From 3d14c5d2b6e15c21d8e5467dc62d33127c23a644 Mon Sep 17 00:00:00 2001 From: Yehuda Sadeh Date: Tue, 6 Apr 2010 15:14:15 -0700 Subject: ceph: factor out libceph from Ceph file system This factors out protocol and low-level storage parts of ceph into a separate libceph module living in net/ceph and include/linux/ceph. This is mostly a matter of moving files around. However, a few key pieces of the interface change as well: - ceph_client becomes ceph_fs_client and ceph_client, where the latter captures the mon and osd clients, and the fs_client gets the mds client and file system specific pieces. - Mount option parsing and debugfs setup is correspondingly broken into two pieces. - The mon client gets a generic handler callback for otherwise unknown messages (mds map, in this case). - The basic supported/required feature bits can be expanded (and are by ceph_fs_client). No functional change, aside from some subtle error handling cases that got cleaned up in the refactoring process. Signed-off-by: Sage Weil --- MAINTAINERS | 2 + fs/ceph/Kconfig | 14 +- fs/ceph/Makefile | 11 +- fs/ceph/README | 20 - fs/ceph/addr.c | 65 +- fs/ceph/armor.c | 103 -- fs/ceph/auth.c | 259 ----- fs/ceph/auth.h | 92 -- fs/ceph/auth_none.c | 131 --- fs/ceph/auth_none.h | 30 - fs/ceph/auth_x.c | 687 ----------- fs/ceph/auth_x.h | 49 - fs/ceph/auth_x_protocol.h | 90 -- fs/ceph/buffer.c | 65 -- fs/ceph/buffer.h | 39 - fs/ceph/caps.c | 35 +- fs/ceph/ceph_debug.h | 37 - fs/ceph/ceph_frag.c | 3 +- fs/ceph/ceph_frag.h | 109 -- fs/ceph/ceph_fs.c | 72 -- fs/ceph/ceph_fs.h | 728 ------------ fs/ceph/ceph_hash.c | 118 -- fs/ceph/ceph_hash.h | 13 - fs/ceph/ceph_strings.c | 193 --- fs/ceph/crush/crush.c | 151 --- fs/ceph/crush/crush.h | 180 --- fs/ceph/crush/hash.c | 149 --- fs/ceph/crush/hash.h | 17 - fs/ceph/crush/mapper.c | 609 ---------- fs/ceph/crush/mapper.h | 20 - fs/ceph/crypto.c | 412 ------- fs/ceph/crypto.h | 48 - fs/ceph/debugfs.c | 407 ++----- fs/ceph/decode.h | 201 ---- fs/ceph/dir.c | 55 +- fs/ceph/export.c | 5 +- fs/ceph/file.c | 207 +--- fs/ceph/inode.c | 19 +- fs/ceph/ioctl.c | 11 +- fs/ceph/locks.c | 6 +- fs/ceph/mds_client.c | 86 +- fs/ceph/mds_client.h | 20 +- fs/ceph/mdsmap.c | 11 +- fs/ceph/mdsmap.h | 62 - fs/ceph/messenger.c | 2432 -------------------------------------- fs/ceph/messenger.h | 257 ---- fs/ceph/mon_client.c | 1018 ---------------- fs/ceph/mon_client.h | 121 -- fs/ceph/msgpool.c | 64 - fs/ceph/msgpool.h | 25 - fs/ceph/msgr.h | 175 --- fs/ceph/osd_client.c | 1771 ---------------------------- fs/ceph/osd_client.h | 233 ---- fs/ceph/osdmap.c | 1123 ------------------ fs/ceph/osdmap.h | 130 --- fs/ceph/pagelist.c | 63 - fs/ceph/pagelist.h | 54 - fs/ceph/rados.h | 405 ------- fs/ceph/snap.c | 10 +- fs/ceph/strings.c | 117 ++ fs/ceph/super.c | 1154 ++++++++---------- fs/ceph/super.h | 397 +++---- fs/ceph/types.h | 29 - fs/ceph/xattr.c | 15 +- include/linux/ceph/auth.h | 92 ++ include/linux/ceph/buffer.h | 39 + include/linux/ceph/ceph_debug.h | 38 + include/linux/ceph/ceph_frag.h | 109 ++ include/linux/ceph/ceph_fs.h | 728 ++++++++++++ include/linux/ceph/ceph_hash.h | 13 + include/linux/ceph/debugfs.h | 33 + include/linux/ceph/decode.h | 201 ++++ include/linux/ceph/libceph.h | 249 ++++ include/linux/ceph/mdsmap.h | 62 + include/linux/ceph/messenger.h | 261 +++++ include/linux/ceph/mon_client.h | 122 ++ include/linux/ceph/msgpool.h | 25 + include/linux/ceph/msgr.h | 175 +++ include/linux/ceph/osd_client.h | 234 ++++ include/linux/ceph/osdmap.h | 130 +++ include/linux/ceph/pagelist.h | 54 + include/linux/ceph/rados.h | 405 +++++++ include/linux/ceph/types.h | 29 + include/linux/crush/crush.h | 180 +++ include/linux/crush/hash.h | 17 + include/linux/crush/mapper.h | 20 + net/Kconfig | 1 + net/Makefile | 1 + net/ceph/Kconfig | 28 + net/ceph/Makefile | 37 + net/ceph/armor.c | 103 ++ net/ceph/auth.c | 259 +++++ net/ceph/auth_none.c | 132 +++ net/ceph/auth_none.h | 29 + net/ceph/auth_x.c | 688 +++++++++++ net/ceph/auth_x.h | 50 + net/ceph/auth_x_protocol.h | 90 ++ net/ceph/buffer.c | 68 ++ net/ceph/ceph_common.c | 529 +++++++++ net/ceph/ceph_fs.c | 75 ++ net/ceph/ceph_hash.c | 118 ++ net/ceph/ceph_strings.c | 84 ++ net/ceph/crush/crush.c | 151 +++ net/ceph/crush/hash.c | 149 +++ net/ceph/crush/mapper.c | 609 ++++++++++ net/ceph/crypto.c | 412 +++++++ net/ceph/crypto.h | 48 + net/ceph/debugfs.c | 268 +++++ net/ceph/messenger.c | 2453 +++++++++++++++++++++++++++++++++++++++ net/ceph/mon_client.c | 1027 ++++++++++++++++ net/ceph/msgpool.c | 64 + net/ceph/osd_client.c | 1773 ++++++++++++++++++++++++++++ net/ceph/osdmap.c | 1128 ++++++++++++++++++ net/ceph/pagelist.c | 65 ++ net/ceph/pagevec.c | 223 ++++ 115 files changed, 14920 insertions(+), 14192 deletions(-) delete mode 100644 fs/ceph/README delete mode 100644 fs/ceph/armor.c delete mode 100644 fs/ceph/auth.c delete mode 100644 fs/ceph/auth.h delete mode 100644 fs/ceph/auth_none.c delete mode 100644 fs/ceph/auth_none.h delete mode 100644 fs/ceph/auth_x.c delete mode 100644 fs/ceph/auth_x.h delete mode 100644 fs/ceph/auth_x_protocol.h delete mode 100644 fs/ceph/buffer.c delete mode 100644 fs/ceph/buffer.h delete mode 100644 fs/ceph/ceph_debug.h delete mode 100644 fs/ceph/ceph_frag.h delete mode 100644 fs/ceph/ceph_fs.c delete mode 100644 fs/ceph/ceph_fs.h delete mode 100644 fs/ceph/ceph_hash.c delete mode 100644 fs/ceph/ceph_hash.h delete mode 100644 fs/ceph/ceph_strings.c delete mode 100644 fs/ceph/crush/crush.c delete mode 100644 fs/ceph/crush/crush.h delete mode 100644 fs/ceph/crush/hash.c delete mode 100644 fs/ceph/crush/hash.h delete mode 100644 fs/ceph/crush/mapper.c delete mode 100644 fs/ceph/crush/mapper.h delete mode 100644 fs/ceph/crypto.c delete mode 100644 fs/ceph/crypto.h delete mode 100644 fs/ceph/decode.h delete mode 100644 fs/ceph/mdsmap.h delete mode 100644 fs/ceph/messenger.c delete mode 100644 fs/ceph/messenger.h delete mode 100644 fs/ceph/mon_client.c delete mode 100644 fs/ceph/mon_client.h delete mode 100644 fs/ceph/msgpool.c delete mode 100644 fs/ceph/msgpool.h delete mode 100644 fs/ceph/msgr.h delete mode 100644 fs/ceph/osd_client.c delete mode 100644 fs/ceph/osd_client.h delete mode 100644 fs/ceph/osdmap.c delete mode 100644 fs/ceph/osdmap.h delete mode 100644 fs/ceph/pagelist.c delete mode 100644 fs/ceph/pagelist.h delete mode 100644 fs/ceph/rados.h create mode 100644 fs/ceph/strings.c delete mode 100644 fs/ceph/types.h create mode 100644 include/linux/ceph/auth.h create mode 100644 include/linux/ceph/buffer.h create mode 100644 include/linux/ceph/ceph_debug.h create mode 100644 include/linux/ceph/ceph_frag.h create mode 100644 include/linux/ceph/ceph_fs.h create mode 100644 include/linux/ceph/ceph_hash.h create mode 100644 include/linux/ceph/debugfs.h create mode 100644 include/linux/ceph/decode.h create mode 100644 include/linux/ceph/libceph.h create mode 100644 include/linux/ceph/mdsmap.h create mode 100644 include/linux/ceph/messenger.h create mode 100644 include/linux/ceph/mon_client.h create mode 100644 include/linux/ceph/msgpool.h create mode 100644 include/linux/ceph/msgr.h create mode 100644 include/linux/ceph/osd_client.h create mode 100644 include/linux/ceph/osdmap.h create mode 100644 include/linux/ceph/pagelist.h create mode 100644 include/linux/ceph/rados.h create mode 100644 include/linux/ceph/types.h create mode 100644 include/linux/crush/crush.h create mode 100644 include/linux/crush/hash.h create mode 100644 include/linux/crush/mapper.h create mode 100644 net/ceph/Kconfig create mode 100644 net/ceph/Makefile create mode 100644 net/ceph/armor.c create mode 100644 net/ceph/auth.c create mode 100644 net/ceph/auth_none.c create mode 100644 net/ceph/auth_none.h create mode 100644 net/ceph/auth_x.c create mode 100644 net/ceph/auth_x.h create mode 100644 net/ceph/auth_x_protocol.h create mode 100644 net/ceph/buffer.c create mode 100644 net/ceph/ceph_common.c create mode 100644 net/ceph/ceph_fs.c create mode 100644 net/ceph/ceph_hash.c create mode 100644 net/ceph/ceph_strings.c create mode 100644 net/ceph/crush/crush.c create mode 100644 net/ceph/crush/hash.c create mode 100644 net/ceph/crush/mapper.c create mode 100644 net/ceph/crypto.c create mode 100644 net/ceph/crypto.h create mode 100644 net/ceph/debugfs.c create mode 100644 net/ceph/messenger.c create mode 100644 net/ceph/mon_client.c create mode 100644 net/ceph/msgpool.c create mode 100644 net/ceph/osd_client.c create mode 100644 net/ceph/osdmap.c create mode 100644 net/ceph/pagelist.c create mode 100644 net/ceph/pagevec.c diff --git a/MAINTAINERS b/MAINTAINERS index 7679bf32f7bb..48d05654d456 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1527,6 +1527,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git S: Supported F: Documentation/filesystems/ceph.txt F: fs/ceph +F: net/ceph +F: include/linux/ceph CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM: M: David Vrabel diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index 0fcd2640c23f..9eb134ea6eb2 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -1,9 +1,11 @@ config CEPH_FS tristate "Ceph distributed file system (EXPERIMENTAL)" depends on INET && EXPERIMENTAL + select CEPH_LIB select LIBCRC32C select CRYPTO_AES select CRYPTO + default n help Choose Y or M here to include support for mounting the experimental Ceph distributed file system. Ceph is an extremely @@ -14,15 +16,3 @@ config CEPH_FS If unsure, say N. -config CEPH_FS_PRETTYDEBUG - bool "Include file:line in ceph debug output" - depends on CEPH_FS - default n - help - If you say Y here, debug output will include a filename and - line to aid debugging. This icnreases kernel size and slows - execution slightly when debug call sites are enabled (e.g., - via CONFIG_DYNAMIC_DEBUG). - - If unsure, say N. - diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile index 278e1172600d..9e6c4f2e8ff1 100644 --- a/fs/ceph/Makefile +++ b/fs/ceph/Makefile @@ -8,15 +8,8 @@ obj-$(CONFIG_CEPH_FS) += ceph.o ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \ export.o caps.o snap.o xattr.o \ - messenger.o msgpool.o buffer.o pagelist.o \ - mds_client.o mdsmap.o \ - mon_client.o \ - osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \ - debugfs.o \ - auth.o auth_none.o \ - crypto.o armor.o \ - auth_x.o \ - ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o + mds_client.o mdsmap.o strings.o ceph_frag.o \ + debugfs.o else #Otherwise we were called directly from the command diff --git a/fs/ceph/README b/fs/ceph/README deleted file mode 100644 index 18352fab37c0..000000000000 --- a/fs/ceph/README +++ /dev/null @@ -1,20 +0,0 @@ -# -# The following files are shared by (and manually synchronized -# between) the Ceph userland and kernel client. -# -# userland kernel -src/include/ceph_fs.h fs/ceph/ceph_fs.h -src/include/ceph_fs.cc fs/ceph/ceph_fs.c -src/include/msgr.h fs/ceph/msgr.h -src/include/rados.h fs/ceph/rados.h -src/include/ceph_strings.cc fs/ceph/ceph_strings.c -src/include/ceph_frag.h fs/ceph/ceph_frag.h -src/include/ceph_frag.cc fs/ceph/ceph_frag.c -src/include/ceph_hash.h fs/ceph/ceph_hash.h -src/include/ceph_hash.cc fs/ceph/ceph_hash.c -src/crush/crush.c fs/ceph/crush/crush.c -src/crush/crush.h fs/ceph/crush/crush.h -src/crush/mapper.c fs/ceph/crush/mapper.c -src/crush/mapper.h fs/ceph/crush/mapper.h -src/crush/hash.h fs/ceph/crush/hash.h -src/crush/hash.c fs/ceph/crush/hash.c diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index efbc604001c8..51bcc5ce3230 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -10,7 +10,8 @@ #include #include "super.h" -#include "osd_client.h" +#include "mds_client.h" +#include /* * Ceph address space ops. @@ -193,7 +194,8 @@ static int readpage_nounlock(struct file *filp, struct page *page) { struct inode *inode = filp->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc; + struct ceph_osd_client *osdc = + &ceph_inode_to_client(inode)->client->osdc; int err = 0; u64 len = PAGE_CACHE_SIZE; @@ -265,7 +267,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, { struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc; + struct ceph_osd_client *osdc = + &ceph_inode_to_client(inode)->client->osdc; int rc = 0; struct page **pages; loff_t offset; @@ -365,7 +368,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) { struct inode *inode; struct ceph_inode_info *ci; - struct ceph_client *client; + struct ceph_fs_client *fsc; struct ceph_osd_client *osdc; loff_t page_off = page->index << PAGE_CACHE_SHIFT; int len = PAGE_CACHE_SIZE; @@ -383,8 +386,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) } inode = page->mapping->host; ci = ceph_inode(inode); - client = ceph_inode_to_client(inode); - osdc = &client->osdc; + fsc = ceph_inode_to_client(inode); + osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ snapc = (void *)page->private; @@ -414,10 +417,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p page %p index %lu on %llu~%u snapc %p\n", inode, page, page->index, page_off, len, snapc); - writeback_stat = atomic_long_inc_return(&client->writeback_count); + writeback_stat = atomic_long_inc_return(&fsc->writeback_count); if (writeback_stat > - CONGESTION_ON_THRESH(client->mount_args->congestion_kb)) - set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC); + CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) + set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); set_page_writeback(page); err = ceph_osdc_writepages(osdc, ceph_vino(inode), @@ -496,7 +499,7 @@ static void writepages_finish(struct ceph_osd_request *req, struct address_space *mapping = inode->i_mapping; __s32 rc = -EIO; u64 bytes = 0; - struct ceph_client *client = ceph_inode_to_client(inode); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); long writeback_stat; unsigned issued = ceph_caps_issued(ci); @@ -529,10 +532,10 @@ static void writepages_finish(struct ceph_osd_request *req, WARN_ON(!PageUptodate(page)); writeback_stat = - atomic_long_dec_return(&client->writeback_count); + atomic_long_dec_return(&fsc->writeback_count); if (writeback_stat < - CONGESTION_OFF_THRESH(client->mount_args->congestion_kb)) - clear_bdi_congested(&client->backing_dev_info, + CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb)) + clear_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); ceph_put_snap_context((void *)page->private); @@ -569,13 +572,13 @@ static void writepages_finish(struct ceph_osd_request *req, * mempool. we avoid the mempool if we can because req->r_num_pages * may be less than the maximum write size. */ -static void alloc_page_vec(struct ceph_client *client, +static void alloc_page_vec(struct ceph_fs_client *fsc, struct ceph_osd_request *req) { req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages, GFP_NOFS); if (!req->r_pages) { - req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS); + req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS); req->r_pages_from_pool = 1; WARN_ON(!req->r_pages); } @@ -590,7 +593,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct inode *inode = mapping->host; struct backing_dev_info *bdi = mapping->backing_dev_info; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_client *client; + struct ceph_fs_client *fsc; pgoff_t index, start, end; int range_whole = 0; int should_loop = 1; @@ -617,13 +620,13 @@ static int ceph_writepages_start(struct address_space *mapping, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); - client = ceph_inode_to_client(inode); - if (client->mount_state == CEPH_MOUNT_SHUTDOWN) { + fsc = ceph_inode_to_client(inode); + if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) { pr_warning("writepage_start %p on forced umount\n", inode); return -EIO; /* we're in a forced umount, don't write! */ } - if (client->mount_args->wsize && client->mount_args->wsize < wsize) - wsize = client->mount_args->wsize; + if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize) + wsize = fsc->mount_options->wsize; if (wsize < PAGE_CACHE_SIZE) wsize = PAGE_CACHE_SIZE; max_pages_ever = wsize >> PAGE_CACHE_SHIFT; @@ -769,7 +772,7 @@ get_more_pages: offset = (unsigned long long)page->index << PAGE_CACHE_SHIFT; len = wsize; - req = ceph_osdc_new_request(&client->osdc, + req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, ceph_vino(inode), offset, &len, @@ -782,7 +785,7 @@ get_more_pages: &inode->i_mtime, true, 1); max_pages = req->r_num_pages; - alloc_page_vec(client, req); + alloc_page_vec(fsc, req); req->r_callback = writepages_finish; req->r_inode = inode; } @@ -794,10 +797,10 @@ get_more_pages: inode, page, page->index); writeback_stat = - atomic_long_inc_return(&client->writeback_count); + atomic_long_inc_return(&fsc->writeback_count); if (writeback_stat > CONGESTION_ON_THRESH( - client->mount_args->congestion_kb)) { - set_bdi_congested(&client->backing_dev_info, + fsc->mount_options->congestion_kb)) { + set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); } @@ -846,7 +849,7 @@ get_more_pages: op->payload_len = cpu_to_le32(len); req->r_request->hdr.data_len = cpu_to_le32(len); - ceph_osdc_start_request(&client->osdc, req, true); + ceph_osdc_start_request(&fsc->client->osdc, req, true); req = NULL; /* continue? */ @@ -915,7 +918,7 @@ static int ceph_update_writeable_page(struct file *file, { struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc; + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; loff_t page_off = pos & PAGE_CACHE_MASK; int pos_in_page = pos & ~PAGE_CACHE_MASK; int end_in_page = pos_in_page + len; @@ -1053,8 +1056,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = file->f_dentry->d_inode; - struct ceph_client *client = ceph_inode_to_client(inode); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_client *mdsc = fsc->mdsc; unsigned from = pos & (PAGE_CACHE_SIZE - 1); int check_cap = 0; @@ -1123,7 +1126,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = vma->vm_file->f_dentry->d_inode; struct page *page = vmf->page; - struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc; + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; loff_t off = page->index << PAGE_CACHE_SHIFT; loff_t size, len; int ret; diff --git a/fs/ceph/armor.c b/fs/ceph/armor.c deleted file mode 100644 index eb2a666b0be7..000000000000 --- a/fs/ceph/armor.c +++ /dev/null @@ -1,103 +0,0 @@ - -#include - -int ceph_armor(char *dst, const char *src, const char *end); -int ceph_unarmor(char *dst, const char *src, const char *end); - -/* - * base64 encode/decode. - */ - -static const char *pem_key = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; - -static int encode_bits(int c) -{ - return pem_key[c]; -} - -static int decode_bits(char c) -{ - if (c >= 'A' && c <= 'Z') - return c - 'A'; - if (c >= 'a' && c <= 'z') - return c - 'a' + 26; - if (c >= '0' && c <= '9') - return c - '0' + 52; - if (c == '+') - return 62; - if (c == '/') - return 63; - if (c == '=') - return 0; /* just non-negative, please */ - return -EINVAL; -} - -int ceph_armor(char *dst, const char *src, const char *end) -{ - int olen = 0; - int line = 0; - - while (src < end) { - unsigned char a, b, c; - - a = *src++; - *dst++ = encode_bits(a >> 2); - if (src < end) { - b = *src++; - *dst++ = encode_bits(((a & 3) << 4) | (b >> 4)); - if (src < end) { - c = *src++; - *dst++ = encode_bits(((b & 15) << 2) | - (c >> 6)); - *dst++ = encode_bits(c & 63); - } else { - *dst++ = encode_bits((b & 15) << 2); - *dst++ = '='; - } - } else { - *dst++ = encode_bits(((a & 3) << 4)); - *dst++ = '='; - *dst++ = '='; - } - olen += 4; - line += 4; - if (line == 64) { - line = 0; - *(dst++) = '\n'; - olen++; - } - } - return olen; -} - -int ceph_unarmor(char *dst, const char *src, const char *end) -{ - int olen = 0; - - while (src < end) { - int a, b, c, d; - - if (src < end && src[0] == '\n') - src++; - if (src + 4 > end) - return -EINVAL; - a = decode_bits(src[0]); - b = decode_bits(src[1]); - c = decode_bits(src[2]); - d = decode_bits(src[3]); - if (a < 0 || b < 0 || c < 0 || d < 0) - return -EINVAL; - - *dst++ = (a << 2) | (b >> 4); - if (src[2] == '=') - return olen + 1; - *dst++ = ((b & 15) << 4) | (c >> 2); - if (src[3] == '=') - return olen + 2; - *dst++ = ((c & 3) << 6) | d; - olen += 3; - src += 4; - } - return olen; -} diff --git a/fs/ceph/auth.c b/fs/ceph/auth.c deleted file mode 100644 index 6d2e30600627..000000000000 --- a/fs/ceph/auth.c +++ /dev/null @@ -1,259 +0,0 @@ -#include "ceph_debug.h" - -#include -#include -#include - -#include "types.h" -#include "auth_none.h" -#include "auth_x.h" -#include "decode.h" -#include "super.h" - -#include "messenger.h" - -/* - * get protocol handler - */ -static u32 supported_protocols[] = { - CEPH_AUTH_NONE, - CEPH_AUTH_CEPHX -}; - -static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol) -{ - switch (protocol) { - case CEPH_AUTH_NONE: - return ceph_auth_none_init(ac); - case CEPH_AUTH_CEPHX: - return ceph_x_init(ac); - default: - return -ENOENT; - } -} - -/* - * setup, teardown. - */ -struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) -{ - struct ceph_auth_client *ac; - int ret; - - dout("auth_init name '%s' secret '%s'\n", name, secret); - - ret = -ENOMEM; - ac = kzalloc(sizeof(*ac), GFP_NOFS); - if (!ac) - goto out; - - ac->negotiating = true; - if (name) - ac->name = name; - else - ac->name = CEPH_AUTH_NAME_DEFAULT; - dout("auth_init name %s secret %s\n", ac->name, secret); - ac->secret = secret; - return ac; - -out: - return ERR_PTR(ret); -} - -void ceph_auth_destroy(struct ceph_auth_client *ac) -{ - dout("auth_destroy %p\n", ac); - if (ac->ops) - ac->ops->destroy(ac); - kfree(ac); -} - -/* - * Reset occurs when reconnecting to the monitor. - */ -void ceph_auth_reset(struct ceph_auth_client *ac) -{ - dout("auth_reset %p\n", ac); - if (ac->ops && !ac->negotiating) - ac->ops->reset(ac); - ac->negotiating = true; -} - -int ceph_entity_name_encode(const char *name, void **p, void *end) -{ - int len = strlen(name); - - if (*p + 2*sizeof(u32) + len > end) - return -ERANGE; - ceph_encode_32(p, CEPH_ENTITY_TYPE_CLIENT); - ceph_encode_32(p, len); - ceph_encode_copy(p, name, len); - return 0; -} - -/* - * Initiate protocol negotiation with monitor. Include entity name - * and list supported protocols. - */ -int ceph_auth_build_hello(struct ceph_auth_client *ac, void *buf, size_t len) -{ - struct ceph_mon_request_header *monhdr = buf; - void *p = monhdr + 1, *end = buf + len, *lenp; - int i, num; - int ret; - - dout("auth_build_hello\n"); - monhdr->have_version = 0; - monhdr->session_mon = cpu_to_le16(-1); - monhdr->session_mon_tid = 0; - - ceph_encode_32(&p, 0); /* no protocol, yet */ - - lenp = p; - p += sizeof(u32); - - ceph_decode_need(&p, end, 1 + sizeof(u32), bad); - ceph_encode_8(&p, 1); - num = ARRAY_SIZE(supported_protocols); - ceph_encode_32(&p, num); - ceph_decode_need(&p, end, num * sizeof(u32), bad); - for (i = 0; i < num; i++) - ceph_encode_32(&p, supported_protocols[i]); - - ret = ceph_entity_name_encode(ac->name, &p, end); - if (ret < 0) - return ret; - ceph_decode_need(&p, end, sizeof(u64), bad); - ceph_encode_64(&p, ac->global_id); - - ceph_encode_32(&lenp, p - lenp - sizeof(u32)); - return p - buf; - -bad: - return -ERANGE; -} - -static int ceph_build_auth_request(struct ceph_auth_client *ac, - void *msg_buf, size_t msg_len) -{ - struct ceph_mon_request_header *monhdr = msg_buf; - void *p = monhdr + 1; - void *end = msg_buf + msg_len; - int ret; - - monhdr->have_version = 0; - monhdr->session_mon = cpu_to_le16(-1); - monhdr->session_mon_tid = 0; - - ceph_encode_32(&p, ac->protocol); - - ret = ac->ops->build_request(ac, p + sizeof(u32), end); - if (ret < 0) { - pr_err("error %d building auth method %s request\n", ret, - ac->ops->name); - return ret; - } - dout(" built request %d bytes\n", ret); - ceph_encode_32(&p, ret); - return p + ret - msg_buf; -} - -/* - * Handle auth message from monitor. - */ -int ceph_handle_auth_reply(struct ceph_auth_client *ac, - void *buf, size_t len, - void *reply_buf, size_t reply_len) -{ - void *p = buf; - void *end = buf + len; - int protocol; - s32 result; - u64 global_id; - void *payload, *payload_end; - int payload_len; - char *result_msg; - int result_msg_len; - int ret = -EINVAL; - - dout("handle_auth_reply %p %p\n", p, end); - ceph_decode_need(&p, end, sizeof(u32) * 3 + sizeof(u64), bad); - protocol = ceph_decode_32(&p); - result = ceph_decode_32(&p); - global_id = ceph_decode_64(&p); - payload_len = ceph_decode_32(&p); - payload = p; - p += payload_len; - ceph_decode_need(&p, end, sizeof(u32), bad); - result_msg_len = ceph_decode_32(&p); - result_msg = p; - p += result_msg_len; - if (p != end) - goto bad; - - dout(" result %d '%.