + +#ifdef CONFIG_DRBD_FAULT_INJECTION +extern int enable_faults; +extern int fault_rate; +extern int fault_devs; +#endif + +extern char usermode_helper[]; + + +#ifndef TRUE +#define TRUE 1 +#endif +#ifndef FALSE +#define FALSE 0 +#endif + +/* I don't remember why XCPU ... + * This is used to wake the asender, + * and to interrupt sending the sending task + * on disconnect. + */ +#define DRBD_SIG SIGXCPU + +/* This is used to stop/restart our threads. + * Cannot use SIGTERM nor SIGKILL, since these + * are sent out by init on runlevel changes + * I choose SIGHUP for now. + */ +#define DRBD_SIGKILL SIGHUP + +/* All EEs on the free list should have ID_VACANT (== 0) + * freshly allocated EEs get !ID_VACANT (== 1) + * so if it says "cannot dereference null pointer at adress 0x00000001", + * it is most likely one of these :( */ + +#define ID_IN_SYNC (4711ULL) +#define ID_OUT_OF_SYNC (4712ULL) + +#define ID_SYNCER (-1ULL) +#define ID_VACANT 0 +#define is_syncer_block_id(id) ((id) == ID_SYNCER) + +struct drbd_conf; + + +/* to shorten dev_warn(DEV, "msg"); and relatives statements */ +#define DEV (disk_to_dev(mdev->vdisk)) + +#define D_ASSERT(exp) if (!(exp)) \ + dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__) + +#define ERR_IF(exp) if (({ \ + int _b = (exp) != 0; \ + if (_b) dev_err(DEV, "%s: (%s) in %s:%d\n", \ + __func__, #exp, __FILE__, __LINE__); \ + _b; \ + })) + +/* Defines to control fault insertion */ +enum { + DRBD_FAULT_MD_WR = 0, /* meta data write */ + DRBD_FAULT_MD_RD = 1, /* read */ + DRBD_FAULT_RS_WR = 2, /* resync */ + DRBD_FAULT_RS_RD = 3, + DRBD_FAULT_DT_WR = 4, /* data */ + DRBD_FAULT_DT_RD = 5, + DRBD_FAULT_DT_RA = 6, /* data read ahead */ + DRBD_FAULT_BM_ALLOC = 7, /* bitmap allocation */ + DRBD_FAULT_AL_EE = 8, /* alloc ee */ + + DRBD_FAULT_MAX, +}; + +#ifdef CONFIG_DRBD_FAULT_INJECTION +extern unsigned int +_drbd_insert_fault(struct drbd_conf *mdev, unsigned int type); +static inline int +drbd_insert_fault(struct drbd_conf *mdev, unsigned int type) { + return fault_rate && + (enable_faults & (1< P_MAY_IGNORE) ... */ + P_MAX_OPT_CMD = 0x101, + + /* special command ids for handshake */ + + P_HAND_SHAKE_M = 0xfff1, /* First Packet on the MetaSock */ + P_HAND_SHAKE_S = 0xfff2, /* First Packet on the Socket */ + + P_HAND_SHAKE = 0xfffe /* FIXED for the next century! */ +}; + +static inline const char *cmdname(enum drbd_packets cmd) +{ + /* THINK may need to become several global tables + * when we want to support more than + * one PRO_VERSION */ + static const char *cmdnames[] = { + [P_DATA] = "Data", + [P_DATA_REPLY] = "DataReply", + [P_RS_DATA_REPLY] = "RSDataReply", + [P_BARRIER] = "Barrier", + [P_BITMAP] = "ReportBitMap", + [P_BECOME_SYNC_TARGET] = "BecomeSyncTarget", + [P_BECOME_SYNC_SOURCE] = "BecomeSyncSource", + [P_UNPLUG_REMOTE] = "UnplugRemote", + [P_DATA_REQUEST] = "DataRequest", + [P_RS_DATA_REQUEST] = "RSDataRequest", + [P_SYNC_PARAM] = "SyncParam", + [P_SYNC_PARAM89] = "SyncParam89", + [P_PROTOCOL] = "ReportProtocol", + [P_UUIDS] = "ReportUUIDs", + [P_SIZES] = "ReportSizes", + [P_STATE] = "ReportState", + [P_SYNC_UUID] = "ReportSyncUUID", + [P_AUTH_CHALLENGE] = "AuthChallenge", + [P_AUTH_RESPONSE] = "AuthResponse", + [P_PING] = "Ping", + [P_PING_ACK] = "PingAck", + [P_RECV_ACK] = "RecvAck", + [P_WRITE_ACK] = "WriteAck", + [P_RS_WRITE_ACK] = "RSWriteAck", + [P_DISCARD_ACK] = "DiscardAck", + [P_NEG_ACK] = "NegAck", + [P_NEG_DREPLY] = "NegDReply", + [P_NEG_RS_DREPLY] = "NegRSDReply", + [P_BARRIER_ACK] = "BarrierAck", + [P_STATE_CHG_REQ] = "StateChgRequest", + [P_STATE_CHG_REPLY] = "StateChgReply", + [P_OV_REQUEST] = "OVRequest", + [P_OV_REPLY] = "OVReply", + [P_OV_RESULT] = "OVResult", + [P_MAX_CMD] = NULL, + }; + + if (cmd == P_HAND_SHAKE_M) + return "HandShakeM"; + if (cmd == P_HAND_SHAKE_S) + return "HandShakeS"; + if (cmd == P_HAND_SHAKE) + return "HandShake"; + if (cmd >= P_MAX_CMD) + return "Unknown"; + return cmdnames[cmd]; +} + +/* for sending/receiving the bitmap, + * possibly in some encoding scheme */ +struct bm_xfer_ctx { + /* "const" + * stores total bits and long words + * of the bitmap, so we don't need to + * call the accessor functions over and again. */ + unsigned long bm_bits; + unsigned long bm_words; + /* during xfer, current position within the bitmap */ + unsigned long bit_offset; + unsigned long word_offset; + + /* statistics; index: (h->command == P_BITMAP) */ + unsigned packets[2]; + unsigned bytes[2]; +}; + +extern void INFO_bm_xfer_stats(struct drbd_conf *mdev, + const char *direction, struct bm_xfer_ctx *c); + +static inline void bm_xfer_ctx_bit_to_word_offset(struct bm_xfer_ctx *c) +{ + /* word_offset counts "native long words" (32 or 64 bit), + * aligned at 64 bit. + * Encoded packet may end at an unaligned bit offset. + * In case a fallback clear text packet is transmitted in + * between, we adjust this offset back to the last 64bit + * aligned "native long word", which makes coding and decoding + * the plain text bitmap much more convenient. */ +#if BITS_PER_LONG == 64 + c->word_offset = c->bit_offset >> 6; +#elif BITS_PER_LONG == 32 + c->word_offset = c->bit_offset >> 5; + c->word_offset &= ~(1UL); +#else +# error "unsupported BITS_PER_LONG" +#endif +} + +#ifndef __packed +#define __packed __attribute__((packed)) +#endif + +/* This is the layout for a packet on the wire. + * The byteorder is the network byte order. + * (except block_id and barrier fields. + * these are pointers to local structs + * and have no relevance for the partner, + * which just echoes them as received.) + * + * NOTE that the payload starts at a long aligned offset, + * regardless of 32 or 64 bit arch! + */ +struct p_header { + u32 magic; + u16 command; + u16 length; /* bytes of data after this header */ + u8 payload[0]; +} __packed; +/* 8 bytes. packet FIXED for the next century! */ + +/* + * short commands, packets without payload, plain p_header: + * P_PING + * P_PING_ACK + * P_BECOME_SYNC_TARGET + * P_BECOME_SYNC_SOURCE + * P_UNPLUG_REMOTE + */ + +/* + * commands with out-of-struct payload: + * P_BITMAP (no additional fields) + * P_DATA, P_DATA_REPLY (see p_data) + * P_COMPRESSED_BITMAP (see receive_compressed_bitmap) + */ + +/* these defines must not be changed without changing the protocol version */ +#define DP_HARDBARRIER 1 +#define DP_RW_SYNC 2 +#define DP_MAY_SET_IN_SYNC 4 + +struct p_data { + struct p_header head; + u64 sector; /* 64 bits sector number */ + u64 block_id; /* to identify the request in protocol B&C */ + u32 seq_num; + u32 dp_flags; +} __packed; + +/* + * commands which share a struct: + * p_block_ack: + * P_RECV_ACK (proto B), P_WRITE_ACK (proto C), + * P_DISCARD_ACK (proto C, two-primaries conflict detection) + * p_block_req: + * P_DATA_REQUEST, P_RS_DATA_REQUEST + */ +struct p_block_ack { + struct p_header head; + u64 sector; + u64 block_id; + u32 blksize; + u32 seq_num; +} __packed; + + +struct p_block_req { + struct p_header head; + u64 sector; + u64 block_id; + u32 blksize; + u32 pad; /* to multiple of 8 Byte */ +} __packed; + +/* + * commands with their own struct for additional fields: + * P_HAND_SHAKE + * P_BARRIER + * P_BARRIER_ACK + * P_SYNC_PARAM + * ReportParams + */ + +struct p_handshake { + struct p_header head; /* 8 bytes */ + u32 protocol_min; + u32 feature_flags; + u32 protocol_max; + + /* should be more than enough for future enhancements + * for now, feature_flags and the reserverd array shall be zero. + */ + + u32 _pad; + u64 reserverd[7]; +} __packed; +/* 80 bytes, FIXED for the next century */ + +struct p_barrier { + struct p_header head; + u32 barrier; /* barrier number _handle_ only */ + u32 pad; /* to multiple of 8 Byte */ +} __packed; + +struct p_barrier_ack { + struct p_header head; + u32 barrier; + u32 set_size; +} __packed; + +struct p_rs_param { + struct p_header head; + u32 rate; + + /* Since protocol version 88 and higher. */ + char verify_alg[0]; +} __packed; + +struct p_rs_param_89 { + struct p_header head; + u32 rate; + /* protocol version 89: */ + char verify_alg[SHARED_SECRET_MAX]; + char csums_alg[SHARED_SECRET_MAX]; +} __packed; + +struct p_protocol { + struct p_header head; + u32 protocol; + u32 after_sb_0p; + u32 after_sb_1p; + u32 after_sb_2p; + u32 want_lose; + u32 two_primaries; + + /* Since protocol version 87 and higher. */ + char integrity_alg[0]; + +} __packed; + +struct p_uuids { + struct p_header head; + u64 uuid[UI_EXTENDED_SIZE]; +} __packed; + +struct p_rs_uuid { + struct p_header head; + u64 uuid; +} __packed; + +struct p_sizes { + struct p_header head; + u64 d_size; /* size of disk */ + u64 u_size; /* user requested size */ + u64 c_size; /* current exported size */ + u32 max_segment_size; /* Maximal size of a BIO */ + u32 queue_order_type; +} __packed; + +struct p_state { + struct p_header head; + u32 state; +} __packed; + +struct p_req_state { + struct p_header head; + u32 mask; + u32 val; +} __packed; + +struct p_req_state_reply { + struct p_header head; + u32 retcode; +} __packed; + +struct p_drbd06_param { + u64 size; + u32 state; + u32 blksize; + u32 protocol; + u32 version; + u32 gen_cnt[5]; + u32 bit_map_gen[5]; +} __packed; + +struct p_discard { + struct p_header head; + u64 block_id; + u32 seq_num; + u32 pad; +} __packed; + +/* Valid values for the encoding field. + * Bump proto version when changing this. */ +enum drbd_bitmap_code { + /* RLE_VLI_Bytes = 0, + * and other bit variants had been defined during + * algorithm evaluation. */ + RLE_VLI_Bits = 2, +}; + +struct p_compressed_bm { + struct p_header head; + /* (encoding & 0x0f): actual encoding, see enum drbd_bitmap_code + * (encoding & 0x80): polarity (set/unset) of first runlength + * ((encoding >> 4) & 0x07): pad_bits, number of trailing zero bits + * used to pad up to head.length bytes + */ + u8 encoding; + + u8 code[0]; +} __packed; + +/* DCBP: Drbd Compressed Bitmap Packet ... */ +static inline enum drbd_bitmap_code +DCBP_get_code(struct p_compressed_bm *p) +{ + return (enum drbd_bitmap_code)(p->encoding & 0x0f); +} + +static inline void +DCBP_set_code(struct p_compressed_bm *p, enum drbd_bitmap_code code) +{ + BUG_ON(code & ~0xf); + p->encoding = (p->encoding & ~0xf) | code; +} + +static inline int +DCBP_get_start(struct p_compressed_bm *p) +{ + return (p->encoding & 0x80) != 0; +} + +static inline void +DCBP_set_start(struct p_compressed_bm *p, int set) +{ + p->encoding = (p->encoding & ~0x80) | (set ? 0x80 : 0); +} + +static inline int +DCBP_get_pad_bits(struct p_compressed_bm *p) +{ + return (p->encoding >> 4) & 0x7; +} + +static inline void +DCBP_set_pad_bits(struct p_compressed_bm *p, int n) +{ + BUG_ON(n & ~0x7); + p->encoding = (p->encoding & (~0x7 << 4)) | (n << 4); +} + +/* one bitmap packet, including the p_header, + * should fit within one _architecture independend_ page. + * so we need to use the fixed size 4KiB page size + * most architechtures have used for a long time. + */ +#define BM_PACKET_PAYLOAD_BYTES (4096 - sizeof(struct p_header)) +#define BM_PACKET_WORDS (BM_PACKET_PAYLOAD_BYTES/sizeof(long)) +#define BM_PACKET_VLI_BYTES_MAX (4096 - sizeof(struct p_compressed_bm)) +#if (PAGE_SIZE < 4096) +/* drbd_send_bitmap / receive_bitmap would break horribly */ +#error "PAGE_SIZE too small" +#endif + +union p_polymorph { + struct p_header header; + struct p_handshake handshake; + struct p_data data; + struct p_block_ack block_ack; + struct p_barrier barrier; + struct p_barrier_ack barrier_ack; + struct p_rs_param_89 rs_param_89; + struct p_protocol protocol; + struct p_sizes sizes; + struct p_uuids uuids; + struct p_state state; + struct p_req_state req_state; + struct p_req_state_reply req_state_reply; + struct p_block_req block_req; +} __packed; + +/**********************************************************************/ +enum drbd_thread_state { + None, + Running, + Exiting, + Restarting +}; + +struct drbd_thread { + spinlock_t t_lock; + struct task_struct *task; + struct completion stop; + enum drbd_thread_state t_state; + int (*function) (struct drbd_thread *); + struct drbd_conf *mdev; + int reset_cpu_mask; +}; + +static inline enum drbd_thread_state get_t_state(struct drbd_thread *thi) +{ + /* THINK testing the t_state seems to be uncritical in all cases + * (but thread_{start,stop}), so we can read it *without* the lock. + * --lge */ + + smp_rmb(); + return thi->t_state; +} + + +/* + * Having this as the first member of a struct provides sort of "inheritance". + * "derived" structs can be "drbd_queue_work()"ed. + * The callback should know and cast back to the descendant struct. + * drbd_request and drbd_epoch_entry are descendants of drbd_work. + */ +struct drbd_work; +typedef int (*drbd_work_cb)(struct drbd_conf *, struct drbd_work *, int cancel); +struct drbd_work { + struct list_head list; + drbd_work_cb cb; +}; + +struct drbd_tl_epoch; +struct drbd_request { + struct drbd_work w; + struct drbd_conf *mdev; + + /* if local IO is not allowed, will be NULL. + * if local IO _is_ allowed, holds the locally submitted bio clone, + * or, after local IO completion, the ERR_PTR(error). + * see drbd_endio_pri(). */ + struct bio *private_bio; + + struct hlist_node colision; + sector_t sector; + unsigned int size; + unsigned int epoch; /* barrier_nr */ + + /* barrier_nr: used to check on "completion" whether this req was in + * the current epoch, and we therefore have to close it, + * starting a new epoch... + */ + + /* up to here, the struct layout is identical to drbd_epoch_entry; + * we might be able to use that to our advantage... */ + + struct list_head tl_requests; /* ring list in the transfer log */ + struct bio *master_bio; /* master bio pointer */ + unsigned long rq_state; /* see comments above _req_mod() */ + int seq_num; + unsigned long start_time; +}; + +struct drbd_tl_epoch { + struct drbd_work w; + struct list_head requests; /* requests before */ + struct drbd_tl_epoch *next; /* pointer to the next barrier */ + unsigned int br_number; /* the barriers identifier. */ + int n_req; /* number of requests attached before this barrier */ +}; + +struct drbd_request; + +/* These Tl_epoch_entries may be in one of 6 lists: + active_ee .. data packet being written + sync_ee .. syncer block being written + done_ee .. block written, need to send P_WRITE_ACK + read_ee .. [RS]P_DATA_REQUEST being read +*/ + +struct drbd_epoch { + struct list_head list; + unsigned int barrier_nr; + atomic_t epoch_size; /* increased on every request added. */ + atomic_t active; /* increased on every req. added, and dec on every finished. */ + unsigned long flags; +}; + +/* drbd_epoch flag bits */ +enum { + DE_BARRIER_IN_NEXT_EPOCH_ISSUED, + DE_BARRIER_IN_NEXT_EPOCH_DONE, + DE_CONTAINS_A_BARRIER, + DE_HAVE_BARRIER_NUMBER, + DE_IS_FINISHING, +}; + +enum epoch_event { + EV_PUT, + EV_GOT_BARRIER_NR, + EV_BARRIER_DONE, + EV_BECAME_LAST, + EV_CLEANUP = 32, /* used as flag */ +}; + +struct drbd_epoch_entry { + struct drbd_work w; + struct drbd_conf *mdev; + struct bio *private_bio; + struct hlist_node colision; + sector_t sector; + unsigned int size; + struct drbd_epoch *epoch; + + /* up to here, the struct layout is identical to drbd_request; + * we might be able to use that to our advantage... */ + + unsigned int flags; + u64 block_id; +}; + +struct drbd_wq_barrier { + struct drbd_work w; + struct completion done; +}; + +struct digest_info { + int digest_size; + void *digest; +}; + +/* ee flag bits */ +enum { + __EE_CALL_AL_COMPLETE_IO, + __EE_CONFLICT_PENDING, + __EE_MAY_SET_IN_SYNC, + __EE_IS_BARRIER, +}; +#define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO) +#define EE_CONFLICT_PENDING (1<<__EE_CONFLICT_PENDING) +#define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC) +#define EE_IS_BARRIER (1<<__EE_IS_BARRIER) + +/* global flag bits */ +enum { + CREATE_BARRIER, /* next P_DATA is preceeded by a P_BARRIER */ + SIGNAL_ASENDER, /* whether asender wants to be interrupted */ + SEND_PING, /* whether asender should send a ping asap */ + + STOP_SYNC_TIMER, /* tell timer to cancel itself */ + UNPLUG_QUEUED, /* only relevant with kernel 2.4 */ + UNPLUG_REMOTE, /* sending a "UnplugRemote" could help */ + MD_DIRTY, /* current uuids and flags not yet on disk */ + DISCARD_CONCURRENT, /* Set on one node, cleared on the peer! */ + USE_DEGR_WFC_T, /* degr-wfc-timeout instead of wfc-timeout. */ + CLUSTER_ST_CHANGE, /* Cluster wide state change going on... */ + CL_ST_CHG_SUCCESS, + CL_ST_CHG_FAIL, + CRASHED_PRIMARY, /* This node was a crashed primary. + * Gets cleared when the state.conn + * goes into C_CONNECTED state. */ + WRITE_BM_AFTER_RESYNC, /* A kmalloc() during resync failed */ + NO_BARRIER_SUPP, /* underlying block device doesn't implement barriers */ + CONSIDER_RESYNC, + + MD_NO_BARRIER, /* meta data device does not support barriers, + so don't even try */ + SUSPEND_IO, /* suspend application io */ + BITMAP_IO, /* suspend application io; + once no more io in flight, start bitmap io */ + BITMAP_IO_QUEUED, /* Started bitmap IO */ + RESYNC_AFTER_NEG, /* Resync after online grow after the attach&negotiate finished. */ + NET_CONGESTED, /* The data socket is congested */ + + CONFIG_PENDING, /* serialization of (re)configuration requests. + * if set, also prevents the device from dying */ + DEVICE_DYING, /* device became unconfigured, + * but worker thread is still handling the cleanup. + * reconfiguring (nl_disk_conf, nl_net_conf) is dissalowed, + * while this is set. */ + RESIZE_PENDING, /* Size change detected locally, waiting for the response from + * the peer, if it changed there as well. */ +}; + +struct drbd_bitmap; /* opaque for drbd_conf */ + +/* TODO sort members for performance + * MAYBE group them further */ + +/* THINK maybe we actually want to use the default "event/%s" worker threads + * or similar in linux 2.6, which uses per cpu data and threads. + * + * To be general, this might need a spin_lock member. + * For now, please use the mdev->req_lock to protect list_head, + * see drbd_queue_work below. + */ +struct drbd_work_queue { + struct list_head q; + struct semaphore s; /* producers up it, worker down()s it */ + spinlock_t q_lock; /* to protect the list. */ +}; + +struct drbd_socket { + struct drbd_work_queue work; + struct mutex mutex; + struct socket *socket; + /* this way we get our + * send/receive buffers off the stack */ + union p_polymorph sbuf; + union p_polymorph rbuf; +}; + +struct drbd_md { + u64 md_offset; /* sector offset to 'super' block */ + + u64 la_size_sect; /* last agreed size, unit sectors */ + u64 uuid[UI_SIZE]; + u64 device_uuid; + u32 flags; + u32 md_size_sect; + + s32 al_offset; /* signed relative sector offset to al area */ + s32 bm_offset; /* signed relative sector offset to bitmap */ + + /* u32 al_nr_extents; important for restoring the AL + * is stored into sync_conf.al_extents, which in turn + * gets applied to act_log->nr_elements + */ +}; + +/* for sync_conf and other types... */ +#define NL_PACKET(name, number, fields) struct name { fields }; +#define NL_INTEGER(pn,pr,member) int member; +#define NL_INT64(pn,pr,member) __u64 member; +#define NL_BIT(pn,pr,member) unsigned member:1; +#define NL_STRING(pn,pr,member,len) unsigned char member[len]; int member ## _len; +#include "linux/drbd_nl.h" + +struct drbd_backing_dev { + struct block_device *backing_bdev; + struct block_device *md_bdev; + struct file *lo_file; + struct file *md_file; + struct drbd_md md; + struct disk_conf dc; /* The user provided config... */ + sector_t known_size; /* last known size of that backing device */ +}; + +struct drbd_md_io { + struct drbd_conf *mdev; + struct completion event; + int error; +}; + +struct bm_io_work { + struct drbd_work w; + char *why; + int (*io_fn)(struct drbd_conf *mdev); + void (*done)(struct drbd_conf *mdev, int rv); +}; + +enum write_ordering_e { + WO_none, + WO_drain_io, + WO_bdev_flush, + WO_bio_barrier +}; + +struct drbd_conf { + /* things that are stored as / read from meta data on disk */ + unsigned long flags; + + /* configured by drbdsetup */ + struct net_conf *net_conf; /* protected by get_net_conf() and put_net_conf() */ + struct syncer_conf sync_conf; + struct drbd_backing_dev *ldev __protected_by(local); + + sector_t p_size; /* partner's disk size */ + struct request_queue *rq_queue; + struct block_device *this_bdev; + struct gendisk *vdisk; + + struct drbd_socket data; /* data/barrier/cstate/parameter packets */ + struct drbd_socket meta; /* ping/ack (metadata) packets */ + int agreed_pro_version; /* actually used protocol version */ + unsigned long last_received; /* in jiffies, either socket */ + unsigned int ko_count; + struct drbd_work resync_work, + unplug_work, + md_sync_work; + struct timer_list resync_timer; + struct timer_list md_sync_timer; + + /* Used after attach while negotiating new disk state. */ + union drbd_state new_state_tmp; + + union drbd_state state; + wait_queue_head_t misc_wait; + wait_queue_head_t state_wait; /* upon each state change. */ + unsigned int send_cnt; + unsigned int recv_cnt; + unsigned int read_cnt; + unsigned int writ_cnt; + unsigned int al_writ_cnt; + unsigned int bm_writ_cnt; + atomic_t ap_bio_cnt; /* Requests we need to complete */ + atomic_t ap_pending_cnt; /* AP data packets on the wire, ack expected */ + atomic_t rs_pending_cnt; /* RS request/data packets on the wire */ + atomic_t unacked_cnt; /* Need to send replys for */ + atomic_t local_cnt; /* Waiting for local completion */ + atomic_t net_cnt; /* Users of net_conf */ + spinlock_t req_lock; + struct drbd_tl_epoch *unused_spare_tle; /* for pre-allocation */ + struct drbd_tl_epoch *newest_tle; + struct drbd_tl_epoch *oldest_tle; + struct list_head out_of_sequence_requests; + struct hlist_head *tl_hash; + unsigned int tl_hash_s; + + /* blocks to sync in this run [unit BM_BLOCK_SIZE] */ + unsigned long rs_total; + /* number of sync IOs that failed in this run */ + unsigned long rs_failed; + /* Syncer's start time [unit jiffies] */ + unsigned long rs_start; + /* cumulated time in PausedSyncX state [unit jiffies] */ + unsigned long rs_paused; + /* block not up-to-date at mark [unit BM_BLOCK_SIZE] */ + unsigned long rs_mark_left; + /* marks's time [unit jiffies] */ + unsigned long rs_mark_time; + /* skipped because csum was equeal [unit BM_BLOCK_SIZE] */ + unsigned long rs_same_csum; + + /* where does the admin want us to start? (sector) */ + sector_t ov_start_sector; + /* where are we now? (sector) */ + sector_t ov_position; + /* Start sector of out of sync range (to merge printk reporting). */ + sector_t ov_last_oos_start; + /* size of out-of-sync range in sectors. */ + sector_t ov_last_oos_size; + unsigned long ov_left; /* in bits */ + struct crypto_hash *csums_tfm; + struct crypto_hash *verify_tfm; + + struct drbd_thread receiver; + struct drbd_thread worker; + struct drbd_thread asender; + struct drbd_bitmap *bitmap; + unsigned long bm_resync_fo; /* bit offset for drbd_bm_find_next */ + + /* Used to track operations of resync... */ + struct lru_cache *resync; + /* Number of locked elements in resync LRU */ + unsigned int resync_locked; + /* resync extent number waiting for application requests */ + unsigned int resync_wenr; + + int open_cnt; + u64 *p_uuid; + struct drbd_epoch *current_epoch; + spinlock_t epoch_lock; + unsigned int epochs; + enum write_ordering_e write_ordering; + struct list_head active_ee; /* IO in progress */ + struct list_head sync_ee; /* IO in progress */ + struct list_head done_ee; /* send ack */ + struct list_head read_ee; /* IO in progress */ + struct list_head net_ee; /* zero-copy network send in progress */ + struct hlist_head *ee_hash; /* is proteced by req_lock! */ + unsigned int ee_hash_s; + + /* this one is protected by ee_lock, single thread */ + struct drbd_epoch_entry *last_write_w_barrier; + + int next_barrier_nr; + struct hlist_head *app_reads_hash; /* is proteced by req_lock */ + struct list_head resync_reads; + atomic_t pp_in_use; + wait_queue_head_t ee_wait; + struct page *md_io_page; /* one page buffer for md_io */ + struct page *md_io_tmpp; /* for logical_block_size != 512 */ + struct mutex md_io_mutex; /* protects the md_io_buffer */ + spinlock_t al_lock; + wait_queue_head_t al_wait; + struct lru_cache *act_log; /* activity log */ + unsigned int al_tr_number; + int al_tr_cycle; + int al_tr_pos; /* position of the next transaction in the journal */ + struct crypto_hash *cram_hmac_tfm; + struct crypto_hash *integrity_w_tfm; /* to be used by the worker thread */ + struct crypto_hash *integrity_r_tfm; /* to be used by the receiver thread */ + void *int_dig_out; + void *int_dig_in; + void *int_dig_vv; + wait_queue_head_t seq_wait; + atomic_t packet_seq; + unsigned int peer_seq; + spinlock_t peer_seq_lock; + unsigned int minor; + unsigned long comm_bm_set; /* communicated number of set bits. */ + cpumask_var_t cpu_mask; + struct bm_io_work bm_io_work; + u64 ed_uuid; /* UUID of the exposed data */ + struct mutex state_mutex; + char congestion_reason; /* Why we where congested... */ +}; + +static inline struct drbd_conf *minor_to_mdev(unsigned int minor) +{ + struct drbd_conf *mdev; + + mdev = minor < minor_count ? minor_table[minor] : NULL; + + return mdev; +} + +static inline unsigned int mdev_to_minor(struct drbd_conf *mdev) +{ + return mdev->minor; +} + +/* returns 1 if it was successfull, + * returns 0 if there was no data socket. + * so wherever you are going to use the data.socket, e.g. do + * if (!drbd_get_data_sock(mdev)) + * return 0; + * CODE(); + * drbd_put_data_sock(mdev); + */ +static inline int drbd_get_data_sock(struct drbd_conf *mdev) +{ + mutex_lock(&mdev->data.mutex); + /* drbd_disconnect() could have called drbd_free_sock() + * while we were waiting in down()... */ + if (unlikely(mdev->data.socket == NULL)) { + mutex_unlock(&mdev->data.mutex); + return 0; + } + return 1; +} + +static inline void drbd_put_data_sock(struct drbd_conf *mdev) +{ + mutex_unlock(&mdev->data.mutex); +} + +/* + * function declarations + *************************/ + +/* drbd_main.c */ + +enum chg_state_flags { + CS_HARD = 1, + CS_VERBOSE = 2, + CS_WAIT_COMPLETE = 4, + CS_SERIALIZE = 8, + CS_ORDERED = CS_WAIT_COMPLETE + CS_SERIALIZE, +}; + +extern void drbd_init_set_defaults(struct drbd_conf *mdev); +extern int drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f, + union drbd_state mask, union drbd_state val); +extern void drbd_force_state(struct drbd_conf *, union drbd_state, + union drbd_state); +extern int _drbd_request_state(struct drbd_conf *, union drbd_state, + union drbd_state, enum chg_state_flags); +extern int __drbd_set_state(struct drbd_conf *, union drbd_state, + enum chg_state_flags, struct completion *done); +extern void print_st_err(struct drbd_conf *, union drbd_state, + union drbd_state, int); +extern int drbd_thread_start(struct drbd_thread *thi); +extern void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait); +#ifdef CONFIG_SMP +extern void drbd_thread_current_set_cpu(struct drbd_conf *mdev); +extern void drbd_calc_cpu_mask(struct drbd_conf *mdev); +#else +#define drbd_thread_current_set_cpu(A) ({}) +#define drbd_calc_cpu_mask(A) ({}) +#endif +extern void drbd_free_resources(struct drbd_conf *mdev); +extern void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr, + unsigned int set_size); +extern void tl_clear(struct drbd_conf *mdev); +extern void _tl_add_barrier(struct drbd_conf *, struct drbd_tl_epoch *); +extern void drbd_free_sock(struct drbd_conf *mdev); +extern int drbd_send(struct drbd_conf *mdev, struct socket *sock, + void *buf, size_t size, unsigned msg_flags); +extern int drbd_send_protocol(struct drbd_conf *mdev); +extern int drbd_send_uuids(struct drbd_conf *mdev); +extern int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev); +extern int drbd_send_sync_uuid(struct drbd_conf *mdev, u64 val); +extern int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply); +extern int _drbd_send_state(struct drbd_conf *mdev); +extern int drbd_send_state(struct drbd_conf *mdev); +extern int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock, + enum drbd_packets cmd, struct p_header *h, + size_t size, unsigned msg_flags); +#define USE_DATA_SOCKET 1 +#define USE_META_SOCKET 0 +extern int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket, + enum drbd_packets cmd, struct p_header *h, + size_t size); +extern int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, + char *data, size_t size); +extern int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc); +extern int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr, + u32 set_size); +extern int drbd_send_ack(struct drbd_conf *mdev, enum drbd_packets cmd, + struct drbd_epoch_entry *e); +extern int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd, + struct p_block_req *rp); +extern int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd, + struct p_data *dp); +extern int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd, + sector_t sector, int blksize, u64 block_id); +extern int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd, + struct drbd_epoch_entry *e); +extern int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req); +extern int _drbd_send_barrier(struct drbd_conf *mdev, + struct drbd_tl_epoch *barrier); +extern int drbd_send_drequest(struct drbd_conf *mdev, int cmd, + sector_t sector, int size, u64 block_id); +extern int drbd_send_drequest_csum(struct drbd_conf *mdev, + sector_t sector,int size, + void *digest, int digest_size, + enum drbd_packets cmd); +extern int drbd_send_ov_request(struct drbd_conf *mdev,sector_t sector,int size); + +extern int drbd_send_bitmap(struct drbd_conf *mdev); +extern int _drbd_send_bitmap(struct drbd_conf *mdev); +extern int drbd_send_sr_reply(struct drbd_conf *mdev, int retcode); +extern void drbd_free_bc(struct drbd_backing_dev *ldev); +extern void drbd_mdev_cleanup(struct drbd_conf *mdev); + +/* drbd_meta-data.c (still in drbd_main.c) */ +extern void drbd_md_sync(struct drbd_conf *mdev); +extern int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev); +/* maybe define them below as inline? */ +extern void drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local); +extern void _drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local); +extern void drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local); +extern void _drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local); +extern void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local); +extern void drbd_md_set_flag(struct drbd_conf *mdev, int flags) __must_hold(local); +extern void drbd_md_clear_flag(struct drbd_conf *mdev, int flags)__must_hold(local); +extern int drbd_md_test_flag(struct drbd_backing_dev *, int); +extern void drbd_md_mark_dirty(struct drbd_conf *mdev); +extern void drbd_queue_bitmap_io(struct drbd_conf *mdev, + int (*io_fn)(struct drbd_conf *), + void (*done)(struct drbd_conf *, int), + char *why); +extern int drbd_bmio_set_n_write(struct drbd_conf *mdev); +extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev); +extern int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why); + + +/* Meta data layout + We reserve a 128MB Block (4k aligned) + * either at the end of the backing device + * or on a seperate meta data device. */ + +#define MD_RESERVED_SECT (128LU << 11) /* 128 MB, unit sectors */ +/* The following numbers are sectors */ +#define MD_AL_OFFSET 8 /* 8 Sectors after start of meta area */ +#define MD_AL_MAX_SIZE 64 /* = 32 kb LOG ~ 3776 extents ~ 14 GB Storage */ +/* Allows up to about 3.8TB */ +#define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_MAX_SIZE) + +/* Since the smalles IO unit is usually 512 byte */ +#define MD_SECTOR_SHIFT 9 +#define MD_SECTOR_SIZE (1< we need 32 KB bitmap. + * Bit 0 ==> local node thinks this block is binary identical on both nodes + * Bit 1 ==> local node thinks this block needs to be synced. + */ + +#define BM_BLOCK_SHIFT 12 /* 4k per bit */ +#define BM_BLOCK_SIZE (1<>(BM_BLOCK_SHIFT-9)) +#define BM_BIT_TO_SECT(x) ((sector_t)(x)<<(BM_BLOCK_SHIFT-9)) +#define BM_SECT_PER_BIT BM_BIT_TO_SECT(1) + +/* bit to represented kilo byte conversion */ +#define Bit2KB(bits) ((bits)<<(BM_BLOCK_SHIFT-10)) + +/* in which _bitmap_ extent (resp. sector) the bit for a certain + * _storage_ sector is located in */ +#define BM_SECT_TO_EXT(x) ((x)>>(BM_EXT_SHIFT-9)) + +/* how much _storage_ sectors we have per bitmap sector */ +#define BM_EXT_TO_SECT(x) ((sector_t)(x) << (BM_EXT_SHIFT-9)) +#define BM_SECT_PER_EXT BM_EXT_TO_SECT(1) + +/* in one sector of the bitmap, we have this many activity_log extents. */ +#define AL_EXT_PER_BM_SECT (1 << (BM_EXT_SHIFT - AL_EXTENT_SHIFT)) +#define BM_WORDS_PER_AL_EXT (1 << (AL_EXTENT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL)) + +#define BM_BLOCKS_PER_BM_EXT_B (BM_EXT_SHIFT - BM_BLOCK_SHIFT) +#define BM_BLOCKS_PER_BM_EXT_MASK ((1<ov_last_oos_size) { + dev_err(DEV, "Out of sync: start=%llu, size=%lu (sectors)\n", + (unsigned long long)mdev->ov_last_oos_start, + (unsigned long)mdev->ov_last_oos_size); + } + mdev->ov_last_oos_size=0; +} + + +extern void drbd_csum(struct drbd_conf *, struct crypto_hash *, struct bio *, void *); +/* worker callbacks */ +extern int w_req_cancel_conflict(struct drbd_conf *, struct drbd_work *, int); +extern int w_read_retry_remote(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_end_data_req(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_end_rsdata_req(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_end_csum_rs_req(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_end_ov_reply(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_end_ov_req(struct drbd_conf *, struct drbd_work *, int); +extern int w_ov_finished(struct drbd_conf *, struct drbd_work *, int); +extern int w_resync_inactive(struct drbd_conf *, struct drbd_work *, int); +extern int w_resume_next_sg(struct drbd_conf *, struct drbd_work *, int); +extern int w_io_error(struct drbd_conf *, struct drbd_work *, int); +extern int w_send_write_hint(struct drbd_conf *, struct drbd_work *, int); +extern int w_make_resync_request(struct drbd_conf *, struct drbd_work *, int); +extern int w_send_dblock(struct drbd_conf *, struct drbd_work *, int); +extern int w_send_barrier(struct drbd_conf *, struct drbd_work *, int); +extern int w_send_read_req(struct drbd_conf *, struct drbd_work *, int); +extern int w_prev_work_done(struct drbd_conf *, struct drbd_work *, int); +extern int w_e_reissue(struct drbd_conf *, struct drbd_work *, int); + +extern void resync_timer_fn(unsigned long data); + +/* drbd_receiver.c */ +extern int drbd_release_ee(struct drbd_conf *mdev, struct list_head *list); +extern struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev, + u64 id, + sector_t sector, + unsigned int data_size, + gfp_t gfp_mask) __must_hold(local); +extern void drbd_free_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e); +extern void drbd_wait_ee_list_empty(struct drbd_conf *mdev, + struct list_head *head); +extern void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, + struct list_head *head); +extern void drbd_set_recv_tcq(struct drbd_conf *mdev, int tcq_enabled); +extern void _drbd_clear_done_ee(struct drbd_conf *mdev, struct list_head *to_be_freed); +extern void drbd_flush_workqueue(struct drbd_conf *mdev); + +/* yes, there is kernel_setsockopt, but only since 2.6.18. we don't need to + * mess with get_fs/set_fs, we know we are KERNEL_DS always. */ +static inline int drbd_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + int err; + if (level == SOL_SOCKET) + err = sock_setsockopt(sock, level, optname, optval, optlen); + else + err = sock->ops->setsockopt(sock, level, optname, optval, + optlen); + return err; +} + +static inline void drbd_tcp_cork(struct socket *sock) +{ + int __user val = 1; + (void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK, + (char __user *)&val, sizeof(val)); +} + +static inline void drbd_tcp_uncork(struct socket *sock) +{ + int __user val = 0; + (void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK, + (char __user *)&val, sizeof(val)); +} + +static inline void drbd_tcp_nodelay(struct socket *sock) +{ + int __user val = 1; + (void) drbd_setsockopt(sock, SOL_TCP, TCP_NODELAY, + (char __user *)&val, sizeof(val)); +} + +static inline void drbd_tcp_quickack(struct socket *sock) +{ + int __user val = 1; + (void) drbd_setsockopt(sock, SOL_TCP, TCP_QUICKACK, + (char __user *)&val, sizeof(val)); +} + +void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo); + +/* drbd_proc.c */ +extern struct proc_dir_entry *drbd_proc; +extern struct file_operations drbd_proc_fops; +extern const char *drbd_conn_str(enum drbd_conns s); +extern const char *drbd_role_str(enum drbd_role s); + +/* drbd_actlog.c */ +extern void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector); +extern void drbd_al_complete_io(struct drbd_conf *mdev, sector_t sector); +extern void drbd_rs_complete_io(struct drbd_conf *mdev, sector_t sector); +extern int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector); +extern int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector); +extern void drbd_rs_cancel_all(struct drbd_conf *mdev); +extern int drbd_rs_del_all(struct drbd_conf *mdev); +extern void drbd_rs_failed_io(struct drbd_conf *mdev, + sector_t sector, int size); +extern int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *); +extern void __drbd_set_in_sync(struct drbd_conf *mdev, sector_t sector, + int size, const char *file, const unsigned int line); +#define drbd_set_in_sync(mdev, sector, size) \ + __drbd_set_in_sync(mdev, sector, size, __FILE__, __LINE__) +extern void __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, + int size, const char *file, const unsigned int line); +#define drbd_set_out_of_sync(mdev, sector, size) \ + __drbd_set_out_of_sync(mdev, sector, size, __FILE__, __LINE__) +extern void drbd_al_apply_to_bm(struct drbd_conf *mdev); +extern void drbd_al_to_on_disk_bm(struct drbd_conf *mdev); +extern void drbd_al_shrink(struct drbd_conf *mdev); + + +/* drbd_nl.c */ + +void drbd_nl_cleanup(void); +int __init drbd_nl_init(void); +void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state); +void drbd_bcast_sync_progress(struct drbd_conf *mdev); +void drbd_bcast_ee(struct drbd_conf *mdev, + const char *reason, const int dgs, + const char* seen_hash, const char* calc_hash, + const struct drbd_epoch_entry* e); + + +/** + * DOC: DRBD State macros + * + * These macros are used to express state changes in easily readable form. + * + * The NS macros expand to a mask and a value, that can be bit ored onto the + * current state as soon as the spinlock (req_lock) was taken. + * + * The _NS macros are used for state functions that get called with the + * spinlock. These macros expand directly to the new state value. + * + * Besides the basic forms NS() and _NS() additional _?NS[23] are defined + * to express state changes that affect more than one aspect of the state. + * + * E.g. NS2(conn, C_CONNECTED, peer, R_SECONDARY) + * Means that the network connection was established and that the peer + * is in secondary role. + */ +#define role_MASK R_MASK +#define peer_MASK R_MASK +#define disk_MASK D_MASK +#define pdsk_MASK D_MASK +#define conn_MASK C_MASK +#define susp_MASK 1 +#define user_isp_MASK 1 +#define aftr_isp_MASK 1 + +#define NS(T, S) \ + ({ union drbd_state mask; mask.i = 0; mask.T = T##_MASK; mask; }), \ + ({ union drbd_state val; val.i = 0; val.T = (S); val; }) +#define NS2(T1, S1, T2, S2) \ + ({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \ + mask.T2 = T2##_MASK; mask; }), \ + ({ union drbd_state val; val.i = 0; val.T1 = (S1); \ + val.T2 = (S2); val; }) +#define NS3(T1, S1, T2, S2, T3, S3) \ + ({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \ + mask.T2 = T2##_MASK; mask.T3 = T3##_MASK; mask; }), \ + ({ union drbd_state val; val.i = 0; val.T1 = (S1); \ + val.T2 = (S2); val.T3 = (S3); val; }) + +#define _NS(D, T, S) \ + D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T = (S); __ns; }) +#define _NS2(D, T1, S1, T2, S2) \ + D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T1 = (S1); \ + __ns.T2 = (S2); __ns; }) +#define _NS3(D, T1, S1, T2, S2, T3, S3) \ + D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T1 = (S1); \ + __ns.T2 = (S2); __ns.T3 = (S3); __ns; }) + +/* + * inline helper functions + *************************/ + +static inline void drbd_state_lock(struct drbd_conf *mdev) +{ + wait_event(mdev->misc_wait, + !test_and_set_bit(CLUSTER_ST_CHANGE, &mdev->flags)); +} + +static inline void drbd_state_unlock(struct drbd_conf *mdev) +{ + clear_bit(CLUSTER_ST_CHANGE, &mdev->flags); + wake_up(&mdev->misc_wait); +} + +static inline int _drbd_set_state(struct drbd_conf *mdev, + union drbd_state ns, enum chg_state_flags flags, + struct completion *done) +{ + int rv; + + read_lock(&global_state_lock); + rv = __drbd_set_state(mdev, ns, flags, done); + read_unlock(&global_state_lock); + + return rv; +} + +/** + * drbd_request_state() - Reqest a state change + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + * + * This is the most graceful way of requesting a state change. It is verbose + * quite verbose in case the state change is not possible, and all those + * state changes are globally serialized. + */ +static inline int drbd_request_state(struct drbd_conf *mdev, + union drbd_state mask, + union drbd_state val) +{ + return _drbd_request_state(mdev, mask, val, CS_VERBOSE + CS_ORDERED); +} + +#define __drbd_chk_io_error(m,f) __drbd_chk_io_error_(m,f, __func__) +static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach, const char *where) +{ + switch (mdev->ldev->dc.on_io_error) { + case EP_PASS_ON: + if (!forcedetach) { + if (printk_ratelimit()) + dev_err(DEV, "Local IO failed in %s." + "Passing error on...\n", where); + break; + } + /* NOTE fall through to detach case if forcedetach set */ + case EP_DETACH: + case EP_CALL_HELPER: + if (mdev->state.disk > D_FAILED) { + _drbd_set_state(_NS(mdev, disk, D_FAILED), CS_HARD, NULL); + dev_err(DEV, "Local IO failed in %s." + "Detaching...\n", where); + } + break; + } +} + +/** + * drbd_chk_io_error: Handle the on_io_error setting, should be called from all io completion handlers + * @mdev: DRBD device. + * @error: Error code passed to the IO completion callback + * @forcedetach: Force detach. I.e. the error happened while accessing the meta data + * + * See also drbd_main.c:after_state_ch() if (os.disk > D_FAILED && ns.disk == D_FAILED) + */ +#define drbd_chk_io_error(m,e,f) drbd_chk_io_error_(m,e,f, __func__) +static inline void drbd_chk_io_error_(struct drbd_conf *mdev, + int error, int forcedetach, const char *where) +{ + if (error) { + unsigned long flags; + spin_lock_irqsave(&mdev->req_lock, flags); + __drbd_chk_io_error_(mdev, forcedetach, where); + spin_unlock_irqrestore(&mdev->req_lock, flags); + } +} + + +/** + * drbd_md_first_sector() - Returns the first sector number of the meta data area + * @bdev: Meta data block device. + * + * BTW, for internal meta data, this happens to be the maximum capacity + * we could agree upon with our peer node. + */ +static inline sector_t drbd_md_first_sector(struct drbd_backing_dev *bdev) +{ + switch (bdev->dc.meta_dev_idx) { + case DRBD_MD_INDEX_INTERNAL: + case DRBD_MD_INDEX_FLEX_INT: + return bdev->md.md_offset + bdev->md.bm_offset; + case DRBD_MD_INDEX_FLEX_EXT: + default: + return bdev->md.md_offset; + } +} + +/** + * drbd_md_last_sector() - Return the last sector number of the meta data area + * @bdev: Meta data block device. + */ +static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev) +{ + switch (bdev->dc.meta_dev_idx) { + case DRBD_MD_INDEX_INTERNAL: + case DRBD_MD_INDEX_FLEX_INT: + return bdev->md.md_offset + MD_AL_OFFSET - 1; + case DRBD_MD_INDEX_FLEX_EXT: + default: + return bdev->md.md_offset + bdev->md.md_size_sect; + } +} + +/* Returns the number of 512 byte sectors of the device */ +static inline sector_t drbd_get_capacity(struct block_device *bdev) +{ + /* return bdev ? get_capacity(bdev->bd_disk) : 0; */ + return bdev ? bdev->bd_inode->i_size >> 9 : 0; +} + +/** + * drbd_get_max_capacity() - Returns the capacity we announce to out peer + * @bdev: Meta data block device. + * + * returns the capacity we announce to out peer. we clip ourselves at the + * various MAX_SECTORS, because if we don't, current implementation will + * oops sooner or later + */ +static inline sector_t drbd_get_max_capacity(struct drbd_backing_dev *bdev) +{ + sector_t s; + switch (bdev->dc.meta_dev_idx) { + case DRBD_MD_INDEX_INTERNAL: + case DRBD_MD_INDEX_FLEX_INT: + s = drbd_get_capacity(bdev->backing_bdev) + ? min_t(sector_t, DRBD_MAX_SECTORS_FLEX, + drbd_md_first_sector(bdev)) + : 0; + break; + case DRBD_MD_INDEX_FLEX_EXT: + s = min_t(sector_t, DRBD_MAX_SECTORS_FLEX, + drbd_get_capacity(bdev->backing_bdev)); + /* clip at maximum size the meta device can support */ + s = min_t(sector_t, s, + BM_EXT_TO_SECT(bdev->md.md_size_sect + - bdev->md.bm_offset)); + break; + default: + s = min_t(sector_t, DRBD_MAX_SECTORS, + drbd_get_capacity(bdev->backing_bdev)); + } + return s; +} + +/** + * drbd_md_ss__() - Return the sector number of our meta data super block + * @mdev: DRBD device. + * @bdev: Meta data block device. + */ +static inline sector_t drbd_md_ss__(struct drbd_conf *mdev, + struct drbd_backing_dev *bdev) +{ + switch (bdev->dc.meta_dev_idx) { + default: /* external, some index */ + return MD_RESERVED_SECT * bdev->dc.meta_dev_idx; + case DRBD_MD_INDEX_INTERNAL: + /* with drbd08, internal meta data is always "flexible" */ + case DRBD_MD_INDEX_FLEX_INT: + /* sizeof(struct md_on_disk_07) == 4k + * position: last 4k aligned block of 4k size */ + if (!bdev->backing_bdev) { + if (__ratelimit(&drbd_ratelimit_state)) { + dev_err(DEV, "bdev->backing_bdev==NULL\n"); + dump_stack(); + } + return 0; + } + return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) + - MD_AL_OFFSET; + case DRBD_MD_INDEX_FLEX_EXT: + return 0; + } +} + +static inline void +_drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w) +{ + list_add_tail(&w->list, &q->q); + up(&q->s); +} + +static inline void +drbd_queue_work_front(struct drbd_work_queue *q, struct drbd_work *w) +{ + unsigned long flags; + spin_lock_irqsave(&q->q_lock, flags); + list_add(&w->list, &q->q); + up(&q->s); /* within the spinlock, + see comment near end of drbd_worker() */ + spin_unlock_irqrestore(&q->q_lock, flags); +} + +static inline void +drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w) +{ + unsigned long flags; + spin_lock_irqsave(&q->q_lock, flags); + list_add_tail(&w->list, &q->q); + up(&q->s); /* within the spinlock, + see comment near end of drbd_worker() */ + spin_unlock_irqrestore(&q->q_lock, flags); +} + +static inline void wake_asender(struct drbd_conf *mdev) +{ + if (test_bit(SIGNAL_ASENDER, &mdev->flags)) + force_sig(DRBD_SIG, mdev->asender.task); +} + +static inline void request_ping(struct drbd_conf *mdev) +{ + set_bit(SEND_PING, &mdev->flags); + wake_asender(mdev); +} + +static inline int drbd_send_short_cmd(struct drbd_conf *mdev, + enum drbd_packets cmd) +{ + struct p_header h; + return drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd, &h, sizeof(h)); +} + +static inline int drbd_send_ping(struct drbd_conf *mdev) +{ + struct p_header h; + return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING, &h, sizeof(h)); +} + +static inline int drbd_send_ping_ack(struct drbd_conf *mdev) +{ + struct p_header h; + return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING_ACK, &h, sizeof(h)); +} + +static inline void drbd_thread_stop(struct drbd_thread *thi) +{ + _drbd_thread_stop(thi, FALSE, TRUE); +} + +static inline void drbd_thread_stop_nowait(struct drbd_thread *thi) +{ + _drbd_thread_stop(thi, FALSE, FALSE); +} + +static inline void drbd_thread_restart_nowait(struct drbd_thread *thi) +{ + _drbd_thread_stop(thi, TRUE, FALSE); +} + +/* counts how many answer packets packets we expect from our peer, + * for either explicit application requests, + * or implicit barrier packets as necessary. + * increased: + * w_send_barrier + * _req_mod(req, queue_for_net_write or queue_for_net_read); + * it is much easier and equally valid to count what we queue for the + * worker, even before it actually was queued or send. + * (drbd_make_request_common; recovery path on read io-error) + * decreased: + * got_BarrierAck (respective tl_clear, tl_clear_barrier) + * _req_mod(req, data_received) + * [from receive_DataReply] + * _req_mod(req, write_acked_by_peer or recv_acked_by_peer or neg_acked) + * [from got_BlockAck (P_WRITE_ACK, P_RECV_ACK)] + * for some reason it is NOT decreased in got_NegAck, + * but in the resulting cleanup code from report_params. + * we should try to remember the reason for that... + * _req_mod(req, send_failed or send_canceled) + * _req_mod(req, connection_lost_while_pending) + * [from tl_clear_barrier] + */ +static inline void inc_ap_pending(struct drbd_conf *mdev) +{ + atomic_inc(&mdev->ap_pending_cnt); +} + +#define ERR_IF_CNT_IS_NEGATIVE(which) \ + if (atomic_read(&mdev->which) < 0) \ + dev_err(DEV, "in %s:%d: " #which " = %d < 0 !\n", \ + __func__ , __LINE__ , \ + atomic_read(&mdev->which)) + +#define dec_ap_pending(mdev) do { \ + typecheck(struct drbd_conf *, mdev); \ + if (atomic_dec_and_test(&mdev->ap_pending_cnt)) \ + wake_up(&mdev->misc_wait); \ + ERR_IF_CNT_IS_NEGATIVE(ap_pending_cnt); } while (0) + +/* counts how many resync-related answers we still expect from the peer + * increase decrease + * C_SYNC_TARGET sends P_RS_DATA_REQUEST (and expects P_RS_DATA_REPLY) + * C_SYNC_SOURCE sends P_RS_DATA_REPLY (and expects P_WRITE_ACK whith ID_SYNCER) + * (or P_NEG_ACK with ID_SYNCER) + */ +static inline void inc_rs_pending(struct drbd_conf *mdev) +{ + atomic_inc(&mdev->rs_pending_cnt); +} + +#define dec_rs_pending(mdev) do { \ + typecheck(struct drbd_conf *, mdev); \ + atomic_dec(&mdev->rs_pending_cnt); \ + ERR_IF_CNT_IS_NEGATIVE(rs_pending_cnt); } while (0) + +/* counts how many answers we still need to send to the peer. + * increased on + * receive_Data unless protocol A; + * we need to send a P_RECV_ACK (proto B) + * or P_WRITE_ACK (proto C) + * receive_RSDataReply (recv_resync_read) we need to send a P_WRITE_ACK + * receive_DataRequest (receive_RSDataRequest) we need to send back P_DATA + * receive_Barrier_* we need to send a P_BARRIER_ACK + */ +static inline void inc_unacked(struct drbd_conf *mdev) +{ + atomic_inc(&mdev->unacked_cnt); +} + +#define dec_unacked(mdev) do { \ + typecheck(struct drbd_conf *, mdev); \ + atomic_dec(&mdev->unacked_cnt); \ + ERR_IF_CNT_IS_NEGATIVE(unacked_cnt); } while (0) + +#define sub_unacked(mdev, n) do { \ + typecheck(struct drbd_conf *, mdev); \ + atomic_sub(n, &mdev->unacked_cnt); \ + ERR_IF_CNT_IS_NEGATIVE(unacked_cnt); } while (0) + + +static inline void put_net_conf(struct drbd_conf *mdev) +{ + if (atomic_dec_and_test(&mdev->net_cnt)) + wake_up(&mdev->misc_wait); +} + +/** + * get_net_conf() - Increase ref count on mdev->net_conf; Returns 0 if nothing there + * @mdev: DRBD device. + * + * You have to call put_net_conf() when finished working with mdev->net_conf. + */ +static inline int get_net_conf(struct drbd_conf *mdev) +{ + int have_net_conf; + + atomic_inc(&mdev->net_cnt); + have_net_conf = mdev->state.conn >= C_UNCONNECTED; + if (!have_net_conf) + put_net_conf(mdev); + return have_net_conf; +} + +/** + * get_ldev() - Increase the ref count on mdev->ldev. Returns 0 if there is no ldev + * @M: DRBD device. + * + * You have to call put_ldev() when finished working with mdev->ldev. + */ +#define get_ldev(M) __cond_lock(local, _get_ldev_if_state(M,D_INCONSISTENT)) +#define get_ldev_if_state(M,MINS) __cond_lock(local, _get_ldev_if_state(M,MINS)) + +static inline void put_ldev(struct drbd_conf *mdev) +{ + __release(local); + if (atomic_dec_and_test(&mdev->local_cnt)) + wake_up(&mdev->misc_wait); + D_ASSERT(atomic_read(&mdev->local_cnt) >= 0); +} + +#ifndef __CHECKER__ +static inline int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins) +{ + int io_allowed; + + atomic_inc(&mdev->local_cnt); + io_allowed = (mdev->state.disk >= mins); + if (!io_allowed) + put_ldev(mdev); + return io_allowed; +} +#else +extern int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins); +#endif + +/* you must have an "get_ldev" reference */ +static inline void drbd_get_syncer_progress(struct drbd_conf *mdev, + unsigned long *bits_left, unsigned int *per_mil_done) +{ + /* + * this is to break it at compile time when we change that + * (we may feel 4TB maximum storage per drbd is not enough) + */ + typecheck(unsigned long, mdev->rs_total); + + /* note: both rs_total and rs_left are in bits, i.e. in + * units of BM_BLOCK_SIZE. + * for the percentage, we don't care. */ + + *bits_left = drbd_bm_total_weight(mdev) - mdev->rs_failed; + /* >> 10 to prevent overflow, + * +1 to prevent division by zero */ + if (*bits_left > mdev->rs_total) { + /* doh. maybe a logic bug somewhere. + * may also be just a race condition + * between this and a disconnect during sync. + * for now, just prevent in-kernel buffer overflow. + */ + smp_rmb(); + dev_warn(DEV, "cs:%s rs_left=%lu > rs_total=%lu (rs_failed %lu)\n", + drbd_conn_str(mdev->state.conn), + *bits_left, mdev->rs_total, mdev->rs_failed); + *per_mil_done = 0; + } else { + /* make sure the calculation happens in long context */ + unsigned long tmp = 1000UL - + (*bits_left >> 10)*1000UL + / ((mdev->rs_total >> 10) + 1UL); + *per_mil_done = tmp; + } +} + + +/* this throttles on-the-fly application requests + * according to max_buffers settings; + * maybe re-implement using semaphores? */ +static inline int drbd_get_max_buffers(struct drbd_conf *mdev) +{ + int mxb = 1000000; /* arbitrary limit on open requests */ + if (get_net_conf(mdev)) { + mxb = mdev->net_conf->max_buffers; + put_net_conf(mdev); + } + return mxb; +} + +static inline int drbd_state_is_stable(union drbd_state s) +{ + + /* DO NOT add a default clause, we want the compiler to warn us + * for any newly introduced state we may have forgotten to add here */ + + switch ((enum drbd_conns)s.conn) { + /* new io only accepted when there is no connection, ... */ + case C_STANDALONE: + case C_WF_CONNECTION: + /* ... or there is a well established connection. */ + case C_CONNECTED: + case C_SYNC_SOURCE: + case C_SYNC_TARGET: + case C_VERIFY_S: + case C_VERIFY_T: + case C_PAUSED_SYNC_S: + case C_PAUSED_SYNC_T: + /* maybe stable, look at the disk state */ + break; + + /* no new io accepted during tansitional states + * like handshake or teardown */ + case C_DISCONNECTING: + case C_UNCONNECTED: + case C_TIMEOUT: + case C_BROKEN_PIPE: + case C_NETWORK_FAILURE: + case C_PROTOCOL_ERROR: + case C_TEAR_DOWN: + case C_WF_REPORT_PARAMS: + case C_STARTING_SYNC_S: + case C_STARTING_SYNC_T: + case C_WF_BITMAP_S: + case C_WF_BITMAP_T: + case C_WF_SYNC_UUID: + case C_MASK: + /* not "stable" */ + return 0; + } + + switch ((enum drbd_disk_state)s.disk) { + case D_DISKLESS: + case D_INCONSISTENT: + case D_OUTDATED: + case D_CONSISTENT: + case D_UP_TO_DATE: + /* disk state is stable as well. */ + break; + + /* no new io accepted during tansitional states */ + case D_ATTACHING: + case D_FAILED: + case D_NEGOTIATING: + case D_UNKNOWN: + case D_MASK: + /* not "stable" */ + return 0; + } + + return 1; +} + +static inline int __inc_ap_bio_cond(struct drbd_conf *mdev) +{ + int mxb = drbd_get_max_buffers(mdev); + + if (mdev->state.susp) + return 0; + if (test_bit(SUSPEND_IO, &mdev->flags)) + return 0; + + /* to avoid potential deadlock or bitmap corruption, + * in various places, we only allow new application io + * to start during "stable" states. */ + + /* no new io accepted when attaching or detaching the disk */ + if (!drbd_state_is_stable(mdev->state)) + return 0; + + /* since some older kernels don't have atomic_add_unless, + * and we are within the spinlock anyways, we have this workaround. */ + if (atomic_read(&mdev->ap_bio_cnt) > mxb) + return 0; + if (test_bit(BITMAP_IO, &mdev->flags)) + return 0; + return 1; +} + +/* I'd like to use wait_event_lock_irq, + * but I'm not sure when it got introduced, + * and not sure when it has 3 or 4 arguments */ +static inline void inc_ap_bio(struct drbd_conf *mdev, int one_or_two) +{ + /* compare with after_state_ch, + * os.conn != C_WF_BITMAP_S && ns.conn == C_WF_BITMAP_S */ + DEFINE_WAIT(wait); + + /* we wait here + * as long as the device is suspended + * until the bitmap is no longer on the fly during connection + * handshake as long as we would exeed the max_buffer limit. + * + * to avoid races with the reconnect code, + * we need to atomic_inc within the spinlock. */ + + spin_lock_irq(&mdev->req_lock); + while (!__inc_ap_bio_cond(mdev)) { + prepare_to_wait(&mdev->misc_wait, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&mdev->req_lock); + schedule(); + finish_wait(&mdev->misc_wait, &wait); + spin_lock_irq(&mdev->req_lock); + } + atomic_add(one_or_two, &mdev->ap_bio_cnt); + spin_unlock_irq(&mdev->req_lock); +} + +static inline void dec_ap_bio(struct drbd_conf *mdev) +{ + int mxb = drbd_get_max_buffers(mdev); + int ap_bio = atomic_dec_return(&mdev->ap_bio_cnt); + + D_ASSERT(ap_bio >= 0); + /* this currently does wake_up for every dec_ap_bio! + * maybe rather introduce some type of hysteresis? + * e.g. (ap_bio == mxb/2 || ap_bio == 0) ? */ + if (ap_bio < mxb) + wake_up(&mdev->misc_wait); + if (ap_bio == 0 && test_bit(BITMAP_IO, &mdev->flags)) { + if (!test_and_set_bit(BITMAP_IO_QUEUED, &mdev->flags)) + drbd_queue_work(&mdev->data.work, &mdev->bm_io_work.w); + } +} + +static inline void drbd_set_ed_uuid(struct drbd_conf *mdev, u64 val) +{ + mdev->ed_uuid = val; +} + +static inline int seq_cmp(u32 a, u32 b) +{ + /* we assume wrap around at 32bit. + * for wrap around at 24bit (old atomic_t), + * we'd have to + * a <<= 8; b <<= 8; + */ + return (s32)(a) - (s32)(b); +} +#define seq_lt(a, b) (seq_cmp((a), (b)) < 0) +#define seq_gt(a, b) (seq_cmp((a), (b)) > 0) +#define seq_ge(a, b) (seq_cmp((a), (b)) >= 0) +#define seq_le(a, b) (seq_cmp((a), (b)) <= 0) +/* CAUTION: please no side effects in arguments! */ +#define seq_max(a, b) ((u32)(seq_gt((a), (b)) ? (a) : (b))) + +static inline void update_peer_seq(struct drbd_conf *mdev, unsigned int new_seq) +{ + unsigned int m; + spin_lock(&mdev->peer_seq_lock); + m = seq_max(mdev->peer_seq, new_seq); + mdev->peer_seq = m; + spin_unlock(&mdev->peer_seq_lock); + if (m == new_seq) + wake_up(&mdev->seq_wait); +} + +static inline void drbd_update_congested(struct drbd_conf *mdev) +{ + struct sock *sk = mdev->data.socket->sk; + if (sk->sk_wmem_queued > sk->sk_sndbuf * 4 / 5) + set_bit(NET_CONGESTED, &mdev->flags); +} + +static inline int drbd_queue_order_type(struct drbd_conf *mdev) +{ + /* sorry, we currently have no working implementation + * of distributed TCQ stuff */ +#ifndef QUEUE_ORDERED_NONE +#define QUEUE_ORDERED_NONE 0 +#endif + return QUEUE_ORDERED_NONE; +} + +static inline void drbd_blk_run_queue(struct request_queue *q) +{ + if (q && q->unplug_fn) + q->unplug_fn(q); +} + +static inline void drbd_kick_lo(struct drbd_conf *mdev) +{ + if (get_ldev(mdev)) { + drbd_blk_run_queue(bdev_get_queue(mdev->ldev->backing_bdev)); + put_ldev(mdev); + } +} + +static inline void drbd_md_flush(struct drbd_conf *mdev) +{ + int r; + + if (test_bit(MD_NO_BARRIER, &mdev->flags)) + return; + + r = blkdev_issue_flush(mdev->ldev->md_bdev, NULL); + if (r) { + set_bit(MD_NO_BARRIER, &mdev->flags); + dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r); + } +} + +#endif diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c new file mode 100644 index 000000000000..157d1e4343c2 --- /dev/null +++ b/drivers/block/drbd/drbd_main.c @@ -0,0 +1,3699 @@ +/* + drbd.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + Thanks to Carter Burden, Bart Grantham and Gennadiy Nerubayev + from Logicworks, Inc. for making SDP replication support possible. + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define __KERNEL_SYSCALLS__ +#include +#include + +#include +#include "drbd_int.h" +#include "drbd_req.h" /* only for _req_mod in tl_release and tl_clear */ + +#include "drbd_vli.h" + +struct after_state_chg_work { + struct drbd_work w; + union drbd_state os; + union drbd_state ns; + enum chg_state_flags flags; + struct completion *done; +}; + +int drbdd_init(struct drbd_thread *); +int drbd_worker(struct drbd_thread *); +int drbd_asender(struct drbd_thread *); + +int drbd_init(void); +static int drbd_open(struct block_device *bdev, fmode_t mode); +static int drbd_release(struct gendisk *gd, fmode_t mode); +static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused); +static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, enum chg_state_flags flags); +static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused); +static void md_sync_timer_fn(unsigned long data); +static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused); + +MODULE_AUTHOR("Philipp Reisner , " + "Lars Ellenberg "); +MODULE_DESCRIPTION("drbd - Distributed Replicated Block Device v" REL_VERSION); +MODULE_VERSION(REL_VERSION); +MODULE_LICENSE("GPL"); +MODULE_PARM_DESC(minor_count, "Maximum number of drbd devices (1-255)"); +MODULE_ALIAS_BLOCKDEV_MAJOR(DRBD_MAJOR); + +#include +/* allow_open_on_secondary */ +MODULE_PARM_DESC(allow_oos, "DONT USE!"); +/* thanks to these macros, if compiled into the kernel (not-module), + * this becomes the boot parameter drbd.minor_count */ +module_param(minor_count, uint, 0444); +module_param(disable_sendpage, bool, 0644); +module_param(allow_oos, bool, 0); +module_param(cn_idx, uint, 0444); +module_param(proc_details, int, 0644); + +#ifdef CONFIG_DRBD_FAULT_INJECTION +int enable_faults; +int fault_rate; +static int fault_count; +int fault_devs; +/* bitmap of enabled faults */ +module_param(enable_faults, int, 0664); +/* fault rate % value - applies to all enabled faults */ +module_param(fault_rate, int, 0664); +/* count of faults inserted */ +module_param(fault_count, int, 0664); +/* bitmap of devices to insert faults on */ +module_param(fault_devs, int, 0644); +#endif + +/* module parameter, defined */ +unsigned int minor_count = 32; +int disable_sendpage; +int allow_oos; +unsigned int cn_idx = CN_IDX_DRBD; +int proc_details; /* Detail level in proc drbd*/ + +/* Module parameter for setting the user mode helper program + * to run. Default is /sbin/drbdadm */ +char usermode_helper[80] = "/sbin/drbdadm"; + +module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0644); + +/* in 2.6.x, our device mapping and config info contains our virtual gendisks + * as member "struct gendisk *vdisk;" + */ +struct drbd_conf **minor_table; + +struct kmem_cache *drbd_request_cache; +struct kmem_cache *drbd_ee_cache; /* epoch entries */ +struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */ +struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ +mempool_t *drbd_request_mempool; +mempool_t *drbd_ee_mempool; + +/* I do not use a standard mempool, because: + 1) I want to hand out the pre-allocated objects first. + 2) I want to be able to interrupt sleeping allocation with a signal. + Note: This is a single linked list, the next pointer is the private + member of struct page. + */ +struct page *drbd_pp_pool; +spinlock_t drbd_pp_lock; +int drbd_pp_vacant; +wait_queue_head_t drbd_pp_wait; + +DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5); + +static struct block_device_operations drbd_ops = { + .owner = THIS_MODULE, + .open = drbd_open, + .release = drbd_release, +}; + +#define ARRY_SIZE(A) (sizeof(A)/sizeof(A[0])) + +#ifdef __CHECKER__ +/* When checking with sparse, and this is an inline function, sparse will + give tons of false positives. When this is a real functions sparse works. + */ +int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins) +{ + int io_allowed; + + atomic_inc(&mdev->local_cnt); + io_allowed = (mdev->state.disk >= mins); + if (!io_allowed) { + if (atomic_dec_and_test(&mdev->local_cnt)) + wake_up(&mdev->misc_wait); + } + return io_allowed; +} + +#endif + +/** + * DOC: The transfer log + * + * The transfer log is a single linked list of &struct drbd_tl_epoch objects. + * mdev->newest_tle points to the head, mdev->oldest_tle points to the tail + * of the list. There is always at least one &struct drbd_tl_epoch object. + * + * Each &struct drbd_tl_epoch has a circular double linked list of requests + * attached. + */ +static int tl_init(struct drbd_conf *mdev) +{ + struct drbd_tl_epoch *b; + + /* during device minor initialization, we may well use GFP_KERNEL */ + b = kmalloc(sizeof(struct drbd_tl_epoch), GFP_KERNEL); + if (!b) + return 0; + INIT_LIST_HEAD(&b->requests); + INIT_LIST_HEAD(&b->w.list); + b->next = NULL; + b->br_number = 4711; + b->n_req = 0; + b->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */ + + mdev->oldest_tle = b; + mdev->newest_tle = b; + INIT_LIST_HEAD(&mdev->out_of_sequence_requests); + + mdev->tl_hash = NULL; + mdev->tl_hash_s = 0; + + return 1; +} + +static void tl_cleanup(struct drbd_conf *mdev) +{ + D_ASSERT(mdev->oldest_tle == mdev->newest_tle); + D_ASSERT(list_empty(&mdev->out_of_sequence_requests)); + kfree(mdev->oldest_tle); + mdev->oldest_tle = NULL; + kfree(mdev->unused_spare_tle); + mdev->unused_spare_tle = NULL; + kfree(mdev->tl_hash); + mdev->tl_hash = NULL; + mdev->tl_hash_s = 0; +} + +/** + * _tl_add_barrier() - Adds a barrier to the transfer log + * @mdev: DRBD device. + * @new: Barrier to be added before the current head of the TL. + * + * The caller must hold the req_lock. + */ +void _tl_add_barrier(struct drbd_conf *mdev, struct drbd_tl_epoch *new) +{ + struct drbd_tl_epoch *newest_before; + + INIT_LIST_HEAD(&new->requests); + INIT_LIST_HEAD(&new->w.list); + new->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */ + new->next = NULL; + new->n_req = 0; + + newest_before = mdev->newest_tle; + /* never send a barrier number == 0, because that is special-cased + * when using TCQ for our write ordering code */ + new->br_number = (newest_before->br_number+1) ?: 1; + if (mdev->newest_tle != new) { + mdev->newest_tle->next = new; + mdev->newest_tle = new; + } +} + +/** + * tl_release() - Free or recycle the oldest &struct drbd_tl_epoch object of the TL + * @mdev: DRBD device. + * @barrier_nr: Expected identifier of the DRBD write barrier packet. + * @set_size: Expected number of requests before that barrier. + * + * In case the passed barrier_nr or set_size does not match the oldest + * &struct drbd_tl_epoch objects this function will cause a termination + * of the connection. + */ +void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr, + unsigned int set_size) +{ + struct drbd_tl_epoch *b, *nob; /* next old barrier */ + struct list_head *le, *tle; + struct drbd_request *r; + + spin_lock_irq(&mdev->req_lock); + + b = mdev->oldest_tle; + + /* first some paranoia code */ + if (b == NULL) { + dev_err(DEV, "BAD! BarrierAck #%u received, but no epoch in tl!?