*s' gid %llu len %d\n", result, result_msg_len, - result_msg, global_id, payload_len); - - payload_end = payload + payload_len; - - if (global_id && ac->global_id != global_id) { - dout(" set global_id %lld -> %lld\n", ac->global_id, global_id); - ac->global_id = global_id; - } - - if (ac->negotiating) { - /* server does not support our protocols? */ - if (!protocol && result < 0) { - ret = result; - goto out; - } - /* set up (new) protocol handler? */ - if (ac->protocol && ac->protocol != protocol) { - ac->ops->destroy(ac); - ac->protocol = 0; - ac->ops = NULL; - } - if (ac->protocol != protocol) { - ret = ceph_auth_init_protocol(ac, protocol); - if (ret) { - pr_err("error %d on auth protocol %d init\n", - ret, protocol); - goto out; - } - } - - ac->negotiating = false; - } - - ret = ac->ops->handle_reply(ac, result, payload, payload_end); - if (ret == -EAGAIN) { - return ceph_build_auth_request(ac, reply_buf, reply_len); - } else if (ret) { - pr_err("auth method '%s' error %d\n", ac->ops->name, ret); - return ret; - } - return 0; - -bad: - pr_err("failed to decode auth msg\n"); -out: - return ret; -} - -int ceph_build_auth(struct ceph_auth_client *ac, - void *msg_buf, size_t msg_len) -{ - if (!ac->protocol) - return ceph_auth_build_hello(ac, msg_buf, msg_len); - BUG_ON(!ac->ops); - if (ac->ops->should_authenticate(ac)) - return ceph_build_auth_request(ac, msg_buf, msg_len); - return 0; -} - -int ceph_auth_is_authenticated(struct ceph_auth_client *ac) -{ - if (!ac->ops) - return 0; - return ac->ops->is_authenticated(ac); -} diff --git a/fs/ceph/auth.h b/fs/ceph/auth.h deleted file mode 100644 index d38a2fb4a137..000000000000 --- a/fs/ceph/auth.h +++ /dev/null @@ -1,92 +0,0 @@ -#ifndef _FS_CEPH_AUTH_H -#define _FS_CEPH_AUTH_H - -#include "types.h" -#include "buffer.h" - -/* - * Abstract interface for communicating with the authenticate module. - * There is some handshake that takes place between us and the monitor - * to acquire the necessary keys. These are used to generate an - * 'authorizer' that we use when connecting to a service (mds, osd). - */ - -struct ceph_auth_client; -struct ceph_authorizer; - -struct ceph_auth_client_ops { - const char *name; - - /* - * true if we are authenticated and can connect to - * services. - */ - int (*is_authenticated)(struct ceph_auth_client *ac); - - /* - * true if we should (re)authenticate, e.g., when our tickets - * are getting old and crusty. - */ - int (*should_authenticate)(struct ceph_auth_client *ac); - - /* - * build requests and process replies during monitor - * handshake. if handle_reply returns -EAGAIN, we build - * another request. - */ - int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end); - int (*handle_reply)(struct ceph_auth_client *ac, int result, - void *buf, void *end); - - /* - * Create authorizer for connecting to a service, and verify - * the response to authenticate the service. - */ - int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type, - struct ceph_authorizer **a, - void **buf, size_t *len, - void **reply_buf, size_t *reply_len); - int (*verify_authorizer_reply)(struct ceph_auth_client *ac, - struct ceph_authorizer *a, size_t len); - void (*destroy_authorizer)(struct ceph_auth_client *ac, - struct ceph_authorizer *a); - void (*invalidate_authorizer)(struct ceph_auth_client *ac, - int peer_type); - - /* reset when we (re)connect to a monitor */ - void (*reset)(struct ceph_auth_client *ac); - - void (*destroy)(struct ceph_auth_client *ac); -}; - -struct ceph_auth_client { - u32 protocol; /* CEPH_AUTH_* */ - void *private; /* for use by protocol implementation */ - const struct ceph_auth_client_ops *ops; /* null iff protocol==0 */ - - bool negotiating; /* true if negotiating protocol */ - const char *name; /* entity name */ - u64 global_id; /* our unique id in system */ - const char *secret; /* our secret key */ - unsigned want_keys; /* which services we want */ -}; - -extern struct ceph_auth_client *ceph_auth_init(const char *name, - const char *secret); -extern void ceph_auth_destroy(struct ceph_auth_client *ac); - -extern void ceph_auth_reset(struct ceph_auth_client *ac); - -extern int ceph_auth_build_hello(struct ceph_auth_client *ac, - void *buf, size_t len); -extern int ceph_handle_auth_reply(struct ceph_auth_client *ac, - void *buf, size_t len, - void *reply_buf, size_t reply_len); -extern int ceph_entity_name_encode(const char *name, void **p, void *end); - -extern int ceph_build_auth(struct ceph_auth_client *ac, - void *msg_buf, size_t msg_len); - -extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); - -#endif diff --git a/fs/ceph/auth_none.c b/fs/ceph/auth_none.c deleted file mode 100644 index ad1dc21286c7..000000000000 --- a/fs/ceph/auth_none.c +++ /dev/null @@ -1,131 +0,0 @@ - -#include "ceph_debug.h" - -#include -#include -#include -#include - -#include "auth_none.h" -#include "auth.h" -#include "decode.h" - -static void reset(struct ceph_auth_client *ac) -{ - struct ceph_auth_none_info *xi = ac->private; - - xi->starting = true; - xi->built_authorizer = false; -} - -static void destroy(struct ceph_auth_client *ac) -{ - kfree(ac->private); - ac->private = NULL; -} - -static int is_authenticated(struct ceph_auth_client *ac) -{ - struct ceph_auth_none_info *xi = ac->private; - - return !xi->starting; -} - -static int should_authenticate(struct ceph_auth_client *ac) -{ - struct ceph_auth_none_info *xi = ac->private; - - return xi->starting; -} - -/* - * the generic auth code decode the global_id, and we carry no actual - * authenticate state, so nothing happens here. - */ -static int handle_reply(struct ceph_auth_client *ac, int result, - void *buf, void *end) -{ - struct ceph_auth_none_info *xi = ac->private; - - xi->starting = false; - return result; -} - -/* - * build an 'authorizer' with our entity_name and global_id. we can - * reuse a single static copy since it is identical for all services - * we connect to. - */ -static int ceph_auth_none_create_authorizer( - struct ceph_auth_client *ac, int peer_type, - struct ceph_authorizer **a, - void **buf, size_t *len, - void **reply_buf, size_t *reply_len) -{ - struct ceph_auth_none_info *ai = ac->private; - struct ceph_none_authorizer *au = &ai->au; - void *p, *end; - int ret; - - if (!ai->built_authorizer) { - p = au->buf; - end = p + sizeof(au->buf); - ceph_encode_8(&p, 1); - ret = ceph_entity_name_encode(ac->name, &p, end - 8); - if (ret < 0) - goto bad; - ceph_decode_need(&p, end, sizeof(u64), bad2); - ceph_encode_64(&p, ac->global_id); - au->buf_len = p - (void *)au->buf; - ai->built_authorizer = true; - dout("built authorizer len %d\n", au->buf_len); - } - - *a = (struct ceph_authorizer *)au; - *buf = au->buf; - *len = au->buf_len; - *reply_buf = au->reply_buf; - *reply_len = sizeof(au->reply_buf); - return 0; - -bad2: - ret = -ERANGE; -bad: - return ret; -} - -static void ceph_auth_none_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - /* nothing to do */ -} - -static const struct ceph_auth_client_ops ceph_auth_none_ops = { - .name = "none", - .reset = reset, - .destroy = destroy, - .is_authenticated = is_authenticated, - .should_authenticate = should_authenticate, - .handle_reply = handle_reply, - .create_authorizer = ceph_auth_none_create_authorizer, - .destroy_authorizer = ceph_auth_none_destroy_authorizer, -}; - -int ceph_auth_none_init(struct ceph_auth_client *ac) -{ - struct ceph_auth_none_info *xi; - - dout("ceph_auth_none_init %p\n", ac); - xi = kzalloc(sizeof(*xi), GFP_NOFS); - if (!xi) - return -ENOMEM; - - xi->starting = true; - xi->built_authorizer = false; - - ac->protocol = CEPH_AUTH_NONE; - ac->private = xi; - ac->ops = &ceph_auth_none_ops; - return 0; -} - diff --git a/fs/ceph/auth_none.h b/fs/ceph/auth_none.h deleted file mode 100644 index 8164df1a08be..000000000000 --- a/fs/ceph/auth_none.h +++ /dev/null @@ -1,30 +0,0 @@ -#ifndef _FS_CEPH_AUTH_NONE_H -#define _FS_CEPH_AUTH_NONE_H - -#include - -#include "auth.h" - -/* - * null security mode. - * - * we use a single static authorizer that simply encodes our entity name - * and global id. - */ - -struct ceph_none_authorizer { - char buf[128]; - int buf_len; - char reply_buf[0]; -}; - -struct ceph_auth_none_info { - bool starting; - bool built_authorizer; - struct ceph_none_authorizer au; /* we only need one; it's static */ -}; - -extern int ceph_auth_none_init(struct ceph_auth_client *ac); - -#endif - diff --git a/fs/ceph/auth_x.c b/fs/ceph/auth_x.c deleted file mode 100644 index a2d002cbdec2..000000000000 --- a/fs/ceph/auth_x.c +++ /dev/null @@ -1,687 +0,0 @@ - -#include "ceph_debug.h" - -#include -#include -#include -#include - -#include "auth_x.h" -#include "auth_x_protocol.h" -#include "crypto.h" -#include "auth.h" -#include "decode.h" - -#define TEMP_TICKET_BUF_LEN 256 - -static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed); - -static int ceph_x_is_authenticated(struct ceph_auth_client *ac) -{ - struct ceph_x_info *xi = ac->private; - int need; - - ceph_x_validate_tickets(ac, &need); - dout("ceph_x_is_authenticated want=%d need=%d have=%d\n", - ac->want_keys, need, xi->have_keys); - return (ac->want_keys & xi->have_keys) == ac->want_keys; -} - -static int ceph_x_should_authenticate(struct ceph_auth_client *ac) -{ - struct ceph_x_info *xi = ac->private; - int need; - - ceph_x_validate_tickets(ac, &need); - dout("ceph_x_should_authenticate want=%d need=%d have=%d\n", - ac->want_keys, need, xi->have_keys); - return need != 0; -} - -static int ceph_x_encrypt_buflen(int ilen) -{ - return sizeof(struct ceph_x_encrypt_header) + ilen + 16 + - sizeof(u32); -} - -static int ceph_x_encrypt(struct ceph_crypto_key *secret, - void *ibuf, int ilen, void *obuf, size_t olen) -{ - struct ceph_x_encrypt_header head = { - .struct_v = 1, - .magic = cpu_to_le64(CEPHX_ENC_MAGIC) - }; - size_t len = olen - sizeof(u32); - int ret; - - ret = ceph_encrypt2(secret, obuf + sizeof(u32), &len, - &head, sizeof(head), ibuf, ilen); - if (ret) - return ret; - ceph_encode_32(&obuf, len); - return len + sizeof(u32); -} - -static int ceph_x_decrypt(struct ceph_crypto_key *secret, - void **p, void *end, void *obuf, size_t olen) -{ - struct ceph_x_encrypt_header head; - size_t head_len = sizeof(head); - int len, ret; - - len = ceph_decode_32(p); - if (*p + len > end) - return -EINVAL; - - dout("ceph_x_decrypt len %d\n", len); - ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen, - *p, len); - if (ret) - return ret; - if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC) - return -EPERM; - *p += len; - return olen; -} - -/* - * get existing (or insert new) ticket handler - */ -static struct ceph_x_ticket_handler * -get_ticket_handler(struct ceph_auth_client *ac, int service) -{ - struct ceph_x_ticket_handler *th; - struct ceph_x_info *xi = ac->private; - struct rb_node *parent = NULL, **p = &xi->ticket_handlers.rb_node; - - while (*p) { - parent = *p; - th = rb_entry(parent, struct ceph_x_ticket_handler, node); - if (service < th->service) - p = &(*p)->rb_left; - else if (service > th->service) - p = &(*p)->rb_right; - else - return th; - } - - /* add it */ - th = kzalloc(sizeof(*th), GFP_NOFS); - if (!th) - return ERR_PTR(-ENOMEM); - th->service = service; - rb_link_node(&th->node, parent, p); - rb_insert_color(&th->node, &xi->ticket_handlers); - return th; -} - -static void remove_ticket_handler(struct ceph_auth_client *ac, - struct ceph_x_ticket_handler *th) -{ - struct ceph_x_info *xi = ac->private; - - dout("remove_ticket_handler %p %d\n", th, th->service); - rb_erase(&th->node, &xi->ticket_handlers); - ceph_crypto_key_destroy(&th->session_key); - if (th->ticket_blob) - ceph_buffer_put(th->ticket_blob); - kfree(th); -} - -static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, - struct ceph_crypto_key *secret, - void *buf, void *end) -{ - struct ceph_x_info *xi = ac->private; - int num; - void *p = buf; - int ret; - char *dbuf; - char *ticket_buf; - u8 reply_struct_v; - - dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!dbuf) - return -ENOMEM; - - ret = -ENOMEM; - ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!ticket_buf) - goto out_dbuf; - - ceph_decode_need(&p, end, 1 + sizeof(u32), bad); - reply_struct_v = ceph_decode_8(&p); - if (reply_struct_v != 1) - goto bad; - num = ceph_decode_32(&p); - dout("%d tickets\n", num); - while (num--) { - int type; - u8 tkt_struct_v, blob_struct_v; - struct ceph_x_ticket_handler *th; - void *dp, *dend; - int dlen; - char is_enc; - struct timespec validity; - struct ceph_crypto_key old_key; - void *tp, *tpend; - struct ceph_timespec new_validity; - struct ceph_crypto_key new_session_key; - struct ceph_buffer *new_ticket_blob; - unsigned long new_expires, new_renew_after; - u64 new_secret_id; - - ceph_decode_need(&p, end, sizeof(u32) + 1, bad); - - type = ceph_decode_32(&p); - dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - - tkt_struct_v = ceph_decode_8(&p); - if (tkt_struct_v != 1) - goto bad; - - th = get_ticket_handler(ac, type); - if (IS_ERR(th)) { - ret = PTR_ERR(th); - goto out; - } - - /* blob for me */ - dlen = ceph_x_decrypt(secret, &p, end, dbuf, - TEMP_TICKET_BUF_LEN); - if (dlen <= 0) { - ret = dlen; - goto out; - } - dout(" decrypted %d bytes\n", dlen); - dend = dbuf + dlen; - dp = dbuf; - - tkt_struct_v = ceph_decode_8(&dp); - if (tkt_struct_v != 1) - goto bad; - - memcpy(&old_key, &th->session_key, sizeof(old_key)); - ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); - if (ret) - goto out; - - ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); - ceph_decode_timespec(&validity, &new_validity); - new_expires = get_seconds() + validity.tv_sec; - new_renew_after = new_expires - (validity.tv_sec / 4); - dout(" expires=%lu renew_after=%lu\n", new_expires, - new_renew_after); - - /* ticket blob for service */ - ceph_decode_8_safe(&p, end, is_enc, bad); - tp = ticket_buf; - if (is_enc) { - /* encrypted */ - dout(" encrypted ticket\n"); - dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf, - TEMP_TICKET_BUF_LEN); - if (dlen < 0) { - ret = dlen; - goto out; - } - dlen = ceph_decode_32(&tp); - } else { - /* unencrypted */ - ceph_decode_32_safe(&p, end, dlen, bad); - ceph_decode_need(&p, end, dlen, bad); - ceph_decode_copy(&p, ticket_buf, dlen); - } - tpend = tp + dlen; - dout(" ticket blob is %d bytes\n", dlen); - ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); - blob_struct_v = ceph_decode_8(&tp); - new_secret_id = ceph_decode_64(&tp); - ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); - if (ret) - goto out; - - /* all is well, update our ticket */ - ceph_crypto_key_destroy(&th->session_key); - if (th->ticket_blob) - ceph_buffer_put(th->ticket_blob); - th->session_key = new_session_key; - th->ticket_blob = new_ticket_blob; - th->validity = new_validity; - th->secret_id = new_secret_id; - th->expires = new_expires; - th->renew_after = new_renew_after; - dout(" got ticket service %d (%s) secret_id %lld len %d\n", - type, ceph_entity_type_name(type), th->secret_id, - (int)th->ticket_blob->vec.iov_len); - xi->have_keys |= th->service; - } - - ret = 0; -out: - kfree(ticket_buf); -out_dbuf: - kfree(dbuf); - return ret; - -bad: - ret = -EINVAL; - goto out; -} - -static int ceph_x_build_authorizer(struct ceph_auth_client *ac, - struct ceph_x_ticket_handler *th, - struct ceph_x_authorizer *au) -{ - int maxlen; - struct ceph_x_authorize_a *msg_a; - struct ceph_x_authorize_b msg_b; - void *p, *end; - int ret; - int ticket_blob_len = - (th->ticket_blob ? th->ticket_blob->vec.iov_len : 0); - - dout("build_authorizer for %s %p\n", - ceph_entity_type_name(th->service), au); - - maxlen = sizeof(*msg_a) + sizeof(msg_b) + - ceph_x_encrypt_buflen(ticket_blob_len); - dout(" need len %d\n", maxlen); - if (au->buf && au->buf->alloc_len < maxlen) { - ceph_buffer_put(au->buf); - au->buf = NULL; - } - if (!au->buf) { - au->buf = ceph_buffer_new(maxlen, GFP_NOFS); - if (!au->buf) - return -ENOMEM; - } - au->service = th->service; - - msg_a = au->buf->vec.iov_base; - msg_a->struct_v = 1; - msg_a->global_id = cpu_to_le64(ac->global_id); - msg_a->service_id = cpu_to_le32(th->service); - msg_a->ticket_blob.struct_v = 1; - msg_a->ticket_blob.secret_id = cpu_to_le64(th->secret_id); - msg_a->ticket_blob.blob_len = cpu_to_le32(ticket_blob_len); - if (ticket_blob_len) { - memcpy(msg_a->ticket_blob.blob, th->ticket_blob->vec.iov_base, - th->ticket_blob->vec.iov_len); - } - dout(" th %p secret_id %lld %lld\n", th, th->secret_id, - le64_to_cpu(msg_a->ticket_blob.secret_id)); - - p = msg_a + 1; - p += ticket_blob_len; - end = au->buf->vec.iov_base + au->buf->vec.iov_len; - - get_random_bytes(&au->nonce, sizeof(au->nonce)); - msg_b.struct_v = 1; - msg_b.nonce = cpu_to_le64(au->nonce); - ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b), - p, end - p); - if (ret < 0) - goto out_buf; - p += ret; - au->buf->vec.iov_len = p - au->buf->vec.iov_base; - dout(" built authorizer nonce %llx len %d\n", au->nonce, - (int)au->buf->vec.iov_len); - BUG_ON(au->buf->vec.iov_len > maxlen); - return 0; - -out_buf: - ceph_buffer_put(au->buf); - au->buf = NULL; - return ret; -} - -static int ceph_x_encode_ticket(struct ceph_x_ticket_handler *th, - void **p, void *end) -{ - ceph_decode_need(p, end, 1 + sizeof(u64), bad); - ceph_encode_8(p, 1); - ceph_encode_64(p, th->secret_id); - if (th->ticket_blob) { - const char *buf = th->ticket_blob->vec.iov_base; - u32 len = th->ticket_blob->vec.iov_len; - - ceph_encode_32_safe(p, end, len, bad); - ceph_encode_copy_safe(p, end, buf, len, bad); - } else { - ceph_encode_32_safe(p, end, 0, bad); - } - - return 0; -bad: - return -ERANGE; -} - -static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed) -{ - int want = ac->want_keys; - struct ceph_x_info *xi = ac->private; - int service; - - *pneed = ac->want_keys & ~(xi->have_keys); - - for (service = 1; service <= want; service <<= 1) { - struct ceph_x_ticket_handler *th; - - if (!(ac->want_keys & service)) - continue; - - if (*pneed & service) - continue; - - th = get_ticket_handler(ac, service); - - if (IS_ERR(th)) { - *pneed |= service; - continue; - } - - if (get_seconds() >= th->renew_after) - *pneed |= service; - if (get_seconds() >= th->expires) - xi->have_keys &= ~service; - } -} - - -static int ceph_x_build_request(struct ceph_auth_client *ac, - void *buf, void *end) -{ - struct ceph_x_info *xi = ac->private; - int need; - struct ceph_x_request_header *head = buf; - int ret; - struct ceph_x_ticket_handler *th = - get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH); - - if (IS_ERR(th)) - return PTR_ERR(th); - - ceph_x_validate_tickets(ac, &need); - - dout("build_request want %x have %x need %x\n", - ac->want_keys, xi->have_keys, need); - - if (need & CEPH_ENTITY_TYPE_AUTH) { - struct ceph_x_authenticate *auth = (void *)(head + 1); - void *p = auth + 1; - struct ceph_x_challenge_blob tmp; - char tmp_enc[40]; - u64 *u; - - if (p > end) - return -ERANGE; - - dout(" get_auth_session_key\n"); - head->op = cpu_to_le16(CEPHX_GET_AUTH_SESSION_KEY); - - /* encrypt and hash */ - get_random_bytes(&auth->client_challenge, sizeof(u64)); - tmp.client_challenge = auth->client_challenge; - tmp.server_challenge = cpu_to_le64(xi->server_challenge); - ret = ceph_x_encrypt(&xi->secret, &tmp, sizeof(tmp), - tmp_enc, sizeof(tmp_enc)); - if (ret < 0) - return ret; - - auth->struct_v = 1; - auth->key = 0; - for (u = (u64 *)tmp_enc; u + 1 <= (u64 *)(tmp_enc + ret); u++) - auth->key ^= *(__le64 *)u; - dout(" server_challenge %llx client_challenge %llx key %llx\n", - xi->server_challenge, le64_to_cpu(auth->client_challenge), - le64_to_cpu(auth->key)); - - /* now encode the old ticket if exists */ - ret = ceph_x_encode_ticket(th, &p, end); - if (ret < 0) - return ret; - - return p - buf; - } - - if (need) { - void *p = head + 1; - struct ceph_x_service_ticket_request *req; - - if (p > end) - return -ERANGE; - head->op = cpu_to_le16(CEPHX_GET_PRINCIPAL_SESSION_KEY); - - ret = ceph_x_build_authorizer(ac, th, &xi->auth_authorizer); - if (ret) - return ret; - ceph_encode_copy(&p, xi->auth_authorizer.buf->vec.iov_base, - xi->auth_authorizer.buf->vec.iov_len); - - req = p; - req->keys = cpu_to_le32(need); - p += sizeof(*req); - return p - buf; - } - - return 0; -} - -static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result, - void *buf, void *end) -{ - struct ceph_x_info *xi = ac->private; - struct ceph_x_reply_header *head = buf; - struct ceph_x_ticket_handler *th; - int len = end - buf; - int op; - int ret; - - if (result) - return result; /* XXX hmm? */ - - if (xi->starting) { - /* it's a hello */ - struct ceph_x_server_challenge *sc = buf; - - if (len != sizeof(*sc)) - return -EINVAL; - xi->server_challenge = le64_to_cpu(sc->server_challenge); - dout("handle_reply got server challenge %llx\n", - xi->server_challenge); - xi->starting = false; - xi->have_keys &= ~CEPH_ENTITY_TYPE_AUTH; - return -EAGAIN; - } - - op = le16_to_cpu(head->op); - result = le32_to_cpu(head->result); - dout("handle_reply op %d result %d\n", op, result); - switch (op) { - case CEPHX_GET_AUTH_SESSION_KEY: - /* verify auth key */ - ret = ceph_x_proc_ticket_reply(ac, &xi->secret, - buf + sizeof(*head), end); - break; - - case CEPHX_GET_PRINCIPAL_SESSION_KEY: - th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH); - if (IS_ERR(th)) - return PTR_ERR(th); - ret = ceph_x_proc_ticket_reply(ac, &th->session_key, - buf + sizeof(*head), end); - break; - - default: - return -EINVAL; - } - if (ret) - return ret; - if (ac->want_keys == xi->have_keys) - return 0; - return -EAGAIN; -} - -static int ceph_x_create_authorizer( - struct ceph_auth_client *ac, int peer_type, - struct ceph_authorizer **a, - void **buf, size_t *len, - void **reply_buf, size_t *reply_len) -{ - struct ceph_x_authorizer *au; - struct ceph_x_ticket_handler *th; - int ret; - - th = get_ticket_handler(ac, peer_type); - if (IS_ERR(th)) - return PTR_ERR(th); - - au = kzalloc(sizeof(*au), GFP_NOFS); - if (!au) - return -ENOMEM; - - ret = ceph_x_build_authorizer(ac, th, au); - if (ret) { - kfree(au); - return ret; - } - - *a = (struct ceph_authorizer *)au; - *buf = au->buf->vec.iov_base; - *len = au->buf->vec.iov_len; - *reply_buf = au->reply_buf; - *reply_len = sizeof(au->reply_buf); - return 0; -} - -static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, - struct ceph_authorizer *a, size_t len) -{ - struct ceph_x_authorizer *au = (void *)a; - struct ceph_x_ticket_handler *th; - int ret = 0; - struct ceph_x_authorize_reply reply; - void *p = au->reply_buf; - void *end = p + sizeof(au->reply_buf); - - th = get_ticket_handler(ac, au->service); - if (IS_ERR(th)) - return PTR_ERR(th); - ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply)); - if (ret < 0) - return ret; - if (ret != sizeof(reply)) - return -EPERM; - - if (au->nonce + 1 != le64_to_cpu(reply.nonce_plus_one)) - ret = -EPERM; - else - ret = 0; - dout("verify_authorizer_reply nonce %llx got %llx ret %d\n", - au->nonce, le64_to_cpu(reply.nonce_plus_one), ret); - return ret; -} - -static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - struct ceph_x_authorizer *au = (void *)a; - - ceph_buffer_put(au->buf); - kfree(au); -} - - -static void ceph_x_reset(struct ceph_auth_client *ac) -{ - struct ceph_x_info *xi = ac->private; - - dout("reset\n"); - xi->starting = true; - xi->server_challenge = 0; -} - -static void ceph_x_destroy(struct ceph_auth_client *ac) -{ - struct ceph_x_info *xi = ac->private; - struct rb_node *p; - - dout("ceph_x_destroy %p\n", ac); - ceph_crypto_key_destroy(&xi->secret); - - while ((p = rb_first(&xi->ticket_handlers)) != NULL) { - struct ceph_x_ticket_handler *th = - rb_entry(p, struct ceph_x_ticket_handler, node); - remove_ticket_handler(ac, th); - } - - if (xi->auth_authorizer.buf) - ceph_buffer_put(xi->auth_authorizer.buf); - - kfree(ac->private); - ac->private = NULL; -} - -static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac, - int peer_type) -{ - struct ceph_x_ticket_handler *th; - - th = get_ticket_handler(ac, peer_type); - if (!IS_ERR(th)) - remove_ticket_handler(ac, th); -} - - -static const struct ceph_auth_client_ops ceph_x_ops = { - .name = "x", - .is_authenticated = ceph_x_is_authenticated, - .should_authenticate = ceph_x_should_authenticate, - .build_request = ceph_x_build_request, - .handle_reply = ceph_x_handle_reply, - .create_authorizer = ceph_x_create_authorizer, - .verify_authorizer_reply = ceph_x_verify_authorizer_reply, - .destroy_authorizer = ceph_x_destroy_authorizer, - .invalidate_authorizer = ceph_x_invalidate_authorizer, - .reset = ceph_x_reset, - .destroy = ceph_x_destroy, -}; - - -int ceph_x_init(struct ceph_auth_client *ac) -{ - struct ceph_x_info *xi; - int ret; - - dout("ceph_x_init %p\n", ac); - ret = -ENOMEM; - xi = kzalloc(sizeof(*xi), GFP_NOFS); - if (!xi) - goto out; - - ret = -EINVAL; - if (!ac->secret) { - pr_err("no secret set (for auth_x protocol)\n"); - goto out_nomem; - } - - ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret); - if (ret) - goto out_nomem; - - xi->starting = true; - xi->ticket_handlers = RB_ROOT; - - ac->protocol = CEPH_AUTH_CEPHX; - ac->private = xi; - ac->ops = &ceph_x_ops; - return 0; - -out_nomem: - kfree(xi); -out: - return ret; -} - - diff --git a/fs/ceph/auth_x.h b/fs/ceph/auth_x.h deleted file mode 100644 index ff6f8180e681..000000000000 --- a/fs/ceph/auth_x.h +++ /dev/null @@ -1,49 +0,0 @@ -#ifndef _FS_CEPH_AUTH_X_H -#define _FS_CEPH_AUTH_X_H - -#include - -#include "crypto.h" -#include "auth.h" -#include "auth_x_protocol.h" - -/* - * Handle ticket for a single service. - */ -struct ceph_x_ticket_handler { - struct rb_node node; - unsigned service; - - struct ceph_crypto_key session_key; - struct ceph_timespec validity; - - u64 secret_id; - struct ceph_buffer *ticket_blob; - - unsigned long renew_after, expires; -}; - - -struct ceph_x_authorizer { - struct ceph_buffer *buf; - unsigned service; - u64 nonce; - char reply_buf[128]; /* big enough for encrypted blob */ -}; - -struct ceph_x_info { - struct ceph_crypto_key secret; - - bool starting; - u64 server_challenge; - - unsigned have_keys; - struct rb_root ticket_handlers; - - struct ceph_x_authorizer auth_authorizer; -}; - -extern int ceph_x_init(struct ceph_auth_client *ac); - -#endif - diff --git a/fs/ceph/auth_x_protocol.h b/fs/ceph/auth_x_protocol.h deleted file mode 100644 index 671d30576c4f..000000000000 --- a/fs/ceph/auth_x_protocol.h +++ /dev/null @@ -1,90 +0,0 @@ -#ifndef __FS_CEPH_AUTH_X_PROTOCOL -#define __FS_CEPH_AUTH_X_PROTOCOL - -#define CEPHX_GET_AUTH_SESSION_KEY 0x0100 -#define CEPHX_GET_PRINCIPAL_SESSION_KEY 0x0200 -#define CEPHX_GET_ROTATING_KEY 0x0400 - -/* common bits */ -struct ceph_x_ticket_blob { - __u8 struct_v; - __le64 secret_id; - __le32 blob_len; - char blob[]; -} __attribute__ ((packed)); - - -/* common request/reply headers */ -struct ceph_x_request_header { - __le16 op; -} __attribute__ ((packed)); - -struct ceph_x_reply_header { - __le16 op; - __le32 result; -} __attribute__ ((packed)); - - -/* authenticate handshake */ - -/* initial hello (no reply header) */ -struct ceph_x_server_challenge { - __u8 struct_v; - __le64 server_challenge; -} __attribute__ ((packed)); - -struct ceph_x_authenticate { - __u8 struct_v; - __le64 client_challenge; - __le64 key; - /* ticket blob */ -} __attribute__ ((packed)); - -struct ceph_x_service_ticket_request { - __u8 struct_v; - __le32 keys; -} __attribute__ ((packed)); - -struct ceph_x_challenge_blob { - __le64 server_challenge; - __le64 client_challenge; -} __attribute__ ((packed)); - - - -/* authorize handshake */ - -/* - * The authorizer consists of two pieces: - * a - service id, ticket blob - * b - encrypted with session key - */ -struct ceph_x_authorize_a { - __u8 struct_v; - __le64 global_id; - __le32 service_id; - struct ceph_x_ticket_blob ticket_blob; -} __attribute__ ((packed)); - -struct ceph_x_authorize_b { - __u8 struct_v; - __le64 nonce; -} __attribute__ ((packed)); - -struct ceph_x_authorize_reply { - __u8 struct_v; - __le64 nonce_plus_one; -} __attribute__ ((packed)); - - -/* - * encyption bundle - */ -#define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull - -struct ceph_x_encrypt_header { - __u8 struct_v; - __le64 magic; -} __attribute__ ((packed)); - -#endif diff --git a/fs/ceph/buffer.c b/fs/ceph/buffer.c deleted file mode 100644 index cd39f17021de..000000000000 --- a/fs/ceph/buffer.c +++ /dev/null @@ -1,65 +0,0 @@ - -#include "ceph_debug.h" - -#include - -#include "buffer.h" -#include "decode.h" - -struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) -{ - struct ceph_buffer *b; - - b = kmalloc(sizeof(*b), gfp); - if (!b) - return NULL; - - b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN); - if (b->vec.iov_base) { - b->is_vmalloc = false; - } else { - b->vec.iov_base = __vmalloc(len, gfp, PAGE_KERNEL); - if (!b->vec.iov_base) { - kfree(b); - return NULL; - } - b->is_vmalloc = true; - } - - kref_init(&b->kref); - b->alloc_len = len; - b->vec.iov_len = len; - dout("buffer_new %p\n", b); - return b; -} - -void ceph_buffer_release(struct kref *kref) -{ - struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref); - - dout("buffer_release %p\n", b); - if (b->vec.iov_base) { - if (b->is_vmalloc) - vfree(b->vec.iov_base); - else - kfree(b->vec.iov_base); - } - kfree(b); -} - -int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end) -{ - size_t len; - - ceph_decode_need(p, end, sizeof(u32), bad); - len = ceph_decode_32(p); - dout("decode_buffer len %d\n", (int)len); - ceph_decode_need(p, end, len, bad); - *b = ceph_buffer_new(len, GFP_NOFS); - if (!*b) - return -ENOMEM; - ceph_decode_copy(p, (*b)->vec.iov_base, len); - return 0; -bad: - return -EINVAL; -} diff --git a/fs/ceph/buffer.h b/fs/ceph/buffer.h deleted file mode 100644 index 58d19014068f..000000000000 --- a/fs/ceph/buffer.h +++ /dev/null @@ -1,39 +0,0 @@ -#ifndef __FS_CEPH_BUFFER_H -#define __FS_CEPH_BUFFER_H - -#include -#include -#include -#include -#include - -/* - * a simple reference counted buffer. - * - * use kmalloc for small sizes (<= one page), vmalloc for larger - * sizes. - */ -struct ceph_buffer { - struct kref kref; - struct kvec vec; - size_t alloc_len; - bool is_vmalloc; -}; - -extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp); -extern void ceph_buffer_release(struct kref *kref); - -static inline struct ceph_buffer *ceph_buffer_get(struct ceph_buffer *b) -{ - kref_get(&b->kref); - return b; -} - -static inline void ceph_buffer_put(struct ceph_buffer *b) -{ - kref_put(&b->kref, ceph_buffer_release); -} - -extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end); - -#endif diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 5e9da996a151..3cff67cbb9c0 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -9,8 +9,9 @@ #include #include "super.h" -#include "decode.h" -#include "messenger.h" +#include "mds_client.h" +#include +#include /* * Capability management @@ -287,11 +288,11 @@ void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap) spin_unlock(&mdsc->caps_list_lock); } -void ceph_reservation_status(struct ceph_client *client, +void ceph_reservation_status(struct ceph_fs_client *fsc, int *total, int *avail, int *used, int *reserved, int *min) { - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_mds_client *mdsc = fsc->mdsc; if (total) *total = mdsc->caps_total_count; @@ -399,7 +400,7 @@ static void __insert_cap_node(struct ceph_inode_info *ci, static void __cap_set_timeouts(struct ceph_mds_client *mdsc, struct ceph_inode_info *ci) { - struct ceph_mount_args *ma = mdsc->client->mount_args; + struct ceph_mount_options *ma = mdsc->fsc->mount_options; ci->i_hold_caps_min = round_jiffies(jiffies + ma->caps_wanted_delay_min * HZ); @@ -515,7 +516,7 @@ int ceph_add_cap(struct inode *inode, unsigned seq, unsigned mseq, u64 realmino, int flags, struct ceph_cap_reservation *caps_reservation) { - struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc; + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_cap *new_cap = NULL; struct ceph_cap *cap; @@ -873,7 +874,7 @@ void __ceph_remove_cap(struct ceph_cap *cap) struct ceph_mds_session *session = cap->session; struct ceph_inode_info *ci = cap->ci; struct ceph_mds_client *mdsc = - &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; + ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; int removed = 0; dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); @@ -1210,7 +1211,7 @@ void __ceph_flush_snaps(struct ceph_inode_info *ci, int mds; struct ceph_cap_snap *capsnap; u32 mseq; - struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc; + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_session *session = NULL; /* if session != NULL, we hold session->s_mutex */ u64 next_follows = 0; /* keep track of how far we've gotten through the @@ -1336,7 +1337,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci) void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask) { struct ceph_mds_client *mdsc = - &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; + ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; struct inode *inode = &ci->vfs_inode; int was = ci->i_dirty_caps; int dirty = 0; @@ -1378,7 +1379,7 @@ void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask) static int __mark_caps_flushing(struct inode *inode, struct ceph_mds_session *session) { - struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); int flushing; @@ -1462,8 +1463,8 @@ static int try_nonblocking_invalidate(struct inode *inode) void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session) { - struct ceph_client *client = ceph_inode_to_client(&ci->vfs_inode); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode); + struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = &ci->vfs_inode; struct ceph_cap *cap; int file_wanted, used; @@ -1706,7 +1707,7 @@ ack: static int try_flush_caps(struct inode *inode, struct ceph_mds_session *session, unsigned *flush_tid) { - struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); int unlock_session = session ? 0 : 1; int flushing = 0; @@ -1872,7 +1873,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc) caps_are_flushed(inode, flush_tid)); } else { struct ceph_mds_client *mdsc = - &ceph_sb_to_client(inode->i_sb)->mdsc; + ceph_sb_to_client(inode->i_sb)->mdsc; spin_lock(&inode->i_lock); if (__ceph_caps_dirty(ci)) @@ -2465,7 +2466,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid, __releases(inode->i_lock) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; unsigned seq = le32_to_cpu(m->seq); int dirty = le32_to_cpu(m->dirty); int cleaned = 0; @@ -2713,7 +2714,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, struct ceph_msg *msg) { struct ceph_mds_client *mdsc = session->s_mdsc; - struct super_block *sb = mdsc->client->sb; + struct super_block *sb = mdsc->fsc->sb; struct inode *inode; struct ceph_cap *cap; struct ceph_mds_caps *h; diff --git a/fs/ceph/ceph_debug.h b/fs/ceph/ceph_debug.h deleted file mode 100644 index 1818c2305610..000000000000 --- a/fs/ceph/ceph_debug.h +++ /dev/null @@ -1,37 +0,0 @@ -#ifndef _FS_CEPH_DEBUG_H -#define _FS_CEPH_DEBUG_H - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#ifdef CONFIG_CEPH_FS_PRETTYDEBUG - -/* - * wrap pr_debug to include a filename:lineno prefix on each line. - * this incurs some overhead (kernel size and execution time) due to - * the extra function call at each call site. - */ - -# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) -extern const char *ceph_file_part(const char *s, int len); -# define dout(fmt, ...) \ - pr_debug(" %12.12s:%-4d : " fmt, \ - ceph_file_part(__FILE__, sizeof(__FILE__)), \ - __LINE__, ##__VA_ARGS__) -# else -/* faux printk call just to see any compiler warnings. */ -# define dout(fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ - } while (0) -# endif - -#else - -/* - * or, just wrap pr_debug - */ -# define dout(fmt, ...) pr_debug(" " fmt, ##__VA_ARGS__) - -#endif - -#endif diff --git a/fs/ceph/ceph_frag.c b/fs/ceph/ceph_frag.c index ab6cf35c4091..bdce8b1fbd06 100644 --- a/fs/ceph/ceph_frag.c +++ b/fs/ceph/ceph_frag.c @@ -1,7 +1,8 @@ /* * Ceph 'frag' type */ -#include "types.h" +#include +#include int ceph_frag_compare(__u32 a, __u32 b) { diff --git a/fs/ceph/ceph_frag.h b/fs/ceph/ceph_frag.h deleted file mode 100644 index 5babb8e95352..000000000000 --- a/fs/ceph/ceph_frag.h +++ /dev/null @@ -1,109 +0,0 @@ -#ifndef FS_CEPH_FRAG_H -#define FS_CEPH_FRAG_H - -/* - * "Frags" are a way to describe a subset of a 32-bit number space, - * using a mask and a value to match against that mask. Any given frag - * (subset of the number space) can be partitioned into 2^n sub-frags. - * - * Frags are encoded into a 32-bit word: - * 8 upper bits = "bits" - * 24 lower bits = "value" - * (We could go to 5+27 bits, but who cares.) - * - * We use the _most_ significant bits of the 24 bit value. This makes - * values logically sort. - * - * Unfortunately, because the "bits" field is still in the high bits, we - * can't sort encoded frags numerically. However, it does allow you - * to feed encoded frags as values into frag_contains_value. - */ -static inline __u32 ceph_frag_make(__u32 b, __u32 v) -{ - return (b << 24) | - (v & (0xffffffu << (24-b)) & 0xffffffu); -} -static inline __u32 ceph_frag_bits(__u32 f) -{ - return f >> 24; -} -static inline __u32 ceph_frag_value(__u32 f) -{ - return f & 0xffffffu; -} -static inline __u32 ceph_frag_mask(__u32 f) -{ - return (0xffffffu << (24-ceph_frag_bits(f))) & 0xffffffu; -} -static inline __u32 ceph_frag_mask_shift(__u32 f) -{ - return 24 - ceph_frag_bits(f); -} - -static inline int ceph_frag_contains_value(__u32 f, __u32 v) -{ - return (v & ceph_frag_mask(f)) == ceph_frag_value(f); -} -static inline int ceph_frag_contains_frag(__u32 f, __u32 sub) -{ - /* is sub as specific as us, and contained by us? */ - return ceph_frag_bits(sub) >= ceph_frag_bits(f) && - (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f); -} - -static inline __u32 ceph_frag_parent(__u32 f) -{ - return ceph_frag_make(ceph_frag_bits(f) - 1, - ceph_frag_value(f) & (ceph_frag_mask(f) << 1)); -} -static inline int ceph_frag_is_left_child(__u32 f) -{ - return ceph_frag_bits(f) > 0 && - (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0; -} -static inline int ceph_frag_is_right_child(__u32 f) -{ - return ceph_frag_bits(f) > 0 && - (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1; -} -static inline __u32 ceph_frag_sibling(__u32 f) -{ - return ceph_frag_make(ceph_frag_bits(f), - ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f))); -} -static inline __u32 ceph_frag_left_child(__u32 f) -{ - return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f)); -} -static inline __u32 ceph_frag_right_child(__u32 f) -{ - return ceph_frag_make(ceph_frag_bits(f)+1, - ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f)))); -} -static inline __u32 ceph_frag_make_child(__u32 f, int by, int i) -{ - int newbits = ceph_frag_bits(f) + by; - return ceph_frag_make(newbits, - ceph_frag_value(f) | (i << (24 - newbits))); -} -static inline int ceph_frag_is_leftmost(__u32 f) -{ - return ceph_frag_value(f) == 0; -} -static inline int ceph_frag_is_rightmost(__u32 f) -{ - return ceph_frag_value(f) == ceph_frag_mask(f); -} -static inline __u32 ceph_frag_next(__u32 f) -{ - return ceph_frag_make(ceph_frag_bits(f), - ceph_frag_value(f) + (0x1000000 >> ceph_frag_bits(f))); -} - -/* - * comparator to sort frags logically, as when traversing the - * number space in ascending order... - */ -int ceph_frag_compare(__u32 a, __u32 b); - -#endif diff --git a/fs/ceph/ceph_fs.c b/fs/ceph/ceph_fs.c deleted file mode 100644 index 3ac6cc7c1156..000000000000 --- a/fs/ceph/ceph_fs.c +++ /dev/null @@ -1,72 +0,0 @@ -/* - * Some non-inline ceph helpers - */ -#include "types.h" - -/* - * return true if @layout appears to be valid - */ -int ceph_file_layout_is_valid(const struct ceph_file_layout *layout) -{ - __u32 su = le32_to_cpu(layout->fl_stripe_unit); - __u32 sc = le32_to_cpu(layout->fl_stripe_count); - __u32 os = le32_to_cpu(layout->fl_object_size); - - /* stripe unit, object size must be non-zero, 64k increment */ - if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1))) - return 0; - if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1))) - return 0; - /* object size must be a multiple of stripe unit */ - if (os < su || os % su) - return 0; - /* stripe count must be non-zero */ - if (!sc) - return 0; - return 1; -} - - -int ceph_flags_to_mode(int flags) -{ - int mode; - -#ifdef O_DIRECTORY /* fixme */ - if ((flags & O_DIRECTORY) == O_DIRECTORY) - return CEPH_FILE_MODE_PIN; -#endif - if ((flags & O_APPEND) == O_APPEND) - flags |= O_WRONLY; - - if ((flags & O_ACCMODE) == O_RDWR) - mode = CEPH_FILE_MODE_RDWR; - else if ((flags & O_ACCMODE) == O_WRONLY) - mode = CEPH_FILE_MODE_WR; - else - mode = CEPH_FILE_MODE_RD; - -#ifdef O_LAZY - if (flags & O_LAZY) - mode |= CEPH_FILE_MODE_LAZY; -#endif - - return mode; -} - -int ceph_caps_for_mode(int mode) -{ - int caps = CEPH_CAP_PIN; - - if (mode & CEPH_FILE_MODE_RD) - caps |= CEPH_CAP_FILE_SHARED | - CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE; - if (mode & CEPH_FILE_MODE_WR) - caps |= CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | - CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL | - CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL; - if (mode & CEPH_FILE_MODE_LAZY) - caps |= CEPH_CAP_FILE_LAZYIO; - - return caps; -} diff --git a/fs/ceph/ceph_fs.h b/fs/ceph/ceph_fs.h deleted file mode 100644 index d5619ac86711..000000000000 --- a/fs/ceph/ceph_fs.h +++ /dev/null @@ -1,728 +0,0 @@ -/* - * ceph_fs.h - Ceph constants and data types to share between kernel and - * user space. - * - * Most types in this file are defined as little-endian, and are - * primarily intended to describe data structures that pass over the - * wire or that are stored on disk. - * - * LGPL2 - */ - -#ifndef CEPH_FS_H -#define CEPH_FS_H - -#include "msgr.h" -#include "rados.h" - -/* - * subprotocol versions. when specific messages types or high-level - * protocols change, bump the affected components. we keep rev - * internal cluster protocols separately from the public, - * client-facing protocol. - */ -#define CEPH_OSD_PROTOCOL 8 /* cluster internal */ -#define CEPH_MDS_PROTOCOL 12 /* cluster internal */ -#define CEPH_MON_PROTOCOL 5 /* cluster internal */ -#define CEPH_OSDC_PROTOCOL 24 /* server/client */ -#define CEPH_MDSC_PROTOCOL 32 /* server/client */ -#define CEPH_MONC_PROTOCOL 15 /* server/client */ - - -#define CEPH_INO_ROOT 1 -#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ - -/* arbitrary limit on max # of monitors (cluster of 3 is typical) */ -#define CEPH_MAX_MON 31 - - -/* - * feature bits - */ -#define