\n", + barrier_nr); + goto bail; + } + if (b->br_number != barrier_nr) { + dev_err(DEV, "BAD! BarrierAck #%u received, expected #%u!\n", + barrier_nr, b->br_number); + goto bail; + } + if (b->n_req != set_size) { + dev_err(DEV, "BAD! BarrierAck #%u received with n_req=%u, expected n_req=%u!\n", + barrier_nr, set_size, b->n_req); + goto bail; + } + + /* Clean up list of requests processed during current epoch */ + list_for_each_safe(le, tle, &b->requests) { + r = list_entry(le, struct drbd_request, tl_requests); + _req_mod(r, barrier_acked); + } + /* There could be requests on the list waiting for completion + of the write to the local disk. To avoid corruptions of + slab's data structures we have to remove the lists head. + + Also there could have been a barrier ack out of sequence, overtaking + the write acks - which would be a bug and violating write ordering. + To not deadlock in case we lose connection while such requests are + still pending, we need some way to find them for the + _req_mode(connection_lost_while_pending). + + These have been list_move'd to the out_of_sequence_requests list in + _req_mod(, barrier_acked) above. + */ + list_del_init(&b->requests); + + nob = b->next; + if (test_and_clear_bit(CREATE_BARRIER, &mdev->flags)) { + _tl_add_barrier(mdev, b); + if (nob) + mdev->oldest_tle = nob; + /* if nob == NULL b was the only barrier, and becomes the new + barrier. Therefore mdev->oldest_tle points already to b */ + } else { + D_ASSERT(nob != NULL); + mdev->oldest_tle = nob; + kfree(b); + } + + spin_unlock_irq(&mdev->req_lock); + dec_ap_pending(mdev); + + return; + +bail: + spin_unlock_irq(&mdev->req_lock); + drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR)); +} + + +/** + * tl_clear() - Clears all requests and &struct drbd_tl_epoch objects out of the TL + * @mdev: DRBD device. + * + * This is called after the connection to the peer was lost. The storage covered + * by the requests on the transfer gets marked as our of sync. Called from the + * receiver thread and the worker thread. + */ +void tl_clear(struct drbd_conf *mdev) +{ + struct drbd_tl_epoch *b, *tmp; + struct list_head *le, *tle; + struct drbd_request *r; + int new_initial_bnr = net_random(); + + spin_lock_irq(&mdev->req_lock); + + b = mdev->oldest_tle; + while (b) { + list_for_each_safe(le, tle, &b->requests) { + r = list_entry(le, struct drbd_request, tl_requests); + /* It would be nice to complete outside of spinlock. + * But this is easier for now. */ + _req_mod(r, connection_lost_while_pending); + } + tmp = b->next; + + /* there could still be requests on that ring list, + * in case local io is still pending */ + list_del(&b->requests); + + /* dec_ap_pending corresponding to queue_barrier. + * the newest barrier may not have been queued yet, + * in which case w.cb is still NULL. */ + if (b->w.cb != NULL) + dec_ap_pending(mdev); + + if (b == mdev->newest_tle) { + /* recycle, but reinit! */ + D_ASSERT(tmp == NULL); + INIT_LIST_HEAD(&b->requests); + INIT_LIST_HEAD(&b->w.list); + b->w.cb = NULL; + b->br_number = new_initial_bnr; + b->n_req = 0; + + mdev->oldest_tle = b; + break; + } + kfree(b); + b = tmp; + } + + /* we expect this list to be empty. */ + D_ASSERT(list_empty(&mdev->out_of_sequence_requests)); + + /* but just in case, clean it up anyways! */ + list_for_each_safe(le, tle, &mdev->out_of_sequence_requests) { + r = list_entry(le, struct drbd_request, tl_requests); + /* It would be nice to complete outside of spinlock. + * But this is easier for now. */ + _req_mod(r, connection_lost_while_pending); + } + + /* ensure bit indicating barrier is required is clear */ + clear_bit(CREATE_BARRIER, &mdev->flags); + + spin_unlock_irq(&mdev->req_lock); +} + +/** + * cl_wide_st_chg() - TRUE if the state change is a cluster wide one + * @mdev: DRBD device. + * @os: old (current) state. + * @ns: new (wanted) state. + */ +static int cl_wide_st_chg(struct drbd_conf *mdev, + union drbd_state os, union drbd_state ns) +{ + return (os.conn >= C_CONNECTED && ns.conn >= C_CONNECTED && + ((os.role != R_PRIMARY && ns.role == R_PRIMARY) || + (os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) || + (os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S) || + (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))) || + (os.conn >= C_CONNECTED && ns.conn == C_DISCONNECTING) || + (os.conn == C_CONNECTED && ns.conn == C_VERIFY_S); +} + +int drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f, + union drbd_state mask, union drbd_state val) +{ + unsigned long flags; + union drbd_state os, ns; + int rv; + + spin_lock_irqsave(&mdev->req_lock, flags); + os = mdev->state; + ns.i = (os.i & ~mask.i) | val.i; + rv = _drbd_set_state(mdev, ns, f, NULL); + ns = mdev->state; + spin_unlock_irqrestore(&mdev->req_lock, flags); + + return rv; +} + +/** + * drbd_force_state() - Impose a change which happens outside our control on our state + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + */ +void drbd_force_state(struct drbd_conf *mdev, + union drbd_state mask, union drbd_state val) +{ + drbd_change_state(mdev, CS_HARD, mask, val); +} + +static int is_valid_state(struct drbd_conf *mdev, union drbd_state ns); +static int is_valid_state_transition(struct drbd_conf *, + union drbd_state, union drbd_state); +static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, int *warn_sync_abort); +int drbd_send_state_req(struct drbd_conf *, + union drbd_state, union drbd_state); + +static enum drbd_state_ret_codes _req_st_cond(struct drbd_conf *mdev, + union drbd_state mask, union drbd_state val) +{ + union drbd_state os, ns; + unsigned long flags; + int rv; + + if (test_and_clear_bit(CL_ST_CHG_SUCCESS, &mdev->flags)) + return SS_CW_SUCCESS; + + if (test_and_clear_bit(CL_ST_CHG_FAIL, &mdev->flags)) + return SS_CW_FAILED_BY_PEER; + + rv = 0; + spin_lock_irqsave(&mdev->req_lock, flags); + os = mdev->state; + ns.i = (os.i & ~mask.i) | val.i; + ns = sanitize_state(mdev, os, ns, NULL); + + if (!cl_wide_st_chg(mdev, os, ns)) + rv = SS_CW_NO_NEED; + if (!rv) { + rv = is_valid_state(mdev, ns); + if (rv == SS_SUCCESS) { + rv = is_valid_state_transition(mdev, ns, os); + if (rv == SS_SUCCESS) + rv = 0; /* cont waiting, otherwise fail. */ + } + } + spin_unlock_irqrestore(&mdev->req_lock, flags); + + return rv; +} + +/** + * drbd_req_state() - Perform an eventually cluster wide state change + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + * @f: flags + * + * Should not be called directly, use drbd_request_state() or + * _drbd_request_state(). + */ +static int drbd_req_state(struct drbd_conf *mdev, + union drbd_state mask, union drbd_state val, + enum chg_state_flags f) +{ + struct completion done; + unsigned long flags; + union drbd_state os, ns; + int rv; + + init_completion(&done); + + if (f & CS_SERIALIZE) + mutex_lock(&mdev->state_mutex); + + spin_lock_irqsave(&mdev->req_lock, flags); + os = mdev->state; + ns.i = (os.i & ~mask.i) | val.i; + ns = sanitize_state(mdev, os, ns, NULL); + + if (cl_wide_st_chg(mdev, os, ns)) { + rv = is_valid_state(mdev, ns); + if (rv == SS_SUCCESS) + rv = is_valid_state_transition(mdev, ns, os); + spin_unlock_irqrestore(&mdev->req_lock, flags); + + if (rv < SS_SUCCESS) { + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + + drbd_state_lock(mdev); + if (!drbd_send_state_req(mdev, mask, val)) { + drbd_state_unlock(mdev); + rv = SS_CW_FAILED_BY_PEER; + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + + wait_event(mdev->state_wait, + (rv = _req_st_cond(mdev, mask, val))); + + if (rv < SS_SUCCESS) { + drbd_state_unlock(mdev); + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + spin_lock_irqsave(&mdev->req_lock, flags); + os = mdev->state; + ns.i = (os.i & ~mask.i) | val.i; + rv = _drbd_set_state(mdev, ns, f, &done); + drbd_state_unlock(mdev); + } else { + rv = _drbd_set_state(mdev, ns, f, &done); + } + + spin_unlock_irqrestore(&mdev->req_lock, flags); + + if (f & CS_WAIT_COMPLETE && rv == SS_SUCCESS) { + D_ASSERT(current != mdev->worker.task); + wait_for_completion(&done); + } + +abort: + if (f & CS_SERIALIZE) + mutex_unlock(&mdev->state_mutex); + + return rv; +} + +/** + * _drbd_request_state() - Request a state change (with flags) + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + * @f: flags + * + * Cousin of drbd_request_state(), useful with the CS_WAIT_COMPLETE + * flag, or when logging of failed state change requests is not desired. + */ +int _drbd_request_state(struct drbd_conf *mdev, union drbd_state mask, + union drbd_state val, enum chg_state_flags f) +{ + int rv; + + wait_event(mdev->state_wait, + (rv = drbd_req_state(mdev, mask, val, f)) != SS_IN_TRANSIENT_STATE); + + return rv; +} + +static void print_st(struct drbd_conf *mdev, char *name, union drbd_state ns) +{ + dev_err(DEV, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c }\n", + name, + drbd_conn_str(ns.conn), + drbd_role_str(ns.role), + drbd_role_str(ns.peer), + drbd_disk_str(ns.disk), + drbd_disk_str(ns.pdsk), + ns.susp ? 's' : 'r', + ns.aftr_isp ? 'a' : '-', + ns.peer_isp ? 'p' : '-', + ns.user_isp ? 'u' : '-' + ); +} + +void print_st_err(struct drbd_conf *mdev, + union drbd_state os, union drbd_state ns, int err) +{ + if (err == SS_IN_TRANSIENT_STATE) + return; + dev_err(DEV, "State change failed: %s\n", drbd_set_st_err_str(err)); + print_st(mdev, " state", os); + print_st(mdev, "wanted", ns); +} + + +#define drbd_peer_str drbd_role_str +#define drbd_pdsk_str drbd_disk_str + +#define drbd_susp_str(A) ((A) ? "1" : "0") +#define drbd_aftr_isp_str(A) ((A) ? "1" : "0") +#define drbd_peer_isp_str(A) ((A) ? "1" : "0") +#define drbd_user_isp_str(A) ((A) ? "1" : "0") + +#define PSC(A) \ + ({ if (ns.A != os.A) { \ + pbp += sprintf(pbp, #A "( %s -> %s ) ", \ + drbd_##A##_str(os.A), \ + drbd_##A##_str(ns.A)); \ + } }) + +/** + * is_valid_state() - Returns an SS_ error code if ns is not valid + * @mdev: DRBD device. + * @ns: State to consider. + */ +static int is_valid_state(struct drbd_conf *mdev, union drbd_state ns) +{ + /* See drbd_state_sw_errors in drbd_strings.c */ + + enum drbd_fencing_p fp; + int rv = SS_SUCCESS; + + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + fp = mdev->ldev->dc.fencing; + put_ldev(mdev); + } + + if (get_net_conf(mdev)) { + if (!mdev->net_conf->two_primaries && + ns.role == R_PRIMARY && ns.peer == R_PRIMARY) + rv = SS_TWO_PRIMARIES; + put_net_conf(mdev); + } + + if (rv <= 0) + /* already found a reason to abort */; + else if (ns.role == R_SECONDARY && mdev->open_cnt) + rv = SS_DEVICE_IN_USE; + + else if (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.disk < D_UP_TO_DATE) + rv = SS_NO_UP_TO_DATE_DISK; + + else if (fp >= FP_RESOURCE && + ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk >= D_UNKNOWN) + rv = SS_PRIMARY_NOP; + + else if (ns.role == R_PRIMARY && ns.disk <= D_INCONSISTENT && ns.pdsk <= D_INCONSISTENT) + rv = SS_NO_UP_TO_DATE_DISK; + + else if (ns.conn > C_CONNECTED && ns.disk < D_INCONSISTENT) + rv = SS_NO_LOCAL_DISK; + + else if (ns.conn > C_CONNECTED && ns.pdsk < D_INCONSISTENT) + rv = SS_NO_REMOTE_DISK; + + else if ((ns.conn == C_CONNECTED || + ns.conn == C_WF_BITMAP_S || + ns.conn == C_SYNC_SOURCE || + ns.conn == C_PAUSED_SYNC_S) && + ns.disk == D_OUTDATED) + rv = SS_CONNECTED_OUTDATES; + + else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + (mdev->sync_conf.verify_alg[0] == 0)) + rv = SS_NO_VERIFY_ALG; + + else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + mdev->agreed_pro_version < 88) + rv = SS_NOT_SUPPORTED; + + return rv; +} + +/** + * is_valid_state_transition() - Returns an SS_ error code if the state transition is not possible + * @mdev: DRBD device. + * @ns: new state. + * @os: old state. + */ +static int is_valid_state_transition(struct drbd_conf *mdev, + union drbd_state ns, union drbd_state os) +{ + int rv = SS_SUCCESS; + + if ((ns.conn == C_STARTING_SYNC_T || ns.conn == C_STARTING_SYNC_S) && + os.conn > C_CONNECTED) + rv = SS_RESYNC_RUNNING; + + if (ns.conn == C_DISCONNECTING && os.conn == C_STANDALONE) + rv = SS_ALREADY_STANDALONE; + + if (ns.disk > D_ATTACHING && os.disk == D_DISKLESS) + rv = SS_IS_DISKLESS; + + if (ns.conn == C_WF_CONNECTION && os.conn < C_UNCONNECTED) + rv = SS_NO_NET_CONFIG; + + if (ns.disk == D_OUTDATED && os.disk < D_OUTDATED && os.disk != D_ATTACHING) + rv = SS_LOWER_THAN_OUTDATED; + + if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED) + rv = SS_IN_TRANSIENT_STATE; + + if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS) + rv = SS_IN_TRANSIENT_STATE; + + if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED) + rv = SS_NEED_CONNECTION; + + if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + ns.conn != os.conn && os.conn > C_CONNECTED) + rv = SS_RESYNC_RUNNING; + + if ((ns.conn == C_STARTING_SYNC_S || ns.conn == C_STARTING_SYNC_T) && + os.conn < C_CONNECTED) + rv = SS_NEED_CONNECTION; + + return rv; +} + +/** + * sanitize_state() - Resolves implicitly necessary additional changes to a state transition + * @mdev: DRBD device. + * @os: old state. + * @ns: new state. + * @warn_sync_abort: + * + * When we loose connection, we have to set the state of the peers disk (pdsk) + * to D_UNKNOWN. This rule and many more along those lines are in this function. + */ +static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, int *warn_sync_abort) +{ + enum drbd_fencing_p fp; + + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + fp = mdev->ldev->dc.fencing; + put_ldev(mdev); + } + + /* Disallow Network errors to configure a device's network part */ + if ((ns.conn >= C_TIMEOUT && ns.conn <= C_TEAR_DOWN) && + os.conn <= C_DISCONNECTING) + ns.conn = os.conn; + + /* After a network error (+C_TEAR_DOWN) only C_UNCONNECTED or C_DISCONNECTING can follow */ + if (os.conn >= C_TIMEOUT && os.conn <= C_TEAR_DOWN && + ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING) + ns.conn = os.conn; + + /* After C_DISCONNECTING only C_STANDALONE may follow */ + if (os.conn == C_DISCONNECTING && ns.conn != C_STANDALONE) + ns.conn = os.conn; + + if (ns.conn < C_CONNECTED) { + ns.peer_isp = 0; + ns.peer = R_UNKNOWN; + if (ns.pdsk > D_UNKNOWN || ns.pdsk < D_INCONSISTENT) + ns.pdsk = D_UNKNOWN; + } + + /* Clear the aftr_isp when becoming unconfigured */ + if (ns.conn == C_STANDALONE && ns.disk == D_DISKLESS && ns.role == R_SECONDARY) + ns.aftr_isp = 0; + + if (ns.conn <= C_DISCONNECTING && ns.disk == D_DISKLESS) + ns.pdsk = D_UNKNOWN; + + /* Abort resync if a disk fails/detaches */ + if (os.conn > C_CONNECTED && ns.conn > C_CONNECTED && + (ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) { + if (warn_sync_abort) + *warn_sync_abort = 1; + ns.conn = C_CONNECTED; + } + + if (ns.conn >= C_CONNECTED && + ((ns.disk == D_CONSISTENT || ns.disk == D_OUTDATED) || + (ns.disk == D_NEGOTIATING && ns.conn == C_WF_BITMAP_T))) { + switch (ns.conn) { + case C_WF_BITMAP_T: + case C_PAUSED_SYNC_T: + ns.disk = D_OUTDATED; + break; + case C_CONNECTED: + case C_WF_BITMAP_S: + case C_SYNC_SOURCE: + case C_PAUSED_SYNC_S: + ns.disk = D_UP_TO_DATE; + break; + case C_SYNC_TARGET: + ns.disk = D_INCONSISTENT; + dev_warn(DEV, "Implicitly set disk state Inconsistent!\n"); + break; + } + if (os.disk == D_OUTDATED && ns.disk == D_UP_TO_DATE) + dev_warn(DEV, "Implicitly set disk from Outdated to UpToDate\n"); + } + + if (ns.conn >= C_CONNECTED && + (ns.pdsk == D_CONSISTENT || ns.pdsk == D_OUTDATED)) { + switch (ns.conn) { + case C_CONNECTED: + case C_WF_BITMAP_T: + case C_PAUSED_SYNC_T: + case C_SYNC_TARGET: + ns.pdsk = D_UP_TO_DATE; + break; + case C_WF_BITMAP_S: + case C_PAUSED_SYNC_S: + ns.pdsk = D_OUTDATED; + break; + case C_SYNC_SOURCE: + ns.pdsk = D_INCONSISTENT; + dev_warn(DEV, "Implicitly set pdsk Inconsistent!\n"); + break; + } + if (os.pdsk == D_OUTDATED && ns.pdsk == D_UP_TO_DATE) + dev_warn(DEV, "Implicitly set pdsk from Outdated to UpToDate\n"); + } + + /* Connection breaks down before we finished "Negotiating" */ + if (ns.conn < C_CONNECTED && ns.disk == D_NEGOTIATING && + get_ldev_if_state(mdev, D_NEGOTIATING)) { + if (mdev->ed_uuid == mdev->ldev->md.uuid[UI_CURRENT]) { + ns.disk = mdev->new_state_tmp.disk; + ns.pdsk = mdev->new_state_tmp.pdsk; + } else { + dev_alert(DEV, "Connection lost while negotiating, no data!\n"); + ns.disk = D_DISKLESS; + ns.pdsk = D_UNKNOWN; + } + put_ldev(mdev); + } + + if (fp == FP_STONITH && + (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED) && + !(os.role == R_PRIMARY && os.conn < C_CONNECTED && os.pdsk > D_OUTDATED)) + ns.susp = 1; + + if (ns.aftr_isp || ns.peer_isp || ns.user_isp) { + if (ns.conn == C_SYNC_SOURCE) + ns.conn = C_PAUSED_SYNC_S; + if (ns.conn == C_SYNC_TARGET) + ns.conn = C_PAUSED_SYNC_T; + } else { + if (ns.conn == C_PAUSED_SYNC_S) + ns.conn = C_SYNC_SOURCE; + if (ns.conn == C_PAUSED_SYNC_T) + ns.conn = C_SYNC_TARGET; + } + + return ns; +} + +/* helper for __drbd_set_state */ +static void set_ov_position(struct drbd_conf *mdev, enum drbd_conns cs) +{ + if (cs == C_VERIFY_T) { + /* starting online verify from an arbitrary position + * does not fit well into the existing protocol. + * on C_VERIFY_T, we initialize ov_left and friends + * implicitly in receive_DataRequest once the + * first P_OV_REQUEST is received */ + mdev->ov_start_sector = ~(sector_t)0; + } else { + unsigned long bit = BM_SECT_TO_BIT(mdev->ov_start_sector); + if (bit >= mdev->rs_total) + mdev->ov_start_sector = + BM_BIT_TO_SECT(mdev->rs_total - 1); + mdev->ov_position = mdev->ov_start_sector; + } +} + +/** + * __drbd_set_state() - Set a new DRBD state + * @mdev: DRBD device. + * @ns: new state. + * @flags: Flags + * @done: Optional completion, that will get completed after the after_state_ch() finished + * + * Caller needs to hold req_lock, and global_state_lock. Do not call directly. + */ +int __drbd_set_state(struct drbd_conf *mdev, + union drbd_state ns, enum chg_state_flags flags, + struct completion *done) +{ + union drbd_state os; + int rv = SS_SUCCESS; + int warn_sync_abort = 0; + struct after_state_chg_work *ascw; + + os = mdev->state; + + ns = sanitize_state(mdev, os, ns, &warn_sync_abort); + + if (ns.i == os.i) + return SS_NOTHING_TO_DO; + + if (!(flags & CS_HARD)) { + /* pre-state-change checks ; only look at ns */ + /* See drbd_state_sw_errors in drbd_strings.c */ + + rv = is_valid_state(mdev, ns); + if (rv < SS_SUCCESS) { + /* If the old state was illegal as well, then let + this happen...*/ + + if (is_valid_state(mdev, os) == rv) { + dev_err(DEV, "Considering state change from bad state. " + "Error would be: '%s'\n", + drbd_set_st_err_str(rv)); + print_st(mdev, "old", os); + print_st(mdev, "new", ns); + rv = is_valid_state_transition(mdev, ns, os); + } + } else + rv = is_valid_state_transition(mdev, ns, os); + } + + if (rv < SS_SUCCESS) { + if (flags & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + return rv; + } + + if (warn_sync_abort) + dev_warn(DEV, "Resync aborted.\n"); + + { + char *pbp, pb[300]; + pbp = pb; + *pbp = 0; + PSC(role); + PSC(peer); + PSC(conn); + PSC(disk); + PSC(pdsk); + PSC(susp); + PSC(aftr_isp); + PSC(peer_isp); + PSC(user_isp); + dev_info(DEV, "%s\n", pb); + } + + /* solve the race between becoming unconfigured, + * worker doing the cleanup, and + * admin reconfiguring us: + * on (re)configure, first set CONFIG_PENDING, + * then wait for a potentially exiting worker, + * start the worker, and schedule one no_op. + * then proceed with configuration. + */ + if (ns.disk == D_DISKLESS && + ns.conn == C_STANDALONE && + ns.role == R_SECONDARY && + !test_and_set_bit(CONFIG_PENDING, &mdev->flags)) + set_bit(DEVICE_DYING, &mdev->flags); + + mdev->state.i = ns.i; + wake_up(&mdev->misc_wait); + wake_up(&mdev->state_wait); + + /* post-state-change actions */ + if (os.conn >= C_SYNC_SOURCE && ns.conn <= C_CONNECTED) { + set_bit(STOP_SYNC_TIMER, &mdev->flags); + mod_timer(&mdev->resync_timer, jiffies); + } + + /* aborted verify run. log the last position */ + if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) && + ns.conn < C_CONNECTED) { + mdev->ov_start_sector = + BM_BIT_TO_SECT(mdev->rs_total - mdev->ov_left); + dev_info(DEV, "Online Verify reached sector %llu\n", + (unsigned long long)mdev->ov_start_sector); + } + + if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) && + (ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE)) { + dev_info(DEV, "Syncer continues.\n"); + mdev->rs_paused += (long)jiffies-(long)mdev->rs_mark_time; + if (ns.conn == C_SYNC_TARGET) { + if (!test_and_clear_bit(STOP_SYNC_TIMER, &mdev->flags)) + mod_timer(&mdev->resync_timer, jiffies); + /* This if (!test_bit) is only needed for the case + that a device that has ceased to used its timer, + i.e. it is already in drbd_resync_finished() gets + paused and resumed. */ + } + } + + if ((os.conn == C_SYNC_TARGET || os.conn == C_SYNC_SOURCE) && + (ns.conn == C_PAUSED_SYNC_T || ns.conn == C_PAUSED_SYNC_S)) { + dev_info(DEV, "Resync suspended\n"); + mdev->rs_mark_time = jiffies; + if (ns.conn == C_PAUSED_SYNC_T) + set_bit(STOP_SYNC_TIMER, &mdev->flags); + } + + if (os.conn == C_CONNECTED && + (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T)) { + mdev->ov_position = 0; + mdev->rs_total = + mdev->rs_mark_left = drbd_bm_bits(mdev); + if (mdev->agreed_pro_version >= 90) + set_ov_position(mdev, ns.conn); + else + mdev->ov_start_sector = 0; + mdev->ov_left = mdev->rs_total + - BM_SECT_TO_BIT(mdev->ov_position); + mdev->rs_start = + mdev->rs_mark_time = jiffies; + mdev->ov_last_oos_size = 0; + mdev->ov_last_oos_start = 0; + + if (ns.conn == C_VERIFY_S) { + dev_info(DEV, "Starting Online Verify from sector %llu\n", + (unsigned long long)mdev->ov_position); + mod_timer(&mdev->resync_timer, jiffies); + } + } + + if (get_ldev(mdev)) { + u32 mdf = mdev->ldev->md.flags & ~(MDF_CONSISTENT|MDF_PRIMARY_IND| + MDF_CONNECTED_IND|MDF_WAS_UP_TO_DATE| + MDF_PEER_OUT_DATED|MDF_CRASHED_PRIMARY); + + if (test_bit(CRASHED_PRIMARY, &mdev->flags)) + mdf |= MDF_CRASHED_PRIMARY; + if (mdev->state.role == R_PRIMARY || + (mdev->state.pdsk < D_INCONSISTENT && mdev->state.peer == R_PRIMARY)) + mdf |= MDF_PRIMARY_IND; + if (mdev->state.conn > C_WF_REPORT_PARAMS) + mdf |= MDF_CONNECTED_IND; + if (mdev->state.disk > D_INCONSISTENT) + mdf |= MDF_CONSISTENT; + if (mdev->state.disk > D_OUTDATED) + mdf |= MDF_WAS_UP_TO_DATE; + if (mdev->state.pdsk <= D_OUTDATED && mdev->state.pdsk >= D_INCONSISTENT) + mdf |= MDF_PEER_OUT_DATED; + if (mdf != mdev->ldev->md.flags) { + mdev->ldev->md.flags = mdf; + drbd_md_mark_dirty(mdev); + } + if (os.disk < D_CONSISTENT && ns.disk >= D_CONSISTENT) + drbd_set_ed_uuid(mdev, mdev->ldev->md.uuid[UI_CURRENT]); + put_ldev(mdev); + } + + /* Peer was forced D_UP_TO_DATE & R_PRIMARY, consider to resync */ + if (os.disk == D_INCONSISTENT && os.pdsk == D_INCONSISTENT && + os.peer == R_SECONDARY && ns.peer == R_PRIMARY) + set_bit(CONSIDER_RESYNC, &mdev->flags); + + /* Receiver should clean up itself */ + if (os.conn != C_DISCONNECTING && ns.conn == C_DISCONNECTING) + drbd_thread_stop_nowait(&mdev->receiver); + + /* Now the receiver finished cleaning up itself, it should die */ + if (os.conn != C_STANDALONE && ns.conn == C_STANDALONE) + drbd_thread_stop_nowait(&mdev->receiver); + + /* Upon network failure, we need to restart the receiver. */ + if (os.conn > C_TEAR_DOWN && + ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT) + drbd_thread_restart_nowait(&mdev->receiver); + + ascw = kmalloc(sizeof(*ascw), GFP_ATOMIC); + if (ascw) { + ascw->os = os; + ascw->ns = ns; + ascw->flags = flags; + ascw->w.cb = w_after_state_ch; + ascw->done = done; + drbd_queue_work(&mdev->data.work, &ascw->w); + } else { + dev_warn(DEV, "Could not kmalloc an ascw\n"); + } + + return rv; +} + +static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct after_state_chg_work *ascw = + container_of(w, struct after_state_chg_work, w); + after_state_ch(mdev, ascw->os, ascw->ns, ascw->flags); + if (ascw->flags & CS_WAIT_COMPLETE) { + D_ASSERT(ascw->done != NULL); + complete(ascw->done); + } + kfree(ascw); + + return 1; +} + +static void abw_start_sync(struct drbd_conf *mdev, int rv) +{ + if (rv) { + dev_err(DEV, "Writing the bitmap failed not starting resync.\n"); + _drbd_request_state(mdev, NS(conn, C_CONNECTED), CS_VERBOSE); + return; + } + + switch (mdev->state.conn) { + case C_STARTING_SYNC_T: + _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE); + break; + case C_STARTING_SYNC_S: + drbd_start_resync(mdev, C_SYNC_SOURCE); + break; + } +} + +/** + * after_state_ch() - Perform after state change actions that may sleep + * @mdev: DRBD device. + * @os: old state. + * @ns: new state. + * @flags: Flags + */ +static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, enum chg_state_flags flags) +{ + enum drbd_fencing_p fp; + + if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) { + clear_bit(CRASHED_PRIMARY, &mdev->flags); + if (mdev->p_uuid) + mdev->p_uuid[UI_FLAGS] &= ~((u64)2); + } + + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + fp = mdev->ldev->dc.fencing; + put_ldev(mdev); + } + + /* Inform userspace about the change... */ + drbd_bcast_state(mdev, ns); + + if (!(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE) && + (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE)) + drbd_khelper(mdev, "pri-on-incon-degr"); + + /* Here we have the actions that are performed after a + state change. This function might sleep */ + + if (fp == FP_STONITH && ns.susp) { + /* case1: The outdate peer handler is successful: + * case2: The connection was established again: */ + if ((os.pdsk > D_OUTDATED && ns.pdsk <= D_OUTDATED) || + (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)) { + tl_clear(mdev); + spin_lock_irq(&mdev->req_lock); + _drbd_set_state(_NS(mdev, susp, 0), CS_VERBOSE, NULL); + spin_unlock_irq(&mdev->req_lock); + } + } + /* Do not change the order of the if above and the two below... */ + if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) { /* attach on the peer */ + drbd_send_uuids(mdev); + drbd_send_state(mdev); + } + if (os.conn != C_WF_BITMAP_S && ns.conn == C_WF_BITMAP_S) + drbd_queue_bitmap_io(mdev, &drbd_send_bitmap, NULL, "send_bitmap (WFBitMapS)"); + + /* Lost contact to peer's copy of the data */ + if ((os.pdsk >= D_INCONSISTENT && + os.pdsk != D_UNKNOWN && + os.pdsk != D_OUTDATED) + && (ns.pdsk < D_INCONSISTENT || + ns.pdsk == D_UNKNOWN || + ns.pdsk == D_OUTDATED)) { + kfree(mdev->p_uuid); + mdev->p_uuid = NULL; + if (get_ldev(mdev)) { + if ((ns.role == R_PRIMARY || ns.peer == R_PRIMARY) && + mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) { + drbd_uuid_new_current(mdev); + drbd_send_uuids(mdev); + } + put_ldev(mdev); + } + } + + if (ns.pdsk < D_INCONSISTENT && get_ldev(mdev)) { + if (ns.peer == R_PRIMARY && mdev->ldev->md.uuid[UI_BITMAP] == 0) + drbd_uuid_new_current(mdev); + + /* D_DISKLESS Peer becomes secondary */ + if (os.peer == R_PRIMARY && ns.peer == R_SECONDARY) + drbd_al_to_on_disk_bm(mdev); + put_ldev(mdev); + } + + /* Last part of the attaching process ... */ + if (ns.conn >= C_CONNECTED && + os.disk == D_ATTACHING && ns.disk == D_NEGOTIATING) { + kfree(mdev->p_uuid); /* We expect to receive up-to-date UUIDs soon. */ + mdev->p_uuid = NULL; /* ...to not use the old ones in the mean time */ + drbd_send_sizes(mdev, 0); /* to start sync... */ + drbd_send_uuids(mdev); + drbd_send_state(mdev); + } + + /* We want to pause/continue resync, tell peer. */ + if (ns.conn >= C_CONNECTED && + ((os.aftr_isp != ns.aftr_isp) || + (os.user_isp != ns.user_isp))) + drbd_send_state(mdev); + + /* In case one of the isp bits got set, suspend other devices. */ + if ((!os.aftr_isp && !os.peer_isp && !os.user_isp) && + (ns.aftr_isp || ns.peer_isp || ns.user_isp)) + suspend_other_sg(mdev); + + /* Make sure the peer gets informed about eventual state + changes (ISP bits) while we were in WFReportParams. */ + if (os.conn == C_WF_REPORT_PARAMS && ns.conn >= C_CONNECTED) + drbd_send_state(mdev); + + /* We are in the progress to start a full sync... */ + if ((os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) || + (os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S)) + drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, &abw_start_sync, "set_n_write from StartingSync"); + + /* We are invalidating our self... */ + if (os.conn < C_CONNECTED && ns.conn < C_CONNECTED && + os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT) + drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL, "set_n_write from invalidate"); + + if (os.disk > D_FAILED && ns.disk == D_FAILED) { + enum drbd_io_error_p eh; + + eh = EP_PASS_ON; + if (get_ldev_if_state(mdev, D_FAILED)) { + eh = mdev->ldev->dc.on_io_error; + put_ldev(mdev); + } + + drbd_rs_cancel_all(mdev); + /* since get_ldev() only works as long as disk>=D_INCONSISTENT, + and it is D_DISKLESS here, local_cnt can only go down, it can + not increase... It will reach zero */ + wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt)); + mdev->rs_total = 0; + mdev->rs_failed = 0; + atomic_set(&mdev->rs_pending_cnt, 0); + + spin_lock_irq(&mdev->req_lock); + _drbd_set_state(_NS(mdev, disk, D_DISKLESS), CS_HARD, NULL); + spin_unlock_irq(&mdev->req_lock); + + if (eh == EP_CALL_HELPER) + drbd_khelper(mdev, "local-io-error"); + } + + if (os.disk > D_DISKLESS && ns.disk == D_DISKLESS) { + + if (os.disk == D_FAILED) /* && ns.disk == D_DISKLESS*/ { + if (drbd_send_state(mdev)) + dev_warn(DEV, "Notified peer that my disk is broken.\n"); + else + dev_err(DEV, "Sending state in drbd_io_error() failed\n"); + } + + lc_destroy(mdev->resync); + mdev->resync = NULL; + lc_destroy(mdev->act_log); + mdev->act_log = NULL; + __no_warn(local, + drbd_free_bc(mdev->ldev); + mdev->ldev = NULL;); + + if (mdev->md_io_tmpp) + __free_page(mdev->md_io_tmpp); + } + + /* Disks got bigger while they were detached */ + if (ns.disk > D_NEGOTIATING && ns.pdsk > D_NEGOTIATING && + test_and_clear_bit(RESYNC_AFTER_NEG, &mdev->flags)) { + if (ns.conn == C_CONNECTED) + resync_after_online_grow(mdev); + } + + /* A resync finished or aborted, wake paused devices... */ + if ((os.conn > C_CONNECTED && ns.conn <= C_CONNECTED) || + (os.peer_isp && !ns.peer_isp) || + (os.user_isp && !ns.user_isp)) + resume_next_sg(mdev); + + /* Upon network connection, we need to start the receiver */ + if (os.conn == C_STANDALONE && ns.conn == C_UNCONNECTED) + drbd_thread_start(&mdev->receiver); + + /* Terminate worker thread if we are unconfigured - it will be + restarted as needed... */ + if (ns.disk == D_DISKLESS && + ns.conn == C_STANDALONE && + ns.role == R_SECONDARY) { + if (os.aftr_isp != ns.aftr_isp) + resume_next_sg(mdev); + /* set in __drbd_set_state, unless CONFIG_PENDING was set */ + if (test_bit(DEVICE_DYING, &mdev->flags)) + drbd_thread_stop_nowait(&mdev->worker); + } + + drbd_md_sync(mdev); +} + + +static int drbd_thread_setup(void *arg) +{ + struct drbd_thread *thi = (struct drbd_thread *) arg; + struct drbd_conf *mdev = thi->mdev; + unsigned long flags; + int retval; + +restart: + retval = thi->function(thi); + + spin_lock_irqsave(&thi->t_lock, flags); + + /* if the receiver has been "Exiting", the last thing it did + * was set the conn state to "StandAlone", + * if now a re-connect request comes in, conn state goes C_UNCONNECTED, + * and receiver thread will be "started". + * drbd_thread_start needs to set "Restarting" in that case. + * t_state check and assignment needs to be within the same spinlock, + * so either thread_start sees Exiting, and can remap to Restarting, + * or thread_start see None, and can proceed as normal. + */ + + if (thi->t_state == Restarting) { + dev_info(DEV, "Restarting %s\n", current->comm); + thi->t_state = Running; + spin_unlock_irqrestore(&thi->t_lock, flags); + goto restart; + } + + thi->task = NULL; + thi->t_state = None; + smp_mb(); + complete(&thi->stop); + spin_unlock_irqrestore(&thi->t_lock, flags); + + dev_info(DEV, "Terminating %s\n", current->comm); + + /* Release mod reference taken when thread was started */ + module_put(THIS_MODULE); + return retval; +} + +static void drbd_thread_init(struct drbd_conf *mdev, struct drbd_thread *thi, + int (*func) (struct drbd_thread *)) +{ + spin_lock_init(&thi->t_lock); + thi->task = NULL; + thi->t_state = None; + thi->function = func; + thi->mdev = mdev; +} + +int drbd_thread_start(struct drbd_thread *thi) +{ + struct drbd_conf *mdev = thi->mdev; + struct task_struct *nt; + unsigned long flags; + + const char *me = + thi == &mdev->receiver ? "receiver" : + thi == &mdev->asender ? "asender" : + thi == &mdev->worker ? "worker" : "NONSENSE"; + + /* is used from state engine doing drbd_thread_stop_nowait, + * while holding the req lock irqsave */ + spin_lock_irqsave(&thi->t_lock, flags); + + switch (thi->t_state) { + case None: + dev_info(DEV, "Starting %s thread (from %s [%d])\n", + me, current->comm, current->pid); + + /* Get ref on module for thread - this is released when thread exits */ + if (!try_module_get(THIS_MODULE)) { + dev_err(DEV, "Failed to get module reference in drbd_thread_start\n"); + spin_unlock_irqrestore(&thi->t_lock, flags); + return FALSE; + } + + init_completion(&thi->stop); + D_ASSERT(thi->task == NULL); + thi->reset_cpu_mask = 1; + thi->t_state = Running; + spin_unlock_irqrestore(&thi->t_lock, flags); + flush_signals(current); /* otherw. may get -ERESTARTNOINTR */ + + nt = kthread_create(drbd_thread_setup, (void *) thi, + "drbd%d_%s", mdev_to_minor(mdev), me); + + if (IS_ERR(nt)) { + dev_err(DEV, "Couldn't start thread\n"); + + module_put(THIS_MODULE); + return FALSE; + } + spin_lock_irqsave(&thi->t_lock, flags); + thi->task = nt; + thi->t_state = Running; + spin_unlock_irqrestore(&thi->t_lock, flags); + wake_up_process(nt); + break; + case Exiting: + thi->t_state = Restarting; + dev_info(DEV, "Restarting %s thread (from %s [%d])\n", + me, current->comm, current->pid); + /* fall through */ + case Running: + case Restarting: + default: + spin_unlock_irqrestore(&thi->t_lock, flags); + break; + } + + return TRUE; +} + + +void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait) +{ + unsigned long flags; + + enum drbd_thread_state ns = restart ? Restarting : Exiting; + + /* may be called from state engine, holding the req lock irqsave */ + spin_lock_irqsave(&thi->t_lock, flags); + + if (thi->t_state == None) { + spin_unlock_irqrestore(&thi->t_lock, flags); + if (restart) + drbd_thread_start(thi); + return; + } + + if (thi->t_state != ns) { + if (thi->task == NULL) { + spin_unlock_irqrestore(&thi->t_lock, flags); + return; + } + + thi->t_state = ns; + smp_mb(); + init_completion(&thi->stop); + if (thi->task != current) + force_sig(DRBD_SIGKILL, thi->task); + + } + + spin_unlock_irqrestore(&thi->t_lock, flags); + + if (wait) + wait_for_completion(&thi->stop); +} + +#ifdef CONFIG_SMP +/** + * drbd_calc_cpu_mask() - Generate CPU masks, spread over all CPUs + * @mdev: DRBD device. + * + * Forces all threads of a device onto the same CPU. This is beneficial for + * DRBD's performance. May be overwritten by user's configuration. + */ +void drbd_calc_cpu_mask(struct drbd_conf *mdev) +{ + int ord, cpu; + + /* user override. */ + if (cpumask_weight(mdev->cpu_mask)) + return; + + ord = mdev_to_minor(mdev) % cpumask_weight(cpu_online_mask); + for_each_online_cpu(cpu) { + if (ord-- == 0) { + cpumask_set_cpu(cpu, mdev->cpu_mask); + return; + } + } + /* should not be reached */ + cpumask_setall(mdev->cpu_mask); +} + +/** + * drbd_thread_current_set_cpu() - modifies the cpu mask of the _current_ thread + * @mdev: DRBD device. + * + * call in the "main loop" of _all_ threads, no need for any mutex, current won't die + * prematurely. + */ +void drbd_thread_current_set_cpu(struct drbd_conf *mdev) +{ + struct task_struct *p = current; + struct drbd_thread *thi = + p == mdev->asender.task ? &mdev->asender : + p == mdev->receiver.task ? &mdev->receiver : + p == mdev->worker.task ? &mdev->worker : + NULL; + ERR_IF(thi == NULL) + return; + if (!thi->reset_cpu_mask) + return; + thi->reset_cpu_mask = 0; + set_cpus_allowed_ptr(p, mdev->cpu_mask); +} +#endif + +/* the appropriate socket mutex must be held already */ +int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock, + enum drbd_packets cmd, struct p_header *h, + size_t size, unsigned msg_flags) +{ + int sent, ok; + + ERR_IF(!h) return FALSE; + ERR_IF(!size) return FALSE; + + h->magic = BE_DRBD_MAGIC; + h->command = cpu_to_be16(cmd); + h->length = cpu_to_be16(size-sizeof(struct p_header)); + + sent = drbd_send(mdev, sock, h, size, msg_flags); + + ok = (sent == size); + if (!ok) + dev_err(DEV, "short sent %s size=%d sent=%d\n", + cmdname(cmd), (int)size, sent); + return ok; +} + +/* don't pass the socket. we may only look at it + * when we hold the appropriate socket mutex. + */ +int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket, + enum drbd_packets cmd, struct p_header *h, size_t size) +{ + int ok = 0; + struct socket *sock; + + if (use_data_socket) { + mutex_lock(&mdev->data.mutex); + sock = mdev->data.socket; + } else { + mutex_lock(&mdev->meta.mutex); + sock = mdev->meta.socket; + } + + /* drbd_disconnect() could have called drbd_free_sock() + * while we were waiting in down()... */ + if (likely(sock != NULL)) + ok = _drbd_send_cmd(mdev, sock, cmd, h, size, 0); + + if (use_data_socket) + mutex_unlock(&mdev->data.mutex); + else + mutex_unlock(&mdev->meta.mutex); + return ok; +} + +int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data, + size_t size) +{ + struct p_header h; + int ok; + + h.magic = BE_DRBD_MAGIC; + h.command = cpu_to_be16(cmd); + h.length = cpu_to_be16(size); + + if (!drbd_get_data_sock(mdev)) + return 0; + + ok = (sizeof(h) == + drbd_send(mdev, mdev->data.socket, &h, sizeof(h), 0)); + ok = ok && (size == + drbd_send(mdev, mdev->data.socket, data, size, 0)); + + drbd_put_data_sock(mdev); + + return ok; +} + +int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc) +{ + struct p_rs_param_89 *p; + struct socket *sock; + int size, rv; + const int apv = mdev->agreed_pro_version; + + size = apv <= 87 ? sizeof(struct p_rs_param) + : apv == 88 ? sizeof(struct p_rs_param) + + strlen(mdev->sync_conf.verify_alg) + 1 + : /* 89 */ sizeof(struct p_rs_param_89); + + /* used from admin command context and receiver/worker context. + * to avoid kmalloc, grab the socket right here, + * then use the pre-allocated sbuf there */ + mutex_lock(&mdev->data.mutex); + sock = mdev->data.socket; + + if (likely(sock != NULL)) { + enum drbd_packets cmd = apv >= 89 ? P_SYNC_PARAM89 : P_SYNC_PARAM; + + p = &mdev->data.sbuf.rs_param_89; + + /* initialize verify_alg and csums_alg */ + memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX); + + p->rate = cpu_to_be32(sc->rate); + + if (apv >= 88) + strcpy(p->verify_alg, mdev->sync_conf.verify_alg); + if (apv >= 89) + strcpy(p->csums_alg, mdev->sync_conf.csums_alg); + + rv = _drbd_send_cmd(mdev, sock, cmd, &p->head, size, 0); + } else + rv = 0; /* not ok */ + + mutex_unlock(&mdev->data.mutex); + + return rv; +} + +int drbd_send_protocol(struct drbd_conf *mdev) +{ + struct p_protocol *p; + int size, rv; + + size = sizeof(struct p_protocol); + + if (mdev->agreed_pro_version >= 87) + size += strlen(mdev->net_conf->integrity_alg) + 1; + + /* we must not recurse into our own queue, + * as that is blocked during handshake */ + p = kmalloc(size, GFP_NOIO); + if (p == NULL) + return 0; + + p->protocol = cpu_to_be32(mdev->net_conf->wire_protocol); + p->after_sb_0p = cpu_to_be32(mdev->net_conf->after_sb_0p); + p->after_sb_1p = cpu_to_be32(mdev->net_conf->after_sb_1p); + p->after_sb_2p = cpu_to_be32(mdev->net_conf->after_sb_2p); + p->want_lose = cpu_to_be32(mdev->net_conf->want_lose); + p->two_primaries = cpu_to_be32(mdev->net_conf->two_primaries); + + if (mdev->agreed_pro_version >= 87) + strcpy(p->integrity_alg, mdev->net_conf->integrity_alg); + + rv = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_PROTOCOL, + (struct p_header *)p, size); + kfree(p); + return rv; +} + +int _drbd_send_uuids(struct drbd_conf *mdev, u64 uuid_flags) +{ + struct p_uuids p; + int i; + + if (!get_ldev_if_state(mdev, D_NEGOTIATING)) + return 1; + + for (i = UI_CURRENT; i < UI_SIZE; i++) + p.uuid[i] = mdev->ldev ? cpu_to_be64(mdev->ldev->md.uuid[i]) : 0; + + mdev->comm_bm_set = drbd_bm_total_weight(mdev); + p.uuid[UI_SIZE] = cpu_to_be64(mdev->comm_bm_set); + uuid_flags |= mdev->net_conf->want_lose ? 1 : 0; + uuid_flags |= test_bit(CRASHED_PRIMARY, &mdev->flags) ? 2 : 0; + uuid_flags |= mdev->new_state_tmp.disk == D_INCONSISTENT ? 4 : 0; + p.uuid[UI_FLAGS] = cpu_to_be64(uuid_flags); + + put_ldev(mdev); + + return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_UUIDS, + (struct p_header *)&p, sizeof(p)); +} + +int drbd_send_uuids(struct drbd_conf *mdev) +{ + return _drbd_send_uuids(mdev, 0); +} + +int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev) +{ + return _drbd_send_uuids(mdev, 8); +} + + +int drbd_send_sync_uuid(struct drbd_conf *mdev, u64 val) +{ + struct p_rs_uuid p; + + p.uuid = cpu_to_be64(val); + + return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SYNC_UUID, + (struct p_header *)&p, sizeof(p)); +} + +int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply) +{ + struct p_sizes p; + sector_t d_size, u_size; + int q_order_type; + int ok; + + if (get_ldev_if_state(mdev, D_NEGOTIATING)) { + D_ASSERT(mdev->ldev->backing_bdev); + d_size = drbd_get_max_capacity(mdev->ldev); + u_size = mdev->ldev->dc.disk_size; + q_order_type = drbd_queue_order_type(mdev); + p.queue_order_type = cpu_to_be32(drbd_queue_order_type(mdev)); + put_ldev(mdev); + } else { + d_size = 0; + u_size = 0; + q_order_type = QUEUE_ORDERED_NONE; + } + + p.d_size = cpu_to_be64(d_size); + p.u_size = cpu_to_be64(u_size); + p.c_size = cpu_to_be64(trigger_reply ? 0 : drbd_get_capacity(mdev->this_bdev)); + p.max_segment_size = cpu_to_be32(queue_max_segment_size(mdev->rq_queue)); + p.queue_order_type = cpu_to_be32(q_order_type); + + ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SIZES, + (struct p_header *)&p, sizeof(p)); + return ok; +} + +/** + * drbd_send_state() - Sends the drbd state to the peer + * @mdev: DRBD device. + */ +int drbd_send_state(struct drbd_conf *mdev) +{ + struct socket *sock; + struct p_state p; + int ok = 0; + + /* Grab state lock so we wont send state if we're in the middle + * of a cluster wide state change on another thread */ + drbd_state_lock(mdev); + + mutex_lock(&mdev->data.mutex); + + p.state = cpu_to_be32(mdev->state.i); /* Within the send mutex */ + sock = mdev->data.socket; + + if (likely(sock != NULL)) { + ok = _drbd_send_cmd(mdev, sock, P_STATE, + (struct p_header *)&p, sizeof(p), 0); + } + + mutex_unlock(&mdev->data.mutex); + + drbd_state_unlock(mdev); + return ok; +} + +int drbd_send_state_req(struct drbd_conf *mdev, + union drbd_state mask, union drbd_state val) +{ + struct p_req_state p; + + p.mask = cpu_to_be32(mask.i); + p.val = cpu_to_be32(val.i); + + return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_STATE_CHG_REQ, + (struct p_header *)&p, sizeof(p)); +} + +int drbd_send_sr_reply(struct drbd_conf *mdev, int retcode) +{ + struct p_req_state_reply p; + + p.retcode = cpu_to_be32(retcode); + + return drbd_send_cmd(mdev, USE_META_SOCKET, P_STATE_CHG_REPLY, + (struct p_header *)&p, sizeof(p)); +} + +int fill_bitmap_rle_bits(struct drbd_conf *mdev, + struct p_compressed_bm *p, + struct bm_xfer_ctx *c) +{ + struct bitstream bs; + unsigned long plain_bits; + unsigned long tmp; + unsigned long rl; + unsigned len; + unsigned toggle; + int bits; + + /* may we use this feature? */ + if ((mdev->sync_conf.use_rle == 0) || + (mdev->agreed_pro_version < 90)) + return 0; + + if (c->bit_offset >= c->bm_bits) + return 0; /* nothing to do. */ + + /* use at most thus many bytes */ + bitstream_init(&bs, p->code, BM_PACKET_VLI_BYTES_MAX, 0); + memset(p->code, 0, BM_PACKET_VLI_BYTES_MAX); + /* plain bits covered in this code string */ + plain_bits = 0; + + /* p->encoding & 0x80 stores whether the first run length is set. + * bit offset is implicit. + * start with toggle == 2 to be able to tell the first iteration */ + toggle = 2; + + /* see how much plain bits we can stuff into one packet + * using RLE and VLI. */ + do { + tmp = (toggle == 0) ? _drbd_bm_find_next_zero(mdev, c->bit_offset) + : _drbd_bm_find_next(mdev, c->bit_offset); + if (tmp == -1UL) + tmp = c->bm_bits; + rl = tmp - c->bit_offset; + + if (toggle == 2) { /* first iteration */ + if (rl == 0) { + /* the first checked bit was set, + * store start value, */ + DCBP_set_start(p, 1); + /* but skip encoding of zero run length */ + toggle = !toggle; + continue; + } + DCBP_set_start(p, 0); + } + + /* paranoia: catch zero runlength. + * can only happen if bitmap is modified while we scan it. */ + if (rl == 0) { + dev_err(DEV, "unexpected zero runlength while encoding bitmap " + "t:%u bo:%lu\n", toggle, c->bit_offset); + return -1; + } + + bits = vli_encode_bits(&bs, rl); + if (bits == -ENOBUFS) /* buffer full */ + break; + if (bits <= 0) { + dev_err(DEV, "error while encoding bitmap: %d\n", bits); + return 0; + } + + toggle = !toggle; + plain_bits += rl; + c->bit_offset = tmp; + } while (c->bit_offset < c->bm_bits); + + len = bs.cur.b - p->code + !!bs.cur.bit; + + if (plain_bits < (len << 3)) { + /* incompressible with this method. + * we need to rewind both word and bit position. */ + c->bit_offset -= plain_bits; + bm_xfer_ctx_bit_to_word_offset(c); + c->bit_offset = c->word_offset * BITS_PER_LONG; + return 0; + } + + /* RLE + VLI was able to compress it just fine. + * update c->word_offset. */ + bm_xfer_ctx_bit_to_word_offset(c); + + /* store pad_bits */ + DCBP_set_pad_bits(p, (8 - bs.cur.bit) & 0x7); + + return len; +} + +enum { OK, FAILED, DONE } +send_bitmap_rle_or_plain(struct drbd_conf *mdev, + struct p_header *h, struct bm_xfer_ctx *c) +{ + struct p_compressed_bm *p = (void*)h; + unsigned long num_words; + int len; + int ok; + + len = fill_bitmap_rle_bits(mdev, p, c); + + if (len < 0) + return FAILED; + + if (len) { + DCBP_set_code(p, RLE_VLI_Bits); + ok = _drbd_send_cmd(mdev, mdev->data.socket, P_COMPRESSED_BITMAP, h, + sizeof(*p) + len, 0); + + c->packets[0]++; + c->bytes[0] += sizeof(*p) + len; + + if (c->bit_offset >= c->bm_bits) + len = 0; /* DONE */ + } else { + /* was not compressible. + * send a buffer full of plain text bits instead. */ + num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset); + len = num_words * sizeof(long); + if (len) + drbd_bm_get_lel(mdev, c->word_offset, num_words, (unsigned long*)h->payload); + ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BITMAP, + h, sizeof(struct p_header) + len, 0); + c->word_offset += num_words; + c->bit_offset = c->word_offset * BITS_PER_LONG; + + c->packets[1]++; + c->bytes[1] += sizeof(struct p_header) + len; + + if (c->bit_offset > c->bm_bits) + c->bit_offset = c->bm_bits; + } + ok = ok ? ((len == 0) ? DONE : OK) : FAILED; + + if (ok == DONE) + INFO_bm_xfer_stats(mdev, "send", c); + return ok; +} + +/* See the comment at receive_bitmap() */ +int _drbd_send_bitmap(struct drbd_conf *mdev) +{ + struct bm_xfer_ctx c; + struct p_header *p; + int ret; + + ERR_IF(!mdev->bitmap) return FALSE; + + /* maybe we should use some per thread scratch page, + * and allocate that during initial device creation? */ + p = (struct p_header *) __get_free_page(GFP_NOIO); + if (!p) { + dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__); + return FALSE; + } + + if (get_ldev(mdev)) { + if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) { + dev_info(DEV, "Writing the whole bitmap, MDF_FullSync was set.\n"); + drbd_bm_set_all(mdev); + if (drbd_bm_write(mdev)) { + /* write_bm did fail! Leave full sync flag set in Meta P_DATA + * but otherwise process as per normal - need to tell other + * side that a full resync is required! */ + dev_err(DEV, "Failed to write bitmap to disk!\n"); + } else { + drbd_md_clear_flag(mdev, MDF_FULL_SYNC); + drbd_md_sync(mdev); + } + } + put_ldev(mdev); + } + + c = (struct bm_xfer_ctx) { + .bm_bits = drbd_bm_bits(mdev), + .bm_words = drbd_bm_words(mdev), + }; + + do { + ret = send_bitmap_rle_or_plain(mdev, p, &c); + } while (ret == OK); + + free_page((unsigned long) p); + return (ret == DONE); +} + +int drbd_send_bitmap(struct drbd_conf *mdev) +{ + int err; + + if (!drbd_get_data_sock(mdev)) + return -1; + err = !_drbd_send_bitmap(mdev); + drbd_put_data_sock(mdev); + return err; +} + +int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr, u32 set_size) +{ + int ok; + struct p_barrier_ack p; + + p.barrier = barrier_nr; + p.set_size = cpu_to_be32(set_size); + + if (mdev->state.conn < C_CONNECTED) + return FALSE; + ok = drbd_send_cmd(mdev, USE_META_SOCKET, P_BARRIER_ACK, + (struct p_header *)&p, sizeof(p)); + return ok; +} + +/** + * _drbd_send_ack() - Sends an ack packet + * @mdev: DRBD device. + * @cmd: Packet command code. + * @sector: sector, needs to be in big endian byte order + * @blksize: size in byte, needs to be in big endian byte order + * @block_id: Id, big endian byte order + */ +static int _drbd_send_ack(struct drbd_conf *mdev, enum drbd_packets cmd, + u64 sector, + u32 blksize, + u64 block_id) +{ + int ok; + struct p_block_ack p; + + p.sector = sector; + p.block_id = block_id; + p.blksize = blksize; + p.seq_num = cpu_to_be32(atomic_add_return(1, &mdev->packet_seq)); + + if (!mdev->meta.socket || mdev->state.conn < C_CONNECTED) + return FALSE; + ok = drbd_send_cmd(mdev, USE_META_SOCKET, cmd, + (struct p_header *)&p, sizeof(p)); + return ok; +} + +int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd, + struct p_data *dp) +{ + const int header_size = sizeof(struct p_data) + - sizeof(struct p_header); + int data_size = ((struct p_header *)dp)->length - header_size; + + return _drbd_send_ack(mdev, cmd, dp->sector, cpu_to_be32(data_size), + dp->block_id); +} + +int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd, + struct p_block_req *rp) +{ + return _drbd_send_ack(mdev, cmd, rp->sector, rp->blksize, rp->block_id); +} + +/** + * drbd_send_ack() - Sends an ack packet + * @mdev: DRBD device. + * @cmd: Packet command code. + * @e: Epoch entry. + */ +int drbd_send_ack(struct drbd_conf *mdev, + enum drbd_packets cmd, struct drbd_epoch_entry *e) +{ + return _drbd_send_ack(mdev, cmd, + cpu_to_be64(e->sector), + cpu_to_be32(e->size), + e->block_id); +} + +/* This function misuses the block_id field to signal if the blocks + * are is sync or not. */ +int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd, + sector_t sector, int blksize, u64 block_id) +{ + return _drbd_send_ack(mdev, cmd, + cpu_to_be64(sector), + cpu_to_be32(blksize), + cpu_to_be64(block_id)); +} + +int drbd_send_drequest(struct drbd_conf *mdev, int cmd, + sector_t sector, int size, u64 block_id) +{ + int ok; + struct p_block_req p; + + p.sector = cpu_to_be64(sector); + p.block_id = block_id; + p.blksize = cpu_to_be32(size); + + ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd, + (struct p_header *)&p, sizeof(p)); + return ok; +} + +int drbd_send_drequest_csum(struct drbd_conf *mdev, + sector_t sector, int size, + void *digest, int digest_size, + enum drbd_packets cmd) +{ + int ok; + struct p_block_req p; + + p.sector = cpu_to_be64(sector); + p.block_id = BE_DRBD_MAGIC + 0xbeef; + p.blksize = cpu_to_be32(size); + + p.head.magic = BE_DRBD_MAGIC; + p.head.command = cpu_to_be16(cmd); + p.head.length = cpu_to_be16(sizeof(p) - sizeof(struct p_header) + digest_size); + + mutex_lock(&mdev->data.mutex); + + ok = (sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, sizeof(p), 0)); + ok = ok && (digest_size == drbd_send(mdev, mdev->data.socket, digest, digest_size, 0)); + + mutex_unlock(&mdev->data.mutex); + + return ok; +} + +int drbd_send_ov_request(struct drbd_conf *mdev, sector_t sector, int size) +{ + int ok; + struct p_block_req p; + + p.sector = cpu_to_be64(sector); + p.block_id = BE_DRBD_MAGIC + 0xbabe; + p.blksize = cpu_to_be32(size); + + ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_OV_REQUEST, + (struct p_header *)&p, sizeof(p)); + return ok; +} + +/* called on sndtimeo + * returns FALSE if we should retry, + * TRUE if we think connection is dead + */ +static int we_should_drop_the_connection(struct drbd_conf *mdev, struct socket *sock) +{ + int drop_it; + /* long elapsed = (long)(jiffies - mdev->last_received); */ + + drop_it = mdev->meta.socket == sock + || !mdev->asender.task + || get_t_state(&mdev->asender) != Running + || mdev->state.conn < C_CONNECTED; + + if (drop_it) + return TRUE; + + drop_it = !--mdev->ko_count; + if (!drop_it) { + dev_err(DEV, "[%s/%d] sock_sendmsg time expired, ko = %u\n", + current->comm, current->pid, mdev->ko_count); + request_ping(mdev); + } + + return drop_it; /* && (mdev->state == R_PRIMARY) */; +} + +/* The idea of sendpage seems to be to put some kind of reference + * to the page into the skb, and to hand it over to the NIC. In + * this process get_page() gets called. + * + * As soon as the page was really sent over the network put_page() + * gets called by some part of the network layer. [ NIC driver? ] + * + * [ get_page() / put_page() increment/decrement the count. If count + * reaches 0 the page will be freed. ] + * + * This works nicely with pages from FSs. + * But this means that in protocol A we might signal IO completion too early! + * + * In order not to corrupt data during a resync we must make sure + * that we do not reuse our own buffer pages (EEs) to early, therefore + * we have the net_ee list. + * + * XFS seems to have problems, still, it submits pages with page_count == 0! + * As a workaround, we disable sendpage on pages + * with page_count == 0 or PageSlab. + */ +static int _drbd_no_send_page(struct drbd_conf *mdev, struct page *page, + int offset, size_t size) +{ + int sent = drbd_send(mdev, mdev->data.socket, kmap(page) + offset, size, 0); + kunmap(page); + if (sent == size) + mdev->send_cnt += size>>9; + return sent == size; +} + +static int _drbd_send_page(struct drbd_conf *mdev, struct page *page, + int offset, size_t size) +{ + mm_segment_t oldfs = get_fs(); + int sent, ok; + int len = size; + + /* e.g. XFS meta- & log-data is in slab pages, which have a + * page_count of 0 and/or have PageSlab() set. + * we cannot use send_page for those, as that does get_page(); + * put_page(); and would cause either a VM_BUG directly, or + * __page_cache_release a page that would actually still be referenced + * by someone, leading to some obscure delayed Oops somewhere else. */ + if (disable_sendpage || (page_count(page) < 1) || PageSlab(page)) + return _drbd_no_send_page(mdev, page, offset, size); + + drbd_update_congested(mdev); + set_fs(KERNEL_DS); + do { + sent = mdev->data.socket->ops->sendpage(mdev->data.socket, page, + offset, len, + MSG_NOSIGNAL); + if (sent == -EAGAIN) { + if (we_should_drop_the_connection(mdev, + mdev->data.socket)) + break; + else + continue; + } + if (sent <= 0) { + dev_warn(DEV, "%s: size=%d len=%d sent=%d\n", + __func__, (int)size, len, sent); + break; + } + len -= sent; + offset += sent; + } while (len > 0 /* THINK && mdev->cstate >= C_CONNECTED*/); + set_fs(oldfs); + clear_bit(NET_CONGESTED, &mdev->flags); + + ok = (len == 0); + if (likely(ok)) + mdev->send_cnt += size>>9; + return ok; +} + +static int _drbd_send_bio(struct drbd_conf *mdev, struct bio *bio) +{ + struct bio_vec *bvec; + int i; + __bio_for_each_segment(bvec, bio, i, 0) { + if (!_drbd_no_send_page(mdev, bvec->bv_page, + bvec->bv_offset, bvec->bv_len)) + return 0; + } + return 1; +} + +static int _drbd_send_zc_bio(struct drbd_conf *mdev, struct bio *bio) +{ + struct bio_vec *bvec; + int i; + __bio_for_each_segment(bvec, bio, i, 0) { + if (!_drbd_send_page(mdev, bvec->bv_page, + bvec->bv_offset, bvec->bv_len)) + return 0; + } + + return 1; +} + +/* Used to send write requests + * R_PRIMARY -> Peer (P_DATA) + */ +int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req) +{ + int ok = 1; + struct p_data p; + unsigned int dp_flags = 0; + void *dgb; + int dgs; + + if (!drbd_get_data_sock(mdev)) + return 0; + + dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ? + crypto_hash_digestsize(mdev->integrity_w_tfm) : 0; + + p.head.magic = BE_DRBD_MAGIC; + p.head.command = cpu_to_be16(P_DATA); + p.head.length = + cpu_to_be16(sizeof(p) - sizeof(struct p_header) + dgs + req->size); + + p.sector = cpu_to_be64(req->sector); + p.block_id = (unsigned long)req; + p.seq_num = cpu_to_be32(req->seq_num = + atomic_add_return(1, &mdev->packet_seq)); + dp_flags = 0; + + /* NOTE: no need to check if barriers supported here as we would + * not pass the test in make_request_common in that case + */ + if (bio_rw_flagged(req->master_bio, BIO_RW_BARRIER)) { + dev_err(DEV, "ASSERT FAILED would have set DP_HARDBARRIER\n"); + /* dp_flags |= DP_HARDBARRIER; */ + } + if (bio_rw_flagged(req->master_bio, BIO_RW_SYNCIO)) + dp_flags |= DP_RW_SYNC; + /* for now handle SYNCIO and UNPLUG + * as if they still were one and the same flag */ + if (bio_rw_flagged(req->master_bio, BIO_RW_UNPLUG)) + dp_flags |= DP_RW_SYNC; + if (mdev->state.conn >= C_SYNC_SOURCE && + mdev->state.conn <= C_PAUSED_SYNC_T) + dp_flags |= DP_MAY_SET_IN_SYNC; + + p.dp_flags = cpu_to_be32(dp_flags); + set_bit(UNPLUG_REMOTE, &mdev->flags); + ok = (sizeof(p) == + drbd_send(mdev, mdev->data.socket, &p, sizeof(p), MSG_MORE)); + if (ok && dgs) { + dgb = mdev->int_dig_out; + drbd_csum(mdev, mdev->integrity_w_tfm, req->master_bio, dgb); + ok = drbd_send(mdev, mdev->data.socket, dgb, dgs, MSG_MORE); + } + if (ok) { + if (mdev->net_conf->wire_protocol == DRBD_PROT_A) + ok = _drbd_send_bio(mdev, req->master_bio); + else + ok = _drbd_send_zc_bio(mdev, req->master_bio); + } + + drbd_put_data_sock(mdev); + return ok; +} + +/* answer packet, used to send data back for read requests: + * Peer -> (diskless) R_PRIMARY (P_DATA_REPLY) + * C_SYNC_SOURCE -> C_SYNC_TARGET (P_RS_DATA_REPLY) + */ +int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd, + struct drbd_epoch_entry *e) +{ + int ok; + struct p_data p; + void *dgb; + int dgs; + + dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ? + crypto_hash_digestsize(mdev->integrity_w_tfm) : 0; + + p.head.magic = BE_DRBD_MAGIC; + p.head.command = cpu_to_be16(cmd); + p.head.length = + cpu_to_be16(sizeof(p) - sizeof(struct p_header) + dgs + e->size); + + p.sector = cpu_to_be64(e->sector); + p.block_id = e->block_id; + /* p.seq_num = 0; No sequence numbers here.. */ + + /* Only called by our kernel thread. + * This one may be interrupted by DRBD_SIG and/or DRBD_SIGKILL + * in response to admin command or module unload. + */ + if (!drbd_get_data_sock(mdev)) + return 0; + + ok = sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, + sizeof(p), MSG_MORE); + if (ok && dgs) { + dgb = mdev->int_dig_out; + drbd_csum(mdev, mdev->integrity_w_tfm, e->private_bio, dgb); + ok = drbd_send(mdev, mdev->data.socket, dgb, dgs, MSG_MORE); + } + if (ok) + ok = _drbd_send_zc_bio(mdev, e->private_bio); + + drbd_put_data_sock(mdev); + return ok; +} + +/* + drbd_send distinguishes two cases: + + Packets sent via the data socket "sock" + and packets sent via the meta data socket "msock" + + sock msock + -----------------+-------------------------+------------------------------ + timeout conf.timeout / 2 conf.timeout / 2 + timeout action send a ping via msock Abort communication + and close all sockets +*/ + +/* + * you must have down()ed the appropriate [m]sock_mutex elsewhere! + */ +int drbd_send(struct drbd_conf *mdev, struct socket *sock, + void *buf, size_t size, unsigned msg_flags) +{ + struct kvec iov; + struct msghdr msg; + int rv, sent = 0; + + if (!sock) + return -1000; + + /* THINK if (signal_pending) return ... ? */ + + iov.iov_base = buf; + iov.iov_len = size; + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = msg_flags | MSG_NOSIGNAL; + + if (sock == mdev->data.socket) { + mdev->ko_count = mdev->net_conf->ko_count; + drbd_update_congested(mdev); + } + do { + /* STRANGE + * tcp_sendmsg does _not_ use its size parameter at all ? + * + * -EAGAIN on timeout, -EINTR on signal. + */ +/* THINK + * do we need to block DRBD_SIG if sock == &meta.socket ?? + * otherwise wake_asender() might interrupt some send_*Ack ! + */ + rv = kernel_sendmsg(sock, &msg, &iov, 1, size); + if (rv == -EAGAIN) { + if (we_should_drop_the_connection(mdev, sock)) + break; + else + continue; + } + D_ASSERT(rv != 0); + if (rv == -EINTR) { + flush_signals(current); + rv = 0; + } + if (rv < 0) + break; + sent += rv; + iov.iov_base += rv; + iov.iov_len -= rv; + } while (sent < size); + + if (sock == mdev->data.socket) + clear_bit(NET_CONGESTED, &mdev->flags); + + if (rv <= 0) { + if (rv != -EAGAIN) { + dev_err(DEV, "%s_sendmsg returned %d\n", + sock == mdev->meta.socket ? "msock" : "sock", + rv); + drbd_force_state(mdev, NS(conn, C_BROKEN_PIPE)); + } else + drbd_force_state(mdev, NS(conn, C_TIMEOUT)); + } + + return sent; +} + +static int drbd_open(struct block_device *bdev, fmode_t mode) +{ + struct drbd_conf *mdev = bdev->bd_disk->private_data; + unsigned long flags; + int rv = 0; + + spin_lock_irqsave(&mdev->req_lock, flags); + /* to have a stable mdev->state.role + * and no race with updating open_cnt */ + + if (mdev->state.role != R_PRIMARY) { + if (mode & FMODE_WRITE) + rv = -EROFS; + else if (!allow_oos) + rv = -EMEDIUMTYPE; + } + + if (!rv) + mdev->open_cnt++; + spin_unlock_irqrestore(&mdev->req_lock, flags); + + return rv; +} + +static int drbd_release(struct gendisk *gd, fmode_t mode) +{ + struct drbd_conf *mdev = gd->private_data; + mdev->open_cnt--; + return 0; +} + +static void drbd_unplug_fn(struct request_queue *q) +{ + struct drbd_conf *mdev = q->queuedata; + + /* unplug FIRST */ + spin_lock_irq(q->queue_lock); + blk_remove_plug(q); + spin_unlock_irq(q->queue_lock); + + /* only if connected */ + spin_lock_irq(&mdev->req_lock); + if (mdev->state.pdsk >= D_INCONSISTENT && mdev->state.conn >= C_CONNECTED) { + D_ASSERT(mdev->state.role == R_PRIMARY); + if (test_and_clear_bit(UNPLUG_REMOTE, &mdev->flags)) { + /* add to the data.work queue, + * unless already queued. + * XXX this might be a good addition to drbd_queue_work + * anyways, to detect "double queuing" ... */ + if (list_empty(&mdev->unplug_work.list)) + drbd_queue_work(&mdev->data.work, + &mdev->unplug_work); + } + } + spin_unlock_irq(&mdev->req_lock); + + if (mdev->state.disk >= D_INCONSISTENT) + drbd_kick_lo(mdev); +} + +static void drbd_set_defaults(struct drbd_conf *mdev) +{ + mdev->sync_conf.after = DRBD_AFTER_DEF; + mdev->sync_conf.rate = DRBD_RATE_DEF; + mdev->sync_conf.al_extents = DRBD_AL_EXTENTS_DEF; + mdev->state = (union drbd_state) { + { .role = R_SECONDARY, + .peer = R_UNKNOWN, + .conn = C_STANDALONE, + .disk = D_DISKLESS, + .pdsk = D_UNKNOWN, + .susp = 0 + } }; +} + +void drbd_init_set_defaults(struct drbd_conf *mdev) +{ + /* the memset(,0,) did most of this. + * note: only assignments, no allocation in here */ + + drbd_set_defaults(mdev); + + /* for now, we do NOT yet support it, + * even though we start some framework + * to eventually support barriers */ + set_bit(NO_BARRIER_SUPP, &mdev->flags); + + atomic_set(&mdev->ap_bio_cnt, 0); + atomic_set(&mdev->ap_pending_cnt, 0); + atomic_set(&mdev->rs_pending_cnt, 0); + atomic_set(&mdev->unacked_cnt, 0); + atomic_set(&mdev->local_cnt, 0); + atomic_set(&mdev->net_cnt, 0); + atomic_set(&mdev->packet_seq, 0); + atomic_set(&mdev->pp_in_use, 0); + + mutex_init(&mdev->md_io_mutex); + mutex_init(&mdev->data.mutex); + mutex_init(&mdev->meta.mutex); + sema_init(&mdev->data.work.s, 0); + sema_init(&mdev->meta.work.s, 0); + mutex_init(&mdev->state_mutex); + + spin_lock_init(&mdev->data.work.q_lock); + spin_lock_init(&mdev->meta.work.q_lock); + + spin_lock_init(&mdev->al_lock); + spin_lock_init(&mdev->req_lock); + spin_lock_init(&mdev->peer_seq_lock); + spin_lock_init(&mdev->epoch_lock); + + INIT_LIST_HEAD(&mdev->active_ee); + INIT_LIST_HEAD(&mdev->sync_ee); + INIT_LIST_HEAD(&mdev->done_ee); + INIT_LIST_HEAD(&mdev->read_ee); + INIT_LIST_HEAD(&mdev->net_ee); + INIT_LIST_HEAD(&mdev->resync_reads); + INIT_LIST_HEAD(&mdev->data.work.q); + INIT_LIST_HEAD(&mdev->meta.work.q); + INIT_LIST_HEAD(&mdev->resync_work.list); + INIT_LIST_HEAD(&mdev->unplug_work.list); + INIT_LIST_HEAD(&mdev->md_sync_work.list); + INIT_LIST_HEAD(&mdev->bm_io_work.w.list); + mdev->resync_work.cb = w_resync_inactive; + mdev->unplug_work.cb = w_send_write_hint; + mdev->md_sync_work.cb = w_md_sync; + mdev->bm_io_work.w.cb = w_bitmap_io; + init_timer(&mdev->resync_timer); + init_timer(&mdev->md_sync_timer); + mdev->resync_timer.function = resync_timer_fn; + mdev->resync_timer.data = (unsigned long) mdev; + mdev->md_sync_timer.function = md_sync_timer_fn; + mdev->md_sync_timer.data = (unsigned long) mdev; + + init_waitqueue_head(&mdev->misc_wait); + init_waitqueue_head(&mdev->state_wait); + init_waitqueue_head(&mdev->ee_wait); + init_waitqueue_head(&mdev->al_wait); + init_waitqueue_head(&mdev->seq_wait); + + drbd_thread_init(mdev, &mdev->receiver, drbdd_init); + drbd_thread_init(mdev, &mdev->worker, drbd_worker); + drbd_thread_init(mdev, &mdev->asender, drbd_asender); + + mdev->agreed_pro_version = PRO_VERSION_MAX; + mdev->write_ordering = WO_bio_barrier; + mdev->resync_wenr = LC_FREE; +} + +void drbd_mdev_cleanup(struct drbd_conf *mdev) +{ + if (mdev->receiver.t_state != None) + dev_err(DEV, "ASSERT FAILED: receiver t_state == %d expected 0.