CEPH_FEATURE_UID (1<<0) -#define CEPH_FEATURE_NOSRCADDR (1<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) -#define CEPH_FEATURE_FLOCK (1<<3) - - -/* - * ceph_file_layout - describe data layout for a file/inode - */ -struct ceph_file_layout { - /* file -> object mapping */ - __le32 fl_stripe_unit; /* stripe unit, in bytes. must be multiple - of page size. */ - __le32 fl_stripe_count; /* over this many objects */ - __le32 fl_object_size; /* until objects are this big, then move to - new objects */ - __le32 fl_cas_hash; /* 0 = none; 1 = sha256 */ - - /* pg -> disk layout */ - __le32 fl_object_stripe_unit; /* for per-object parity, if any */ - - /* object -> pg layout */ - __le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */ - __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ -} __attribute__ ((packed)); - -#define CEPH_MIN_STRIPE_UNIT 65536 - -int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); - - -/* crypto algorithms */ -#define CEPH_CRYPTO_NONE 0x0 -#define CEPH_CRYPTO_AES 0x1 - -#define CEPH_AES_IV "cephsageyudagreg" - -/* security/authentication protocols */ -#define CEPH_AUTH_UNKNOWN 0x0 -#define CEPH_AUTH_NONE 0x1 -#define CEPH_AUTH_CEPHX 0x2 - -#define CEPH_AUTH_UID_DEFAULT ((__u64) -1) - - -/********************************************* - * message layer - */ - -/* - * message types - */ - -/* misc */ -#define CEPH_MSG_SHUTDOWN 1 -#define CEPH_MSG_PING 2 - -/* client <-> monitor */ -#define CEPH_MSG_MON_MAP 4 -#define CEPH_MSG_MON_GET_MAP 5 -#define CEPH_MSG_STATFS 13 -#define CEPH_MSG_STATFS_REPLY 14 -#define CEPH_MSG_MON_SUBSCRIBE 15 -#define CEPH_MSG_MON_SUBSCRIBE_ACK 16 -#define CEPH_MSG_AUTH 17 -#define CEPH_MSG_AUTH_REPLY 18 - -/* client <-> mds */ -#define CEPH_MSG_MDS_MAP 21 - -#define CEPH_MSG_CLIENT_SESSION 22 -#define CEPH_MSG_CLIENT_RECONNECT 23 - -#define CEPH_MSG_CLIENT_REQUEST 24 -#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25 -#define CEPH_MSG_CLIENT_REPLY 26 -#define CEPH_MSG_CLIENT_CAPS 0x310 -#define CEPH_MSG_CLIENT_LEASE 0x311 -#define CEPH_MSG_CLIENT_SNAP 0x312 -#define CEPH_MSG_CLIENT_CAPRELEASE 0x313 - -/* pool ops */ -#define CEPH_MSG_POOLOP_REPLY 48 -#define CEPH_MSG_POOLOP 49 - - -/* osd */ -#define CEPH_MSG_OSD_MAP 41 -#define CEPH_MSG_OSD_OP 42 -#define CEPH_MSG_OSD_OPREPLY 43 - -/* pool operations */ -enum { - POOL_OP_CREATE = 0x01, - POOL_OP_DELETE = 0x02, - POOL_OP_AUID_CHANGE = 0x03, - POOL_OP_CREATE_SNAP = 0x11, - POOL_OP_DELETE_SNAP = 0x12, - POOL_OP_CREATE_UNMANAGED_SNAP = 0x21, - POOL_OP_DELETE_UNMANAGED_SNAP = 0x22, -}; - -struct ceph_mon_request_header { - __le64 have_version; - __le16 session_mon; - __le64 session_mon_tid; -} __attribute__ ((packed)); - -struct ceph_mon_statfs { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; -} __attribute__ ((packed)); - -struct ceph_statfs { - __le64 kb, kb_used, kb_avail; - __le64 num_objects; -} __attribute__ ((packed)); - -struct ceph_mon_statfs_reply { - struct ceph_fsid fsid; - __le64 version; - struct ceph_statfs st; -} __attribute__ ((packed)); - -const char *ceph_pool_op_name(int op); - -struct ceph_mon_poolop { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; - __le32 pool; - __le32 op; - __le64 auid; - __le64 snapid; - __le32 name_len; -} __attribute__ ((packed)); - -struct ceph_mon_poolop_reply { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; - __le32 reply_code; - __le32 epoch; - char has_data; - char data[0]; -} __attribute__ ((packed)); - -struct ceph_mon_unmanaged_snap { - __le64 snapid; -} __attribute__ ((packed)); - -struct ceph_osd_getmap { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; - __le32 start; -} __attribute__ ((packed)); - -struct ceph_mds_getmap { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; -} __attribute__ ((packed)); - -struct ceph_client_mount { - struct ceph_mon_request_header monhdr; -} __attribute__ ((packed)); - -struct ceph_mon_subscribe_item { - __le64 have_version; __le64 have; - __u8 onetime; -} __attribute__ ((packed)); - -struct ceph_mon_subscribe_ack { - __le32 duration; /* seconds */ - struct ceph_fsid fsid; -} __attribute__ ((packed)); - -/* - * mds states - * > 0 -> in - * <= 0 -> out - */ -#define CEPH_MDS_STATE_DNE 0 /* down, does not exist. */ -#define CEPH_MDS_STATE_STOPPED -1 /* down, once existed, but no subtrees. - empty log. */ -#define CEPH_MDS_STATE_BOOT -4 /* up, boot announcement. */ -#define CEPH_MDS_STATE_STANDBY -5 /* up, idle. waiting for assignment. */ -#define CEPH_MDS_STATE_CREATING -6 /* up, creating MDS instance. */ -#define CEPH_MDS_STATE_STARTING -7 /* up, starting previously stopped mds */ -#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */ - -#define CEPH_MDS_STATE_REPLAY 8 /* up, replaying journal. */ -#define CEPH_MDS_STATE_RESOLVE 9 /* up, disambiguating distributed - operations (import, rename, etc.) */ -#define CEPH_MDS_STATE_RECONNECT 10 /* up, reconnect to clients */ -#define CEPH_MDS_STATE_REJOIN 11 /* up, rejoining distributed cache */ -#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */ -#define CEPH_MDS_STATE_ACTIVE 13 /* up, active */ -#define CEPH_MDS_STATE_STOPPING 14 /* up, but exporting metadata */ - -extern const char *ceph_mds_state_name(int s); - - -/* - * metadata lock types. - * - these are bitmasks.. we can compose them - * - they also define the lock ordering by the MDS - * - a few of these are internal to the mds - */ -#define CEPH_LOCK_DVERSION 1 -#define CEPH_LOCK_DN 2 -#define CEPH_LOCK_ISNAP 16 -#define CEPH_LOCK_IVERSION 32 /* mds internal */ -#define CEPH_LOCK_IFILE 64 -#define CEPH_LOCK_IAUTH 128 -#define CEPH_LOCK_ILINK 256 -#define CEPH_LOCK_IDFT 512 /* dir frag tree */ -#define CEPH_LOCK_INEST 1024 /* mds internal */ -#define CEPH_LOCK_IXATTR 2048 -#define CEPH_LOCK_IFLOCK 4096 /* advisory file locks */ -#define CEPH_LOCK_INO 8192 /* immutable inode bits; not a lock */ - -/* client_session ops */ -enum { - CEPH_SESSION_REQUEST_OPEN, - CEPH_SESSION_OPEN, - CEPH_SESSION_REQUEST_CLOSE, - CEPH_SESSION_CLOSE, - CEPH_SESSION_REQUEST_RENEWCAPS, - CEPH_SESSION_RENEWCAPS, - CEPH_SESSION_STALE, - CEPH_SESSION_RECALL_STATE, -}; - -extern const char *ceph_session_op_name(int op); - -struct ceph_mds_session_head { - __le32 op; - __le64 seq; - struct ceph_timespec stamp; - __le32 max_caps, max_leases; -} __attribute__ ((packed)); - -/* client_request */ -/* - * metadata ops. - * & 0x001000 -> write op - * & 0x010000 -> follow symlink (e.g. stat(), not lstat()). - & & 0x100000 -> use weird ino/path trace - */ -#define CEPH_MDS_OP_WRITE 0x001000 -enum { - CEPH_MDS_OP_LOOKUP = 0x00100, - CEPH_MDS_OP_GETATTR = 0x00101, - CEPH_MDS_OP_LOOKUPHASH = 0x00102, - CEPH_MDS_OP_LOOKUPPARENT = 0x00103, - - CEPH_MDS_OP_SETXATTR = 0x01105, - CEPH_MDS_OP_RMXATTR = 0x01106, - CEPH_MDS_OP_SETLAYOUT = 0x01107, - CEPH_MDS_OP_SETATTR = 0x01108, - CEPH_MDS_OP_SETFILELOCK= 0x01109, - CEPH_MDS_OP_GETFILELOCK= 0x00110, - - CEPH_MDS_OP_MKNOD = 0x01201, - CEPH_MDS_OP_LINK = 0x01202, - CEPH_MDS_OP_UNLINK = 0x01203, - CEPH_MDS_OP_RENAME = 0x01204, - CEPH_MDS_OP_MKDIR = 0x01220, - CEPH_MDS_OP_RMDIR = 0x01221, - CEPH_MDS_OP_SYMLINK = 0x01222, - - CEPH_MDS_OP_CREATE = 0x01301, - CEPH_MDS_OP_OPEN = 0x00302, - CEPH_MDS_OP_READDIR = 0x00305, - - CEPH_MDS_OP_LOOKUPSNAP = 0x00400, - CEPH_MDS_OP_MKSNAP = 0x01400, - CEPH_MDS_OP_RMSNAP = 0x01401, - CEPH_MDS_OP_LSSNAP = 0x00402, -}; - -extern const char *ceph_mds_op_name(int op); - - -#define CEPH_SETATTR_MODE 1 -#define CEPH_SETATTR_UID 2 -#define CEPH_SETATTR_GID 4 -#define CEPH_SETATTR_MTIME 8 -#define CEPH_SETATTR_ATIME 16 -#define CEPH_SETATTR_SIZE 32 -#define CEPH_SETATTR_CTIME 64 - -union ceph_mds_request_args { - struct { - __le32 mask; /* CEPH_CAP_* */ - } __attribute__ ((packed)) getattr; - struct { - __le32 mode; - __le32 uid; - __le32 gid; - struct ceph_timespec mtime; - struct ceph_timespec atime; - __le64 size, old_size; /* old_size needed by truncate */ - __le32 mask; /* CEPH_SETATTR_* */ - } __attribute__ ((packed)) setattr; - struct { - __le32 frag; /* which dir fragment */ - __le32 max_entries; /* how many dentries to grab */ - __le32 max_bytes; - } __attribute__ ((packed)) readdir; - struct { - __le32 mode; - __le32 rdev; - } __attribute__ ((packed)) mknod; - struct { - __le32 mode; - } __attribute__ ((packed)) mkdir; - struct { - __le32 flags; - __le32 mode; - __le32 stripe_unit; /* layout for newly created file */ - __le32 stripe_count; /* ... */ - __le32 object_size; - __le32 file_replication; - __le32 preferred; - } __attribute__ ((packed)) open; - struct { - __le32 flags; - } __attribute__ ((packed)) setxattr; - struct { - struct ceph_file_layout layout; - } __attribute__ ((packed)) setlayout; - struct { - __u8 rule; /* currently fcntl or flock */ - __u8 type; /* shared, exclusive, remove*/ - __le64 pid; /* process id requesting the lock */ - __le64 pid_namespace; - __le64 start; /* initial location to lock */ - __le64 length; /* num bytes to lock from start */ - __u8 wait; /* will caller wait for lock to become available? */ - } __attribute__ ((packed)) filelock_change; -} __attribute__ ((packed)); - -#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ -#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */ - -struct ceph_mds_request_head { - __le64 oldest_client_tid; - __le32 mdsmap_epoch; /* on client */ - __le32 flags; /* CEPH_MDS_FLAG_* */ - __u8 num_retry, num_fwd; /* count retry, fwd attempts */ - __le16 num_releases; /* # include cap/lease release records */ - __le32 op; /* mds op code */ - __le32 caller_uid, caller_gid; - __le64 ino; /* use this ino for openc, mkdir, mknod, - etc. (if replaying) */ - union ceph_mds_request_args args; -} __attribute__ ((packed)); - -/* cap/lease release record */ -struct ceph_mds_request_release { - __le64 ino, cap_id; /* ino and unique cap id */ - __le32 caps, wanted; /* new issued, wanted */ - __le32 seq, issue_seq, mseq; - __le32 dname_seq; /* if releasing a dentry lease, a */ - __le32 dname_len; /* string follows. */ -} __attribute__ ((packed)); - -/* client reply */ -struct ceph_mds_reply_head { - __le32 op; - __le32 result; - __le32 mdsmap_epoch; - __u8 safe; /* true if committed to disk */ - __u8 is_dentry, is_target; /* true if dentry, target inode records - are included with reply */ -} __attribute__ ((packed)); - -/* one for each node split */ -struct ceph_frag_tree_split { - __le32 frag; /* this frag splits... */ - __le32 by; /* ...by this many bits */ -} __attribute__ ((packed)); - -struct ceph_frag_tree_head { - __le32 nsplits; /* num ceph_frag_tree_split records */ - struct ceph_frag_tree_split splits[]; -} __attribute__ ((packed)); - -/* capability issue, for bundling with mds reply */ -struct ceph_mds_reply_cap { - __le32 caps, wanted; /* caps issued, wanted */ - __le64 cap_id; - __le32 seq, mseq; - __le64 realm; /* snap realm */ - __u8 flags; /* CEPH_CAP_FLAG_* */ -} __attribute__ ((packed)); - -#define CEPH_CAP_FLAG_AUTH 1 /* cap is issued by auth mds */ - -/* inode record, for bundling with mds reply */ -struct ceph_mds_reply_inode { - __le64 ino; - __le64 snapid; - __le32 rdev; - __le64 version; /* inode version */ - __le64 xattr_version; /* version for xattr blob */ - struct ceph_mds_reply_cap cap; /* caps issued for this inode */ - struct ceph_file_layout layout; - struct ceph_timespec ctime, mtime, atime; - __le32 time_warp_seq; - __le64 size, max_size, truncate_size; - __le32 truncate_seq; - __le32 mode, uid, gid; - __le32 nlink; - __le64 files, subdirs, rbytes, rfiles, rsubdirs; /* dir stats */ - struct ceph_timespec rctime; - struct ceph_frag_tree_head fragtree; /* (must be at end of struct) */ -} __attribute__ ((packed)); -/* followed by frag array, then symlink string, then xattr blob */ - -/* reply_lease follows dname, and reply_inode */ -struct ceph_mds_reply_lease { - __le16 mask; /* lease type(s) */ - __le32 duration_ms; /* lease duration */ - __le32 seq; -} __attribute__ ((packed)); - -struct ceph_mds_reply_dirfrag { - __le32 frag; /* fragment */ - __le32 auth; /* auth mds, if this is a delegation point */ - __le32 ndist; /* number of mds' this is replicated on */ - __le32 dist[]; -} __attribute__ ((packed)); - -#define CEPH_LOCK_FCNTL 1 -#define CEPH_LOCK_FLOCK 2 - -#define CEPH_LOCK_SHARED 1 -#define CEPH_LOCK_EXCL 2 -#define CEPH_LOCK_UNLOCK 4 - -struct ceph_filelock { - __le64 start;/* file offset to start lock at */ - __le64 length; /* num bytes to lock; 0 for all following start */ - __le64 client; /* which client holds the lock */ - __le64 pid; /* process id holding the lock on the client */ - __le64 pid_namespace; - __u8 type; /* shared lock, exclusive lock, or unlock */ -} __attribute__ ((packed)); - - -/* file access modes */ -#define CEPH_FILE_MODE_PIN 0 -#define CEPH_FILE_MODE_RD 1 -#define CEPH_FILE_MODE_WR 2 -#define CEPH_FILE_MODE_RDWR 3 /* RD | WR */ -#define CEPH_FILE_MODE_LAZY 4 /* lazy io */ -#define CEPH_FILE_MODE_NUM 8 /* bc these are bit fields.. mostly */ - -int ceph_flags_to_mode(int flags); - - -/* capability bits */ -#define CEPH_CAP_PIN 1 /* no specific capabilities beyond the pin */ - -/* generic cap bits */ -#define CEPH_CAP_GSHARED 1 /* client can reads */ -#define CEPH_CAP_GEXCL 2 /* client can read and update */ -#define CEPH_CAP_GCACHE 4 /* (file) client can cache reads */ -#define CEPH_CAP_GRD 8 /* (file) client can read */ -#define CEPH_CAP_GWR 16 /* (file) client can write */ -#define CEPH_CAP_GBUFFER 32 /* (file) client can buffer writes */ -#define CEPH_CAP_GWREXTEND 64 /* (file) client can extend EOF */ -#define CEPH_CAP_GLAZYIO 128 /* (file) client can perform lazy io */ - -/* per-lock shift */ -#define CEPH_CAP_SAUTH 2 -#define CEPH_CAP_SLINK 4 -#define CEPH_CAP_SXATTR 6 -#define CEPH_CAP_SFILE 8 -#define CEPH_CAP_SFLOCK 20 - -#define CEPH_CAP_BITS 22 - -/* composed values */ -#define CEPH_CAP_AUTH_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SAUTH) -#define CEPH_CAP_AUTH_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SAUTH) -#define CEPH_CAP_LINK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SLINK) -#define CEPH_CAP_LINK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SLINK) -#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SXATTR) -#define CEPH_CAP_XATTR_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SXATTR) -#define CEPH_CAP_FILE(x) (x << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_CACHE (CEPH_CAP_GCACHE << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_RD (CEPH_CAP_GRD << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_WR (CEPH_CAP_GWR << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_BUFFER (CEPH_CAP_GBUFFER << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE) -#define CEPH_CAP_FILE_LAZYIO (CEPH_CAP_GLAZYIO << CEPH_CAP_SFILE) -#define CEPH_CAP_FLOCK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFLOCK) -#define CEPH_CAP_FLOCK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFLOCK) - - -/* cap masks (for getattr) */ -#define CEPH_STAT_CAP_INODE CEPH_CAP_PIN -#define CEPH_STAT_CAP_TYPE CEPH_CAP_PIN /* mode >> 12 */ -#define CEPH_STAT_CAP_SYMLINK CEPH_CAP_PIN -#define CEPH_STAT_CAP_UID CEPH_CAP_AUTH_SHARED -#define CEPH_STAT_CAP_GID CEPH_CAP_AUTH_SHARED -#define CEPH_STAT_CAP_MODE CEPH_CAP_AUTH_SHARED -#define CEPH_STAT_CAP_NLINK CEPH_CAP_LINK_SHARED -#define CEPH_STAT_CAP_LAYOUT CEPH_CAP_FILE_SHARED -#define CEPH_STAT_CAP_MTIME CEPH_CAP_FILE_SHARED -#define CEPH_STAT_CAP_SIZE CEPH_CAP_FILE_SHARED -#define CEPH_STAT_CAP_ATIME CEPH_CAP_FILE_SHARED /* fixme */ -#define CEPH_STAT_CAP_XATTR CEPH_CAP_XATTR_SHARED -#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN | \ - CEPH_CAP_AUTH_SHARED | \ - CEPH_CAP_LINK_SHARED | \ - CEPH_CAP_FILE_SHARED | \ - CEPH_CAP_XATTR_SHARED) - -#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \ - CEPH_CAP_LINK_SHARED | \ - CEPH_CAP_XATTR_SHARED | \ - CEPH_CAP_FILE_SHARED) -#define CEPH_CAP_ANY_RD (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD | \ - CEPH_CAP_FILE_CACHE) - -#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL | \ - CEPH_CAP_LINK_EXCL | \ - CEPH_CAP_XATTR_EXCL | \ - CEPH_CAP_FILE_EXCL) -#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | \ - CEPH_CAP_FILE_EXCL) -#define CEPH_CAP_ANY_WR (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR) -#define CEPH_CAP_ANY (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \ - CEPH_CAP_ANY_FILE_WR | CEPH_CAP_FILE_LAZYIO | \ - CEPH_CAP_PIN) - -#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \ - CEPH_LOCK_IXATTR) - -int ceph_caps_for_mode(int mode); - -enum { - CEPH_CAP_OP_GRANT, /* mds->client grant */ - CEPH_CAP_OP_REVOKE, /* mds->client revoke */ - CEPH_CAP_OP_TRUNC, /* mds->client trunc notify */ - CEPH_CAP_OP_EXPORT, /* mds has exported the cap */ - CEPH_CAP_OP_IMPORT, /* mds has imported the cap */ - CEPH_CAP_OP_UPDATE, /* client->mds update */ - CEPH_CAP_OP_DROP, /* client->mds drop cap bits */ - CEPH_CAP_OP_FLUSH, /* client->mds cap writeback */ - CEPH_CAP_OP_FLUSH_ACK, /* mds->client flushed */ - CEPH_CAP_OP_FLUSHSNAP, /* client->mds flush snapped metadata */ - CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed snapped metadata */ - CEPH_CAP_OP_RELEASE, /* client->mds release (clean) cap */ - CEPH_CAP_OP_RENEW, /* client->mds renewal request */ -}; - -extern const char *ceph_cap_op_name(int op); - -/* - * caps message, used for capability callbacks, acks, requests, etc. - */ -struct ceph_mds_caps { - __le32 op; /* CEPH_CAP_OP_* */ - __le64 ino, realm; - __le64 cap_id; - __le32 seq, issue_seq; - __le32 caps, wanted, dirty; /* latest issued/wanted/dirty */ - __le32 migrate_seq; - __le64 snap_follows; - __le32 snap_trace_len; - - /* authlock */ - __le32 uid, gid, mode; - - /* linklock */ - __le32 nlink; - - /* xattrlock */ - __le32 xattr_len; - __le64 xattr_version; - - /* filelock */ - __le64 size, max_size, truncate_size; - __le32 truncate_seq; - struct ceph_timespec mtime, atime, ctime; - struct ceph_file_layout layout; - __le32 time_warp_seq; -} __attribute__ ((packed)); - -/* cap release msg head */ -struct ceph_mds_cap_release { - __le32 num; /* number of cap_items that follow */ -} __attribute__ ((packed)); - -struct ceph_mds_cap_item { - __le64 ino; - __le64 cap_id; - __le32 migrate_seq, seq; -} __attribute__ ((packed)); - -#define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */ -#define CEPH_MDS_LEASE_RELEASE 2 /* client -> mds */ -#define CEPH_MDS_LEASE_RENEW 3 /* client <-> mds */ -#define CEPH_MDS_LEASE_REVOKE_ACK 4 /* client -> mds */ - -extern const char *ceph_lease_op_name(int o); - -/* lease msg header */ -struct ceph_mds_lease { - __u8 action; /* CEPH_MDS_LEASE_* */ - __le16 mask; /* which lease */ - __le64 ino; - __le64 first, last; /* snap range */ - __le32 seq; - __le32 duration_ms; /* duration of renewal */ -} __attribute__ ((packed)); -/* followed by a __le32+string for dname */ - -/* client reconnect */ -struct ceph_mds_cap_reconnect { - __le64 cap_id; - __le32 wanted; - __le32 issued; - __le64 snaprealm; - __le64 pathbase; /* base ino for our path to this ino */ - __le32 flock_len; /* size of flock state blob, if any */ -} __attribute__ ((packed)); -/* followed by flock blob */ - -struct ceph_mds_cap_reconnect_v1 { - __le64 cap_id; - __le32 wanted; - __le32 issued; - __le64 size; - struct ceph_timespec mtime, atime; - __le64 snaprealm; - __le64 pathbase; /* base ino for our path to this ino */ -} __attribute__ ((packed)); - -struct ceph_mds_snaprealm_reconnect { - __le64 ino; /* snap realm base */ - __le64 seq; /* snap seq for this snap realm */ - __le64 parent; /* parent realm */ -} __attribute__ ((packed)); - -/* - * snaps - */ -enum { - CEPH_SNAP_OP_UPDATE, /* CREATE or DESTROY */ - CEPH_SNAP_OP_CREATE, - CEPH_SNAP_OP_DESTROY, - CEPH_SNAP_OP_SPLIT, -}; - -extern const char *ceph_snap_op_name(int o); - -/* snap msg header */ -struct ceph_mds_snap_head { - __le32 op; /* CEPH_SNAP_OP_* */ - __le64 split; /* ino to split off, if any */ - __le32 num_split_inos; /* # inos belonging to new child realm */ - __le32 num_split_realms; /* # child realms udner new child realm */ - __le32 trace_len; /* size of snap trace blob */ -} __attribute__ ((packed)); -/* followed by split ino list, then split realms, then the trace blob */ - -/* - * encode info about a snaprealm, as viewed by a client - */ -struct ceph_mds_snap_realm { - __le64 ino; /* ino */ - __le64 created; /* snap: when created */ - __le64 parent; /* ino: parent realm */ - __le64 parent_since; /* snap: same parent since */ - __le64 seq; /* snap: version */ - __le32 num_snaps; - __le32 num_prior_parent_snaps; -} __attribute__ ((packed)); -/* followed by my snap list, then prior parent snap list */ - -#endif diff --git a/fs/ceph/ceph_hash.c b/fs/ceph/ceph_hash.c deleted file mode 100644 index bd570015d147..000000000000 --- a/fs/ceph/ceph_hash.c +++ /dev/null @@ -1,118 +0,0 @@ - -#include "types.h" - -/* - * Robert Jenkin's hash function. - * http://burtleburtle.net/bob/hash/evahash.html - * This is in the public domain. - */ -#define mix(a, b, c) \ - do { \ - a = a - b; a = a - c; a = a ^ (c >> 13); \ - b = b - c; b = b - a; b = b ^ (a << 8); \ - c = c - a; c = c - b; c = c ^ (b >> 13); \ - a = a - b; a = a - c; a = a ^ (c >> 12); \ - b = b - c; b = b - a; b = b ^ (a << 16); \ - c = c - a; c = c - b; c = c ^ (b >> 5); \ - a = a - b; a = a - c; a = a ^ (c >> 3); \ - b = b - c; b = b - a; b = b ^ (a << 10); \ - c = c - a; c = c - b; c = c ^ (b >> 15); \ - } while (0) - -unsigned ceph_str_hash_rjenkins(const char *str, unsigned length) -{ - const unsigned char *k = (const unsigned char *)str; - __u32 a, b, c; /* the internal state */ - __u32 len; /* how many key bytes still need mixing */ - - /* Set up the internal state */ - len = length; - a = 0x9e3779b9; /* the golden ratio; an arbitrary value */ - b = a; - c = 0; /* variable initialization of internal state */ - - /* handle most of the key */ - while (len >= 12) { - a = a + (k[0] + ((__u32)k[1] << 8) + ((__u32)k[2] << 16) + - ((__u32)k[3] << 24)); - b = b + (k[4] + ((__u32)k[5] << 8) + ((__u32)k[6] << 16) + - ((__u32)k[7] << 24)); - c = c + (k[8] + ((__u32)k[9] << 8) + ((__u32)k[10] << 16) + - ((__u32)k[11] << 24)); - mix(a, b, c); - k = k + 12; - len = len - 12; - } - - /* handle the last 11 bytes */ - c = c + length; - switch (len) { /* all the case statements fall through */ - case 11: - c = c + ((__u32)k[10] << 24); - case 10: - c = c + ((__u32)k[9] << 16); - case 9: - c = c + ((__u32)k[8] << 8); - /* the first byte of c is reserved for the length */ - case 8: - b = b + ((__u32)k[7] << 24); - case 7: - b = b + ((__u32)k[6] << 16); - case 6: - b = b + ((__u32)k[5] << 8); - case 5: - b = b + k[4]; - case 4: - a = a + ((__u32)k[3] << 24); - case 3: - a = a + ((__u32)k[2] << 16); - case 2: - a = a + ((__u32)k[1] << 8); - case 1: - a = a + k[0]; - /* case 0: nothing left to add */ - } - mix(a, b, c); - - return c; -} - -/* - * linux dcache hash - */ -unsigned ceph_str_hash_linux(const char *str, unsigned length) -{ - unsigned long hash = 0; - unsigned char c; - - while (length--) { - c = *str++; - hash = (hash + (c << 4) + (c >> 4)) * 11; - } - return hash; -} - - -unsigned ceph_str_hash(int type, const char *s, unsigned len) -{ - switch (type) { - case CEPH_STR_HASH_LINUX: - return ceph_str_hash_linux(s, len); - case CEPH_STR_HASH_RJENKINS: - return ceph_str_hash_rjenkins(s, len); - default: - return -1; - } -} - -const char *ceph_str_hash_name(int type) -{ - switch (type) { - case CEPH_STR_HASH_LINUX: - return "linux"; - case CEPH_STR_HASH_RJENKINS: - return "rjenkins"; - default: - return "unknown"; - } -} diff --git a/fs/ceph/ceph_hash.h b/fs/ceph/ceph_hash.h deleted file mode 100644 index d099c3f90236..000000000000 --- a/fs/ceph/ceph_hash.