\n", + mdev->receiver.t_state); + + /* no need to lock it, I'm the only thread alive */ + if (atomic_read(&mdev->current_epoch->epoch_size) != 0) + dev_err(DEV, "epoch_size:%d\n", atomic_read(&mdev->current_epoch->epoch_size)); + mdev->al_writ_cnt = + mdev->bm_writ_cnt = + mdev->read_cnt = + mdev->recv_cnt = + mdev->send_cnt = + mdev->writ_cnt = + mdev->p_size = + mdev->rs_start = + mdev->rs_total = + mdev->rs_failed = + mdev->rs_mark_left = + mdev->rs_mark_time = 0; + D_ASSERT(mdev->net_conf == NULL); + + drbd_set_my_capacity(mdev, 0); + if (mdev->bitmap) { + /* maybe never allocated. */ + drbd_bm_resize(mdev, 0); + drbd_bm_cleanup(mdev); + } + + drbd_free_resources(mdev); + + /* + * currently we drbd_init_ee only on module load, so + * we may do drbd_release_ee only on module unload! + */ + D_ASSERT(list_empty(&mdev->active_ee)); + D_ASSERT(list_empty(&mdev->sync_ee)); + D_ASSERT(list_empty(&mdev->done_ee)); + D_ASSERT(list_empty(&mdev->read_ee)); + D_ASSERT(list_empty(&mdev->net_ee)); + D_ASSERT(list_empty(&mdev->resync_reads)); + D_ASSERT(list_empty(&mdev->data.work.q)); + D_ASSERT(list_empty(&mdev->meta.work.q)); + D_ASSERT(list_empty(&mdev->resync_work.list)); + D_ASSERT(list_empty(&mdev->unplug_work.list)); + +} + + +static void drbd_destroy_mempools(void) +{ + struct page *page; + + while (drbd_pp_pool) { + page = drbd_pp_pool; + drbd_pp_pool = (struct page *)page_private(page); + __free_page(page); + drbd_pp_vacant--; + } + + /* D_ASSERT(atomic_read(&drbd_pp_vacant)==0); */ + + if (drbd_ee_mempool) + mempool_destroy(drbd_ee_mempool); + if (drbd_request_mempool) + mempool_destroy(drbd_request_mempool); + if (drbd_ee_cache) + kmem_cache_destroy(drbd_ee_cache); + if (drbd_request_cache) + kmem_cache_destroy(drbd_request_cache); + if (drbd_bm_ext_cache) + kmem_cache_destroy(drbd_bm_ext_cache); + if (drbd_al_ext_cache) + kmem_cache_destroy(drbd_al_ext_cache); + + drbd_ee_mempool = NULL; + drbd_request_mempool = NULL; + drbd_ee_cache = NULL; + drbd_request_cache = NULL; + drbd_bm_ext_cache = NULL; + drbd_al_ext_cache = NULL; + + return; +} + +static int drbd_create_mempools(void) +{ + struct page *page; + const int number = (DRBD_MAX_SEGMENT_SIZE/PAGE_SIZE) * minor_count; + int i; + + /* prepare our caches and mempools */ + drbd_request_mempool = NULL; + drbd_ee_cache = NULL; + drbd_request_cache = NULL; + drbd_bm_ext_cache = NULL; + drbd_al_ext_cache = NULL; + drbd_pp_pool = NULL; + + /* caches */ + drbd_request_cache = kmem_cache_create( + "drbd_req", sizeof(struct drbd_request), 0, 0, NULL); + if (drbd_request_cache == NULL) + goto Enomem; + + drbd_ee_cache = kmem_cache_create( + "drbd_ee", sizeof(struct drbd_epoch_entry), 0, 0, NULL); + if (drbd_ee_cache == NULL) + goto Enomem; + + drbd_bm_ext_cache = kmem_cache_create( + "drbd_bm", sizeof(struct bm_extent), 0, 0, NULL); + if (drbd_bm_ext_cache == NULL) + goto Enomem; + + drbd_al_ext_cache = kmem_cache_create( + "drbd_al", sizeof(struct lc_element), 0, 0, NULL); + if (drbd_al_ext_cache == NULL) + goto Enomem; + + /* mempools */ + drbd_request_mempool = mempool_create(number, + mempool_alloc_slab, mempool_free_slab, drbd_request_cache); + if (drbd_request_mempool == NULL) + goto Enomem; + + drbd_ee_mempool = mempool_create(number, + mempool_alloc_slab, mempool_free_slab, drbd_ee_cache); + if (drbd_request_mempool == NULL) + goto Enomem; + + /* drbd's page pool */ + spin_lock_init(&drbd_pp_lock); + + for (i = 0; i < number; i++) { + page = alloc_page(GFP_HIGHUSER); + if (!page) + goto Enomem; + set_page_private(page, (unsigned long)drbd_pp_pool); + drbd_pp_pool = page; + } + drbd_pp_vacant = number; + + return 0; + +Enomem: + drbd_destroy_mempools(); /* in case we allocated some */ + return -ENOMEM; +} + +static int drbd_notify_sys(struct notifier_block *this, unsigned long code, + void *unused) +{ + /* just so we have it. you never know what interesting things we + * might want to do here some day... + */ + + return NOTIFY_DONE; +} + +static struct notifier_block drbd_notifier = { + .notifier_call = drbd_notify_sys, +}; + +static void drbd_release_ee_lists(struct drbd_conf *mdev) +{ + int rr; + + rr = drbd_release_ee(mdev, &mdev->active_ee); + if (rr) + dev_err(DEV, "%d EEs in active list found!\n", rr); + + rr = drbd_release_ee(mdev, &mdev->sync_ee); + if (rr) + dev_err(DEV, "%d EEs in sync list found!\n", rr); + + rr = drbd_release_ee(mdev, &mdev->read_ee); + if (rr) + dev_err(DEV, "%d EEs in read list found!\n", rr); + + rr = drbd_release_ee(mdev, &mdev->done_ee); + if (rr) + dev_err(DEV, "%d EEs in done list found!\n", rr); + + rr = drbd_release_ee(mdev, &mdev->net_ee); + if (rr) + dev_err(DEV, "%d EEs in net list found!\n", rr); +} + +/* caution. no locking. + * currently only used from module cleanup code. */ +static void drbd_delete_device(unsigned int minor) +{ + struct drbd_conf *mdev = minor_to_mdev(minor); + + if (!mdev) + return; + + /* paranoia asserts */ + if (mdev->open_cnt != 0) + dev_err(DEV, "open_cnt = %d in %s:%u", mdev->open_cnt, + __FILE__ , __LINE__); + + ERR_IF (!list_empty(&mdev->data.work.q)) { + struct list_head *lp; + list_for_each(lp, &mdev->data.work.q) { + dev_err(DEV, "lp = %p\n", lp); + } + }; + /* end paranoia asserts */ + + del_gendisk(mdev->vdisk); + + /* cleanup stuff that may have been allocated during + * device (re-)configuration or state changes */ + + if (mdev->this_bdev) + bdput(mdev->this_bdev); + + drbd_free_resources(mdev); + + drbd_release_ee_lists(mdev); + + /* should be free'd on disconnect? */ + kfree(mdev->ee_hash); + /* + mdev->ee_hash_s = 0; + mdev->ee_hash = NULL; + */ + + lc_destroy(mdev->act_log); + lc_destroy(mdev->resync); + + kfree(mdev->p_uuid); + /* mdev->p_uuid = NULL; */ + + kfree(mdev->int_dig_out); + kfree(mdev->int_dig_in); + kfree(mdev->int_dig_vv); + + /* cleanup the rest that has been + * allocated from drbd_new_device + * and actually free the mdev itself */ + drbd_free_mdev(mdev); +} + +static void drbd_cleanup(void) +{ + unsigned int i; + + unregister_reboot_notifier(&drbd_notifier); + + drbd_nl_cleanup(); + + if (minor_table) { + if (drbd_proc) + remove_proc_entry("drbd", NULL); + i = minor_count; + while (i--) + drbd_delete_device(i); + drbd_destroy_mempools(); + } + + kfree(minor_table); + + unregister_blkdev(DRBD_MAJOR, "drbd"); + + printk(KERN_INFO "drbd: module cleanup done.\n"); +} + +/** + * drbd_congested() - Callback for pdflush + * @congested_data: User data + * @bdi_bits: Bits pdflush is currently interested in + * + * Returns 1<ldev->backing_bdev); + r = bdi_congested(&q->backing_dev_info, bdi_bits); + put_ldev(mdev); + if (r) + reason = 'b'; + } + + if (bdi_bits & (1 << BDI_async_congested) && test_bit(NET_CONGESTED, &mdev->flags)) { + r |= (1 << BDI_async_congested); + reason = reason == 'b' ? 'a' : 'n'; + } + +out: + mdev->congestion_reason = reason; + return r; +} + +struct drbd_conf *drbd_new_device(unsigned int minor) +{ + struct drbd_conf *mdev; + struct gendisk *disk; + struct request_queue *q; + + /* GFP_KERNEL, we are outside of all write-out paths */ + mdev = kzalloc(sizeof(struct drbd_conf), GFP_KERNEL); + if (!mdev) + return NULL; + if (!zalloc_cpumask_var(&mdev->cpu_mask, GFP_KERNEL)) + goto out_no_cpumask; + + mdev->minor = minor; + + drbd_init_set_defaults(mdev); + + q = blk_alloc_queue(GFP_KERNEL); + if (!q) + goto out_no_q; + mdev->rq_queue = q; + q->queuedata = mdev; + blk_queue_max_segment_size(q, DRBD_MAX_SEGMENT_SIZE); + + disk = alloc_disk(1); + if (!disk) + goto out_no_disk; + mdev->vdisk = disk; + + set_disk_ro(disk, TRUE); + + disk->queue = q; + disk->major = DRBD_MAJOR; + disk->first_minor = minor; + disk->fops = &drbd_ops; + sprintf(disk->disk_name, "drbd%d", minor); + disk->private_data = mdev; + + mdev->this_bdev = bdget(MKDEV(DRBD_MAJOR, minor)); + /* we have no partitions. we contain only ourselves. */ + mdev->this_bdev->bd_contains = mdev->this_bdev; + + q->backing_dev_info.congested_fn = drbd_congested; + q->backing_dev_info.congested_data = mdev; + + blk_queue_make_request(q, drbd_make_request_26); + blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); + blk_queue_merge_bvec(q, drbd_merge_bvec); + q->queue_lock = &mdev->req_lock; /* needed since we use */ + /* plugging on a queue, that actually has no requests! */ + q->unplug_fn = drbd_unplug_fn; + + mdev->md_io_page = alloc_page(GFP_KERNEL); + if (!mdev->md_io_page) + goto out_no_io_page; + + if (drbd_bm_init(mdev)) + goto out_no_bitmap; + /* no need to lock access, we are still initializing this minor device. */ + if (!tl_init(mdev)) + goto out_no_tl; + + mdev->app_reads_hash = kzalloc(APP_R_HSIZE*sizeof(void *), GFP_KERNEL); + if (!mdev->app_reads_hash) + goto out_no_app_reads; + + mdev->current_epoch = kzalloc(sizeof(struct drbd_epoch), GFP_KERNEL); + if (!mdev->current_epoch) + goto out_no_epoch; + + INIT_LIST_HEAD(&mdev->current_epoch->list); + mdev->epochs = 1; + + return mdev; + +/* out_whatever_else: + kfree(mdev->current_epoch); */ +out_no_epoch: + kfree(mdev->app_reads_hash); +out_no_app_reads: + tl_cleanup(mdev); +out_no_tl: + drbd_bm_cleanup(mdev); +out_no_bitmap: + __free_page(mdev->md_io_page); +out_no_io_page: + put_disk(disk); +out_no_disk: + blk_cleanup_queue(q); +out_no_q: + free_cpumask_var(mdev->cpu_mask); +out_no_cpumask: + kfree(mdev); + return NULL; +} + +/* counterpart of drbd_new_device. + * last part of drbd_delete_device. */ +void drbd_free_mdev(struct drbd_conf *mdev) +{ + kfree(mdev->current_epoch); + kfree(mdev->app_reads_hash); + tl_cleanup(mdev); + if (mdev->bitmap) /* should no longer be there. */ + drbd_bm_cleanup(mdev); + __free_page(mdev->md_io_page); + put_disk(mdev->vdisk); + blk_cleanup_queue(mdev->rq_queue); + free_cpumask_var(mdev->cpu_mask); + kfree(mdev); +} + + +int __init drbd_init(void) +{ + int err; + + if (sizeof(struct p_handshake) != 80) { + printk(KERN_ERR + "drbd: never change the size or layout " + "of the HandShake packet.\n"); + return -EINVAL; + } + + if (1 > minor_count || minor_count > 255) { + printk(KERN_ERR + "drbd: invalid minor_count (%d)\n", minor_count); +#ifdef MODULE + return -EINVAL; +#else + minor_count = 8; +#endif + } + + err = drbd_nl_init(); + if (err) + return err; + + err = register_blkdev(DRBD_MAJOR, "drbd"); + if (err) { + printk(KERN_ERR + "drbd: unable to register block device major %d\n", + DRBD_MAJOR); + return err; + } + + register_reboot_notifier(&drbd_notifier); + + /* + * allocate all necessary structs + */ + err = -ENOMEM; + + init_waitqueue_head(&drbd_pp_wait); + + drbd_proc = NULL; /* play safe for drbd_cleanup */ + minor_table = kzalloc(sizeof(struct drbd_conf *)*minor_count, + GFP_KERNEL); + if (!minor_table) + goto Enomem; + + err = drbd_create_mempools(); + if (err) + goto Enomem; + + drbd_proc = proc_create("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops); + if (!drbd_proc) { + printk(KERN_ERR "drbd: unable to register proc file\n"); + goto Enomem; + } + + rwlock_init(&global_state_lock); + + printk(KERN_INFO "drbd: initialized. " + "Version: " REL_VERSION " (api:%d/proto:%d-%d)\n", + API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX); + printk(KERN_INFO "drbd: %s\n", drbd_buildtag()); + printk(KERN_INFO "drbd: registered as block device major %d\n", + DRBD_MAJOR); + printk(KERN_INFO "drbd: minor_table @ 0x%p\n", minor_table); + + return 0; /* Success! */ + +Enomem: + drbd_cleanup(); + if (err == -ENOMEM) + /* currently always the case */ + printk(KERN_ERR "drbd: ran out of memory\n"); + else + printk(KERN_ERR "drbd: initialization failure\n"); + return err; +} + +void drbd_free_bc(struct drbd_backing_dev *ldev) +{ + if (ldev == NULL) + return; + + bd_release(ldev->backing_bdev); + bd_release(ldev->md_bdev); + + fput(ldev->lo_file); + fput(ldev->md_file); + + kfree(ldev); +} + +void drbd_free_sock(struct drbd_conf *mdev) +{ + if (mdev->data.socket) { + kernel_sock_shutdown(mdev->data.socket, SHUT_RDWR); + sock_release(mdev->data.socket); + mdev->data.socket = NULL; + } + if (mdev->meta.socket) { + kernel_sock_shutdown(mdev->meta.socket, SHUT_RDWR); + sock_release(mdev->meta.socket); + mdev->meta.socket = NULL; + } +} + + +void drbd_free_resources(struct drbd_conf *mdev) +{ + crypto_free_hash(mdev->csums_tfm); + mdev->csums_tfm = NULL; + crypto_free_hash(mdev->verify_tfm); + mdev->verify_tfm = NULL; + crypto_free_hash(mdev->cram_hmac_tfm); + mdev->cram_hmac_tfm = NULL; + crypto_free_hash(mdev->integrity_w_tfm); + mdev->integrity_w_tfm = NULL; + crypto_free_hash(mdev->integrity_r_tfm); + mdev->integrity_r_tfm = NULL; + + drbd_free_sock(mdev); + + __no_warn(local, + drbd_free_bc(mdev->ldev); + mdev->ldev = NULL;); +} + +/* meta data management */ + +struct meta_data_on_disk { + u64 la_size; /* last agreed size. */ + u64 uuid[UI_SIZE]; /* UUIDs. */ + u64 device_uuid; + u64 reserved_u64_1; + u32 flags; /* MDF */ + u32 magic; + u32 md_size_sect; + u32 al_offset; /* offset to this block */ + u32 al_nr_extents; /* important for restoring the AL */ + /* `-- act_log->nr_elements <-- sync_conf.al_extents */ + u32 bm_offset; /* offset to the bitmap, from here */ + u32 bm_bytes_per_bit; /* BM_BLOCK_SIZE */ + u32 reserved_u32[4]; + +} __packed; + +/** + * drbd_md_sync() - Writes the meta data super block if the MD_DIRTY flag bit is set + * @mdev: DRBD device. + */ +void drbd_md_sync(struct drbd_conf *mdev) +{ + struct meta_data_on_disk *buffer; + sector_t sector; + int i; + + if (!test_and_clear_bit(MD_DIRTY, &mdev->flags)) + return; + del_timer(&mdev->md_sync_timer); + + /* We use here D_FAILED and not D_ATTACHING because we try to write + * metadata even if we detach due to a disk failure! */ + if (!get_ldev_if_state(mdev, D_FAILED)) + return; + + mutex_lock(&mdev->md_io_mutex); + buffer = (struct meta_data_on_disk *)page_address(mdev->md_io_page); + memset(buffer, 0, 512); + + buffer->la_size = cpu_to_be64(drbd_get_capacity(mdev->this_bdev)); + for (i = UI_CURRENT; i < UI_SIZE; i++) + buffer->uuid[i] = cpu_to_be64(mdev->ldev->md.uuid[i]); + buffer->flags = cpu_to_be32(mdev->ldev->md.flags); + buffer->magic = cpu_to_be32(DRBD_MD_MAGIC); + + buffer->md_size_sect = cpu_to_be32(mdev->ldev->md.md_size_sect); + buffer->al_offset = cpu_to_be32(mdev->ldev->md.al_offset); + buffer->al_nr_extents = cpu_to_be32(mdev->act_log->nr_elements); + buffer->bm_bytes_per_bit = cpu_to_be32(BM_BLOCK_SIZE); + buffer->device_uuid = cpu_to_be64(mdev->ldev->md.device_uuid); + + buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset); + + D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset); + sector = mdev->ldev->md.md_offset; + + if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) { + clear_bit(MD_DIRTY, &mdev->flags); + } else { + /* this was a try anyways ... */ + dev_err(DEV, "meta data update failed!\n"); + + drbd_chk_io_error(mdev, 1, TRUE); + } + + /* Update mdev->ldev->md.la_size_sect, + * since we updated it on metadata. */ + mdev->ldev->md.la_size_sect = drbd_get_capacity(mdev->this_bdev); + + mutex_unlock(&mdev->md_io_mutex); + put_ldev(mdev); +} + +/** + * drbd_md_read() - Reads in the meta data super block + * @mdev: DRBD device. + * @bdev: Device from which the meta data should be read in. + * + * Return 0 (NO_ERROR) on success, and an enum drbd_ret_codes in case + * something goes wrong. Currently only: ERR_IO_MD_DISK, ERR_MD_INVALID. + */ +int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev) +{ + struct meta_data_on_disk *buffer; + int i, rv = NO_ERROR; + + if (!get_ldev_if_state(mdev, D_ATTACHING)) + return ERR_IO_MD_DISK; + + mutex_lock(&mdev->md_io_mutex); + buffer = (struct meta_data_on_disk *)page_address(mdev->md_io_page); + + if (!drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) { + /* NOTE: cant do normal error processing here as this is + called BEFORE disk is attached */ + dev_err(DEV, "Error while reading metadata.\n"); + rv = ERR_IO_MD_DISK; + goto err; + } + + if (be32_to_cpu(buffer->magic) != DRBD_MD_MAGIC) { + dev_err(DEV, "Error while reading metadata, magic not found.\n"); + rv = ERR_MD_INVALID; + goto err; + } + if (be32_to_cpu(buffer->al_offset) != bdev->md.al_offset) { + dev_err(DEV, "unexpected al_offset: %d (expected %d)\n", + be32_to_cpu(buffer->al_offset), bdev->md.al_offset); + rv = ERR_MD_INVALID; + goto err; + } + if (be32_to_cpu(buffer->bm_offset) != bdev->md.bm_offset) { + dev_err(DEV, "unexpected bm_offset: %d (expected %d)\n", + be32_to_cpu(buffer->bm_offset), bdev->md.bm_offset); + rv = ERR_MD_INVALID; + goto err; + } + if (be32_to_cpu(buffer->md_size_sect) != bdev->md.md_size_sect) { + dev_err(DEV, "unexpected md_size: %u (expected %u)\n", + be32_to_cpu(buffer->md_size_sect), bdev->md.md_size_sect); + rv = ERR_MD_INVALID; + goto err; + } + + if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) { + dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n", + be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE); + rv = ERR_MD_INVALID; + goto err; + } + + bdev->md.la_size_sect = be64_to_cpu(buffer->la_size); + for (i = UI_CURRENT; i < UI_SIZE; i++) + bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]); + bdev->md.flags = be32_to_cpu(buffer->flags); + mdev->sync_conf.al_extents = be32_to_cpu(buffer->al_nr_extents); + bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid); + + if (mdev->sync_conf.al_extents < 7) + mdev->sync_conf.al_extents = 127; + + err: + mutex_unlock(&mdev->md_io_mutex); + put_ldev(mdev); + + return rv; +} + +/** + * drbd_md_mark_dirty() - Mark meta data super block as dirty + * @mdev: DRBD device. + * + * Call this function if you change anything that should be written to + * the meta-data super block. This function sets MD_DIRTY, and starts a + * timer that ensures that within five seconds you have to call drbd_md_sync(). + */ +void drbd_md_mark_dirty(struct drbd_conf *mdev) +{ + set_bit(MD_DIRTY, &mdev->flags); + mod_timer(&mdev->md_sync_timer, jiffies + 5*HZ); +} + + +static void drbd_uuid_move_history(struct drbd_conf *mdev) __must_hold(local) +{ + int i; + + for (i = UI_HISTORY_START; i < UI_HISTORY_END; i++) + mdev->ldev->md.uuid[i+1] = mdev->ldev->md.uuid[i]; +} + +void _drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local) +{ + if (idx == UI_CURRENT) { + if (mdev->state.role == R_PRIMARY) + val |= 1; + else + val &= ~((u64)1); + + drbd_set_ed_uuid(mdev, val); + } + + mdev->ldev->md.uuid[idx] = val; + drbd_md_mark_dirty(mdev); +} + + +void drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local) +{ + if (mdev->ldev->md.uuid[idx]) { + drbd_uuid_move_history(mdev); + mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[idx]; + } + _drbd_uuid_set(mdev, idx, val); +} + +/** + * drbd_uuid_new_current() - Creates a new current UUID + * @mdev: DRBD device. + * + * Creates a new current UUID, and rotates the old current UUID into + * the bitmap slot. Causes an incremental resync upon next connect. + */ +void drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local) +{ + u64 val; + + dev_info(DEV, "Creating new current UUID\n"); + D_ASSERT(mdev->ldev->md.uuid[UI_BITMAP] == 0); + mdev->ldev->md.uuid[UI_BITMAP] = mdev->ldev->md.uuid[UI_CURRENT]; + + get_random_bytes(&val, sizeof(u64)); + _drbd_uuid_set(mdev, UI_CURRENT, val); +} + +void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local) +{ + if (mdev->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) + return; + + if (val == 0) { + drbd_uuid_move_history(mdev); + mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[UI_BITMAP]; + mdev->ldev->md.uuid[UI_BITMAP] = 0; + } else { + if (mdev->ldev->md.uuid[UI_BITMAP]) + dev_warn(DEV, "bm UUID already set"); + + mdev->ldev->md.uuid[UI_BITMAP] = val; + mdev->ldev->md.uuid[UI_BITMAP] &= ~((u64)1); + + } + drbd_md_mark_dirty(mdev); +} + +/** + * drbd_bmio_set_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io() + * @mdev: DRBD device. + * + * Sets all bits in the bitmap and writes the whole bitmap to stable storage. + */ +int drbd_bmio_set_n_write(struct drbd_conf *mdev) +{ + int rv = -EIO; + + if (get_ldev_if_state(mdev, D_ATTACHING)) { + drbd_md_set_flag(mdev, MDF_FULL_SYNC); + drbd_md_sync(mdev); + drbd_bm_set_all(mdev); + + rv = drbd_bm_write(mdev); + + if (!rv) { + drbd_md_clear_flag(mdev, MDF_FULL_SYNC); + drbd_md_sync(mdev); + } + + put_ldev(mdev); + } + + return rv; +} + +/** + * drbd_bmio_clear_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io() + * @mdev: DRBD device. + * + * Clears all bits in the bitmap and writes the whole bitmap to stable storage. + */ +int drbd_bmio_clear_n_write(struct drbd_conf *mdev) +{ + int rv = -EIO; + + if (get_ldev_if_state(mdev, D_ATTACHING)) { + drbd_bm_clear_all(mdev); + rv = drbd_bm_write(mdev); + put_ldev(mdev); + } + + return rv; +} + +static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct bm_io_work *work = container_of(w, struct bm_io_work, w); + int rv; + + D_ASSERT(atomic_read(&mdev->ap_bio_cnt) == 0); + + drbd_bm_lock(mdev, work->why); + rv = work->io_fn(mdev); + drbd_bm_unlock(mdev); + + clear_bit(BITMAP_IO, &mdev->flags); + wake_up(&mdev->misc_wait); + + if (work->done) + work->done(mdev, rv); + + clear_bit(BITMAP_IO_QUEUED, &mdev->flags); + work->why = NULL; + + return 1; +} + +/** + * drbd_queue_bitmap_io() - Queues an IO operation on the whole bitmap + * @mdev: DRBD device. + * @io_fn: IO callback to be called when bitmap IO is possible + * @done: callback to be called after the bitmap IO was performed + * @why: Descriptive text of the reason for doing the IO + * + * While IO on the bitmap happens we freeze application IO thus we ensure + * that drbd_set_out_of_sync() can not be called. This function MAY ONLY be + * called from worker context. It MUST NOT be used while a previous such + * work is still pending! + */ +void drbd_queue_bitmap_io(struct drbd_conf *mdev, + int (*io_fn)(struct drbd_conf *), + void (*done)(struct drbd_conf *, int), + char *why) +{ + D_ASSERT(current == mdev->worker.task); + + D_ASSERT(!test_bit(BITMAP_IO_QUEUED, &mdev->flags)); + D_ASSERT(!test_bit(BITMAP_IO, &mdev->flags)); + D_ASSERT(list_empty(&mdev->bm_io_work.w.list)); + if (mdev->bm_io_work.why) + dev_err(DEV, "FIXME going to queue '%s' but '%s' still pending?\n", + why, mdev->bm_io_work.why); + + mdev->bm_io_work.io_fn = io_fn; + mdev->bm_io_work.done = done; + mdev->bm_io_work.why = why; + + set_bit(BITMAP_IO, &mdev->flags); + if (atomic_read(&mdev->ap_bio_cnt) == 0) { + if (list_empty(&mdev->bm_io_work.w.list)) { + set_bit(BITMAP_IO_QUEUED, &mdev->flags); + drbd_queue_work(&mdev->data.work, &mdev->bm_io_work.w); + } else + dev_err(DEV, "FIXME avoided double queuing bm_io_work\n"); + } +} + +/** + * drbd_bitmap_io() - Does an IO operation on the whole bitmap + * @mdev: DRBD device. + * @io_fn: IO callback to be called when bitmap IO is possible + * @why: Descriptive text of the reason for doing the IO + * + * freezes application IO while that the actual IO operations runs. This + * functions MAY NOT be called from worker context. + */ +int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why) +{ + int rv; + + D_ASSERT(current != mdev->worker.task); + + drbd_suspend_io(mdev); + + drbd_bm_lock(mdev, why); + rv = io_fn(mdev); + drbd_bm_unlock(mdev); + + drbd_resume_io(mdev); + + return rv; +} + +void drbd_md_set_flag(struct drbd_conf *mdev, int flag) __must_hold(local) +{ + if ((mdev->ldev->md.flags & flag) != flag) { + drbd_md_mark_dirty(mdev); + mdev->ldev->md.flags |= flag; + } +} + +void drbd_md_clear_flag(struct drbd_conf *mdev, int flag) __must_hold(local) +{ + if ((mdev->ldev->md.flags & flag) != 0) { + drbd_md_mark_dirty(mdev); + mdev->ldev->md.flags &= ~flag; + } +} +int drbd_md_test_flag(struct drbd_backing_dev *bdev, int flag) +{ + return (bdev->md.flags & flag) != 0; +} + +static void md_sync_timer_fn(unsigned long data) +{ + struct drbd_conf *mdev = (struct drbd_conf *) data; + + drbd_queue_work_front(&mdev->data.work, &mdev->md_sync_work); +} + +static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + dev_warn(DEV, "md_sync_timer expired! Worker calls drbd_md_sync().\n"); + drbd_md_sync(mdev); + + return 1; +} + +#ifdef CONFIG_DRBD_FAULT_INJECTION +/* Fault insertion support including random number generator shamelessly + * stolen from kernel/rcutorture.c */ +struct fault_random_state { + unsigned long state; + unsigned long count; +}; + +#define FAULT_RANDOM_MULT 39916801 /* prime */ +#define FAULT_RANDOM_ADD 479001701 /* prime */ +#define FAULT_RANDOM_REFRESH 10000 + +/* + * Crude but fast random-number generator. Uses a linear congruential + * generator, with occasional help from get_random_bytes(). + */ +static unsigned long +_drbd_fault_random(struct fault_random_state *rsp) +{ + long refresh; + + if (--rsp->count < 0) { + get_random_bytes(&refresh, sizeof(refresh)); + rsp->state += refresh; + rsp->count = FAULT_RANDOM_REFRESH; + } + rsp->state = rsp->state * FAULT_RANDOM_MULT + FAULT_RANDOM_ADD; + return swahw32(rsp->state); +} + +static char * +_drbd_fault_str(unsigned int type) { + static char *_faults[] = { + [DRBD_FAULT_MD_WR] = "Meta-data write", + [DRBD_FAULT_MD_RD] = "Meta-data read", + [DRBD_FAULT_RS_WR] = "Resync write", + [DRBD_FAULT_RS_RD] = "Resync read", + [DRBD_FAULT_DT_WR] = "Data write", + [DRBD_FAULT_DT_RD] = "Data read", + [DRBD_FAULT_DT_RA] = "Data read ahead", + [DRBD_FAULT_BM_ALLOC] = "BM allocation", + [DRBD_FAULT_AL_EE] = "EE allocation" + }; + + return (type < DRBD_FAULT_MAX) ? _faults[type] : "**Unknown**"; +} + +unsigned int +_drbd_insert_fault(struct drbd_conf *mdev, unsigned int type) +{ + static struct fault_random_state rrs = {0, 0}; + + unsigned int ret = ( + (fault_devs == 0 || + ((1 << mdev_to_minor(mdev)) & fault_devs) != 0) && + (((_drbd_fault_random(&rrs) % 100) + 1) <= fault_rate)); + + if (ret) { + fault_count++; + + if (printk_ratelimit()) + dev_warn(DEV, "***Simulating %s failure\n", + _drbd_fault_str(type)); + } + + return ret; +} +#endif + +const char *drbd_buildtag(void) +{ + /* DRBD built from external sources has here a reference to the + git hash of the source code. */ + + static char buildtag[38] = "\0uilt-in"; + + if (buildtag[0] == 0) { +#ifdef CONFIG_MODULES + if (THIS_MODULE != NULL) + sprintf(buildtag, "srcversion: %-24s", THIS_MODULE->srcversion); + else +#endif + buildtag[0] = 'b'; + } + + return buildtag; +} + +module_init(drbd_init) +module_exit(drbd_cleanup) + +EXPORT_SYMBOL(drbd_conn_str); +EXPORT_SYMBOL(drbd_role_str); +EXPORT_SYMBOL(drbd_disk_str); +EXPORT_SYMBOL(drbd_set_st_err_str); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c new file mode 100644 index 000000000000..436a090b532b --- /dev/null +++ b/drivers/block/drbd/drbd_nl.c @@ -0,0 +1,2364 @@ +/* + drbd_nl.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "drbd_int.h" +#include "drbd_wrappers.h" +#include +#include +#include + +static unsigned short *tl_add_blob(unsigned short *, enum drbd_tags, const void *, int); +static unsigned short *tl_add_str(unsigned short *, enum drbd_tags, const char *); +static unsigned short *tl_add_int(unsigned short *, enum drbd_tags, const void *); + +/* see get_sb_bdev and bd_claim */ +static char *drbd_m_holder = "Hands off! this is DRBD's meta data device."; + +/* Generate the tag_list to struct functions */ +#define NL_PACKET(name, number, fields) \ +static int name ## _from_tags(struct drbd_conf *mdev, \ + unsigned short *tags, struct name *arg) __attribute__ ((unused)); \ +static int name ## _from_tags(struct drbd_conf *mdev, \ + unsigned short *tags, struct name *arg) \ +{ \ + int tag; \ + int dlen; \ + \ + while ((tag = get_unaligned(tags++)) != TT_END) { \ + dlen = get_unaligned(tags++); \ + switch (tag_number(tag)) { \ + fields \ + default: \ + if (tag & T_MANDATORY) { \ + dev_err(DEV, "Unknown tag: %d\n", tag_number(tag)); \ + return 0; \ + } \ + } \ + tags = (unsigned short *)((char *)tags + dlen); \ + } \ + return 1; \ +} +#define NL_INTEGER(pn, pr, member) \ + case pn: /* D_ASSERT( tag_type(tag) == TT_INTEGER ); */ \ + arg->member = get_unaligned((int *)(tags)); \ + break; +#define NL_INT64(pn, pr, member) \ + case pn: /* D_ASSERT( tag_type(tag) == TT_INT64 ); */ \ + arg->member = get_unaligned((u64 *)(tags)); \ + break; +#define NL_BIT(pn, pr, member) \ + case pn: /* D_ASSERT( tag_type(tag) == TT_BIT ); */ \ + arg->member = *(char *)(tags) ? 1 : 0; \ + break; +#define NL_STRING(pn, pr, member, len) \ + case pn: /* D_ASSERT( tag_type(tag) == TT_STRING ); */ \ + if (dlen > len) { \ + dev_err(DEV, "arg too long: %s (%u wanted, max len: %u bytes)\n", \ + #member, dlen, (unsigned int)len); \ + return 0; \ + } \ + arg->member ## _len = dlen; \ + memcpy(arg->member, tags, min_t(size_t, dlen, len)); \ + break; +#include "linux/drbd_nl.h" + +/* Generate the struct to tag_list functions */ +#define NL_PACKET(name, number, fields) \ +static unsigned short* \ +name ## _to_tags(struct drbd_conf *mdev, \ + struct name *arg, unsigned short *tags) __attribute__ ((unused)); \ +static unsigned short* \ +name ## _to_tags(struct drbd_conf *mdev, \ + struct name *arg, unsigned short *tags) \ +{ \ + fields \ + return tags; \ +} + +#define NL_INTEGER(pn, pr, member) \ + put_unaligned(pn | pr | TT_INTEGER, tags++); \ + put_unaligned(sizeof(int), tags++); \ + put_unaligned(arg->member, (int *)tags); \ + tags = (unsigned short *)((char *)tags+sizeof(int)); +#define NL_INT64(pn, pr, member) \ + put_unaligned(pn | pr | TT_INT64, tags++); \ + put_unaligned(sizeof(u64), tags++); \ + put_unaligned(arg->member, (u64 *)tags); \ + tags = (unsigned short *)((char *)tags+sizeof(u64)); +#define NL_BIT(pn, pr, member) \ + put_unaligned(pn | pr | TT_BIT, tags++); \ + put_unaligned(sizeof(char), tags++); \ + *(char *)tags = arg->member; \ + tags = (unsigned short *)((char *)tags+sizeof(char)); +#define NL_STRING(pn, pr, member, len) \ + put_unaligned(pn | pr | TT_STRING, tags++); \ + put_unaligned(arg->member ## _len, tags++); \ + memcpy(tags, arg->member, arg->member ## _len); \ + tags = (unsigned short *)((char *)tags + arg->member ## _len); +#include "linux/drbd_nl.h" + +void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name); +void drbd_nl_send_reply(struct cn_msg *, int); + +int drbd_khelper(struct drbd_conf *mdev, char *cmd) +{ + char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL, /* Will be set to address family */ + NULL, /* Will be set to address */ + NULL }; + + char mb[12], af[20], ad[60], *afs; + char *argv[] = {usermode_helper, cmd, mb, NULL }; + int ret; + + snprintf(mb, 12, "minor-%d", mdev_to_minor(mdev)); + + if (get_net_conf(mdev)) { + switch (((struct sockaddr *)mdev->net_conf->peer_addr)->sa_family) { + case AF_INET6: + afs = "ipv6"; + snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI6", + &((struct sockaddr_in6 *)mdev->net_conf->peer_addr)->sin6_addr); + break; + case AF_INET: + afs = "ipv4"; + snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4", + &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr); + break; + default: + afs = "ssocks"; + snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4", + &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr); + } + snprintf(af, 20, "DRBD_PEER_AF=%s", afs); + envp[3]=af; + envp[4]=ad; + put_net_conf(mdev); + } + + dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb); + + drbd_bcast_ev_helper(mdev, cmd); + ret = call_usermodehelper(usermode_helper, argv, envp, 1); + if (ret) + dev_warn(DEV, "helper command: %s %s %s exit code %u (0x%x)\n", + usermode_helper, cmd, mb, + (ret >> 8) & 0xff, ret); + else + dev_info(DEV, "helper command: %s %s %s exit code %u (0x%x)\n", + usermode_helper, cmd, mb, + (ret >> 8) & 0xff, ret); + + if (ret < 0) /* Ignore any ERRNOs we got. */ + ret = 0; + + return ret; +} + +enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev) +{ + char *ex_to_string; + int r; + enum drbd_disk_state nps; + enum drbd_fencing_p fp; + + D_ASSERT(mdev->state.pdsk == D_UNKNOWN); + + if (get_ldev_if_state(mdev, D_CONSISTENT)) { + fp = mdev->ldev->dc.fencing; + put_ldev(mdev); + } else { + dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n"); + return mdev->state.pdsk; + } + + if (fp == FP_STONITH) + _drbd_request_state(mdev, NS(susp, 1), CS_WAIT_COMPLETE); + + r = drbd_khelper(mdev, "fence-peer"); + + switch ((r>>8) & 0xff) { + case 3: /* peer is inconsistent */ + ex_to_string = "peer is inconsistent or worse"; + nps = D_INCONSISTENT; + break; + case 4: /* peer got outdated, or was already outdated */ + ex_to_string = "peer was fenced"; + nps = D_OUTDATED; + break; + case 5: /* peer was down */ + if (mdev->state.disk == D_UP_TO_DATE) { + /* we will(have) create(d) a new UUID anyways... */ + ex_to_string = "peer is unreachable, assumed to be dead"; + nps = D_OUTDATED; + } else { + ex_to_string = "peer unreachable, doing nothing since disk != UpToDate"; + nps = mdev->state.pdsk; + } + break; + case 6: /* Peer is primary, voluntarily outdate myself. + * This is useful when an unconnected R_SECONDARY is asked to + * become R_PRIMARY, but finds the other peer being active. */ + ex_to_string = "peer is active"; + dev_warn(DEV, "Peer is primary, outdating myself.\n"); + nps = D_UNKNOWN; + _drbd_request_state(mdev, NS(disk, D_OUTDATED), CS_WAIT_COMPLETE); + break; + case 7: + if (fp != FP_STONITH) + dev_err(DEV, "fence-peer() = 7 && fencing != Stonith !!!\n"); + ex_to_string = "peer was stonithed"; + nps = D_OUTDATED; + break; + default: + /* The script is broken ... */ + nps = D_UNKNOWN; + dev_err(DEV, "fence-peer helper broken, returned %d\n", (r>>8)&0xff); + return nps; + } + + dev_info(DEV, "fence-peer helper returned %d (%s)\n", + (r>>8) & 0xff, ex_to_string); + return nps; +} + + +int drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force) +{ + const int max_tries = 4; + int r = 0; + int try = 0; + int forced = 0; + union drbd_state mask, val; + enum drbd_disk_state nps; + + if (new_role == R_PRIMARY) + request_ping(mdev); /* Detect a dead peer ASAP */ + + mutex_lock(&mdev->state_mutex); + + mask.i = 0; mask.role = R_MASK; + val.i = 0; val.role = new_role; + + while (try++ < max_tries) { + r = _drbd_request_state(mdev, mask, val, CS_WAIT_COMPLETE); + + /* in case we first succeeded to outdate, + * but now suddenly could establish a connection */ + if (r == SS_CW_FAILED_BY_PEER && mask.pdsk != 0) { + val.pdsk = 0; + mask.pdsk = 0; + continue; + } + + if (r == SS_NO_UP_TO_DATE_DISK && force && + (mdev->state.disk == D_INCONSISTENT || + mdev->state.disk == D_OUTDATED)) { + mask.disk = D_MASK; + val.disk = D_UP_TO_DATE; + forced = 1; + continue; + } + + if (r == SS_NO_UP_TO_DATE_DISK && + mdev->state.disk == D_CONSISTENT && mask.pdsk == 0) { + D_ASSERT(mdev->state.pdsk == D_UNKNOWN); + nps = drbd_try_outdate_peer(mdev); + + if (nps == D_OUTDATED || nps == D_INCONSISTENT) { + val.disk = D_UP_TO_DATE; + mask.disk = D_MASK; + } + + val.pdsk = nps; + mask.pdsk = D_MASK; + + continue; + } + + if (r == SS_NOTHING_TO_DO) + goto fail; + if (r == SS_PRIMARY_NOP && mask.pdsk == 0) { + nps = drbd_try_outdate_peer(mdev); + + if (force && nps > D_OUTDATED) { + dev_warn(DEV, "Forced into split brain situation!\n"); + nps = D_OUTDATED; + } + + mask.pdsk = D_MASK; + val.pdsk = nps; + + continue; + } + if (r == SS_TWO_PRIMARIES) { + /* Maybe the peer is detected as dead very soon... + retry at most once more in this case. */ + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout((mdev->net_conf->ping_timeo+1)*HZ/10); + if (try < max_tries) + try = max_tries - 1; + continue; + } + if (r < SS_SUCCESS) { + r = _drbd_request_state(mdev, mask, val, + CS_VERBOSE + CS_WAIT_COMPLETE); + if (r < SS_SUCCESS) + goto fail; + } + break; + } + + if (r < SS_SUCCESS) + goto fail; + + if (forced) + dev_warn(DEV, "Forced to consider local data as UpToDate!\n"); + + /* Wait until nothing is on the fly :) */ + wait_event(mdev->misc_wait, atomic_read(&mdev->ap_pending_cnt) == 0); + + if (new_role == R_SECONDARY) { + set_disk_ro(mdev->vdisk, TRUE); + if (get_ldev(mdev)) { + mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; + put_ldev(mdev); + } + } else { + if (get_net_conf(mdev)) { + mdev->net_conf->want_lose = 0; + put_net_conf(mdev); + } + set_disk_ro(mdev->vdisk, FALSE); + if (get_ldev(mdev)) { + if (((mdev->state.conn < C_CONNECTED || + mdev->state.pdsk <= D_FAILED) + && mdev->ldev->md.uuid[UI_BITMAP] == 0) || forced) + drbd_uuid_new_current(mdev); + + mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1; + put_ldev(mdev); + } + } + + if ((new_role == R_SECONDARY) && get_ldev(mdev)) { + drbd_al_to_on_disk_bm(mdev); + put_ldev(mdev); + } + + if (mdev->state.conn >= C_WF_REPORT_PARAMS) { + /* if this was forced, we should consider sync */ + if (forced) + drbd_send_uuids(mdev); + drbd_send_state(mdev); + } + + drbd_md_sync(mdev); + + kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); + fail: + mutex_unlock(&mdev->state_mutex); + return r; +} + + +static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + struct primary primary_args; + + memset(&primary_args, 0, sizeof(struct primary)); + if (!primary_from_tags(mdev, nlp->tag_list, &primary_args)) { + reply->ret_code = ERR_MANDATORY_TAG; + return 0; + } + + reply->ret_code = + drbd_set_role(mdev, R_PRIMARY, primary_args.overwrite_peer); + + return 0; +} + +static int drbd_nl_secondary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + reply->ret_code = drbd_set_role(mdev, R_SECONDARY, 0); + + return 0; +} + +/* initializes the md.*_offset members, so we are able to find + * the on disk meta data */ +static void drbd_md_set_sector_offsets(struct drbd_conf *mdev, + struct drbd_backing_dev *bdev) +{ + sector_t md_size_sect = 0; + switch (bdev->dc.meta_dev_idx) { + default: + /* v07 style fixed size indexed meta data */ + bdev->md.md_size_sect = MD_RESERVED_SECT; + bdev->md.md_offset = drbd_md_ss__(mdev, bdev); + bdev->md.al_offset = MD_AL_OFFSET; + bdev->md.bm_offset = MD_BM_OFFSET; + break; + case DRBD_MD_INDEX_FLEX_EXT: + /* just occupy the full device; unit: sectors */ + bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev); + bdev->md.md_offset = 0; + bdev->md.al_offset = MD_AL_OFFSET; + bdev->md.bm_offset = MD_BM_OFFSET; + break; + case DRBD_MD_INDEX_INTERNAL: + case DRBD_MD_INDEX_FLEX_INT: + bdev->md.md_offset = drbd_md_ss__(mdev, bdev); + /* al size is still fixed */ + bdev->md.al_offset = -MD_AL_MAX_SIZE; + /* we need (slightly less than) ~ this much bitmap sectors: */ + md_size_sect = drbd_get_capacity(bdev->backing_bdev); + md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT); + md_size_sect = BM_SECT_TO_EXT(md_size_sect); + md_size_sect = ALIGN(md_size_sect, 8); + + /* plus the "drbd meta data super block", + * and the activity log; */ + md_size_sect += MD_BM_OFFSET; + + bdev->md.md_size_sect = md_size_sect; + /* bitmap offset is adjusted by 'super' block size */ + bdev->md.bm_offset = -md_size_sect + MD_AL_OFFSET; + break; + } +} + +char *ppsize(char *buf, unsigned long long size) +{ + /* Needs 9 bytes at max. */ + static char units[] = { 'K', 'M', 'G', 'T', 'P', 'E' }; + int base = 0; + while (size >= 10000) { + /* shift + round */ + size = (size >> 10) + !!(size & (1<<9)); + base++; + } + sprintf(buf, "%lu %cB", (long)size, units[base]); + + return buf; +} + +/* there is still a theoretical deadlock when called from receiver + * on an D_INCONSISTENT R_PRIMARY: + * remote READ does inc_ap_bio, receiver would need to receive answer + * packet from remote to dec_ap_bio again. + * receiver receive_sizes(), comes here, + * waits for ap_bio_cnt == 0. -> deadlock. + * but this cannot happen, actually, because: + * R_PRIMARY D_INCONSISTENT, and peer's disk is unreachable + * (not connected, or bad/no disk on peer): + * see drbd_fail_request_early, ap_bio_cnt is zero. + * R_PRIMARY D_INCONSISTENT, and C_SYNC_TARGET: + * peer may not initiate a resize. + */ +void drbd_suspend_io(struct drbd_conf *mdev) +{ + set_bit(SUSPEND_IO, &mdev->flags); + wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt)); +} + +void drbd_resume_io(struct drbd_conf *mdev) +{ + clear_bit(SUSPEND_IO, &mdev->flags); + wake_up(&mdev->misc_wait); +} + +/** + * drbd_determine_dev_size() - Sets the right device size obeying all constraints + * @mdev: DRBD device. + * + * Returns 0 on success, negative return values indicate errors. + * You should call drbd_md_sync() after calling this function. + */ +enum determine_dev_size drbd_determin_dev_size(struct drbd_conf *mdev) __must_hold(local) +{ + sector_t prev_first_sect, prev_size; /* previous meta location */ + sector_t la_size; + sector_t size; + char ppb[10]; + + int md_moved, la_size_changed; + enum determine_dev_size rv = unchanged; + + /* race: + * application request passes inc_ap_bio, + * but then cannot get an AL-reference. + * this function later may wait on ap_bio_cnt == 0. -> deadlock. + * + * to avoid that: + * Suspend IO right here. + * still lock the act_log to not trigger ASSERTs there. + */ + drbd_suspend_io(mdev); + + /* no wait necessary anymore, actually we could assert that */ + wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); + + prev_first_sect = drbd_md_first_sector(mdev->ldev); + prev_size = mdev->ldev->md.md_size_sect; + la_size = mdev->ldev->md.la_size_sect; + + /* TODO: should only be some assert here, not (re)init... */ + drbd_md_set_sector_offsets(mdev, mdev->ldev); + + size = drbd_new_dev_size(mdev, mdev->ldev); + + if (drbd_get_capacity(mdev->this_bdev) != size || + drbd_bm_capacity(mdev) != size) { + int err; + err = drbd_bm_resize(mdev, size); + if (unlikely(err)) { + /* currently there is only one error: ENOMEM! */ + size = drbd_bm_capacity(mdev)>>1; + if (size == 0) { + dev_err(DEV, "OUT OF MEMORY! " + "Could not allocate bitmap!\n"); + } else { + dev_err(DEV, "BM resizing failed. " + "Leaving size unchanged at size = %lu KB\n", + (unsigned long)size); + } + rv = dev_size_error; + } + /* racy, see comments above. */ + drbd_set_my_capacity(mdev, size); + mdev->ldev->md.la_size_sect = size; + dev_info(DEV, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), + (unsigned long long)size>>1); + } + if (rv == dev_size_error) + goto out; + + la_size_changed = (la_size != mdev->ldev->md.la_size_sect); + + md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev) + || prev_size != mdev->ldev->md.md_size_sect; + + if (la_size_changed || md_moved) { + drbd_al_shrink(mdev); /* All extents inactive. */ + dev_info(DEV, "Writing the whole bitmap, %s\n", + la_size_changed && md_moved ? "size changed and md moved" : + la_size_changed ? "size changed" : "md moved"); + rv = drbd_bitmap_io(mdev, &drbd_bm_write, "size changed"); /* does drbd_resume_io() ! */ + drbd_md_mark_dirty(mdev); + } + + if (size > la_size) + rv = grew; + if (size < la_size) + rv = shrunk; +out: + lc_unlock(mdev->act_log); + wake_up(&mdev->al_wait); + drbd_resume_io(mdev); + + return rv; +} + +sector_t +drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev) +{ + sector_t p_size = mdev->p_size; /* partner's disk size. */ + sector_t la_size = bdev->md.la_size_sect; /* last agreed size. */ + sector_t m_size; /* my size */ + sector_t u_size = bdev->dc.disk_size; /* size requested by user. */ + sector_t size = 0; + + m_size = drbd_get_max_capacity(bdev); + + if (p_size && m_size) { + size = min_t(sector_t, p_size, m_size); + } else { + if (la_size) { + size = la_size; + if (m_size && m_size < size) + size = m_size; + if (p_size && p_size < size) + size = p_size; + } else { + if (m_size) + size = m_size; + if (p_size) + size = p_size; + } + } + + if (size == 0) + dev_err(DEV, "Both nodes diskless!\n"); + + if (u_size) { + if (u_size > size) + dev_err(DEV, "Requested disk size is too big (%lu > %lu)\n", + (unsigned long)u_size>>1, (unsigned long)size>>1); + else + size = u_size; + } + + return size; +} + +/** + * drbd_check_al_size() - Ensures that the AL is of the right size + * @mdev: DRBD device. + * + * Returns -EBUSY if current al lru is still used, -ENOMEM when allocation + * failed, and 0 on success. You should call drbd_md_sync() after you called + * this function. + */ +static int drbd_check_al_size(struct drbd_conf *mdev) +{ + struct lru_cache *n, *t; + struct lc_element *e; + unsigned int in_use; + int i; + + ERR_IF(mdev->sync_conf.al_extents < 7) + mdev->sync_conf.al_extents = 127; + + if (mdev->act_log && + mdev->act_log->nr_elements == mdev->sync_conf.al_extents) + return 0; + + in_use = 0; + t = mdev->act_log; + n = lc_create("act_log", drbd_al_ext_cache, + mdev->sync_conf.al_extents, sizeof(struct lc_element), 0); + + if (n == NULL) { + dev_err(DEV, "Cannot allocate act_log lru!\n"); + return -ENOMEM; + } + spin_lock_irq(&mdev->al_lock); + if (t) { + for (i = 0; i < t->nr_elements; i++) { + e = lc_element_by_index(t, i); + if (e->refcnt) + dev_err(DEV, "refcnt(%d)==%d\n", + e->lc_number, e->refcnt); + in_use += e->refcnt; + } + } + if (!in_use) + mdev->act_log = n; + spin_unlock_irq(&mdev->al_lock); + if (in_use) { + dev_err(DEV, "Activity log still in use!\n"); + lc_destroy(n); + return -EBUSY; + } else { + if (t) + lc_destroy(t); + } + drbd_md_mark_dirty(mdev); /* we changed mdev->act_log->nr_elemens */ + return 0; +} + +void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_seg_s) __must_hold(local) +{ + struct request_queue * const q = mdev->rq_queue; + struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; + int max_segments = mdev->ldev->dc.max_bio_bvecs; + + if (b->merge_bvec_fn && !mdev->ldev->dc.use_bmbv) + max_seg_s = PAGE_SIZE; + + max_seg_s = min(queue_max_sectors(b) * queue_logical_block_size(b), max_seg_s); + + blk_queue_max_sectors(q, max_seg_s >> 9); + blk_queue_max_phys_segments(q, max_segments ? max_segments : MAX_PHYS_SEGMENTS); + blk_queue_max_hw_segments(q, max_segments ? max_segments : MAX_HW_SEGMENTS); + blk_queue_max_segment_size(q, max_seg_s); + blk_queue_logical_block_size(q, 512); + blk_queue_segment_boundary(q, PAGE_SIZE-1); + blk_stack_limits(&q->limits, &b->limits, 0); + + if (b->merge_bvec_fn) + dev_warn(DEV, "Backing device's merge_bvec_fn() = %p\n", + b->merge_bvec_fn); + dev_info(DEV, "max_segment_size ( = BIO size ) = %u\n", queue_max_segment_size(q)); + + if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) { + dev_info(DEV, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n", + q->backing_dev_info.ra_pages, + b->backing_dev_info.ra_pages); + q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages; + } +} + +/* serialize deconfig (worker exiting, doing cleanup) + * and reconfig (drbdsetup disk, drbdsetup net) + * + * wait for a potentially exiting worker, then restart it, + * or start a new one. + */ +static void drbd_reconfig_start(struct drbd_conf *mdev) +{ + wait_event(mdev->state_wait, !test_and_set_bit(CONFIG_PENDING, &mdev->flags)); + wait_event(mdev->state_wait, !test_bit(DEVICE_DYING, &mdev->flags)); + drbd_thread_start(&mdev->worker); +} + +/* if still unconfigured, stops worker again. + * if configured now, clears CONFIG_PENDING. + * wakes potential waiters */ +static void drbd_reconfig_done(struct drbd_conf *mdev) +{ + spin_lock_irq(&mdev->req_lock); + if (mdev->state.disk == D_DISKLESS && + mdev->state.conn == C_STANDALONE && + mdev->state.role == R_SECONDARY) { + set_bit(DEVICE_DYING, &mdev->flags); + drbd_thread_stop_nowait(&mdev->worker); + } else + clear_bit(CONFIG_PENDING, &mdev->flags); + spin_unlock_irq(&mdev->req_lock); + wake_up(&mdev->state_wait); +} + +/* does always return 0; + * interesting return code is in reply->ret_code */ +static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + enum drbd_ret_codes retcode; + enum determine_dev_size dd; + sector_t max_possible_sectors; + sector_t min_md_device_sectors; + struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */ + struct inode *inode, *inode2; + struct lru_cache *resync_lru = NULL; + union drbd_state ns, os; + int rv; + int cp_discovered = 0; + int logical_block_size; + + drbd_reconfig_start(mdev); + + /* if you want to reconfigure, please tear down first */ + if (mdev->state.disk > D_DISKLESS) { + retcode = ERR_DISK_CONFIGURED; + goto fail; + } + + /* allocation not in the IO path, cqueue thread context */ + nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL); + if (!nbc) { + retcode = ERR_NOMEM; + goto fail; + } + + nbc->dc.disk_size = DRBD_DISK_SIZE_SECT_DEF; + nbc->dc.on_io_error = DRBD_ON_IO_ERROR_DEF; + nbc->dc.fencing = DRBD_FENCING_DEF; + nbc->dc.max_bio_bvecs = DRBD_MAX_BIO_BVECS_DEF; + + if (!disk_conf_from_tags(mdev, nlp->tag_list, &nbc->dc)) { + retcode = ERR_MANDATORY_TAG; + goto fail; + } + + if (nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) { + retcode = ERR_MD_IDX_INVALID; + goto fail; + } + + nbc->lo_file = filp_open(nbc->dc.backing_dev, O_RDWR, 0); + if (IS_ERR(nbc->lo_file)) { + dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev, + PTR_ERR(nbc->lo_file)); + nbc->lo_file = NULL; + retcode = ERR_OPEN_DISK; + goto fail; + } + + inode = nbc->lo_file->f_dentry->d_inode; + + if (!S_ISBLK(inode->i_mode)) { + retcode = ERR_DISK_NOT_BDEV; + goto fail; + } + + nbc->md_file = filp_open(nbc->dc.meta_dev, O_RDWR, 0); + if (IS_ERR(nbc->md_file)) { + dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev, + PTR_ERR(nbc->md_file)); + nbc->md_file = NULL; + retcode = ERR_OPEN_MD_DISK; + goto fail; + } + + inode2 = nbc->md_file->f_dentry->d_inode; + + if (!S_ISBLK(inode2->i_mode)) { + retcode = ERR_MD_NOT_BDEV; + goto fail; + } + + nbc->backing_bdev = inode->i_bdev; + if (bd_claim(nbc->backing_bdev, mdev)) { + printk(KERN_ERR "drbd: bd_claim(%p,%p); failed [%p;%p;%u]\n", + nbc->backing_bdev, mdev, + nbc->backing_bdev->bd_holder, + nbc->backing_bdev->bd_contains->bd_holder, + nbc->backing_bdev->bd_holders); + retcode = ERR_BDCLAIM_DISK; + goto fail; + } + + resync_lru = lc_create("resync", drbd_bm_ext_cache, + 61, sizeof(struct bm_extent), + offsetof(struct bm_extent, lce)); + if (!resync_lru) { + retcode = ERR_NOMEM; + goto release_bdev_fail; + } + + /* meta_dev_idx >= 0: external fixed size, + * possibly multiple drbd sharing one meta device. + * TODO in that case, paranoia check that [md_bdev, meta_dev_idx] is + * not yet used by some other drbd minor! + * (if you use drbd.conf + drbdadm, + * that should check it for you already; but if you don't, or someone + * fooled it, we need to double check here) */ + nbc->md_bdev = inode2->i_bdev; + if (bd_claim(nbc->md_bdev, (nbc->dc.meta_dev_idx < 0) ? (void *)mdev + : (void *) drbd_m_holder)) { + retcode = ERR_BDCLAIM_MD_DISK; + goto release_bdev_fail; + } + + if ((nbc->backing_bdev == nbc->md_bdev) != + (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL || + nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) { + retcode = ERR_MD_IDX_INVALID; + goto release_bdev2_fail; + } + + /* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */ + drbd_md_set_sector_offsets(mdev, nbc); + + if (drbd_get_max_capacity(nbc) < nbc->dc.disk_size) { + dev_err(DEV, "max capacity %llu smaller than disk size %llu\n", + (unsigned long long) drbd_get_max_capacity(nbc), + (unsigned long long) nbc->dc.disk_size); + retcode = ERR_DISK_TO_SMALL; + goto release_bdev2_fail; + } + + if (nbc->dc.meta_dev_idx < 0) { + max_possible_sectors = DRBD_MAX_SECTORS_FLEX; + /* at least one MB, otherwise it does not make sense */ + min_md_device_sectors = (2<<10); + } else { + max_possible_sectors = DRBD_MAX_SECTORS; + min_md_device_sectors = MD_RESERVED_SECT * (nbc->dc.meta_dev_idx + 1); + } + + if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) { + retcode = ERR_MD_DISK_TO_SMALL; + dev_warn(DEV, "refusing attach: md-device too small, " + "at least %llu sectors needed for this meta-disk type\n", + (unsigned long long) min_md_device_sectors); + goto release_bdev2_fail; + } + + /* Make sure the new disk is big enough + * (we may currently be R_PRIMARY with no local disk...) */ + if (drbd_get_max_capacity(nbc) < + drbd_get_capacity(mdev->this_bdev)) { + retcode = ERR_DISK_TO_SMALL; + goto release_bdev2_fail; + } + + nbc->known_size = drbd_get_capacity(nbc->backing_bdev); + + if (nbc->known_size > max_possible_sectors) { + dev_warn(DEV, "==> truncating very big lower level device " + "to currently maximum possible %llu sectors <==\n", + (unsigned long long) max_possible_sectors); + if (nbc->dc.meta_dev_idx >= 0) + dev_warn(DEV, "==>> using internal or flexible " + "meta data may help <<==\n"); + } + + drbd_suspend_io(mdev); + /* also wait for the last barrier ack. */ + wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt)); + /* and for any other previously queued work */ + drbd_flush_workqueue(mdev); + + retcode = _drbd_request_state(mdev, NS(disk, D_ATTACHING), CS_VERBOSE); + drbd_resume_io(mdev); + if (retcode < SS_SUCCESS) + goto release_bdev2_fail; + + if (!get_ldev_if_state(mdev, D_ATTACHING)) + goto force_diskless; + + drbd_md_set_sector_offsets(mdev, nbc); + + if (!mdev->bitmap) { + if (drbd_bm_init(mdev)) { + retcode = ERR_NOMEM; + goto force_diskless_dec; + } + } + + retcode = drbd_md_read(mdev, nbc); + if (retcode != NO_ERROR) + goto force_diskless_dec; + + if (mdev->state.conn < C_CONNECTED && + mdev->state.role == R_PRIMARY && + (mdev->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) { + dev_err(DEV, "Can only attach to data with current UUID=%016llX\n", + (unsigned long long)mdev->ed_uuid); + retcode = ERR_DATA_NOT_CURRENT; + goto force_diskless_dec; + } + + /* Since we are diskless, fix the activity log first... */ + if (drbd_check_al_size(mdev)) { + retcode = ERR_NOMEM; + goto force_diskless_dec; + } + + /* Prevent shrinking of consistent devices ! */ + if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && + drbd_new_dev_size(mdev, nbc) < nbc->md.la_size_sect) { + dev_warn(DEV, "refusing to truncate a consistent device\n"); + retcode = ERR_DISK_TO_SMALL; + goto force_diskless_dec; + } + + if (!drbd_al_read_log(mdev, nbc)) { + retcode = ERR_IO_MD_DISK; + goto force_diskless_dec; + } + + /* allocate a second IO page if logical_block_size != 512 */ + logical_block_size = bdev_logical_block_size(nbc->md_bdev); + if (logical_block_size == 0) + logical_block_size = MD_SECTOR_SIZE; + + if (logical_block_size != MD_SECTOR_SIZE) { + if (!mdev->md_io_tmpp) { + struct page *page = alloc_page(GFP_NOIO); + if (!page) + goto force_diskless_dec; + + dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n", + logical_block_size, MD_SECTOR_SIZE); + dev_warn(DEV, "Workaround engaged (has performance impact).\n"); + + mdev->md_io_tmpp = page; + } + } + + /* Reset the "barriers don't work" bits here, then force meta data to + * be written, to ensure we determine if barriers are supported. */ + if (nbc->dc.no_md_flush) + set_bit(MD_NO_BARRIER, &mdev->flags); + else + clear_bit(MD_NO_BARRIER, &mdev->flags); + + /* Point of no return reached. + * Devices and memory are no longer released by error cleanup below. + * now mdev takes over responsibility, and the state engine should + * clean it up somewhere. */ + D_ASSERT(mdev->ldev == NULL); + mdev->ldev = nbc; + mdev->resync = resync_lru; + nbc = NULL; + resync_lru = NULL; + + mdev->write_ordering = WO_bio_barrier; + drbd_bump_write_ordering(mdev, WO_bio_barrier); + + if (drbd_md_test_flag(mdev->ldev, MDF_CRASHED_PRIMARY)) + set_bit(CRASHED_PRIMARY, &mdev->flags); + else + clear_bit(CRASHED_PRIMARY, &mdev->flags); + + if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND)) { + set_bit(CRASHED_PRIMARY, &mdev->flags); + cp_discovered = 1; + } + + mdev->send_cnt = 0; + mdev->recv_cnt = 0; + mdev->read_cnt = 0; + mdev->writ_cnt = 0; + + drbd_setup_queue_param(mdev, DRBD_MAX_SEGMENT_SIZE); + + /* If I am currently not R_PRIMARY, + * but meta data primary indicator is set, + * I just now recover from a hard crash, + * and have been R_PRIMARY before that crash. + * + * Now, if I had no connection before that crash + * (have been degraded R_PRIMARY), chances are that + * I won't find my peer now either. + * + * In that case, and _only_ in that case, + * we use the degr-wfc-timeout instead of the default, + * so we can automatically recover from a crash of a + * degraded but active "cluster" after a certain timeout. + */ + clear_bit(USE_DEGR_WFC_T, &mdev->flags); + if (mdev->state.role != R_PRIMARY && + drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) && + !drbd_md_test_flag(mdev->ldev, MDF_CONNECTED_IND)) + set_bit(USE_DEGR_WFC_T, &mdev->flags); + + dd = drbd_determin_dev_size(mdev); + if (dd == dev_size_error) { + retcode = ERR_NOMEM_BITMAP; + goto force_diskless_dec; + } else if (dd == grew) + set_bit(RESYNC_AFTER_NEG, &mdev->flags); + + if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) { + dev_info(DEV, "Assuming that all blocks are out of sync " + "(aka FullSync)\n"); + if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from attaching")) { + retcode = ERR_IO_MD_DISK; + goto force_diskless_dec; + } + } else { + if (drbd_bitmap_io(mdev, &drbd_bm_read, "read from attaching") < 0) { + retcode = ERR_IO_MD_DISK; + goto force_diskless_dec; + } + } + + if (cp_discovered) { + drbd_al_apply_to_bm(mdev); + drbd_al_to_on_disk_bm(mdev); + } + + spin_lock_irq(&mdev->req_lock); + os = mdev->state; + ns.i = os.i; + /* If MDF_CONSISTENT is not set go into inconsistent state, + otherwise investigate MDF_WasUpToDate... + If MDF_WAS_UP_TO_DATE is not set go into D_OUTDATED disk state, + otherwise into D_CONSISTENT state. + */ + if (drbd_md_test_flag(mdev->ldev, MDF_CONSISTENT)) { + if (drbd_md_test_flag(mdev->ldev, MDF_WAS_UP_TO_DATE)) + ns.disk = D_CONSISTENT; + else + ns.disk = D_OUTDATED; + } else { + ns.disk = D_INCONSISTENT; + } + + if (drbd_md_test_flag(mdev->ldev, MDF_PEER_OUT_DATED)) + ns.pdsk = D_OUTDATED; + + if ( ns.disk == D_CONSISTENT && + (ns.pdsk == D_OUTDATED || mdev->ldev->dc.fencing == FP_DONT_CARE)) + ns.disk = D_UP_TO_DATE; + + /* All tests on MDF_PRIMARY_IND, MDF_CONNECTED_IND, + MDF_CONSISTENT and MDF_WAS_UP_TO_DATE must happen before + this point, because drbd_request_state() modifies these + flags. */ + + /* In case we are C_CONNECTED postpone any decision on the new disk + state after the negotiation phase. */ + if (mdev->state.conn == C_CONNECTED) { + mdev->new_state_tmp.i = ns.i; + ns.i = os.i; + ns.disk = D_NEGOTIATING; + } + + rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL); + ns = mdev->state; + spin_unlock_irq(&mdev->req_lock); + + if (rv < SS_SUCCESS) + goto force_diskless_dec; + + if (mdev->state.role == R_PRIMARY) + mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1; + else + mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; + + drbd_md_mark_dirty(mdev); + drbd_md_sync(mdev); + + kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); + put_ldev(mdev); + reply->ret_code = retcode; + drbd_reconfig_done(mdev); + return 0; + + force_diskless_dec: + put_ldev(mdev); + force_diskless: + drbd_force_state(mdev, NS(disk, D_DISKLESS)); + drbd_md_sync(mdev); + release_bdev2_fail: + if (nbc) + bd_release(nbc->md_bdev); + release_bdev_fail: + if (nbc) + bd_release(nbc->backing_bdev); + fail: + if (nbc) { + if (nbc->lo_file) + fput(nbc->lo_file); + if (nbc->md_file) + fput(nbc->md_file); + kfree(nbc); + } + lc_destroy(resync_lru); + + reply->ret_code = retcode; + drbd_reconfig_done(mdev); + return 0; +} + +static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS)); + return 0; +} + +static int drbd_nl_net_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int i, ns; + enum drbd_ret_codes retcode; + struct net_conf *new_conf = NULL; + struct crypto_hash *tfm = NULL; + struct crypto_hash *integrity_w_tfm = NULL; + struct crypto_hash *integrity_r_tfm = NULL; + struct hlist_head *new_tl_hash = NULL; + struct hlist_head *new_ee_hash = NULL; + struct drbd_conf *odev; + char hmac_name[CRYPTO_MAX_ALG_NAME]; + void *int_dig_out = NULL; + void *int_dig_in = NULL; + void *int_dig_vv = NULL; + struct sockaddr *new_my_addr, *new_peer_addr, *taken_addr; + + drbd_reconfig_start(mdev); + + if (mdev->state.conn > C_STANDALONE) { + retcode = ERR_NET_CONFIGURED; + goto fail; + } + + /* allocation not in the IO path, cqueue thread context */ + new_conf = kmalloc(sizeof(struct net_conf), GFP_KERNEL); + if (!new_conf) { + retcode = ERR_NOMEM; + goto fail; + } + + memset(new_conf, 0, sizeof(struct net_conf)); + new_conf->timeout = DRBD_TIMEOUT_DEF; + new_conf->try_connect_int = DRBD_CONNECT_INT_DEF; + new_conf->ping_int = DRBD_PING_INT_DEF; + new_conf->max_epoch_size = DRBD_MAX_EPOCH_SIZE_DEF; + new_conf->max_buffers = DRBD_MAX_BUFFERS_DEF; + new_conf->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF; + new_conf->sndbuf_size = DRBD_SNDBUF_SIZE_DEF; + new_conf->rcvbuf_size = DRBD_RCVBUF_SIZE_DEF; + new_conf->ko_count = DRBD_KO_COUNT_DEF; + new_conf->after_sb_0p = DRBD_AFTER_SB_0P_DEF; + new_conf->after_sb_1p = DRBD_AFTER_SB_1P_DEF; + new_conf->after_sb_2p = DRBD_AFTER_SB_2P_DEF; + new_conf->want_lose = 0; + new_conf->two_primaries = 0; + new_conf->wire_protocol = DRBD_PROT_C; + new_conf->ping_timeo = DRBD_PING_TIMEO_DEF; + new_conf->rr_conflict = DRBD_RR_CONFLICT_DEF; + + if (!net_conf_from_tags(mdev, nlp->tag_list, new_conf)) { + retcode = ERR_MANDATORY_TAG; + goto fail; + } + + if (new_conf->two_primaries + && (new_conf->wire_protocol != DRBD_PROT_C)) { + retcode = ERR_NOT_PROTO_C; + goto fail; + }; + + if (mdev->state.role == R_PRIMARY && new_conf->want_lose) { + retcode = ERR_DISCARD; + goto fail; + } + + retcode = NO_ERROR; + + new_my_addr = (struct sockaddr *)&new_conf->my_addr; + new_peer_addr = (struct sockaddr *)&new_conf->peer_addr; + for (i = 0; i < minor_count; i++) { + odev = minor_to_mdev(i); + if (!odev || odev == mdev) + continue; + if (get_net_conf(odev)) { + taken_addr = (struct sockaddr *)&odev->net_conf->my_addr; + if (new_conf->my_addr_len == odev->net_conf->my_addr_len && + !memcmp(new_my_addr, taken_addr, new_conf->my_addr_len)) + retcode = ERR_LOCAL_ADDR; + + taken_addr = (struct sockaddr *)&odev->net_conf->peer_addr; + if (new_conf->peer_addr_len == odev->net_conf->peer_addr_len && + !memcmp(new_peer_addr, taken_addr, new_conf->peer_addr_len)) + retcode = ERR_PEER_ADDR; + + put_net_conf(odev); + if (retcode != NO_ERROR) + goto fail; + } + } + + if (new_conf->cram_hmac_alg[0] != 0) { + snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", + new_conf->cram_hmac_alg); + tfm = crypto_alloc_hash(hmac_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) { + tfm = NULL; + retcode = ERR_AUTH_ALG; + goto fail; + } + + if (crypto_tfm_alg_type(crypto_hash_tfm(tfm)) + != CRYPTO_ALG_TYPE_HASH) { + retcode = ERR_AUTH_ALG_ND; + goto fail; + } + } + + if (new_conf->integrity_alg[0]) { + integrity_w_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(integrity_w_tfm)) { + integrity_w_tfm = NULL; + retcode=ERR_INTEGRITY_ALG; + goto fail; + } + + if (!drbd_crypto_is_hash(crypto_hash_tfm(integrity_w_tfm))) { + retcode=ERR_INTEGRITY_ALG_ND; + goto fail; + } + + integrity_r_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(integrity_r_tfm)) { + integrity_r_tfm = NULL; + retcode=ERR_INTEGRITY_ALG; + goto fail; + } + } + + ns = new_conf->max_epoch_size/8; + if (mdev->tl_hash_s != ns) { + new_tl_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL); + if (!new_tl_hash) { + retcode = ERR_NOMEM; + goto fail; + } + } + + ns = new_conf->max_buffers/8; + if (new_conf->two_primaries && (mdev->ee_hash_s != ns)) { + new_ee_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL); + if (!new_ee_hash) { + retcode = ERR_NOMEM; + goto fail; + } + } + + ((char *)new_conf->shared_secret)[SHARED_SECRET_MAX-1] = 0; + + if (integrity_w_tfm) { + i = crypto_hash_digestsize(integrity_w_tfm); + int_dig_out = kmalloc(i, GFP_KERNEL); + if (!int_dig_out) { + retcode = ERR_NOMEM; + goto fail; + } + int_dig_in = kmalloc(i, GFP_KERNEL); + if (!int_dig_in) { + retcode = ERR_NOMEM; + goto fail; + } + int_dig_vv = kmalloc(i, GFP_KERNEL); + if (!int_dig_vv) { + retcode = ERR_NOMEM; + goto fail; + } + } + + if (!mdev->bitmap) { + if(drbd_bm_init(mdev)) { + retcode = ERR_NOMEM; + goto fail; + } + } + + spin_lock_irq(&mdev->req_lock); + if (mdev->net_conf != NULL) { + retcode = ERR_NET_CONFIGURED; + spin_unlock_irq(&mdev->req_lock); + goto fail; + } + mdev->net_conf = new_conf; + + mdev->send_cnt = 0; + mdev->recv_cnt = 0; + + if (new_tl_hash) { + kfree(mdev->tl_hash); + mdev->tl_hash_s = mdev->net_conf->max_epoch_size/8; + mdev->tl_hash = new_tl_hash; + } + + if (new_ee_hash) { + kfree(mdev->ee_hash); + mdev->ee_hash_s = mdev->net_conf->max_buffers/8; + mdev->ee_hash = new_ee_hash; + } + + crypto_free_hash(mdev->cram_hmac_tfm); + mdev->cram_hmac_tfm = tfm; + + crypto_free_hash(mdev->integrity_w_tfm); + mdev->integrity_w_tfm = integrity_w_tfm; + + crypto_free_hash(mdev->integrity_r_tfm); + mdev->integrity_r_tfm = integrity_r_tfm; + + kfree(mdev->int_dig_out); + kfree(mdev->int_dig_in); + kfree(mdev->int_dig_vv); + mdev->int_dig_out=int_dig_out; + mdev->int_dig_in=int_dig_in; + mdev->int_dig_vv=int_dig_vv; + spin_unlock_irq(&mdev->req_lock); + + retcode = _drbd_request_state(mdev, NS(conn, C_UNCONNECTED), CS_VERBOSE); + + kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); + reply->ret_code = retcode; + drbd_reconfig_done(mdev); + return 0; + +fail: + kfree(int_dig_out); + kfree(int_dig_in); + kfree(int_dig_vv); + crypto_free_hash(tfm); + crypto_free_hash(integrity_w_tfm); + crypto_free_hash(integrity_r_tfm); + kfree(new_tl_hash); + kfree(new_ee_hash); + kfree(new_conf); + + reply->ret_code = retcode; + drbd_reconfig_done(mdev); + return 0; +} + +static int drbd_nl_disconnect(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode; + + retcode = _drbd_request_state(mdev, NS(conn, C_DISCONNECTING), CS_ORDERED); + + if (retcode == SS_NOTHING_TO_DO) + goto done; + else if (retcode == SS_ALREADY_STANDALONE) + goto done; + else if (retcode == SS_PRIMARY_NOP) { + /* Our statche checking code wants to see the peer outdated. */ + retcode = drbd_request_state(mdev, NS2(conn, C_DISCONNECTING, + pdsk, D_OUTDATED)); + } else if (retcode == SS_CW_FAILED_BY_PEER) { + /* The peer probably wants to see us outdated. */ + retcode = _drbd_request_state(mdev, NS2(conn, C_DISCONNECTING, + disk, D_OUTDATED), + CS_ORDERED); + if (retcode == SS_IS_DISKLESS || retcode == SS_LOWER_THAN_OUTDATED) { + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + retcode = SS_SUCCESS; + } + } + + if (retcode < SS_SUCCESS) + goto fail; + + if (wait_event_interruptible(mdev->state_wait, + mdev->state.conn != C_DISCONNECTING)) { + /* Do not test for mdev->state.conn == C_STANDALONE, since + someone else might connect us in the mean time! */ + retcode = ERR_INTR; + goto fail; + } + + done: + retcode = NO_ERROR; + fail: + drbd_md_sync(mdev); + reply->ret_code = retcode; + return 0; +} + +void resync_after_online_grow(struct drbd_conf *mdev) +{ + int iass; /* I am sync source */ + + dev_info(DEV, "Resync of new storage after online grow\n"); + if (mdev->state.role != mdev->state.peer) + iass = (mdev->state.role == R_PRIMARY); + else + iass = test_bit(DISCARD_CONCURRENT, &mdev->flags); + + if (iass) + drbd_start_resync(mdev, C_SYNC_SOURCE); + else + _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE); +} + +static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + struct resize rs; + int retcode = NO_ERROR; + int ldsc = 0; /* local disk size changed */ + enum determine_dev_size dd; + + memset(&rs, 0, sizeof(struct resize)); + if (!resize_from_tags(mdev, nlp->tag_list, &rs)) { + retcode = ERR_MANDATORY_TAG; + goto fail; + } + + if (mdev->state.conn > C_CONNECTED) { + retcode = ERR_RESIZE_RESYNC; + goto fail; + } + + if (mdev->state.role == R_SECONDARY && + mdev->state.peer == R_SECONDARY) { + retcode = ERR_NO_PRIMARY; + goto fail; + } + + if (!get_ldev(mdev)) { + retcode = ERR_NO_DISK; + goto fail; + } + + if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) { + mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev); + ldsc = 1; + } + + mdev->ldev->dc.disk_size = (sector_t)rs.resize_size; + dd = drbd_determin_dev_size(mdev); + drbd_md_sync(mdev); + put_ldev(mdev); + if (dd == dev_size_error) { + retcode = ERR_NOMEM_BITMAP; + goto fail; + } + + if (mdev->state.conn == C_CONNECTED && (dd != unchanged || ldsc)) { + if (dd == grew) + set_bit(RESIZE_PENDING, &mdev->flags); + + drbd_send_uuids(mdev); + drbd_send_sizes(mdev, 1); + } + + fail: + reply->ret_code = retcode; + return 0; +} + +static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode = NO_ERROR; + int err; + int ovr; /* online verify running */ + int rsr; /* re-sync running */ + struct crypto_hash *verify_tfm = NULL; + struct crypto_hash *csums_tfm = NULL; + struct syncer_conf sc; + cpumask_var_t new_cpu_mask; + + if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL)) { + retcode = ERR_NOMEM; + goto fail; + } + + if (nlp->flags & DRBD_NL_SET_DEFAULTS) { + memset(&sc, 0, sizeof(struct syncer_conf)); + sc.rate = DRBD_RATE_DEF; + sc.after = DRBD_AFTER_DEF; + sc.al_extents = DRBD_AL_EXTENTS_DEF; + } else + memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf)); + + if (!syncer_conf_from_tags(mdev, nlp->tag_list, &sc)) { + retcode = ERR_MANDATORY_TAG; + goto fail; + } + + /* re-sync running */ + rsr = ( mdev->state.conn == C_SYNC_SOURCE || + mdev->state.conn == C_SYNC_TARGET || + mdev->state.conn == C_PAUSED_SYNC_S || + mdev->state.conn == C_PAUSED_SYNC_T ); + + if (rsr && strcmp(sc.csums_alg, mdev->sync_conf.csums_alg)) { + retcode = ERR_CSUMS_RESYNC_RUNNING; + goto fail; + } + + if (!rsr && sc.csums_alg[0]) { + csums_tfm = crypto_alloc_hash(sc.csums_alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(csums_tfm)) { + csums_tfm = NULL; + retcode = ERR_CSUMS_ALG; + goto fail; + } + + if (!drbd_crypto_is_hash(crypto_hash_tfm(csums_tfm))) { + retcode = ERR_CSUMS_ALG_ND; + goto fail; + } + } + + /* online verify running */ + ovr = (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T); + + if (ovr) { + if (strcmp(sc.verify_alg, mdev->sync_conf.verify_alg)) { + retcode = ERR_VERIFY_RUNNING; + goto fail; + } + } + + if (!ovr && sc.verify_alg[0]) { + verify_tfm = crypto_alloc_hash(sc.verify_alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(verify_tfm)) { + verify_tfm = NULL; + retcode = ERR_VERIFY_ALG; + goto fail; + } + + if (!drbd_crypto_is_hash(crypto_hash_tfm(verify_tfm))) { + retcode = ERR_VERIFY_ALG_ND; + goto fail; + } + } + + /* silently ignore cpu mask on UP kernel */ + if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) { + err = __bitmap_parse(sc.cpu_mask, 32, 0, + cpumask_bits(new_cpu_mask), nr_cpu_ids); + if (err) { + dev_warn(DEV, "__bitmap_parse() failed with %d\n", err); + retcode = ERR_CPU_MASK_PARSE; + goto fail; + } + } + + ERR_IF (sc.rate < 1) sc.rate = 1; + ERR_IF (sc.al_extents < 7) sc.al_extents = 127; /* arbitrary minimum */ +#define AL_MAX ((MD_AL_MAX_SIZE-1) * AL_EXTENTS_PT) + if (sc.al_extents > AL_MAX) { + dev_err(DEV, "sc.al_extents > %d\n", AL_MAX); + sc.al_extents = AL_MAX; + } +#undef AL_MAX + + /* most sanity checks done, try to assign the new sync-after + * dependency. need to hold the global lock in there, + * to avoid a race in the dependency loop check. */ + retcode = drbd_alter_sa(mdev, sc.after); + if (retcode != NO_ERROR) + goto fail; + + /* ok, assign the rest of it as well. + * lock against receive_SyncParam() */ + spin_lock(&mdev->peer_seq_lock); + mdev->sync_conf = sc; + + if (!rsr) { + crypto_free_hash(mdev->csums_tfm); + mdev->csums_tfm = csums_tfm; + csums_tfm = NULL; + } + + if (!ovr) { + crypto_free_hash(mdev->verify_tfm); + mdev->verify_tfm = verify_tfm; + verify_tfm = NULL; + } + spin_unlock(&mdev->peer_seq_lock); + + if (get_ldev(mdev)) { + wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); + drbd_al_shrink(mdev); + err = drbd_check_al_size(mdev); + lc_unlock(mdev->act_log); + wake_up(&mdev->al_wait); + + put_ldev(mdev); + drbd_md_sync(mdev); + + if (err) { + retcode = ERR_NOMEM; + goto fail; + } + } + + if (mdev->state.conn >= C_CONNECTED) + drbd_send_sync_param(mdev, &sc); + + if (!cpumask_equal(mdev->cpu_mask, new_cpu_mask)) { + cpumask_copy(mdev->cpu_mask, new_cpu_mask); + drbd_calc_cpu_mask(mdev); + mdev->receiver.reset_cpu_mask = 1; + mdev->asender.reset_cpu_mask = 1; + mdev->worker.reset_cpu_mask = 1; + } + + kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); +fail: + free_cpumask_var(new_cpu_mask); + crypto_free_hash(csums_tfm); + crypto_free_hash(verify_tfm); + reply->ret_code = retcode; + return 0; +} + +static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode; + + retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED); + + if (retcode < SS_SUCCESS && retcode != SS_NEED_CONNECTION) + retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T)); + + while (retcode == SS_NEED_CONNECTION) { + spin_lock_irq(&mdev->req_lock); + if (mdev->state.conn < C_CONNECTED) + retcode = _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_VERBOSE, NULL); + spin_unlock_irq(&mdev->req_lock); + + if (retcode != SS_NEED_CONNECTION) + break; + + retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T)); + } + + reply->ret_code = retcode; + return 0; +} + +static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + + reply->ret_code = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S)); + + return 0; +} + +static int drbd_nl_pause_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode = NO_ERROR; + + if (drbd_request_state(mdev, NS(user_isp, 1)) == SS_NOTHING_TO_DO) + retcode = ERR_PAUSE_IS_SET; + + reply->ret_code = retcode; + return 0; +} + +static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode = NO_ERROR; + + if (drbd_request_state(mdev, NS(user_isp, 0)) == SS_NOTHING_TO_DO) + retcode = ERR_PAUSE_IS_CLEAR; + + reply->ret_code = retcode; + return 0; +} + +static int drbd_nl_suspend_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + reply->ret_code = drbd_request_state(mdev, NS(susp, 1)); + + return 0; +} + +static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + reply->ret_code = drbd_request_state(mdev, NS(susp, 0)); + return 0; +} + +static int drbd_nl_outdate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + reply->ret_code = drbd_request_state(mdev, NS(disk, D_OUTDATED)); + return 0; +} + +static int drbd_nl_get_config(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + unsigned short *tl; + + tl = reply->tag_list; + + if (get_ldev(mdev)) { + tl = disk_conf_to_tags(mdev, &mdev->ldev->dc, tl); + put_ldev(mdev); + } + + if (get_net_conf(mdev)) { + tl = net_conf_to_tags(mdev, mdev->net_conf, tl); + put_net_conf(mdev); + } + tl = syncer_conf_to_tags(mdev, &mdev->sync_conf, tl); + + put_unaligned(TT_END, tl++); /* Close the tag list */ + + return (int)((char *)tl - (char *)reply->tag_list); +} + +static int drbd_nl_get_state(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + unsigned short *tl = reply->tag_list; + union drbd_state s = mdev->state; + unsigned long rs_left; + unsigned int res; + + tl = get_state_to_tags(mdev, (struct get_state *)&s, tl); + + /* no local ref, no bitmap, no syncer progress. */ + if (s.conn >= C_SYNC_SOURCE && s.conn <= C_PAUSED_SYNC_T) { + if (get_ldev(mdev)) { + drbd_get_syncer_progress(mdev, &rs_left, &res); + tl = tl_add_int(tl, T_sync_progress, &res); + put_ldev(mdev); + } + } + put_unaligned(TT_END, tl++); /* Close the tag list */ + + return (int)((char *)tl - (char *)reply->tag_list); +} + +static int drbd_nl_get_uuids(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + unsigned short *tl; + + tl = reply->tag_list; + + if (get_ldev(mdev)) { + tl = tl_add_blob(tl, T_uuids, mdev->ldev->md.uuid, UI_SIZE*sizeof(u64)); + tl = tl_add_int(tl, T_uuids_flags, &mdev->ldev->md.flags); + put_ldev(mdev); + } + put_unaligned(TT_END, tl++); /* Close the tag list */ + + return (int)((char *)tl - (char *)reply->tag_list); +} + +/** + * drbd_nl_get_timeout_flag() - Used by drbdsetup to find out which timeout value to use + * @mdev: DRBD device. + * @nlp: Netlink/connector packet from drbdsetup + * @reply: Reply packet for drbdsetup + */ +static int drbd_nl_get_timeout_flag(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + unsigned short *tl; + char rv; + + tl = reply->tag_list; + + rv = mdev->state.pdsk == D_OUTDATED ? UT_PEER_OUTDATED : + test_bit(USE_DEGR_WFC_T, &mdev->flags) ? UT_DEGRADED : UT_DEFAULT; + + tl = tl_add_blob(tl, T_use_degraded, &rv, sizeof(rv)); + put_unaligned(TT_END, tl++); /* Close the tag list */ + + return (int)((char *)tl - (char *)reply->tag_list); +} + +static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + /* default to resume from last known position, if possible */ + struct start_ov args = + { .start_sector = mdev->ov_start_sector }; + + if (!start_ov_from_tags(mdev, nlp->tag_list, &args)) { + reply->ret_code = ERR_MANDATORY_TAG; + return 0; + } + /* w_make_ov_request expects position to be aligned */ + mdev->ov_start_sector = args.start_sector & ~BM_SECT_PER_BIT; + reply->ret_code = drbd_request_state(mdev,NS(conn,C_VERIFY_S)); + return 0; +} + + +static int drbd_nl_new_c_uuid(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, + struct drbd_nl_cfg_reply *reply) +{ + int retcode = NO_ERROR; + int skip_initial_sync = 0; + int err; + + struct new_c_uuid args; + + memset(&args, 0, sizeof(struct new_c_uuid)); + if (!new_c_uuid_from_tags(mdev, nlp->tag_list, &args)) { + reply->ret_code = ERR_MANDATORY_TAG; + return 0; + } + + mutex_lock(&mdev->state_mutex); /* Protects us against serialized state changes. */ + + if (!get_ldev(mdev)) { + retcode = ERR_NO_DISK; + goto out; + } + + /* this is "skip initial sync", assume to be clean */ + if (mdev->state.conn == C_CONNECTED && mdev->agreed_pro_version >= 90 && + mdev->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED && args.clear_bm) { + dev_info(DEV, "Preparing to skip initial sync\n"); + skip_initial_sync = 1; + } else if (mdev->state.conn != C_STANDALONE) { + retcode = ERR_CONNECTED; + goto out_dec; + } + + drbd_uuid_set(mdev, UI_BITMAP, 0); /* Rotate UI_BITMAP to History 1, etc... */ + drbd_uuid_new_current(mdev); /* New current, previous to UI_BITMAP */ + + if (args.clear_bm) { + err = drbd_bitmap_io(mdev, &drbd_bmio_clear_n_write, "clear_n_write from new_c_uuid"); + if (err) { + dev_err(DEV, "Writing bitmap failed with %d\n",err); + retcode = ERR_IO_MD_DISK; + } + if (skip_initial_sync) { + drbd_send_uuids_skip_initial_sync(mdev); + _drbd_uuid_set(mdev, UI_BITMAP, 0); + spin_lock_irq(&mdev->req_lock); + _drbd_set_state(_NS2(mdev, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE), + CS_VERBOSE, NULL); + spin_unlock_irq(&mdev->req_lock); + } + } + + drbd_md_sync(mdev); +out_dec: + put_ldev(mdev); +out: + mutex_unlock(&mdev->state_mutex); + + reply->ret_code = retcode; + return 0; +} + +static struct drbd_conf *ensure_mdev(struct drbd_nl_cfg_req *nlp) +{ + struct drbd_conf *mdev; + + if (nlp->drbd_minor >= minor_count) + return NULL; + + mdev = minor_to_mdev(nlp->drbd_minor); + + if (!mdev && (nlp->flags & DRBD_NL_CREATE_DEVICE)) { + struct gendisk *disk = NULL; + mdev = drbd_new_device(nlp->drbd_minor); + + spin_lock_irq(&drbd_pp_lock); + if (minor_table[nlp->drbd_minor] == NULL) { + minor_table[nlp->drbd_minor] = mdev; + disk = mdev->vdisk; + mdev = NULL; + } /* else: we lost the race */ + spin_unlock_irq(&drbd_pp_lock); + + if (disk) /* we won the race above */ + /* in case we ever add a drbd_delete_device(), + * don't forget the del_gendisk! */ + add_disk(disk); + else /* we lost the race above */ + drbd_free_mdev(mdev); + + mdev = minor_to_mdev(nlp->drbd_minor); + } + + return mdev; +} + +struct cn_handler_struct { + int (*function)(struct drbd_conf *, + struct drbd_nl_cfg_req *, + struct drbd_nl_cfg_reply *); + int reply_body_size; +}; + +static struct cn_handler_struct cnd_table[] = { + [ P_primary ] = { &drbd_nl_primary, 0 }, + [ P_secondary ] = { &drbd_nl_secondary, 0 }, + [ P_disk_conf ] = { &drbd_nl_disk_conf, 0 }, + [ P_detach ] = { &drbd_nl_detach, 0 }, + [ P_net_conf ] = { &drbd_nl_net_conf, 0 }, + [ P_disconnect ] = { &drbd_nl_disconnect, 0 }, + [ P_resize ] = { &drbd_nl_resize, 0 }, + [ P_syncer_conf ] = { &drbd_nl_syncer_conf, 0 }, + [ P_invalidate ] = { &drbd_nl_invalidate, 0 }, + [ P_invalidate_peer ] = { &drbd_nl_invalidate_peer, 0 }, + [ P_pause_sync ] = { &drbd_nl_pause_sync, 0 }, + [ P_resume_sync ] = { &drbd_nl_resume_sync, 0 }, + [ P_suspend_io ] = { &drbd_nl_suspend_io, 0 }, + [ P_resume_io ] = { &drbd_nl_resume_io, 0 }, + [ P_outdate ] = { &drbd_nl_outdate, 0 }, + [ P_get_config ] = { &drbd_nl_get_config, + sizeof(struct syncer_conf_tag_len_struct) + + sizeof(struct disk_conf_tag_len_struct) + + sizeof(struct net_conf_tag_len_struct) }, + [ P_get_state ] = { &drbd_nl_get_state, + sizeof(struct get_state_tag_len_struct) + + sizeof(struct sync_progress_tag_len_struct) }, + [ P_get_uuids ] = { &drbd_nl_get_uuids, + sizeof(struct get_uuids_tag_len_struct) }, + [ P_get_timeout_flag ] = { &drbd_nl_get_timeout_flag, + sizeof(struct get_timeout_flag_tag_len_struct)}, + [ P_start_ov ] = { &drbd_nl_start_ov, 0 }, + [ P_new_c_uuid ] = { &drbd_nl_new_c_uuid, 0 }, +}; + +static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp) +{ + struct drbd_nl_cfg_req *nlp = (struct drbd_nl_cfg_req *)req->data; + struct cn_handler_struct *cm; + struct cn_msg *cn_reply; + struct drbd_nl_cfg_reply *reply; + struct drbd_conf *mdev; + int retcode, rr; + int reply_size = sizeof(struct cn_msg) + + sizeof(struct drbd_nl_cfg_reply) + + sizeof(short int); + + if (!try_module_get(THIS_MODULE)) { + printk(KERN_ERR "drbd: try_module_get() failed!\n"); + return; + } + + if (!cap_raised(nsp->eff_cap, CAP_SYS_ADMIN)) { + retcode = ERR_PERM; + goto fail; + } + + mdev = ensure_mdev(nlp); + if (!mdev) { + retcode = ERR_MINOR_INVALID; + goto fail; + } + + if (nlp->packet_type >= P_nl_after_last_packet) { + retcode = ERR_PACKET_NR; + goto fail; + } + + cm = cnd_table + nlp->packet_type; + + /* This may happen if packet number is 0: */ + if (cm->function == NULL) { + retcode = ERR_PACKET_NR; + goto fail; + } + + reply_size += cm->reply_body_size; + + /* allocation not in the IO path, cqueue thread context */ + cn_reply = kmalloc(reply_size, GFP_KERNEL); + if (!cn_reply) { + retcode = ERR_NOMEM; + goto fail; + } + reply = (struct drbd_nl_cfg_reply *) cn_reply->data; + + reply->packet_type = + cm->reply_body_size ? nlp->packet_type : P_nl_after_last_packet; + reply->minor = nlp->drbd_minor; + reply->ret_code = NO_ERROR; /* Might by modified by cm->function. */ + /* reply->tag_list; might be modified by cm->function. */ + + rr = cm->function(mdev, nlp, reply); + + cn_reply->id = req->id; + cn_reply->seq = req->seq; + cn_reply->ack = req->ack + 1; + cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + rr; + cn_reply->flags = 0; + + rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL); + if (rr && rr != -ESRCH) + printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr); + + kfree(cn_reply); + module_put(THIS_MODULE); + return; + fail: + drbd_nl_send_reply(req, retcode); + module_put(THIS_MODULE); +} + +static atomic_t drbd_nl_seq = ATOMIC_INIT(2); /* two. */ + +static unsigned short * +__tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, + unsigned short len, int nul_terminated) +{ + unsigned short l = tag_descriptions[tag_number(tag)].max_len; + len = (len < l) ? len : l; + put_unaligned(tag, tl++); + put_unaligned(len, tl++); + memcpy(tl, data, len); + tl = (unsigned short*)((char*)tl + len); + if (nul_terminated) + *((char*)tl - 1) = 0; + return tl; +} + +static unsigned short * +tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, int len) +{ + return __tl_add_blob(tl, tag, data, len, 0); +} + +static unsigned short * +tl_add_str(unsigned short *tl, enum drbd_tags tag, const char *str) +{ + return __tl_add_blob(tl, tag, str, strlen(str)+1, 0); +} + +static unsigned short * +tl_add_int(unsigned short *tl, enum drbd_tags tag, const void *val) +{ + put_unaligned(tag, tl++); + switch(tag_type(tag)) { + case TT_INTEGER: + put_unaligned(sizeof(int), tl++); + put_unaligned(*(int *)val, (int *)tl); + tl = (unsigned short*)((char*)tl+sizeof(int)); + break; + case TT_INT64: + put_unaligned(sizeof(u64), tl++); + put_unaligned(*(u64 *)val, (u64 *)tl); + tl = (unsigned short*)((char*)tl+sizeof(u64)); + break; + default: + /* someone did something stupid. */ + ; + } + return tl; +} + +void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state state) +{ + char buffer[sizeof(struct cn_msg)+ + sizeof(struct drbd_nl_cfg_reply)+ + sizeof(struct get_state_tag_len_struct)+ + sizeof(short int)]; + struct cn_msg *cn_reply = (struct cn_msg *) buffer; + struct drbd_nl_cfg_reply *reply = + (struct drbd_nl_cfg_reply *)cn_reply->data; + unsigned short *tl = reply->tag_list; + + /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */ + + tl = get_state_to_tags(mdev, (struct get_state *)&state, tl); + + put_unaligned(TT_END, tl++); /* Close the tag list */ + + cn_reply->id.idx = CN_IDX_DRBD; + cn_reply->id.val = CN_VAL_DRBD; + + cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); + cn_reply->ack = 0; /* not used here. */ + cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + + (int)((char *)tl - (char *)reply->tag_list); + cn_reply->flags = 0; + + reply->packet_type = P_get_state; + reply->minor = mdev_to_minor(mdev); + reply->ret_code = NO_ERROR; + + cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); +} + +void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name) +{ + char buffer[sizeof(struct cn_msg)+ + sizeof(struct drbd_nl_cfg_reply)+ + sizeof(struct call_helper_tag_len_struct)+ + sizeof(short int)]; + struct cn_msg *cn_reply = (struct cn_msg *) buffer; + struct drbd_nl_cfg_reply *reply = + (struct drbd_nl_cfg_reply *)cn_reply->data; + unsigned short *tl = reply->tag_list; + + /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */ + + tl = tl_add_str(tl, T_helper, helper_name); + put_unaligned(TT_END, tl++); /* Close the tag list */ + + cn_reply->id.idx = CN_IDX_DRBD; + cn_reply->id.val = CN_VAL_DRBD; + + cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); + cn_reply->ack = 0; /* not used here. */ + cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + + (int)((char *)tl - (char *)reply->tag_list); + cn_reply->flags = 0; + + reply->packet_type = P_call_helper; + reply->minor = mdev_to_minor(mdev); + reply->ret_code = NO_ERROR; + + cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); +} + +void drbd_bcast_ee(struct drbd_conf *mdev, + const char *reason, const int dgs, + const char* seen_hash, const char* calc_hash, + const struct drbd_epoch_entry* e) +{ + struct cn_msg *cn_reply; + struct drbd_nl_cfg_reply *reply; + struct bio_vec *bvec; + unsigned short *tl; + int i; + + if (!e) + return; + if (!reason || !reason[0]) + return; + + /* apparently we have to memcpy twice, first to prepare the data for the + * struct cn_msg, then within cn_netlink_send from the cn_msg to the + * netlink skb. */ + /* receiver thread context, which is not in the writeout path (of this node), + * but may be in the writeout path of the _other_ node. + * GFP_NOIO to avoid potential "distributed deadlock". */ + cn_reply = kmalloc( + sizeof(struct cn_msg)+ + sizeof(struct drbd_nl_cfg_reply)+ + sizeof(struct dump_ee_tag_len_struct)+ + sizeof(short int), + GFP_NOIO); + + if (!cn_reply) { + dev_err(DEV, "could not kmalloc buffer for drbd_bcast_ee, sector %llu, size %u\n", + (unsigned long long)e->sector, e->size); + return; + } + + reply = (struct drbd_nl_cfg_reply*)cn_reply->data; + tl = reply->tag_list; + + tl = tl_add_str(tl, T_dump_ee_reason, reason); + tl = tl_add_blob(tl, T_seen_digest, seen_hash, dgs); + tl = tl_add_blob(tl, T_calc_digest, calc_hash, dgs); + tl = tl_add_int(tl, T_ee_sector, &e->sector); + tl = tl_add_int(tl, T_ee_block_id, &e->block_id); + + put_unaligned(T_ee_data, tl++); + put_unaligned(e->size, tl++); + + __bio_for_each_segment(bvec, e->private_bio, i, 0) { + void *d = kmap(bvec->bv_page); + memcpy(tl, d + bvec->bv_offset, bvec->bv_len); + kunmap(bvec->bv_page); + tl=(unsigned short*)((char*)tl + bvec->bv_len); + } + put_unaligned(TT_END, tl++); /* Close the tag list */ + + cn_reply->id.idx = CN_IDX_DRBD; + cn_reply->id.val = CN_VAL_DRBD; + + cn_reply->seq = atomic_add_return(1,&drbd_nl_seq); + cn_reply->ack = 0; // not used here. + cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + + (int)((char*)tl - (char*)reply->tag_list); + cn_reply->flags = 0; + + reply->packet_type = P_dump_ee; + reply->minor = mdev_to_minor(mdev); + reply->ret_code = NO_ERROR; + + cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); + kfree(cn_reply); +} + +void drbd_bcast_sync_progress(struct drbd_conf *mdev) +{ + char buffer[sizeof(struct cn_msg)+ + sizeof(struct drbd_nl_cfg_reply)+ + sizeof(struct sync_progress_tag_len_struct)+ + sizeof(short int)]; + struct cn_msg *cn_reply = (struct cn_msg *) buffer; + struct drbd_nl_cfg_reply *reply = + (struct drbd_nl_cfg_reply *)cn_reply->data; + unsigned short *tl = reply->tag_list; + unsigned long rs_left; + unsigned int res; + + /* no local ref, no bitmap, no syncer progress, no broadcast. */ + if (!get_ldev(mdev)) + return; + drbd_get_syncer_progress(mdev, &rs_left, &res); + put_ldev(mdev); + + tl = tl_add_int(tl, T_sync_progress, &res); + put_unaligned(TT_END, tl++); /* Close the tag list */ + + cn_reply->id.idx = CN_IDX_DRBD; + cn_reply->id.val = CN_VAL_DRBD; + + cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); + cn_reply->ack = 0; /* not used here. */ + cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + + (int)((char *)tl - (char *)reply->tag_list); + cn_reply->flags = 0; + + reply->packet_type = P_sync_progress; + reply->minor = mdev_to_minor(mdev); + reply->ret_code = NO_ERROR; + + cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); +} + +int __init drbd_nl_init(void) +{ + static struct cb_id cn_id_drbd; + int err, try=10; + + cn_id_drbd.val = CN_VAL_DRBD; + do { + cn_id_drbd.idx = cn_idx; + err = cn_add_callback(&cn_id_drbd, "cn_drbd", &drbd_connector_callback); + if (!err) + break; + cn_idx = (cn_idx + CN_IDX_STEP); + } while (try--); + + if (err) { + printk(KERN_ERR "drbd: cn_drbd failed to register\n"); + return err; + } + + return 0; +} + +void drbd_nl_cleanup(void) +{ + static struct cb_id cn_id_drbd; + + cn_id_drbd.idx = cn_idx; + cn_id_drbd.val = CN_VAL_DRBD; + + cn_del_callback(&cn_id_drbd); +} + +void drbd_nl_send_reply(struct cn_msg *req, int ret_code) +{ + char buffer[sizeof(struct cn_msg)+sizeof(struct drbd_nl_cfg_reply)]; + struct cn_msg *cn_reply = (struct cn_msg *) buffer; + struct drbd_nl_cfg_reply *reply = + (struct drbd_nl_cfg_reply *)cn_reply->data; + int rr; + + cn_reply->id = req->id; + + cn_reply->seq = req->seq; + cn_reply->ack = req->ack + 1; + cn_reply->len = sizeof(struct drbd_nl_cfg_reply); + cn_reply->flags = 0; + + reply->minor = ((struct drbd_nl_cfg_req *)req->data)->drbd_minor; + reply->ret_code = ret_code; + + rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); + if (rr && rr != -ESRCH) + printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr); +} + diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c new file mode 100644 index 000000000000..bdd0b4943b10 --- /dev/null +++ b/drivers/block/drbd/drbd_proc.c @@ -0,0 +1,265 @@ +/* + drbd_proc.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include + +#include +#include +#include +#include +#include +#include +#include +#include "drbd_int.h" + +static int drbd_proc_open(struct inode *inode, struct file *file); + + +struct proc_dir_entry *drbd_proc; +struct file_operations drbd_proc_fops = { + .owner = THIS_MODULE, + .open = drbd_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + + +/*lge + * progress bars shamelessly adapted from driver/md/md.c + * output looks like + * [=====>..............] 33.5% (23456/123456) + * finish: 2:20:20 speed: 6,345 (6,456) K/sec + */ +static void drbd_syncer_progress(struct drbd_conf *mdev, struct seq_file *seq) +{ + unsigned long db, dt, dbdt, rt, rs_left; + unsigned int res; + int i, x, y; + + drbd_get_syncer_progress(mdev, &rs_left, &res); + + x = res/50; + y = 20-x; + seq_printf(seq, "\t["); + for (i = 1; i < x; i++) + seq_printf(seq, "="); + seq_printf(seq, ">"); + for (i = 0; i < y; i++) + seq_printf(seq, "."); + seq_printf(seq, "] "); + + seq_printf(seq, "sync'ed:%3u.%u%% ", res / 10, res % 10); + /* if more than 1 GB display in MB */ + if (mdev->rs_total > 0x100000L) + seq_printf(seq, "(%lu/%lu)M\n\t", + (unsigned long) Bit2KB(rs_left >> 10), + (unsigned long) Bit2KB(mdev->rs_total >> 10)); + else + seq_printf(seq, "(%lu/%lu)K\n\t", + (unsigned long) Bit2KB(rs_left), + (unsigned long) Bit2KB(mdev->rs_total)); + + /* see drivers/md/md.c + * We do not want to overflow, so the order of operands and + * the * 100 / 100 trick are important. We do a +1 to be + * safe against division by zero. We only estimate anyway. + * + * dt: time from mark until now + * db: blocks written from mark until now + * rt: remaining time + */ + dt = (jiffies - mdev->rs_mark_time) / HZ; + + if (dt > 20) { + /* if we made no update to rs_mark_time for too long, + * we are stalled. show that. */ + seq_printf(seq, "stalled\n"); + return; + } + + if (!dt) + dt++; + db = mdev->rs_mark_left - rs_left; + rt = (dt * (rs_left / (db/100+1)))/100; /* seconds */ + + seq_printf(seq, "finish: %lu:%02lu:%02lu", + rt / 3600, (rt % 3600) / 60, rt % 60); + + /* current speed average over (SYNC_MARKS * SYNC_MARK_STEP) jiffies */ + dbdt = Bit2KB(db/dt); + if (dbdt > 1000) + seq_printf(seq, " speed: %ld,%03ld", + dbdt/1000, dbdt % 1000); + else + seq_printf(seq, " speed: %ld", dbdt); + + /* mean speed since syncer started + * we do account for PausedSync periods */ + dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ; + if (dt <= 0) + dt = 1; + db = mdev->rs_total - rs_left; + dbdt = Bit2KB(db/dt); + if (dbdt > 1000) + seq_printf(seq, " (%ld,%03ld)", + dbdt/1000, dbdt % 1000); + else + seq_printf(seq, " (%ld)", dbdt); + + seq_printf(seq, " K/sec\n"); +} + +static void resync_dump_detail(struct seq_file *seq, struct lc_element *e) +{ + struct bm_extent *bme = lc_entry(e, struct bm_extent, lce); + + seq_printf(seq, "%5d %s %s\n", bme->rs_left, + bme->flags & BME_NO_WRITES ? "NO_WRITES" : "---------", + bme->flags & BME_LOCKED ? "LOCKED" : "------" + ); +} + +static int drbd_seq_show(struct seq_file *seq, void *v) +{ + int i, hole = 0; + const char *sn; + struct drbd_conf *mdev; + + static char write_ordering_chars[] = { + [WO_none] = 'n', + [WO_drain_io] = 'd', + [WO_bdev_flush] = 'f', + [WO_bio_barrier] = 'b', + }; + + seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n", + API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); + + /* + cs .. connection state + ro .. node role (local/remote) + ds .. disk state (local/remote) + protocol + various flags + ns .. network send + nr .. network receive + dw .. disk write + dr .. disk read + al .. activity log write count + bm .. bitmap update write count + pe .. pending (waiting for ack or data reply) + ua .. unack'd (still need to send ack or data reply) + ap .. application requests accepted, but not yet completed + ep .. number of epochs currently "on the fly", P_BARRIER_ACK pending + wo .. write ordering mode currently in use + oos .. known out-of-sync kB + */ + + for (i = 0; i < minor_count; i++) { + mdev = minor_to_mdev(i); + if (!mdev) { + hole = 1; + continue; + } + if (hole) { + hole = 0; + seq_printf(seq, "\n"); + } + + sn = drbd_conn_str(mdev->state.conn); + + if (mdev->state.conn == C_STANDALONE && + mdev->state.disk == D_DISKLESS && + mdev->state.role == R_SECONDARY) { + seq_printf(seq, "%2d: cs:Unconfigured\n", i); + } else { + seq_printf(seq, + "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c\n" + " ns:%u nr:%u dw:%u dr:%u al:%u bm:%u " + "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c", + i, sn, + drbd_role_str(mdev->state.role), + drbd_role_str(mdev->state.peer), + drbd_disk_str(mdev->state.disk), + drbd_disk_str(mdev->state.pdsk), + (mdev->net_conf == NULL ? ' ' : + (mdev->net_conf->wire_protocol - DRBD_PROT_A+'A')), + mdev->state.susp ? 's' : 'r', + mdev->state.aftr_isp ? 'a' : '-', + mdev->state.peer_isp ? 'p' : '-', + mdev->state.user_isp ? 'u' : '-', + mdev->congestion_reason ?: '-', + mdev->send_cnt/2, + mdev->recv_cnt/2, + mdev->writ_cnt/2, + mdev->read_cnt/2, + mdev->al_writ_cnt, + mdev->bm_writ_cnt, + atomic_read(&mdev->local_cnt), + atomic_read(&mdev->ap_pending_cnt) + + atomic_read(&mdev->rs_pending_cnt), + atomic_read(&mdev->unacked_cnt), + atomic_read(&mdev->ap_bio_cnt), + mdev->epochs, + write_ordering_chars[mdev->write_ordering] + ); + seq_printf(seq, " oos:%lu\n", + Bit2KB(drbd_bm_total_weight(mdev))); + } + if (mdev->state.conn == C_SYNC_SOURCE || + mdev->state.conn == C_SYNC_TARGET) + drbd_syncer_progress(mdev, seq); + + if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T) + seq_printf(seq, "\t%3d%% %lu/%lu\n", + (int)((mdev->rs_total-mdev->ov_left) / + (mdev->rs_total/100+1)), + mdev->rs_total - mdev->ov_left, + mdev->rs_total); + + if (proc_details >= 1 && get_ldev_if_state(mdev, D_FAILED)) { + lc_seq_printf_stats(seq, mdev->resync); + lc_seq_printf_stats(seq, mdev->act_log); + put_ldev(mdev); + } + + if (proc_details >= 2) { + if (mdev->resync) { + lc_seq_dump_details(seq, mdev->resync, "rs_left", + resync_dump_detail); + } + } + } + + return 0; +} + +static int drbd_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, drbd_seq_show, PDE(inode)->data); +} + +/* PROC FS stuff end */ diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c new file mode 100644 index 000000000000..c548f24f54a1 --- /dev/null +++ b/drivers/block/drbd/drbd_receiver.c @@ -0,0 +1,4426 @@ +/* + drbd_receiver.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ + + +#include + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#define __KERNEL_SYSCALLS__ +#include +#include +#include +#include +#include +#include +#include "drbd_int.h" +#include "drbd_req.h" + +#include "drbd_vli.h" + +struct flush_work { + struct drbd_work w; + struct drbd_epoch *epoch; +}; + +enum finish_epoch { + FE_STILL_LIVE, + FE_DESTROYED, + FE_RECYCLED, +}; + +static int drbd_do_handshake(struct drbd_conf *mdev); +static int drbd_do_auth(struct drbd_conf *mdev); + +static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *, struct drbd_epoch *, enum epoch_event); +static int e_end_block(struct drbd_conf *, struct drbd_work *, int); + +static struct drbd_epoch *previous_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch) +{ + struct drbd_epoch *prev; + spin_lock(&mdev->epoch_lock); + prev = list_entry(epoch->list.prev, struct drbd_epoch, list); + if (prev == epoch || prev == mdev->current_epoch) + prev = NULL; + spin_unlock(&mdev->epoch_lock); + return prev; +} + +#define GFP_TRY (__GFP_HIGHMEM | __GFP_NOWARN) + +static struct page *drbd_pp_first_page_or_try_alloc(struct drbd_conf *mdev) +{ + struct page *page = NULL; + + /* Yes, testing drbd_pp_vacant outside the lock is racy. + * So what. It saves a spin_lock. */ + if (drbd_pp_vacant > 0) { + spin_lock(&drbd_pp_lock); + page = drbd_pp_pool; + if (page) { + drbd_pp_pool = (struct page *)page_private(page); + set_page_private(page, 0); /* just to be polite */ + drbd_pp_vacant--; + } + spin_unlock(&drbd_pp_lock); + } + /* GFP_TRY, because we must not cause arbitrary write-out: in a DRBD + * "criss-cross" setup, that might cause write-out on some other DRBD, + * which in turn might block on the other node at this very place. */ + if (!page) + page = alloc_page(GFP_TRY); + if (page) + atomic_inc(&mdev->pp_in_use); + return page; +} + +/* kick lower level device, if we have more than (arbitrary number) + * reference counts on it, which typically are locally submitted io + * requests. don't use unacked_cnt, so we speed up proto A and B, too. */ +static void maybe_kick_lo(struct drbd_conf *mdev) +{ + if (atomic_read(&mdev->local_cnt) >= mdev->net_conf->unplug_watermark) + drbd_kick_lo(mdev); +} + +static void reclaim_net_ee(struct drbd_conf *mdev, struct list_head *to_be_freed) +{ + struct drbd_epoch_entry *e; + struct list_head *le, *tle; + + /* The EEs are always appended to the end of the list. Since + they are sent in order over the wire, they have to finish + in order. As soon as we see the first not finished we can + stop to examine the list... */ + + list_for_each_safe(le, tle, &mdev->net_ee) { + e = list_entry(le, struct drbd_epoch_entry, w.list); + if (drbd_bio_has_active_page(e->private_bio)) + break; + list_move(le, to_be_freed); + } +} + +static void drbd_kick_lo_and_reclaim_net(struct drbd_conf *mdev) +{ + LIST_HEAD(reclaimed); + struct drbd_epoch_entry *e, *t; + + maybe_kick_lo(mdev); + spin_lock_irq(&mdev->req_lock); + reclaim_net_ee(mdev, &reclaimed); + spin_unlock_irq(&mdev->req_lock); + + list_for_each_entry_safe(e, t, &reclaimed, w.list) + drbd_free_ee(mdev, e); +} + +/** + * drbd_pp_alloc() - Returns a page, fails only if a signal comes in + * @mdev: DRBD device. + * @retry: whether or not to retry allocation forever (or until signalled) + * + * Tries to allocate a page, first from our own page pool, then from the + * kernel, unless this allocation would exceed the max_buffers setting. + * If @retry is non-zero, retry until DRBD frees a page somewhere else. + */ +static struct page *drbd_pp_alloc(struct drbd_conf *mdev, int retry) +{ + struct page *page = NULL; + DEFINE_WAIT(wait); + + if (atomic_read(&mdev->pp_in_use) < mdev->net_conf->max_buffers) { + page = drbd_pp_first_page_or_try_alloc(mdev); + if (page) + return page; + } + + for (;;) { + prepare_to_wait(&drbd_pp_wait, &wait, TASK_INTERRUPTIBLE); + + drbd_kick_lo_and_reclaim_net(mdev); + + if (atomic_read(&mdev->pp_in_use) < mdev->net_conf->max_buffers) { + page = drbd_pp_first_page_or_try_alloc(mdev); + if (page) + break; + } + + if (!retry) + break; + + if (signal_pending(current)) { + dev_warn(DEV, "drbd_pp_alloc interrupted!\n"); + break; + } + + schedule(); + } + finish_wait(&drbd_pp_wait, &wait); + + return page; +} + +/* Must not be used from irq, as that may deadlock: see drbd_pp_alloc. + * Is also used from inside an other spin_lock_irq(&mdev->req_lock) */ +static void drbd_pp_free(struct drbd_conf *mdev, struct page *page) +{ + int free_it; + + spin_lock(&drbd_pp_lock); + if (drbd_pp_vacant > (DRBD_MAX_SEGMENT_SIZE/PAGE_SIZE)*minor_count) { + free_it = 1; + } else { + set_page_private(page, (unsigned long)drbd_pp_pool); + drbd_pp_pool = page; + drbd_pp_vacant++; + free_it = 0; + } + spin_unlock(&drbd_pp_lock); + + atomic_dec(&mdev->pp_in_use); + + if (free_it) + __free_page(page); + + wake_up(&drbd_pp_wait); +} + +static void drbd_pp_free_bio_pages(struct drbd_conf *mdev, struct bio *bio) +{ + struct page *p_to_be_freed = NULL; + struct page *page; + struct bio_vec *bvec; + int i; + + spin_lock(&drbd_pp_lock); + __bio_for_each_segment(bvec, bio, i, 0) { + if (drbd_pp_vacant > (DRBD_MAX_SEGMENT_SIZE/PAGE_SIZE)*minor_count) { + set_page_private(bvec->bv_page, (unsigned long)p_to_be_freed); + p_to_be_freed = bvec->bv_page; + } else { + set_page_private(bvec->bv_page, (unsigned long)drbd_pp_pool); + drbd_pp_pool = bvec->bv_page; + drbd_pp_vacant++; + } + } + spin_unlock(&drbd_pp_lock); + atomic_sub(bio->bi_vcnt, &mdev->pp_in_use); + + while (p_to_be_freed) { + page = p_to_be_freed; + p_to_be_freed = (struct page *)page_private(page); + set_page_private(page, 0); /* just to be polite */ + put_page(page); + } + + wake_up(&drbd_pp_wait); +} + +/* +You need to hold the req_lock: + _drbd_wait_ee_list_empty() + +You must not have the req_lock: + drbd_free_ee() + drbd_alloc_ee() + drbd_init_ee() + drbd_release_ee() + drbd_ee_fix_bhs() + drbd_process_done_ee() + drbd_clear_done_ee() + drbd_wait_ee_list_empty() +*/ + +struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev, + u64 id, + sector_t sector, + unsigned int data_size, + gfp_t gfp_mask) __must_hold(local) +{ + struct request_queue *q; + struct drbd_epoch_entry *e; + struct page *page; + struct bio *bio; + unsigned int ds; + + if (FAULT_ACTIVE(mdev, DRBD_FAULT_AL_EE)) + return NULL; + + e = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM); + if (!e) { + if (!(gfp_mask & __GFP_NOWARN)) + dev_err(DEV, "alloc_ee: Allocation of an EE failed\n"); + return NULL; + } + + bio = bio_alloc(gfp_mask & ~__GFP_HIGHMEM, div_ceil(data_size, PAGE_SIZE)); + if (!bio) { + if (!(gfp_mask & __GFP_NOWARN)) + dev_err(DEV, "alloc_ee: Allocation of a bio failed\n"); + goto fail1; + } + + bio->bi_bdev = mdev->ldev->backing_bdev; + bio->bi_sector = sector; + + ds = data_size; + while (ds) { + page = drbd_pp_alloc(mdev, (gfp_mask & __GFP_WAIT)); + if (!page) { + if (!(gfp_mask & __GFP_NOWARN)) + dev_err(DEV, "alloc_ee: Allocation of a page failed\n"); + goto fail2; + } + if (!bio_add_page(bio, page, min_t(int, ds, PAGE_SIZE), 0)) { + drbd_pp_free(mdev, page); + dev_err(DEV, "alloc_ee: bio_add_page(s=%llu," + "data_size=%u,ds=%u) failed\n", + (unsigned long long)sector, data_size, ds); + + q = bdev_get_queue(bio->bi_bdev); + if (q->merge_bvec_fn) { + struct bvec_merge_data bvm = { + .bi_bdev = bio->bi_bdev, + .bi_sector = bio->bi_sector, + .bi_size = bio->bi_size, + .bi_rw = bio->bi_rw, + }; + int l = q->merge_bvec_fn(q, &bvm, + &bio->bi_io_vec[bio->bi_vcnt]); + dev_err(DEV, "merge_bvec_fn() = %d\n", l); + } + + /* dump more of the bio. */ + dev_err(DEV, "bio->bi_max_vecs = %d\n", bio->bi_max_vecs); + dev_err(DEV, "bio->bi_vcnt = %d\n", bio->bi_vcnt); + dev_err(DEV, "bio->bi_size = %d\n", bio->bi_size); + dev_err(DEV, "bio->bi_phys_segments = %d\n", bio->bi_phys_segments); + + goto fail2; + break; + } + ds -= min_t(int, ds, PAGE_SIZE); + } + + D_ASSERT(data_size == bio->bi_size); + + bio->bi_private = e; + e->mdev = mdev; + e->sector = sector; + e->size = bio->bi_size; + + e->private_bio = bio; + e->block_id = id; + INIT_HLIST_NODE(&e->colision); + e->epoch = NULL; + e->flags = 0; + + return e; + + fail2: + drbd_pp_free_bio_pages(mdev, bio); + bio_put(bio); + fail1: + mempool_free(e, drbd_ee_mempool); + + return NULL; +} + +void drbd_free_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e) +{ + struct bio *bio = e->private_bio; + drbd_pp_free_bio_pages(mdev, bio); + bio_put(bio); + D_ASSERT(hlist_unhashed(&e->colision)); + mempool_free(e, drbd_ee_mempool); +} + +int drbd_release_ee(struct drbd_conf *mdev, struct list_head *list) +{ + LIST_HEAD(work_list); + struct drbd_epoch_entry *e, *t; + int count = 0; + + spin_lock_irq(&mdev->req_lock); + list_splice_init(list, &work_list); + spin_unlock_irq(&mdev->req_lock); + + list_for_each_entry_safe(e, t, &work_list, w.list) { + drbd_free_ee(mdev, e); + count++; + } + return count; +} + + +/* + * This function is called from _asender only_ + * but see also comments in _req_mod(,barrier_acked) + * and receive_Barrier. + * + * Move entries from net_ee to done_ee, if ready. + * Grab done_ee, call all callbacks, free the entries. + * The callbacks typically send out ACKs. + */ +static int drbd_process_done_ee(struct drbd_conf *mdev) +{ + LIST_HEAD(work_list); + LIST_HEAD(reclaimed); + struct drbd_epoch_entry *e, *t; + int ok = (mdev->state.conn >= C_WF_REPORT_PARAMS); + + spin_lock_irq(&mdev->req_lock); + reclaim_net_ee(mdev, &reclaimed); + list_splice_init(&mdev->done_ee, &work_list); + spin_unlock_irq(&mdev->req_lock); + + list_for_each_entry_safe(e, t, &reclaimed, w.list) + drbd_free_ee(mdev, e); + + /* possible callbacks here: + * e_end_block, and e_end_resync_block, e_send_discard_ack. + * all ignore the last argument. + */ + list_for_each_entry_safe(e, t, &work_list, w.list) { + /* list_del not necessary, next/prev members not touched */ + ok = e->w.cb(mdev, &e->w, !ok) && ok; + drbd_free_ee(mdev, e); + } + wake_up(&mdev->ee_wait); + + return ok; +} + +void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head) +{ + DEFINE_WAIT(wait); + + /* avoids spin_lock/unlock + * and calling prepare_to_wait in the fast path */ + while (!list_empty(head)) { + prepare_to_wait(&mdev->ee_wait, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&mdev->req_lock); + drbd_kick_lo(mdev); + schedule(); + finish_wait(&mdev->ee_wait, &wait); + spin_lock_irq(&mdev->req_lock); + } +} + +void drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head) +{ + spin_lock_irq(&mdev->req_lock); + _drbd_wait_ee_list_empty(mdev, head); + spin_unlock_irq(&mdev->req_lock); +} + +/* see also kernel_accept; which is only present since 2.6.18. + * also we want to log which part of it failed, exactly */ +static int drbd_accept(struct drbd_conf *mdev, const char **what, + struct socket *sock, struct socket **newsock) +{ + struct sock *sk = sock->sk; + int err = 0; + + *what = "listen"; + err = sock->ops->listen(sock, 5); + if (err < 0) + goto out; + + *what = "sock_create_lite"; + err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, + newsock); + if (err < 0) + goto out; + + *what = "accept"; + err = sock->ops->accept(sock, *newsock, 0); + if (err < 0) { + sock_release(*newsock); + *newsock = NULL; + goto out; + } + (*newsock)->ops = sock->ops; + +out: + return err; +} + +static int drbd_recv_short(struct drbd_conf *mdev, struct socket *sock, + void *buf, size_t size, int flags) +{ + mm_segment_t oldfs; + struct kvec iov = { + .iov_base = buf, + .iov_len = size, + }; + struct msghdr msg = { + .msg_iovlen = 1, + .msg_iov = (struct iovec *)&iov, + .msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL) + }; + int rv; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + rv = sock_recvmsg(sock, &msg, size, msg.msg_flags); + set_fs(oldfs); + + return rv; +} + +static int drbd_recv(struct drbd_conf *mdev, void *buf, size_t size) +{ + mm_segment_t oldfs; + struct kvec iov = { + .iov_base = buf, + .iov_len = size, + }; + struct msghdr msg = { + .msg_iovlen = 1, + .msg_iov = (struct iovec *)&iov, + .msg_flags = MSG_WAITALL | MSG_NOSIGNAL + }; + int rv; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + + for (;;) { + rv = sock_recvmsg(mdev->data.socket, &msg, size, msg.msg_flags); + if (rv == size) + break; + + /* Note: + * ECONNRESET other side closed the connection + * ERESTARTSYS (on sock) we got a signal + */ + + if (rv < 0) { + if (rv == -ECONNRESET) + dev_info(DEV, "sock was reset by peer\n"); + else if (rv != -ERESTARTSYS) + dev_err(DEV, "sock_recvmsg returned %d\n", rv); + break; + } else if (rv == 0) { + dev_info(DEV, "sock was shut down by peer\n"); + break; + } else { + /* signal came in, or peer/link went down, + * after we read a partial message + */ + /* D_ASSERT(signal_pending(current)); */ + break; + } + }; + + set_fs(oldfs); + + if (rv != size) + drbd_force_state(mdev, NS(conn, C_BROKEN_PIPE)); + + return rv; +} + +static struct socket *drbd_try_connect(struct drbd_conf *mdev) +{ + const char *what; + struct socket *sock; + struct sockaddr_in6 src_in6; + int err; + int disconnect_on_error = 1; + + if (!get_net_conf(mdev)) + return NULL; + + what = "sock_create_kern"; + err = sock_create_kern(((struct sockaddr *)mdev->net_conf->my_addr)->sa_family, + SOCK_STREAM, IPPROTO_TCP, &sock); + if (err < 0) { + sock = NULL; + goto out; + } + + sock->sk->sk_rcvtimeo = + sock->sk->sk_sndtimeo = mdev->net_conf->try_connect_int*HZ; + + /* explicitly bind to the configured IP as source IP + * for the outgoing connections. + * This is needed for multihomed hosts and to be + * able to use lo: interfaces for drbd. + * Make sure to use 0 as port number, so linux selects + * a free one dynamically. + */ + memcpy(&src_in6, mdev->net_conf->my_addr, + min_t(int, mdev->net_conf->my_addr_len, sizeof(src_in6))); + if (((struct sockaddr *)mdev->net_conf->my_addr)->sa_family == AF_INET6) + src_in6.sin6_port = 0; + else + ((struct sockaddr_in *)&src_in6)->sin_port = 0; /* AF_INET & AF_SCI */ + + what = "bind before connect"; + err = sock->ops->bind(sock, + (struct sockaddr *) &src_in6, + mdev->net_conf->my_addr_len); + if (err < 0) + goto out; + + /* connect may fail, peer not yet available. + * stay C_WF_CONNECTION, don't go Disconnecting! */ + disconnect_on_error = 0; + what = "connect"; + err = sock->ops->connect(sock, + (struct sockaddr *)mdev->net_conf->peer_addr, + mdev->net_conf->peer_addr_len, 0); + +out: + if (err < 0) { + if (sock) { + sock_release(sock); + sock = NULL; + } + switch (-err) { + /* timeout, busy, signal pending */ + case ETIMEDOUT: case EAGAIN: case EINPROGRESS: + case EINTR: case ERESTARTSYS: + /* peer not (yet) available, network problem */ + case ECONNREFUSED: case ENETUNREACH: + case EHOSTDOWN: case EHOSTUNREACH: + disconnect_on_error = 0; + break; + default: + dev_err(DEV, "%s failed, err = %d\n", what, err); + } + if (disconnect_on_error) + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + } + put_net_conf(mdev); + return sock; +} + +static struct socket *drbd_wait_for_connect(struct drbd_conf *mdev) +{ + int timeo, err; + struct socket *s_estab = NULL, *s_listen; + const char *what; + + if (!get_net_conf(mdev)) + return NULL; + + what = "sock_create_kern"; + err = sock_create_kern(((struct sockaddr *)mdev->net_conf->my_addr)->sa_family, + SOCK_STREAM, IPPROTO_TCP, &s_listen); + if (err) { + s_listen = NULL; + goto out; + } + + timeo = mdev->net_conf->try_connect_int * HZ; + timeo += (random32() & 1) ? timeo / 7 : -timeo / 7; /* 28.5% random jitter */ + + s_listen->sk->sk_reuse = 1; /* SO_REUSEADDR */ + s_listen->sk->sk_rcvtimeo = timeo; + s_listen->sk->sk_sndtimeo = timeo; + + what = "bind before listen"; + err = s_listen->ops->bind(s_listen, + (struct sockaddr *) mdev->net_conf->my_addr, + mdev->net_conf->my_addr_len); + if (err < 0) + goto out; + + err = drbd_accept(mdev, &what, s_listen, &s_estab); + +out: + if (s_listen) + sock_release(s_listen); + if (err < 0) { + if (err != -EAGAIN && err != -EINTR && err != -ERESTARTSYS) { + dev_err(DEV, "%s failed, err = %d\n", what, err); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + } + } + put_net_conf(mdev); + + return s_estab; +} + +static int drbd_send_fp(struct drbd_conf *mdev, + struct socket *sock, enum drbd_packets cmd) +{ + struct p_header *h = (struct p_header *) &mdev->data.sbuf.header; + + return _drbd_send_cmd(mdev, sock, cmd, h, sizeof(*h), 0); +} + +static enum drbd_packets drbd_recv_fp(struct drbd_conf *mdev, struct socket *sock) +{ + struct p_header *h = (struct p_header *) &mdev->data.sbuf.header; + int rr; + + rr = drbd_recv_short(mdev, sock, h, sizeof(*h), 0); + + if (rr == sizeof(*h) && h->magic == BE_DRBD_MAGIC) + return be16_to_cpu(h->command); + + return 0xffff; +} + +/** + * drbd_socket_okay() - Free the socket if its connection is not okay + * @mdev: DRBD device. + * @sock: pointer to the pointer to the socket. + */ +static int drbd_socket_okay(struct drbd_conf *mdev, struct socket **sock) +{ + int rr; + char tb[4]; + + if (!*sock) + return FALSE; + + rr = drbd_recv_short(mdev, *sock, tb, 4, MSG_DONTWAIT | MSG_PEEK); + + if (rr > 0 || rr == -EAGAIN) { + return TRUE; + } else { + sock_release(*sock); + *sock = NULL; + return FALSE; + } +} + +/* + * return values: + * 1 yes, we have a valid connection + * 0 oops, did not work out, please try again + * -1 peer talks different language, + * no point in trying again, please go standalone. + * -2 We do not have a network config... + */ +static int drbd_connect(struct drbd_conf *mdev) +{ + struct socket *s, *sock, *msock; + int try, h, ok; + + D_ASSERT(!mdev->data.socket); + + if (test_and_clear_bit(CREATE_BARRIER, &mdev->flags)) + dev_err(DEV, "CREATE_BARRIER flag was set in drbd_connect - now cleared!\n"); + + if (drbd_request_state(mdev, NS(conn, C_WF_CONNECTION)) < SS_SUCCESS) + return -2; + + clear_bit(DISCARD_CONCURRENT, &mdev->flags); + + sock = NULL; + msock = NULL; + + do { + for (try = 0;;) { + /* 3 tries, this should take less than a second! */ + s = drbd_try_connect(mdev); + if (s || ++try >= 3) + break; + /* give the other side time to call bind() & listen() */ + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ / 10); + } + + if (s) { + if (!sock) { + drbd_send_fp(mdev, s, P_HAND_SHAKE_S); + sock = s; + s = NULL; + } else if (!msock) { + drbd_send_fp(mdev, s, P_HAND_SHAKE_M); + msock = s; + s = NULL; + } else { + dev_err(DEV, "Logic error in drbd_connect()\n"); + goto out_release_sockets; + } + } + + if (sock && msock) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ / 10); + ok = drbd_socket_okay(mdev, &sock); + ok = drbd_socket_okay(mdev, &msock) && ok; + if (ok) + break; + } + +retry: + s = drbd_wait_for_connect(mdev); + if (s) { + try = drbd_recv_fp(mdev, s); + drbd_socket_okay(mdev, &sock); + drbd_socket_okay(mdev, &msock); + switch (try) { + case P_HAND_SHAKE_S: + if (sock) { + dev_warn(DEV, "initial packet S crossed\n"); + sock_release(sock); + } + sock = s; + break; + case P_HAND_SHAKE_M: + if (msock) { + dev_warn(DEV, "initial packet M crossed\n"); + sock_release(msock); + } + msock = s; + set_bit(DISCARD_CONCURRENT, &mdev->flags); + break; + default: + dev_warn(DEV, "Error receiving initial packet\n"); + sock_release(s); + if (random32() & 1) + goto retry; + } + } + + if (mdev->state.conn <= C_DISCONNECTING) + goto out_release_sockets; + if (signal_pending(current)) { + flush_signals(current); + smp_rmb(); + if (get_t_state(&mdev->receiver) == Exiting) + goto out_release_sockets; + } + + if (sock && msock) { + ok = drbd_socket_okay(mdev, &sock); + ok = drbd_socket_okay(mdev, &msock) && ok; + if (ok) + break; + } + } while (1); + + msock->sk->sk_reuse = 1; /* SO_REUSEADDR */ + sock->sk->sk_reuse = 1; /* SO_REUSEADDR */ + + sock->sk->sk_allocation = GFP_NOIO; + msock->sk->sk_allocation = GFP_NOIO; + + sock->sk->sk_priority = TC_PRIO_INTERACTIVE_BULK; + msock->sk->sk_priority = TC_PRIO_INTERACTIVE; + + if (mdev->net_conf->sndbuf_size) { + sock->sk->sk_sndbuf = mdev->net_conf->sndbuf_size; + sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK; + } + + if (mdev->net_conf->rcvbuf_size) { + sock->sk->sk_rcvbuf = mdev->net_conf->rcvbuf_size; + sock->sk->sk_userlocks |= SOCK_RCVBUF_LOCK; + } + + /* NOT YET ... + * sock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10; + * sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; + * first set it to the P_HAND_SHAKE timeout, + * which we set to 4x the configured ping_timeout. */ + sock->sk->sk_sndtimeo = + sock->sk->sk_rcvtimeo = mdev->net_conf->ping_timeo*4*HZ/10; + + msock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10; + msock->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ; + + /* we don't want delays. + * we use TCP_CORK where apropriate, though */ + drbd_tcp_nodelay(sock); + drbd_tcp_nodelay(msock); + + mdev->data.socket = sock; + mdev->meta.socket = msock; + mdev->last_received = jiffies; + + D_ASSERT(mdev->asender.task == NULL); + + h = drbd_do_handshake(mdev); + if (h <= 0) + return h; + + if (mdev->cram_hmac_tfm) { + /* drbd_request_state(mdev, NS(conn, WFAuth)); */ + if (!drbd_do_auth(mdev)) { + dev_err(DEV, "Authentication of peer failed\n"); + return -1; + } + } + + if (drbd_request_state(mdev, NS(conn, C_WF_REPORT_PARAMS)) < SS_SUCCESS) + return 0; + + sock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10; + sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; + + atomic_set(&mdev->packet_seq, 0); + mdev->peer_seq = 0; + + drbd_thread_start(&mdev->asender); + + drbd_send_protocol(mdev); + drbd_send_sync_param(mdev, &mdev->sync_conf); + drbd_send_sizes(mdev, 0); + drbd_send_uuids(mdev); + drbd_send_state(mdev); + clear_bit(USE_DEGR_WFC_T, &mdev->flags); + clear_bit(RESIZE_PENDING, &mdev->flags); + + return 1; + +out_release_sockets: + if (sock) + sock_release(sock); + if (msock) + sock_release(msock); + return -1; +} + +static int drbd_recv_header(struct drbd_conf *mdev, struct p_header *h) +{ + int r; + + r = drbd_recv(mdev, h, sizeof(*h)); + + if (unlikely(r != sizeof(*h))) { + dev_err(DEV, "short read expecting header on sock: r=%d\n", r); + return FALSE; + }; + h->command = be16_to_cpu(h->command); + h->length = be16_to_cpu(h->length); + if (unlikely(h->magic != BE_DRBD_MAGIC)) { + dev_err(DEV, "magic?? on data m: 0x%lx c: %d l: %d\n", + (long)be32_to_cpu(h->magic), + h->command, h->length); + return FALSE; + } + mdev->last_received = jiffies; + + return TRUE; +} + +static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch) +{ + int rv; + + if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) { + rv = blkdev_issue_flush(mdev->ldev->backing_bdev, NULL); + if (rv) { + dev_err(DEV, "local disk flush failed with status %d\n", rv); + /* would rather check on EOPNOTSUPP, but that is not reliable. + * don't try again for ANY return value != 0 + * if (rv == -EOPNOTSUPP) */ + drbd_bump_write_ordering(mdev, WO_drain_io); + } + put_ldev(mdev); + } + + return drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE); +} + +static int w_flush(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct flush_work *fw = (struct flush_work *)w; + struct drbd_epoch *epoch = fw->epoch; + + kfree(w); + + if (!test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags)) + drbd_flush_after_epoch(mdev, epoch); + + drbd_may_finish_epoch(mdev, epoch, EV_PUT | + (mdev->state.conn < C_CONNECTED ? EV_CLEANUP : 0)); + + return 1; +} + +/** + * drbd_may_finish_epoch() - Applies an epoch_event to the epoch's state, eventually finishes it. + * @mdev: DRBD device. + * @epoch: Epoch object. + * @ev: Epoch event. + */ +static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev, + struct drbd_epoch *epoch, + enum epoch_event ev) +{ + int finish, epoch_size; + struct drbd_epoch *next_epoch; + int schedule_flush = 0; + enum finish_epoch rv = FE_STILL_LIVE; + + spin_lock(&mdev->epoch_lock); + do { + next_epoch = NULL; + finish = 0; + + epoch_size = atomic_read(&epoch->epoch_size); + + switch (ev & ~EV_CLEANUP) { + case EV_PUT: + atomic_dec(&epoch->active); + break; + case EV_GOT_BARRIER_NR: + set_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags); + + /* Special case: If we just switched from WO_bio_barrier to + WO_bdev_flush we should not finish the current epoch */ + if (test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags) && epoch_size == 1 && + mdev->write_ordering != WO_bio_barrier && + epoch == mdev->current_epoch) + clear_bit(DE_CONTAINS_A_BARRIER, &epoch->flags); + break; + case EV_BARRIER_DONE: + set_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags); + break; + case EV_BECAME_LAST: + /* nothing to do*/ + break; + } + + if (epoch_size != 0 && + atomic_read(&epoch->active) == 0 && + test_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags) && + epoch->list.prev == &mdev->current_epoch->list && + !test_bit(DE_IS_FINISHING, &epoch->flags)) { + /* Nearly all conditions are met to finish that epoch... */ + if (test_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags) || + mdev->write_ordering == WO_none || + (epoch_size == 1 && test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) || + ev & EV_CLEANUP) { + finish = 1; + set_bit(DE_IS_FINISHING, &epoch->flags); + } else if (!test_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags) && + mdev->write_ordering == WO_bio_barrier) { + atomic_inc(&epoch->active); + schedule_flush = 1; + } + } + if (finish) { + if (!(ev & EV_CLEANUP)) { + spin_unlock(&mdev->epoch_lock); + drbd_send_b_ack(mdev, epoch->barrier_nr, epoch_size); + spin_lock(&mdev->epoch_lock); + } + dec_unacked(mdev); + + if (mdev->current_epoch != epoch) { + next_epoch = list_entry(epoch->list.next, struct drbd_epoch, list); + list_del(&epoch->list); + ev = EV_BECAME_LAST | (ev & EV_CLEANUP); + mdev->epochs--; + kfree(epoch); + + if (rv == FE_STILL_LIVE) + rv = FE_DESTROYED; + } else { + epoch->flags = 0; + atomic_set(&epoch->epoch_size, 0); + /* atomic_set(&epoch->active, 0); is alrady zero */ + if (rv == FE_STILL_LIVE) + rv = FE_RECYCLED; + } + } + + if (!next_epoch) + break; + + epoch = next_epoch; + } while (1); + + spin_unlock(&mdev->epoch_lock); + + if (schedule_flush) { + struct flush_work *fw; + fw = kmalloc(sizeof(*fw), GFP_ATOMIC); + if (fw) { + fw->w.cb = w_flush; + fw->epoch = epoch; + drbd_queue_work(&mdev->data.work, &fw->w); + } else { + dev_warn(DEV, "Could not kmalloc a flush_work obj\n"); + set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags); + /* That is not a recursion, only one level */ + drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE); + drbd_may_finish_epoch(mdev, epoch, EV_PUT); + } + } + + return rv; +} + +/** + * drbd_bump_write_ordering() - Fall back to an other write ordering method + * @mdev: DRBD device. + * @wo: Write ordering method to try. + */ +void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo) __must_hold(local) +{ + enum write_ordering_e pwo; + static char *write_ordering_str[] = { + [WO_none] = "none", + [WO_drain_io] = "drain", + [WO_bdev_flush] = "flush", + [WO_bio_barrier] = "barrier", + }; + + pwo = mdev->write_ordering; + wo = min(pwo, wo); + if (wo == WO_bio_barrier && mdev->ldev->dc.no_disk_barrier) + wo = WO_bdev_flush; + if (wo == WO_bdev_flush && mdev->ldev->dc.no_disk_flush) + wo = WO_drain_io; + if (wo == WO_drain_io && mdev->ldev->dc.no_disk_drain) + wo = WO_none; + mdev->write_ordering = wo; + if (pwo != mdev->write_ordering || wo == WO_bio_barrier) + dev_info(DEV, "Method to ensure write ordering: %s\n", write_ordering_str[mdev->write_ordering]); +} + +/** + * w_e_reissue() - Worker callback; Resubmit a bio, without BIO_RW_BARRIER set + * @mdev: DRBD device. + * @w: work object. + * @cancel: The connection will be closed anyways (unused in this callback) + */ +int w_e_reissue(struct drbd_conf *mdev, struct drbd_work *w, int cancel) __releases(local) +{ + struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w; + struct bio *bio = e->private_bio; + + /* We leave DE_CONTAINS_A_BARRIER and EE_IS_BARRIER in place, + (and DE_BARRIER_IN_NEXT_EPOCH_ISSUED in the previous Epoch) + so that we can finish that epoch in drbd_may_finish_epoch(). + That is necessary if we already have a long chain of Epochs, before + we realize that BIO_RW_BARRIER is actually not supported */ + + /* As long as the -ENOTSUPP on the barrier is reported immediately + that will never trigger. If it is reported late, we will just + print that warning and continue correctly for all future requests + with WO_bdev_flush */ + if (previous_epoch(mdev, e->epoch)) + dev_warn(DEV, "Write ordering was not enforced (one time event)\n"); + + /* prepare bio for re-submit, + * re-init volatile members */ + /* we still have a local reference, + * get_ldev was done in receive_Data. */ + bio->bi_bdev = mdev->ldev->backing_bdev; + bio->bi_sector = e->sector; + bio->bi_size = e->size; + bio->bi_idx = 0; + + bio->bi_flags &= ~(BIO_POOL_MASK - 1); + bio->bi_flags |= 1 << BIO_UPTODATE; + + /* don't know whether this is necessary: */ + bio->bi_phys_segments = 0; + bio->bi_next = NULL; + + /* these should be unchanged: */ + /* bio->bi_end_io = drbd_endio_write_sec; */ + /* bio->bi_vcnt = whatever; */ + + e->w.cb = e_end_block; + + /* This is no longer a barrier request. */ + bio->bi_rw &= ~(1UL << BIO_RW_BARRIER); + + drbd_generic_make_request(mdev, DRBD_FAULT_DT_WR, bio); + + return 1; +} + +static int receive_Barrier(struct drbd_conf *mdev, struct p_header *h) +{ + int rv, issue_flush; + struct p_barrier *p = (struct p_barrier *)h; + struct drbd_epoch *epoch; + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE; + + rv = drbd_recv(mdev, h->payload, h->length); + ERR_IF(rv != h->length) return FALSE; + + inc_unacked(mdev); + + if (mdev->net_conf->wire_protocol != DRBD_PROT_C) + drbd_kick_lo(mdev); + + mdev->current_epoch->barrier_nr = p->barrier; + rv = drbd_may_finish_epoch(mdev, mdev->current_epoch, EV_GOT_BARRIER_NR); + + /* P_BARRIER_ACK may imply that the corresponding extent is dropped from + * the activity log, which means it would not be resynced in case the + * R_PRIMARY crashes now. + * Therefore we must send the barrier_ack after the barrier request was + * completed. */ + switch (mdev->write_ordering) { + case WO_bio_barrier: + case WO_none: + if (rv == FE_RECYCLED) + return TRUE; + break; + + case WO_bdev_flush: + case WO_drain_io: + D_ASSERT(rv == FE_STILL_LIVE); + set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &mdev->current_epoch->flags); + drbd_wait_ee_list_empty(mdev, &mdev->active_ee); + rv = drbd_flush_after_epoch(mdev, mdev->current_epoch); + if (rv == FE_RECYCLED) + return TRUE; + + /* The asender will send all the ACKs and barrier ACKs out, since + all EEs moved from the active_ee to the done_ee. We need to + provide a new epoch object for the EEs that come in soon */ + break; + } + + /* receiver context, in the writeout path of the other node. + * avoid potential distributed deadlock */ + epoch = kmalloc(sizeof(struct drbd_epoch), GFP_NOIO); + if (!epoch) { + dev_warn(DEV, "Allocation of an epoch failed, slowing down\n"); + issue_flush = !test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags); + drbd_wait_ee_list_empty(mdev, &mdev->active_ee); + if (issue_flush) { + rv = drbd_flush_after_epoch(mdev, mdev->current_epoch); + if (rv == FE_RECYCLED) + return TRUE; + } + + drbd_wait_ee_list_empty(mdev, &mdev->done_ee); + + return TRUE; + } + + epoch->flags = 0; + atomic_set(&epoch->epoch_size, 0); + atomic_set(&epoch->active, 0); + + spin_lock(&mdev->epoch_lock); + if (atomic_read(&mdev->current_epoch->epoch_size)) { + list_add(&epoch->list, &mdev->current_epoch->list); + mdev->current_epoch = epoch; + mdev->epochs++; + } else { + /* The current_epoch got recycled while we allocated this one... */ + kfree(epoch); + } + spin_unlock(&mdev->epoch_lock); + + return TRUE; +} + +/* used from receive_RSDataReply (recv_resync_read) + * and from receive_Data */ +static struct drbd_epoch_entry * +read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __must_hold(local) +{ + struct drbd_epoch_entry *e; + struct bio_vec *bvec; + struct page *page; + struct bio *bio; + int dgs, ds, i, rr; + void *dig_in = mdev->int_dig_in; + void *dig_vv = mdev->int_dig_vv; + + dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_r_tfm) ? + crypto_hash_digestsize(mdev->integrity_r_tfm) : 0; + + if (dgs) { + rr = drbd_recv(mdev, dig_in, dgs); + if (rr != dgs) { + dev_warn(DEV, "short read receiving data digest: read %d expected %d\n", + rr, dgs); + return NULL; + } + } + + data_size -= dgs; + + ERR_IF(data_size & 0x1ff) return NULL; + ERR_IF(data_size > DRBD_MAX_SEGMENT_SIZE) return NULL; + + /* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD + * "criss-cross" setup, that might cause write-out on some other DRBD, + * which in turn might block on the other node at this very place. */ + e = drbd_alloc_ee(mdev, id, sector, data_size, GFP_NOIO); + if (!e) + return NULL; + bio = e->private_bio; + ds = data_size; + bio_for_each_segment(bvec, bio, i) { + page = bvec->bv_page; + rr = drbd_recv(mdev, kmap(page), min_t(int, ds, PAGE_SIZE)); + kunmap(page); + if (rr != min_t(int, ds, PAGE_SIZE)) { + drbd_free_ee(mdev, e); + dev_warn(DEV, "short read receiving data: read %d expected %d\n", + rr, min_t(int, ds, PAGE_SIZE)); + return NULL; + } + ds -= rr; + } + + if (dgs) { + drbd_csum(mdev, mdev->integrity_r_tfm, bio, dig_vv); + if (memcmp(dig_in, dig_vv, dgs)) { + dev_err(DEV, "Digest integrity check FAILED.\n"); + drbd_bcast_ee(mdev, "digest failed", + dgs, dig_in, dig_vv, e); + drbd_free_ee(mdev, e); + return NULL; + } + } + mdev->recv_cnt += data_size>>9; + return e; +} + +/* drbd_drain_block() just takes a data block + * out of the socket input buffer, and discards it. + */ +static int drbd_drain_block(struct drbd_conf *mdev, int data_size) +{ + struct page *page; + int rr, rv = 1; + void *data; + + page = drbd_pp_alloc(mdev, 1); + + data = kmap(page); + while (data_size) { + rr = drbd_recv(mdev, data, min_t(int, data_size, PAGE_SIZE)); + if (rr != min_t(int, data_size, PAGE_SIZE)) { + rv = 0; + dev_warn(DEV, "short read receiving data: read %d expected %d\n", + rr, min_t(int, data_size, PAGE_SIZE)); + break; + } + data_size -= rr; + } + kunmap(page); + drbd_pp_free(mdev, page); + return rv; +} + +static int recv_dless_read(struct drbd_conf *mdev, struct drbd_request *req, + sector_t sector, int data_size) +{ + struct bio_vec *bvec; + struct bio *bio; + int dgs, rr, i, expect; + void *dig_in = mdev->int_dig_in; + void *dig_vv = mdev->int_dig_vv; + + dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_r_tfm) ? + crypto_hash_digestsize(mdev->integrity_r_tfm) : 0; + + if (dgs) { + rr = drbd_recv(mdev, dig_in, dgs); + if (rr != dgs) { + dev_warn(DEV, "short read receiving data reply digest: read %d expected %d\n", + rr, dgs); + return 0; + } + } + + data_size -= dgs; + + /* optimistically update recv_cnt. if receiving fails below, + * we disconnect anyways, and counters will be reset. */ + mdev->recv_cnt += data_size>>9; + + bio = req->master_bio; + D_ASSERT(sector == bio->bi_sector); + + bio_for_each_segment(bvec, bio, i) { + expect = min_t(int, data_size, bvec->bv_len); + rr = drbd_recv(mdev, + kmap(bvec->bv_page)+bvec->bv_offset, + expect); + kunmap(bvec->bv_page); + if (rr != expect) { + dev_warn(DEV, "short read receiving data reply: " + "read %d expected %d\n", + rr, expect); + return 0; + } + data_size -= rr; + } + + if (dgs) { + drbd_csum(mdev, mdev->integrity_r_tfm, bio, dig_vv); + if (memcmp(dig_in, dig_vv, dgs)) { + dev_err(DEV, "Digest integrity check FAILED. Broken NICs?\n"); + return 0; + } + } + + D_ASSERT(data_size == 0); + return 1; +} + +/* e_end_resync_block() is called via + * drbd_process_done_ee() by asender only */ +static int e_end_resync_block(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w; + sector_t sector = e->sector; + int ok; + + D_ASSERT(hlist_unhashed(&e->colision)); + + if (likely(drbd_bio_uptodate(e->private_bio))) { + drbd_set_in_sync(mdev, sector, e->size); + ok = drbd_send_ack(mdev, P_RS_WRITE_ACK, e); + } else { + /* Record failure to sync */ + drbd_rs_failed_io(mdev, sector, e->size); + + ok = drbd_send_ack(mdev, P_NEG_ACK, e); + } + dec_unacked(mdev); + + return ok; +} + +static int recv_resync_read(struct drbd_conf *mdev, sector_t sector, int data_size) __releases(local) +{ + struct drbd_epoch_entry *e; + + e = read_in_block(mdev, ID_SYNCER, sector, data_size); + if (!e) { + put_ldev(mdev); + return FALSE; + } + + dec_rs_pending(mdev); + + e->private_bio->bi_end_io = drbd_endio_write_sec; + e->private_bio->bi_rw = WRITE; + e->w.cb = e_end_resync_block; + + inc_unacked(mdev); + /* corresponding dec_unacked() in e_end_resync_block() + * respective _drbd_clear_done_ee */ + + spin_lock_irq(&mdev->req_lock); + list_add(&e->w.list, &mdev->sync_ee); + spin_unlock_irq(&mdev->req_lock); + + drbd_generic_make_request(mdev, DRBD_FAULT_RS_WR, e->private_bio); + /* accounting done in endio */ + + maybe_kick_lo(mdev); + return TRUE; +} + +static int receive_DataReply(struct drbd_conf *mdev, struct p_header *h) +{ + struct drbd_request *req; + sector_t sector; + unsigned int header_size, data_size; + int ok; + struct p_data *p = (struct p_data *)h; + + header_size = sizeof(*p) - sizeof(*h); + data_size = h->length - header_size; + + ERR_IF(data_size == 0) return FALSE; + + if (drbd_recv(mdev, h->payload, header_size) != header_size) + return FALSE; + + sector = be64_to_cpu(p->sector); + + spin_lock_irq(&mdev->req_lock); + req = _ar_id_to_req(mdev, p->block_id, sector); + spin_unlock_irq(&mdev->req_lock); + if (unlikely(!req)) { + dev_err(DEV, "Got a corrupt block_id/sector pair(1).\n"); + return FALSE; + } + + /* hlist_del(&req->colision) is done in _req_may_be_done, to avoid + * special casing it there for the various failure cases. + * still no race with drbd_fail_pending_reads */ + ok = recv_dless_read(mdev, req, sector, data_size); + + if (ok) + req_mod(req, data_received); + /* else: nothing. handled from drbd_disconnect... + * I don't think we may complete this just yet + * in case we are "on-disconnect: freeze" */ + + return ok; +} + +static int receive_RSDataReply(struct drbd_conf *mdev, struct p_header *h) +{ + sector_t sector; + unsigned int header_size, data_size; + int ok; + struct p_data *p = (struct p_data *)h; + + header_size = sizeof(*p) - sizeof(*h); + data_size = h->length - header_size; + + ERR_IF(data_size == 0) return FALSE; + + if (drbd_recv(mdev, h->payload, header_size) != header_size) + return FALSE; + + sector = be64_to_cpu(p->sector); + D_ASSERT(p->block_id == ID_SYNCER); + + if (get_ldev(mdev)) { + /* data is submitted to disk within recv_resync_read. + * corresponding put_ldev done below on error, + * or in drbd_endio_write_sec. */ + ok = recv_resync_read(mdev, sector, data_size); + } else { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Can not write resync data to local disk.\n"); + + ok = drbd_drain_block(mdev, data_size); + + drbd_send_ack_dp(mdev, P_NEG_ACK, p); + } + + return ok; +} + +/* e_end_block() is called via drbd_process_done_ee(). + * this means this function only runs in the asender thread + */ +static int e_end_block(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w; + sector_t sector = e->sector; + struct drbd_epoch *epoch; + int ok = 1, pcmd; + + if (e->flags & EE_IS_BARRIER) { + epoch = previous_epoch(mdev, e->epoch); + if (epoch) + drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE + (cancel ? EV_CLEANUP : 0)); + } + + if (mdev->net_conf->wire_protocol == DRBD_PROT_C) { + if (likely(drbd_bio_uptodate(e->private_bio))) { + pcmd = (mdev->state.conn >= C_SYNC_SOURCE && + mdev->state.conn <= C_PAUSED_SYNC_T && + e->flags & EE_MAY_SET_IN_SYNC) ? + P_RS_WRITE_ACK : P_WRITE_ACK; + ok &= drbd_send_ack(mdev, pcmd, e); + if (pcmd == P_RS_WRITE_ACK) + drbd_set_in_sync(mdev, sector, e->size); + } else { + ok = drbd_send_ack(mdev, P_NEG_ACK, e); + /* we expect it to be marked out of sync anyways... + * maybe assert this? */ + } + dec_unacked(mdev); + } + /* we delete from the conflict detection hash _after_ we sent out the + * P_WRITE_ACK / P_NEG_ACK, to get the sequence number right. */ + if (mdev->net_conf->two_primaries) { + spin_lock_irq(&mdev->req_lock); + D_ASSERT(!hlist_unhashed(&e->colision)); + hlist_del_init(&e->colision); + spin_unlock_irq(&mdev->req_lock); + } else { + D_ASSERT(hlist_unhashed(&e->colision)); + } + + drbd_may_finish_epoch(mdev, e->epoch, EV_PUT + (cancel ? EV_CLEANUP : 0)); + + return ok; +} + +static int e_send_discard_ack(struct drbd_conf *mdev, struct drbd_work *w, int unused) +{ + struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w; + int ok = 1; + + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C); + ok = drbd_send_ack(mdev, P_DISCARD_ACK, e); + + spin_lock_irq(&mdev->req_lock); + D_ASSERT(!hlist_unhashed(&e->colision)); + hlist_del_init(&e->colision); + spin_unlock_irq(&mdev->req_lock); + + dec_unacked(mdev); + + return ok; +} + +/* Called from receive_Data. + * Synchronize packets on sock with packets on msock. + * + * This is here so even when a P_DATA packet traveling via sock overtook an Ack + * packet traveling on msock, they are still processed in the order they have + * been sent. + * + * Note: we don't care for Ack packets overtaking P_DATA packets. + * + * In case packet_seq is larger than mdev->peer_seq number, there are + * outstanding packets on the msock. We wait for them to arrive. + * In case we are the logically next packet, we update mdev->peer_seq + * ourselves. Correctly handles 32bit wrap around. + * + * Assume we have a 10 GBit connection, that is about 1<<30 byte per second, + * about 1<<21 sectors per second. So "worst" case, we have 1<<3 == 8 seconds + * for the 24bit wrap (historical atomic_t guarantee on some archs), and we have + * 1<<9 == 512 seconds aka ages for the 32bit wrap around... + * + * returns 0 if we may process the packet, + * -ERESTARTSYS if we were interrupted (by disconnect signal). */ +static int drbd_wait_peer_seq(struct drbd_conf *mdev, const u32 packet_seq) +{ + DEFINE_WAIT(wait); + unsigned int p_seq; + long timeout; + int ret = 0; + spin_lock(&mdev->peer_seq_lock); + for (;;) { + prepare_to_wait(&mdev->seq_wait, &wait, TASK_INTERRUPTIBLE); + if (seq_le(packet_seq, mdev->peer_seq+1)) + break; + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + p_seq = mdev->peer_seq; + spin_unlock(&mdev->peer_seq_lock); + timeout = schedule_timeout(30*HZ); + spin_lock(&mdev->peer_seq_lock); + if (timeout == 0 && p_seq == mdev->peer_seq) { + ret = -ETIMEDOUT; + dev_err(DEV, "ASSERT FAILED waited 30 seconds for sequence update, forcing reconnect\n"); + break; + } + } + finish_wait(&mdev->seq_wait, &wait); + if (mdev->peer_seq+1 == packet_seq) + mdev->peer_seq++; + spin_unlock(&mdev->peer_seq_lock); + return ret; +} + +/* mirrored write */ +static int receive_Data(struct drbd_conf *mdev, struct p_header *h) +{ + sector_t sector; + struct drbd_epoch_entry *e; + struct p_data *p = (struct p_data *)h; + int header_size, data_size; + int rw = WRITE; + u32 dp_flags; + + header_size = sizeof(*p) - sizeof(*h); + data_size = h->length - header_size; + + ERR_IF(data_size == 0) return FALSE; + + if (drbd_recv(mdev, h->payload, header_size) != header_size) + return FALSE; + + if (!get_ldev(mdev)) { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Can not write mirrored data block " + "to local disk.\n"); + spin_lock(&mdev->peer_seq_lock); + if (mdev->peer_seq+1 == be32_to_cpu(p->seq_num)) + mdev->peer_seq++; + spin_unlock(&mdev->peer_seq_lock); + + drbd_send_ack_dp(mdev, P_NEG_ACK, p); + atomic_inc(&mdev->current_epoch->epoch_size); + return drbd_drain_block(mdev, data_size); + } + + /* get_ldev(mdev) successful. + * Corresponding put_ldev done either below (on various errors), + * or in drbd_endio_write_sec, if we successfully submit the data at + * the end of this function. */ + + sector = be64_to_cpu(p->sector); + e = read_in_block(mdev, p->block_id, sector, data_size); + if (!e) { + put_ldev(mdev); + return FALSE; + } + + e->private_bio->bi_end_io = drbd_endio_write_sec; + e->w.cb = e_end_block; + + spin_lock(&mdev->epoch_lock); + e->epoch = mdev->current_epoch; + atomic_inc(&e->epoch->epoch_size); + atomic_inc(&e->epoch->active); + + if (mdev->write_ordering == WO_bio_barrier && atomic_read(&e->epoch->epoch_size) == 1) { + struct drbd_epoch *epoch; + /* Issue a barrier if we start a new epoch, and the previous epoch + was not a epoch containing a single request which already was + a Barrier. */ + epoch = list_entry(e->epoch->list.prev, struct drbd_epoch, list); + if (epoch == e->epoch) { + set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags); + rw |= (1<flags |= EE_IS_BARRIER; + } else { + if (atomic_read(&epoch->epoch_size) > 1 || + !test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) { + set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags); + set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags); + rw |= (1<flags |= EE_IS_BARRIER; + } + } + } + spin_unlock(&mdev->epoch_lock); + + dp_flags = be32_to_cpu(p->dp_flags); + if (dp_flags & DP_HARDBARRIER) { + dev_err(DEV, "ASSERT FAILED would have submitted barrier request\n"); + /* rw |= (1<flags |= EE_MAY_SET_IN_SYNC; + + /* I'm the receiver, I do hold a net_cnt reference. */ + if (!mdev->net_conf->two_primaries) { + spin_lock_irq(&mdev->req_lock); + } else { + /* don't get the req_lock yet, + * we may sleep in drbd_wait_peer_seq */ + const int size = e->size; + const int discard = test_bit(DISCARD_CONCURRENT, &mdev->flags); + DEFINE_WAIT(wait); + struct drbd_request *i; + struct hlist_node *n; + struct hlist_head *slot; + int first; + + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C); + BUG_ON(mdev->ee_hash == NULL); + BUG_ON(mdev->tl_hash == NULL); + + /* conflict detection and handling: + * 1. wait on the sequence number, + * in case this data packet overtook ACK packets. + * 2. check our hash tables for conflicting requests. + * we only need to walk the tl_hash, since an ee can not + * have a conflict with an other ee: on the submitting + * node, the corresponding req had already been conflicting, + * and a conflicting req is never sent. + * + * Note: for two_primaries, we are protocol C, + * so there cannot be any request that is DONE + * but still on the transfer log. + * + * unconditionally add to the ee_hash. + * + * if no conflicting request is found: + * submit. + * + * if any conflicting request is found + * that has not yet been acked, + * AND I have the "discard concurrent writes" flag: + * queue (via done_ee) the P_DISCARD_ACK; OUT. + * + * if any conflicting request is found: + * block the receiver, waiting on misc_wait + * until no more conflicting requests are there, + * or we get interrupted (disconnect). + * + * we do not just write after local io completion of those + * requests, but only after req is done completely, i.e. + * we wait for the P_DISCARD_ACK to arrive! + * + * then proceed normally, i.e. submit. + */ + if (drbd_wait_peer_seq(mdev, be32_to_cpu(p->seq_num))) + goto out_interrupted; + + spin_lock_irq(&mdev->req_lock); + + hlist_add_head(&e->colision, ee_hash_slot(mdev, sector)); + +#define OVERLAPS overlaps(i->sector, i->size, sector, size) + slot = tl_hash_slot(mdev, sector); + first = 1; + for (;;) { + int have_unacked = 0; + int have_conflict = 0; + prepare_to_wait(&mdev->misc_wait, &wait, + TASK_INTERRUPTIBLE); + hlist_for_each_entry(i, n, slot, colision) { + if (OVERLAPS) { + /* only ALERT on first iteration, + * we may be woken up early... */ + if (first) + dev_alert(DEV, "%s[%u] Concurrent local write detected!" + " new: %llus +%u; pending: %llus +%u\n", + current->comm, current->pid, + (unsigned long long)sector, size, + (unsigned long long)i->sector, i->size); + if (i->rq_state & RQ_NET_PENDING) + ++have_unacked; + ++have_conflict; + } + } +#undef OVERLAPS + if (!have_conflict) + break; + + /* Discard Ack only for the _first_ iteration */ + if (first && discard && have_unacked) { + dev_alert(DEV, "Concurrent write! [DISCARD BY FLAG] sec=%llus\n", + (unsigned long long)sector); + inc_unacked(mdev); + e->w.cb = e_send_discard_ack; + list_add_tail(&e->w.list, &mdev->done_ee); + + spin_unlock_irq(&mdev->req_lock); + + /* we could probably send that P_DISCARD_ACK ourselves, + * but I don't like the receiver using the msock */ + + put_ldev(mdev); + wake_asender(mdev); + finish_wait(&mdev->misc_wait, &wait); + return TRUE; + } + + if (signal_pending(current)) { + hlist_del_init(&e->colision); + + spin_unlock_irq(&mdev->req_lock); + + finish_wait(&mdev->misc_wait, &wait); + goto out_interrupted; + } + + spin_unlock_irq(&mdev->req_lock); + if (first) { + first = 0; + dev_alert(DEV, "Concurrent write! [W AFTERWARDS] " + "sec=%llus\n", (unsigned long long)sector); + } else if (discard) { + /* we had none on the first iteration. + * there must be none now. */ + D_ASSERT(have_unacked == 0); + } + schedule(); + spin_lock_irq(&mdev->req_lock); + } + finish_wait(&mdev->misc_wait, &wait); + } + + list_add(&e->w.list, &mdev->active_ee); + spin_unlock_irq(&mdev->req_lock); + + switch (mdev->net_conf->wire_protocol) { + case DRBD_PROT_C: + inc_unacked(mdev); + /* corresponding dec_unacked() in e_end_block() + * respective _drbd_clear_done_ee */ + break; + case DRBD_PROT_B: + /* I really don't like it that the receiver thread + * sends on the msock, but anyways */ + drbd_send_ack(mdev, P_RECV_ACK, e); + break; + case DRBD_PROT_A: + /* nothing to do */ + break; + } + + if (mdev->state.pdsk == D_DISKLESS) { + /* In case we have the only disk of the cluster, */ + drbd_set_out_of_sync(mdev, e->sector, e->size); + e->flags |= EE_CALL_AL_COMPLETE_IO; + drbd_al_begin_io(mdev, e->sector); + } + + e->private_bio->bi_rw = rw; + drbd_generic_make_request(mdev, DRBD_FAULT_DT_WR, e->private_bio); + /* accounting done in endio */ + + maybe_kick_lo(mdev); + return TRUE; + +out_interrupted: + /* yes, the epoch_size now is imbalanced. + * but we drop the connection anyways, so we don't have a chance to + * receive a barrier... atomic_inc(&mdev->epoch_size); */ + put_ldev(mdev); + drbd_free_ee(mdev, e); + return FALSE; +} + +static int receive_DataRequest(struct drbd_conf *mdev, struct p_header *h) +{ + sector_t sector; + const sector_t capacity = drbd_get_capacity(mdev->this_bdev); + struct drbd_epoch_entry *e; + struct digest_info *di = NULL; + int size, digest_size; + unsigned int fault_type; + struct p_block_req *p = + (struct p_block_req *)h; + const int brps = sizeof(*p)-sizeof(*h); + + if (drbd_recv(mdev, h->payload, brps) != brps) + return FALSE; + + sector = be64_to_cpu(p->sector); + size = be32_to_cpu(p->blksize); + + if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) { + dev_err(DEV, "%s:%d: sector: %llus, size: %u\n", __FILE__, __LINE__, + (unsigned long long)sector, size); + return FALSE; + } + if (sector + (size>>9) > capacity) { + dev_err(DEV, "%s:%d: sector: %llus, size: %u\n", __FILE__, __LINE__, + (unsigned long long)sector, size); + return FALSE; + } + + if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Can not satisfy peer's read request, " + "no local data.\n"); + drbd_send_ack_rp(mdev, h->command == P_DATA_REQUEST ? P_NEG_DREPLY : + P_NEG_RS_DREPLY , p); + return TRUE; + } + + /* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD + * "criss-cross" setup, that might cause write-out on some other DRBD, + * which in turn might block on the other node at this very place. */ + e = drbd_alloc_ee(mdev, p->block_id, sector, size, GFP_NOIO); + if (!e) { + put_ldev(mdev); + return FALSE; + } + + e->private_bio->bi_rw = READ; + e->private_bio->bi_end_io = drbd_endio_read_sec; + + switch (h->command) { + case P_DATA_REQUEST: + e->w.cb = w_e_end_data_req; + fault_type = DRBD_FAULT_DT_RD; + break; + case P_RS_DATA_REQUEST: + e->w.cb = w_e_end_rsdata_req; + fault_type = DRBD_FAULT_RS_RD; + /* Eventually this should become asynchronously. Currently it + * blocks the whole receiver just to delay the reading of a + * resync data block. + * the drbd_work_queue mechanism is made for this... + */ + if (!drbd_rs_begin_io(mdev, sector)) { + /* we have been interrupted, + * probably connection lost! */ + D_ASSERT(signal_pending(current)); + goto out_free_e; + } + break; + + case P_OV_REPLY: + case P_CSUM_RS_REQUEST: + fault_type = DRBD_FAULT_RS_RD; + digest_size = h->length - brps ; + di = kmalloc(sizeof(*di) + digest_size, GFP_NOIO); + if (!di) + goto out_free_e; + + di->digest_size = digest_size; + di->digest = (((char *)di)+sizeof(struct digest_info)); + + if (drbd_recv(mdev, di->digest, digest_size) != digest_size) + goto out_free_e; + + e->block_id = (u64)(unsigned long)di; + if (h->command == P_CSUM_RS_REQUEST) { + D_ASSERT(mdev->agreed_pro_version >= 89); + e->w.cb = w_e_end_csum_rs_req; + } else if (h->command == P_OV_REPLY) { + e->w.cb = w_e_end_ov_reply; + dec_rs_pending(mdev); + break; + } + + if (!drbd_rs_begin_io(mdev, sector)) { + /* we have been interrupted, probably connection lost! */ + D_ASSERT(signal_pending(current)); + goto out_free_e; + } + break; + + case P_OV_REQUEST: + if (mdev->state.conn >= C_CONNECTED && + mdev->state.conn != C_VERIFY_T) + dev_warn(DEV, "ASSERT FAILED: got P_OV_REQUEST while being %s\n", + drbd_conn_str(mdev->state.conn)); + if (mdev->ov_start_sector == ~(sector_t)0 && + mdev->agreed_pro_version >= 90) { + mdev->ov_start_sector = sector; + mdev->ov_position = sector; + mdev->ov_left = mdev->rs_total - BM_SECT_TO_BIT(sector); + dev_info(DEV, "Online Verify start sector: %llu\n", + (unsigned long long)sector); + } + e->w.cb = w_e_end_ov_req; + fault_type = DRBD_FAULT_RS_RD; + /* Eventually this should become asynchronous. Currently it + * blocks the whole receiver just to delay the reading of a + * resync data block. + * the drbd_work_queue mechanism is made for this... + */ + if (!drbd_rs_begin_io(mdev, sector)) { + /* we have been interrupted, + * probably connection lost! */ + D_ASSERT(signal_pending(current)); + goto out_free_e; + } + break; + + + default: + dev_err(DEV, "unexpected command (%s) in receive_DataRequest\n", + cmdname(h->command)); + fault_type = DRBD_FAULT_MAX; + } + + spin_lock_irq(&mdev->req_lock); + list_add(&e->w.list, &mdev->read_ee); + spin_unlock_irq(&mdev->req_lock); + + inc_unacked(mdev); + + drbd_generic_make_request(mdev, fault_type, e->private_bio); + maybe_kick_lo(mdev); + + return TRUE; + +out_free_e: + kfree(di); + put_ldev(mdev); + drbd_free_ee(mdev, e); + return FALSE; +} + +static int drbd_asb_recover_0p(struct drbd_conf *mdev) __must_hold(local) +{ + int self, peer, rv = -100; + unsigned long ch_self, ch_peer; + + self = mdev->ldev->md.uuid[UI_BITMAP] & 1; + peer = mdev->p_uuid[UI_BITMAP] & 1; + + ch_peer = mdev->p_uuid[UI_SIZE]; + ch_self = mdev->comm_bm_set; + + switch (mdev->net_conf->after_sb_0p) { + case ASB_CONSENSUS: + case ASB_DISCARD_SECONDARY: + case ASB_CALL_HELPER: + dev_err(DEV, "Configuration error.\n"); + break; + case ASB_DISCONNECT: + break; + case ASB_DISCARD_YOUNGER_PRI: + if (self == 0 && peer == 1) { + rv = -1; + break; + } + if (self == 1 && peer == 0) { + rv = 1; + break; + } + /* Else fall through to one of the other strategies... */ + case ASB_DISCARD_OLDER_PRI: + if (self == 0 && peer == 1) { + rv = 1; + break; + } + if (self == 1 && peer == 0) { + rv = -1; + break; + } + /* Else fall through to one of the other strategies... */ + dev_warn(DEV, "Discard younger/older primary did not find a decision\n" + "Using discard-least-changes instead\n"); + case ASB_DISCARD_ZERO_CHG: + if (ch_peer == 0 && ch_self == 0) { + rv = test_bit(DISCARD_CONCURRENT, &mdev->flags) + ? -1 : 1; + break; + } else { + if (ch_peer == 0) { rv = 1; break; } + if (ch_self == 0) { rv = -1; break; } + } + if (mdev->net_conf->after_sb_0p == ASB_DISCARD_ZERO_CHG) + break; + case ASB_DISCARD_LEAST_CHG: + if (ch_self < ch_peer) + rv = -1; + else if (ch_self > ch_peer) + rv = 1; + else /* ( ch_self == ch_peer ) */ + /* Well, then use something else. */ + rv = test_bit(DISCARD_CONCURRENT, &mdev->flags) + ? -1 : 1; + break; + case ASB_DISCARD_LOCAL: + rv = -1; + break; + case ASB_DISCARD_REMOTE: + rv = 1; + } + + return rv; +} + +static int drbd_asb_recover_1p(struct drbd_conf *mdev) __must_hold(local) +{ + int self, peer, hg, rv = -100; + + self = mdev->ldev->md.uuid[UI_BITMAP] & 1; + peer = mdev->p_uuid[UI_BITMAP] & 1; + + switch (mdev->net_conf->after_sb_1p) { + case ASB_DISCARD_YOUNGER_PRI: + case ASB_DISCARD_OLDER_PRI: + case ASB_DISCARD_LEAST_CHG: + case ASB_DISCARD_LOCAL: + case ASB_DISCARD_REMOTE: + dev_err(DEV, "Configuration error.\n"); + break; + case ASB_DISCONNECT: + break; + case ASB_CONSENSUS: + hg = drbd_asb_recover_0p(mdev); + if (hg == -1 && mdev->state.role == R_SECONDARY) + rv = hg; + if (hg == 1 && mdev->state.role == R_PRIMARY) + rv = hg; + break; + case ASB_VIOLENTLY: + rv = drbd_asb_recover_0p(mdev); + break; + case ASB_DISCARD_SECONDARY: + return mdev->state.role == R_PRIMARY ? 1 : -1; + case ASB_CALL_HELPER: + hg = drbd_asb_recover_0p(mdev); + if (hg == -1 && mdev->state.role == R_PRIMARY) { + self = drbd_set_role(mdev, R_SECONDARY, 0); + /* drbd_change_state() does not sleep while in SS_IN_TRANSIENT_STATE, + * we might be here in C_WF_REPORT_PARAMS which is transient. + * we do not need to wait for the after state change work either. */ + self = drbd_change_state(mdev, CS_VERBOSE, NS(role, R_SECONDARY)); + if (self != SS_SUCCESS) { + drbd_khelper(mdev, "pri-lost-after-sb"); + } else { + dev_warn(DEV, "Successfully gave up primary role.\n"); + rv = hg; + } + } else + rv = hg; + } + + return rv; +} + +static int drbd_asb_recover_2p(struct drbd_conf *mdev) __must_hold(local) +{ + int self, peer, hg, rv = -100; + + self = mdev->ldev->md.uuid[UI_BITMAP] & 1; + peer = mdev->p_uuid[UI_BITMAP] & 1; + + switch (mdev->net_conf->after_sb_2p) { + case ASB_DISCARD_YOUNGER_PRI: + case ASB_DISCARD_OLDER_PRI: + case ASB_DISCARD_LEAST_CHG: + case ASB_DISCARD_LOCAL: + case ASB_DISCARD_REMOTE: + case ASB_CONSENSUS: + case ASB_DISCARD_SECONDARY: + dev_err(DEV, "Configuration error.\n"); + break; + case ASB_VIOLENTLY: + rv = drbd_asb_recover_0p(mdev); + break; + case ASB_DISCONNECT: + break; + case ASB_CALL_HELPER: + hg = drbd_asb_recover_0p(mdev); + if (hg == -1) { + /* drbd_change_state() does not sleep while in SS_IN_TRANSIENT_STATE, + * we might be here in C_WF_REPORT_PARAMS which is transient. + * we do not need to wait for the after state change work either. */ + self = drbd_change_state(mdev, CS_VERBOSE, NS(role, R_SECONDARY)); + if (self != SS_SUCCESS) { + drbd_khelper(mdev, "pri-lost-after-sb"); + } else { + dev_warn(DEV, "Successfully gave up primary role.\n"); + rv = hg; + } + } else + rv = hg; + } + + return rv; +} + +static void drbd_uuid_dump(struct drbd_conf *mdev, char *text, u64 *uuid, + u64 bits, u64 flags) +{ + if (!uuid) { + dev_info(DEV, "%s uuid info vanished while I was looking!\n", text); + return; + } + dev_info(DEV, "%s %016llX:%016llX:%016llX:%016llX bits:%llu flags:%llX\n", + text, + (unsigned long long)uuid[UI_CURRENT], + (unsigned long long)uuid[UI_BITMAP], + (unsigned long long)uuid[UI_HISTORY_START], + (unsigned long long)uuid[UI_HISTORY_END], + (unsigned long long)bits, + (unsigned long long)flags); +} + +/* + 100 after split brain try auto recover + 2 C_SYNC_SOURCE set BitMap + 1 C_SYNC_SOURCE use BitMap + 0 no Sync + -1 C_SYNC_TARGET use BitMap + -2 C_SYNC_TARGET set BitMap + -100 after split brain, disconnect +-1000 unrelated data + */ +static int drbd_uuid_compare(struct drbd_conf *mdev, int *rule_nr) __must_hold(local) +{ + u64 self, peer; + int i, j; + + self = mdev->ldev->md.uuid[UI_CURRENT] & ~((u64)1); + peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1); + + *rule_nr = 10; + if (self == UUID_JUST_CREATED && peer == UUID_JUST_CREATED) + return 0; + + *rule_nr = 20; + if ((self == UUID_JUST_CREATED || self == (u64)0) && + peer != UUID_JUST_CREATED) + return -2; + + *rule_nr = 30; + if (self != UUID_JUST_CREATED && + (peer == UUID_JUST_CREATED || peer == (u64)0)) + return 2; + + if (self == peer) { + int rct, dc; /* roles at crash time */ + + if (mdev->p_uuid[UI_BITMAP] == (u64)0 && mdev->ldev->md.uuid[UI_BITMAP] != (u64)0) { + + if (mdev->agreed_pro_version < 91) + return -1001; + + if ((mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START] & ~((u64)1)) && + (mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START + 1] & ~((u64)1))) { + dev_info(DEV, "was SyncSource, missed the resync finished event, corrected myself:\n"); + drbd_uuid_set_bm(mdev, 0UL); + + drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid, + mdev->state.disk >= D_NEGOTIATING ? drbd_bm_total_weight(mdev) : 0, 0); + *rule_nr = 34; + } else { + dev_info(DEV, "was SyncSource (peer failed to write sync_uuid)\n"); + *rule_nr = 36; + } + + return 1; + } + + if (mdev->ldev->md.uuid[UI_BITMAP] == (u64)0 && mdev->p_uuid[UI_BITMAP] != (u64)0) { + + if (mdev->agreed_pro_version < 91) + return -1001; + + if ((mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1)) == (mdev->p_uuid[UI_BITMAP] & ~((u64)1)) && + (mdev->ldev->md.uuid[UI_HISTORY_START + 1] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START] & ~((u64)1))) { + dev_info(DEV, "was SyncTarget, peer missed the resync finished event, corrected peer:\n"); + + mdev->p_uuid[UI_HISTORY_START + 1] = mdev->p_uuid[UI_HISTORY_START]; + mdev->p_uuid[UI_HISTORY_START] = mdev->p_uuid[UI_BITMAP]; + mdev->p_uuid[UI_BITMAP] = 0UL; + + drbd_uuid_dump(mdev, "peer", mdev->p_uuid, mdev->p_uuid[UI_SIZE], mdev->p_uuid[UI_FLAGS]); + *rule_nr = 35; + } else { + dev_info(DEV, "was SyncTarget (failed to write sync_uuid)\n"); + *rule_nr = 37; + } + + return -1; + } + + /* Common power [off|failure] */ + rct = (test_bit(CRASHED_PRIMARY, &mdev->flags) ? 1 : 0) + + (mdev->p_uuid[UI_FLAGS] & 2); + /* lowest bit is set when we were primary, + * next bit (weight 2) is set when peer was primary */ + *rule_nr = 40; + + switch (rct) { + case 0: /* !self_pri && !peer_pri */ return 0; + case 1: /* self_pri && !peer_pri */ return 1; + case 2: /* !self_pri && peer_pri */ return -1; + case 3: /* self_pri && peer_pri */ + dc = test_bit(DISCARD_CONCURRENT, &mdev->flags); + return dc ? -1 : 1; + } + } + + *rule_nr = 50; + peer = mdev->p_uuid[UI_BITMAP] & ~((u64)1); + if (self == peer) + return -1; + + *rule_nr = 51; + peer = mdev->p_uuid[UI_HISTORY_START] & ~((u64)1); + if (self == peer) { + self = mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1); + peer = mdev->p_uuid[UI_HISTORY_START + 1] & ~((u64)1); + if (self == peer) { + /* The last P_SYNC_UUID did not get though. Undo the last start of + resync as sync source modifications of the peer's UUIDs. */ + + if (mdev->agreed_pro_version < 91) + return -1001; + + mdev->p_uuid[UI_BITMAP] = mdev->p_uuid[UI_HISTORY_START]; + mdev->p_uuid[UI_HISTORY_START] = mdev->p_uuid[UI_HISTORY_START + 1]; + return -1; + } + } + + *rule_nr = 60; + self = mdev->ldev->md.uuid[UI_CURRENT] & ~((u64)1); + for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) { + peer = mdev->p_uuid[i] & ~((u64)1); + if (self == peer) + return -2; + } + + *rule_nr = 70; + self = mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1); + peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1); + if (self == peer) + return 1; + + *rule_nr = 71; + self = mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1); + if (self == peer) { + self = mdev->ldev->md.uuid[UI_HISTORY_START + 1] & ~((u64)1); + peer = mdev->p_uuid[UI_HISTORY_START] & ~((u64)1); + if (self == peer) { + /* The last P_SYNC_UUID did not get though. Undo the last start of + resync as sync source modifications of our UUIDs. */ + + if (mdev->agreed_pro_version < 91) + return -1001; + + _drbd_uuid_set(mdev, UI_BITMAP, mdev->ldev->md.uuid[UI_HISTORY_START]); + _drbd_uuid_set(mdev, UI_HISTORY_START, mdev->ldev->md.uuid[UI_HISTORY_START + 1]); + + dev_info(DEV, "Undid last start of resync:\n"); + + drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid, + mdev->state.disk >= D_NEGOTIATING ? drbd_bm_total_weight(mdev) : 0, 0); + + return 1; + } + } + + + *rule_nr = 80; + peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1); + for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) { + self = mdev->ldev->md.uuid[i] & ~((u64)1); + if (self == peer) + return 2; + } + + *rule_nr = 90; + self = mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1); + peer = mdev->p_uuid[UI_BITMAP] & ~((u64)1); + if (self == peer && self != ((u64)0)) + return 100; + + *rule_nr = 100; + for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) { + self = mdev->ldev->md.uuid[i] & ~((u64)1); + for (j = UI_HISTORY_START; j <= UI_HISTORY_END; j++) { + peer = mdev->p_uuid[j] & ~((u64)1); + if (self == peer) + return -100; + } + } + + return -1000; +} + +/* drbd_sync_handshake() returns the new conn state on success, or + CONN_MASK (-1) on failure. + */ +static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_role peer_role, + enum drbd_disk_state peer_disk) __must_hold(local) +{ + int hg, rule_nr; + enum drbd_conns rv = C_MASK; + enum drbd_disk_state mydisk; + + mydisk = mdev->state.disk; + if (mydisk == D_NEGOTIATING) + mydisk = mdev->new_state_tmp.disk; + + dev_info(DEV, "drbd_sync_handshake:\n"); + drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid, mdev->comm_bm_set, 0); + drbd_uuid_dump(mdev, "peer", mdev->p_uuid, + mdev->p_uuid[UI_SIZE], mdev->p_uuid[UI_FLAGS]); + + hg = drbd_uuid_compare(mdev, &rule_nr); + + dev_info(DEV, "uuid_compare()=%d by rule %d\n", hg, rule_nr); + + if (hg == -1000) { + dev_alert(DEV, "Unrelated data, aborting!\n"); + return C_MASK; + } + if (hg == -1001) { + dev_alert(DEV, "To resolve this both sides have to support at least protocol\n"); + return C_MASK; + } + + if ((mydisk == D_INCONSISTENT && peer_disk > D_INCONSISTENT) || + (peer_disk == D_INCONSISTENT && mydisk > D_INCONSISTENT)) { + int f = (hg == -100) || abs(hg) == 2; + hg = mydisk > D_INCONSISTENT ? 1 : -1; + if (f) + hg = hg*2; + dev_info(DEV, "Becoming sync %s due to disk states.\n", + hg > 0 ? "source" : "target"); + } + + if (hg == 100 || (hg == -100 && mdev->net_conf->always_asbp)) { + int pcount = (mdev->state.role == R_PRIMARY) + + (peer_role == R_PRIMARY); + int forced = (hg == -100); + + switch (pcount) { + case 0: + hg = drbd_asb_recover_0p(mdev); + break; + case 1: + hg = drbd_asb_recover_1p(mdev); + break; + case 2: + hg = drbd_asb_recover_2p(mdev); + break; + } + if (abs(hg) < 100) { + dev_warn(DEV, "Split-Brain detected, %d primaries, " + "automatically solved. Sync from %s node\n", + pcount, (hg < 0) ? "peer" : "this"); + if (forced) { + dev_warn(DEV, "Doing a full sync, since" + " UUIDs where ambiguous.\n"); + hg = hg*2; + } + } + } + + if (hg == -100) { + if (mdev->net_conf->want_lose && !(mdev->p_uuid[UI_FLAGS]&1)) + hg = -1; + if (!mdev->net_conf->want_lose && (mdev->p_uuid[UI_FLAGS]&1)) + hg = 1; + + if (abs(hg) < 100) + dev_warn(DEV, "Split-Brain detected, manually solved. " + "Sync from %s node\n", + (hg < 0) ? "peer" : "this"); + } + + if (hg == -100) { + dev_alert(DEV, "Split-Brain detected, dropping connection!\n"); + drbd_khelper(mdev, "split-brain"); + return C_MASK; + } + + if (hg > 0 && mydisk <= D_INCONSISTENT) { + dev_err(DEV, "I shall become SyncSource, but I am inconsistent!\n"); + return C_MASK; + } + + if (hg < 0 && /* by intention we do not use mydisk here. */ + mdev->state.role == R_PRIMARY && mdev->state.disk >= D_CONSISTENT) { + switch (mdev->net_conf->rr_conflict) { + case ASB_CALL_HELPER: + drbd_khelper(mdev, "pri-lost"); + /* fall through */ + case ASB_DISCONNECT: + dev_err(DEV, "I shall become SyncTarget, but I am primary!\n"); + return C_MASK; + case ASB_VIOLENTLY: + dev_warn(DEV, "Becoming SyncTarget, violating the stable-data" + "assumption\n"); + } + } + + if (abs(hg) >= 2) { + dev_info(DEV, "Writing the whole bitmap, full sync required after drbd_sync_handshake.\n"); + if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from sync_handshake")) + return C_MASK; + } + + if (hg > 0) { /* become sync source. */ + rv = C_WF_BITMAP_S; + } else if (hg < 0) { /* become sync target */ + rv = C_WF_BITMAP_T; + } else { + rv = C_CONNECTED; + if (drbd_bm_total_weight(mdev)) { + dev_info(DEV, "No resync, but %lu bits in bitmap!\n", + drbd_bm_total_weight(mdev)); + } + } + + return rv; +} + +/* returns 1 if invalid */ +static int cmp_after_sb(enum drbd_after_sb_p peer, enum drbd_after_sb_p self) +{ + /* ASB_DISCARD_REMOTE - ASB_DISCARD_LOCAL is valid */ + if ((peer == ASB_DISCARD_REMOTE && self == ASB_DISCARD_LOCAL) || + (self == ASB_DISCARD_REMOTE && peer == ASB_DISCARD_LOCAL)) + return 0; + + /* any other things with ASB_DISCARD_REMOTE or ASB_DISCARD_LOCAL are invalid */ + if (peer == ASB_DISCARD_REMOTE || peer == ASB_DISCARD_LOCAL || + self == ASB_DISCARD_REMOTE || self == ASB_DISCARD_LOCAL) + return 1; + + /* everything else is valid if they are equal on both sides. */ + if (peer == self) + return 0; + + /* everything es is invalid. */ + return 1; +} + +static int receive_protocol(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_protocol *p = (struct p_protocol *)h; + int header_size, data_size; + int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p; + int p_want_lose, p_two_primaries; + char p_integrity_alg[SHARED_SECRET_MAX] = ""; + + header_size = sizeof(*p) - sizeof(*h); + data_size = h->length - header_size; + + if (drbd_recv(mdev, h->payload, header_size) != header_size) + return FALSE; + + p_proto = be32_to_cpu(p->protocol); + p_after_sb_0p = be32_to_cpu(p->after_sb_0p); + p_after_sb_1p = be32_to_cpu(p->after_sb_1p); + p_after_sb_2p = be32_to_cpu(p->after_sb_2p); + p_want_lose = be32_to_cpu(p->want_lose); + p_two_primaries = be32_to_cpu(p->two_primaries); + + if (p_proto != mdev->net_conf->wire_protocol) { + dev_err(DEV, "incompatible communication protocols\n"); + goto disconnect; + } + + if (cmp_after_sb(p_after_sb_0p, mdev->net_conf->after_sb_0p)) { + dev_err(DEV, "incompatible after-sb-0pri settings\n"); + goto disconnect; + } + + if (cmp_after_sb(p_after_sb_1p, mdev->net_conf->after_sb_1p)) { + dev_err(DEV, "incompatible after-sb-1pri settings\n"); + goto disconnect; + } + + if (cmp_after_sb(p_after_sb_2p, mdev->net_conf->after_sb_2p)) { + dev_err(DEV, "incompatible after-sb-2pri settings\n"); + goto disconnect; + } + + if (p_want_lose && mdev->net_conf->want_lose) { + dev_err(DEV, "both sides have the 'want_lose' flag set\n"); + goto disconnect; + } + + if (p_two_primaries != mdev->net_conf->two_primaries) { + dev_err(DEV, "incompatible setting of the two-primaries options\n"); + goto disconnect; + } + + if (mdev->agreed_pro_version >= 87) { + unsigned char *my_alg = mdev->net_conf->integrity_alg; + + if (drbd_recv(mdev, p_integrity_alg, data_size) != data_size) + return FALSE; + + p_integrity_alg[SHARED_SECRET_MAX-1] = 0; + if (strcmp(p_integrity_alg, my_alg)) { + dev_err(DEV, "incompatible setting of the data-integrity-alg\n"); + goto disconnect; + } + dev_info(DEV, "data-integrity-alg: %s\n", + my_alg[0] ? my_alg : (unsigned char *)""); + } + + return TRUE; + +disconnect: + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; +} + +/* helper function + * input: alg name, feature name + * return: NULL (alg name was "") + * ERR_PTR(error) if something goes wrong + * or the crypto hash ptr, if it worked out ok. */ +struct crypto_hash *drbd_crypto_alloc_digest_safe(const struct drbd_conf *mdev, + const char *alg, const char *name) +{ + struct crypto_hash *tfm; + + if (!alg[0]) + return NULL; + + tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) { + dev_err(DEV, "Can not allocate \"%s\" as %s (reason: %ld)\n", + alg, name, PTR_ERR(tfm)); + return tfm; + } + if (!drbd_crypto_is_hash(crypto_hash_tfm(tfm))) { + crypto_free_hash(tfm); + dev_err(DEV, "\"%s\" is not a digest (%s)\n", alg, name); + return ERR_PTR(-EINVAL); + } + return tfm; +} + +static int receive_SyncParam(struct drbd_conf *mdev, struct p_header *h) +{ + int ok = TRUE; + struct p_rs_param_89 *p = (struct p_rs_param_89 *)h; + unsigned int header_size, data_size, exp_max_sz; + struct crypto_hash *verify_tfm = NULL; + struct crypto_hash *csums_tfm = NULL; + const int apv = mdev->agreed_pro_version; + + exp_max_sz = apv <= 87 ? sizeof(struct p_rs_param) + : apv == 88 ? sizeof(struct p_rs_param) + + SHARED_SECRET_MAX + : /* 89 */ sizeof(struct p_rs_param_89); + + if (h->length > exp_max_sz) { + dev_err(DEV, "SyncParam packet too long: received %u, expected <= %u bytes\n", + h->length, exp_max_sz); + return FALSE; + } + + if (apv <= 88) { + header_size = sizeof(struct p_rs_param) - sizeof(*h); + data_size = h->length - header_size; + } else /* apv >= 89 */ { + header_size = sizeof(struct p_rs_param_89) - sizeof(*h); + data_size = h->length - header_size; + D_ASSERT(data_size == 0); + } + + /* initialize verify_alg and csums_alg */ + memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX); + + if (drbd_recv(mdev, h->payload, header_size) != header_size) + return FALSE; + + mdev->sync_conf.rate = be32_to_cpu(p->rate); + + if (apv >= 88) { + if (apv == 88) { + if (data_size > SHARED_SECRET_MAX) { + dev_err(DEV, "verify-alg too long, " + "peer wants %u, accepting only %u byte\n", + data_size, SHARED_SECRET_MAX); + return FALSE; + } + + if (drbd_recv(mdev, p->verify_alg, data_size) != data_size) + return FALSE; + + /* we expect NUL terminated string */ + /* but just in case someone tries to be evil */ + D_ASSERT(p->verify_alg[data_size-1] == 0); + p->verify_alg[data_size-1] = 0; + + } else /* apv >= 89 */ { + /* we still expect NUL terminated strings */ + /* but just in case someone tries to be evil */ + D_ASSERT(p->verify_alg[SHARED_SECRET_MAX-1] == 0); + D_ASSERT(p->csums_alg[SHARED_SECRET_MAX-1] == 0); + p->verify_alg[SHARED_SECRET_MAX-1] = 0; + p->csums_alg[SHARED_SECRET_MAX-1] = 0; + } + + if (strcmp(mdev->sync_conf.verify_alg, p->verify_alg)) { + if (mdev->state.conn == C_WF_REPORT_PARAMS) { + dev_err(DEV, "Different verify-alg settings. me=\"%s\" peer=\"%s\"\n", + mdev->sync_conf.verify_alg, p->verify_alg); + goto disconnect; + } + verify_tfm = drbd_crypto_alloc_digest_safe(mdev, + p->verify_alg, "verify-alg"); + if (IS_ERR(verify_tfm)) { + verify_tfm = NULL; + goto disconnect; + } + } + + if (apv >= 89 && strcmp(mdev->sync_conf.csums_alg, p->csums_alg)) { + if (mdev->state.conn == C_WF_REPORT_PARAMS) { + dev_err(DEV, "Different csums-alg settings. me=\"%s\" peer=\"%s\"\n", + mdev->sync_conf.csums_alg, p->csums_alg); + goto disconnect; + } + csums_tfm = drbd_crypto_alloc_digest_safe(mdev, + p->csums_alg, "csums-alg"); + if (IS_ERR(csums_tfm)) { + csums_tfm = NULL; + goto disconnect; + } + } + + + spin_lock(&mdev->peer_seq_lock); + /* lock against drbd_nl_syncer_conf() */ + if (verify_tfm) { + strcpy(mdev->sync_conf.verify_alg, p->verify_alg); + mdev->sync_conf.verify_alg_len = strlen(p->verify_alg) + 1; + crypto_free_hash(mdev->verify_tfm); + mdev->verify_tfm = verify_tfm; + dev_info(DEV, "using verify-alg: \"%s\"\n", p->verify_alg); + } + if (csums_tfm) { + strcpy(mdev->sync_conf.csums_alg, p->csums_alg); + mdev->sync_conf.csums_alg_len = strlen(p->csums_alg) + 1; + crypto_free_hash(mdev->csums_tfm); + mdev->csums_tfm = csums_tfm; + dev_info(DEV, "using csums-alg: \"%s\"\n", p->csums_alg); + } + spin_unlock(&mdev->peer_seq_lock); + } + + return ok; +disconnect: + /* just for completeness: actually not needed, + * as this is not reached if csums_tfm was ok. */ + crypto_free_hash(csums_tfm); + /* but free the verify_tfm again, if csums_tfm did not work out */ + crypto_free_hash(verify_tfm); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; +} + +static void drbd_setup_order_type(struct drbd_conf *mdev, int peer) +{ + /* sorry, we currently have no working implementation + * of distributed TCQ */ +} + +/* warn if the arguments differ by more than 12.5% */ +static void warn_if_differ_considerably(struct drbd_conf *mdev, + const char *s, sector_t a, sector_t b) +{ + sector_t d; + if (a == 0 || b == 0) + return; + d = (a > b) ? (a - b) : (b - a); + if (d > (a>>3) || d > (b>>3)) + dev_warn(DEV, "Considerable difference in %s: %llus vs. %llus\n", s, + (unsigned long long)a, (unsigned long long)b); +} + +static int receive_sizes(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_sizes *p = (struct p_sizes *)h; + enum determine_dev_size dd = unchanged; + unsigned int max_seg_s; + sector_t p_size, p_usize, my_usize; + int ldsc = 0; /* local disk size changed */ + enum drbd_conns nconn; + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE; + if (drbd_recv(mdev, h->payload, h->length) != h->length) + return FALSE; + + p_size = be64_to_cpu(p->d_size); + p_usize = be64_to_cpu(p->u_size); + + if (p_size == 0 && mdev->state.disk == D_DISKLESS) { + dev_err(DEV, "some backing storage is needed\n"); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + + /* just store the peer's disk size for now. + * we still need to figure out whether we accept that. */ + mdev->p_size = p_size; + +#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r)) + if (get_ldev(mdev)) { + warn_if_differ_considerably(mdev, "lower level device sizes", + p_size, drbd_get_max_capacity(mdev->ldev)); + warn_if_differ_considerably(mdev, "user requested size", + p_usize, mdev->ldev->dc.disk_size); + + /* if this is the first connect, or an otherwise expected + * param exchange, choose the minimum */ + if (mdev->state.conn == C_WF_REPORT_PARAMS) + p_usize = min_not_zero((sector_t)mdev->ldev->dc.disk_size, + p_usize); + + my_usize = mdev->ldev->dc.disk_size; + + if (mdev->ldev->dc.disk_size != p_usize) { + mdev->ldev->dc.disk_size = p_usize; + dev_info(DEV, "Peer sets u_size to %lu sectors\n", + (unsigned long)mdev->ldev->dc.disk_size); + } + + /* Never shrink a device with usable data during connect. + But allow online shrinking if we are connected. */ + if (drbd_new_dev_size(mdev, mdev->ldev) < + drbd_get_capacity(mdev->this_bdev) && + mdev->state.disk >= D_OUTDATED && + mdev->state.conn < C_CONNECTED) { + dev_err(DEV, "The peer's disk size is too small!\n"); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + mdev->ldev->dc.disk_size = my_usize; + put_ldev(mdev); + return FALSE; + } + put_ldev(mdev); + } +#undef min_not_zero + + if (get_ldev(mdev)) { + dd = drbd_determin_dev_size(mdev); + put_ldev(mdev); + if (dd == dev_size_error) + return FALSE; + drbd_md_sync(mdev); + } else { + /* I am diskless, need to accept the peer's size. */ + drbd_set_my_capacity(mdev, p_size); + } + + if (mdev->p_uuid && mdev->state.conn <= C_CONNECTED && get_ldev(mdev)) { + nconn = drbd_sync_handshake(mdev, + mdev->state.peer, mdev->state.pdsk); + put_ldev(mdev); + + if (nconn == C_MASK) { + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + + if (drbd_request_state(mdev, NS(conn, nconn)) < SS_SUCCESS) { + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + } + + if (get_ldev(mdev)) { + if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) { + mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev); + ldsc = 1; + } + + max_seg_s = be32_to_cpu(p->max_segment_size); + if (max_seg_s != queue_max_segment_size(mdev->rq_queue)) + drbd_setup_queue_param(mdev, max_seg_s); + + drbd_setup_order_type(mdev, be32_to_cpu(p->queue_order_type)); + put_ldev(mdev); + } + + if (mdev->state.conn > C_WF_REPORT_PARAMS) { + if (be64_to_cpu(p->c_size) != + drbd_get_capacity(mdev->this_bdev) || ldsc) { + /* we have different sizes, probably peer + * needs to know my new size... */ + drbd_send_sizes(mdev, 0); + } + if (test_and_clear_bit(RESIZE_PENDING, &mdev->flags) || + (dd == grew && mdev->state.conn == C_CONNECTED)) { + if (mdev->state.pdsk >= D_INCONSISTENT && + mdev->state.disk >= D_INCONSISTENT) + resync_after_online_grow(mdev); + else + set_bit(RESYNC_AFTER_NEG, &mdev->flags); + } + } + + return TRUE; +} + +static int receive_uuids(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_uuids *p = (struct p_uuids *)h; + u64 *p_uuid; + int i; + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE; + if (drbd_recv(mdev, h->payload, h->length) != h->length) + return FALSE; + + p_uuid = kmalloc(sizeof(u64)*UI_EXTENDED_SIZE, GFP_NOIO); + + for (i = UI_CURRENT; i < UI_EXTENDED_SIZE; i++) + p_uuid[i] = be64_to_cpu(p->uuid[i]); + + kfree(mdev->p_uuid); + mdev->p_uuid = p_uuid; + + if (mdev->state.conn < C_CONNECTED && + mdev->state.disk < D_INCONSISTENT && + mdev->state.role == R_PRIMARY && + (mdev->ed_uuid & ~((u64)1)) != (p_uuid[UI_CURRENT] & ~((u64)1))) { + dev_err(DEV, "Can only connect to data with current UUID=%016llX\n", + (unsigned long long)mdev->ed_uuid); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + + if (get_ldev(mdev)) { + int skip_initial_sync = + mdev->state.conn == C_CONNECTED && + mdev->agreed_pro_version >= 90 && + mdev->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED && + (p_uuid[UI_FLAGS] & 8); + if (skip_initial_sync) { + dev_info(DEV, "Accepted new current UUID, preparing to skip initial sync\n"); + drbd_bitmap_io(mdev, &drbd_bmio_clear_n_write, + "clear_n_write from receive_uuids"); + _drbd_uuid_set(mdev, UI_CURRENT, p_uuid[UI_CURRENT]); + _drbd_uuid_set(mdev, UI_BITMAP, 0); + _drbd_set_state(_NS2(mdev, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE), + CS_VERBOSE, NULL); + drbd_md_sync(mdev); + } + put_ldev(mdev); + } + + /* Before we test for the disk state, we should wait until an eventually + ongoing cluster wide state change is finished. That is important if + we are primary and are detaching from our disk. We need to see the + new disk state... */ + wait_event(mdev->misc_wait, !test_bit(CLUSTER_ST_CHANGE, &mdev->flags)); + if (mdev->state.conn >= C_CONNECTED && mdev->state.disk < D_INCONSISTENT) + drbd_set_ed_uuid(mdev, p_uuid[UI_CURRENT]); + + return TRUE; +} + +/** + * convert_state() - Converts the peer's view of the cluster state to our point of view + * @ps: The state as seen by the peer. + */ +static union drbd_state convert_state(union drbd_state ps) +{ + union drbd_state ms; + + static enum drbd_conns c_tab[] = { + [C_CONNECTED] = C_CONNECTED, + + [C_STARTING_SYNC_S] = C_STARTING_SYNC_T, + [C_STARTING_SYNC_T] = C_STARTING_SYNC_S, + [C_DISCONNECTING] = C_TEAR_DOWN, /* C_NETWORK_FAILURE, */ + [C_VERIFY_S] = C_VERIFY_T, + [C_MASK] = C_MASK, + }; + + ms.i = ps.i; + + ms.conn = c_tab[ps.conn]; + ms.peer = ps.role; + ms.role = ps.peer; + ms.pdsk = ps.disk; + ms.disk = ps.pdsk; + ms.peer_isp = (ps.aftr_isp | ps.user_isp); + + return ms; +} + +static int receive_req_state(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_req_state *p = (struct p_req_state *)h; + union drbd_state mask, val; + int rv; + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE; + if (drbd_recv(mdev, h->payload, h->length) != h->length) + return FALSE; + + mask.i = be32_to_cpu(p->mask); + val.i = be32_to_cpu(p->val); + + if (test_bit(DISCARD_CONCURRENT, &mdev->flags) && + test_bit(CLUSTER_ST_CHANGE, &mdev->flags)) { + drbd_send_sr_reply(mdev, SS_CONCURRENT_ST_CHG); + return TRUE; + } + + mask = convert_state(mask); + val = convert_state(val); + + rv = drbd_change_state(mdev, CS_VERBOSE, mask, val); + + drbd_send_sr_reply(mdev, rv); + drbd_md_sync(mdev); + + return TRUE; +} + +static int receive_state(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_state *p = (struct p_state *)h; + enum drbd_conns nconn, oconn; + union drbd_state ns, peer_state; + enum drbd_disk_state real_peer_disk; + int rv; + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) + return FALSE; + + if (drbd_recv(mdev, h->payload, h->length) != h->length) + return FALSE; + + peer_state.i = be32_to_cpu(p->state); + + real_peer_disk = peer_state.disk; + if (peer_state.disk == D_NEGOTIATING) { + real_peer_disk = mdev->p_uuid[UI_FLAGS] & 4 ? D_INCONSISTENT : D_CONSISTENT; + dev_info(DEV, "real peer disk state = %s\n", drbd_disk_str(real_peer_disk)); + } + + spin_lock_irq(&mdev->req_lock); + retry: + oconn = nconn = mdev->state.conn; + spin_unlock_irq(&mdev->req_lock); + + if (nconn == C_WF_REPORT_PARAMS) + nconn = C_CONNECTED; + + if (mdev->p_uuid && peer_state.disk >= D_NEGOTIATING && + get_ldev_if_state(mdev, D_NEGOTIATING)) { + int cr; /* consider resync */ + + /* if we established a new connection */ + cr = (oconn < C_CONNECTED); + /* if we had an established connection + * and one of the nodes newly attaches a disk */ + cr |= (oconn == C_CONNECTED && + (peer_state.disk == D_NEGOTIATING || + mdev->state.disk == D_NEGOTIATING)); + /* if we have both been inconsistent, and the peer has been + * forced to be UpToDate with --overwrite-data */ + cr |= test_bit(CONSIDER_RESYNC, &mdev->flags); + /* if we had been plain connected, and the admin requested to + * start a sync by "invalidate" or "invalidate-remote" */ + cr |= (oconn == C_CONNECTED && + (peer_state.conn >= C_STARTING_SYNC_S && + peer_state.conn <= C_WF_BITMAP_T)); + + if (cr) + nconn = drbd_sync_handshake(mdev, peer_state.role, real_peer_disk); + + put_ldev(mdev); + if (nconn == C_MASK) { + if (mdev->state.disk == D_NEGOTIATING) { + drbd_force_state(mdev, NS(disk, D_DISKLESS)); + nconn = C_CONNECTED; + } else if (peer_state.disk == D_NEGOTIATING) { + dev_err(DEV, "Disk attach process on the peer node was aborted.\n"); + peer_state.disk = D_DISKLESS; + } else { + D_ASSERT(oconn == C_WF_REPORT_PARAMS); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + } + } + + spin_lock_irq(&mdev->req_lock); + if (mdev->state.conn != oconn) + goto retry; + clear_bit(CONSIDER_RESYNC, &mdev->flags); + ns.i = mdev->state.i; + ns.conn = nconn; + ns.peer = peer_state.role; + ns.pdsk = real_peer_disk; + ns.peer_isp = (peer_state.aftr_isp | peer_state.user_isp); + if ((nconn == C_CONNECTED || nconn == C_WF_BITMAP_S) && ns.disk == D_NEGOTIATING) + ns.disk = mdev->new_state_tmp.disk; + + rv = _drbd_set_state(mdev, ns, CS_VERBOSE | CS_HARD, NULL); + ns = mdev->state; + spin_unlock_irq(&mdev->req_lock); + + if (rv < SS_SUCCESS) { + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return FALSE; + } + + if (oconn > C_WF_REPORT_PARAMS) { + if (nconn > C_CONNECTED && peer_state.conn <= C_CONNECTED && + peer_state.disk != D_NEGOTIATING ) { + /* we want resync, peer has not yet decided to sync... */ + /* Nowadays only used when forcing a node into primary role and + setting its disk to UpToDate with that */ + drbd_send_uuids(mdev); + drbd_send_state(mdev); + } + } + + mdev->net_conf->want_lose = 0; + + drbd_md_sync(mdev); /* update connected indicator, la_size, ... */ + + return TRUE; +} + +static int receive_sync_uuid(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_rs_uuid *p = (struct p_rs_uuid *)h; + + wait_event(mdev->misc_wait, + mdev->state.conn == C_WF_SYNC_UUID || + mdev->state.conn < C_CONNECTED || + mdev->state.disk < D_NEGOTIATING); + + /* D_ASSERT( mdev->state.conn == C_WF_SYNC_UUID ); */ + + ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE; + if (drbd_recv(mdev, h->payload, h->length) != h->length) + return FALSE; + + /* Here the _drbd_uuid_ functions are right, current should + _not_ be rotated into the history */ + if (get_ldev_if_state(mdev, D_NEGOTIATING)) { + _drbd_uuid_set(mdev, UI_CURRENT, be64_to_cpu(p->uuid)); + _drbd_uuid_set(mdev, UI_BITMAP, 0UL); + + drbd_start_resync(mdev, C_SYNC_TARGET); + + put_ldev(mdev); + } else + dev_err(DEV, "Ignoring SyncUUID packet!\n"); + + return TRUE; +} + +enum receive_bitmap_ret { OK, DONE, FAILED }; + +static enum receive_bitmap_ret +receive_bitmap_plain(struct drbd_conf *mdev, struct p_header *h, + unsigned long *buffer, struct bm_xfer_ctx *c) +{ + unsigned num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset); + unsigned want = num_words * sizeof(long); + + if (want != h->length) { + dev_err(DEV, "%s:want (%u) != h->length (%u)\n", __func__, want, h->length); + return FAILED; + } + if (want == 0) + return DONE; + if (drbd_recv(mdev, buffer, want) != want) + return FAILED; + + drbd_bm_merge_lel(mdev, c->word_offset, num_words, buffer); + + c->word_offset += num_words; + c->bit_offset = c->word_offset * BITS_PER_LONG; + if (c->bit_offset > c->bm_bits) + c->bit_offset = c->bm_bits; + + return OK; +} + +static enum receive_bitmap_ret +recv_bm_rle_bits(struct drbd_conf *mdev, + struct p_compressed_bm *p, + struct bm_xfer_ctx *c) +{ + struct bitstream bs; + u64 look_ahead; + u64 rl; + u64 tmp; + unsigned long s = c->bit_offset; + unsigned long e; + int len = p->head.length - (sizeof(*p) - sizeof(p->head)); + int toggle = DCBP_get_start(p); + int have; + int bits; + + bitstream_init(&bs, p->code, len, DCBP_get_pad_bits(p)); + + bits = bitstream_get_bits(&bs, &look_ahead, 64); + if (bits < 0) + return FAILED; + + for (have = bits; have > 0; s += rl, toggle = !toggle) { + bits = vli_decode_bits(&rl, look_ahead); + if (bits <= 0) + return FAILED; + + if (toggle) { + e = s + rl -1; + if (e >= c->bm_bits) { + dev_err(DEV, "bitmap overflow (e:%lu) while decoding bm RLE packet\n", e); + return FAILED; + } + _drbd_bm_set_bits(mdev, s, e); + } + + if (have < bits) { + dev_err(DEV, "bitmap decoding error: h:%d b:%d la:0x%08llx l:%u/%u\n", + have, bits, look_ahead, + (unsigned int)(bs.cur.b - p->code), + (unsigned int)bs.buf_len); + return FAILED; + } + look_ahead >>= bits; + have -= bits; + + bits = bitstream_get_bits(&bs, &tmp, 64 - have); + if (bits < 0) + return FAILED; + look_ahead |= tmp << have; + have += bits; + } + + c->bit_offset = s; + bm_xfer_ctx_bit_to_word_offset(c); + + return (s == c->bm_bits) ? DONE : OK; +} + +static enum receive_bitmap_ret +decode_bitmap_c(struct drbd_conf *mdev, + struct p_compressed_bm *p, + struct bm_xfer_ctx *c) +{ + if (DCBP_get_code(p) == RLE_VLI_Bits) + return recv_bm_rle_bits(mdev, p, c); + + /* other variants had been implemented for evaluation, + * but have been dropped as this one turned out to be "best" + * during all our tests. */ + + dev_err(DEV, "receive_bitmap_c: unknown encoding %u\n", p->encoding); + drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR)); + return FAILED; +} + +void INFO_bm_xfer_stats(struct drbd_conf *mdev, + const char *direction, struct bm_xfer_ctx *c) +{ + /* what would it take to transfer it "plaintext" */ + unsigned plain = sizeof(struct p_header) * + ((c->bm_words+BM_PACKET_WORDS-1)/BM_PACKET_WORDS+1) + + c->bm_words * sizeof(long); + unsigned total = c->bytes[0] + c->bytes[1]; + unsigned r; + + /* total can not be zero. but just in case: */ + if (total == 0) + return; + + /* don't report if not compressed */ + if (total >= plain) + return; + + /* total < plain. check for overflow, still */ + r = (total > UINT_MAX/1000) ? (total / (plain/1000)) + : (1000 * total / plain); + + if (r > 1000) + r = 1000; + + r = 1000 - r; + dev_info(DEV, "%s bitmap stats [Bytes(packets)]: plain %u(%u), RLE %u(%u), " + "total %u; compression: %u.%u%%\n", + direction, + c->bytes[1], c->packets[1], + c->bytes[0], c->packets[0], + total, r/10, r % 10); +} + +/* Since we are processing the bitfield from lower addresses to higher, + it does not matter if the process it in 32 bit chunks or 64 bit + chunks as long as it is little endian. (Understand it as byte stream, + beginning with the lowest byte...) If we would use big endian + we would need to process it from the highest address to the lowest, + in order to be agnostic to the 32 vs 64 bits issue. + + returns 0 on failure, 1 if we successfully received it. */ +static int receive_bitmap(struct drbd_conf *mdev, struct p_header *h) +{ + struct bm_xfer_ctx c; + void *buffer; + enum receive_bitmap_ret ret; + int ok = FALSE; + + wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt)); + + drbd_bm_lock(mdev, "receive bitmap"); + + /* maybe we should use some per thread scratch page, + * and allocate that during initial device creation? */ + buffer = (unsigned long *) __get_free_page(GFP_NOIO); + if (!buffer) { + dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__); + goto out; + } + + c = (struct bm_xfer_ctx) { + .bm_bits = drbd_bm_bits(mdev), + .bm_words = drbd_bm_words(mdev), + }; + + do { + if (h->command == P_BITMAP) { + ret = receive_bitmap_plain(mdev, h, buffer, &c); + } else if (h->command == P_COMPRESSED_BITMAP) { + /* MAYBE: sanity check that we speak proto >= 90, + * and the feature is enabled! */ + struct p_compressed_bm *p; + + if (h->length > BM_PACKET_PAYLOAD_BYTES) { + dev_err(DEV, "ReportCBitmap packet too large\n"); + goto out; + } + /* use the page buff */ + p = buffer; + memcpy(p, h, sizeof(*h)); + if (drbd_recv(mdev, p->head.payload, h->length) != h->length) + goto out; + if (p->head.length <= (sizeof(*p) - sizeof(p->head))) { + dev_err(DEV, "ReportCBitmap packet too small (l:%u)\n", p->head.length); + return FAILED; + } + ret = decode_bitmap_c(mdev, p, &c); + } else { + dev_warn(DEV, "receive_bitmap: h->command neither ReportBitMap nor ReportCBitMap (is 0x%x)", h->command); + goto out; + } + + c.packets[h->command == P_BITMAP]++; + c.bytes[h->command == P_BITMAP] += sizeof(struct p_header) + h->length; + + if (ret != OK) + break; + + if (!drbd_recv_header(mdev, h)) + goto out; + } while (ret == OK); + if (ret == FAILED) + goto out; + + INFO_bm_xfer_stats(mdev, "receive", &c); + + if (mdev->state.conn == C_WF_BITMAP_T) { + ok = !drbd_send_bitmap(mdev); + if (!ok) + goto out; + /* Omit CS_ORDERED with this state transition to avoid deadlocks. */ + ok = _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE); + D_ASSERT(ok == SS_SUCCESS); + } else if (mdev->state.conn != C_WF_BITMAP_S) { + /* admin may have requested C_DISCONNECTING, + * other threads may have noticed network errors */ + dev_info(DEV, "unexpected cstate (%s) in receive_bitmap\n", + drbd_conn_str(mdev->state.conn)); + } + + ok = TRUE; + out: + drbd_bm_unlock(mdev); + if (ok && mdev->state.conn == C_WF_BITMAP_S) + drbd_start_resync(mdev, C_SYNC_SOURCE); + free_page((unsigned long) buffer); + return ok; +} + +static int receive_skip(struct drbd_conf *mdev, struct p_header *h) +{ + /* TODO zero copy sink :) */ + static char sink[128]; + int size, want, r; + + dev_warn(DEV, "skipping unknown optional packet type %d, l: %d!\n", + h->command, h->length); + + size = h->length; + while (size > 0) { + want = min_t(int, size, sizeof(sink)); + r = drbd_recv(mdev, sink, want); + ERR_IF(r <= 0) break; + size -= r; + } + return size == 0; +} + +static int receive_UnplugRemote(struct drbd_conf *mdev, struct p_header *h) +{ + if (mdev->state.disk >= D_INCONSISTENT) + drbd_kick_lo(mdev); + + /* Make sure we've acked all the TCP data associated + * with the data requests being unplugged */ + drbd_tcp_quickack(mdev->data.socket); + + return TRUE; +} + +typedef int (*drbd_cmd_handler_f)(struct drbd_conf *, struct p_header *); + +static drbd_cmd_handler_f drbd_default_handler[] = { + [P_DATA] = receive_Data, + [P_DATA_REPLY] = receive_DataReply, + [P_RS_DATA_REPLY] = receive_RSDataReply, + [P_BARRIER] = receive_Barrier, + [P_BITMAP] = receive_bitmap, + [P_COMPRESSED_BITMAP] = receive_bitmap, + [P_UNPLUG_REMOTE] = receive_UnplugRemote, + [P_DATA_REQUEST] = receive_DataRequest, + [P_RS_DATA_REQUEST] = receive_DataRequest, + [P_SYNC_PARAM] = receive_SyncParam, + [P_SYNC_PARAM89] = receive_SyncParam, + [P_PROTOCOL] = receive_protocol, + [P_UUIDS] = receive_uuids, + [P_SIZES] = receive_sizes, + [P_STATE] = receive_state, + [P_STATE_CHG_REQ] = receive_req_state, + [P_SYNC_UUID] = receive_sync_uuid, + [P_OV_REQUEST] = receive_DataRequest, + [P_OV_REPLY] = receive_DataRequest, + [P_CSUM_RS_REQUEST] = receive_DataRequest, + /* anything missing from this table is in + * the asender_tbl, see get_asender_cmd */ + [P_MAX_CMD] = NULL, +}; + +static drbd_cmd_handler_f *drbd_cmd_handler = drbd_default_handler; +static drbd_cmd_handler_f *drbd_opt_cmd_handler; + +static void drbdd(struct drbd_conf *mdev) +{ + drbd_cmd_handler_f handler; + struct p_header *header = &mdev->data.rbuf.header; + + while (get_t_state(&mdev->receiver) == Running) { + drbd_thread_current_set_cpu(mdev); + if (!drbd_recv_header(mdev, header)) { + drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR)); + break; + } + + if (header->command < P_MAX_CMD) + handler = drbd_cmd_handler[header->command]; + else if (P_MAY_IGNORE < header->command + && header->command < P_MAX_OPT_CMD) + handler = drbd_opt_cmd_handler[header->command-P_MAY_IGNORE]; + else if (header->command > P_MAX_OPT_CMD) + handler = receive_skip; + else + handler = NULL; + + if (unlikely(!handler)) { + dev_err(DEV, "unknown packet type %d, l: %d!\n", + header->command, header->length); + drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR)); + break; + } + if (unlikely(!handler(mdev, header))) { + dev_err(DEV, "error receiving %s, l: %d!