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef FS_CEPH_HASH_H -#define FS_CEPH_HASH_H - -#define CEPH_STR_HASH_LINUX 0x1 /* linux dcache hash */ -#define CEPH_STR_HASH_RJENKINS 0x2 /* robert jenkins' */ - -extern unsigned ceph_str_hash_linux(const char *s, unsigned len); -extern unsigned ceph_str_hash_rjenkins(const char *s, unsigned len); - -extern unsigned ceph_str_hash(int type, const char *s, unsigned len); -extern const char *ceph_str_hash_name(int type); - -#endif diff --git a/fs/ceph/ceph_strings.c b/fs/ceph/ceph_strings.c deleted file mode 100644 index c6179d3a26a2..000000000000 --- a/fs/ceph/ceph_strings.c +++ /dev/null @@ -1,193 +0,0 @@ -/* - * Ceph string constants - */ -#include "types.h" - -const char *ceph_entity_type_name(int type) -{ - switch (type) { - case CEPH_ENTITY_TYPE_MDS: return "mds"; - case CEPH_ENTITY_TYPE_OSD: return "osd"; - case CEPH_ENTITY_TYPE_MON: return "mon"; - case CEPH_ENTITY_TYPE_CLIENT: return "client"; - case CEPH_ENTITY_TYPE_AUTH: return "auth"; - default: return "unknown"; - } -} - -const char *ceph_osd_op_name(int op) -{ - switch (op) { - case CEPH_OSD_OP_READ: return "read"; - case CEPH_OSD_OP_STAT: return "stat"; - - case CEPH_OSD_OP_MASKTRUNC: return "masktrunc"; - - case CEPH_OSD_OP_WRITE: return "write"; - case CEPH_OSD_OP_DELETE: return "delete"; - case CEPH_OSD_OP_TRUNCATE: return "truncate"; - case CEPH_OSD_OP_ZERO: return "zero"; - case CEPH_OSD_OP_WRITEFULL: return "writefull"; - case CEPH_OSD_OP_ROLLBACK: return "rollback"; - - case CEPH_OSD_OP_APPEND: return "append"; - case CEPH_OSD_OP_STARTSYNC: return "startsync"; - case CEPH_OSD_OP_SETTRUNC: return "settrunc"; - case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc"; - - case CEPH_OSD_OP_TMAPUP: return "tmapup"; - case CEPH_OSD_OP_TMAPGET: return "tmapget"; - case CEPH_OSD_OP_TMAPPUT: return "tmapput"; - - case CEPH_OSD_OP_GETXATTR: return "getxattr"; - case CEPH_OSD_OP_GETXATTRS: return "getxattrs"; - case CEPH_OSD_OP_SETXATTR: return "setxattr"; - case CEPH_OSD_OP_SETXATTRS: return "setxattrs"; - case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs"; - case CEPH_OSD_OP_RMXATTR: return "rmxattr"; - case CEPH_OSD_OP_CMPXATTR: return "cmpxattr"; - - case CEPH_OSD_OP_PULL: return "pull"; - case CEPH_OSD_OP_PUSH: return "push"; - case CEPH_OSD_OP_BALANCEREADS: return "balance-reads"; - case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads"; - case CEPH_OSD_OP_SCRUB: return "scrub"; - - case CEPH_OSD_OP_WRLOCK: return "wrlock"; - case CEPH_OSD_OP_WRUNLOCK: return "wrunlock"; - case CEPH_OSD_OP_RDLOCK: return "rdlock"; - case CEPH_OSD_OP_RDUNLOCK: return "rdunlock"; - case CEPH_OSD_OP_UPLOCK: return "uplock"; - case CEPH_OSD_OP_DNLOCK: return "dnlock"; - - case CEPH_OSD_OP_CALL: return "call"; - - case CEPH_OSD_OP_PGLS: return "pgls"; - } - return "???"; -} - -const char *ceph_mds_state_name(int s) -{ - switch (s) { - /* down and out */ - case CEPH_MDS_STATE_DNE: return "down:dne"; - case CEPH_MDS_STATE_STOPPED: return "down:stopped"; - /* up and out */ - case CEPH_MDS_STATE_BOOT: return "up:boot"; - case CEPH_MDS_STATE_STANDBY: return "up:standby"; - case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay"; - case CEPH_MDS_STATE_CREATING: return "up:creating"; - case CEPH_MDS_STATE_STARTING: return "up:starting"; - /* up and in */ - case CEPH_MDS_STATE_REPLAY: return "up:replay"; - case CEPH_MDS_STATE_RESOLVE: return "up:resolve"; - case CEPH_MDS_STATE_RECONNECT: return "up:reconnect"; - case CEPH_MDS_STATE_REJOIN: return "up:rejoin"; - case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay"; - case CEPH_MDS_STATE_ACTIVE: return "up:active"; - case CEPH_MDS_STATE_STOPPING: return "up:stopping"; - } - return "???"; -} - -const char *ceph_session_op_name(int op) -{ - switch (op) { - case CEPH_SESSION_REQUEST_OPEN: return "request_open"; - case CEPH_SESSION_OPEN: return "open"; - case CEPH_SESSION_REQUEST_CLOSE: return "request_close"; - case CEPH_SESSION_CLOSE: return "close"; - case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps"; - case CEPH_SESSION_RENEWCAPS: return "renewcaps"; - case CEPH_SESSION_STALE: return "stale"; - case CEPH_SESSION_RECALL_STATE: return "recall_state"; - } - return "???"; -} - -const char *ceph_mds_op_name(int op) -{ - switch (op) { - case CEPH_MDS_OP_LOOKUP: return "lookup"; - case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash"; - case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent"; - case CEPH_MDS_OP_GETATTR: return "getattr"; - case CEPH_MDS_OP_SETXATTR: return "setxattr"; - case CEPH_MDS_OP_SETATTR: return "setattr"; - case CEPH_MDS_OP_RMXATTR: return "rmxattr"; - case CEPH_MDS_OP_READDIR: return "readdir"; - case CEPH_MDS_OP_MKNOD: return "mknod"; - case CEPH_MDS_OP_LINK: return "link"; - case CEPH_MDS_OP_UNLINK: return "unlink"; - case CEPH_MDS_OP_RENAME: return "rename"; - case CEPH_MDS_OP_MKDIR: return "mkdir"; - case CEPH_MDS_OP_RMDIR: return "rmdir"; - case CEPH_MDS_OP_SYMLINK: return "symlink"; - case CEPH_MDS_OP_CREATE: return "create"; - case CEPH_MDS_OP_OPEN: return "open"; - case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap"; - case CEPH_MDS_OP_LSSNAP: return "lssnap"; - case CEPH_MDS_OP_MKSNAP: return "mksnap"; - case CEPH_MDS_OP_RMSNAP: return "rmsnap"; - case CEPH_MDS_OP_SETFILELOCK: return "setfilelock"; - case CEPH_MDS_OP_GETFILELOCK: return "getfilelock"; - } - return "???"; -} - -const char *ceph_cap_op_name(int op) -{ - switch (op) { - case CEPH_CAP_OP_GRANT: return "grant"; - case CEPH_CAP_OP_REVOKE: return "revoke"; - case CEPH_CAP_OP_TRUNC: return "trunc"; - case CEPH_CAP_OP_EXPORT: return "export"; - case CEPH_CAP_OP_IMPORT: return "import"; - case CEPH_CAP_OP_UPDATE: return "update"; - case CEPH_CAP_OP_DROP: return "drop"; - case CEPH_CAP_OP_FLUSH: return "flush"; - case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack"; - case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap"; - case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack"; - case CEPH_CAP_OP_RELEASE: return "release"; - case CEPH_CAP_OP_RENEW: return "renew"; - } - return "???"; -} - -const char *ceph_lease_op_name(int o) -{ - switch (o) { - case CEPH_MDS_LEASE_REVOKE: return "revoke"; - case CEPH_MDS_LEASE_RELEASE: return "release"; - case CEPH_MDS_LEASE_RENEW: return "renew"; - case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack"; - } - return "???"; -} - -const char *ceph_snap_op_name(int o) -{ - switch (o) { - case CEPH_SNAP_OP_UPDATE: return "update"; - case CEPH_SNAP_OP_CREATE: return "create"; - case CEPH_SNAP_OP_DESTROY: return "destroy"; - case CEPH_SNAP_OP_SPLIT: return "split"; - } - return "???"; -} - -const char *ceph_pool_op_name(int op) -{ - switch (op) { - case POOL_OP_CREATE: return "create"; - case POOL_OP_DELETE: return "delete"; - case POOL_OP_AUID_CHANGE: return "auid change"; - case POOL_OP_CREATE_SNAP: return "create snap"; - case POOL_OP_DELETE_SNAP: return "delete snap"; - case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap"; - case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap"; - } - return "???"; -} diff --git a/fs/ceph/crush/crush.c b/fs/ceph/crush/crush.c deleted file mode 100644 index fabd302e5779..000000000000 --- a/fs/ceph/crush/crush.c +++ /dev/null @@ -1,151 +0,0 @@ - -#ifdef __KERNEL__ -# include -#else -# include -# include -# define kfree(x) do { if (x) free(x); } while (0) -# define BUG_ON(x) assert(!(x)) -#endif - -#include "crush.h" - -const char *crush_bucket_alg_name(int alg) -{ - switch (alg) { - case CRUSH_BUCKET_UNIFORM: return "uniform"; - case CRUSH_BUCKET_LIST: return "list"; - case CRUSH_BUCKET_TREE: return "tree"; - case CRUSH_BUCKET_STRAW: return "straw"; - default: return "unknown"; - } -} - -/** - * crush_get_bucket_item_weight - Get weight of an item in given bucket - * @b: bucket pointer - * @p: item index in bucket - */ -int crush_get_bucket_item_weight(struct crush_bucket *b, int p) -{ - if (p >= b->size) - return 0; - - switch (b->alg) { - case CRUSH_BUCKET_UNIFORM: - return ((struct crush_bucket_uniform *)b)->item_weight; - case CRUSH_BUCKET_LIST: - return ((struct crush_bucket_list *)b)->item_weights[p]; - case CRUSH_BUCKET_TREE: - if (p & 1) - return ((struct crush_bucket_tree *)b)->node_weights[p]; - return 0; - case CRUSH_BUCKET_STRAW: - return ((struct crush_bucket_straw *)b)->item_weights[p]; - } - return 0; -} - -/** - * crush_calc_parents - Calculate parent vectors for the given crush map. - * @map: crush_map pointer - */ -void crush_calc_parents(struct crush_map *map) -{ - int i, b, c; - - for (b = 0; b < map->max_buckets; b++) { - if (map->buckets[b] == NULL) - continue; - for (i = 0; i < map->buckets[b]->size; i++) { - c = map->buckets[b]->items[i]; - BUG_ON(c >= map->max_devices || - c < -map->max_buckets); - if (c >= 0) - map->device_parents[c] = map->buckets[b]->id; - else - map->bucket_parents[-1-c] = map->buckets[b]->id; - } - } -} - -void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b) -{ - kfree(b->h.perm); - kfree(b->h.items); - kfree(b); -} - -void crush_destroy_bucket_list(struct crush_bucket_list *b) -{ - kfree(b->item_weights); - kfree(b->sum_weights); - kfree(b->h.perm); - kfree(b->h.items); - kfree(b); -} - -void crush_destroy_bucket_tree(struct crush_bucket_tree *b) -{ - kfree(b->node_weights); - kfree(b); -} - -void crush_destroy_bucket_straw(struct crush_bucket_straw *b) -{ - kfree(b->straws); - kfree(b->item_weights); - kfree(b->h.perm); - kfree(b->h.items); - kfree(b); -} - -void crush_destroy_bucket(struct crush_bucket *b) -{ - switch (b->alg) { - case CRUSH_BUCKET_UNIFORM: - crush_destroy_bucket_uniform((struct crush_bucket_uniform *)b); - break; - case CRUSH_BUCKET_LIST: - crush_destroy_bucket_list((struct crush_bucket_list *)b); - break; - case CRUSH_BUCKET_TREE: - crush_destroy_bucket_tree((struct crush_bucket_tree *)b); - break; - case CRUSH_BUCKET_STRAW: - crush_destroy_bucket_straw((struct crush_bucket_straw *)b); - break; - } -} - -/** - * crush_destroy - Destroy a crush_map - * @map: crush_map pointer - */ -void crush_destroy(struct crush_map *map) -{ - int b; - - /* buckets */ - if (map->buckets) { - for (b = 0; b < map->max_buckets; b++) { - if (map->buckets[b] == NULL) - continue; - crush_destroy_bucket(map->buckets[b]); - } - kfree(map->buckets); - } - - /* rules */ - if (map->rules) { - for (b = 0; b < map->max_rules; b++) - kfree(map->rules[b]); - kfree(map->rules); - } - - kfree(map->bucket_parents); - kfree(map->device_parents); - kfree(map); -} - - diff --git a/fs/ceph/crush/crush.h b/fs/ceph/crush/crush.h deleted file mode 100644 index 97e435b191f4..000000000000 --- a/fs/ceph/crush/crush.h +++ /dev/null @@ -1,180 +0,0 @@ -#ifndef CEPH_CRUSH_CRUSH_H -#define CEPH_CRUSH_CRUSH_H - -#include - -/* - * CRUSH is a pseudo-random data distribution algorithm that - * efficiently distributes input values (typically, data objects) - * across a heterogeneous, structured storage cluster. - * - * The algorithm was originally described in detail in this paper - * (although the algorithm has evolved somewhat since then): - * - * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf - * - * LGPL2 - */ - - -#define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ - - -#define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ -#define CRUSH_MAX_SET 10 /* max size of a mapping result */ - - -/* - * CRUSH uses user-defined "rules" to describe how inputs should be - * mapped to devices. A rule consists of sequence of steps to perform - * to generate the set of output devices. - */ -struct crush_rule_step { - __u32 op; - __s32 arg1; - __s32 arg2; -}; - -/* step op codes */ -enum { - CRUSH_RULE_NOOP = 0, - CRUSH_RULE_TAKE = 1, /* arg1 = value to start with */ - CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */ - /* arg2 = type */ - CRUSH_RULE_CHOOSE_INDEP = 3, /* same */ - CRUSH_RULE_EMIT = 4, /* no args */ - CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, - CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, -}; - -/* - * for specifying choose num (arg1) relative to the max parameter - * passed to do_rule - */ -#define CRUSH_CHOOSE_N 0 -#define CRUSH_CHOOSE_N_MINUS(x) (-(x)) - -/* - * The rule mask is used to describe what the rule is intended for. - * Given a ruleset and size of output set, we search through the - * rule list for a matching rule_mask. - */ -struct crush_rule_mask { - __u8 ruleset; - __u8 type; - __u8 min_size; - __u8 max_size; -}; - -struct crush_rule { - __u32 len; - struct crush_rule_mask mask; - struct crush_rule_step steps[0]; -}; - -#define crush_rule_size(len) (sizeof(struct crush_rule) + \ - (len)*sizeof(struct crush_rule_step)) - - - -/* - * A bucket is a named container of other items (either devices or - * other buckets). Items within a bucket are chosen using one of a - * few different algorithms. The table summarizes how the speed of - * each option measures up against mapping stability when items are - * added or removed. - * - * Bucket Alg Speed Additions Removals - * ------------------------------------------------ - * uniform O(1) poor poor - * list O(n) optimal poor - * tree O(log n) good good - * straw O(n) optimal optimal - */ -enum { - CRUSH_BUCKET_UNIFORM = 1, - CRUSH_BUCKET_LIST = 2, - CRUSH_BUCKET_TREE = 3, - CRUSH_BUCKET_STRAW = 4 -}; -extern const char *crush_bucket_alg_name(int alg); - -struct crush_bucket { - __s32 id; /* this'll be negative */ - __u16 type; /* non-zero; type=0 is reserved for devices */ - __u8 alg; /* one of CRUSH_BUCKET_* */ - __u8 hash; /* which hash function to use, CRUSH_HASH_* */ - __u32 weight; /* 16-bit fixed point */ - __u32 size; /* num items */ - __s32 *items; - - /* - * cached random permutation: used for uniform bucket and for - * the linear search fallback for the other bucket types. - */ - __u32 perm_x; /* @x for which *perm is defined */ - __u32 perm_n; /* num elements of *perm that are permuted/defined */ - __u32 *perm; -}; - -struct crush_bucket_uniform { - struct crush_bucket h; - __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ -}; - -struct crush_bucket_list { - struct crush_bucket h; - __u32 *item_weights; /* 16-bit fixed point */ - __u32 *sum_weights; /* 16-bit fixed point. element i is sum - of weights 0..i, inclusive */ -}; - -struct crush_bucket_tree { - struct crush_bucket h; /* note: h.size is _tree_ size, not number of - actual items */ - __u8 num_nodes; - __u32 *node_weights; -}; - -struct crush_bucket_straw { - struct crush_bucket h; - __u32 *item_weights; /* 16-bit fixed point */ - __u32 *straws; /* 16-bit fixed point */ -}; - - - -/* - * CRUSH map includes all buckets, rules, etc. - */ -struct crush_map { - struct crush_bucket **buckets; - struct crush_rule **rules; - - /* - * Parent pointers to identify the parent bucket a device or - * bucket in the hierarchy. If an item appears more than - * once, this is the _last_ time it appeared (where buckets - * are processed in bucket id order, from -1 on down to - * -max_buckets. - */ - __u32 *bucket_parents; - __u32 *device_parents; - - __s32 max_buckets; - __u32 max_rules; - __s32 max_devices; -}; - - -/* crush.c */ -extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos); -extern void crush_calc_parents(struct crush_map *map); -extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b); -extern void crush_destroy_bucket_list(struct crush_bucket_list *b); -extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b); -extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b); -extern void crush_destroy_bucket(struct crush_bucket *b); -extern void crush_destroy(struct crush_map *map); - -#endif diff --git a/fs/ceph/crush/hash.c b/fs/ceph/crush/hash.c deleted file mode 100644 index 5873aed694bf..000000000000 --- a/fs/ceph/crush/hash.c +++ /dev/null @@ -1,149 +0,0 @@ - -#include -#include "hash.h" - -/* - * Robert Jenkins' function for mixing 32-bit values - * http://burtleburtle.net/bob/hash/evahash.html - * a, b = random bits, c = input and output - */ -#define crush_hashmix(a, b, c) do { \ - a = a-b; a = a-c; a = a^(c>>13); \ - b = b-c; b = b-a; b = b^(a<<8); \ - c = c-a; c = c-b; c = c^(b>>13); \ - a = a-b; a = a-c; a = a^(c>>12); \ - b = b-c; b = b-a; b = b^(a<<16); \ - c = c-a; c = c-b; c = c^(b>>5); \ - a = a-b; a = a-c; a = a^(c>>3); \ - b = b-c; b = b-a; b = b^(a<<10); \ - c = c-a; c = c-b; c = c^(b>>15); \ - } while (0) - -#define crush_hash_seed 1315423911 - -static __u32 crush_hash32_rjenkins1(__u32 a) -{ - __u32 hash = crush_hash_seed ^ a; - __u32 b = a; - __u32 x = 231232; - __u32 y = 1232; - crush_hashmix(b, x, hash); - crush_hashmix(y, a, hash); - return hash; -} - -static __u32 crush_hash32_rjenkins1_2(__u32 a, __u32 b) -{ - __u32 hash = crush_hash_seed ^ a ^ b; - __u32 x = 231232; - __u32 y = 1232; - crush_hashmix(a, b, hash); - crush_hashmix(x, a, hash); - crush_hashmix(b, y, hash); - return hash; -} - -static __u32 crush_hash32_rjenkins1_3(__u32 a, __u32 b, __u32 c) -{ - __u32 hash = crush_hash_seed ^ a ^ b ^ c; - __u32 x = 231232; - __u32 y = 1232; - crush_hashmix(a, b, hash); - crush_hashmix(c, x, hash); - crush_hashmix(y, a, hash); - crush_hashmix(b, x, hash); - crush_hashmix(y, c, hash); - return hash; -} - -static __u32 crush_hash32_rjenkins1_4(__u32 a, __u32 b, __u32 c, __u32 d) -{ - __u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d; - __u32 x = 231232; - __u32 y = 1232; - crush_hashmix(a, b, hash); - crush_hashmix(c, d, hash); - crush_hashmix(a, x, hash); - crush_hashmix(y, b, hash); - crush_hashmix(c, x, hash); - crush_hashmix(y, d, hash); - return hash; -} - -static __u32 crush_hash32_rjenkins1_5(__u32 a, __u32 b, __u32 c, __u32 d, - __u32 e) -{ - __u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d ^ e; - __u32 x = 231232; - __u32 y = 1232; - crush_hashmix(a, b, hash); - crush_hashmix(c, d, hash); - crush_hashmix(e, x, hash); - crush_hashmix(y, a, hash); - crush_hashmix(b, x, hash); - crush_hashmix(y, c, hash); - crush_hashmix(d, x, hash); - crush_hashmix(y, e, hash); - return hash; -} - - -__u32 crush_hash32(int type, __u32 a) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return crush_hash32_rjenkins1(a); - default: - return 0; - } -} - -__u32 crush_hash32_2(int type, __u32 a, __u32 b) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return crush_hash32_rjenkins1_2(a, b); - default: - return 0; - } -} - -__u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return crush_hash32_rjenkins1_3(a, b, c); - default: - return 0; - } -} - -__u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return crush_hash32_rjenkins1_4(a, b, c, d); - default: - return 0; - } -} - -__u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, __u32 e) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return crush_hash32_rjenkins1_5(a, b, c, d, e); - default: - return 0; - } -} - -const char *crush_hash_name(int type) -{ - switch (type) { - case CRUSH_HASH_RJENKINS1: - return "rjenkins1"; - default: - return "unknown"; - } -} diff --git a/fs/ceph/crush/hash.h b/fs/ceph/crush/hash.h deleted file mode 100644 index 91e884230d5d..000000000000 --- a/fs/ceph/crush/hash.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef CEPH_CRUSH_HASH_H -#define CEPH_CRUSH_HASH_H - -#define CRUSH_HASH_RJENKINS1 0 - -#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 - -extern const char *crush_hash_name(int type); - -extern __u32 crush_hash32(int type, __u32 a); -extern __u32 crush_hash32_2(int type, __u32 a, __u32 b); -extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c); -extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d); -extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, - __u32 e); - -#endif diff --git a/fs/ceph/crush/mapper.c b/fs/ceph/crush/mapper.c deleted file mode 100644 index a4eec133258e..000000000000 --- a/fs/ceph/crush/mapper.c +++ /dev/null @@ -1,609 +0,0 @@ - -#ifdef __KERNEL__ -# include -# include -# include -# include -# ifndef dprintk -# define dprintk(args...) -# endif -#else -# include -# include -# include -# include -# define BUG_ON(x) assert(!(x)) -# define dprintk(args...) /* printf(args) */ -# define kmalloc(x, f) malloc(x) -# define kfree(x) free(x) -#endif - -#include "crush.h" -#include "hash.h" - -/* - * Implement the core CRUSH mapping algorithm. - */ - -/** - * crush_find_rule - find a crush_rule id for a given ruleset, type, and size. - * @map: the crush_map - * @ruleset: the storage ruleset id (user defined) - * @type: storage ruleset type (user defined) - * @size: output set size - */ -int crush_find_rule(struct crush_map *map, int ruleset, int type, int size) -{ - int i; - - for (i = 0; i < map->max_rules; i++) { - if (map->rules[i] && - map->rules[i]->mask.ruleset == ruleset && - map->rules[i]->mask.type == type && - map->rules[i]->mask.min_size <= size && - map->rules[i]->mask.max_size >= size) - return i; - } - return -1; -} - - -/* - * bucket choose methods - * - * For each bucket algorithm, we have a "choose" method that, given a - * crush input @x and replica position (usually, position in output set) @r, - * will produce an item in the bucket. - */ - -/* - * Choose based on a random permutation of the bucket. - * - * We used to use some prime number arithmetic to do this, but it - * wasn't very random, and had some other bad behaviors. Instead, we - * calculate an actual random permutation of the bucket members. - * Since this is expensive, we optimize for the r=0 case, which - * captures the vast majority of calls. - */ -static int bucket_perm_choose(struct crush_bucket *bucket, - int x, int r) -{ - unsigned pr = r % bucket->size; - unsigned i, s; - - /* start a new permutation if @x has changed */ - if (bucket->perm_x != x || bucket->perm_n == 0) { - dprintk("bucket %d new x=%d\n", bucket->id, x); - bucket->perm_x = x; - - /* optimize common r=0 case */ - if (pr == 0) { - s = crush_hash32_3(bucket->hash, x, bucket->id, 0) % - bucket->size; - bucket->perm[0] = s; - bucket->perm_n = 0xffff; /* magic value, see below */ - goto out; - } - - for (i = 0; i < bucket->size; i++) - bucket->perm[i] = i; - bucket->perm_n = 0; - } else if (bucket->perm_n == 0xffff) { - /* clean up after the r=0 case above */ - for (i = 1; i < bucket->size; i++) - bucket->perm[i] = i; - bucket->perm[bucket->perm[0]] = 0; - bucket->perm_n = 1; - } - - /* calculate permutation up to pr */ - for (i = 0; i < bucket->perm_n; i++) - dprintk(" perm_choose have %d: %d\n", i, bucket->perm[i]); - while (bucket->perm_n <= pr) { - unsigned p = bucket->perm_n; - /* no point in swapping the final entry */ - if (p < bucket->size - 1) { - i = crush_hash32_3(bucket->hash, x, bucket->id, p) % - (bucket->size - p); - if (i) { - unsigned t = bucket->perm[p + i]; - bucket->perm[p + i] = bucket->perm[p]; - bucket->perm[p] = t; - } - dprintk(" perm_choose swap %d with %d\n", p, p+i); - } - bucket->perm_n++; - } - for (i = 0; i < bucket->size; i++) - dprintk(" perm_choose %d: %d\n", i, bucket->perm[i]); - - s = bucket->perm[pr]; -out: - dprintk(" perm_choose %d sz=%d x=%d r=%d (%d) s=%d\n", bucket->id, - bucket->size, x, r, pr, s); - return bucket->items[s]; -} - -/* uniform */ -static int bucket_uniform_choose(struct crush_bucket_uniform *bucket, - int x, int r) -{ - return bucket_perm_choose(&bucket->h, x, r); -} - -/* list */ -static int bucket_list_choose(struct crush_bucket_list *bucket, - int x, int r) -{ - int i; - - for (i = bucket->h.size-1; i >= 0; i--) { - __u64 w = crush_hash32_4(bucket->h.hash,x, bucket->h.items[i], - r, bucket->h.id); - w &= 0xffff; - dprintk("list_choose i=%d x=%d r=%d item %d weight %x " - "sw %x rand %llx", - i, x, r, bucket->h.items[i], bucket->item_weights[i], - bucket->sum_weights[i], w); - w *= bucket->sum_weights[i]; - w = w >> 16; - /*dprintk(" scaled %llx\n", w);*/ - if (w < bucket->item_weights[i]) - return bucket->h.items[i]; - } - - BUG_ON(1); - return 0; -} - - -/* (binary) tree */ -static int height(int n) -{ - int h = 0; - while ((n & 1) == 0) { - h++; - n = n >> 1; - } - return h; -} - -static int left(int x) -{ - int h = height(x); - return x - (1 << (h-1)); -} - -static int right(int x) -{ - int h = height(x); - return x + (1 << (h-1)); -} - -static int terminal(int x) -{ - return x & 1; -} - -static int bucket_tree_choose(struct crush_bucket_tree *bucket, - int x, int r) -{ - int n, l; - __u32 w; - __u64 t; - - /* start at root */ - n = bucket->num_nodes >> 1; - - while (!terminal(n)) { - /* pick point in [0, w) */ - w = bucket->node_weights[n]; - t = (__u64)crush_hash32_4(bucket->h.hash, x, n, r, - bucket->h.id) * (__u64)w; - t = t >> 32; - - /* descend to the left or right? */ - l = left(n); - if (t < bucket->node_weights[l]) - n = l; - else - n = right(n); - } - - return bucket->h.items[n >> 1]; -} - - -/* straw */ - -static int bucket_straw_choose(struct crush_bucket_straw *bucket, - int x, int r) -{ - int i; - int high = 0; - __u64 high_draw = 0; - __u64 draw; - - for (i = 0; i < bucket->h.size; i++) { - draw = crush_hash32_3(bucket->h.hash, x, bucket->h.items[i], r); - draw &= 0xffff; - draw *= bucket->straws[i]; - if (i == 0 || draw > high_draw) { - high = i; - high_draw = draw; - } - } - return bucket->h.items[high]; -} - -static int crush_bucket_choose(struct crush_bucket *in, int x, int r) -{ - dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r); - switch (in->alg) { - case CRUSH_BUCKET_UNIFORM: - return bucket_uniform_choose((struct crush_bucket_uniform *)in, - x, r); - case CRUSH_BUCKET_LIST: - return bucket_list_choose((struct crush_bucket_list *)in, - x, r); - case CRUSH_BUCKET_TREE: - return bucket_tree_choose((struct crush_bucket_tree *)in, - x, r); - case CRUSH_BUCKET_STRAW: - return bucket_straw_choose((struct crush_bucket_straw *)in, - x, r); - default: - BUG_ON(1); - return in->items[0]; - } -} - -/* - * true if device is marked "out" (failed, fully offloaded) - * of the cluster - */ -static int is_out(struct crush_map *map, __u32 *weight, int item, int x) -{ - if (weight[item] >= 0x10000) - return 0; - if (weight[item] == 0) - return 1; - if ((crush_hash32_2(CRUSH_HASH_RJENKINS1, x, item) & 0xffff) - < weight[item]) - return 0; - return 1; -} - -/** - * crush_choose - choose numrep distinct items of given type - * @map: the crush_map - * @bucket: the bucket we are choose an item from - * @x: crush input value - * @numrep: the number of items to choose - * @type: the type of item to choose - * @out: pointer to output vector - * @outpos: our position in that vector - * @firstn: true if choosing "first n" items, false if choosing "indep" - * @recurse_to_leaf: true if we want one device under each item of given type - * @out2: second output vector for leaf items (if @recurse_to_leaf) - */ -static int crush_choose(struct crush_map *map, - struct crush_bucket *bucket, - __u32 *weight, - int x, int numrep, int type, - int *out, int outpos, - int firstn, int recurse_to_leaf, - int *out2) -{ - int rep; - int ftotal, flocal; - int retry_descent, retry_bucket, skip_rep; - struct crush_bucket *in = bucket; - int r; - int i; - int item = 0; - int itemtype; - int collide, reject; - const int orig_tries = 5; /* attempts before we fall back to search */ - - dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", - bucket->id, x, outpos, numrep); - - for (rep = outpos; rep < numrep; rep++) { - /* keep trying until we get a non-out, non-colliding item */ - ftotal = 0; - skip_rep = 0; - do { - retry_descent = 0; - in = bucket; /* initial bucket */ - - /* choose through intervening buckets */ - flocal = 0; - do { - collide = 0; - retry_bucket = 0; - r = rep; - if (in->alg == CRUSH_BUCKET_UNIFORM) { - /* be careful */ - if (firstn || numrep >= in->size) - /* r' = r + f_total */ - r += ftotal; - else if (in->size % numrep == 0) - /* r'=r+(n+1)*f_local */ - r += (numrep+1) * - (flocal+ftotal); - else - /* r' = r + n*f_local */ - r += numrep * (flocal+ftotal); - } else { - if (firstn) - /* r' = r + f_total */ - r += ftotal; - else - /* r' = r + n*f_local */ - r += numrep * (flocal+ftotal); - } - - /* bucket choose */ - if (in->size == 0) { - reject = 1; - goto reject; - } - if (flocal >= (in->size>>1) && - flocal > orig_tries) - item = bucket_perm_choose(in, x, r); - else - item = crush_bucket_choose(in, x, r); - BUG_ON(item >= map->max_devices); - - /* desired type? */ - if (item < 0) - itemtype = map->buckets[-1-item]->type; - else - itemtype = 0; - dprintk(" item %d type %d\n", item, itemtype); - - /* keep going? */ - if (itemtype != type) { - BUG_ON(item >= 0 || - (-1-item) >= map->max_buckets); - in = map->buckets[-1-item]; - retry_bucket = 1; - continue; - } - - /* collision? */ - for (i = 0; i < outpos; i++) { - if (out[i] == item) { - collide = 1; - break; - } - } - - reject = 0; - if (recurse_to_leaf) { - if (item < 0) { - if (crush_choose(map, - map->buckets[-1-item], - weight, - x, outpos+1, 0, - out2, outpos, - firstn, 0, - NULL) <= outpos) - /* didn't get leaf */ - reject = 1; - } else { - /* we already have a leaf! */ - out2[outpos] = item; - } - } - - if (!reject) { - /* out? */ - if (itemtype == 0) - reject = is_out(map, weight, - item, x); - else - reject = 0; - } - -reject: - if (reject || collide) { - ftotal++; - flocal++; - - if (collide && flocal < 3) - /* retry locally a few times */ - retry_bucket = 1; - else if (flocal < in->size + orig_tries) - /* exhaustive bucket search */ - retry_bucket = 1; - else if (ftotal < 20) - /* then retry descent */ - retry_descent = 1; - else - /* else give up */ - skip_rep = 1; - dprintk(" reject %d collide %d " - "ftotal %d flocal %d\n", - reject, collide, ftotal, - flocal); - } - } while (retry_bucket); - } while (retry_descent); - - if (skip_rep) { - dprintk("skip rep\n"); - continue; - } - - dprintk("CHOOSE got %d\n", item); - out[outpos] = item; - outpos++; - } - - dprintk("CHOOSE returns %d\n", outpos); - return outpos; -} - - -/** - * crush_do_rule - calculate a mapping with the given input and rule - * @map: the crush_map - * @ruleno: the rule id - * @x: hash input - * @result: pointer to result vector - * @result_max: maximum result size - * @force: force initial replica choice; -1 for none - */ -int crush_do_rule(struct crush_map *map, - int ruleno, int x, int *result, int result_max, - int force, __u32 *weight) -{ - int result_len; - int force_context[CRUSH_MAX_DEPTH]; - int force_pos = -1; - int a[CRUSH_MAX_SET]; - int b[CRUSH_MAX_SET]; - int c[CRUSH_MAX_SET]; - int recurse_to_leaf; - int *w; - int wsize = 0; - int *o; - int osize; - int *tmp; - struct crush_rule *rule; - int step; - int i, j; - int numrep; - int firstn; - int rc = -1; - - BUG_ON(ruleno >= map->max_rules); - - rule = map->rules[ruleno]; - result_len = 0; - w = a; - o = b; - - /* - * determine hierarchical context of force, if any. note - * that this may or may not correspond to the specific types - * referenced by the crush rule. - */ - if (force >= 0) { - if (force >= map->max_devices || - map->device_parents[force] == 0) { - /*dprintk("CRUSH: forcefed device dne\n");*/ - rc = -1; /* force fed device dne */ - goto out; - } - if (!is_out(map, weight, force, x)) { - while (1) { - force_context[++force_pos] = force; - if (force >= 0) - force = map->device_parents[force]; - else - force = map->bucket_parents[-1-force]; - if (force == 0) - break; - } - } - } - - for (step = 0; step < rule->len; step++) { - firstn = 0; - switch (rule->steps[step].op) { - case CRUSH_RULE_TAKE: - w[0] = rule->steps[step].arg1; - if (force_pos >= 0) { - BUG_ON(force_context[force_pos] != w[0]); - force_pos--; - } - wsize = 1; - break; - - case CRUSH_RULE_CHOOSE_LEAF_FIRSTN: - case CRUSH_RULE_CHOOSE_FIRSTN: - firstn = 1; - case CRUSH_RULE_CHOOSE_LEAF_INDEP: - case CRUSH_RULE_CHOOSE_INDEP: - BUG_ON(wsize == 0); - - recurse_to_leaf = - rule->steps[step].op == - CRUSH_RULE_CHOOSE_LEAF_FIRSTN || - rule->steps[step].op == - CRUSH_RULE_CHOOSE_LEAF_INDEP; - - /* reset output */ - osize = 0; - - for (i = 0; i < wsize; i++) { - /* - * see CRUSH_N, CRUSH_N_MINUS macros. - * basically, numrep <= 0 means relative to - * the provided result_max - */ - numrep = rule->steps[step].arg1; - if (numrep <= 0) { - numrep += result_max; - if (numrep <= 0) - continue; - } - j = 0; - if (osize == 0 && force_pos >= 0) { - /* skip any intermediate types */ - while (force_pos && - force_context[force_pos] < 0 && - rule->steps[step].arg2 != - map->buckets[-1 - - force_context[force_pos]]->type) - force_pos--; - o[osize] = force_context[force_pos]; - if (recurse_to_leaf) - c[osize] = force_context[0]; - j++; - force_pos--; - } - osize += crush_choose(map, - map->buckets[-1-w[i]], - weight, - x, numrep, - rule->steps[step].arg2, - o+osize, j, - firstn, - recurse_to_leaf, c+osize); - } - - if (recurse_to_leaf) - /* copy final _leaf_ values to output set */ - memcpy(o, c, osize*sizeof(*o)); - - /* swap t and w arrays */ - tmp = o; - o = w; - w = tmp; - wsize = osize; - break; - - - case CRUSH_RULE_EMIT: - for (i = 0; i < wsize && result_len < result_max; i++) { - result[result_len] = w[i]; - result_len++; - } - wsize = 0; - break; - - default: - BUG_ON(1); - } - } - rc = result_len; - -out: - return rc; -} - - diff --git a/fs/ceph/crush/mapper.h b/fs/ceph/crush/mapper.h deleted file mode 100644 index c46b99c18bb0..000000000000 --- a/fs/ceph/crush/mapper.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef CEPH_CRUSH_MAPPER_H -#define CEPH_CRUSH_MAPPER_H - -/* - * CRUSH functions for find rules and then mapping an input to an - * output set. - * - * LGPL2 - */ - -#include "crush.h" - -extern int crush_find_rule(struct crush_map *map, int pool, int type, int size); -extern int crush_do_rule(struct crush_map *map, - int ruleno, - int x, int *result, int result_max, - int forcefeed, /* -1 for none */ - __u32 *weights); - -#endif diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c deleted file mode 100644 index a3e627f63293..000000000000 --- a/fs/ceph/crypto.c +++ /dev/null @@ -1,412 +0,0 @@ - -#include "ceph_debug.h" - -#include -#include -#include -#include - -#include "crypto.h" -#include "decode.h" - -int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end) -{ - if (*p + sizeof(u16) + sizeof(key->created) + - sizeof(u16) + key->len > end) - return -ERANGE; - ceph_encode_16(p, key->type); - ceph_encode_copy(p, &key->created, sizeof(key->created)); - ceph_encode_16(p, key->len); - ceph_encode_copy(p, key->key, key->len); - return 0; -} - -int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end) -{ - ceph_decode_need(p, end, 2*sizeof(u16) + sizeof(key->created), bad); - key->type = ceph_decode_16(p); - ceph_decode_copy(p, &key->created, sizeof(key->created)); - key->len = ceph_decode_16(p); - ceph_decode_need(p, end, key->len, bad); - key->key = kmalloc(key->len, GFP_NOFS); - if (!key->key) - return -ENOMEM; - ceph_decode_copy(p, key->key, key->len); - return 0; - -bad: - dout("failed to decode crypto key\n"); - return -EINVAL; -} - -int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey) -{ - int inlen = strlen(inkey); - int blen = inlen * 3 / 4; - void *buf, *p; - int ret; - - dout("crypto_key_unarmor %s\n", inkey); - buf = kmalloc(blen, GFP_NOFS); - if (!buf) - return -ENOMEM; - blen = ceph_unarmor(buf, inkey, inkey+inlen); - if (blen < 0) { - kfree(buf); - return blen; - } - - p = buf; - ret = ceph_crypto_key_decode(key, &p, p + blen); - kfree(buf); - if (ret) - return ret; - dout("crypto_key_unarmor key %p type %d len %d\n", key, - key->type, key->len); - return 0; -} - - - -#define AES_KEY_SIZE 16 - -static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) -{ - return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC); -} - -static const u8 *aes_iv = (u8 *)CEPH_AES_IV; - -static int ceph_aes_encrypt(const void *key, int key_len, - void *dst, size_t *dst_len, - const void *src, size_t src_len) -{ - struct scatterlist sg_in[2], sg_out[1]; - struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); - struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; - int ret; - void *iv; - int ivsize; - size_t zero_padding = (0x10 - (src_len & 0x0f)); - char pad[16]; - - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - memset(pad, zero_padding, zero_padding); - - *dst_len = src_len + zero_padding; - - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 2); - sg_set_buf(&sg_in[0], src, src_len); - sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); - iv = crypto_blkcipher_crt(tfm)->iv; - ivsize = crypto_blkcipher_ivsize(tfm); - - memcpy(iv, aes_iv, ivsize); - /* - print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, - key, key_len, 1); - print_hex_dump(KERN_ERR, "enc src: ", DUMP_PREFIX_NONE, 16, 1, - src, src_len, 1); - print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, - pad, zero_padding, 1); - */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, - src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) - pr_err("ceph_aes_crypt failed %d\n", ret); - /* - print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, - dst, *dst_len, 1); - */ - return 0; -} - -static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, - size_t *dst_len, - const void *src1, size_t src1_len, - const void *src2, size_t src2_len) -{ - struct scatterlist sg_in[3], sg_out[1]; - struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); - struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; - int ret; - void *iv; - int ivsize; - size_t zero_padding = (0x10 - ((src1_len + src2_len) & 0x0f)); - char pad[16]; - - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - memset(pad, zero_padding, zero_padding); - - *dst_len = src1_len + src2_len + zero_padding; - - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 3); - sg_set_buf(&sg_in[0], src1, src1_len); - sg_set_buf(&sg_in[1], src2, src2_len); - sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); - iv = crypto_blkcipher_crt(tfm)->iv; - ivsize = crypto_blkcipher_ivsize(tfm); - - memcpy(iv, aes_iv, ivsize); - /* - print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, - key, key_len, 1); - print_hex_dump(KERN_ERR, "enc src1: ", DUMP_PREFIX_NONE, 16, 1, - src1, src1_len, 1); - print_hex_dump(KERN_ERR, "enc src2: ", DUMP_PREFIX_NONE, 16, 1, - src2, src2_len, 1); - print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, - pad, zero_padding, 1); - */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, - src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) - pr_err("ceph_aes_crypt2 failed %d\n", ret); - /* - print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, - dst, *dst_len, 1); - */ - return 0; -} - -static int ceph_aes_decrypt(const void *key, int key_len, - void *dst, size_t *dst_len, - const void *src, size_t src_len) -{ - struct scatterlist sg_in[1], sg_out[2]; - struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); - struct blkcipher_desc desc = { .tfm = tfm }; - char pad[16]; - void *iv; - int ivsize; - int ret; - int last_byte; - - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); - sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); - sg_set_buf(&sg_out[0], dst, *dst_len); - sg_set_buf(&sg_out[1], pad, sizeof(pad)); - - iv = crypto_blkcipher_crt(tfm)->iv; - ivsize = crypto_blkcipher_ivsize(tfm); - - memcpy(iv, aes_iv, ivsize); - - /* - print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1, - key, key_len, 1); - print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, - src, src_len, 1); - */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); - if (ret < 0) { - pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; - } - - if (src_len <= *dst_len) - last_byte = ((char *)dst)[src_len - 1]; - else - last_byte = pad[src_len - *dst_len - 1]; - if (last_byte <= 16 && src_len >= last_byte) { - *dst_len = src_len - last_byte; - } else { - pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n", - last_byte, (int)src_len); - return -EPERM; /* bad padding */ - } - /* - print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, - dst, *dst_len, 1); - */ - return 0; -} - -static int ceph_aes_decrypt2(const void *key, int key_len, - void *dst1, size_t *dst1_len, - void *dst2, size_t *dst2_len, - const void *src, size_t src_len) -{ - struct scatterlist sg_in[1], sg_out[3]; - struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); - struct blkcipher_desc desc = { .tfm = tfm }; - char pad[16]; - void *iv; - int ivsize; - int ret; - int last_byte; - - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); - sg_init_table(sg_out, 3); - sg_set_buf(&sg_out[0], dst1, *dst1_len); - sg_set_buf(&sg_out[1], dst2, *dst2_len); - sg_set_buf(&sg_out[2], pad, sizeof(pad)); - - crypto_blkcipher_setkey((void *)tfm, key, key_len); - iv = crypto_blkcipher_crt(tfm)->iv; - ivsize = crypto_blkcipher_ivsize(tfm); - - memcpy(iv, aes_iv, ivsize); - - /* - print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1, - key, key_len, 1); - print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, - src, src_len, 1); - */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); - if (ret < 0) { - pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; - } - - if (src_len <= *dst1_len) - last_byte = ((char *)dst1)[src_len - 1]; - else if (src_len <= *dst1_len + *dst2_len) - last_byte = ((char *)dst2)[src_len - *dst1_len - 1]; - else - last_byte = pad[src_len - *dst1_len - *dst2_len - 1]; - if (last_byte <= 16 && src_len >= last_byte) { - src_len -= last_byte; - } else { - pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n", - last_byte, (int)src_len); - return -EPERM; /* bad padding */ - } - - if (src_len < *dst1_len) { - *dst1_len = src_len; - *dst2_len = 0; - } else { - *dst2_len = src_len - *dst1_len; - } - /* - print_hex_dump(KERN_ERR, "dec out1: ", DUMP_PREFIX_NONE, 16, 1, - dst1, *dst1_len, 1); - print_hex_dump(KERN_ERR, "dec out2: ", DUMP_PREFIX_NONE, 16, 1, - dst2, *dst2_len, 1); - */ - - return 0; -} - - -int ceph_decrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, - const void *src, size_t src_len) -{ - switch (secret->type) { - case CEPH_CRYPTO_NONE: - if (*dst_len < src_len) - return -ERANGE; - memcpy(dst, src, src_len); - *dst_len = src_len; - return 0; - - case CEPH_CRYPTO_AES: - return ceph_aes_decrypt(secret->key, secret->len, dst, - dst_len, src, src_len); - - default: - return -EINVAL; - } -} - -int ceph_decrypt2(struct ceph_crypto_key *secret, - void *dst1, size_t *dst1_len, - void *dst2, size_t *dst2_len, - const void *src, size_t src_len) -{ - size_t t; - - switch (secret->type) { - case CEPH_CRYPTO_NONE: - if (*dst1_len + *dst2_len < src_len) - return -ERANGE; - t = min(*dst1_len, src_len); - memcpy(dst1, src, t); - *dst1_len = t; - src += t; - src_len -= t; - if (src_len) { - t = min(*dst2_len, src_len); - memcpy(dst2, src, t); - *dst2_len = t; - } - return 0; - - case CEPH_CRYPTO_AES: - return ceph_aes_decrypt2(secret->key, secret->len, - dst1, dst1_len, dst2, dst2_len, - src, src_len); - - default: - return -EINVAL; - } -} - -int ceph_encrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, - const void *src, size_t src_len) -{ - switch (secret->type) { - case CEPH_CRYPTO_NONE: - if (*dst_len < src_len) - return -ERANGE; - memcpy(dst, src, src_len); - *dst_len = src_len; - return 0; - - case CEPH_CRYPTO_AES: - return ceph_aes_encrypt(secret->key, secret->len, dst, - dst_len, src, src_len); - - default: - return -EINVAL; - } -} - -int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, - const void *src1, size_t src1_len, - const void *src2, size_t src2_len) -{ - switch (secret->type) { - case CEPH_CRYPTO_NONE: - if (*dst_len < src1_len + src2_len) - return -ERANGE; - memcpy(dst, src1, src1_len); - memcpy(dst + src1_len, src2, src2_len); - *dst_len = src1_len + src2_len; - return 0; - - case