\n", + cmdname(header->command), header->length); + drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR)); + break; + } + } +} + +static void drbd_fail_pending_reads(struct drbd_conf *mdev) +{ + struct hlist_head *slot; + struct hlist_node *pos; + struct hlist_node *tmp; + struct drbd_request *req; + int i; + + /* + * Application READ requests + */ + spin_lock_irq(&mdev->req_lock); + for (i = 0; i < APP_R_HSIZE; i++) { + slot = mdev->app_reads_hash+i; + hlist_for_each_entry_safe(req, pos, tmp, slot, colision) { + /* it may (but should not any longer!) + * be on the work queue; if that assert triggers, + * we need to also grab the + * spin_lock_irq(&mdev->data.work.q_lock); + * and list_del_init here. */ + D_ASSERT(list_empty(&req->w.list)); + /* It would be nice to complete outside of spinlock. + * But this is easier for now. */ + _req_mod(req, connection_lost_while_pending); + } + } + for (i = 0; i < APP_R_HSIZE; i++) + if (!hlist_empty(mdev->app_reads_hash+i)) + dev_warn(DEV, "ASSERT FAILED: app_reads_hash[%d].first: " + "%p, should be NULL\n", i, mdev->app_reads_hash[i].first); + + memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *)); + spin_unlock_irq(&mdev->req_lock); +} + +void drbd_flush_workqueue(struct drbd_conf *mdev) +{ + struct drbd_wq_barrier barr; + + barr.w.cb = w_prev_work_done; + init_completion(&barr.done); + drbd_queue_work(&mdev->data.work, &barr.w); + wait_for_completion(&barr.done); +} + +static void drbd_disconnect(struct drbd_conf *mdev) +{ + enum drbd_fencing_p fp; + union drbd_state os, ns; + int rv = SS_UNKNOWN_ERROR; + unsigned int i; + + if (mdev->state.conn == C_STANDALONE) + return; + if (mdev->state.conn >= C_WF_CONNECTION) + dev_err(DEV, "ASSERT FAILED cstate = %s, expected < WFConnection\n", + drbd_conn_str(mdev->state.conn)); + + /* asender does not clean up anything. it must not interfere, either */ + drbd_thread_stop(&mdev->asender); + + mutex_lock(&mdev->data.mutex); + drbd_free_sock(mdev); + mutex_unlock(&mdev->data.mutex); + + spin_lock_irq(&mdev->req_lock); + _drbd_wait_ee_list_empty(mdev, &mdev->active_ee); + _drbd_wait_ee_list_empty(mdev, &mdev->sync_ee); + _drbd_wait_ee_list_empty(mdev, &mdev->read_ee); + spin_unlock_irq(&mdev->req_lock); + + /* We do not have data structures that would allow us to + * get the rs_pending_cnt down to 0 again. + * * On C_SYNC_TARGET we do not have any data structures describing + * the pending RSDataRequest's we have sent. + * * On C_SYNC_SOURCE there is no data structure that tracks + * the P_RS_DATA_REPLY blocks that we sent to the SyncTarget. + * And no, it is not the sum of the reference counts in the + * resync_LRU. The resync_LRU tracks the whole operation including + * the disk-IO, while the rs_pending_cnt only tracks the blocks + * on the fly. */ + drbd_rs_cancel_all(mdev); + mdev->rs_total = 0; + mdev->rs_failed = 0; + atomic_set(&mdev->rs_pending_cnt, 0); + wake_up(&mdev->misc_wait); + + /* make sure syncer is stopped and w_resume_next_sg queued */ + del_timer_sync(&mdev->resync_timer); + set_bit(STOP_SYNC_TIMER, &mdev->flags); + resync_timer_fn((unsigned long)mdev); + + /* wait for all w_e_end_data_req, w_e_end_rsdata_req, w_send_barrier, + * w_make_resync_request etc. which may still be on the worker queue + * to be "canceled" */ + drbd_flush_workqueue(mdev); + + /* This also does reclaim_net_ee(). If we do this too early, we might + * miss some resync ee and pages.*/ + drbd_process_done_ee(mdev); + + kfree(mdev->p_uuid); + mdev->p_uuid = NULL; + + if (!mdev->state.susp) + tl_clear(mdev); + + drbd_fail_pending_reads(mdev); + + dev_info(DEV, "Connection closed\n"); + + drbd_md_sync(mdev); + + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + fp = mdev->ldev->dc.fencing; + put_ldev(mdev); + } + + if (mdev->state.role == R_PRIMARY) { + if (fp >= FP_RESOURCE && mdev->state.pdsk >= D_UNKNOWN) { + enum drbd_disk_state nps = drbd_try_outdate_peer(mdev); + drbd_request_state(mdev, NS(pdsk, nps)); + } + } + + spin_lock_irq(&mdev->req_lock); + os = mdev->state; + if (os.conn >= C_UNCONNECTED) { + /* Do not restart in case we are C_DISCONNECTING */ + ns = os; + ns.conn = C_UNCONNECTED; + rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL); + } + spin_unlock_irq(&mdev->req_lock); + + if (os.conn == C_DISCONNECTING) { + struct hlist_head *h; + wait_event(mdev->misc_wait, atomic_read(&mdev->net_cnt) == 0); + + /* we must not free the tl_hash + * while application io is still on the fly */ + wait_event(mdev->misc_wait, atomic_read(&mdev->ap_bio_cnt) == 0); + + spin_lock_irq(&mdev->req_lock); + /* paranoia code */ + for (h = mdev->ee_hash; h < mdev->ee_hash + mdev->ee_hash_s; h++) + if (h->first) + dev_err(DEV, "ASSERT FAILED ee_hash[%u].first == %p, expected NULL\n", + (int)(h - mdev->ee_hash), h->first); + kfree(mdev->ee_hash); + mdev->ee_hash = NULL; + mdev->ee_hash_s = 0; + + /* paranoia code */ + for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++) + if (h->first) + dev_err(DEV, "ASSERT FAILED tl_hash[%u] == %p, expected NULL\n", + (int)(h - mdev->tl_hash), h->first); + kfree(mdev->tl_hash); + mdev->tl_hash = NULL; + mdev->tl_hash_s = 0; + spin_unlock_irq(&mdev->req_lock); + + crypto_free_hash(mdev->cram_hmac_tfm); + mdev->cram_hmac_tfm = NULL; + + kfree(mdev->net_conf); + mdev->net_conf = NULL; + drbd_request_state(mdev, NS(conn, C_STANDALONE)); + } + + /* tcp_close and release of sendpage pages can be deferred. I don't + * want to use SO_LINGER, because apparently it can be deferred for + * more than 20 seconds (longest time I checked). + * + * Actually we don't care for exactly when the network stack does its + * put_page(), but release our reference on these pages right here. + */ + i = drbd_release_ee(mdev, &mdev->net_ee); + if (i) + dev_info(DEV, "net_ee not empty, killed %u entries\n", i); + i = atomic_read(&mdev->pp_in_use); + if (i) + dev_info(DEV, "pp_in_use = %u, expected 0\n", i); + + D_ASSERT(list_empty(&mdev->read_ee)); + D_ASSERT(list_empty(&mdev->active_ee)); + D_ASSERT(list_empty(&mdev->sync_ee)); + D_ASSERT(list_empty(&mdev->done_ee)); + + /* ok, no more ee's on the fly, it is safe to reset the epoch_size */ + atomic_set(&mdev->current_epoch->epoch_size, 0); + D_ASSERT(list_empty(&mdev->current_epoch->list)); +} + +/* + * We support PRO_VERSION_MIN to PRO_VERSION_MAX. The protocol version + * we can agree on is stored in agreed_pro_version. + * + * feature flags and the reserved array should be enough room for future + * enhancements of the handshake protocol, and possible plugins... + * + * for now, they are expected to be zero, but ignored. + */ +static int drbd_send_handshake(struct drbd_conf *mdev) +{ + /* ASSERT current == mdev->receiver ... */ + struct p_handshake *p = &mdev->data.sbuf.handshake; + int ok; + + if (mutex_lock_interruptible(&mdev->data.mutex)) { + dev_err(DEV, "interrupted during initial handshake\n"); + return 0; /* interrupted. not ok. */ + } + + if (mdev->data.socket == NULL) { + mutex_unlock(&mdev->data.mutex); + return 0; + } + + memset(p, 0, sizeof(*p)); + p->protocol_min = cpu_to_be32(PRO_VERSION_MIN); + p->protocol_max = cpu_to_be32(PRO_VERSION_MAX); + ok = _drbd_send_cmd( mdev, mdev->data.socket, P_HAND_SHAKE, + (struct p_header *)p, sizeof(*p), 0 ); + mutex_unlock(&mdev->data.mutex); + return ok; +} + +/* + * return values: + * 1 yes, we have a valid connection + * 0 oops, did not work out, please try again + * -1 peer talks different language, + * no point in trying again, please go standalone. + */ +static int drbd_do_handshake(struct drbd_conf *mdev) +{ + /* ASSERT current == mdev->receiver ... */ + struct p_handshake *p = &mdev->data.rbuf.handshake; + const int expect = sizeof(struct p_handshake) + -sizeof(struct p_header); + int rv; + + rv = drbd_send_handshake(mdev); + if (!rv) + return 0; + + rv = drbd_recv_header(mdev, &p->head); + if (!rv) + return 0; + + if (p->head.command != P_HAND_SHAKE) { + dev_err(DEV, "expected HandShake packet, received: %s (0x%04x)\n", + cmdname(p->head.command), p->head.command); + return -1; + } + + if (p->head.length != expect) { + dev_err(DEV, "expected HandShake length: %u, received: %u\n", + expect, p->head.length); + return -1; + } + + rv = drbd_recv(mdev, &p->head.payload, expect); + + if (rv != expect) { + dev_err(DEV, "short read receiving handshake packet: l=%u\n", rv); + return 0; + } + + p->protocol_min = be32_to_cpu(p->protocol_min); + p->protocol_max = be32_to_cpu(p->protocol_max); + if (p->protocol_max == 0) + p->protocol_max = p->protocol_min; + + if (PRO_VERSION_MAX < p->protocol_min || + PRO_VERSION_MIN > p->protocol_max) + goto incompat; + + mdev->agreed_pro_version = min_t(int, PRO_VERSION_MAX, p->protocol_max); + + dev_info(DEV, "Handshake successful: " + "Agreed network protocol version %d\n", mdev->agreed_pro_version); + + return 1; + + incompat: + dev_err(DEV, "incompatible DRBD dialects: " + "I support %d-%d, peer supports %d-%d\n", + PRO_VERSION_MIN, PRO_VERSION_MAX, + p->protocol_min, p->protocol_max); + return -1; +} + +#if !defined(CONFIG_CRYPTO_HMAC) && !defined(CONFIG_CRYPTO_HMAC_MODULE) +static int drbd_do_auth(struct drbd_conf *mdev) +{ + dev_err(DEV, "This kernel was build without CONFIG_CRYPTO_HMAC.\n"); + dev_err(DEV, "You need to disable 'cram-hmac-alg' in drbd.conf.\n"); + return 0; +} +#else +#define CHALLENGE_LEN 64 +static int drbd_do_auth(struct drbd_conf *mdev) +{ + char my_challenge[CHALLENGE_LEN]; /* 64 Bytes... */ + struct scatterlist sg; + char *response = NULL; + char *right_response = NULL; + char *peers_ch = NULL; + struct p_header p; + unsigned int key_len = strlen(mdev->net_conf->shared_secret); + unsigned int resp_size; + struct hash_desc desc; + int rv; + + desc.tfm = mdev->cram_hmac_tfm; + desc.flags = 0; + + rv = crypto_hash_setkey(mdev->cram_hmac_tfm, + (u8 *)mdev->net_conf->shared_secret, key_len); + if (rv) { + dev_err(DEV, "crypto_hash_setkey() failed with %d\n", rv); + rv = 0; + goto fail; + } + + get_random_bytes(my_challenge, CHALLENGE_LEN); + + rv = drbd_send_cmd2(mdev, P_AUTH_CHALLENGE, my_challenge, CHALLENGE_LEN); + if (!rv) + goto fail; + + rv = drbd_recv_header(mdev, &p); + if (!rv) + goto fail; + + if (p.command != P_AUTH_CHALLENGE) { + dev_err(DEV, "expected AuthChallenge packet, received: %s (0x%04x)\n", + cmdname(p.command), p.command); + rv = 0; + goto fail; + } + + if (p.length > CHALLENGE_LEN*2) { + dev_err(DEV, "expected AuthChallenge payload too big.\n"); + rv = 0; + goto fail; + } + + peers_ch = kmalloc(p.length, GFP_NOIO); + if (peers_ch == NULL) { + dev_err(DEV, "kmalloc of peers_ch failed\n"); + rv = 0; + goto fail; + } + + rv = drbd_recv(mdev, peers_ch, p.length); + + if (rv != p.length) { + dev_err(DEV, "short read AuthChallenge: l=%u\n", rv); + rv = 0; + goto fail; + } + + resp_size = crypto_hash_digestsize(mdev->cram_hmac_tfm); + response = kmalloc(resp_size, GFP_NOIO); + if (response == NULL) { + dev_err(DEV, "kmalloc of response failed\n"); + rv = 0; + goto fail; + } + + sg_init_table(&sg, 1); + sg_set_buf(&sg, peers_ch, p.length); + + rv = crypto_hash_digest(&desc, &sg, sg.length, response); + if (rv) { + dev_err(DEV, "crypto_hash_digest() failed with %d\n", rv); + rv = 0; + goto fail; + } + + rv = drbd_send_cmd2(mdev, P_AUTH_RESPONSE, response, resp_size); + if (!rv) + goto fail; + + rv = drbd_recv_header(mdev, &p); + if (!rv) + goto fail; + + if (p.command != P_AUTH_RESPONSE) { + dev_err(DEV, "expected AuthResponse packet, received: %s (0x%04x)\n", + cmdname(p.command), p.command); + rv = 0; + goto fail; + } + + if (p.length != resp_size) { + dev_err(DEV, "expected AuthResponse payload of wrong size\n"); + rv = 0; + goto fail; + } + + rv = drbd_recv(mdev, response , resp_size); + + if (rv != resp_size) { + dev_err(DEV, "short read receiving AuthResponse: l=%u\n", rv); + rv = 0; + goto fail; + } + + right_response = kmalloc(resp_size, GFP_NOIO); + if (response == NULL) { + dev_err(DEV, "kmalloc of right_response failed\n"); + rv = 0; + goto fail; + } + + sg_set_buf(&sg, my_challenge, CHALLENGE_LEN); + + rv = crypto_hash_digest(&desc, &sg, sg.length, right_response); + if (rv) { + dev_err(DEV, "crypto_hash_digest() failed with %d\n", rv); + rv = 0; + goto fail; + } + + rv = !memcmp(response, right_response, resp_size); + + if (rv) + dev_info(DEV, "Peer authenticated using %d bytes of '%s' HMAC\n", + resp_size, mdev->net_conf->cram_hmac_alg); + + fail: + kfree(peers_ch); + kfree(response); + kfree(right_response); + + return rv; +} +#endif + +int drbdd_init(struct drbd_thread *thi) +{ + struct drbd_conf *mdev = thi->mdev; + unsigned int minor = mdev_to_minor(mdev); + int h; + + sprintf(current->comm, "drbd%d_receiver", minor); + + dev_info(DEV, "receiver (re)started\n"); + + do { + h = drbd_connect(mdev); + if (h == 0) { + drbd_disconnect(mdev); + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ); + } + if (h == -1) { + dev_warn(DEV, "Discarding network configuration.\n"); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + } + } while (h == 0); + + if (h > 0) { + if (get_net_conf(mdev)) { + drbdd(mdev); + put_net_conf(mdev); + } + } + + drbd_disconnect(mdev); + + dev_info(DEV, "receiver terminated\n"); + return 0; +} + +/* ********* acknowledge sender ******** */ + +static int got_RqSReply(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_req_state_reply *p = (struct p_req_state_reply *)h; + + int retcode = be32_to_cpu(p->retcode); + + if (retcode >= SS_SUCCESS) { + set_bit(CL_ST_CHG_SUCCESS, &mdev->flags); + } else { + set_bit(CL_ST_CHG_FAIL, &mdev->flags); + dev_err(DEV, "Requested state change failed by peer: %s (%d)\n", + drbd_set_st_err_str(retcode), retcode); + } + wake_up(&mdev->state_wait); + + return TRUE; +} + +static int got_Ping(struct drbd_conf *mdev, struct p_header *h) +{ + return drbd_send_ping_ack(mdev); + +} + +static int got_PingAck(struct drbd_conf *mdev, struct p_header *h) +{ + /* restore idle timeout */ + mdev->meta.socket->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ; + + return TRUE; +} + +static int got_IsInSync(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_block_ack *p = (struct p_block_ack *)h; + sector_t sector = be64_to_cpu(p->sector); + int blksize = be32_to_cpu(p->blksize); + + D_ASSERT(mdev->agreed_pro_version >= 89); + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + + drbd_rs_complete_io(mdev, sector); + drbd_set_in_sync(mdev, sector, blksize); + /* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */ + mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT); + dec_rs_pending(mdev); + + return TRUE; +} + +/* when we receive the ACK for a write request, + * verify that we actually know about it */ +static struct drbd_request *_ack_id_to_req(struct drbd_conf *mdev, + u64 id, sector_t sector) +{ + struct hlist_head *slot = tl_hash_slot(mdev, sector); + struct hlist_node *n; + struct drbd_request *req; + + hlist_for_each_entry(req, n, slot, colision) { + if ((unsigned long)req == (unsigned long)id) { + if (req->sector != sector) { + dev_err(DEV, "_ack_id_to_req: found req %p but it has " + "wrong sector (%llus versus %llus)\n", req, + (unsigned long long)req->sector, + (unsigned long long)sector); + break; + } + return req; + } + } + dev_err(DEV, "_ack_id_to_req: failed to find req %p, sector %llus in list\n", + (void *)(unsigned long)id, (unsigned long long)sector); + return NULL; +} + +typedef struct drbd_request *(req_validator_fn) + (struct drbd_conf *mdev, u64 id, sector_t sector); + +static int validate_req_change_req_state(struct drbd_conf *mdev, + u64 id, sector_t sector, req_validator_fn validator, + const char *func, enum drbd_req_event what) +{ + struct drbd_request *req; + struct bio_and_error m; + + spin_lock_irq(&mdev->req_lock); + req = validator(mdev, id, sector); + if (unlikely(!req)) { + spin_unlock_irq(&mdev->req_lock); + dev_err(DEV, "%s: got a corrupt block_id/sector pair\n", func); + return FALSE; + } + __req_mod(req, what, &m); + spin_unlock_irq(&mdev->req_lock); + + if (m.bio) + complete_master_bio(mdev, &m); + return TRUE; +} + +static int got_BlockAck(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_block_ack *p = (struct p_block_ack *)h; + sector_t sector = be64_to_cpu(p->sector); + int blksize = be32_to_cpu(p->blksize); + enum drbd_req_event what; + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + + if (is_syncer_block_id(p->block_id)) { + drbd_set_in_sync(mdev, sector, blksize); + dec_rs_pending(mdev); + return TRUE; + } + switch (be16_to_cpu(h->command)) { + case P_RS_WRITE_ACK: + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C); + what = write_acked_by_peer_and_sis; + break; + case P_WRITE_ACK: + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C); + what = write_acked_by_peer; + break; + case P_RECV_ACK: + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_B); + what = recv_acked_by_peer; + break; + case P_DISCARD_ACK: + D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C); + what = conflict_discarded_by_peer; + break; + default: + D_ASSERT(0); + return FALSE; + } + + return validate_req_change_req_state(mdev, p->block_id, sector, + _ack_id_to_req, __func__ , what); +} + +static int got_NegAck(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_block_ack *p = (struct p_block_ack *)h; + sector_t sector = be64_to_cpu(p->sector); + + if (__ratelimit(&drbd_ratelimit_state)) + dev_warn(DEV, "Got NegAck packet. Peer is in troubles?\n"); + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + + if (is_syncer_block_id(p->block_id)) { + int size = be32_to_cpu(p->blksize); + dec_rs_pending(mdev); + drbd_rs_failed_io(mdev, sector, size); + return TRUE; + } + return validate_req_change_req_state(mdev, p->block_id, sector, + _ack_id_to_req, __func__ , neg_acked); +} + +static int got_NegDReply(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_block_ack *p = (struct p_block_ack *)h; + sector_t sector = be64_to_cpu(p->sector); + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + dev_err(DEV, "Got NegDReply; Sector %llus, len %u; Fail original request.\n", + (unsigned long long)sector, be32_to_cpu(p->blksize)); + + return validate_req_change_req_state(mdev, p->block_id, sector, + _ar_id_to_req, __func__ , neg_acked); +} + +static int got_NegRSDReply(struct drbd_conf *mdev, struct p_header *h) +{ + sector_t sector; + int size; + struct p_block_ack *p = (struct p_block_ack *)h; + + sector = be64_to_cpu(p->sector); + size = be32_to_cpu(p->blksize); + D_ASSERT(p->block_id == ID_SYNCER); + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + + dec_rs_pending(mdev); + + if (get_ldev_if_state(mdev, D_FAILED)) { + drbd_rs_complete_io(mdev, sector); + drbd_rs_failed_io(mdev, sector, size); + put_ldev(mdev); + } + + return TRUE; +} + +static int got_BarrierAck(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_barrier_ack *p = (struct p_barrier_ack *)h; + + tl_release(mdev, p->barrier, be32_to_cpu(p->set_size)); + + return TRUE; +} + +static int got_OVResult(struct drbd_conf *mdev, struct p_header *h) +{ + struct p_block_ack *p = (struct p_block_ack *)h; + struct drbd_work *w; + sector_t sector; + int size; + + sector = be64_to_cpu(p->sector); + size = be32_to_cpu(p->blksize); + + update_peer_seq(mdev, be32_to_cpu(p->seq_num)); + + if (be64_to_cpu(p->block_id) == ID_OUT_OF_SYNC) + drbd_ov_oos_found(mdev, sector, size); + else + ov_oos_print(mdev); + + drbd_rs_complete_io(mdev, sector); + dec_rs_pending(mdev); + + if (--mdev->ov_left == 0) { + w = kmalloc(sizeof(*w), GFP_NOIO); + if (w) { + w->cb = w_ov_finished; + drbd_queue_work_front(&mdev->data.work, w); + } else { + dev_err(DEV, "kmalloc(w) failed."); + ov_oos_print(mdev); + drbd_resync_finished(mdev); + } + } + return TRUE; +} + +struct asender_cmd { + size_t pkt_size; + int (*process)(struct drbd_conf *mdev, struct p_header *h); +}; + +static struct asender_cmd *get_asender_cmd(int cmd) +{ + static struct asender_cmd asender_tbl[] = { + /* anything missing from this table is in + * the drbd_cmd_handler (drbd_default_handler) table, + * see the beginning of drbdd() */ + [P_PING] = { sizeof(struct p_header), got_Ping }, + [P_PING_ACK] = { sizeof(struct p_header), got_PingAck }, + [P_RECV_ACK] = { sizeof(struct p_block_ack), got_BlockAck }, + [P_WRITE_ACK] = { sizeof(struct p_block_ack), got_BlockAck }, + [P_RS_WRITE_ACK] = { sizeof(struct p_block_ack), got_BlockAck }, + [P_DISCARD_ACK] = { sizeof(struct p_block_ack), got_BlockAck }, + [P_NEG_ACK] = { sizeof(struct p_block_ack), got_NegAck }, + [P_NEG_DREPLY] = { sizeof(struct p_block_ack), got_NegDReply }, + [P_NEG_RS_DREPLY] = { sizeof(struct p_block_ack), got_NegRSDReply}, + [P_OV_RESULT] = { sizeof(struct p_block_ack), got_OVResult }, + [P_BARRIER_ACK] = { sizeof(struct p_barrier_ack), got_BarrierAck }, + [P_STATE_CHG_REPLY] = { sizeof(struct p_req_state_reply), got_RqSReply }, + [P_RS_IS_IN_SYNC] = { sizeof(struct p_block_ack), got_IsInSync }, + [P_MAX_CMD] = { 0, NULL }, + }; + if (cmd > P_MAX_CMD || asender_tbl[cmd].process == NULL) + return NULL; + return &asender_tbl[cmd]; +} + +int drbd_asender(struct drbd_thread *thi) +{ + struct drbd_conf *mdev = thi->mdev; + struct p_header *h = &mdev->meta.rbuf.header; + struct asender_cmd *cmd = NULL; + + int rv, len; + void *buf = h; + int received = 0; + int expect = sizeof(struct p_header); + int empty; + + sprintf(current->comm, "drbd%d_asender", mdev_to_minor(mdev)); + + current->policy = SCHED_RR; /* Make this a realtime task! */ + current->rt_priority = 2; /* more important than all other tasks */ + + while (get_t_state(thi) == Running) { + drbd_thread_current_set_cpu(mdev); + if (test_and_clear_bit(SEND_PING, &mdev->flags)) { + ERR_IF(!drbd_send_ping(mdev)) goto reconnect; + mdev->meta.socket->sk->sk_rcvtimeo = + mdev->net_conf->ping_timeo*HZ/10; + } + + /* conditionally cork; + * it may hurt latency if we cork without much to send */ + if (!mdev->net_conf->no_cork && + 3 < atomic_read(&mdev->unacked_cnt)) + drbd_tcp_cork(mdev->meta.socket); + while (1) { + clear_bit(SIGNAL_ASENDER, &mdev->flags); + flush_signals(current); + if (!drbd_process_done_ee(mdev)) { + dev_err(DEV, "process_done_ee() = NOT_OK\n"); + goto reconnect; + } + /* to avoid race with newly queued ACKs */ + set_bit(SIGNAL_ASENDER, &mdev->flags); + spin_lock_irq(&mdev->req_lock); + empty = list_empty(&mdev->done_ee); + spin_unlock_irq(&mdev->req_lock); + /* new ack may have been queued right here, + * but then there is also a signal pending, + * and we start over... */ + if (empty) + break; + } + /* but unconditionally uncork unless disabled */ + if (!mdev->net_conf->no_cork) + drbd_tcp_uncork(mdev->meta.socket); + + /* short circuit, recv_msg would return EINTR anyways. */ + if (signal_pending(current)) + continue; + + rv = drbd_recv_short(mdev, mdev->meta.socket, + buf, expect-received, 0); + clear_bit(SIGNAL_ASENDER, &mdev->flags); + + flush_signals(current); + + /* Note: + * -EINTR (on meta) we got a signal + * -EAGAIN (on meta) rcvtimeo expired + * -ECONNRESET other side closed the connection + * -ERESTARTSYS (on data) we got a signal + * rv < 0 other than above: unexpected error! + * rv == expected: full header or command + * rv < expected: "woken" by signal during receive + * rv == 0 : "connection shut down by peer" + */ + if (likely(rv > 0)) { + received += rv; + buf += rv; + } else if (rv == 0) { + dev_err(DEV, "meta connection shut down by peer.\n"); + goto reconnect; + } else if (rv == -EAGAIN) { + if (mdev->meta.socket->sk->sk_rcvtimeo == + mdev->net_conf->ping_timeo*HZ/10) { + dev_err(DEV, "PingAck did not arrive in time.\n"); + goto reconnect; + } + set_bit(SEND_PING, &mdev->flags); + continue; + } else if (rv == -EINTR) { + continue; + } else { + dev_err(DEV, "sock_recvmsg returned %d\n", rv); + goto reconnect; + } + + if (received == expect && cmd == NULL) { + if (unlikely(h->magic != BE_DRBD_MAGIC)) { + dev_err(DEV, "magic?? on meta m: 0x%lx c: %d l: %d\n", + (long)be32_to_cpu(h->magic), + h->command, h->length); + goto reconnect; + } + cmd = get_asender_cmd(be16_to_cpu(h->command)); + len = be16_to_cpu(h->length); + if (unlikely(cmd == NULL)) { + dev_err(DEV, "unknown command?? on meta m: 0x%lx c: %d l: %d\n", + (long)be32_to_cpu(h->magic), + h->command, h->length); + goto disconnect; + } + expect = cmd->pkt_size; + ERR_IF(len != expect-sizeof(struct p_header)) + goto reconnect; + } + if (received == expect) { + D_ASSERT(cmd != NULL); + if (!cmd->process(mdev, h)) + goto reconnect; + + buf = h; + received = 0; + expect = sizeof(struct p_header); + cmd = NULL; + } + } + + if (0) { +reconnect: + drbd_force_state(mdev, NS(conn, C_NETWORK_FAILURE)); + } + if (0) { +disconnect: + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + } + clear_bit(SIGNAL_ASENDER, &mdev->flags); + + D_ASSERT(mdev->state.conn < C_CONNECTED); + dev_info(DEV, "asender terminated\n"); + + return 0; +} diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c new file mode 100644 index 000000000000..de81ab7b4627 --- /dev/null +++ b/drivers/block/drbd/drbd_req.c @@ -0,0 +1,1125 @@ +/* + drbd_req.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include + +#include +#include +#include "drbd_int.h" +#include "drbd_req.h" + + +/* Update disk stats at start of I/O request */ +static void _drbd_start_io_acct(struct drbd_conf *mdev, struct drbd_request *req, struct bio *bio) +{ + const int rw = bio_data_dir(bio); + int cpu; + cpu = part_stat_lock(); + part_stat_inc(cpu, &mdev->vdisk->part0, ios[rw]); + part_stat_add(cpu, &mdev->vdisk->part0, sectors[rw], bio_sectors(bio)); + part_inc_in_flight(&mdev->vdisk->part0, rw); + part_stat_unlock(); +} + +/* Update disk stats when completing request upwards */ +static void _drbd_end_io_acct(struct drbd_conf *mdev, struct drbd_request *req) +{ + int rw = bio_data_dir(req->master_bio); + unsigned long duration = jiffies - req->start_time; + int cpu; + cpu = part_stat_lock(); + part_stat_add(cpu, &mdev->vdisk->part0, ticks[rw], duration); + part_round_stats(cpu, &mdev->vdisk->part0); + part_dec_in_flight(&mdev->vdisk->part0, rw); + part_stat_unlock(); +} + +static void _req_is_done(struct drbd_conf *mdev, struct drbd_request *req, const int rw) +{ + const unsigned long s = req->rq_state; + /* if it was a write, we may have to set the corresponding + * bit(s) out-of-sync first. If it had a local part, we need to + * release the reference to the activity log. */ + if (rw == WRITE) { + /* remove it from the transfer log. + * well, only if it had been there in the first + * place... if it had not (local only or conflicting + * and never sent), it should still be "empty" as + * initialized in drbd_req_new(), so we can list_del() it + * here unconditionally */ + list_del(&req->tl_requests); + /* Set out-of-sync unless both OK flags are set + * (local only or remote failed). + * Other places where we set out-of-sync: + * READ with local io-error */ + if (!(s & RQ_NET_OK) || !(s & RQ_LOCAL_OK)) + drbd_set_out_of_sync(mdev, req->sector, req->size); + + if ((s & RQ_NET_OK) && (s & RQ_LOCAL_OK) && (s & RQ_NET_SIS)) + drbd_set_in_sync(mdev, req->sector, req->size); + + /* one might be tempted to move the drbd_al_complete_io + * to the local io completion callback drbd_endio_pri. + * but, if this was a mirror write, we may only + * drbd_al_complete_io after this is RQ_NET_DONE, + * otherwise the extent could be dropped from the al + * before it has actually been written on the peer. + * if we crash before our peer knows about the request, + * but after the extent has been dropped from the al, + * we would forget to resync the corresponding extent. + */ + if (s & RQ_LOCAL_MASK) { + if (get_ldev_if_state(mdev, D_FAILED)) { + drbd_al_complete_io(mdev, req->sector); + put_ldev(mdev); + } else if (__ratelimit(&drbd_ratelimit_state)) { + dev_warn(DEV, "Should have called drbd_al_complete_io(, %llu), " + "but my Disk seems to have failed :(\n", + (unsigned long long) req->sector); + } + } + } + + /* if it was a local io error, we want to notify our + * peer about that, and see if we need to + * detach the disk and stuff. + * to avoid allocating some special work + * struct, reuse the request. */ + + /* THINK + * why do we do this not when we detect the error, + * but delay it until it is "done", i.e. possibly + * until the next barrier ack? */ + + if (rw == WRITE && + ((s & RQ_LOCAL_MASK) && !(s & RQ_LOCAL_OK))) { + if (!(req->w.list.next == LIST_POISON1 || + list_empty(&req->w.list))) { + /* DEBUG ASSERT only; if this triggers, we + * probably corrupt the worker list here */ + dev_err(DEV, "req->w.list.next = %p\n", req->w.list.next); + dev_err(DEV, "req->w.list.prev = %p\n", req->w.list.prev); + } + req->w.cb = w_io_error; + drbd_queue_work(&mdev->data.work, &req->w); + /* drbd_req_free() is done in w_io_error */ + } else { + drbd_req_free(req); + } +} + +static void queue_barrier(struct drbd_conf *mdev) +{ + struct drbd_tl_epoch *b; + + /* We are within the req_lock. Once we queued the barrier for sending, + * we set the CREATE_BARRIER bit. It is cleared as soon as a new + * barrier/epoch object is added. This is the only place this bit is + * set. It indicates that the barrier for this epoch is already queued, + * and no new epoch has been created yet. */ + if (test_bit(CREATE_BARRIER, &mdev->flags)) + return; + + b = mdev->newest_tle; + b->w.cb = w_send_barrier; + /* inc_ap_pending done here, so we won't + * get imbalanced on connection loss. + * dec_ap_pending will be done in got_BarrierAck + * or (on connection loss) in tl_clear. */ + inc_ap_pending(mdev); + drbd_queue_work(&mdev->data.work, &b->w); + set_bit(CREATE_BARRIER, &mdev->flags); +} + +static void _about_to_complete_local_write(struct drbd_conf *mdev, + struct drbd_request *req) +{ + const unsigned long s = req->rq_state; + struct drbd_request *i; + struct drbd_epoch_entry *e; + struct hlist_node *n; + struct hlist_head *slot; + + /* before we can signal completion to the upper layers, + * we may need to close the current epoch */ + if (mdev->state.conn >= C_CONNECTED && + req->epoch == mdev->newest_tle->br_number) + queue_barrier(mdev); + + /* we need to do the conflict detection stuff, + * if we have the ee_hash (two_primaries) and + * this has been on the network */ + if ((s & RQ_NET_DONE) && mdev->ee_hash != NULL) { + const sector_t sector = req->sector; + const int size = req->size; + + /* ASSERT: + * there must be no conflicting requests, since + * they must have been failed on the spot */ +#define OVERLAPS overlaps(sector, size, i->sector, i->size) + slot = tl_hash_slot(mdev, sector); + hlist_for_each_entry(i, n, slot, colision) { + if (OVERLAPS) { + dev_alert(DEV, "LOGIC BUG: completed: %p %llus +%u; " + "other: %p %llus +%u\n", + req, (unsigned long long)sector, size, + i, (unsigned long long)i->sector, i->size); + } + } + + /* maybe "wake" those conflicting epoch entries + * that wait for this request to finish. + * + * currently, there can be only _one_ such ee + * (well, or some more, which would be pending + * P_DISCARD_ACK not yet sent by the asender...), + * since we block the receiver thread upon the + * first conflict detection, which will wait on + * misc_wait. maybe we want to assert that? + * + * anyways, if we found one, + * we just have to do a wake_up. */ +#undef OVERLAPS +#define OVERLAPS overlaps(sector, size, e->sector, e->size) + slot = ee_hash_slot(mdev, req->sector); + hlist_for_each_entry(e, n, slot, colision) { + if (OVERLAPS) { + wake_up(&mdev->misc_wait); + break; + } + } + } +#undef OVERLAPS +} + +void complete_master_bio(struct drbd_conf *mdev, + struct bio_and_error *m) +{ + bio_endio(m->bio, m->error); + dec_ap_bio(mdev); +} + +/* Helper for __req_mod(). + * Set m->bio to the master bio, if it is fit to be completed, + * or leave it alone (it is initialized to NULL in __req_mod), + * if it has already been completed, or cannot be completed yet. + * If m->bio is set, the error status to be returned is placed in m->error. + */ +void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m) +{ + const unsigned long s = req->rq_state; + struct drbd_conf *mdev = req->mdev; + /* only WRITES may end up here without a master bio (on barrier ack) */ + int rw = req->master_bio ? bio_data_dir(req->master_bio) : WRITE; + + /* we must not complete the master bio, while it is + * still being processed by _drbd_send_zc_bio (drbd_send_dblock) + * not yet acknowledged by the peer + * not yet completed by the local io subsystem + * these flags may get cleared in any order by + * the worker, + * the receiver, + * the bio_endio completion callbacks. + */ + if (s & RQ_NET_QUEUED) + return; + if (s & RQ_NET_PENDING) + return; + if (s & RQ_LOCAL_PENDING) + return; + + if (req->master_bio) { + /* this is data_received (remote read) + * or protocol C P_WRITE_ACK + * or protocol B P_RECV_ACK + * or protocol A "handed_over_to_network" (SendAck) + * or canceled or failed, + * or killed from the transfer log due to connection loss. + */ + + /* + * figure out whether to report success or failure. + * + * report success when at least one of the operations succeeded. + * or, to put the other way, + * only report failure, when both operations failed. + * + * what to do about the failures is handled elsewhere. + * what we need to do here is just: complete the master_bio. + * + * local completion error, if any, has been stored as ERR_PTR + * in private_bio within drbd_endio_pri. + */ + int ok = (s & RQ_LOCAL_OK) || (s & RQ_NET_OK); + int error = PTR_ERR(req->private_bio); + + /* remove the request from the conflict detection + * respective block_id verification hash */ + if (!hlist_unhashed(&req->colision)) + hlist_del(&req->colision); + else + D_ASSERT((s & RQ_NET_MASK) == 0); + + /* for writes we need to do some extra housekeeping */ + if (rw == WRITE) + _about_to_complete_local_write(mdev, req); + + /* Update disk stats */ + _drbd_end_io_acct(mdev, req); + + m->error = ok ? 0 : (error ?: -EIO); + m->bio = req->master_bio; + req->master_bio = NULL; + } + + if ((s & RQ_NET_MASK) == 0 || (s & RQ_NET_DONE)) { + /* this is disconnected (local only) operation, + * or protocol C P_WRITE_ACK, + * or protocol A or B P_BARRIER_ACK, + * or killed from the transfer log due to connection loss. */ + _req_is_done(mdev, req, rw); + } + /* else: network part and not DONE yet. that is + * protocol A or B, barrier ack still pending... */ +} + +/* + * checks whether there was an overlapping request + * or ee already registered. + * + * if so, return 1, in which case this request is completed on the spot, + * without ever being submitted or send. + * + * return 0 if it is ok to submit this request. + * + * NOTE: + * paranoia: assume something above us is broken, and issues different write + * requests for the same block simultaneously... + * + * To ensure these won't be reordered differently on both nodes, resulting in + * diverging data sets, we discard the later one(s). Not that this is supposed + * to happen, but this is the rationale why we also have to check for + * conflicting requests with local origin, and why we have to do so regardless + * of whether we allowed multiple primaries. + * + * BTW, in case we only have one primary, the ee_hash is empty anyways, and the + * second hlist_for_each_entry becomes a noop. This is even simpler than to + * grab a reference on the net_conf, and check for the two_primaries flag... + */ +static int _req_conflicts(struct drbd_request *req) +{ + struct drbd_conf *mdev = req->mdev; + const sector_t sector = req->sector; + const int size = req->size; + struct drbd_request *i; + struct drbd_epoch_entry *e; + struct hlist_node *n; + struct hlist_head *slot; + + D_ASSERT(hlist_unhashed(&req->colision)); + + if (!get_net_conf(mdev)) + return 0; + + /* BUG_ON */ + ERR_IF (mdev->tl_hash_s == 0) + goto out_no_conflict; + BUG_ON(mdev->tl_hash == NULL); + +#define OVERLAPS overlaps(i->sector, i->size, sector, size) + slot = tl_hash_slot(mdev, sector); + hlist_for_each_entry(i, n, slot, colision) { + if (OVERLAPS) { + dev_alert(DEV, "%s[%u] Concurrent local write detected! " + "[DISCARD L] new: %llus +%u; " + "pending: %llus +%u\n", + current->comm, current->pid, + (unsigned long long)sector, size, + (unsigned long long)i->sector, i->size); + goto out_conflict; + } + } + + if (mdev->ee_hash_s) { + /* now, check for overlapping requests with remote origin */ + BUG_ON(mdev->ee_hash == NULL); +#undef OVERLAPS +#define OVERLAPS overlaps(e->sector, e->size, sector, size) + slot = ee_hash_slot(mdev, sector); + hlist_for_each_entry(e, n, slot, colision) { + if (OVERLAPS) { + dev_alert(DEV, "%s[%u] Concurrent remote write detected!" + " [DISCARD L] new: %llus +%u; " + "pending: %llus +%u\n", + current->comm, current->pid, + (unsigned long long)sector, size, + (unsigned long long)e->sector, e->size); + goto out_conflict; + } + } + } +#undef OVERLAPS + +out_no_conflict: + /* this is like it should be, and what we expected. + * our users do behave after all... */ + put_net_conf(mdev); + return 0; + +out_conflict: + put_net_conf(mdev); + return 1; +} + +/* obviously this could be coded as many single functions + * instead of one huge switch, + * or by putting the code directly in the respective locations + * (as it has been before). + * + * but having it this way + * enforces that it is all in this one place, where it is easier to audit, + * it makes it obvious that whatever "event" "happens" to a request should + * happen "atomically" within the req_lock, + * and it enforces that we have to think in a very structured manner + * about the "events" that may happen to a request during its life time ... + */ +void __req_mod(struct drbd_request *req, enum drbd_req_event what, + struct bio_and_error *m) +{ + struct drbd_conf *mdev = req->mdev; + m->bio = NULL; + + switch (what) { + default: + dev_err(DEV, "LOGIC BUG in %s:%u\n", __FILE__ , __LINE__); + break; + + /* does not happen... + * initialization done in drbd_req_new + case created: + break; + */ + + case to_be_send: /* via network */ + /* reached via drbd_make_request_common + * and from w_read_retry_remote */ + D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + req->rq_state |= RQ_NET_PENDING; + inc_ap_pending(mdev); + break; + + case to_be_submitted: /* locally */ + /* reached via drbd_make_request_common */ + D_ASSERT(!(req->rq_state & RQ_LOCAL_MASK)); + req->rq_state |= RQ_LOCAL_PENDING; + break; + + case completed_ok: + if (bio_data_dir(req->master_bio) == WRITE) + mdev->writ_cnt += req->size>>9; + else + mdev->read_cnt += req->size>>9; + + req->rq_state |= (RQ_LOCAL_COMPLETED|RQ_LOCAL_OK); + req->rq_state &= ~RQ_LOCAL_PENDING; + + _req_may_be_done(req, m); + put_ldev(mdev); + break; + + case write_completed_with_error: + req->rq_state |= RQ_LOCAL_COMPLETED; + req->rq_state &= ~RQ_LOCAL_PENDING; + + dev_alert(DEV, "Local WRITE failed sec=%llus size=%u\n", + (unsigned long long)req->sector, req->size); + /* and now: check how to handle local io error. */ + __drbd_chk_io_error(mdev, FALSE); + _req_may_be_done(req, m); + put_ldev(mdev); + break; + + case read_ahead_completed_with_error: + /* it is legal to fail READA */ + req->rq_state |= RQ_LOCAL_COMPLETED; + req->rq_state &= ~RQ_LOCAL_PENDING; + _req_may_be_done(req, m); + put_ldev(mdev); + break; + + case read_completed_with_error: + drbd_set_out_of_sync(mdev, req->sector, req->size); + + req->rq_state |= RQ_LOCAL_COMPLETED; + req->rq_state &= ~RQ_LOCAL_PENDING; + + dev_alert(DEV, "Local READ failed sec=%llus size=%u\n", + (unsigned long long)req->sector, req->size); + /* _req_mod(req,to_be_send); oops, recursion... */ + D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + req->rq_state |= RQ_NET_PENDING; + inc_ap_pending(mdev); + + __drbd_chk_io_error(mdev, FALSE); + put_ldev(mdev); + /* NOTE: if we have no connection, + * or know the peer has no good data either, + * then we don't actually need to "queue_for_net_read", + * but we do so anyways, since the drbd_io_error() + * and the potential state change to "Diskless" + * needs to be done from process context */ + + /* fall through: _req_mod(req,queue_for_net_read); */ + + case queue_for_net_read: + /* READ or READA, and + * no local disk, + * or target area marked as invalid, + * or just got an io-error. */ + /* from drbd_make_request_common + * or from bio_endio during read io-error recovery */ + + /* so we can verify the handle in the answer packet + * corresponding hlist_del is in _req_may_be_done() */ + hlist_add_head(&req->colision, ar_hash_slot(mdev, req->sector)); + + set_bit(UNPLUG_REMOTE, &mdev->flags); + + D_ASSERT(req->rq_state & RQ_NET_PENDING); + req->rq_state |= RQ_NET_QUEUED; + req->w.cb = (req->rq_state & RQ_LOCAL_MASK) + ? w_read_retry_remote + : w_send_read_req; + drbd_queue_work(&mdev->data.work, &req->w); + break; + + case queue_for_net_write: + /* assert something? */ + /* from drbd_make_request_common only */ + + hlist_add_head(&req->colision, tl_hash_slot(mdev, req->sector)); + /* corresponding hlist_del is in _req_may_be_done() */ + + /* NOTE + * In case the req ended up on the transfer log before being + * queued on the worker, it could lead to this request being + * missed during cleanup after connection loss. + * So we have to do both operations here, + * within the same lock that protects the transfer log. + * + * _req_add_to_epoch(req); this has to be after the + * _maybe_start_new_epoch(req); which happened in + * drbd_make_request_common, because we now may set the bit + * again ourselves to close the current epoch. + * + * Add req to the (now) current epoch (barrier). */ + + /* otherwise we may lose an unplug, which may cause some remote + * io-scheduler timeout to expire, increasing maximum latency, + * hurting performance. */ + set_bit(UNPLUG_REMOTE, &mdev->flags); + + /* see drbd_make_request_common, + * just after it grabs the req_lock */ + D_ASSERT(test_bit(CREATE_BARRIER, &mdev->flags) == 0); + + req->epoch = mdev->newest_tle->br_number; + list_add_tail(&req->tl_requests, + &mdev->newest_tle->requests); + + /* increment size of current epoch */ + mdev->newest_tle->n_req++; + + /* queue work item to send data */ + D_ASSERT(req->rq_state & RQ_NET_PENDING); + req->rq_state |= RQ_NET_QUEUED; + req->w.cb = w_send_dblock; + drbd_queue_work(&mdev->data.work, &req->w); + + /* close the epoch, in case it outgrew the limit */ + if (mdev->newest_tle->n_req >= mdev->net_conf->max_epoch_size) + queue_barrier(mdev); + + break; + + case send_canceled: + /* treat it the same */ + case send_failed: + /* real cleanup will be done from tl_clear. just update flags + * so it is no longer marked as on the worker queue */ + req->rq_state &= ~RQ_NET_QUEUED; + /* if we did it right, tl_clear should be scheduled only after + * this, so this should not be necessary! */ + _req_may_be_done(req, m); + break; + + case handed_over_to_network: + /* assert something? */ + if (bio_data_dir(req->master_bio) == WRITE && + mdev->net_conf->wire_protocol == DRBD_PROT_A) { + /* this is what is dangerous about protocol A: + * pretend it was successfully written on the peer. */ + if (req->rq_state & RQ_NET_PENDING) { + dec_ap_pending(mdev); + req->rq_state &= ~RQ_NET_PENDING; + req->rq_state |= RQ_NET_OK; + } /* else: neg-ack was faster... */ + /* it is still not yet RQ_NET_DONE until the + * corresponding epoch barrier got acked as well, + * so we know what to dirty on connection loss */ + } + req->rq_state &= ~RQ_NET_QUEUED; + req->rq_state |= RQ_NET_SENT; + /* because _drbd_send_zc_bio could sleep, and may want to + * dereference the bio even after the "write_acked_by_peer" and + * "completed_ok" events came in, once we return from + * _drbd_send_zc_bio (drbd_send_dblock), we have to check + * whether it is done already, and end it. */ + _req_may_be_done(req, m); + break; + + case connection_lost_while_pending: + /* transfer log cleanup after connection loss */ + /* assert something? */ + if (req->rq_state & RQ_NET_PENDING) + dec_ap_pending(mdev); + req->rq_state &= ~(RQ_NET_OK|RQ_NET_PENDING); + req->rq_state |= RQ_NET_DONE; + /* if it is still queued, we may not complete it here. + * it will be canceled soon. */ + if (!(req->rq_state & RQ_NET_QUEUED)) + _req_may_be_done(req, m); + break; + + case write_acked_by_peer_and_sis: + req->rq_state |= RQ_NET_SIS; + case conflict_discarded_by_peer: + /* for discarded conflicting writes of multiple primaries, + * there is no need to keep anything in the tl, potential + * node crashes are covered by the activity log. */ + if (what == conflict_discarded_by_peer) + dev_alert(DEV, "Got DiscardAck packet %llus +%u!" + " DRBD is not a random data generator!\n", + (unsigned long long)req->sector, req->size); + req->rq_state |= RQ_NET_DONE; + /* fall through */ + case write_acked_by_peer: + /* protocol C; successfully written on peer. + * Nothing to do here. + * We want to keep the tl in place for all protocols, to cater + * for volatile write-back caches on lower level devices. + * + * A barrier request is expected to have forced all prior + * requests onto stable storage, so completion of a barrier + * request could set NET_DONE right here, and not wait for the + * P_BARRIER_ACK, but that is an unnecessary optimization. */ + + /* this makes it effectively the same as for: */ + case recv_acked_by_peer: + /* protocol B; pretends to be successfully written on peer. + * see also notes above in handed_over_to_network about + * protocol != C */ + req->rq_state |= RQ_NET_OK; + D_ASSERT(req->rq_state & RQ_NET_PENDING); + dec_ap_pending(mdev); + req->rq_state &= ~RQ_NET_PENDING; + _req_may_be_done(req, m); + break; + + case neg_acked: + /* assert something? */ + if (req->rq_state & RQ_NET_PENDING) + dec_ap_pending(mdev); + req->rq_state &= ~(RQ_NET_OK|RQ_NET_PENDING); + + req->rq_state |= RQ_NET_DONE; + _req_may_be_done(req, m); + /* else: done by handed_over_to_network */ + break; + + case barrier_acked: + if (req->rq_state & RQ_NET_PENDING) { + /* barrier came in before all requests have been acked. + * this is bad, because if the connection is lost now, + * we won't be able to clean them up... */ + dev_err(DEV, "FIXME (barrier_acked but pending)\n"); + list_move(&req->tl_requests, &mdev->out_of_sequence_requests); + } + D_ASSERT(req->rq_state & RQ_NET_SENT); + req->rq_state |= RQ_NET_DONE; + _req_may_be_done(req, m); + break; + + case data_received: + D_ASSERT(req->rq_state & RQ_NET_PENDING); + dec_ap_pending(mdev); + req->rq_state &= ~RQ_NET_PENDING; + req->rq_state |= (RQ_NET_OK|RQ_NET_DONE); + _req_may_be_done(req, m); + break; + }; +} + +/* we may do a local read if: + * - we are consistent (of course), + * - or we are generally inconsistent, + * BUT we are still/already IN SYNC for this area. + * since size may be bigger than BM_BLOCK_SIZE, + * we may need to check several bits. + */ +static int drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int size) +{ + unsigned long sbnr, ebnr; + sector_t esector, nr_sectors; + + if (mdev->state.disk == D_UP_TO_DATE) + return 1; + if (mdev->state.disk >= D_OUTDATED) + return 0; + if (mdev->state.disk < D_INCONSISTENT) + return 0; + /* state.disk == D_INCONSISTENT We will have a look at the BitMap */ + nr_sectors = drbd_get_capacity(mdev->this_bdev); + esector = sector + (size >> 9) - 1; + + D_ASSERT(sector < nr_sectors); + D_ASSERT(esector < nr_sectors); + + sbnr = BM_SECT_TO_BIT(sector); + ebnr = BM_SECT_TO_BIT(esector); + + return 0 == drbd_bm_count_bits(mdev, sbnr, ebnr); +} + +static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio) +{ + const int rw = bio_rw(bio); + const int size = bio->bi_size; + const sector_t sector = bio->bi_sector; + struct drbd_tl_epoch *b = NULL; + struct drbd_request *req; + int local, remote; + int err = -EIO; + + /* allocate outside of all locks; */ + req = drbd_req_new(mdev, bio); + if (!req) { + dec_ap_bio(mdev); + /* only pass the error to the upper layers. + * if user cannot handle io errors, that's not our business. */ + dev_err(DEV, "could not kmalloc() req\n"); + bio_endio(bio, -ENOMEM); + return 0; + } + + local = get_ldev(mdev); + if (!local) { + bio_put(req->private_bio); /* or we get a bio leak */ + req->private_bio = NULL; + } + if (rw == WRITE) { + remote = 1; + } else { + /* READ || READA */ + if (local) { + if (!drbd_may_do_local_read(mdev, sector, size)) { + /* we could kick the syncer to + * sync this extent asap, wait for + * it, then continue locally. + * Or just issue the request remotely. + */ + local = 0; + bio_put(req->private_bio); + req->private_bio = NULL; + put_ldev(mdev); + } + } + remote = !local && mdev->state.pdsk >= D_UP_TO_DATE; + } + + /* If we have a disk, but a READA request is mapped to remote, + * we are R_PRIMARY, D_INCONSISTENT, SyncTarget. + * Just fail that READA request right here. + * + * THINK: maybe fail all READA when not local? + * or make this configurable... + * if network is slow, READA won't do any good. + */ + if (rw == READA && mdev->state.disk >= D_INCONSISTENT && !local) { + err = -EWOULDBLOCK; + goto fail_and_free_req; + } + + /* For WRITES going to the local disk, grab a reference on the target + * extent. This waits for any resync activity in the corresponding + * resync extent to finish, and, if necessary, pulls in the target + * extent into the activity log, which involves further disk io because + * of transactional on-disk meta data updates. */ + if (rw == WRITE && local) + drbd_al_begin_io(mdev, sector); + + remote = remote && (mdev->state.pdsk == D_UP_TO_DATE || + (mdev->state.pdsk == D_INCONSISTENT && + mdev->state.conn >= C_CONNECTED)); + + if (!(local || remote)) { + dev_err(DEV, "IO ERROR: neither local nor remote disk\n"); + goto fail_free_complete; + } + + /* For WRITE request, we have to make sure that we have an + * unused_spare_tle, in case we need to start a new epoch. + * I try to be smart and avoid to pre-allocate always "just in case", + * but there is a race between testing the bit and pointer outside the + * spinlock, and grabbing the spinlock. + * if we lost that race, we retry. */ + if (rw == WRITE && remote && + mdev->unused_spare_tle == NULL && + test_bit(CREATE_BARRIER, &mdev->flags)) { +allocate_barrier: + b = kmalloc(sizeof(struct drbd_tl_epoch), GFP_NOIO); + if (!b) { + dev_err(DEV, "Failed to alloc barrier.\n"); + err = -ENOMEM; + goto fail_free_complete; + } + } + + /* GOOD, everything prepared, grab the spin_lock */ + spin_lock_irq(&mdev->req_lock); + + if (remote) { + remote = (mdev->state.pdsk == D_UP_TO_DATE || + (mdev->state.pdsk == D_INCONSISTENT && + mdev->state.conn >= C_CONNECTED)); + if (!remote) + dev_warn(DEV, "lost connection while grabbing the req_lock!\n"); + if (!(local || remote)) { + dev_err(DEV, "IO ERROR: neither local nor remote disk\n"); + spin_unlock_irq(&mdev->req_lock); + goto fail_free_complete; + } + } + + if (b && mdev->unused_spare_tle == NULL) { + mdev->unused_spare_tle = b; + b = NULL; + } + if (rw == WRITE && remote && + mdev->unused_spare_tle == NULL && + test_bit(CREATE_BARRIER, &mdev->flags)) { + /* someone closed the current epoch + * while we were grabbing the spinlock */ + spin_unlock_irq(&mdev->req_lock); + goto allocate_barrier; + } + + + /* Update disk stats */ + _drbd_start_io_acct(mdev, req, bio); + + /* _maybe_start_new_epoch(mdev); + * If we need to generate a write barrier packet, we have to add the + * new epoch (barrier) object, and queue the barrier packet for sending, + * and queue the req's data after it _within the same lock_, otherwise + * we have race conditions were the reorder domains could be mixed up. + * + * Even read requests may start a new epoch and queue the corresponding + * barrier packet. To get the write ordering right, we only have to + * make sure that, if this is a write request and it triggered a + * barrier packet, this request is queued within the same spinlock. */ + if (remote && mdev->unused_spare_tle && + test_and_clear_bit(CREATE_BARRIER, &mdev->flags)) { + _tl_add_barrier(mdev, mdev->unused_spare_tle); + mdev->unused_spare_tle = NULL; + } else { + D_ASSERT(!(remote && rw == WRITE && + test_bit(CREATE_BARRIER, &mdev->flags))); + } + + /* NOTE + * Actually, 'local' may be wrong here already, since we may have failed + * to write to the meta data, and may become wrong anytime because of + * local io-error for some other request, which would lead to us + * "detaching" the local disk. + * + * 'remote' may become wrong any time because the network could fail. + * + * This is a harmless race condition, though, since it is handled + * correctly at the appropriate places; so it just defers the failure + * of the respective operation. + */ + + /* mark them early for readability. + * this just sets some state flags. */ + if (remote) + _req_mod(req, to_be_send); + if (local) + _req_mod(req, to_be_submitted); + + /* check this request on the collision detection hash tables. + * if we have a conflict, just complete it here. + * THINK do we want to check reads, too? (I don't think so...) */ + if (rw == WRITE && _req_conflicts(req)) { + /* this is a conflicting request. + * even though it may have been only _partially_ + * overlapping with one of the currently pending requests, + * without even submitting or sending it, we will + * pretend that it was successfully served right now. + */ + if (local) { + bio_put(req->private_bio); + req->private_bio = NULL; + drbd_al_complete_io(mdev, req->sector); + put_ldev(mdev); + local = 0; + } + if (remote) + dec_ap_pending(mdev); + _drbd_end_io_acct(mdev, req); + /* THINK: do we want to fail it (-EIO), or pretend success? */ + bio_endio(req->master_bio, 0); + req->master_bio = NULL; + dec_ap_bio(mdev); + drbd_req_free(req); + remote = 0; + } + + /* NOTE remote first: to get the concurrent write detection right, + * we must register the request before start of local IO. */ + if (remote) { + /* either WRITE and C_CONNECTED, + * or READ, and no local disk, + * or READ, but not in sync. + */ + _req_mod(req, (rw == WRITE) + ? queue_for_net_write + : queue_for_net_read); + } + spin_unlock_irq(&mdev->req_lock); + kfree(b); /* if someone else has beaten us to it... */ + + if (local) { + req->private_bio->bi_bdev = mdev->ldev->backing_bdev; + + if (FAULT_ACTIVE(mdev, rw == WRITE ? DRBD_FAULT_DT_WR + : rw == READ ? DRBD_FAULT_DT_RD + : DRBD_FAULT_DT_RA)) + bio_endio(req->private_bio, -EIO); + else + generic_make_request(req->private_bio); + } + + /* we need to plug ALWAYS since we possibly need to kick lo_dev. + * we plug after submit, so we won't miss an unplug event */ + drbd_plug_device(mdev); + + return 0; + +fail_free_complete: + if (rw == WRITE && local) + drbd_al_complete_io(mdev, sector); +fail_and_free_req: + if (local) { + bio_put(req->private_bio); + req->private_bio = NULL; + put_ldev(mdev); + } + bio_endio(bio, err); + drbd_req_free(req); + dec_ap_bio(mdev); + kfree(b); + + return 0; +} + +/* helper function for drbd_make_request + * if we can determine just by the mdev (state) that this request will fail, + * return 1 + * otherwise return 0 + */ +static int drbd_fail_request_early(struct drbd_conf *mdev, int is_write) +{ + /* Unconfigured */ + if (mdev->state.conn == C_DISCONNECTING && + mdev->state.disk == D_DISKLESS) + return 1; + + if (mdev->state.role != R_PRIMARY && + (!allow_oos || is_write)) { + if (__ratelimit(&drbd_ratelimit_state)) { + dev_err(DEV, "Process %s[%u] tried to %s; " + "since we are not in Primary state, " + "we cannot allow this\n", + current->comm, current->pid, + is_write ? "WRITE" : "READ"); + } + return 1; + } + + /* + * Paranoia: we might have been primary, but sync target, or + * even diskless, then lost the connection. + * This should have been handled (panic? suspend?) somewhere + * else. But maybe it was not, so check again here. + * Caution: as long as we do not have a read/write lock on mdev, + * to serialize state changes, this is racy, since we may lose + * the connection *after* we test for the cstate. + */ + if (mdev->state.disk < D_UP_TO_DATE && mdev->state.pdsk < D_UP_TO_DATE) { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Sorry, I have no access to good data anymore.\n"); + return 1; + } + + return 0; +} + +int drbd_make_request_26(struct request_queue *q, struct bio *bio) +{ + unsigned int s_enr, e_enr; + struct drbd_conf *mdev = (struct drbd_conf *) q->queuedata; + + if (drbd_fail_request_early(mdev, bio_data_dir(bio) & WRITE)) { + bio_endio(bio, -EPERM); + return 0; + } + + /* Reject barrier requests if we know the underlying device does + * not support them. + * XXX: Need to get this info from peer as well some how so we + * XXX: reject if EITHER side/data/metadata area does not support them. + * + * because of those XXX, this is not yet enabled, + * i.e. in drbd_init_set_defaults we set the NO_BARRIER_SUPP bit. + */ + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER) && test_bit(NO_BARRIER_SUPP, &mdev->flags))) { + /* dev_warn(DEV, "Rejecting barrier request as underlying device does not support\n"); */ + bio_endio(bio, -EOPNOTSUPP); + return 0; + } + + /* + * what we "blindly" assume: + */ + D_ASSERT(bio->bi_size > 0); + D_ASSERT((bio->bi_size & 0x1ff) == 0); + D_ASSERT(bio->bi_idx == 0); + + /* to make some things easier, force alignment of requests within the + * granularity of our hash tables */ + s_enr = bio->bi_sector >> HT_SHIFT; + e_enr = (bio->bi_sector+(bio->bi_size>>9)-1) >> HT_SHIFT; + + if (likely(s_enr == e_enr)) { + inc_ap_bio(mdev, 1); + return drbd_make_request_common(mdev, bio); + } + + /* can this bio be split generically? + * Maybe add our own split-arbitrary-bios function. */ + if (bio->bi_vcnt != 1 || bio->bi_idx != 0 || bio->bi_size > DRBD_MAX_SEGMENT_SIZE) { + /* rather error out here than BUG in bio_split */ + dev_err(DEV, "bio would need to, but cannot, be split: " + "(vcnt=%u,idx=%u,size=%u,sector=%llu)\n", + bio->bi_vcnt, bio->bi_idx, bio->bi_size, + (unsigned long long)bio->bi_sector); + bio_endio(bio, -EINVAL); + } else { + /* This bio crosses some boundary, so we have to split it. */ + struct bio_pair *bp; + /* works for the "do not cross hash slot boundaries" case + * e.g. sector 262269, size 4096 + * s_enr = 262269 >> 6 = 4097 + * e_enr = (262269+8-1) >> 6 = 4098 + * HT_SHIFT = 6 + * sps = 64, mask = 63 + * first_sectors = 64 - (262269 & 63) = 3 + */ + const sector_t sect = bio->bi_sector; + const int sps = 1 << HT_SHIFT; /* sectors per slot */ + const int mask = sps - 1; + const sector_t first_sectors = sps - (sect & mask); + bp = bio_split(bio, +#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,28) + bio_split_pool, +#endif + first_sectors); + + /* we need to get a "reference count" (ap_bio_cnt) + * to avoid races with the disconnect/reconnect/suspend code. + * In case we need to split the bio here, we need to get two references + * atomically, otherwise we might deadlock when trying to submit the + * second one! */ + inc_ap_bio(mdev, 2); + + D_ASSERT(e_enr == s_enr + 1); + + drbd_make_request_common(mdev, &bp->bio1); + drbd_make_request_common(mdev, &bp->bio2); + bio_pair_release(bp); + } + return 0; +} + +/* This is called by bio_add_page(). With this function we reduce + * the number of BIOs that span over multiple DRBD_MAX_SEGMENT_SIZEs + * units (was AL_EXTENTs). + * + * we do the calculation within the lower 32bit of the byte offsets, + * since we don't care for actual offset, but only check whether it + * would cross "activity log extent" boundaries. + * + * As long as the BIO is empty we have to allow at least one bvec, + * regardless of size and offset. so the resulting bio may still + * cross extent boundaries. those are dealt with (bio_split) in + * drbd_make_request_26. + */ +int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *bvec) +{ + struct drbd_conf *mdev = (struct drbd_conf *) q->queuedata; + unsigned int bio_offset = + (unsigned int)bvm->bi_sector << 9; /* 32 bit */ + unsigned int bio_size = bvm->bi_size; + int limit, backing_limit; + + limit = DRBD_MAX_SEGMENT_SIZE + - ((bio_offset & (DRBD_MAX_SEGMENT_SIZE-1)) + bio_size); + if (limit < 0) + limit = 0; + if (bio_size == 0) { + if (limit <= bvec->bv_len) + limit = bvec->bv_len; + } else if (limit && get_ldev(mdev)) { + struct request_queue * const b = + mdev->ldev->backing_bdev->bd_disk->queue; + if (b->merge_bvec_fn && mdev->ldev->dc.use_bmbv) { + backing_limit = b->merge_bvec_fn(b, bvm, bvec); + limit = min(limit, backing_limit); + } + put_ldev(mdev); + } + return limit; +} diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h new file mode 100644 index 000000000000..f22c1bc8ec7e --- /dev/null +++ b/drivers/block/drbd/drbd_req.h @@ -0,0 +1,326 @@ +/* + drbd_req.h + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2006-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2006-2008, Lars Ellenberg . + Copyright (C) 2006-2008, Philipp Reisner . + + DRBD is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + DRBD 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _DRBD_REQ_H +#define _DRBD_REQ_H + +#include + +#include +#include +#include "drbd_int.h" +#include "drbd_wrappers.h" + +/* The request callbacks will be called in irq context by the IDE drivers, + and in Softirqs/Tasklets/BH context by the SCSI drivers, + and by the receiver and worker in kernel-thread context. + Try to get the locking right :) */ + +/* + * Objects of type struct drbd_request do only exist on a R_PRIMARY node, and are + * associated with IO requests originating from the block layer above us. + * + * There are quite a few things that may happen to a drbd request + * during its lifetime. + * + * It will be created. + * It will be marked with the intention to be + * submitted to local disk and/or + * send via the network. + * + * It has to be placed on the transfer log and other housekeeping lists, + * In case we have a network connection. + * + * It may be identified as a concurrent (write) request + * and be handled accordingly. + * + * It may me handed over to the local disk subsystem. + * It may be completed by the local disk subsystem, + * either sucessfully or with io-error. + * In case it is a READ request, and it failed locally, + * it may be retried remotely. + * + * It may be queued for sending. + * It may be handed over to the network stack, + * which may fail. + * It may be acknowledged by the "peer" according to the wire_protocol in use. + * this may be a negative ack. + * It may receive a faked ack when the network connection is lost and the + * transfer log is cleaned up. + * Sending may be canceled due to network connection loss. + * When it finally has outlived its time, + * corresponding dirty bits in the resync-bitmap may be cleared or set, + * it will be destroyed, + * and completion will be signalled to the originator, + * with or without "success". + */ + +enum drbd_req_event { + created, + to_be_send, + to_be_submitted, + + /* XXX yes, now I am inconsistent... + * these two are not "events" but "actions" + * oh, well... */ + queue_for_net_write, + queue_for_net_read, + + send_canceled, + send_failed, + handed_over_to_network, + connection_lost_while_pending, + recv_acked_by_peer, + write_acked_by_peer, + write_acked_by_peer_and_sis, /* and set_in_sync */ + conflict_discarded_by_peer, + neg_acked, + barrier_acked, /* in protocol A and B */ + data_received, /* (remote read) */ + + read_completed_with_error, + read_ahead_completed_with_error, + write_completed_with_error, + completed_ok, + nothing, /* for tracing only */ +}; + +/* encoding of request states for now. we don't actually need that many bits. + * we don't need to do atomic bit operations either, since most of the time we + * need to look at the connection state and/or manipulate some lists at the + * same time, so we should hold the request lock anyways. + */ +enum drbd_req_state_bits { + /* 210 + * 000: no local possible + * 001: to be submitted + * UNUSED, we could map: 011: submitted, completion still pending + * 110: completed ok + * 010: completed with error + */ + __RQ_LOCAL_PENDING, + __RQ_LOCAL_COMPLETED, + __RQ_LOCAL_OK, + + /* 76543 + * 00000: no network possible + * 00001: to be send + * 00011: to be send, on worker queue + * 00101: sent, expecting recv_ack (B) or write_ack (C) + * 11101: sent, + * recv_ack (B) or implicit "ack" (A), + * still waiting for the barrier ack. + * master_bio may already be completed and invalidated. + * 11100: write_acked (C), + * data_received (for remote read, any protocol) + * or finally the barrier ack has arrived (B,A)... + * request can be freed + * 01100: neg-acked (write, protocol C) + * or neg-d-acked (read, any protocol) + * or killed from the transfer log + * during cleanup after connection loss + * request can be freed + * 01000: canceled or send failed... + * request can be freed + */ + + /* if "SENT" is not set, yet, this can still fail or be canceled. + * if "SENT" is set already, we still wait for an Ack packet. + * when cleared, the master_bio may be completed. + * in (B,A) the request object may still linger on the transaction log + * until the corresponding barrier ack comes in */ + __RQ_NET_PENDING, + + /* If it is QUEUED, and it is a WRITE, it is also registered in the + * transfer log. Currently we need this flag to avoid conflicts between + * worker canceling the request and tl_clear_barrier killing it from + * transfer log. We should restructure the code so this conflict does + * no longer occur. */ + __RQ_NET_QUEUED, + + /* well, actually only "handed over to the network stack". + * + * TODO can potentially be dropped because of the similar meaning + * of RQ_NET_SENT and ~RQ_NET_QUEUED. + * however it is not exactly the same. before we drop it + * we must ensure that we can tell a request with network part + * from a request without, regardless of what happens to it. */ + __RQ_NET_SENT, + + /* when set, the request may be freed (if RQ_NET_QUEUED is clear). + * basically this means the corresponding P_BARRIER_ACK was received */ + __RQ_NET_DONE, + + /* whether or not we know (C) or pretend (B,A) that the write + * was successfully written on the peer. + */ + __RQ_NET_OK, + + /* peer called drbd_set_in_sync() for this write */ + __RQ_NET_SIS, + + /* keep this last, its for the RQ_NET_MASK */ + __RQ_NET_MAX, +}; + +#define RQ_LOCAL_PENDING (1UL << __RQ_LOCAL_PENDING) +#define RQ_LOCAL_COMPLETED (1UL << __RQ_LOCAL_COMPLETED) +#define RQ_LOCAL_OK (1UL << __RQ_LOCAL_OK) + +#define RQ_LOCAL_MASK ((RQ_LOCAL_OK << 1)-1) /* 0x07 */ + +#define RQ_NET_PENDING (1UL << __RQ_NET_PENDING) +#define RQ_NET_QUEUED (1UL << __RQ_NET_QUEUED) +#define RQ_NET_SENT (1UL << __RQ_NET_SENT) +#define RQ_NET_DONE (1UL << __RQ_NET_DONE) +#define RQ_NET_OK (1UL << __RQ_NET_OK) +#define RQ_NET_SIS (1UL << __RQ_NET_SIS) + +/* 0x1f8 */ +#define RQ_NET_MASK (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK) + +/* epoch entries */ +static inline +struct hlist_head *ee_hash_slot(struct drbd_conf *mdev, sector_t sector) +{ + BUG_ON(mdev->ee_hash_s == 0); + return mdev->ee_hash + + ((unsigned int)(sector>>HT_SHIFT) % mdev->ee_hash_s); +} + +/* transfer log (drbd_request objects) */ +static inline +struct hlist_head *tl_hash_slot(struct drbd_conf *mdev, sector_t sector) +{ + BUG_ON(mdev->tl_hash_s == 0); + return mdev->tl_hash + + ((unsigned int)(sector>>HT_SHIFT) % mdev->tl_hash_s); +} + +/* application reads (drbd_request objects) */ +static struct hlist_head *ar_hash_slot(struct drbd_conf *mdev, sector_t sector) +{ + return mdev->app_reads_hash + + ((unsigned int)(sector) % APP_R_HSIZE); +} + +/* when we receive the answer for a read request, + * verify that we actually know about it */ +static inline struct drbd_request *_ar_id_to_req(struct drbd_conf *mdev, + u64 id, sector_t sector) +{ + struct hlist_head *slot = ar_hash_slot(mdev, sector); + struct hlist_node *n; + struct drbd_request *req; + + hlist_for_each_entry(req, n, slot, colision) { + if ((unsigned long)req == (unsigned long)id) { + D_ASSERT(req->sector == sector); + return req; + } + } + return NULL; +} + +static inline struct drbd_request *drbd_req_new(struct drbd_conf *mdev, + struct bio *bio_src) +{ + struct bio *bio; + struct drbd_request *req = + mempool_alloc(drbd_request_mempool, GFP_NOIO); + if (likely(req)) { + bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */ + + req->rq_state = 0; + req->mdev = mdev; + req->master_bio = bio_src; + req->private_bio = bio; + req->epoch = 0; + req->sector = bio->bi_sector; + req->size = bio->bi_size; + req->start_time = jiffies; + INIT_HLIST_NODE(&req->colision); + INIT_LIST_HEAD(&req->tl_requests); + INIT_LIST_HEAD(&req->w.list); + + bio->bi_private = req; + bio->bi_end_io = drbd_endio_pri; + bio->bi_next = NULL; + } + return req; +} + +static inline void drbd_req_free(struct drbd_request *req) +{ + mempool_free(req, drbd_request_mempool); +} + +static inline int overlaps(sector_t s1, int l1, sector_t s2, int l2) +{ + return !((s1 + (l1>>9) <= s2) || (s1 >= s2 + (l2>>9))); +} + +/* Short lived temporary struct on the stack. + * We could squirrel the error to be returned into + * bio->bi_size, or similar. But that would be too ugly. */ +struct bio_and_error { + struct bio *bio; + int error; +}; + +extern void _req_may_be_done(struct drbd_request *req, + struct bio_and_error *m); +extern void __req_mod(struct drbd_request *req, enum drbd_req_event what, + struct bio_and_error *m); +extern void complete_master_bio(struct drbd_conf *mdev, + struct bio_and_error *m); + +/* use this if you don't want to deal with calling complete_master_bio() + * outside the spinlock, e.g. when walking some list on cleanup. */ +static inline void _req_mod(struct drbd_request *req, enum drbd_req_event what) +{ + struct drbd_conf *mdev = req->mdev; + struct bio_and_error m; + + /* __req_mod possibly frees req, do not touch req after that! */ + __req_mod(req, what, &m); + if (m.bio) + complete_master_bio(mdev, &m); +} + +/* completion of master bio is outside of spinlock. + * If you need it irqsave, do it your self! */ +static inline void req_mod(struct drbd_request *req, + enum drbd_req_event what) +{ + struct drbd_conf *mdev = req->mdev; + struct bio_and_error m; + spin_lock_irq(&mdev->req_lock); + __req_mod(req, what, &m); + spin_unlock_irq(&mdev->req_lock); + + if (m.bio) + complete_master_bio(mdev, &m); +} +#endif diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c new file mode 100644 index 000000000000..76863e3f05be --- /dev/null +++ b/drivers/block/drbd/drbd_strings.c @@ -0,0 +1,113 @@ +/* + drbd.h + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2003-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2003-2008, Philipp Reisner . + Copyright (C) 2003-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + +*/ + +#include + +static const char *drbd_conn_s_names[] = { + [C_STANDALONE] = "StandAlone", + [C_DISCONNECTING] = "Disconnecting", + [C_UNCONNECTED] = "Unconnected", + [C_TIMEOUT] = "Timeout", + [C_BROKEN_PIPE] = "BrokenPipe", + [C_NETWORK_FAILURE] = "NetworkFailure", + [C_PROTOCOL_ERROR] = "ProtocolError", + [C_WF_CONNECTION] = "WFConnection", + [C_WF_REPORT_PARAMS] = "WFReportParams", + [C_TEAR_DOWN] = "TearDown", + [C_CONNECTED] = "Connected", + [C_STARTING_SYNC_S] = "StartingSyncS", + [C_STARTING_SYNC_T] = "StartingSyncT", + [C_WF_BITMAP_S] = "WFBitMapS", + [C_WF_BITMAP_T] = "WFBitMapT", + [C_WF_SYNC_UUID] = "WFSyncUUID", + [C_SYNC_SOURCE] = "SyncSource", + [C_SYNC_TARGET] = "SyncTarget", + [C_PAUSED_SYNC_S] = "PausedSyncS", + [C_PAUSED_SYNC_T] = "PausedSyncT", + [C_VERIFY_S] = "VerifyS", + [C_VERIFY_T] = "VerifyT", +}; + +static const char *drbd_role_s_names[] = { + [R_PRIMARY] = "Primary", + [R_SECONDARY] = "Secondary", + [R_UNKNOWN] = "Unknown" +}; + +static const char *drbd_disk_s_names[] = { + [D_DISKLESS] = "Diskless", + [D_ATTACHING] = "Attaching", + [D_FAILED] = "Failed", + [D_NEGOTIATING] = "Negotiating", + [D_INCONSISTENT] = "Inconsistent", + [D_OUTDATED] = "Outdated", + [D_UNKNOWN] = "DUnknown", + [D_CONSISTENT] = "Consistent", + [D_UP_TO_DATE] = "UpToDate", +}; + +static const char *drbd_state_sw_errors[] = { + [-SS_TWO_PRIMARIES] = "Multiple primaries not allowed by config", + [-SS_NO_UP_TO_DATE_DISK] = "Refusing to be Primary without at least one UpToDate disk", + [-SS_NO_LOCAL_DISK] = "Can not resync without local disk", + [-SS_NO_REMOTE_DISK] = "Can not resync without remote disk", + [-SS_CONNECTED_OUTDATES] = "Refusing to be Outdated while Connected", + [-SS_PRIMARY_NOP] = "Refusing to be Primary while peer is not outdated", + [-SS_RESYNC_RUNNING] = "Can not start OV/resync since it is already active", + [-SS_ALREADY_STANDALONE] = "Can not disconnect a StandAlone device", + [-SS_CW_FAILED_BY_PEER] = "State change was refused by peer node", + [-SS_IS_DISKLESS] = "Device is diskless, the requested operation requires a disk", + [-SS_DEVICE_IN_USE] = "Device is held open by someone", + [-SS_NO_NET_CONFIG] = "Have no net/connection configuration", + [-SS_NO_VERIFY_ALG] = "Need a verify algorithm to start online verify", + [-SS_NEED_CONNECTION] = "Need a connection to start verify or resync", + [-SS_NOT_SUPPORTED] = "Peer does not support protocol", + [-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated", + [-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change", + [-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted", +}; + +const char *drbd_conn_str(enum drbd_conns s) +{ + /* enums are unsigned... */ + return s > C_PAUSED_SYNC_T ? "TOO_LARGE" : drbd_conn_s_names[s]; +} + +const char *drbd_role_str(enum drbd_role s) +{ + return s > R_SECONDARY ? "TOO_LARGE" : drbd_role_s_names[s]; +} + +const char *drbd_disk_str(enum drbd_disk_state s) +{ + return s > D_UP_TO_DATE ? "TOO_LARGE" : drbd_disk_s_names[s]; +} + +const char *drbd_set_st_err_str(enum drbd_state_ret_codes err) +{ + return err <= SS_AFTER_LAST_ERROR ? "TOO_SMALL" : + err > SS_TWO_PRIMARIES ? "TOO_LARGE" + : drbd_state_sw_errors[-err]; +} diff --git a/drivers/block/drbd/drbd_vli.h b/drivers/block/drbd/drbd_vli.h new file mode 100644 index 000000000000..fc824006e721 --- /dev/null +++ b/drivers/block/drbd/drbd_vli.h @@ -0,0 +1,351 @@ +/* +-*- linux-c -*- + drbd_receiver.c + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _DRBD_VLI_H +#define _DRBD_VLI_H + +/* + * At a granularity of 4KiB storage represented per bit, + * and stroage sizes of several TiB, + * and possibly small-bandwidth replication, + * the bitmap transfer time can take much too long, + * if transmitted in plain text. + * + * We try to reduce the transfered bitmap information + * by encoding runlengths of bit polarity. + * + * We never actually need to encode a "zero" (runlengths are positive). + * But then we have to store the value of the first bit. + * The first bit of information thus shall encode if the first runlength + * gives the number of set or unset bits. + * + * We assume that large areas are either completely set or unset, + * which gives good compression with any runlength method, + * even when encoding the runlength as fixed size 32bit/64bit integers. + * + * Still, there may be areas where the polarity flips every few bits, + * and encoding the runlength sequence of those areas with fix size + * integers would be much worse than plaintext. + * + * We want to encode small runlength values with minimum code length, + * while still being able to encode a Huge run of all zeros. + * + * Thus we need a Variable Length Integer encoding, VLI. + * + * For some cases, we produce more code bits than plaintext input. + * We need to send incompressible chunks as plaintext, skip over them + * and then see if the next chunk compresses better. + * + * We don't care too much about "excellent" compression ratio for large + * runlengths (all set/all clear): whether we achieve a factor of 100 + * or 1000 is not that much of an issue. + * We do not want to waste too much on short runlengths in the "noisy" + * parts of the bitmap, though. + * + * There are endless variants of VLI, we experimented with: + * * simple byte-based + * * various bit based with different code word length. + * + * To avoid yet an other configuration parameter (choice of bitmap compression + * algorithm) which was difficult to explain and tune, we just chose the one + * variant that turned out best in all test cases. + * Based on real world usage patterns, with device sizes ranging from a few GiB + * to several TiB, file server/mailserver/webserver/mysql/postgress, + * mostly idle to really busy, the all time winner (though sometimes only + * marginally better) is: + */ + +/* + * encoding is "visualised" as + * __little endian__ bitstream, least significant bit first (left most) + * + * this particular encoding is chosen so that the prefix code + * starts as unary encoding the level, then modified so that + * 10 levels can be described in 8bit, with minimal overhead + * for the smaller levels. + * + * Number of data bits follow fibonacci sequence, with the exception of the + * last level (+1 data bit, so it makes 64bit total). The only worse code when + * encoding bit polarity runlength is 1 plain bits => 2 code bits. +prefix data bits max val Nº data bits +0 x 0x2 1 +10 x 0x4 1 +110 xx 0x8 2 +1110 xxx 0x10 3 +11110 xxx xx 0x30 5 +111110 xx xxxxxx 0x130 8 +11111100 xxxxxxxx xxxxx 0x2130 13 +11111110 xxxxxxxx xxxxxxxx xxxxx 0x202130 21 +11111101 xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xx 0x400202130 34 +11111111 xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx 56 + * maximum encodable value: 0x100000400202130 == 2**56 + some */ + +/* compression "table": + transmitted x 0.29 + as plaintext x ........................ + x ........................ + x ........................ + x 0.59 0.21........................ + x ........................................................ + x .. c ................................................... + x 0.44.. o ................................................... + x .......... d ................................................... + x .......... e ................................................... + X............. ................................................... + x.............. b ................................................... +2.0x............... i ................................................... + #X................ t ................................................... + #................. s ........................... plain bits .......... +-+----------------------------------------------------------------------- + 1 16 32 64 +*/ + +/* LEVEL: (total bits, prefix bits, prefix value), + * sorted ascending by number of total bits. + * The rest of the code table is calculated at compiletime from this. */ + +/* fibonacci data 1, 1, ... */ +#define VLI_L_1_1() do { \ + LEVEL( 2, 1, 0x00); \ + LEVEL( 3, 2, 0x01); \ + LEVEL( 5, 3, 0x03); \ + LEVEL( 7, 4, 0x07); \ + LEVEL(10, 5, 0x0f); \ + LEVEL(14, 6, 0x1f); \ + LEVEL(21, 8, 0x3f); \ + LEVEL(29, 8, 0x7f); \ + LEVEL(42, 8, 0xbf); \ + LEVEL(64, 8, 0xff); \ + } while (0) + +/* finds a suitable level to decode the least significant part of in. + * returns number of bits consumed. + * + * BUG() for bad input, as that would mean a buggy code table. */ +static inline int vli_decode_bits(u64 *out, const u64 in) +{ + u64 adj = 1; + +#define LEVEL(t,b,v) \ + do { \ + if ((in & ((1 << b) -1)) == v) { \ + *out = ((in & ((~0ULL) >> (64-t))) >> b) + adj; \ + return t; \ + } \ + adj += 1ULL << (t - b); \ + } while (0) + + VLI_L_1_1(); + + /* NOT REACHED, if VLI_LEVELS code table is defined properly */ + BUG(); +#undef LEVEL +} + +/* return number of code bits needed, + * or negative error number */ +static inline int __vli_encode_bits(u64 *out, const u64 in) +{ + u64 max = 0; + u64 adj = 1; + + if (in == 0) + return -EINVAL; + +#define LEVEL(t,b,v) do { \ + max += 1ULL << (t - b); \ + if (in <= max) { \ + if (out) \ + *out = ((in - adj) << b) | v; \ + return t; \ + } \ + adj = max + 1; \ + } while (0) + + VLI_L_1_1(); + + return -EOVERFLOW; +#undef LEVEL +} + +#undef VLI_L_1_1 + +/* code from here down is independend of actually used bit code */ + +/* + * Code length is determined by some unique (e.g. unary) prefix. + * This encodes arbitrary bit length, not whole bytes: we have a bit-stream, + * not a byte stream. + */ + +/* for the bitstream, we need a cursor */ +struct bitstream_cursor { + /* the current byte */ + u8 *b; + /* the current bit within *b, nomalized: 0..7 */ + unsigned int bit; +}; + +/* initialize cursor to point to first bit of stream */ +static inline void bitstream_cursor_reset(struct bitstream_cursor *cur, void *s) +{ + cur->b = s; + cur->bit = 0; +} + +/* advance cursor by that many bits; maximum expected input value: 64, + * but depending on VLI implementation, it may be more. */ +static inline void bitstream_cursor_advance(struct bitstream_cursor *cur, unsigned int bits) +{ + bits += cur->bit; + cur->b = cur->b + (bits >> 3); + cur->bit = bits & 7; +} + +/* the bitstream itself knows its length */ +struct bitstream { + struct bitstream_cursor cur; + unsigned char *buf; + size_t buf_len; /* in bytes */ + + /* for input stream: + * number of trailing 0 bits for padding + * total number of valid bits in stream: buf_len * 8 - pad_bits */ + unsigned int pad_bits; +}; + +static inline void bitstream_init(struct bitstream *bs, void *s, size_t len, unsigned int pad_bits) +{ + bs->buf = s; + bs->buf_len = len; + bs->pad_bits = pad_bits; + bitstream_cursor_reset(&bs->cur, bs->buf); +} + +static inline void bitstream_rewind(struct bitstream *bs) +{ + bitstream_cursor_reset(&bs->cur, bs->buf); + memset(bs->buf, 0, bs->buf_len); +} + +/* Put (at most 64) least significant bits of val into bitstream, and advance cursor. + * Ignores "pad_bits". + * Returns zero if bits == 0 (nothing to do). + * Returns number of bits used if successful. + * + * If there is not enough room left in bitstream, + * leaves bitstream unchanged and returns -ENOBUFS. + */ +static inline int bitstream_put_bits(struct bitstream *bs, u64 val, const unsigned int bits) +{ + unsigned char *b = bs->cur.b; + unsigned int tmp; + + if (bits == 0) + return 0; + + if ((bs->cur.b + ((bs->cur.bit + bits -1) >> 3)) - bs->buf >= bs->buf_len) + return -ENOBUFS; + + /* paranoia: strip off hi bits; they should not be set anyways. */ + if (bits < 64) + val &= ~0ULL >> (64 - bits); + + *b++ |= (val & 0xff) << bs->cur.bit; + + for (tmp = 8 - bs->cur.bit; tmp < bits; tmp += 8) + *b++ |= (val >> tmp) & 0xff; + + bitstream_cursor_advance(&bs->cur, bits); + return bits; +} + +/* Fetch (at most 64) bits from bitstream into *out, and advance cursor. + * + * If more than 64 bits are requested, returns -EINVAL and leave *out unchanged. + * + * If there are less than the requested number of valid bits left in the + * bitstream, still fetches all available bits. + * + * Returns number of actually fetched bits. + */ +static inline int bitstream_get_bits(struct bitstream *bs, u64 *out, int bits) +{ + u64 val; + unsigned int n; + + if (bits > 64) + return -EINVAL; + + if (bs->cur.b + ((bs->cur.bit + bs->pad_bits + bits -1) >> 3) - bs->buf >= bs->buf_len) + bits = ((bs->buf_len - (bs->cur.b - bs->buf)) << 3) + - bs->cur.bit - bs->pad_bits; + + if (bits == 0) { + *out = 0; + return 0; + } + + /* get the high bits */ + val = 0; + n = (bs->cur.bit + bits + 7) >> 3; + /* n may be at most 9, if cur.bit + bits > 64 */ + /* which means this copies at most 8 byte */ + if (n) { + memcpy(&val, bs->cur.b+1, n - 1); + val = le64_to_cpu(val) << (8 - bs->cur.bit); + } + + /* we still need the low bits */ + val |= bs->cur.b[0] >> bs->cur.bit; + + /* and mask out bits we don't want */ + val &= ~0ULL >> (64 - bits); + + bitstream_cursor_advance(&bs->cur, bits); + *out = val; + + return bits; +} + +/* encodes @in as vli into @bs; + + * return values + * > 0: number of bits successfully stored in bitstream + * -ENOBUFS @bs is full + * -EINVAL input zero (invalid) + * -EOVERFLOW input too large for this vli code (invalid) + */ +static inline int vli_encode_bits(struct bitstream *bs, u64 in) +{ + u64 code = code; + int bits = __vli_encode_bits(&code, in); + + if (bits <= 0) + return bits; + + return bitstream_put_bits(bs, code, bits); +} + +#endif diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c new file mode 100644 index 000000000000..ed8796f1112d --- /dev/null +++ b/drivers/block/drbd/drbd_worker.c @@ -0,0 +1,1512 @@ +/* + drbd_worker.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "drbd_int.h" +#include "drbd_req.h" + +#define SLEEP_TIME (HZ/10) + +static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int cancel); + + + +/* defined here: + drbd_md_io_complete + drbd_endio_write_sec + drbd_endio_read_sec + drbd_endio_pri + + * more endio handlers: + atodb_endio in drbd_actlog.c + drbd_bm_async_io_complete in drbd_bitmap.c + + * For all these callbacks, note the following: + * The callbacks will be called in irq context by the IDE drivers, + * and in Softirqs/Tasklets/BH context by the SCSI drivers. + * Try to get the locking right :) + * + */ + + +/* About the global_state_lock + Each state transition on an device holds a read lock. In case we have + to evaluate the sync after dependencies, we grab a write lock, because + we need stable states on all devices for that. */ +rwlock_t global_state_lock; + +/* used for synchronous meta data and bitmap IO + * submitted by drbd_md_sync_page_io() + */ +void drbd_md_io_complete(struct bio *bio, int error) +{ + struct drbd_md_io *md_io; + + md_io = (struct drbd_md_io *)bio->bi_private; + md_io->error = error; + + complete(&md_io->event); +} + +/* reads on behalf of the partner, + * "submitted" by the receiver + */ +void drbd_endio_read_sec(struct bio *bio, int error) __releases(local) +{ + unsigned long flags = 0; + struct drbd_epoch_entry *e = NULL; + struct drbd_conf *mdev; + int uptodate = bio_flagged(bio, BIO_UPTODATE); + + e = bio->bi_private; + mdev = e->mdev; + + if (error) + dev_warn(DEV, "read: error=%d s=%llus\n", error, + (unsigned long long)e->sector); + if (!error && !uptodate) { + dev_warn(DEV, "read: setting error to -EIO s=%llus\n", + (unsigned long long)e->sector); + /* strange behavior of some lower level drivers... + * fail the request by clearing the uptodate flag, + * but do not return any error?! */ + error = -EIO; + } + + D_ASSERT(e->block_id != ID_VACANT); + + spin_lock_irqsave(&mdev->req_lock, flags); + mdev->read_cnt += e->size >> 9; + list_del(&e->w.list); + if (list_empty(&mdev->read_ee)) + wake_up(&mdev->ee_wait); + spin_unlock_irqrestore(&mdev->req_lock, flags); + + drbd_chk_io_error(mdev, error, FALSE); + drbd_queue_work(&mdev->data.work, &e->w); + put_ldev(mdev); +} + +/* writes on behalf of the partner, or resync writes, + * "submitted" by the receiver. + */ +void drbd_endio_write_sec(struct bio *bio, int error) __releases(local) +{ + unsigned long flags = 0; + struct drbd_epoch_entry *e = NULL; + struct drbd_conf *mdev; + sector_t e_sector; + int do_wake; + int is_syncer_req; + int do_al_complete_io; + int uptodate = bio_flagged(bio, BIO_UPTODATE); + int is_barrier = bio_rw_flagged(bio, BIO_RW_BARRIER); + + e = bio->bi_private; + mdev = e->mdev; + + if (error) + dev_warn(DEV, "write: error=%d s=%llus\n", error, + (unsigned long long)e->sector); + if (!error && !uptodate) { + dev_warn(DEV, "write: setting error to -EIO s=%llus\n", + (unsigned long long)e->sector); + /* strange behavior of some lower level drivers... + * fail the request by clearing the uptodate flag, + * but do not return any error?! */ + error = -EIO; + } + + /* error == -ENOTSUPP would be a better test, + * alas it is not reliable */ + if (error && is_barrier && e->flags & EE_IS_BARRIER) { + drbd_bump_write_ordering(mdev, WO_bdev_flush); + spin_lock_irqsave(&mdev->req_lock, flags); + list_del(&e->w.list); + e->w.cb = w_e_reissue; + /* put_ldev actually happens below, once we come here again. */ + __release(local); + spin_unlock_irqrestore(&mdev->req_lock, flags); + drbd_queue_work(&mdev->data.work, &e->w); + return; + } + + D_ASSERT(e->block_id != ID_VACANT); + + spin_lock_irqsave(&mdev->req_lock, flags); + mdev->writ_cnt += e->size >> 9; + is_syncer_req = is_syncer_block_id(e->block_id); + + /* after we moved e to done_ee, + * we may no longer access it, + * it may be freed/reused already! + * (as soon as we release the req_lock) */ + e_sector = e->sector; + do_al_complete_io = e->flags & EE_CALL_AL_COMPLETE_IO; + + list_del(&e->w.list); /* has been on active_ee or sync_ee */ + list_add_tail(&e->w.list, &mdev->done_ee); + + /* No hlist_del_init(&e->colision) here, we did not send the Ack yet, + * neither did we wake possibly waiting conflicting requests. + * done from "drbd_process_done_ee" within the appropriate w.cb + * (e_end_block/e_end_resync_block) or from _drbd_clear_done_ee */ + + do_wake = is_syncer_req + ? list_empty(&mdev->sync_ee) + : list_empty(&mdev->active_ee); + + if (error) + __drbd_chk_io_error(mdev, FALSE); + spin_unlock_irqrestore(&mdev->req_lock, flags); + + if (is_syncer_req) + drbd_rs_complete_io(mdev, e_sector); + + if (do_wake) + wake_up(&mdev->ee_wait); + + if (do_al_complete_io) + drbd_al_complete_io(mdev, e_sector); + + wake_asender(mdev); + put_ldev(mdev); + +} + +/* read, readA or write requests on R_PRIMARY coming from drbd_make_request + */ +void drbd_endio_pri(struct bio *bio, int error) +{ + unsigned long flags; + struct drbd_request *req = bio->bi_private; + struct drbd_conf *mdev = req->mdev; + struct bio_and_error m; + enum drbd_req_event what; + int uptodate = bio_flagged(bio, BIO_UPTODATE); + + if (error) + dev_warn(DEV, "p %s: error=%d\n", + bio_data_dir(bio) == WRITE ? "write" : "read", error); + if (!error && !uptodate) { + dev_warn(DEV, "p %s: setting error to -EIO\n", + bio_data_dir(bio) == WRITE ? "write" : "read"); + /* strange behavior of some lower level drivers... + * fail the request by clearing the uptodate flag, + * but do not return any error?! */ + error = -EIO; + } + + /* to avoid recursion in __req_mod */ + if (unlikely(error)) { + what = (bio_data_dir(bio) == WRITE) + ? write_completed_with_error + : (bio_rw(bio) == READA) + ? read_completed_with_error + : read_ahead_completed_with_error; + } else + what = completed_ok; + + bio_put(req->private_bio); + req->private_bio = ERR_PTR(error); + + spin_lock_irqsave(&mdev->req_lock, flags); + __req_mod(req, what, &m); + spin_unlock_irqrestore(&mdev->req_lock, flags); + + if (m.bio) + complete_master_bio(mdev, &m); +} + +int w_io_error(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_request *req = container_of(w, struct drbd_request, w); + + /* NOTE: mdev->ldev can be NULL by the time we get here! */ + /* D_ASSERT(mdev->ldev->dc.on_io_error != EP_PASS_ON); */ + + /* the only way this callback is scheduled is from _req_may_be_done, + * when it is done and had a local write error, see comments there */ + drbd_req_free(req); + + return TRUE; +} + +int w_read_retry_remote(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_request *req = container_of(w, struct drbd_request, w); + + /* We should not detach for read io-error, + * but try to WRITE the P_DATA_REPLY to the failed location, + * to give the disk the chance to relocate that block */ + + spin_lock_irq(&mdev->req_lock); + if (cancel || + mdev->state.conn < C_CONNECTED || + mdev->state.pdsk <= D_INCONSISTENT) { + _req_mod(req, send_canceled); + spin_unlock_irq(&mdev->req_lock); + dev_alert(DEV, "WE ARE LOST. Local IO failure, no peer.\n"); + return 1; + } + spin_unlock_irq(&mdev->req_lock); + + return w_send_read_req(mdev, w, 0); +} + +int w_resync_inactive(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + ERR_IF(cancel) return 1; + dev_err(DEV, "resync inactive, but callback triggered??\n"); + return 1; /* Simply ignore this! */ +} + +void drbd_csum(struct drbd_conf *mdev, struct crypto_hash *tfm, struct bio *bio, void *digest) +{ + struct hash_desc desc; + struct scatterlist sg; + struct bio_vec *bvec; + int i; + + desc.tfm = tfm; + desc.flags = 0; + + sg_init_table(&sg, 1); + crypto_hash_init(&desc); + + __bio_for_each_segment(bvec, bio, i, 0) { + sg_set_page(&sg, bvec->bv_page, bvec->bv_len, bvec->bv_offset); + crypto_hash_update(&desc, &sg, sg.length); + } + crypto_hash_final(&desc, digest); +} + +static int w_e_send_csum(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + int digest_size; + void *digest; + int ok; + + D_ASSERT(e->block_id == DRBD_MAGIC + 0xbeef); + + if (unlikely(cancel)) { + drbd_free_ee(mdev, e); + return 1; + } + + if (likely(drbd_bio_uptodate(e->private_bio))) { + digest_size = crypto_hash_digestsize(mdev->csums_tfm); + digest = kmalloc(digest_size, GFP_NOIO); + if (digest) { + drbd_csum(mdev, mdev->csums_tfm, e->private_bio, digest); + + inc_rs_pending(mdev); + ok = drbd_send_drequest_csum(mdev, + e->sector, + e->size, + digest, + digest_size, + P_CSUM_RS_REQUEST); + kfree(digest); + } else { + dev_err(DEV, "kmalloc() of digest failed.\n"); + ok = 0; + } + } else + ok = 1; + + drbd_free_ee(mdev, e); + + if (unlikely(!ok)) + dev_err(DEV, "drbd_send_drequest(..., csum) failed\n"); + return ok; +} + +#define GFP_TRY (__GFP_HIGHMEM | __GFP_NOWARN) + +static int read_for_csum(struct drbd_conf *mdev, sector_t sector, int size) +{ + struct drbd_epoch_entry *e; + + if (!get_ldev(mdev)) + return 0; + + /* GFP_TRY, because if there is no memory available right now, this may + * be rescheduled for later. It is "only" background resync, after all. */ + e = drbd_alloc_ee(mdev, DRBD_MAGIC+0xbeef, sector, size, GFP_TRY); + if (!e) { + put_ldev(mdev); + return 2; + } + + spin_lock_irq(&mdev->req_lock); + list_add(&e->w.list, &mdev->read_ee); + spin_unlock_irq(&mdev->req_lock); + + e->private_bio->bi_end_io = drbd_endio_read_sec; + e->private_bio->bi_rw = READ; + e->w.cb = w_e_send_csum; + + mdev->read_cnt += size >> 9; + drbd_generic_make_request(mdev, DRBD_FAULT_RS_RD, e->private_bio); + + return 1; +} + +void resync_timer_fn(unsigned long data) +{ + unsigned long flags; + struct drbd_conf *mdev = (struct drbd_conf *) data; + int queue; + + spin_lock_irqsave(&mdev->req_lock, flags); + + if (likely(!test_and_clear_bit(STOP_SYNC_TIMER, &mdev->flags))) { + queue = 1; + if (mdev->state.conn == C_VERIFY_S) + mdev->resync_work.cb = w_make_ov_request; + else + mdev->resync_work.cb = w_make_resync_request; + } else { + queue = 0; + mdev->resync_work.cb = w_resync_inactive; + } + + spin_unlock_irqrestore(&mdev->req_lock, flags); + + /* harmless race: list_empty outside data.work.q_lock */ + if (list_empty(&mdev->resync_work.list) && queue) + drbd_queue_work(&mdev->data.work, &mdev->resync_work); +} + +int w_make_resync_request(struct drbd_conf *mdev, + struct drbd_work *w, int cancel) +{ + unsigned long bit; + sector_t sector; + const sector_t capacity = drbd_get_capacity(mdev->this_bdev); + int max_segment_size = queue_max_segment_size(mdev->rq_queue); + int number, i, size, pe, mx; + int align, queued, sndbuf; + + if (unlikely(cancel)) + return 1; + + if (unlikely(mdev->state.conn < C_CONNECTED)) { + dev_err(DEV, "Confused in w_make_resync_request()! cstate < Connected"); + return 0; + } + + if (mdev->state.conn != C_SYNC_TARGET) + dev_err(DEV, "%s in w_make_resync_request\n", + drbd_conn_str(mdev->state.conn)); + + if (!get_ldev(mdev)) { + /* Since we only need to access mdev->rsync a + get_ldev_if_state(mdev,D_FAILED) would be sufficient, but + to continue resync with a broken disk makes no sense at + all */ + dev_err(DEV, "Disk broke down during resync!\n"); + mdev->resync_work.cb = w_resync_inactive; + return 1; + } + + number = SLEEP_TIME * mdev->sync_conf.rate / ((BM_BLOCK_SIZE/1024)*HZ); + pe = atomic_read(&mdev->rs_pending_cnt); + + mutex_lock(&mdev->data.mutex); + if (mdev->data.socket) + mx = mdev->data.socket->sk->sk_rcvbuf / sizeof(struct p_block_req); + else + mx = 1; + mutex_unlock(&mdev->data.mutex); + + /* For resync rates >160MB/sec, allow more pending RS requests */ + if (number > mx) + mx = number; + + /* Limit the number of pending RS requests to no more than the peer's receive buffer */ + if ((pe + number) > mx) { + number = mx - pe; + } + + for (i = 0; i < number; i++) { + /* Stop generating RS requests, when half of the send buffer is filled */ + mutex_lock(&mdev->data.mutex); + if (mdev->data.socket) { + queued = mdev->data.socket->sk->sk_wmem_queued; + sndbuf = mdev->data.socket->sk->sk_sndbuf; + } else { + queued = 1; + sndbuf = 0; + } + mutex_unlock(&mdev->data.mutex); + if (queued > sndbuf / 2) + goto requeue; + +next_sector: + size = BM_BLOCK_SIZE; + bit = drbd_bm_find_next(mdev, mdev->bm_resync_fo); + + if (bit == -1UL) { + mdev->bm_resync_fo = drbd_bm_bits(mdev); + mdev->resync_work.cb = w_resync_inactive; + put_ldev(mdev); + return 1; + } + + sector = BM_BIT_TO_SECT(bit); + + if (drbd_try_rs_begin_io(mdev, sector)) { + mdev->bm_resync_fo = bit; + goto requeue; + } + mdev->bm_resync_fo = bit + 1; + + if (unlikely(drbd_bm_test_bit(mdev, bit) == 0)) { + drbd_rs_complete_io(mdev, sector); + goto next_sector; + } + +#if DRBD_MAX_SEGMENT_SIZE > BM_BLOCK_SIZE + /* try to find some adjacent bits. + * we stop if we have already the maximum req size. + * + * Additionally always align bigger requests, in order to + * be prepared for all stripe sizes of software RAIDs. + * + * we _do_ care about the agreed-upon q->max_segment_size + * here, as splitting up the requests on the other side is more + * difficult. the consequence is, that on lvm and md and other + * "indirect" devices, this is dead code, since + * q->max_segment_size will be PAGE_SIZE. + */ + align = 1; + for (;;) { + if (size + BM_BLOCK_SIZE > max_segment_size) + break; + + /* Be always aligned */ + if (sector & ((1<<(align+3))-1)) + break; + + /* do not cross extent boundaries */ + if (((bit+1) & BM_BLOCKS_PER_BM_EXT_MASK) == 0) + break; + /* now, is it actually dirty, after all? + * caution, drbd_bm_test_bit is tri-state for some + * obscure reason; ( b == 0 ) would get the out-of-band + * only accidentally right because of the "oddly sized" + * adjustment below */ + if (drbd_bm_test_bit(mdev, bit+1) != 1) + break; + bit++; + size += BM_BLOCK_SIZE; + if ((BM_BLOCK_SIZE << align) <= size) + align++; + i++; + } + /* if we merged some, + * reset the offset to start the next drbd_bm_find_next from */ + if (size > BM_BLOCK_SIZE) + mdev->bm_resync_fo = bit + 1; +#endif + + /* adjust very last sectors, in case we are oddly sized */ + if (sector + (size>>9) > capacity) + size = (capacity-sector)<<9; + if (mdev->agreed_pro_version >= 89 && mdev->csums_tfm) { + switch (read_for_csum(mdev, sector, size)) { + case 0: /* Disk failure*/ + put_ldev(mdev); + return 0; + case 2: /* Allocation failed */ + drbd_rs_complete_io(mdev, sector); + mdev->bm_resync_fo = BM_SECT_TO_BIT(sector); + goto requeue; + /* case 1: everything ok */ + } + } else { + inc_rs_pending(mdev); + if (!drbd_send_drequest(mdev, P_RS_DATA_REQUEST, + sector, size, ID_SYNCER)) { + dev_err(DEV, "drbd_send_drequest() failed, aborting...\n"); + dec_rs_pending(mdev); + put_ldev(mdev); + return 0; + } + } + } + + if (mdev->bm_resync_fo >= drbd_bm_bits(mdev)) { + /* last syncer _request_ was sent, + * but the P_RS_DATA_REPLY not yet received. sync will end (and + * next sync group will resume), as soon as we receive the last + * resync data block, and the last bit is cleared. + * until then resync "work" is "inactive" ... + */ + mdev->resync_work.cb = w_resync_inactive; + put_ldev(mdev); + return 1; + } + + requeue: + mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME); + put_ldev(mdev); + return 1; +} + +static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + int number, i, size; + sector_t sector; + const sector_t capacity = drbd_get_capacity(mdev->this_bdev); + + if (unlikely(cancel)) + return 1; + + if (unlikely(mdev->state.conn < C_CONNECTED)) { + dev_err(DEV, "Confused in w_make_ov_request()! cstate < Connected"); + return 0; + } + + number = SLEEP_TIME*mdev->sync_conf.rate / ((BM_BLOCK_SIZE/1024)*HZ); + if (atomic_read(&mdev->rs_pending_cnt) > number) + goto requeue; + + number -= atomic_read(&mdev->rs_pending_cnt); + + sector = mdev->ov_position; + for (i = 0; i < number; i++) { + if (sector >= capacity) { + mdev->resync_work.cb = w_resync_inactive; + return 1; + } + + size = BM_BLOCK_SIZE; + + if (drbd_try_rs_begin_io(mdev, sector)) { + mdev->ov_position = sector; + goto requeue; + } + + if (sector + (size>>9) > capacity) + size = (capacity-sector)<<9; + + inc_rs_pending(mdev); + if (!drbd_send_ov_request(mdev, sector, size)) { + dec_rs_pending(mdev); + return 0; + } + sector += BM_SECT_PER_BIT; + } + mdev->ov_position = sector; + + requeue: + mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME); + return 1; +} + + +int w_ov_finished(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + kfree(w); + ov_oos_print(mdev); + drbd_resync_finished(mdev); + + return 1; +} + +static int w_resync_finished(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + kfree(w); + + drbd_resync_finished(mdev); + + return 1; +} + +int drbd_resync_finished(struct drbd_conf *mdev) +{ + unsigned long db, dt, dbdt; + unsigned long n_oos; + union drbd_state os, ns; + struct drbd_work *w; + char *khelper_cmd = NULL; + + /* Remove all elements from the resync LRU. Since future actions + * might set bits in the (main) bitmap, then the entries in the + * resync LRU would be wrong. */ + if (drbd_rs_del_all(mdev)) { + /* In case this is not possible now, most probably because + * there are P_RS_DATA_REPLY Packets lingering on the worker's + * queue (or even the read operations for those packets + * is not finished by now). Retry in 100ms. */ + + drbd_kick_lo(mdev); + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ / 10); + w = kmalloc(sizeof(struct drbd_work), GFP_ATOMIC); + if (w) { + w->cb = w_resync_finished; + drbd_queue_work(&mdev->data.work, w); + return 1; + } + dev_err(DEV, "Warn failed to drbd_rs_del_all() and to kmalloc(w).\n"); + } + + dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ; + if (dt <= 0) + dt = 1; + db = mdev->rs_total; + dbdt = Bit2KB(db/dt); + mdev->rs_paused /= HZ; + + if (!get_ldev(mdev)) + goto out; + + spin_lock_irq(&mdev->req_lock); + os = mdev->state; + + /* This protects us against multiple calls (that can happen in the presence + of application IO), and against connectivity loss just before we arrive here. */ + if (os.conn <= C_CONNECTED) + goto out_unlock; + + ns = os; + ns.conn = C_CONNECTED; + + dev_info(DEV, "%s done (total %lu sec; paused %lu sec; %lu K/sec)\n", + (os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) ? + "Online verify " : "Resync", + dt + mdev->rs_paused, mdev->rs_paused, dbdt); + + n_oos = drbd_bm_total_weight(mdev); + + if (os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) { + if (n_oos) { + dev_alert(DEV, "Online verify found %lu %dk block out of sync!\n", + n_oos, Bit2KB(1)); + khelper_cmd = "out-of-sync"; + } + } else { + D_ASSERT((n_oos - mdev->rs_failed) == 0); + + if (os.conn == C_SYNC_TARGET || os.conn == C_PAUSED_SYNC_T) + khelper_cmd = "after-resync-target"; + + if (mdev->csums_tfm && mdev->rs_total) { + const unsigned long s = mdev->rs_same_csum; + const unsigned long t = mdev->rs_total; + const int ratio = + (t == 0) ? 0 : + (t < 100000) ? ((s*100)/t) : (s/(t/100)); + dev_info(DEV, "%u %% had equal check sums, eliminated: %luK; " + "transferred %luK total %luK\n", + ratio, + Bit2KB(mdev->rs_same_csum), + Bit2KB(mdev->rs_total - mdev->rs_same_csum), + Bit2KB(mdev->rs_total)); + } + } + + if (mdev->rs_failed) { + dev_info(DEV, " %lu failed blocks\n", mdev->rs_failed); + + if (os.conn == C_SYNC_TARGET || os.conn == C_PAUSED_SYNC_T) { + ns.disk = D_INCONSISTENT; + ns.pdsk = D_UP_TO_DATE; + } else { + ns.disk = D_UP_TO_DATE; + ns.pdsk = D_INCONSISTENT; + } + } else { + ns.disk = D_UP_TO_DATE; + ns.pdsk = D_UP_TO_DATE; + + if (os.conn == C_SYNC_TARGET || os.conn == C_PAUSED_SYNC_T) { + if (mdev->p_uuid) { + int i; + for (i = UI_BITMAP ; i <= UI_HISTORY_END ; i++) + _drbd_uuid_set(mdev, i, mdev->p_uuid[i]); + drbd_uuid_set(mdev, UI_BITMAP, mdev->ldev->md.uuid[UI_CURRENT]); + _drbd_uuid_set(mdev, UI_CURRENT, mdev->p_uuid[UI_CURRENT]); + } else { + dev_err(DEV, "mdev->p_uuid is NULL! BUG\n"); + } + } + + drbd_uuid_set_bm(mdev, 0UL); + + if (mdev->p_uuid) { + /* Now the two UUID sets are equal, update what we + * know of the peer. */ + int i; + for (i = UI_CURRENT ; i <= UI_HISTORY_END ; i++) + mdev->p_uuid[i] = mdev->ldev->md.uuid[i]; + } + } + + _drbd_set_state(mdev, ns, CS_VERBOSE, NULL); +out_unlock: + spin_unlock_irq(&mdev->req_lock); + put_ldev(mdev); +out: + mdev->rs_total = 0; + mdev->rs_failed = 0; + mdev->rs_paused = 0; + mdev->ov_start_sector = 0; + + if (test_and_clear_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags)) { + dev_warn(DEV, "Writing the whole bitmap, due to failed kmalloc\n"); + drbd_queue_bitmap_io(mdev, &drbd_bm_write, NULL, "write from resync_finished"); + } + + if (khelper_cmd) + drbd_khelper(mdev, khelper_cmd); + + return 1; +} + +/* helper */ +static void move_to_net_ee_or_free(struct drbd_conf *mdev, struct drbd_epoch_entry *e) +{ + if (drbd_bio_has_active_page(e->private_bio)) { + /* This might happen if sendpage() has not finished */ + spin_lock_irq(&mdev->req_lock); + list_add_tail(&e->w.list, &mdev->net_ee); + spin_unlock_irq(&mdev->req_lock); + } else + drbd_free_ee(mdev, e); +} + +/** + * w_e_end_data_req() - Worker callback, to send a P_DATA_REPLY packet in response to a P_DATA_REQUEST + * @mdev: DRBD device. + * @w: work object. + * @cancel: The connection will be closed anyways + */ +int w_e_end_data_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + int ok; + + if (unlikely(cancel)) { + drbd_free_ee(mdev, e); + dec_unacked(mdev); + return 1; + } + + if (likely(drbd_bio_uptodate(e->private_bio))) { + ok = drbd_send_block(mdev, P_DATA_REPLY, e); + } else { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Sending NegDReply. sector=%llus.\n", + (unsigned long long)e->sector); + + ok = drbd_send_ack(mdev, P_NEG_DREPLY, e); + } + + dec_unacked(mdev); + + move_to_net_ee_or_free(mdev, e); + + if (unlikely(!ok)) + dev_err(DEV, "drbd_send_block() failed\n"); + return ok; +} + +/** + * w_e_end_rsdata_req() - Worker callback to send a P_RS_DATA_REPLY packet in response to a P_RS_DATA_REQUESTRS + * @mdev: DRBD device. + * @w: work object. + * @cancel: The connection will be closed anyways + */ +int w_e_end_rsdata_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + int ok; + + if (unlikely(cancel)) { + drbd_free_ee(mdev, e); + dec_unacked(mdev); + return 1; + } + + if (get_ldev_if_state(mdev, D_FAILED)) { + drbd_rs_complete_io(mdev, e->sector); + put_ldev(mdev); + } + + if (likely(drbd_bio_uptodate(e->private_bio))) { + if (likely(mdev->state.pdsk >= D_INCONSISTENT)) { + inc_rs_pending(mdev); + ok = drbd_send_block(mdev, P_RS_DATA_REPLY, e); + } else { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Not sending RSDataReply, " + "partner DISKLESS!\n"); + ok = 1; + } + } else { + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Sending NegRSDReply. sector %llus.\n", + (unsigned long long)e->sector); + + ok = drbd_send_ack(mdev, P_NEG_RS_DREPLY, e); + + /* update resync data with failure */ + drbd_rs_failed_io(mdev, e->sector, e->size); + } + + dec_unacked(mdev); + + move_to_net_ee_or_free(mdev, e); + + if (unlikely(!ok)) + dev_err(DEV, "drbd_send_block() failed\n"); + return ok; +} + +int w_e_end_csum_rs_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + struct digest_info *di; + int digest_size; + void *digest = NULL; + int ok, eq = 0; + + if (unlikely(cancel)) { + drbd_free_ee(mdev, e); + dec_unacked(mdev); + return 1; + } + + drbd_rs_complete_io(mdev, e->sector); + + di = (struct digest_info *)(unsigned long)e->block_id; + + if (likely(drbd_bio_uptodate(e->private_bio))) { + /* quick hack to try to avoid a race against reconfiguration. + * a real fix would be much more involved, + * introducing more locking mechanisms */ + if (mdev->csums_tfm) { + digest_size = crypto_hash_digestsize(mdev->csums_tfm); + D_ASSERT(digest_size == di->digest_size); + digest = kmalloc(digest_size, GFP_NOIO); + } + if (digest) { + drbd_csum(mdev, mdev->csums_tfm, e->private_bio, digest); + eq = !memcmp(digest, di->digest, digest_size); + kfree(digest); + } + + if (eq) { + drbd_set_in_sync(mdev, e->sector, e->size); + mdev->rs_same_csum++; + ok = drbd_send_ack(mdev, P_RS_IS_IN_SYNC, e); + } else { + inc_rs_pending(mdev); + e->block_id = ID_SYNCER; + ok = drbd_send_block(mdev, P_RS_DATA_REPLY, e); + } + } else { + ok = drbd_send_ack(mdev, P_NEG_RS_DREPLY, e); + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Sending NegDReply. I guess it gets messy.\n"); + } + + dec_unacked(mdev); + + kfree(di); + + move_to_net_ee_or_free(mdev, e); + + if (unlikely(!ok)) + dev_err(DEV, "drbd_send_block/ack() failed\n"); + return ok; +} + +int w_e_end_ov_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + int digest_size; + void *digest; + int ok = 1; + + if (unlikely(cancel)) + goto out; + + if (unlikely(!drbd_bio_uptodate(e->private_bio))) + goto out; + + digest_size = crypto_hash_digestsize(mdev->verify_tfm); + /* FIXME if this allocation fails, online verify will not terminate! */ + digest = kmalloc(digest_size, GFP_NOIO); + if (digest) { + drbd_csum(mdev, mdev->verify_tfm, e->private_bio, digest); + inc_rs_pending(mdev); + ok = drbd_send_drequest_csum(mdev, e->sector, e->size, + digest, digest_size, P_OV_REPLY); + if (!ok) + dec_rs_pending(mdev); + kfree(digest); + } + +out: + drbd_free_ee(mdev, e); + + dec_unacked(mdev); + + return ok; +} + +void drbd_ov_oos_found(struct drbd_conf *mdev, sector_t sector, int size) +{ + if (mdev->ov_last_oos_start + mdev->ov_last_oos_size == sector) { + mdev->ov_last_oos_size += size>>9; + } else { + mdev->ov_last_oos_start = sector; + mdev->ov_last_oos_size = size>>9; + } + drbd_set_out_of_sync(mdev, sector, size); + set_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags); +} + +int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w); + struct digest_info *di; + int digest_size; + void *digest; + int ok, eq = 0; + + if (unlikely(cancel)) { + drbd_free_ee(mdev, e); + dec_unacked(mdev); + return 1; + } + + /* after "cancel", because after drbd_disconnect/drbd_rs_cancel_all + * the resync lru has been cleaned up already */ + drbd_rs_complete_io(mdev, e->sector); + + di = (struct digest_info *)(unsigned long)e->block_id; + + if (likely(drbd_bio_uptodate(e->private_bio))) { + digest_size = crypto_hash_digestsize(mdev->verify_tfm); + digest = kmalloc(digest_size, GFP_NOIO); + if (digest) { + drbd_csum(mdev, mdev->verify_tfm, e->private_bio, digest); + + D_ASSERT(digest_size == di->digest_size); + eq = !memcmp(digest, di->digest, digest_size); + kfree(digest); + } + } else { + ok = drbd_send_ack(mdev, P_NEG_RS_DREPLY, e); + if (__ratelimit(&drbd_ratelimit_state)) + dev_err(DEV, "Sending NegDReply. I guess it gets messy.\n"); + } + + dec_unacked(mdev); + + kfree(di); + + if (!eq) + drbd_ov_oos_found(mdev, e->sector, e->size); + else + ov_oos_print(mdev); + + ok = drbd_send_ack_ex(mdev, P_OV_RESULT, e->sector, e->size, + eq ? ID_IN_SYNC : ID_OUT_OF_SYNC); + + drbd_free_ee(mdev, e); + + if (--mdev->ov_left == 0) { + ov_oos_print(mdev); + drbd_resync_finished(mdev); + } + + return ok; +} + +int w_prev_work_done(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_wq_barrier *b = container_of(w, struct drbd_wq_barrier, w); + complete(&b->done); + return 1; +} + +int w_send_barrier(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_tl_epoch *b = container_of(w, struct drbd_tl_epoch, w); + struct p_barrier *p = &mdev->data.sbuf.barrier; + int ok = 1; + + /* really avoid racing with tl_clear. w.cb may have been referenced + * just before it was reassigned and re-queued, so double check that. + * actually, this race was harmless, since we only try to send the + * barrier packet here, and otherwise do nothing with the object. + * but compare with the head of w_clear_epoch */ + spin_lock_irq(&mdev->req_lock); + if (w->cb != w_send_barrier || mdev->state.conn < C_CONNECTED) + cancel = 1; + spin_unlock_irq(&mdev->req_lock); + if (cancel) + return 1; + + if (!drbd_get_data_sock(mdev)) + return 0; + p->barrier = b->br_number; + /* inc_ap_pending was done where this was queued. + * dec_ap_pending will be done in got_BarrierAck + * or (on connection loss) in w_clear_epoch. */ + ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BARRIER, + (struct p_header *)p, sizeof(*p), 0); + drbd_put_data_sock(mdev); + + return ok; +} + +int w_send_write_hint(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + if (cancel) + return 1; + return drbd_send_short_cmd(mdev, P_UNPLUG_REMOTE); +} + +/** + * w_send_dblock() - Worker callback to send a P_DATA packet in order to mirror a write request + * @mdev: DRBD device. + * @w: work object. + * @cancel: The connection will be closed anyways + */ +int w_send_dblock(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_request *req = container_of(w, struct drbd_request, w); + int ok; + + if (unlikely(cancel)) { + req_mod(req, send_canceled); + return 1; + } + + ok = drbd_send_dblock(mdev, req); + req_mod(req, ok ? handed_over_to_network : send_failed); + + return ok; +} + +/** + * w_send_read_req() - Worker callback to send a read request (P_DATA_REQUEST) packet + * @mdev: DRBD device. + * @w: work object. + * @cancel: The connection will be closed anyways + */ +int w_send_read_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel) +{ + struct drbd_request *req = container_of(w, struct drbd_request, w); + int ok; + + if (unlikely(cancel)) { + req_mod(req, send_canceled); + return 1; + } + + ok = drbd_send_drequest(mdev, P_DATA_REQUEST, req->sector, req->size, + (unsigned long)req); + + if (!ok) { + /* ?? we set C_TIMEOUT or C_BROKEN_PIPE in drbd_send(); + * so this is probably redundant */ + if (mdev->state.conn >= C_CONNECTED) + drbd_force_state(mdev, NS(conn, C_NETWORK_FAILURE)); + } + req_mod(req, ok ? handed_over_to_network : send_failed); + + return ok; +} + +static int _drbd_may_sync_now(struct drbd_conf *mdev) +{ + struct drbd_conf *odev = mdev; + + while (1) { + if (odev->sync_conf.after == -1) + return 1; + odev = minor_to_mdev(odev->sync_conf.after); + ERR_IF(!odev) return 1; + if ((odev->state.conn >= C_SYNC_SOURCE && + odev->state.conn <= C_PAUSED_SYNC_T) || + odev->state.aftr_isp || odev->state.peer_isp || + odev->state.user_isp) + return 0; + } +} + +/** + * _drbd_pause_after() - Pause resync on all devices that may not resync now + * @mdev: DRBD device. + * + * Called from process context only (admin command and after_state_ch). + */ +static int _drbd_pause_after(struct drbd_conf *mdev) +{ + struct drbd_conf *odev; + int i, rv = 0; + + for (i = 0; i < minor_count; i++) { + odev = minor_to_mdev(i); + if (!odev) + continue; + if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS) + continue; + if (!_drbd_may_sync_now(odev)) + rv |= (__drbd_set_state(_NS(odev, aftr_isp, 1), CS_HARD, NULL) + != SS_NOTHING_TO_DO); + } + + return rv; +} + +/** + * _drbd_resume_next() - Resume resync on all devices that may resync now + * @mdev: DRBD device. + * + * Called from process context only (admin command and worker). + */ +static int _drbd_resume_next(struct drbd_conf *mdev) +{ + struct drbd_conf *odev; + int i, rv = 0; + + for (i = 0; i < minor_count; i++) { + odev = minor_to_mdev(i); + if (!odev) + continue; + if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS) + continue; + if (odev->state.aftr_isp) { + if (_drbd_may_sync_now(odev)) + rv |= (__drbd_set_state(_NS(odev, aftr_isp, 0), + CS_HARD, NULL) + != SS_NOTHING_TO_DO) ; + } + } + return rv; +} + +void resume_next_sg(struct drbd_conf *mdev) +{ + write_lock_irq(&global_state_lock); + _drbd_resume_next(mdev); + write_unlock_irq(&global_state_lock); +} + +void suspend_other_sg(struct drbd_conf *mdev) +{ + write_lock_irq(&global_state_lock); + _drbd_pause_after(mdev); + write_unlock_irq(&global_state_lock); +} + +static int sync_after_error(struct drbd_conf *mdev, int o_minor) +{ + struct drbd_conf *odev; + + if (o_minor == -1) + return NO_ERROR; + if (o_minor < -1 || minor_to_mdev(o_minor) == NULL) + return ERR_SYNC_AFTER; + + /* check for loops */ + odev = minor_to_mdev(o_minor); + while (1) { + if (odev == mdev) + return ERR_SYNC_AFTER_CYCLE; + + /* dependency chain ends here, no cycles. */ + if (odev->sync_conf.after == -1) + return NO_ERROR; + + /* follow the dependency chain */ + odev = minor_to_mdev(odev->sync_conf.after); + } +} + +int drbd_alter_sa(struct drbd_conf *mdev, int na) +{ + int changes; + int retcode; + + write_lock_irq(&global_state_lock); + retcode = sync_after_error(mdev, na); + if (retcode == NO_ERROR) { + mdev->sync_conf.after = na; + do { + changes = _drbd_pause_after(mdev); + changes |= _drbd_resume_next(mdev); + } while (changes); + } + write_unlock_irq(&global_state_lock); + return retcode; +} + +/** + * drbd_start_resync() - Start the resync process + * @mdev: DRBD device. + * @side: Either C_SYNC_SOURCE or C_SYNC_TARGET + * + * This function might bring you directly into one of the + * C_PAUSED_SYNC_* states. + */ +void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side) +{ + union drbd_state ns; + int r; + + if (mdev->state.conn >= C_SYNC_SOURCE) { + dev_err(DEV, "Resync already running!\n"); + return; + } + + /* In case a previous resync run was aborted by an IO error/detach on the peer. */ + drbd_rs_cancel_all(mdev); + + if (side == C_SYNC_TARGET) { + /* Since application IO was locked out during C_WF_BITMAP_T and + C_WF_SYNC_UUID we are still unmodified. Before going to C_SYNC_TARGET + we check that we might make the data inconsistent. */ + r = drbd_khelper(mdev, "before-resync-target"); + r = (r >> 8) & 0xff; + if (r > 0) { + dev_info(DEV, "before-resync-target handler returned %d, " + "dropping connection.\n", r); + drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); + return; + } + } + + drbd_state_lock(mdev); + + if (!get_ldev_if_state(mdev, D_NEGOTIATING)) { + drbd_state_unlock(mdev); + return; + } + + if (side == C_SYNC_TARGET) { + mdev->bm_resync_fo = 0; + } else /* side == C_SYNC_SOURCE */ { + u64 uuid; + + get_random_bytes(&uuid, sizeof(u64)); + drbd_uuid_set(mdev, UI_BITMAP, uuid); + drbd_send_sync_uuid(mdev, uuid); + + D_ASSERT(mdev->state.disk == D_UP_TO_DATE); + } + + write_lock_irq(&global_state_lock); + ns = mdev->state; + + ns.aftr_isp = !_drbd_may_sync_now(mdev); + + ns.conn = side; + + if (side == C_SYNC_TARGET) + ns.disk = D_INCONSISTENT; + else /* side == C_SYNC_SOURCE */ + ns.pdsk = D_INCONSISTENT; + + r = __drbd_set_state(mdev, ns, CS_VERBOSE, NULL); + ns = mdev->state; + + if (ns.conn < C_CONNECTED) + r = SS_UNKNOWN_ERROR; + + if (r == SS_SUCCESS) { + mdev->rs_total = + mdev->rs_mark_left = drbd_bm_total_weight(mdev); + mdev->rs_failed = 0; + mdev->rs_paused = 0; + mdev->rs_start = + mdev->rs_mark_time = jiffies; + mdev->rs_same_csum = 0; + _drbd_pause_after(mdev); + } + write_unlock_irq(&global_state_lock); + drbd_state_unlock(mdev); + put_ldev(mdev); + + if (r == SS_SUCCESS) { + dev_info(DEV, "Began resync as %s (will sync %lu KB [%lu bits set]).\n", + drbd_conn_str(ns.conn), + (unsigned long) mdev->rs_total << (BM_BLOCK_SHIFT-10), + (unsigned long) mdev->rs_total); + + if (mdev->rs_total == 0) { + /* Peer still reachable? Beware of failing before-resync-target handlers! */ + request_ping(mdev); + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(mdev->net_conf->ping_timeo*HZ/9); /* 9 instead 10 */ + drbd_resync_finished(mdev); + return; + } + + /* ns.conn may already be != mdev->state.conn, + * we may have been paused in between, or become paused until + * the timer triggers. + * No matter, that is handled in resync_timer_fn() */ + if (ns.conn == C_SYNC_TARGET) + mod_timer(&mdev->resync_timer, jiffies); + + drbd_md_sync(mdev); + } +} + +int drbd_worker(struct drbd_thread *thi) +{ + struct drbd_conf *mdev = thi->mdev; + struct drbd_work *w = NULL; + LIST_HEAD(work_list); + int intr = 0, i; + + sprintf(current->comm, "drbd%d_worker", mdev_to_minor(mdev)); + + while (get_t_state(thi) == Running) { + drbd_thread_current_set_cpu(mdev); + + if (down_trylock(&mdev->data.work.s)) { + mutex_lock(&mdev->data.mutex); + if (mdev->data.socket && !mdev->net_conf->no_cork) + drbd_tcp_uncork(mdev->data.socket); + mutex_unlock(&mdev->data.mutex); + + intr = down_interruptible(&mdev->data.work.s); + + mutex_lock(&mdev->data.mutex); + if (mdev->data.socket && !mdev->net_conf->no_cork) + drbd_tcp_cork(mdev->data.socket); + mutex_unlock(&mdev->data.mutex); + } + + if (intr) { + D_ASSERT(intr == -EINTR); + flush_signals(current); + ERR_IF (get_t_state(thi) == Running) + continue; + break; + } + + if (get_t_state(thi) != Running) + break; + /* With this break, we have done a down() but not consumed + the entry from the list. The cleanup code takes care of + this... */ + + w = NULL; + spin_lock_irq(&mdev->data.work.q_lock); + ERR_IF(list_empty(&mdev->data.work.q)) { + /* something terribly wrong in our logic. + * we were able to down() the semaphore, + * but the list is empty... doh. + * + * what is the best thing to do now? + * try again from scratch, restarting the receiver, + * asender, whatnot? could break even more ugly, + * e.g. when we are primary, but no good local data. + * + * I'll try to get away just starting over this loop. + */ + spin_unlock_irq(&mdev->data.work.q_lock); + continue; + } + w = list_entry(mdev->data.work.q.next, struct drbd_work, list); + list_del_init(&w->list); + spin_unlock_irq(&mdev->data.work.q_lock); + + if (!w->cb(mdev, w, mdev->state.conn < C_CONNECTED)) { + /* dev_warn(DEV, "worker: a callback failed! \n"); */ + if (mdev->state.conn >= C_CONNECTED) + drbd_force_state(mdev, + NS(conn, C_NETWORK_FAILURE)); + } + } + D_ASSERT(test_bit(DEVICE_DYING, &mdev->flags)); + D_ASSERT(test_bit(CONFIG_PENDING, &mdev->flags)); + + spin_lock_irq(&mdev->data.work.q_lock); + i = 0; + while (!list_empty(&mdev->data.work.q)) { + list_splice_init(&mdev->data.work.q, &work_list); + spin_unlock_irq(&mdev->data.work.q_lock); + + while (!list_empty(&work_list)) { + w = list_entry(work_list.next, struct drbd_work, list); + list_del_init(&w->list); + w->cb(mdev, w, 1); + i++; /* dead debugging code */ + } + + spin_lock_irq(&mdev->data.work.q_lock); + } + sema_init(&mdev->data.work.s, 0); + /* DANGEROUS race: if someone did queue his work within the spinlock, + * but up() ed outside the spinlock, we could get an up() on the + * semaphore without corresponding list entry. + * So don't do that. + */ + spin_unlock_irq(&mdev->data.work.q_lock); + + D_ASSERT(mdev->state.disk == D_DISKLESS && mdev->state.conn == C_STANDALONE); + /* _drbd_set_state only uses stop_nowait. + * wait here for the Exiting receiver. */ + drbd_thread_stop(&mdev->receiver); + drbd_mdev_cleanup(mdev); + + dev_info(DEV, "worker terminated\n"); + + clear_bit(DEVICE_DYING, &mdev->flags); + clear_bit(CONFIG_PENDING, &mdev->flags); + wake_up(&mdev->state_wait); + + return 0; +} diff --git a/drivers/block/drbd/drbd_wrappers.h b/drivers/block/drbd/drbd_wrappers.h new file mode 100644 index 000000000000..f93fa111ce50 --- /dev/null +++ b/drivers/block/drbd/drbd_wrappers.h @@ -0,0 +1,91 @@ +#ifndef _DRBD_WRAPPERS_H +#define _DRBD_WRAPPERS_H + +#include +#include + +/* see get_sb_bdev and bd_claim */ +extern char *drbd_sec_holder; + +/* sets the number of 512 byte sectors of our virtual device */ +static inline void drbd_set_my_capacity(struct drbd_conf *mdev, + sector_t size) +{ + /* set_capacity(mdev->this_bdev->bd_disk, size); */ + set_capacity(mdev->vdisk, size); + mdev->this_bdev->bd_inode->i_size = (loff_t)size << 9; +} + +#define drbd_bio_uptodate(bio) bio_flagged(bio, BIO_UPTODATE) + +static inline int drbd_bio_has_active_page(struct bio *bio) +{ + struct bio_vec *bvec; + int i; + + __bio_for_each_segment(bvec, bio, i, 0) { + if (page_count(bvec->bv_page) > 1) + return 1; + } + + return 0; +} + +/* bi_end_io handlers */ +extern void drbd_md_io_complete(struct bio *bio, int error); +extern void drbd_endio_read_sec(struct bio *bio, int error); +extern void drbd_endio_write_sec(struct bio *bio, int error); +extern void drbd_endio_pri(struct bio *bio, int error); + +/* + * used to submit our private bio + */ +static inline void drbd_generic_make_request(struct drbd_conf *mdev, + int fault_type, struct bio *bio) +{ + __release(local); + if (!bio->bi_bdev) { + printk(KERN_ERR "drbd%d: drbd_generic_make_request: " + "bio->bi_bdev == NULL\n", + mdev_to_minor(mdev)); + dump_stack(); + bio_endio(bio, -ENODEV); + return; + } + + if (FAULT_ACTIVE(mdev, fault_type)) + bio_endio(bio, -EIO); + else + generic_make_request(bio); +} + +static inline void drbd_plug_device(struct drbd_conf *mdev) +{ + struct request_queue *q; + q = bdev_get_queue(mdev->this_bdev); + + spin_lock_irq(q->queue_lock); + +/* XXX the check on !blk_queue_plugged is redundant, + * implicitly checked in blk_plug_device */ + + if (!blk_queue_plugged(q)) { + blk_plug_device(q); + del_timer(&q->unplug_timer); + /* unplugging should not happen automatically... */ + } + spin_unlock_irq(q->queue_lock); +} + +static inline int drbd_crypto_is_hash(struct crypto_tfm *tfm) +{ + return (crypto_tfm_alg_type(tfm) & CRYPTO_ALG_TYPE_HASH_MASK) + == CRYPTO_ALG_TYPE_HASH; +} + +#ifndef __CHECKER__ +# undef __cond_lock +# define __cond_lock(x,c) (c) +#endif + +#endif diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 3bb7c47c869f..1fb6c3135fc8 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -123,7 +123,15 @@ static int ps3vram_notifier_wait(struct ps3_system_bus_device *dev, { struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); u32 *notify = ps3vram_get_notifier(priv->reports, NOTIFIER); - unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms); + unsigned long timeout; + + for (timeout = 20; timeout; timeout--) { + if (!notify[3]) + return 0; + udelay(10); + } + + timeout = jiffies + msecs_to_jiffies(timeout_ms); do { if (!notify[3]) diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 8ca17a3e96ea..64e2b379a350 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -59,12 +59,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->readsect(dev, block, buf)) return -EIO; + rq_flush_dcache_pages(req); return 0; case WRITE: if (!tr->writesect) return -EIO; + rq_flush_dcache_pages(req); for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->writesect(dev, block, buf)) return -EIO; diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c index c94de3139223..f69b7783027f 100644 --- a/drivers/staging/pohmelfs/inode.c +++ b/drivers/staging/pohmelfs/inode.c @@ -143,7 +143,6 @@ static int pohmelfs_writepages(struct address_space *mapping, struct writeback_c struct inode *inode = mapping->host; struct pohmelfs_inode *pi = POHMELFS_I(inode); struct pohmelfs_sb *psb = POHMELFS_SB(inode->i_sb); - struct backing_dev_info *bdi = mapping->backing_dev_info; int err = 0; int done = 0; int nr_pages; @@ -152,11 +151,6 @@ static int pohmelfs_writepages(struct address_space *mapping, struct writeback_c int scanned = 0; int range_whole = 0; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ end = -1; @@ -248,10 +242,6 @@ retry: if (wbc->nr_to_write <= 0) done = 1; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - done = 1; - } continue; out_continue: diff --git a/fs/aio.c b/fs/aio.c index 02a2c9340573..c30dfc006108 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define DEBUG 0 @@ -32,6 +33,9 @@ #include #include #include +#include +#include +#include #include #include @@ -60,6 +64,14 @@ static DECLARE_WORK(fput_work, aio_fput_routine); static DEFINE_SPINLOCK(fput_lock); static LIST_HEAD(fput_head); +#define AIO_BATCH_HASH_BITS 3 /* allocated on-stack, so don't go crazy */ +#define AIO_BATCH_HASH_SIZE (1 << AIO_BATCH_HASH_BITS) +struct aio_batch_entry { + struct hlist_node list; + struct address_space *mapping; +}; +mempool_t *abe_pool; + static void aio_kick_handler(struct work_struct *); static void aio_queue_work(struct kioctx *); @@ -73,6 +85,8 @@ static int __init aio_setup(void) kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); aio_wq = create_workqueue("aio"); + abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry)); + BUG_ON(!abe_pool); pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page)); @@ -1531,8 +1545,44 @@ static int aio_wake_function(wait_queue_t *wait, unsigned mode, return 1; } +static void aio_batch_add(struct address_space *mapping, + struct hlist_head *batch_hash) +{ + struct aio_batch_entry *abe; + struct hlist_node *pos; + unsigned bucket; + + bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS); + hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) { + if (abe->mapping == mapping) + return; + } + + abe = mempool_alloc(abe_pool, GFP_KERNEL); + BUG_ON(!igrab(mapping->host)); + abe->mapping = mapping; + hlist_add_head(&abe->list, &batch_hash[bucket]); + return; +} + +static void aio_batch_free(struct hlist_head *batch_hash) +{ + struct aio_batch_entry *abe; + struct hlist_node *pos, *n; + int i; + + for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) { + hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) { + blk_run_address_space(abe->mapping); + iput(abe->mapping->host); + hlist_del(&abe->list); + mempool_free(abe, abe_pool); + } + } +} + static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, - struct iocb *iocb) + struct iocb *iocb, struct hlist_head *batch_hash) { struct kiocb *req; struct file *file; @@ -1608,6 +1658,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, ; } spin_unlock_irq(&ctx->ctx_lock); + if (req->ki_opcode == IOCB_CMD_PREAD || + req->ki_opcode == IOCB_CMD_PREADV || + req->ki_opcode == IOCB_CMD_PWRITE || + req->ki_opcode == IOCB_CMD_PWRITEV) + aio_batch_add(file->f_mapping, batch_hash); + aio_put_req(req); /* drop extra ref to req */ return 0; @@ -1635,6 +1691,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, struct kioctx *ctx; long ret = 0; int i; + struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, }; if (unlikely(nr < 0)) return -EINVAL; @@ -1666,10 +1723,11 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, break; } - ret = io_submit_one(ctx, user_iocb, &tmp); + ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash); if (ret) break; } + aio_batch_free(batch_hash); put_ioctx(ctx); return i ? i : ret; diff --git a/fs/bio.c b/fs/bio.c index 12da5db8682c..e23a63f4f7de 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1393,6 +1393,18 @@ void bio_check_pages_dirty(struct bio *bio) } } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +void bio_flush_dcache_pages(struct bio *bi) +{ + int i; + struct bio_vec *bvec; + + bio_for_each_segment(bvec, bi, i) + flush_dcache_page(bvec->bv_page); +} +EXPORT_SYMBOL(bio_flush_dcache_pages); +#endif + /** * bio_endio - end I/O on a bio * @bio: bio diff --git a/fs/block_dev.c b/fs/block_dev.c index 8bed0557d88c..73d6a735b8f3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -405,7 +405,17 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin) static int block_fsync(struct file *filp, struct dentry *dentry, int datasync) { - return sync_blockdev(I_BDEV(filp->f_mapping->host)); + struct block_device *bdev = I_BDEV(filp->f_mapping->host); + int error; + + error = sync_blockdev(bdev); + if (error) + return error; + + error = blkdev_issue_flush(bdev, NULL); + if (error == -EOPNOTSUPP) + error = 0; + return error; } /* diff --git a/fs/direct-io.c b/fs/direct-io.c index 8b10b87dc01a..b912270942fa 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1028,9 +1028,6 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode, if (dio->bio) dio_bio_submit(dio); - /* All IO is now issued, send it on its way */ - blk_run_address_space(inode->i_mapping); - /* * It is possible that, we return short IO due to end of file. * In that case, we need to release all the pages we got hold on. @@ -1057,8 +1054,11 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode, ((rw & READ) || (dio->result == dio->size))) ret = -EIOCBQUEUED; - if (ret != -EIOCBQUEUED) + if (ret != -EIOCBQUEUED) { + /* All IO is now issued, send it on its way */ + blk_run_address_space(inode->i_mapping); dio_await_completion(dio); + } /* * Sync will always be dropping the final ref and completing the @@ -1124,7 +1124,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, int acquire_i_mutex = 0; if (rw & WRITE) - rw = WRITE_ODIRECT; + rw = WRITE_ODIRECT_PLUG; if (bdev) bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev)); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 9d5360c4c2af..49bc1b8e8f19 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -614,7 +614,6 @@ static void writeback_inodes_wb(struct bdi_writeback *wb, struct writeback_control *wbc) { struct super_block *sb = wbc->sb, *pin_sb = NULL; - const int is_blkdev_sb = sb_is_blkdev_sb(sb); const unsigned long start = jiffies; /* livelock avoidance */ spin_lock(&inode_lock); @@ -635,36 +634,11 @@ static void writeback_inodes_wb(struct bdi_writeback *wb, continue; } - if (!bdi_cap_writeback_dirty(wb->bdi)) { - redirty_tail(inode); - if (is_blkdev_sb) { - /* - * Dirty memory-backed blockdev: the ramdisk - * driver does this. Skip just this inode - */ - continue; - } - /* - * Dirty memory-backed inode against a filesystem other - * than the kernel-internal bdev filesystem. Skip the - * entire superblock. - */ - break; - } - if (inode->i_state & (I_NEW | I_WILL_FREE)) { requeue_io(inode); continue; } - if (wbc->nonblocking && bdi_write_congested(wb->bdi)) { - wbc->encountered_congestion = 1; - if (!is_blkdev_sb) - break; /* Skip a congested fs */ - requeue_io(inode); - continue; /* Skip a congested blockdev */ - } - /* * Was this inode dirtied after sync_sb_inodes was called? * This keeps sync from extra jobs and livelock. @@ -756,6 +730,7 @@ static long wb_writeback(struct bdi_writeback *wb, .sync_mode = args->sync_mode, .older_than_this = NULL, .for_kupdate = args->for_kupdate, + .for_background = args->for_background, .range_cyclic = args->range_cyclic, }; unsigned long oldest_jif; @@ -787,7 +762,6 @@ static long wb_writeback(struct bdi_writeback *wb, break; wbc.more_io = 0; - wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; writeback_inodes_wb(wb, &wbc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 53eb26c16b50..c84b5cc1a943 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -178,7 +178,7 @@ static int wb_priority(struct writeback_control *wbc) { if (wbc->for_reclaim) return FLUSH_HIGHPRI | FLUSH_STABLE; - if (wbc->for_kupdate) + if (wbc->for_kupdate || wbc->for_background) return FLUSH_LOWPRI; return 0; } diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 7b685e10cbad..64bc8998ac9a 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -226,6 +226,13 @@ ssize_t part_alignment_offset_show(struct device *dev, return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset); } +ssize_t part_discard_alignment_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + return sprintf(buf, "%u\n", p->discard_alignment); +} + ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -288,6 +295,8 @@ static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL); static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); +static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show, + NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -300,6 +309,7 @@ static struct attribute *part_attrs[] = { &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, + &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -403,6 +413,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, p->start_sect = start; p->alignment_offset = queue_sector_alignment_offset(disk->queue, start); + p->discard_alignment = queue_sector_discard_alignment(disk->queue, + start); p->nr_sects = len; p->partno = partno; p->policy = get_disk_ro(disk); diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c index 038a6022152f..49cfd5f54238 100644 --- a/fs/partitions/efi.c +++ b/fs/partitions/efi.c @@ -1,7 +1,9 @@ /************************************************************ * EFI GUID Partition Table handling - * Per Intel EFI Specification v1.02 - * http://developer.intel.com/technology/efi/efi.htm + * + * http://www.uefi.org/specs/ + * http://www.intel.com/technology/efi/ + * * efi.