CEPH_CRYPTO_AES: - return ceph_aes_encrypt2(secret->key, secret->len, dst, dst_len, - src1, src1_len, src2, src2_len); - - default: - return -EINVAL; - } -} diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h deleted file mode 100644 index bdf38607323c..000000000000 --- a/fs/ceph/crypto.h +++ /dev/null @@ -1,48 +0,0 @@ -#ifndef _FS_CEPH_CRYPTO_H -#define _FS_CEPH_CRYPTO_H - -#include "types.h" -#include "buffer.h" - -/* - * cryptographic secret - */ -struct ceph_crypto_key { - int type; - struct ceph_timespec created; - int len; - void *key; -}; - -static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) -{ - kfree(key->key); -} - -extern int ceph_crypto_key_encode(struct ceph_crypto_key *key, - void **p, void *end); -extern int ceph_crypto_key_decode(struct ceph_crypto_key *key, - void **p, void *end); -extern int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *in); - -/* crypto.c */ -extern int ceph_decrypt(struct ceph_crypto_key *secret, - void *dst, size_t *dst_len, - const void *src, size_t src_len); -extern int ceph_encrypt(struct ceph_crypto_key *secret, - void *dst, size_t *dst_len, - const void *src, size_t src_len); -extern int ceph_decrypt2(struct ceph_crypto_key *secret, - void *dst1, size_t *dst1_len, - void *dst2, size_t *dst2_len, - const void *src, size_t src_len); -extern int ceph_encrypt2(struct ceph_crypto_key *secret, - void *dst, size_t *dst_len, - const void *src1, size_t src1_len, - const void *src2, size_t src2_len); - -/* armor.c */ -extern int ceph_armor(char *dst, const char *src, const char *end); -extern int ceph_unarmor(char *dst, const char *src, const char *end); - -#endif diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 6fd8b20a8611..94fe1d284c3a 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -7,143 +7,48 @@ #include #include -#include "super.h" -#include "mds_client.h" -#include "mon_client.h" -#include "auth.h" +#include +#include +#include +#include #ifdef CONFIG_DEBUG_FS -/* - * Implement /sys/kernel/debug/ceph fun - * - * /sys/kernel/debug/ceph/client* - an instance of the ceph client - * .../osdmap - current osdmap - * .../mdsmap - current mdsmap - * .../monmap - current monmap - * .../osdc - active osd requests - * .../mdsc - active mds requests - * .../monc - mon client state - * .../dentry_lru - dump contents of dentry lru - * .../caps - expose cap (reservation) stats - * .../bdi - symlink to ../../bdi/something - */ - -static struct dentry *ceph_debugfs_dir; - -static int monmap_show(struct seq_file *s, void *p) -{ - int i; - struct ceph_client *client = s->private; - - if (client->monc.monmap == NULL) - return 0; - - seq_printf(s, "epoch %d\n", client->monc.monmap->epoch); - for (i = 0; i < client->monc.monmap->num_mon; i++) { - struct ceph_entity_inst *inst = - &client->monc.monmap->mon_inst[i]; - - seq_printf(s, "\t%s%lld\t%s\n", - ENTITY_NAME(inst->name), - pr_addr(&inst->addr.in_addr)); - } - return 0; -} +#include "super.h" +#include "mds_client.h" static int mdsmap_show(struct seq_file *s, void *p) { int i; - struct ceph_client *client = s->private; + struct ceph_fs_client *fsc = s->private; - if (client->mdsc.mdsmap == NULL) + if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL) return 0; - seq_printf(s, "epoch %d\n", client->mdsc.mdsmap->m_epoch); - seq_printf(s, "root %d\n", client->mdsc.mdsmap->m_root); + seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch); + seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root); seq_printf(s, "session_timeout %d\n", - client->mdsc.mdsmap->m_session_timeout); + fsc->mdsc->mdsmap->m_session_timeout); seq_printf(s, "session_autoclose %d\n", - client->mdsc.mdsmap->m_session_autoclose); - for (i = 0; i < client->mdsc.mdsmap->m_max_mds; i++) { + fsc->mdsc->mdsmap->m_session_autoclose); + for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) { struct ceph_entity_addr *addr = - &client->mdsc.mdsmap->m_info[i].addr; - int state = client->mdsc.mdsmap->m_info[i].state; + &fsc->mdsc->mdsmap->m_info[i].addr; + int state = fsc->mdsc->mdsmap->m_info[i].state; - seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, pr_addr(&addr->in_addr), + seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, + ceph_pr_addr(&addr->in_addr), ceph_mds_state_name(state)); } return 0; } -static int osdmap_show(struct seq_file *s, void *p) -{ - int i; - struct ceph_client *client = s->private; - struct rb_node *n; - - if (client->osdc.osdmap == NULL) - return 0; - seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch); - seq_printf(s, "flags%s%s\n", - (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ? - " NEARFULL" : "", - (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ? - " FULL" : ""); - for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) { - struct ceph_pg_pool_info *pool = - rb_entry(n, struct ceph_pg_pool_info, node); - seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n", - pool->id, pool->v.pg_num, pool->pg_num_mask, - pool->v.lpg_num, pool->lpg_num_mask); - } - for (i = 0; i < client->osdc.osdmap->max_osd; i++) { - struct ceph_entity_addr *addr = - &client->osdc.osdmap->osd_addr[i]; - int state = client->osdc.osdmap->osd_state[i]; - char sb[64]; - - seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n", - i, pr_addr(&addr->in_addr), - ((client->osdc.osdmap->osd_weight[i]*100) >> 16), - ceph_osdmap_state_str(sb, sizeof(sb), state)); - } - return 0; -} - -static int monc_show(struct seq_file *s, void *p) -{ - struct ceph_client *client = s->private; - struct ceph_mon_generic_request *req; - struct ceph_mon_client *monc = &client->monc; - struct rb_node *rp; - - mutex_lock(&monc->mutex); - - if (monc->have_mdsmap) - seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap); - if (monc->have_osdmap) - seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap); - if (monc->want_next_osdmap) - seq_printf(s, "want next osdmap\n"); - - for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) { - __u16 op; - req = rb_entry(rp, struct ceph_mon_generic_request, node); - op = le16_to_cpu(req->request->hdr.type); - if (op == CEPH_MSG_STATFS) - seq_printf(s, "%lld statfs\n", req->tid); - else - seq_printf(s, "%lld unknown\n", req->tid); - } - - mutex_unlock(&monc->mutex); - return 0; -} - +/* + * mdsc debugfs + */ static int mdsc_show(struct seq_file *s, void *p) { - struct ceph_client *client = s->private; - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = s->private; + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; struct rb_node *rp; int pathlen; @@ -214,61 +119,12 @@ static int mdsc_show(struct seq_file *s, void *p) return 0; } -static int osdc_show(struct seq_file *s, void *pp) -{ - struct ceph_client *client = s->private; - struct ceph_osd_client *osdc = &client->osdc; - struct rb_node *p; - - mutex_lock(&osdc->request_mutex); - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { - struct ceph_osd_request *req; - struct ceph_osd_request_head *head; - struct ceph_osd_op *op; - int num_ops; - int opcode, olen; - int i; - - req = rb_entry(p, struct ceph_osd_request, r_node); - - seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1, - le32_to_cpu(req->r_pgid.pool), - le16_to_cpu(req->r_pgid.ps)); - - head = req->r_request->front.iov_base; - op = (void *)(head + 1); - - num_ops = le16_to_cpu(head->num_ops); - olen = le32_to_cpu(head->object_len); - seq_printf(s, "%.*s", olen, - (const char *)(head->ops + num_ops)); - - if (req->r_reassert_version.epoch) - seq_printf(s, "\t%u'%llu", - (unsigned)le32_to_cpu(req->r_reassert_version.epoch), - le64_to_cpu(req->r_reassert_version.version)); - else - seq_printf(s, "\t"); - - for (i = 0; i < num_ops; i++) { - opcode = le16_to_cpu(op->op); - seq_printf(s, "\t%s", ceph_osd_op_name(opcode)); - op++; - } - - seq_printf(s, "\n"); - } - mutex_unlock(&osdc->request_mutex); - return 0; -} - static int caps_show(struct seq_file *s, void *p) { - struct ceph_client *client = s->private; + struct ceph_fs_client *fsc = s->private; int total, avail, used, reserved, min; - ceph_reservation_status(client, &total, &avail, &used, &reserved, &min); + ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min); seq_printf(s, "total\t\t%d\n" "avail\t\t%d\n" "used\t\t%d\n" @@ -280,8 +136,8 @@ static int caps_show(struct seq_file *s, void *p) static int dentry_lru_show(struct seq_file *s, void *ptr) { - struct ceph_client *client = s->private; - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = s->private; + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_dentry_info *di; spin_lock(&mdsc->dentry_lru_lock); @@ -295,199 +151,124 @@ static int dentry_lru_show(struct seq_file *s, void *ptr) return 0; } -#define DEFINE_SHOW_FUNC(name) \ -static int name##_open(struct inode *inode, struct file *file) \ -{ \ - struct seq_file *sf; \ - int ret; \ - \ - ret = single_open(file, name, NULL); \ - sf = file->private_data; \ - sf->private = inode->i_private; \ - return ret; \ -} \ - \ -static const struct file_operations name##_fops = { \ - .open = name##_open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ -}; - -DEFINE_SHOW_FUNC(monmap_show) -DEFINE_SHOW_FUNC(mdsmap_show) -DEFINE_SHOW_FUNC(osdmap_show) -DEFINE_SHOW_FUNC(monc_show) -DEFINE_SHOW_FUNC(mdsc_show) -DEFINE_SHOW_FUNC(osdc_show) -DEFINE_SHOW_FUNC(dentry_lru_show) -DEFINE_SHOW_FUNC(caps_show) +CEPH_DEFINE_SHOW_FUNC(mdsmap_show) +CEPH_DEFINE_SHOW_FUNC(mdsc_show) +CEPH_DEFINE_SHOW_FUNC(caps_show) +CEPH_DEFINE_SHOW_FUNC(dentry_lru_show) + +/* + * debugfs + */ static int congestion_kb_set(void *data, u64 val) { - struct ceph_client *client = (struct ceph_client *)data; - - if (client) - client->mount_args->congestion_kb = (int)val; + struct ceph_fs_client *fsc = (struct ceph_fs_client *)data; + fsc->mount_options->congestion_kb = (int)val; return 0; } static int congestion_kb_get(void *data, u64 *val) { - struct ceph_client *client = (struct ceph_client *)data; - - if (client) - *val = (u64)client->mount_args->congestion_kb; + struct ceph_fs_client *fsc = (struct ceph_fs_client *)data; + *val = (u64)fsc->mount_options->congestion_kb; return 0; } - DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get, congestion_kb_set, "%llu\n"); -int __init ceph_debugfs_init(void) -{ - ceph_debugfs_dir = debugfs_create_dir("ceph", NULL); - if (!ceph_debugfs_dir) - return -ENOMEM; - return 0; -} -void ceph_debugfs_cleanup(void) +void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) { - debugfs_remove(ceph_debugfs_dir); + dout("ceph_fs_debugfs_cleanup\n"); + debugfs_remove(fsc->debugfs_bdi); + debugfs_remove(fsc->debugfs_congestion_kb); + debugfs_remove(fsc->debugfs_mdsmap); + debugfs_remove(fsc->debugfs_caps); + debugfs_remove(fsc->debugfs_mdsc); + debugfs_remove(fsc->debugfs_dentry_lru); } -int ceph_debugfs_client_init(struct ceph_client *client) +int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { - int ret = 0; - char name[80]; - - snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid, - client->monc.auth->global_id); - - client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir); - if (!client->debugfs_dir) - goto out; + char name[100]; + int err = -ENOMEM; - client->monc.debugfs_file = debugfs_create_file("monc", - 0600, - client->debugfs_dir, - client, - &monc_show_fops); - if (!client->monc.debugfs_file) - goto out; - - client->mdsc.debugfs_file = debugfs_create_file("mdsc", - 0600, - client->debugfs_dir, - client, - &mdsc_show_fops); - if (!client->mdsc.debugfs_file) + dout("ceph_fs_debugfs_init\n"); + fsc->debugfs_congestion_kb = + debugfs_create_file("writeback_congestion_kb", + 0600, + fsc->client->debugfs_dir, + fsc, + &congestion_kb_fops); + if (!fsc->debugfs_congestion_kb) goto out; - client->osdc.debugfs_file = debugfs_create_file("osdc", - 0600, - client->debugfs_dir, - client, - &osdc_show_fops); - if (!client->osdc.debugfs_file) - goto out; + dout("a\n"); - client->debugfs_monmap = debugfs_create_file("monmap", - 0600, - client->debugfs_dir, - client, - &monmap_show_fops); - if (!client->debugfs_monmap) + snprintf(name, sizeof(name), "../../bdi/%s", + dev_name(fsc->backing_dev_info.dev)); + fsc->debugfs_bdi = + debugfs_create_symlink("bdi", + fsc->client->debugfs_dir, + name); + if (!fsc->debugfs_bdi) goto out; - client->debugfs_mdsmap = debugfs_create_file("mdsmap", + dout("b\n"); + fsc->debugfs_mdsmap = debugfs_create_file("mdsmap", 0600, - client->debugfs_dir, - client, + fsc->client->debugfs_dir, + fsc, &mdsmap_show_fops); - if (!client->debugfs_mdsmap) + if (!fsc->debugfs_mdsmap) goto out; - client->debugfs_osdmap = debugfs_create_file("osdmap", - 0600, - client->debugfs_dir, - client, - &osdmap_show_fops); - if (!client->debugfs_osdmap) + dout("ca\n"); + fsc->debugfs_mdsc = debugfs_create_file("mdsc", + 0600, + fsc->client->debugfs_dir, + fsc, + &mdsc_show_fops); + if (!fsc->debugfs_mdsc) goto out; - client->debugfs_dentry_lru = debugfs_create_file("dentry_lru", - 0600, - client->debugfs_dir, - client, - &dentry_lru_show_fops); - if (!client->debugfs_dentry_lru) - goto out; - - client->debugfs_caps = debugfs_create_file("caps", + dout("da\n"); + fsc->debugfs_caps = debugfs_create_file("caps", 0400, - client->debugfs_dir, - client, + fsc->client->debugfs_dir, + fsc, &caps_show_fops); - if (!client->debugfs_caps) + if (!fsc->debugfs_caps) goto out; - client->debugfs_congestion_kb = - debugfs_create_file("writeback_congestion_kb", - 0600, - client->debugfs_dir, - client, - &congestion_kb_fops); - if (!client->debugfs_congestion_kb) + dout("ea\n"); + fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru", + 0600, + fsc->client->debugfs_dir, + fsc, + &dentry_lru_show_fops); + if (!fsc->debugfs_dentry_lru) goto out; - sprintf(name, "../../bdi/%s", dev_name(client->sb->s_bdi->dev)); - client->debugfs_bdi = debugfs_create_symlink("bdi", client->debugfs_dir, - name); - return 0; out: - ceph_debugfs_client_cleanup(client); - return ret; + ceph_fs_debugfs_cleanup(fsc); + return err; } -void ceph_debugfs_client_cleanup(struct ceph_client *client) -{ - debugfs_remove(client->debugfs_bdi); - debugfs_remove(client->debugfs_caps); - debugfs_remove(client->debugfs_dentry_lru); - debugfs_remove(client->debugfs_osdmap); - debugfs_remove(client->debugfs_mdsmap); - debugfs_remove(client->debugfs_monmap); - debugfs_remove(client->osdc.debugfs_file); - debugfs_remove(client->mdsc.debugfs_file); - debugfs_remove(client->monc.debugfs_file); - debugfs_remove(client->debugfs_congestion_kb); - debugfs_remove(client->debugfs_dir); -} #else /* CONFIG_DEBUG_FS */ -int __init ceph_debugfs_init(void) -{ - return 0; -} - -void ceph_debugfs_cleanup(void) -{ -} - -int ceph_debugfs_client_init(struct ceph_client *client) +int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { return 0; } -void ceph_debugfs_client_cleanup(struct ceph_client *client) +void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) { } diff --git a/fs/ceph/decode.h b/fs/ceph/decode.h deleted file mode 100644 index c5b6939fb32a..000000000000 --- a/fs/ceph/decode.h +++ /dev/null @@ -1,201 +0,0 @@ -#ifndef __CEPH_DECODE_H -#define __CEPH_DECODE_H - -#include -#include - -#include "types.h" - -/* - * in all cases, - * void **p pointer to position pointer - * void *end pointer to end of buffer (last byte + 1) - */ - -static inline u64 ceph_decode_64(void **p) -{ - u64 v = get_unaligned_le64(*p); - *p += sizeof(u64); - return v; -} -static inline u32 ceph_decode_32(void **p) -{ - u32 v = get_unaligned_le32(*p); - *p += sizeof(u32); - return v; -} -static inline u16 ceph_decode_16(void **p) -{ - u16 v = get_unaligned_le16(*p); - *p += sizeof(u16); - return v; -} -static inline u8 ceph_decode_8(void **p) -{ - u8 v = *(u8 *)*p; - (*p)++; - return v; -} -static inline void ceph_decode_copy(void **p, void *pv, size_t n) -{ - memcpy(pv, *p, n); - *p += n; -} - -/* - * bounds check input. - */ -#define ceph_decode_need(p, end, n, bad) \ - do { \ - if (unlikely(*(p) + (n) > (end))) \ - goto bad; \ - } while (0) - -#define ceph_decode_64_safe(p, end, v, bad) \ - do { \ - ceph_decode_need(p, end, sizeof(u64), bad); \ - v = ceph_decode_64(p); \ - } while (0) -#define ceph_decode_32_safe(p, end, v, bad) \ - do { \ - ceph_decode_need(p, end, sizeof(u32), bad); \ - v = ceph_decode_32(p); \ - } while (0) -#define ceph_decode_16_safe(p, end, v, bad) \ - do { \ - ceph_decode_need(p, end, sizeof(u16), bad); \ - v = ceph_decode_16(p); \ - } while (0) -#define ceph_decode_8_safe(p, end, v, bad) \ - do { \ - ceph_decode_need(p, end, sizeof(u8), bad); \ - v = ceph_decode_8(p); \ - } while (0) - -#define ceph_decode_copy_safe(p, end, pv, n, bad) \ - do { \ - ceph_decode_need(p, end, n, bad); \ - ceph_decode_copy(p, pv, n); \ - } while (0) - -/* - * struct ceph_timespec <-> struct timespec - */ -static inline void ceph_decode_timespec(struct timespec *ts, - const struct ceph_timespec *tv) -{ - ts->tv_sec = le32_to_cpu(tv->tv_sec); - ts->tv_nsec = le32_to_cpu(tv->tv_nsec); -} -static inline void ceph_encode_timespec(struct ceph_timespec *tv, - const struct timespec *ts) -{ - tv->tv_sec = cpu_to_le32(ts->tv_sec); - tv->tv_nsec = cpu_to_le32(ts->tv_nsec); -} - -/* - * sockaddr_storage <-> ceph_sockaddr - */ -static inline void ceph_encode_addr(struct ceph_entity_addr *a) -{ - __be16 ss_family = htons(a->in_addr.ss_family); - a->in_addr.ss_family = *(__u16 *)&ss_family; -} -static inline void ceph_decode_addr(struct ceph_entity_addr *a) -{ - __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; - a->in_addr.ss_family = ntohs(ss_family); - WARN_ON(a->in_addr.ss_family == 512); -} - -/* - * encoders - */ -static inline void ceph_encode_64(void **p, u64 v) -{ - put_unaligned_le64(v, (__le64 *)*p); - *p += sizeof(u64); -} -static inline void ceph_encode_32(void **p, u32 v) -{ - put_unaligned_le32(v, (__le32 *)*p); - *p += sizeof(u32); -} -static inline void ceph_encode_16(void **p, u16 v) -{ - put_unaligned_le16(v, (__le16 *)*p); - *p += sizeof(u16); -} -static inline void ceph_encode_8(void **p, u8 v) -{ - *(u8 *)*p = v; - (*p)++; -} -static inline void ceph_encode_copy(void **p, const void *s, int len) -{ - memcpy(*p, s, len); - *p += len; -} - -/* - * filepath, string encoders - */ -static inline void ceph_encode_filepath(void **p, void *end, - u64 ino, const char *path) -{ - u32 len = path ? strlen(path) : 0; - BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end); - ceph_encode_8(p, 1); - ceph_encode_64(p, ino); - ceph_encode_32(p, len); - if (len) - memcpy(*p, path, len); - *p += len; -} - -static inline void ceph_encode_string(void **p, void *end, - const char *s, u32 len) -{ - BUG_ON(*p + sizeof(len) + len > end); - ceph_encode_32(p, len); - if (len) - memcpy(*p, s, len); - *p += len; -} - -#define ceph_encode_need(p, end, n, bad) \ - do { \ - if (unlikely(*(p) + (n) > (end))) \ - goto bad; \ - } while (0) - -#define ceph_encode_64_safe(p, end, v, bad) \ - do { \ - ceph_encode_need(p, end, sizeof(u64), bad); \ - ceph_encode_64(p, v); \ - } while (0) -#define ceph_encode_32_safe(p, end, v, bad) \ - do { \ - ceph_encode_need(p, end, sizeof(u32), bad); \ - ceph_encode_32(p, v); \ - } while (0) -#define ceph_encode_16_safe(p, end, v, bad) \ - do { \ - ceph_encode_need(p, end, sizeof(u16), bad); \ - ceph_encode_16(p, v); \ - } while (0) - -#define ceph_encode_copy_safe(p, end, pv, n, bad) \ - do { \ - ceph_encode_need(p, end, n, bad); \ - ceph_encode_copy(p, pv, n); \ - } while (0) -#define ceph_encode_string_safe(p, end, s, n, bad) \ - do { \ - ceph_encode_need(p, end, n, bad); \ - ceph_encode_string(p, end, s, n); \ - } while (0) - - -#endif diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index a1986eb52045..a8d2aacc612b 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -7,6 +7,7 @@ #include #include "super.h" +#include "mds_client.h" /* * Directory operations: readdir, lookup, create, link, unlink, @@ -227,15 +228,15 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir) struct ceph_file_info *fi = filp->private_data; struct inode *inode = filp->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_client *client = ceph_inode_to_client(inode); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_client *mdsc = fsc->mdsc; unsigned frag = fpos_frag(filp->f_pos); int off = fpos_off(filp->f_pos); int err; u32 ftype; struct ceph_mds_reply_info_parsed *rinfo; - const int max_entries = client->mount_args->max_readdir; - const int max_bytes = client->mount_args->max_readdir_bytes; + const int max_entries = fsc->mount_options->max_readdir; + const int max_bytes = fsc->mount_options->max_readdir_bytes; dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off); if (fi->at_end) @@ -267,7 +268,7 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir) /* can we use the dcache? */ spin_lock(&inode->i_lock); if ((filp->f_pos == 2 || fi->dentry) && - !ceph_test_opt(client, NOASYNCREADDIR) && + !ceph_test_mount_opt(fsc, NOASYNCREADDIR) && ceph_snap(inode) != CEPH_SNAPDIR && (ci->i_ceph_flags & CEPH_I_COMPLETE) && __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) { @@ -487,14 +488,14 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin) struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, struct dentry *dentry, int err) { - struct ceph_client *client = ceph_sb_to_client(dentry->d_sb); + struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); struct inode *parent = dentry->d_parent->d_inode; /* .snap dir? */ if (err == -ENOENT && ceph_vino(parent).ino != CEPH_INO_ROOT && /* no .snap in root dir */ strcmp(dentry->d_name.name, - client->mount_args->snapdir_name) == 0) { + fsc->mount_options->snapdir_name) == 0) { struct inode *inode = ceph_get_snapdir(parent); dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n", dentry, dentry->d_name.len, dentry->d_name.name, inode); @@ -539,8 +540,8 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry) static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int op; int err; @@ -572,7 +573,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, spin_lock(&dir->i_lock); dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags); if (strncmp(dentry->d_name.name, - client->mount_args->snapdir_name, + fsc->mount_options->snapdir_name, dentry->d_name.len) && !is_root_ceph_dentry(dir, dentry) && (ci->i_ceph_flags & CEPH_I_COMPLETE) && @@ -629,8 +630,8 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry) static int ceph_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err; @@ -685,8 +686,8 @@ static int ceph_create(struct inode *dir, struct dentry *dentry, int mode, static int ceph_symlink(struct inode *dir, struct dentry *dentry, const char *dest) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err; @@ -716,8 +717,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, static int ceph_mkdir(struct inode *dir, struct dentry *dentry, int mode) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err = -EROFS; int op; @@ -758,8 +759,8 @@ out: static int ceph_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err; @@ -813,8 +814,8 @@ static int drop_caps_for_unlink(struct inode *inode) */ static int ceph_unlink(struct inode *dir, struct dentry *dentry) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = dentry->d_inode; struct ceph_mds_request *req; int err = -EROFS; @@ -854,8 +855,8 @@ out: static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { - struct ceph_client *client = ceph_sb_to_client(old_dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err; @@ -1076,7 +1077,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size, struct ceph_inode_info *ci = ceph_inode(inode); int left; - if (!ceph_test_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT)) + if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT)) return -EISDIR; if (!cf->dir_info) { @@ -1177,7 +1178,7 @@ void ceph_dentry_lru_add(struct dentry *dn) dout("dentry_lru_add %p %p '%.