[ch] by Matt Domsch * Copyright 2000,2001,2002,2004 Dell Inc. * @@ -92,6 +94,7 @@ * ************************************************************/ #include +#include #include "check.h" #include "efi.h" @@ -141,7 +144,8 @@ last_lba(struct block_device *bdev) { if (!bdev || !bdev->bd_inode) return 0; - return (bdev->bd_inode->i_size >> 9) - 1ULL; + return div_u64(bdev->bd_inode->i_size, + bdev_logical_block_size(bdev)) - 1ULL; } static inline int @@ -188,6 +192,7 @@ static size_t read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count) { size_t totalreadcount = 0; + sector_t n = lba * (bdev_logical_block_size(bdev) / 512); if (!bdev || !buffer || lba > last_lba(bdev)) return 0; @@ -195,7 +200,7 @@ read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count) while (count) { int copied = 512; Sector sect; - unsigned char *data = read_dev_sector(bdev, lba++, §); + unsigned char *data = read_dev_sector(bdev, n++, §); if (!data) break; if (copied > count) @@ -257,15 +262,16 @@ static gpt_header * alloc_read_gpt_header(struct block_device *bdev, u64 lba) { gpt_header *gpt; + unsigned ssz = bdev_logical_block_size(bdev); + if (!bdev) return NULL; - gpt = kzalloc(sizeof (gpt_header), GFP_KERNEL); + gpt = kzalloc(ssz, GFP_KERNEL); if (!gpt) return NULL; - if (read_lba(bdev, lba, (u8 *) gpt, - sizeof (gpt_header)) < sizeof (gpt_header)) { + if (read_lba(bdev, lba, (u8 *) gpt, ssz) < ssz) { kfree(gpt); gpt=NULL; return NULL; @@ -601,6 +607,7 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev) gpt_header *gpt = NULL; gpt_entry *ptes = NULL; u32 i; + unsigned ssz = bdev_logical_block_size(bdev) / 512; if (!find_valid_gpt(bdev, &gpt, &ptes) || !gpt || !ptes) { kfree(gpt); @@ -611,13 +618,14 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev) pr_debug("GUID Partition Table is valid! Yea!\n"); for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) { + u64 start = le64_to_cpu(ptes[i].starting_lba); + u64 size = le64_to_cpu(ptes[i].ending_lba) - + le64_to_cpu(ptes[i].starting_lba) + 1ULL; + if (!is_pte_valid(&ptes[i], last_lba(bdev))) continue; - put_partition(state, i+1, le64_to_cpu(ptes[i].starting_lba), - (le64_to_cpu(ptes[i].ending_lba) - - le64_to_cpu(ptes[i].starting_lba) + - 1ULL)); + put_partition(state, i+1, start * ssz, size * ssz); /* If this is a RAID volume, tell md */ if (!efi_guidcmp(ptes[i].partition_type_guid, diff --git a/fs/partitions/efi.h b/fs/partitions/efi.h index 2cc89d0475bf..6998b589abf9 100644 --- a/fs/partitions/efi.h +++ b/fs/partitions/efi.h @@ -37,7 +37,6 @@ #define EFI_PMBR_OSTYPE_EFI 0xEF #define EFI_PMBR_OSTYPE_EFI_GPT 0xEE -#define GPT_BLOCK_SIZE 512 #define GPT_HEADER_SIGNATURE 0x5452415020494645ULL #define GPT_HEADER_REVISION_V1 0x00010000 #define GPT_PRIMARY_PARTITION_TABLE_LBA 1 @@ -79,7 +78,12 @@ typedef struct _gpt_header { __le32 num_partition_entries; __le32 sizeof_partition_entry; __le32 partition_entry_array_crc32; - u8 reserved2[GPT_BLOCK_SIZE - 92]; + + /* The rest of the logical block is reserved by UEFI and must be zero. + * EFI standard handles this by: + * + * uint8_t reserved2[ BlockSize - 92 ]; + */ } __attribute__ ((packed)) gpt_header; typedef struct _gpt_entry_attributes { diff --git a/fs/read_write.c b/fs/read_write.c index 3ac28987f22a..b7f4a1f94d48 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -826,8 +826,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!(out_file->f_mode & FMODE_WRITE)) goto fput_out; retval = -EINVAL; - if (!out_file->f_op || !out_file->f_op->sendpage) - goto fput_out; in_inode = in_file->f_path.dentry->d_inode; out_inode = out_file->f_path.dentry->d_inode; retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count); diff --git a/fs/splice.c b/fs/splice.c index 7394e9e17534..39208663aaf1 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -648,9 +648,11 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, ret = buf->ops->confirm(pipe, buf); if (!ret) { more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len; - - ret = file->f_op->sendpage(file, buf->page, buf->offset, - sd->len, &pos, more); + if (file->f_op && file->f_op->sendpage) + ret = file->f_op->sendpage(file, buf->page, buf->offset, + sd->len, &pos, more); + else + ret = -EINVAL; } return ret; @@ -1068,8 +1070,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, if (unlikely(ret < 0)) return ret; - splice_write = out->f_op->splice_write; - if (!splice_write) + if (out->f_op && out->f_op->splice_write) + splice_write = out->f_op->splice_write; + else splice_write = default_file_splice_write; return splice_write(pipe, out, ppos, len, flags); @@ -1093,8 +1096,9 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; - splice_read = in->f_op->splice_read; - if (!splice_read) + if (in->f_op && in->f_op->splice_read) + splice_read = in->f_op->splice_read; + else splice_read = default_file_splice_read; return splice_read(in, ppos, pipe, len, flags); @@ -1316,7 +1320,8 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (off_in) return -ESPIPE; if (off_out) { - if (out->f_op->llseek == no_llseek) + if (!out->f_op || !out->f_op->llseek || + out->f_op->llseek == no_llseek) return -EINVAL; if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; @@ -1336,7 +1341,8 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (off_out) return -ESPIPE; if (off_in) { - if (in->f_op->llseek == no_llseek) + if (!in->f_op || !in->f_op->llseek || + in->f_op->llseek == no_llseek) return -EINVAL; if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index c2e30eea74dc..70f989895d15 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -904,16 +904,9 @@ xfs_convert_page( if (startio) { if (count) { - struct backing_dev_info *bdi; - - bdi = inode->i_mapping->backing_dev_info; wbc->nr_to_write--; - if (bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; + if (wbc->nr_to_write <= 0) done = 1; - } else if (wbc->nr_to_write <= 0) { - done = 1; - } } xfs_start_page_writeback(page, !page_dirty, count); } diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index ba4ec39a1131..57b5c3c82e86 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -13,6 +13,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index b449e738533a..fcbc26af00e4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -331,4 +331,17 @@ static inline int bdi_sched_wait(void *word) return 0; } +static inline void blk_run_backing_dev(struct backing_dev_info *bdi, + struct page *page) +{ + if (bdi && bdi->unplug_io_fn) + bdi->unplug_io_fn(bdi, page); +} + +static inline void blk_run_address_space(struct address_space *mapping) +{ + if (mapping) + blk_run_backing_dev(mapping->backing_dev_info, NULL); +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/bio.h b/include/linux/bio.h index 5be93f18d842..7fc5606e6ea5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -391,6 +391,18 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, gfp_t, int); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); + +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void bio_flush_dcache_pages(struct bio *bi); +#else +static inline void bio_flush_dcache_pages(struct bio *bi) +{ +} +#endif + extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, @@ -450,11 +462,8 @@ extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly; /* * remember never ever reenable interrupts between a bvec_kmap_irq and * bvec_kunmap_irq! - * - * This function MUST be inlined - it plays with the CPU interrupt flags. */ -static __always_inline char *bvec_kmap_irq(struct bio_vec *bvec, - unsigned long *flags) +static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { unsigned long addr; @@ -470,8 +479,7 @@ static __always_inline char *bvec_kmap_irq(struct bio_vec *bvec, return (char *) addr + bvec->bv_offset; } -static __always_inline void bvec_kunmap_irq(char *buffer, - unsigned long *flags) +static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 221cecd86bd3..784a919aa0d0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -312,13 +312,17 @@ struct queue_limits { unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; + unsigned int discard_granularity; + unsigned int discard_alignment; unsigned short logical_block_size; unsigned short max_hw_segments; unsigned short max_phys_segments; unsigned char misaligned; + unsigned char discard_misaligned; unsigned char no_cluster; + signed char discard_zeroes_data; }; struct request_queue @@ -749,6 +753,17 @@ struct req_iterator { #define rq_iter_last(rq, _iter) \ (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void rq_flush_dcache_pages(struct request *rq); +#else +static inline void rq_flush_dcache_pages(struct request *rq) +{ +} +#endif + extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern void register_disk(struct gendisk *dev); @@ -823,19 +838,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_disk->queue; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) -{ - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); -} - -static inline void blk_run_address_space(struct address_space *mapping) -{ - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -} - /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request @@ -1134,6 +1136,34 @@ static inline int bdev_alignment_offset(struct block_device *bdev) return q->limits.alignment_offset; } +static inline int queue_discard_alignment(struct request_queue *q) +{ + if (q->limits.discard_misaligned) + return -1; + + return q->limits.discard_alignment; +} + +static inline int queue_sector_discard_alignment(struct request_queue *q, + sector_t sector) +{ + return ((sector << 9) - q->limits.discard_alignment) + & (q->limits.discard_granularity - 1); +} + +static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) +{ + if (q->limits.discard_zeroes_data == 1) + return 1; + + return 0; +} + +static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) +{ + return queue_discard_zeroes_data(bdev_get_queue(bdev)); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 9c8d31bacf46..ccefff02b6cb 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -60,3 +60,9 @@ SUBSYS(net_cls) #endif /* */ + +#ifdef CONFIG_BLK_CGROUP +SUBSYS(blkio) +#endif + +/* */ diff --git a/include/linux/connector.h b/include/linux/connector.h index 3a14615fd35c..72ba63eb83c5 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -43,6 +43,8 @@ #define CN_DST_VAL 0x1 #define CN_IDX_DM 0x7 /* Device Mapper */ #define CN_VAL_DM_USERSPACE_LOG 0x1 +#define CN_IDX_DRBD 0x8 +#define CN_VAL_DRBD 0x1 #define CN_NETLINK_USERS 8 diff --git a/include/linux/drbd.h b/include/linux/drbd.h new file mode 100644 index 000000000000..e84f4733cb55 --- /dev/null +++ b/include/linux/drbd.h @@ -0,0 +1,343 @@ +/* + drbd.h + Kernel module for 2.6.x Kernels + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2001-2008, Philipp Reisner . + Copyright (C) 2001-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + +*/ +#ifndef DRBD_H +#define DRBD_H +#include +#include + +#ifdef __KERNEL__ +#include +#include +#else +#include +#include +#include + +/* Altough the Linux source code makes a difference between + generic endianness and the bitfields' endianness, there is no + architecture as of Linux-2.6.24-rc4 where the bitfileds' endianness + does not match the generic endianness. */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define __LITTLE_ENDIAN_BITFIELD +#elif __BYTE_ORDER == __BIG_ENDIAN +#define __BIG_ENDIAN_BITFIELD +#else +# error "sorry, weird endianness on this box" +#endif + +#endif + + +extern const char *drbd_buildtag(void); +#define REL_VERSION "8.3.6" +#define API_VERSION 88 +#define PRO_VERSION_MIN 86 +#define PRO_VERSION_MAX 91 + + +enum drbd_io_error_p { + EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ + EP_CALL_HELPER, + EP_DETACH +}; + +enum drbd_fencing_p { + FP_DONT_CARE, + FP_RESOURCE, + FP_STONITH +}; + +enum drbd_disconnect_p { + DP_RECONNECT, + DP_DROP_NET_CONF, + DP_FREEZE_IO +}; + +enum drbd_after_sb_p { + ASB_DISCONNECT, + ASB_DISCARD_YOUNGER_PRI, + ASB_DISCARD_OLDER_PRI, + ASB_DISCARD_ZERO_CHG, + ASB_DISCARD_LEAST_CHG, + ASB_DISCARD_LOCAL, + ASB_DISCARD_REMOTE, + ASB_CONSENSUS, + ASB_DISCARD_SECONDARY, + ASB_CALL_HELPER, + ASB_VIOLENTLY +}; + +/* KEEP the order, do not delete or insert. Only append. */ +enum drbd_ret_codes { + ERR_CODE_BASE = 100, + NO_ERROR = 101, + ERR_LOCAL_ADDR = 102, + ERR_PEER_ADDR = 103, + ERR_OPEN_DISK = 104, + ERR_OPEN_MD_DISK = 105, + ERR_DISK_NOT_BDEV = 107, + ERR_MD_NOT_BDEV = 108, + ERR_DISK_TO_SMALL = 111, + ERR_MD_DISK_TO_SMALL = 112, + ERR_BDCLAIM_DISK = 114, + ERR_BDCLAIM_MD_DISK = 115, + ERR_MD_IDX_INVALID = 116, + ERR_IO_MD_DISK = 118, + ERR_MD_INVALID = 119, + ERR_AUTH_ALG = 120, + ERR_AUTH_ALG_ND = 121, + ERR_NOMEM = 122, + ERR_DISCARD = 123, + ERR_DISK_CONFIGURED = 124, + ERR_NET_CONFIGURED = 125, + ERR_MANDATORY_TAG = 126, + ERR_MINOR_INVALID = 127, + ERR_INTR = 129, /* EINTR */ + ERR_RESIZE_RESYNC = 130, + ERR_NO_PRIMARY = 131, + ERR_SYNC_AFTER = 132, + ERR_SYNC_AFTER_CYCLE = 133, + ERR_PAUSE_IS_SET = 134, + ERR_PAUSE_IS_CLEAR = 135, + ERR_PACKET_NR = 137, + ERR_NO_DISK = 138, + ERR_NOT_PROTO_C = 139, + ERR_NOMEM_BITMAP = 140, + ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */ + ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */ + ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */ + ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */ + ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */ + ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */ + ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */ + ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */ + ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */ + ERR_DATA_NOT_CURRENT = 150, + ERR_CONNECTED = 151, /* DRBD 8.3 only */ + ERR_PERM = 152, + + /* insert new ones above this line */ + AFTER_LAST_ERR_CODE +}; + +#define DRBD_PROT_A 1 +#define DRBD_PROT_B 2 +#define DRBD_PROT_C 3 + +enum drbd_role { + R_UNKNOWN = 0, + R_PRIMARY = 1, /* role */ + R_SECONDARY = 2, /* role */ + R_MASK = 3, +}; + +/* The order of these constants is important. + * The lower ones (=C_WF_REPORT_PARAMS ==> There is a socket + */ +enum drbd_conns { + C_STANDALONE, + C_DISCONNECTING, /* Temporal state on the way to StandAlone. */ + C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */ + + /* These temporal states are all used on the way + * from >= C_CONNECTED to Unconnected. + * The 'disconnect reason' states + * I do not allow to change beween them. */ + C_TIMEOUT, + C_BROKEN_PIPE, + C_NETWORK_FAILURE, + C_PROTOCOL_ERROR, + C_TEAR_DOWN, + + C_WF_CONNECTION, + C_WF_REPORT_PARAMS, /* we have a socket */ + C_CONNECTED, /* we have introduced each other */ + C_STARTING_SYNC_S, /* starting full sync by admin request. */ + C_STARTING_SYNC_T, /* stariing full sync by admin request. */ + C_WF_BITMAP_S, + C_WF_BITMAP_T, + C_WF_SYNC_UUID, + + /* All SyncStates are tested with this comparison + * xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */ + C_SYNC_SOURCE, + C_SYNC_TARGET, + C_VERIFY_S, + C_VERIFY_T, + C_PAUSED_SYNC_S, + C_PAUSED_SYNC_T, + C_MASK = 31 +}; + +enum drbd_disk_state { + D_DISKLESS, + D_ATTACHING, /* In the process of reading the meta-data */ + D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */ + /* when >= D_FAILED it is legal to access mdev->bc */ + D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */ + D_INCONSISTENT, + D_OUTDATED, + D_UNKNOWN, /* Only used for the peer, never for myself */ + D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */ + D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */ + D_MASK = 15 +}; + +union drbd_state { +/* According to gcc's docs is the ... + * The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1). + * Determined by ABI. + * pointed out by Maxim Uvarov q + * even though we transmit as "cpu_to_be32(state)", + * the offsets of the bitfields still need to be swapped + * on different endianess. + */ + struct { +#if defined(__LITTLE_ENDIAN_BITFIELD) + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes */ + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned peer_isp:1 ; + unsigned user_isp:1 ; + unsigned _pad:11; /* 0 unused */ +#elif defined(__BIG_ENDIAN_BITFIELD) + unsigned _pad:11; /* 0 unused */ + unsigned user_isp:1 ; + unsigned peer_isp:1 ; + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ +#else +# error "this endianess is not supported" +#endif + }; + unsigned int i; +}; + +enum drbd_state_ret_codes { + SS_CW_NO_NEED = 4, + SS_CW_SUCCESS = 3, + SS_NOTHING_TO_DO = 2, + SS_SUCCESS = 1, + SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */ + SS_TWO_PRIMARIES = -1, + SS_NO_UP_TO_DATE_DISK = -2, + SS_NO_LOCAL_DISK = -4, + SS_NO_REMOTE_DISK = -5, + SS_CONNECTED_OUTDATES = -6, + SS_PRIMARY_NOP = -7, + SS_RESYNC_RUNNING = -8, + SS_ALREADY_STANDALONE = -9, + SS_CW_FAILED_BY_PEER = -10, + SS_IS_DISKLESS = -11, + SS_DEVICE_IN_USE = -12, + SS_NO_NET_CONFIG = -13, + SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */ + SS_NEED_CONNECTION = -15, /* drbd-8.2 only */ + SS_LOWER_THAN_OUTDATED = -16, + SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */ + SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ + SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ + SS_AFTER_LAST_ERROR = -20, /* Keep this at bottom */ +}; + +/* from drbd_strings.c */ +extern const char *drbd_conn_str(enum drbd_conns); +extern const char *drbd_role_str(enum drbd_role); +extern const char *drbd_disk_str(enum drbd_disk_state); +extern const char *drbd_set_st_err_str(enum drbd_state_ret_codes); + +#define SHARED_SECRET_MAX 64 + +#define MDF_CONSISTENT (1 << 0) +#define MDF_PRIMARY_IND (1 << 1) +#define MDF_CONNECTED_IND (1 << 2) +#define MDF_FULL_SYNC (1 << 3) +#define MDF_WAS_UP_TO_DATE (1 << 4) +#define MDF_PEER_OUT_DATED (1 << 5) +#define MDF_CRASHED_PRIMARY (1 << 6) + +enum drbd_uuid_index { + UI_CURRENT, + UI_BITMAP, + UI_HISTORY_START, + UI_HISTORY_END, + UI_SIZE, /* nl-packet: number of dirty bits */ + UI_FLAGS, /* nl-packet: flags */ + UI_EXTENDED_SIZE /* Everything. */ +}; + +enum drbd_timeout_flag { + UT_DEFAULT = 0, + UT_DEGRADED = 1, + UT_PEER_OUTDATED = 2, +}; + +#define UUID_JUST_CREATED ((__u64)4) + +#define DRBD_MAGIC 0x83740267 +#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC) + +/* these are of type "int" */ +#define DRBD_MD_INDEX_INTERNAL -1 +#define DRBD_MD_INDEX_FLEX_EXT -2 +#define DRBD_MD_INDEX_FLEX_INT -3 + +/* Start of the new netlink/connector stuff */ + +#define DRBD_NL_CREATE_DEVICE 0x01 +#define DRBD_NL_SET_DEFAULTS 0x02 + + +/* For searching a vacant cn_idx value */ +#define CN_IDX_STEP 6977 + +struct drbd_nl_cfg_req { + int packet_type; + unsigned int drbd_minor; + int flags; + unsigned short tag_list[]; +}; + +struct drbd_nl_cfg_reply { + int packet_type; + unsigned int minor; + int ret_code; /* enum ret_code or set_st_err_t */ + unsigned short tag_list[]; /* only used with get_* calls */ +}; + +#endif diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h new file mode 100644 index 000000000000..51f47a586ad8 --- /dev/null +++ b/include/linux/drbd_limits.h @@ -0,0 +1,137 @@ +/* + drbd_limits.h + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. +*/ + +/* + * Our current limitations. + * Some of them are hard limits, + * some of them are arbitrary range limits, that make it easier to provide + * feedback about nonsense settings for certain configurable values. + */ + +#ifndef DRBD_LIMITS_H +#define DRBD_LIMITS_H 1 + +#define DEBUG_RANGE_CHECK 0 + +#define DRBD_MINOR_COUNT_MIN 1 +#define DRBD_MINOR_COUNT_MAX 255 + +#define DRBD_DIALOG_REFRESH_MIN 0 +#define DRBD_DIALOG_REFRESH_MAX 600 + +/* valid port number */ +#define DRBD_PORT_MIN 1 +#define DRBD_PORT_MAX 0xffff + +/* startup { */ + /* if you want more than 3.4 days, disable */ +#define DRBD_WFC_TIMEOUT_MIN 0 +#define DRBD_WFC_TIMEOUT_MAX 300000 +#define DRBD_WFC_TIMEOUT_DEF 0 + +#define DRBD_DEGR_WFC_TIMEOUT_MIN 0 +#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000 +#define DRBD_DEGR_WFC_TIMEOUT_DEF 0 + +#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0 +#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000 +#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0 +/* }*/ + +/* net { */ + /* timeout, unit centi seconds + * more than one minute timeout is not usefull */ +#define DRBD_TIMEOUT_MIN 1 +#define DRBD_TIMEOUT_MAX 600 +#define DRBD_TIMEOUT_DEF 60 /* 6 seconds */ + + /* active connection retries when C_WF_CONNECTION */ +#define DRBD_CONNECT_INT_MIN 1 +#define DRBD_CONNECT_INT_MAX 120 +#define DRBD_CONNECT_INT_DEF 10 /* seconds */ + + /* keep-alive probes when idle */ +#define DRBD_PING_INT_MIN 1 +#define DRBD_PING_INT_MAX 120 +#define DRBD_PING_INT_DEF 10 + + /* timeout for the ping packets.*/ +#define DRBD_PING_TIMEO_MIN 1 +#define DRBD_PING_TIMEO_MAX 100 +#define DRBD_PING_TIMEO_DEF 5 + + /* max number of write requests between write barriers */ +#define DRBD_MAX_EPOCH_SIZE_MIN 1 +#define DRBD_MAX_EPOCH_SIZE_MAX 20000 +#define DRBD_MAX_EPOCH_SIZE_DEF 2048 + + /* I don't think that a tcp send buffer of more than 10M is usefull */ +#define DRBD_SNDBUF_SIZE_MIN 0 +#define DRBD_SNDBUF_SIZE_MAX (10<<20) +#define DRBD_SNDBUF_SIZE_DEF 0 + +#define DRBD_RCVBUF_SIZE_MIN 0 +#define DRBD_RCVBUF_SIZE_MAX (10<<20) +#define DRBD_RCVBUF_SIZE_DEF 0 + + /* @4k PageSize -> 128kB - 512MB */ +#define DRBD_MAX_BUFFERS_MIN 32 +#define DRBD_MAX_BUFFERS_MAX 131072 +#define DRBD_MAX_BUFFERS_DEF 2048 + + /* @4k PageSize -> 4kB - 512MB */ +#define DRBD_UNPLUG_WATERMARK_MIN 1 +#define DRBD_UNPLUG_WATERMARK_MAX 131072 +#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) + + /* 0 is disabled. + * 200 should be more than enough even for very short timeouts */ +#define DRBD_KO_COUNT_MIN 0 +#define DRBD_KO_COUNT_MAX 200 +#define DRBD_KO_COUNT_DEF 0 +/* } */ + +/* syncer { */ + /* FIXME allow rate to be zero? */ +#define DRBD_RATE_MIN 1 +/* channel bonding 10 GbE, or other hardware */ +#define DRBD_RATE_MAX (4 << 20) +#define DRBD_RATE_DEF 250 /* kb/second */ + + /* less than 7 would hit performance unneccessarily. + * 3833 is the largest prime that still does fit + * into 64 sectors of activity log */ +#define DRBD_AL_EXTENTS_MIN 7 +#define DRBD_AL_EXTENTS_MAX 3833 +#define DRBD_AL_EXTENTS_DEF 127 + +#define DRBD_AFTER_MIN -1 +#define DRBD_AFTER_MAX 255 +#define DRBD_AFTER_DEF -1 + +/* } */ + +/* drbdsetup XY resize -d Z + * you are free to reduce the device size to nothing, if you want to. + * the upper limit with 64bit kernel, enough ram and flexible meta data + * is 16 TB, currently. */ +/* DRBD_MAX_SECTORS */ +#define DRBD_DISK_SIZE_SECT_MIN 0 +#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30)) +#define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */ + +#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON +#define DRBD_FENCING_DEF FP_DONT_CARE +#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT +#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT + +#define DRBD_MAX_BIO_BVECS_MIN 0 +#define DRBD_MAX_BIO_BVECS_MAX 128 +#define DRBD_MAX_BIO_BVECS_DEF 0 + +#undef RANGE +#endif diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h new file mode 100644 index 000000000000..db5721ad50d1 --- /dev/null +++ b/include/linux/drbd_nl.h @@ -0,0 +1,137 @@ +/* + PAKET( name, + TYPE ( pn, pr, member ) + ... + ) + + You may never reissue one of the pn arguments +*/ + +#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64) +#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined" +#endif + +NL_PACKET(primary, 1, + NL_BIT( 1, T_MAY_IGNORE, overwrite_peer) +) + +NL_PACKET(secondary, 2, ) + +NL_PACKET(disk_conf, 3, + NL_INT64( 2, T_MAY_IGNORE, disk_size) + NL_STRING( 3, T_MANDATORY, backing_dev, 128) + NL_STRING( 4, T_MANDATORY, meta_dev, 128) + NL_INTEGER( 5, T_MANDATORY, meta_dev_idx) + NL_INTEGER( 6, T_MAY_IGNORE, on_io_error) + NL_INTEGER( 7, T_MAY_IGNORE, fencing) + NL_BIT( 37, T_MAY_IGNORE, use_bmbv) + NL_BIT( 53, T_MAY_IGNORE, no_disk_flush) + NL_BIT( 54, T_MAY_IGNORE, no_md_flush) + /* 55 max_bio_size was available in 8.2.6rc2 */ + NL_INTEGER( 56, T_MAY_IGNORE, max_bio_bvecs) + NL_BIT( 57, T_MAY_IGNORE, no_disk_barrier) + NL_BIT( 58, T_MAY_IGNORE, no_disk_drain) +) + +NL_PACKET(detach, 4, ) + +NL_PACKET(net_conf, 5, + NL_STRING( 8, T_MANDATORY, my_addr, 128) + NL_STRING( 9, T_MANDATORY, peer_addr, 128) + NL_STRING( 10, T_MAY_IGNORE, shared_secret, SHARED_SECRET_MAX) + NL_STRING( 11, T_MAY_IGNORE, cram_hmac_alg, SHARED_SECRET_MAX) + NL_STRING( 44, T_MAY_IGNORE, integrity_alg, SHARED_SECRET_MAX) + NL_INTEGER( 14, T_MAY_IGNORE, timeout) + NL_INTEGER( 15, T_MANDATORY, wire_protocol) + NL_INTEGER( 16, T_MAY_IGNORE, try_connect_int) + NL_INTEGER( 17, T_MAY_IGNORE, ping_int) + NL_INTEGER( 18, T_MAY_IGNORE, max_epoch_size) + NL_INTEGER( 19, T_MAY_IGNORE, max_buffers) + NL_INTEGER( 20, T_MAY_IGNORE, unplug_watermark) + NL_INTEGER( 21, T_MAY_IGNORE, sndbuf_size) + NL_INTEGER( 22, T_MAY_IGNORE, ko_count) + NL_INTEGER( 24, T_MAY_IGNORE, after_sb_0p) + NL_INTEGER( 25, T_MAY_IGNORE, after_sb_1p) + NL_INTEGER( 26, T_MAY_IGNORE, after_sb_2p) + NL_INTEGER( 39, T_MAY_IGNORE, rr_conflict) + NL_INTEGER( 40, T_MAY_IGNORE, ping_timeo) + NL_INTEGER( 67, T_MAY_IGNORE, rcvbuf_size) + /* 59 addr_family was available in GIT, never released */ + NL_BIT( 60, T_MANDATORY, mind_af) + NL_BIT( 27, T_MAY_IGNORE, want_lose) + NL_BIT( 28, T_MAY_IGNORE, two_primaries) + NL_BIT( 41, T_MAY_IGNORE, always_asbp) + NL_BIT( 61, T_MAY_IGNORE, no_cork) + NL_BIT( 62, T_MANDATORY, auto_sndbuf_size) +) + +NL_PACKET(disconnect, 6, ) + +NL_PACKET(resize, 7, + NL_INT64( 29, T_MAY_IGNORE, resize_size) +) + +NL_PACKET(syncer_conf, 8, + NL_INTEGER( 30, T_MAY_IGNORE, rate) + NL_INTEGER( 31, T_MAY_IGNORE, after) + NL_INTEGER( 32, T_MAY_IGNORE, al_extents) + NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX) + NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32) + NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX) + NL_BIT( 65, T_MAY_IGNORE, use_rle) +) + +NL_PACKET(invalidate, 9, ) +NL_PACKET(invalidate_peer, 10, ) +NL_PACKET(pause_sync, 11, ) +NL_PACKET(resume_sync, 12, ) +NL_PACKET(suspend_io, 13, ) +NL_PACKET(resume_io, 14, ) +NL_PACKET(outdate, 15, ) +NL_PACKET(get_config, 16, ) +NL_PACKET(get_state, 17, + NL_INTEGER( 33, T_MAY_IGNORE, state_i) +) + +NL_PACKET(get_uuids, 18, + NL_STRING( 34, T_MAY_IGNORE, uuids, (UI_SIZE*sizeof(__u64))) + NL_INTEGER( 35, T_MAY_IGNORE, uuids_flags) +) + +NL_PACKET(get_timeout_flag, 19, + NL_BIT( 36, T_MAY_IGNORE, use_degraded) +) + +NL_PACKET(call_helper, 20, + NL_STRING( 38, T_MAY_IGNORE, helper, 32) +) + +/* Tag nr 42 already allocated in drbd-8.1 development. */ + +NL_PACKET(sync_progress, 23, + NL_INTEGER( 43, T_MAY_IGNORE, sync_progress) +) + +NL_PACKET(dump_ee, 24, + NL_STRING( 45, T_MAY_IGNORE, dump_ee_reason, 32) + NL_STRING( 46, T_MAY_IGNORE, seen_digest, SHARED_SECRET_MAX) + NL_STRING( 47, T_MAY_IGNORE, calc_digest, SHARED_SECRET_MAX) + NL_INT64( 48, T_MAY_IGNORE, ee_sector) + NL_INT64( 49, T_MAY_IGNORE, ee_block_id) + NL_STRING( 50, T_MAY_IGNORE, ee_data, 32 << 10) +) + +NL_PACKET(start_ov, 25, + NL_INT64( 66, T_MAY_IGNORE, start_sector) +) + +NL_PACKET(new_c_uuid, 26, + NL_BIT( 63, T_MANDATORY, clear_bm) +) + +#undef NL_PACKET +#undef NL_INTEGER +#undef NL_INT64 +#undef NL_BIT +#undef NL_STRING + diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h new file mode 100644 index 000000000000..fcdff8410e99 --- /dev/null +++ b/include/linux/drbd_tag_magic.h @@ -0,0 +1,83 @@ +#ifndef DRBD_TAG_MAGIC_H +#define DRBD_TAG_MAGIC_H + +#define TT_END 0 +#define TT_REMOVED 0xE000 + +/* declare packet_type enums */ +enum packet_types { +#define NL_PACKET(name, number, fields) P_ ## name = number, +#define NL_INTEGER(pn, pr, member) +#define NL_INT64(pn, pr, member) +#define NL_BIT(pn, pr, member) +#define NL_STRING(pn, pr, member, len) +#include "drbd_nl.h" + P_nl_after_last_packet, +}; + +/* These struct are used to deduce the size of the tag lists: */ +#define NL_PACKET(name, number, fields) \ + struct name ## _tag_len_struct { fields }; +#define NL_INTEGER(pn, pr, member) \ + int member; int tag_and_len ## member; +#define NL_INT64(pn, pr, member) \ + __u64 member; int tag_and_len ## member; +#define NL_BIT(pn, pr, member) \ + unsigned char member:1; int tag_and_len ## member; +#define NL_STRING(pn, pr, member, len) \ + unsigned char member[len]; int member ## _len; \ + int tag_and_len ## member; +#include "linux/drbd_nl.h" + +/* declate tag-list-sizes */ +static const int tag_list_sizes[] = { +#define NL_PACKET(name, number, fields) 2 fields , +#define NL_INTEGER(pn, pr, member) + 4 + 4 +#define NL_INT64(pn, pr, member) + 4 + 8 +#define NL_BIT(pn, pr, member) + 4 + 1 +#define NL_STRING(pn, pr, member, len) + 4 + (len) +#include "drbd_nl.h" +}; + +/* The two highest bits are used for the tag type */ +#define TT_MASK 0xC000 +#define TT_INTEGER 0x0000 +#define TT_INT64 0x4000 +#define TT_BIT 0x8000 +#define TT_STRING 0xC000 +/* The next bit indicates if processing of the tag is mandatory */ +#define T_MANDATORY 0x2000 +#define T_MAY_IGNORE 0x0000 +#define TN_MASK 0x1fff +/* The remaining 13 bits are used to enumerate the tags */ + +#define tag_type(T) ((T) & TT_MASK) +#define tag_number(T) ((T) & TN_MASK) + +/* declare tag enums */ +#define NL_PACKET(name, number, fields) fields +enum drbd_tags { +#define NL_INTEGER(pn, pr, member) T_ ## member = pn | TT_INTEGER | pr , +#define NL_INT64(pn, pr, member) T_ ## member = pn | TT_INT64 | pr , +#define NL_BIT(pn, pr, member) T_ ## member = pn | TT_BIT | pr , +#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING | pr , +#include "drbd_nl.h" +}; + +struct tag { + const char *name; + int type_n_flags; + int max_len; +}; + +/* declare tag names */ +#define NL_PACKET(name, number, fields) fields +static const struct tag tag_descriptions[] = { +#define NL_INTEGER(pn, pr, member) [ pn ] = { #member, TT_INTEGER | pr, sizeof(int) }, +#define NL_INT64(pn, pr, member) [ pn ] = { #member, TT_INT64 | pr, sizeof(__u64) }, +#define NL_BIT(pn, pr, member) [ pn ] = { #member, TT_BIT | pr, sizeof(int) }, +#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING | pr, (len) }, +#include "drbd_nl.h" +}; + +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 2620a8c63571..891f7d642e5c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -129,7 +129,7 @@ struct inodes_stat_t { * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device * immediately after submission. The write equivalent * of READ_SYNC. - * WRITE_ODIRECT Special case write for O_DIRECT only. + * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. * SWRITE_SYNC * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. * See SWRITE. @@ -151,7 +151,7 @@ struct inodes_stat_t { #define READ_META (READ | (1 << BIO_RW_META)) #define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_ODIRECT (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) +#define WRITE_ODIRECT_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) #define SWRITE_SYNC_PLUG \ (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) @@ -304,6 +304,7 @@ struct inodes_stat_t { #define BLKIOOPT _IO(0x12,121) #define BLKALIGNOFF _IO(0x12,122) #define BLKPBSZGET _IO(0x12,123) +#define BLKDISCARDZEROES _IO(0x12,124) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 297df45ffd0a..c6c0c41af35f 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -91,6 +91,7 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; sector_t alignment_offset; + unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; int policy, partno; diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 4da4a75c3f1e..a63235996309 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -40,16 +40,11 @@ struct cfq_io_context { struct io_context *ioc; unsigned long last_end_request; - sector_t last_request_pos; unsigned long ttime_total; unsigned long ttime_samples; unsigned long ttime_mean; - unsigned int seek_samples; - u64 seek_total; - sector_t seek_mean; - struct list_head queue_list; struct hlist_node cic_list; @@ -73,6 +68,10 @@ struct io_context { unsigned short ioprio; unsigned short ioprio_changed; +#ifdef CONFIG_BLK_CGROUP + unsigned short cgroup_changed; +#endif + /* * For request batching */ @@ -99,14 +98,15 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc) return NULL; } +struct task_struct; #ifdef CONFIG_BLOCK int put_io_context(struct io_context *ioc); -void exit_io_context(void); +void exit_io_context(struct task_struct *task); struct io_context *get_io_context(gfp_t gfp_flags, int node); struct io_context *alloc_io_context(gfp_t gfp_flags, int node); void copy_io_context(struct io_context **pdst, struct io_context **psrc); #else -static inline void exit_io_context(void) +static inline void exit_io_context(struct task_struct *task) { } diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h new file mode 100644 index 000000000000..3a2b2d9b0472 --- /dev/null +++ b/include/linux/lru_cache.h @@ -0,0 +1,294 @@ +/* + lru_cache.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2003-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2003-2008, Philipp Reisner . + Copyright (C) 2003-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#ifndef LRU_CACHE_H +#define LRU_CACHE_H + +#include +#include +#include +#include /* for memset */ +#include + +/* +This header file (and its .c file; kernel-doc of functions see there) + define a helper framework to easily keep track of index:label associations, + and changes to an "active set" of objects, as well as pending transactions, + to persistently record those changes. + + We use an LRU policy if it is necessary to "cool down" a region currently in + the active set before we can "heat" a previously unused region. + + Because of this later property, it is called "lru_cache". + As it actually Tracks Objects in an Active SeT, we could also call it + toast (incidentally that is what may happen to the data on the + backend storage uppon next resync, if we don't get it right). + +What for? + +We replicate IO (more or less synchronously) to local and remote disk. + +For crash recovery after replication node failure, + we need to resync all regions that have been target of in-flight WRITE IO + (in use, or "hot", regions), as we don't know wether or not those WRITEs have + made it to stable storage. + + To avoid a "full resync", we need to persistently track these regions. + + This is known as "write intent log", and can be implemented as on-disk + (coarse or fine grained) bitmap, or other meta data. + + To avoid the overhead of frequent extra writes to this meta data area, + usually the condition is softened to regions that _may_ have been target of + in-flight WRITE IO, e.g. by only lazily clearing the on-disk write-intent + bitmap, trading frequency of meta data transactions against amount of + (possibly unneccessary) resync traffic. + + If we set a hard limit on the area that may be "hot" at any given time, we + limit the amount of resync traffic needed for crash recovery. + +For recovery after replication link failure, + we need to resync all blocks that have been changed on the other replica + in the mean time, or, if both replica have been changed independently [*], + all blocks that have been changed on either replica in the mean time. + [*] usually as a result of a cluster split-brain and insufficient protection. + but there are valid use cases to do this on purpose. + + Tracking those blocks can be implemented as "dirty bitmap". + Having it fine-grained reduces the amount of resync traffic. + It should also be persistent, to allow for reboots (or crashes) + while the replication link is down. + +There are various possible implementations for persistently storing +write intent log information, three of which are mentioned here. + +"Chunk dirtying" + The on-disk "dirty bitmap" may be re-used as "write-intent" bitmap as well. + To reduce the frequency of bitmap updates for write-intent log purposes, + one could dirty "chunks" (of some size) at a time of the (fine grained) + on-disk bitmap, while keeping the in-memory "dirty" bitmap as clean as + possible, flushing it to disk again when a previously "hot" (and on-disk + dirtied as full chunk) area "cools down" again (no IO in flight anymore, + and none expected in the near future either). + +"Explicit (coarse) write intent bitmap" + An other implementation could chose a (probably coarse) explicit bitmap, + for write-intent log purposes, additionally to the fine grained dirty bitmap. + +"Activity log" + Yet an other implementation may keep track of the hot regions, by starting + with an empty set, and writing down a journal of region numbers that have + become "hot", or have "cooled down" again. + + To be able to use a ring buffer for this journal of changes to the active + set, we not only record the actual changes to that set, but also record the + not changing members of the set in a round robin fashion. To do so, we use a + fixed (but configurable) number of slots which we can identify by index, and + associate region numbers (labels) with these indices. + For each transaction recording a change to the active set, we record the + change itself (index: -old_label, +new_label), and which index is associated + with which label (index: current_label) within a certain sliding window that + is moved further over the available indices with each such transaction. + + Thus, for crash recovery, if the ringbuffer is sufficiently large, we can + accurately reconstruct the active set. + + Sufficiently large depends only on maximum number of active objects, and the + size of the sliding window recording "index: current_label" associations within + each transaction. + + This is what we call the "activity log". + + Currently we need one activity log transaction per single label change, which + does not give much benefit over the "dirty chunks of bitmap" approach, other + than potentially less seeks. + + We plan to change the transaction format to support multiple changes per + transaction, which then would reduce several (disjoint, "random") updates to + the bitmap into one transaction to the activity log ring buffer. +*/ + +/* this defines an element in a tracked set + * .colision is for hash table lookup. + * When we process a new IO request, we know its sector, thus can deduce the + * region number (label) easily. To do the label -> object lookup without a + * full list walk, we use a simple hash table. + * + * .list is on one of three lists: + * in_use: currently in use (refcnt > 0, lc_number != LC_FREE) + * lru: unused but ready to be reused or recycled + * (ts_refcnt == 0, lc_number != LC_FREE), + * free: unused but ready to be recycled + * (ts_refcnt == 0, lc_number == LC_FREE), + * + * an element is said to be "in the active set", + * if either on "in_use" or "lru", i.e. lc_number != LC_FREE. + * + * DRBD currently (May 2009) only uses 61 elements on the resync lru_cache + * (total memory usage 2 pages), and up to 3833 elements on the act_log + * lru_cache, totalling ~215 kB for 64bit architechture, ~53 pages. + * + * We usually do not actually free these objects again, but only "recycle" + * them, as the change "index: -old_label, +LC_FREE" would need a transaction + * as well. Which also means that using a kmem_cache to allocate the objects + * from wastes some resources. + * But it avoids high order page allocations in kmalloc. + */ +struct lc_element { + struct hlist_node colision; + struct list_head list; /* LRU list or free list */ + unsigned refcnt; + /* back "pointer" into ts_cache->element[index], + * for paranoia, and for "ts_element_to_index" */ + unsigned lc_index; + /* if we want to track a larger set of objects, + * it needs to become arch independend u64 */ + unsigned lc_number; + + /* special label when on free list */ +#define LC_FREE (~0U) +}; + +struct lru_cache { + /* the least recently used item is kept at lru->prev */ + struct list_head lru; + struct list_head free; + struct list_head in_use; + + /* the pre-created kmem cache to allocate the objects from */ + struct kmem_cache *lc_cache; + + /* size of tracked objects, used to memset(,0,) them in lc_reset */ + size_t element_size; + /* offset of struct lc_element member in the tracked object */ + size_t element_off; + + /* number of elements (indices) */ + unsigned int nr_elements; + /* Arbitrary limit on maximum tracked objects. Practical limit is much + * lower due to allocation failures, probably. For typical use cases, + * nr_elements should be a few thousand at most. + * This also limits the maximum value of ts_element.ts_index, allowing the + * 8 high bits of .ts_index to be overloaded with flags in the future. */ +#define LC_MAX_ACTIVE (1<<24) + + /* statistics */ + unsigned used; /* number of lelements currently on in_use list */ + unsigned long hits, misses, starving, dirty, changed; + + /* see below: flag-bits for lru_cache */ + unsigned long flags; + + /* when changing the label of an index element */ + unsigned int new_number; + + /* for paranoia when changing the label of an index element */ + struct lc_element *changing_element; + + void *lc_private; + const char *name; + + /* nr_elements there */ + struct hlist_head *lc_slot; + struct lc_element **lc_element; +}; + + +/* flag-bits for lru_cache */ +enum { + /* debugging aid, to catch concurrent access early. + * user needs to guarantee exclusive access by proper locking! */ + __LC_PARANOIA, + /* if we need to change the set, but currently there is a changing + * transaction pending, we are "dirty", and must deferr further + * changing requests */ + __LC_DIRTY, + /* if we need to change the set, but currently there is no free nor + * unused element available, we are "starving", and must not give out + * further references, to guarantee that eventually some refcnt will + * drop to zero and we will be able to make progress again, changing + * the set, writing the transaction. + * if the statistics say we are frequently starving, + * nr_elements is too small. */ + __LC_STARVING, +}; +#define LC_PARANOIA (1<<__LC_PARANOIA) +#define LC_DIRTY (1<<__LC_DIRTY) +#define LC_STARVING (1<<__LC_STARVING) + +extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache, + unsigned e_count, size_t e_size, size_t e_off); +extern void lc_reset(struct lru_cache *lc); +extern void lc_destroy(struct lru_cache *lc); +extern void lc_set(struct lru_cache *lc, unsigned int enr, int index); +extern void lc_del(struct lru_cache *lc, struct lc_element *element); + +extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); +extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); +extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); +extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e); +extern void lc_changed(struct lru_cache *lc, struct lc_element *e); + +struct seq_file; +extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc); + +extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext, + void (*detail) (struct seq_file *, struct lc_element *)); + +/** + * lc_try_lock - can be used to stop lc_get() from changing the tracked set + * @lc: the lru cache to operate on + * + * Note that the reference counts and order on the active and lru lists may + * still change. Returns true if we aquired the lock. + */ +static inline int lc_try_lock(struct lru_cache *lc) +{ + return !test_and_set_bit(__LC_DIRTY, &lc->flags); +} + +/** + * lc_unlock - unlock @lc, allow lc_get() to change the set again + * @lc: the lru cache to operate on + */ +static inline void lc_unlock(struct lru_cache *lc) +{ + clear_bit(__LC_DIRTY, &lc->flags); + smp_mb__after_clear_bit(); +} + +static inline int lc_is_used(struct lru_cache *lc, unsigned int enr) +{ + struct lc_element *e = lc_find(lc, enr); + return e && e->refcnt; +} + +#define lc_entry(ptr, type, member) \ + container_of(ptr, type, member) + +extern struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i); +extern unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e); + +#endif diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 66ebddcff664..705f01fe413a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -49,6 +49,7 @@ struct writeback_control { unsigned nonblocking:1; /* Don't get stuck on request queues */ unsigned encountered_congestion:1; /* An output: a queue is full */ unsigned for_kupdate:1; /* A kupdate writeback */ + unsigned for_background:1; /* A background writeback */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ diff --git a/kernel/exit.c b/kernel/exit.c index 80ae941cfd2e..1143012951e9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1009,7 +1009,7 @@ NORET_TYPE void do_exit(long code) tsk->flags |= PF_EXITPIDONE; if (tsk->io_context) - exit_io_context(); + exit_io_context(tsk); if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); diff --git a/kernel/fork.c b/kernel/fork.c index edeff9ceaab9..1415dc4598ae 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1317,7 +1317,8 @@ bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: - put_io_context(p->io_context); + if (p->io_context) + exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: diff --git a/lib/Kconfig b/lib/Kconfig index bb1326d3839c..1cfe51628e1b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -200,4 +200,7 @@ config NLATTR config GENERIC_ATOMIC64 bool +config LRU_CACHE + tristate + endmenu diff --git a/lib/Makefile b/lib/Makefile index 2e78277eff9d..347ad8db29d3 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -91,6 +91,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o obj-$(CONFIG_NLATTR) += nlattr.o +obj-$(CONFIG_LRU_CACHE) += lru_cache.o + obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o obj-$(CONFIG_GENERIC_CSUM) += checksum.o diff --git a/lib/lru_cache.c b/lib/lru_cache.c new file mode 100644 index 000000000000..270de9d31b8c --- /dev/null +++ b/lib/lru_cache.c @@ -0,0 +1,560 @@ +/* + lru_cache.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2003-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2003-2008, Philipp Reisner . + Copyright (C) 2003-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd 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 drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#include +#include +#include +#include /* for memset */ +#include /* for seq_printf */ +#include + +MODULE_AUTHOR("Philipp Reisner , " + "Lars Ellenberg "); +MODULE_DESCRIPTION("lru_cache - Track sets of hot objects"); +MODULE_LICENSE("GPL"); + +/* this is developers aid only. + * it catches concurrent access (lack of locking on the users part) */ +#define PARANOIA_ENTRY() do { \ + BUG_ON(!lc); \ + BUG_ON(!lc->nr_elements); \ + BUG_ON(test_and_set_bit(__LC_PARANOIA, &lc->flags)); \ +} while (0) + +#define RETURN(x...) do { \ + clear_bit(__LC_PARANOIA, &lc->flags); \ + smp_mb__after_clear_bit(); return x ; } while (0) + +/* BUG() if e is not one of the elements tracked by lc */ +#define PARANOIA_LC_ELEMENT(lc, e) do { \ + struct lru_cache *lc_ = (lc); \ + struct lc_element *e_ = (e); \ + unsigned i = e_->lc_index; \ + BUG_ON(i >= lc_->nr_elements); \ + BUG_ON(lc_->lc_element[i] != e_); } while (0) + +/** + * lc_create - prepares to track objects in an active set + * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details + * @e_count: number of elements allowed to be active simultaneously + * @e_size: size of the tracked objects + * @e_off: offset to the &struct lc_element member in a tracked object + * + * Returns a pointer to a newly initialized struct lru_cache on success, + * or NULL on (allocation) failure. + */ +struct lru_cache *lc_create(const char *name, struct kmem_cache *cache, + unsigned e_count, size_t e_size, size_t e_off) +{ + struct hlist_head *slot = NULL; + struct lc_element **element = NULL; + struct lru_cache *lc; + struct lc_element *e; + unsigned cache_obj_size = kmem_cache_size(cache); + unsigned i; + + WARN_ON(cache_obj_size < e_size); + if (cache_obj_size < e_size) + return NULL; + + /* e_count too big; would probably fail the allocation below anyways. + * for typical use cases, e_count should be few thousand at most. */ + if (e_count > LC_MAX_ACTIVE) + return NULL; + + slot = kzalloc(e_count * sizeof(struct hlist_head*), GFP_KERNEL); + if (!slot) + goto out_fail; + element = kzalloc(e_count * sizeof(struct lc_element *), GFP_KERNEL); + if (!element) + goto out_fail; + + lc = kzalloc(sizeof(*lc), GFP_KERNEL); + if (!lc) + goto out_fail; + + INIT_LIST_HEAD(&lc->in_use); + INIT_LIST_HEAD(&lc->lru); + INIT_LIST_HEAD(&lc->free); + + lc->name = name; + lc->element_size = e_size; + lc->element_off = e_off; + lc->nr_elements = e_count; + lc->new_number = LC_FREE; + lc->lc_cache = cache; + lc->lc_element = element; + lc->lc_slot = slot; + + /* preallocate all objects */ + for (i = 0; i < e_count; i++) { + void *p = kmem_cache_alloc(cache, GFP_KERNEL); + if (!p) + break; + memset(p, 0, lc->element_size); + e = p + e_off; + e->lc_index = i; + e->lc_number = LC_FREE; + list_add(&e->list, &lc->free); + element[i] = e; + } + if (i == e_count) + return lc; + + /* else: could not allocate all elements, give up */ + for (i--; i; i--) { + void *p = element[i]; + kmem_cache_free(cache, p - e_off); + } + kfree(lc); +out_fail: + kfree(element); + kfree(slot); + return NULL; +} + +void lc_free_by_index(struct lru_cache *lc, unsigned i) +{ + void *p = lc->lc_element[i]; + WARN_ON(!p); + if (p) { + p -= lc->element_off; + kmem_cache_free(lc->lc_cache, p); + } +} + +/** + * lc_destroy - frees memory allocated by lc_create() + * @lc: the lru cache to destroy + */ +void lc_destroy(struct lru_cache *lc) +{ + unsigned i; + if (!lc) + return; + for (i = 0; i < lc->nr_elements; i++) + lc_free_by_index(lc, i); + kfree(lc->lc_element); + kfree(lc->lc_slot); + kfree(lc); +} + +/** + * lc_reset - does a full reset for @lc and the hash table slots. + * @lc: the lru cache to operate on + * + * It is roughly the equivalent of re-allocating a fresh lru_cache object, + * basically a short cut to lc_destroy(lc); lc = lc_create(...); + */ +void lc_reset(struct lru_cache *lc) +{ + unsigned i; + + INIT_LIST_HEAD(&lc->in_use); + INIT_LIST_HEAD(&lc->lru); + INIT_LIST_HEAD(&lc->free); + lc->used = 0; + lc->hits = 0; + lc->misses = 0; + lc->starving = 0; + lc->dirty = 0; + lc->changed = 0; + lc->flags = 0; + lc->changing_element = NULL; + lc->new_number = LC_FREE; + memset(lc->lc_slot, 0, sizeof(struct hlist_head) * lc->nr_elements); + + for (i = 0; i < lc->nr_elements; i++) { + struct lc_element *e = lc->lc_element[i]; + void *p = e; + p -= lc->element_off; + memset(p, 0, lc->element_size); + /* re-init it */ + e->lc_index = i; + e->lc_number = LC_FREE; + list_add(&e->list, &lc->free); + } +} + +/** + * lc_seq_printf_stats - print stats about @lc into @seq + * @seq: the seq_file to print into + * @lc: the lru cache to print statistics of + */ +size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc) +{ + /* NOTE: + * total calls to lc_get are + * (starving + hits + misses) + * misses include "dirty" count (update from an other thread in + * progress) and "changed", when this in fact lead to an successful + * update of the cache. + */ + return seq_printf(seq, "\t%s: used:%u/%u " + "hits:%lu misses:%lu starving:%lu dirty:%lu changed:%lu\n", + lc->name, lc->used, lc->nr_elements, + lc->hits, lc->misses, lc->starving, lc->dirty, lc->changed); +} + +static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr) +{ + return lc->lc_slot + (enr % lc->nr_elements); +} + + +/** + * lc_find - find element by label, if present in the hash table + * @lc: The lru_cache object + * @enr: element number + * + * Returns the pointer to an element, if the element with the requested + * "label" or element number is present in the hash table, + * or NULL if not found. Does not change the refcnt. + */ +struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr) +{ + struct hlist_node *n; + struct lc_element *e; + + BUG_ON(!lc); + BUG_ON(!lc->nr_elements); + hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) { + if (e->lc_number == enr) + return e; + } + return NULL; +} + +/* returned element will be "recycled" immediately */ +static struct lc_element *lc_evict(struct lru_cache *lc) +{ + struct list_head *n; + struct lc_element *e; + + if (list_empty(&lc->lru)) + return NULL; + + n = lc->lru.prev; + e = list_entry(n, struct lc_element, list); + + PARANOIA_LC_ELEMENT(lc, e); + + list_del(&e->list); + hlist_del(&e->colision); + return e; +} + +/** + * lc_del - removes an element from the cache + * @lc: The lru_cache object + * @e: The element to remove + * + * @e must be unused (refcnt == 0). Moves @e from "lru" to "free" list, + * sets @e->enr to %LC_FREE. + */ +void lc_del(struct lru_cache *lc, struct lc_element *e) +{ + PARANOIA_ENTRY(); + PARANOIA_LC_ELEMENT(lc, e); + BUG_ON(e->refcnt); + + e->lc_number = LC_FREE; + hlist_del_init(&e->colision); + list_move(&e->list, &lc->free); + RETURN(); +} + +static struct lc_element *lc_get_unused_element(struct lru_cache *lc) +{ + struct list_head *n; + + if (list_empty(&lc->free)) + return lc_evict(lc); + + n = lc->free.next; + list_del(n); + return list_entry(n, struct lc_element, list); +} + +static int lc_unused_element_available(struct lru_cache *lc) +{ + if (!list_empty(&lc->free)) + return 1; /* something on the free list */ + if (!list_empty(&lc->lru)) + return 1; /* something to evict */ + + return 0; +} + + +/** + * lc_get - get element by label, maybe change the active set + * @lc: the lru cache to operate on + * @enr: the label to look up + * + * Finds an element in the cache, increases its usage count, + * "touches" and returns it. + * + * In case the requested number is not present, it needs to be added to the + * cache. Therefore it is possible that an other element becomes evicted from + * the cache. In either case, the user is notified so he is able to e.g. keep + * a persistent log of the cache changes, and therefore the objects in use. + * + * Return values: + * NULL + * The cache was marked %LC_STARVING, + * or the requested label was not in the active set + * and a changing transaction is still pending (@lc was marked %LC_DIRTY). + * Or no unused or free element could be recycled (@lc will be marked as + * %LC_STARVING, blocking further lc_get() operations). + * + * pointer to the element with the REQUESTED element number. + * In this case, it can be used right away + * + * pointer to an UNUSED element with some different element number, + * where that different number may also be %LC_FREE. + * + * In this case, the cache is marked %LC_DIRTY (blocking further changes), + * and the returned element pointer is removed from the lru list and + * hash collision chains. The user now should do whatever housekeeping + * is necessary. + * Then he must call lc_changed(lc,element_pointer), to finish + * the change. + * + * NOTE: The user needs to check the lc_number on EACH use, so he recognizes + * any cache set change. + */ +struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr) +{ + struct lc_element *e; + + PARANOIA_ENTRY(); + if (lc->flags & LC_STARVING) { + ++lc->starving; + RETURN(NULL); + } + + e = lc_find(lc, enr); + if (e) { + ++lc->hits; + if (e->refcnt++ == 0) + lc->used++; + list_move(&e->list, &lc->in_use); /* Not evictable... */ + RETURN(e); + } + + ++lc->misses; + + /* In case there is nothing available and we can not kick out + * the LRU element, we have to wait ... + */ + if (!lc_unused_element_available(lc)) { + __set_bit(__LC_STARVING, &lc->flags); + RETURN(NULL); + } + + /* it was not present in the active set. + * we are going to recycle an unused (or even "free") element. + * user may need to commit a transaction to record that change. + * we serialize on flags & TF_DIRTY */ + if (test_and_set_bit(__LC_DIRTY, &lc->flags)) { + ++lc->dirty; + RETURN(NULL); + } + + e = lc_get_unused_element(lc); + BUG_ON(!e); + + clear_bit(__LC_STARVING, &lc->flags); + BUG_ON(++e->refcnt != 1); + lc->used++; + + lc->changing_element = e; + lc->new_number = enr; + + RETURN(e); +} + +/* similar to lc_get, + * but only gets a new reference on an existing element. + * you either get the requested element, or NULL. + * will be consolidated into one function. + */ +struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr) +{ + struct lc_element *e; + + PARANOIA_ENTRY(); + if (lc->flags & LC_STARVING) { + ++lc->starving; + RETURN(NULL); + } + + e = lc_find(lc, enr); + if (e) { + ++lc->hits; + if (e->refcnt++ == 0) + lc->used++; + list_move(&e->list, &lc->in_use); /* Not evictable... */ + } + RETURN(e); +} + +/** + * lc_changed - tell @lc that the change has been recorded + * @lc: the lru cache to operate on + * @e: the element pending label change + */ +void lc_changed(struct lru_cache *lc, struct lc_element *e) +{ + PARANOIA_ENTRY(); + BUG_ON(e != lc->changing_element); + PARANOIA_LC_ELEMENT(lc, e); + ++lc->changed; + e->lc_number = lc->new_number; + list_add(&e->list, &lc->in_use); + hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number)); + lc->changing_element = NULL; + lc->new_number = LC_FREE; + clear_bit(__LC_DIRTY, &lc->flags); + smp_mb__after_clear_bit(); + RETURN(); +} + + +/** + * lc_put - give up refcnt of @e + * @lc: the lru cache to operate on + * @e: the element to put + * + * If refcnt reaches zero, the element is moved to the lru list, + * and a %LC_STARVING (if set) is cleared. + * Returns the new (post-decrement) refcnt. + */ +unsigned int lc_put(struct lru_cache *lc, struct lc_element *e) +{ + PARANOIA_ENTRY(); + PARANOIA_LC_ELEMENT(lc, e); + BUG_ON(e->refcnt == 0); + BUG_ON(e == lc->changing_element); + if (--e->refcnt == 0) { + /* move it to the front of LRU. */ + list_move(&e->list, &lc->lru); + lc->used--; + clear_bit(__LC_STARVING, &lc->flags); + smp_mb__after_clear_bit(); + } + RETURN(e->refcnt); +} + +/** + * lc_element_by_index + * @lc: the lru cache to operate on + * @i: the index of the element to return + */ +struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i) +{ + BUG_ON(i >= lc->nr_elements); + BUG_ON(lc->lc_element[i] == NULL); + BUG_ON(lc->lc_element[i]->lc_index != i); + return lc->lc_element[i]; +} + +/** + * lc_index_of + * @lc: the lru cache to operate on + * @e: the element to query for its index position in lc->element + */ +unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e) +{ + PARANOIA_LC_ELEMENT(lc, e); + return e->lc_index; +} + +/** + * lc_set - associate index with label + * @lc: the lru cache to operate on + * @enr: the label to set + * @index: the element index to associate label with. + * + * Used to initialize the active set to some previously recorded state. + */ +void lc_set(struct lru_cache *lc, unsigned int enr, int index) +{ + struct lc_element *e; + + if (index < 0 || index >= lc->nr_elements) + return; + + e = lc_element_by_index(lc, index); + e->lc_number = enr; + + hlist_del_init(&e->colision); + hlist_add_head(&e->colision, lc_hash_slot(lc, enr)); + list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru); +} + +/** + * lc_dump - Dump a complete LRU cache to seq in textual form. + * @lc: the lru cache to operate on + * @seq: the &struct seq_file pointer to seq_printf into + * @utext: user supplied "heading" or other info + * @detail: function pointer the user may provide to dump further details + * of the object the lc_element is embedded in. + */ +void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext, + void (*detail) (struct seq_file *, struct lc_element *)) +{ + unsigned int nr_elements = lc->nr_elements; + struct lc_element *e; + int i; + + seq_printf(seq, "\tnn: lc_number refcnt %s\n ", utext); + for (i = 0; i < nr_elements; i++) { + e = lc_element_by_index(lc, i); + if (e->lc_number == LC_FREE) { + seq_printf(seq, "\t%2d: FREE\n", i); + } else { + seq_printf(seq, "\t%2d: %4u %4u ", i, + e->lc_number, e->refcnt); + detail(seq, e); + } + } +} + +EXPORT_SYMBOL(lc_create); +EXPORT_SYMBOL(lc_reset); +EXPORT_SYMBOL(lc_destroy); +EXPORT_SYMBOL(lc_set); +EXPORT_SYMBOL(lc_del); +EXPORT_SYMBOL(lc_try_get); +EXPORT_SYMBOL(lc_find); +EXPORT_SYMBOL(lc_get); +EXPORT_SYMBOL(lc_put); +EXPORT_SYMBOL(lc_changed); +EXPORT_SYMBOL(lc_element_by_index); +EXPORT_SYMBOL(lc_index_of); +EXPORT_SYMBOL(lc_seq_printf_stats); +EXPORT_SYMBOL(lc_seq_dump_details); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 67a33a5a1a93..0e8ca0347707 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -609,7 +609,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) * it would never exet if it is currently stuck in the refrigerator. */ list_for_each_entry(wb, &bdi->wb_list, list) { - wb->task->flags &= ~PF_FROZEN; + thaw_process(wb->task); kthread_stop(wb->task); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2c5d79236ead..0b19943ecf8b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -821,7 +821,6 @@ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { - struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; @@ -834,11 +833,6 @@ int write_cache_pages(struct address_space *mapping, int range_whole = 0; long nr_to_write = wbc->nr_to_write; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - pagevec_init(&pvec, 0); if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ @@ -957,12 +951,6 @@ continue_unlock: break; } } - - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - done = 1; - break; - } } pagevec_release(&pvec); cond_resched();