*s'\n", di, dn, dn->d_name.len, dn->d_name.name); if (di) { - mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc; + mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_add_tail(&di->lru, &mdsc->dentry_lru); mdsc->num_dentry++; @@ -1193,7 +1194,7 @@ void ceph_dentry_lru_touch(struct dentry *dn) dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn, dn->d_name.len, dn->d_name.name, di->offset); if (di) { - mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc; + mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_move_tail(&di->lru, &mdsc->dentry_lru); spin_unlock(&mdsc->dentry_lru_lock); @@ -1208,7 +1209,7 @@ void ceph_dentry_lru_del(struct dentry *dn) dout("dentry_lru_del %p %p '%.*s'\n", di, dn, dn->d_name.len, dn->d_name.name); if (di) { - mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc; + mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_del_init(&di->lru); mdsc->num_dentry--; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index e38423e82f2e..2297d9426992 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -1,10 +1,11 @@ -#include "ceph_debug.h" +#include #include #include #include #include "super.h" +#include "mds_client.h" /* * NFS export support @@ -120,7 +121,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, static struct dentry *__cfh_to_dentry(struct super_block *sb, struct ceph_nfs_confh *cfh) { - struct ceph_mds_client *mdsc = &ceph_sb_to_client(sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc; struct inode *inode; struct dentry *dentry; struct ceph_vino vino; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 66e4da6dba22..e77c28cf3690 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1,5 +1,6 @@ -#include "ceph_debug.h" +#include +#include #include #include #include @@ -38,8 +39,8 @@ static struct ceph_mds_request * prepare_open_request(struct super_block *sb, int flags, int create_mode) { - struct ceph_client *client = ceph_sb_to_client(sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int want_auth = USE_ANY_MDS; int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN; @@ -117,8 +118,8 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) int ceph_open(struct inode *inode, struct file *file) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_client *client = ceph_sb_to_client(inode->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; struct ceph_file_info *cf = file->private_data; struct inode *parent_inode = file->f_dentry->d_parent->d_inode; @@ -216,8 +217,8 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd, int mode, int locked_dir) { - struct ceph_client *client = ceph_sb_to_client(dir->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct file *file = nd->intent.open.file; struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry); struct ceph_mds_request *req; @@ -269,163 +270,6 @@ int ceph_release(struct inode *inode, struct file *file) return 0; } -/* - * build a vector of user pages - */ -static struct page **get_direct_page_vector(const char __user *data, - int num_pages, - loff_t off, size_t len) -{ - struct page **pages; - int rc; - - pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS); - if (!pages) - return ERR_PTR(-ENOMEM); - - down_read(¤t->mm->mmap_sem); - rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, 0, 0, pages, NULL); - up_read(¤t->mm->mmap_sem); - if (rc < 0) - goto fail; - return pages; - -fail: - kfree(pages); - return ERR_PTR(rc); -} - -static void put_page_vector(struct page **pages, int num_pages) -{ - int i; - - for (i = 0; i < num_pages; i++) - put_page(pages[i]); - kfree(pages); -} - -void ceph_release_page_vector(struct page **pages, int num_pages) -{ - int i; - - for (i = 0; i < num_pages; i++) - __free_pages(pages[i], 0); - kfree(pages); -} - -/* - * allocate a vector new pages - */ -static struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags) -{ - struct page **pages; - int i; - - pages = kmalloc(sizeof(*pages) * num_pages, flags); - if (!pages) - return ERR_PTR(-ENOMEM); - for (i = 0; i < num_pages; i++) { - pages[i] = __page_cache_alloc(flags); - if (pages[i] == NULL) { - ceph_release_page_vector(pages, i); - return ERR_PTR(-ENOMEM); - } - } - return pages; -} - -/* - * copy user data into a page vector - */ -static int copy_user_to_page_vector(struct page **pages, - const char __user *data, - loff_t off, size_t len) -{ - int i = 0; - int po = off & ~PAGE_CACHE_MASK; - int left = len; - int l, bad; - - while (left > 0) { - l = min_t(int, PAGE_CACHE_SIZE-po, left); - bad = copy_from_user(page_address(pages[i]) + po, data, l); - if (bad == l) - return -EFAULT; - data += l - bad; - left -= l - bad; - po += l - bad; - if (po == PAGE_CACHE_SIZE) { - po = 0; - i++; - } - } - return len; -} - -/* - * copy user data from a page vector into a user pointer - */ -static int copy_page_vector_to_user(struct page **pages, char __user *data, - loff_t off, size_t len) -{ - int i = 0; - int po = off & ~PAGE_CACHE_MASK; - int left = len; - int l, bad; - - while (left > 0) { - l = min_t(int, left, PAGE_CACHE_SIZE-po); - bad = copy_to_user(data, page_address(pages[i]) + po, l); - if (bad == l) - return -EFAULT; - data += l - bad; - left -= l - bad; - if (po) { - po += l - bad; - if (po == PAGE_CACHE_SIZE) - po = 0; - } - i++; - } - return len; -} - -/* - * Zero an extent within a page vector. Offset is relative to the - * start of the first page. - */ -static void zero_page_vector_range(int off, int len, struct page **pages) -{ - int i = off >> PAGE_CACHE_SHIFT; - - off &= ~PAGE_CACHE_MASK; - - dout("zero_page_vector_page %u~%u\n", off, len); - - /* leading partial page? */ - if (off) { - int end = min((int)PAGE_CACHE_SIZE, off + len); - dout("zeroing %d %p head from %d\n", i, pages[i], - (int)off); - zero_user_segment(pages[i], off, end); - len -= (end - off); - i++; - } - while (len >= PAGE_CACHE_SIZE) { - dout("zeroing %d %p len=%d\n", i, pages[i], len); - zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); - len -= PAGE_CACHE_SIZE; - i++; - } - /* trailing partial page? */ - if (len) { - dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len); - zero_user_segment(pages[i], 0, len); - } -} - - /* * Read a range of bytes striped over one or more objects. Iterate over * objects we stripe over. (That's not atomic, but good enough for now.) @@ -438,7 +282,7 @@ static int striped_read(struct inode *inode, struct page **pages, int num_pages, int *checkeof) { - struct ceph_client *client = ceph_inode_to_client(inode); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); u64 pos, this_len; int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */ @@ -459,7 +303,7 @@ static int striped_read(struct inode *inode, more: this_len = left; - ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode), + ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode), &ci->i_layout, pos, &this_len, ci->i_truncate_seq, ci->i_truncate_size, @@ -477,8 +321,8 @@ more: if (read < pos - off) { dout(" zero gap %llu to %llu\n", off + read, pos); - zero_page_vector_range(page_off + read, - pos - off - read, pages); + ceph_zero_page_vector_range(page_off + read, + pos - off - read, pages); } pos += ret; read = pos - off; @@ -495,8 +339,8 @@ more: /* was original extent fully inside i_size? */ if (pos + left <= inode->i_size) { dout("zero tail\n"); - zero_page_vector_range(page_off + read, len - read, - pages); + ceph_zero_page_vector_range(page_off + read, len - read, + pages); read = len; goto out; } @@ -531,7 +375,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); if (file->f_flags & O_DIRECT) { - pages = get_direct_page_vector(data, num_pages, off, len); + pages = ceph_get_direct_page_vector(data, num_pages, off, len); /* * flush any page cache pages in this range. this @@ -552,13 +396,13 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data, ret = striped_read(inode, off, len, pages, num_pages, checkeof); if (ret >= 0 && (file->f_flags & O_DIRECT) == 0) - ret = copy_page_vector_to_user(pages, data, off, ret); + ret = ceph_copy_page_vector_to_user(pages, data, off, ret); if (ret >= 0) *poff = off + ret; done: if (file->f_flags & O_DIRECT) - put_page_vector(pages, num_pages); + ceph_put_page_vector(pages, num_pages); else ceph_release_page_vector(pages, num_pages); dout("sync_read result %d\n", ret); @@ -594,7 +438,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, { struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_client *client = ceph_inode_to_client(inode); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_osd_request *req; struct page **pages; int num_pages; @@ -642,7 +486,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, */ more: len = left; - req = ceph_osdc_new_request(&client->osdc, &ci->i_layout, + req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, ceph_vino(inode), pos, &len, CEPH_OSD_OP_WRITE, flags, ci->i_snap_realm->cached_context, @@ -655,7 +499,7 @@ more: num_pages = calc_pages_for(pos, len); if (file->f_flags & O_DIRECT) { - pages = get_direct_page_vector(data, num_pages, pos, len); + pages = ceph_get_direct_page_vector(data, num_pages, pos, len); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out; @@ -673,7 +517,7 @@ more: ret = PTR_ERR(pages); goto out; } - ret = copy_user_to_page_vector(pages, data, pos, len); + ret = ceph_copy_user_to_page_vector(pages, data, pos, len); if (ret < 0) { ceph_release_page_vector(pages, num_pages); goto out; @@ -689,7 +533,7 @@ more: req->r_num_pages = num_pages; req->r_inode = inode; - ret = ceph_osdc_start_request(&client->osdc, req, false); + ret = ceph_osdc_start_request(&fsc->client->osdc, req, false); if (!ret) { if (req->r_safe_callback) { /* @@ -701,11 +545,11 @@ more: spin_unlock(&ci->i_unsafe_lock); ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR); } - ret = ceph_osdc_wait_request(&client->osdc, req); + ret = ceph_osdc_wait_request(&fsc->client->osdc, req); } if (file->f_flags & O_DIRECT) - put_page_vector(pages, num_pages); + ceph_put_page_vector(pages, num_pages); else if (file->f_flags & O_SYNC) ceph_release_page_vector(pages, num_pages); @@ -814,7 +658,8 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, struct ceph_file_info *fi = file->private_data; struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc; + struct ceph_osd_client *osdc = + &ceph_sb_to_client(inode->i_sb)->client->osdc; loff_t endoff = pos + iov->iov_len; int want, got = 0; int ret, err; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 62377ec37edf..1d6a45b5a04c 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -13,7 +13,8 @@ #include #include "super.h" -#include "decode.h" +#include "mds_client.h" +#include /* * Ceph inode operations @@ -384,7 +385,7 @@ void ceph_destroy_inode(struct inode *inode) */ if (ci->i_snap_realm) { struct ceph_mds_client *mdsc = - &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; + ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; struct ceph_snap_realm *realm = ci->i_snap_realm; dout(" dropping residual ref to snap realm %p\n", realm); @@ -685,7 +686,7 @@ static int fill_inode(struct inode *inode, } /* it may be better to set st_size in getattr instead? */ - if (ceph_test_opt(ceph_sb_to_client(inode->i_sb), RBYTES)) + if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES)) inode->i_size = ci->i_rbytes; break; default: @@ -901,7 +902,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct inode *in = NULL; struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; - struct ceph_client *client = ceph_sb_to_client(sb); + struct ceph_fs_client *fsc = ceph_sb_to_client(sb); int i = 0; int err = 0; @@ -965,7 +966,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, */ if (rinfo->head->is_dentry && !req->r_aborted && (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name, - client->mount_args->snapdir_name, + fsc->mount_options->snapdir_name, req->r_dentry->d_name.len))) { /* * lookup link rename : null -> possibly existing inode @@ -1533,7 +1534,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) struct inode *parent_inode = dentry->d_parent->d_inode; const unsigned int ia_valid = attr->ia_valid; struct ceph_mds_request *req; - struct ceph_mds_client *mdsc = &ceph_sb_to_client(dentry->d_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc; int issued; int release = 0, dirtied = 0; int mask = 0; @@ -1728,8 +1729,8 @@ out: */ int ceph_do_getattr(struct inode *inode, int mask) { - struct ceph_client *client = ceph_sb_to_client(inode->i_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; int err; diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 76e307d2aba1..899578b0c46b 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -1,8 +1,10 @@ #include -#include "ioctl.h" #include "super.h" -#include "ceph_debug.h" +#include "mds_client.h" +#include + +#include "ioctl.h" /* @@ -37,7 +39,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) { struct inode *inode = file->f_dentry->d_inode; struct inode *parent_inode = file->f_dentry->d_parent->d_inode; - struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_mds_request *req; struct ceph_ioctl_layout l; int err, i; @@ -98,7 +100,8 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) struct ceph_ioctl_dataloc dl; struct inode *inode = file->f_dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc; + struct ceph_osd_client *osdc = + &ceph_sb_to_client(inode->i_sb)->client->osdc; u64 len = 1, olen; u64 tmp; struct ceph_object_layout ol; diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index ff4e753aae92..087afe9ca367 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -1,11 +1,11 @@ -#include "ceph_debug.h" +#include #include #include #include "super.h" #include "mds_client.h" -#include "pagelist.h" +#include /** * Implement fcntl and flock locking functions. @@ -16,7 +16,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file, { struct inode *inode = file->f_dentry->d_inode; struct ceph_mds_client *mdsc = - &ceph_sb_to_client(inode->i_sb)->mdsc; + ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_mds_request *req; int err; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fad95f8f2608..33568239a08e 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1,17 +1,20 @@ -#include "ceph_debug.h" +#include #include #include #include #include +#include +#include -#include "mds_client.h" -#include "mon_client.h" #include "super.h" -#include "messenger.h" -#include "decode.h" -#include "auth.h" -#include "pagelist.h" +#include "mds_client.h" + +#include +#include +#include +#include +#include /* * A cluster of MDS (metadata server) daemons is responsible for @@ -286,8 +289,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s) atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1); if (atomic_dec_and_test(&s->s_ref)) { if (s->s_authorizer) - s->s_mdsc->client->monc.auth->ops->destroy_authorizer( - s->s_mdsc->client->monc.auth, s->s_authorizer); + s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer( + s->s_mdsc->fsc->client->monc.auth, + s->s_authorizer); kfree(s); } } @@ -344,7 +348,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, s->s_seq = 0; mutex_init(&s->s_mutex); - ceph_con_init(mdsc->client->msgr, &s->s_con); + ceph_con_init(mdsc->fsc->client->msgr, &s->s_con); s->s_con.private = s; s->s_con.ops = &mds_con_ops; s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS; @@ -599,7 +603,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, } else if (req->r_dentry) { struct inode *dir = req->r_dentry->d_parent->d_inode; - if (dir->i_sb != mdsc->client->sb) { + if (dir->i_sb != mdsc->fsc->sb) { /* not this fs! */ inode = req->r_dentry->d_inode; } else if (ceph_snap(dir) != CEPH_NOSNAP) { @@ -884,7 +888,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, __ceph_remove_cap(cap); if (!__ceph_is_any_real_caps(ci)) { struct ceph_mds_client *mdsc = - &ceph_sb_to_client(inode->i_sb)->mdsc; + ceph_sb_to_client(inode->i_sb)->mdsc; spin_lock(&mdsc->cap_dirty_lock); if (!list_empty(&ci->i_dirty_item)) { @@ -1146,7 +1150,7 @@ int ceph_add_cap_releases(struct ceph_mds_client *mdsc, struct ceph_msg *msg, *partial = NULL; struct ceph_mds_cap_release *head; int err = -ENOMEM; - int extra = mdsc->client->mount_args->cap_release_safety; + int extra = mdsc->fsc->mount_options->cap_release_safety; int num; dout("add_cap_releases %p mds%d extra %d\n", session, session->s_mds, @@ -2085,7 +2089,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) /* insert trace into our cache */ mutex_lock(&req->r_fill_mutex); - err = ceph_fill_trace(mdsc->client->sb, req, req->r_session); + err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session); if (err == 0) { if (result == 0 && rinfo->dir_nr) ceph_readdir_prepopulate(req, req->r_session); @@ -2613,7 +2617,7 @@ static void handle_lease(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg) { - struct super_block *sb = mdsc->client->sb; + struct super_block *sb = mdsc->fsc->sb; struct inode *inode; struct ceph_inode_info *ci; struct dentry *parent, *dentry; @@ -2891,10 +2895,16 @@ static void delayed_work(struct work_struct *work) schedule_delayed(mdsc); } +int ceph_mdsc_init(struct ceph_fs_client *fsc) -int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client) { - mdsc->client = client; + struct ceph_mds_client *mdsc; + + mdsc = kzalloc(sizeof(struct ceph_mds_client), GFP_NOFS); + if (!mdsc) + return -ENOMEM; + mdsc->fsc = fsc; + fsc->mdsc = mdsc; mutex_init(&mdsc->mutex); mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS); if (mdsc->mdsmap == NULL) @@ -2927,7 +2937,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client) INIT_LIST_HEAD(&mdsc->dentry_lru); ceph_caps_init(mdsc); - ceph_adjust_min_caps(mdsc, client->min_caps); + ceph_adjust_min_caps(mdsc, fsc->min_caps); return 0; } @@ -2939,7 +2949,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client) static void wait_requests(struct ceph_mds_client *mdsc) { struct ceph_mds_request *req; - struct ceph_client *client = mdsc->client; + struct ceph_fs_client *fsc = mdsc->fsc; mutex_lock(&mdsc->mutex); if (__get_oldest_req(mdsc)) { @@ -2947,7 +2957,7 @@ static void wait_requests(struct ceph_mds_client *mdsc) dout("wait_requests waiting for requests\n"); wait_for_completion_timeout(&mdsc->safe_umount_waiters, - client->mount_args->mount_timeout * HZ); + fsc->client->options->mount_timeout * HZ); /* tear down remaining requests */ mutex_lock(&mdsc->mutex); @@ -3030,7 +3040,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc) { u64 want_tid, want_flush; - if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN) + if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN) return; dout("sync\n"); @@ -3053,7 +3063,7 @@ bool done_closing_sessions(struct ceph_mds_client *mdsc) { int i, n = 0; - if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN) + if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN) return true; mutex_lock(&mdsc->mutex); @@ -3071,8 +3081,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) { struct ceph_mds_session *session; int i; - struct ceph_client *client = mdsc->client; - unsigned long timeout = client->mount_args->mount_timeout * HZ; + struct ceph_fs_client *fsc = mdsc->fsc; + unsigned long timeout = fsc->client->options->mount_timeout * HZ; dout("close_sessions\n"); @@ -3119,7 +3129,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) dout("stopped\n"); } -void ceph_mdsc_stop(struct ceph_mds_client *mdsc) +static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) { dout("stop\n"); cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */ @@ -3129,6 +3139,15 @@ void ceph_mdsc_stop(struct ceph_mds_client *mdsc) ceph_caps_finalize(mdsc); } +void ceph_mdsc_destroy(struct ceph_fs_client *fsc) +{ + struct ceph_mds_client *mdsc = fsc->mdsc; + + ceph_mdsc_stop(mdsc); + fsc->mdsc = NULL; + kfree(mdsc); +} + /* * handle mds map update. @@ -3145,14 +3164,14 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg) ceph_decode_need(&p, end, sizeof(fsid)+2*sizeof(u32), bad); ceph_decode_copy(&p, &fsid, sizeof(fsid)); - if (ceph_check_fsid(mdsc->client, &fsid) < 0) + if (ceph_check_fsid(mdsc->fsc->client, &fsid) < 0) return; epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); dout("handle_map epoch %u len %d\n", epoch, (int)maplen); /* do we need it? */ - ceph_monc_got_mdsmap(&mdsc->client->monc, epoch); + ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch); mutex_lock(&mdsc->mutex); if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) { dout("handle_map epoch %u <= our %u\n", @@ -3176,7 +3195,7 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg) } else { mdsc->mdsmap = newmap; /* first mds map */ } - mdsc->client->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size; + mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size; __wake_requests(mdsc, &mdsc->waiting_for_map); @@ -3277,7 +3296,7 @@ static int get_authorizer(struct ceph_connection *con, { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; - struct ceph_auth_client *ac = mdsc->client->monc.auth; + struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth; int ret = 0; if (force_new && s->s_authorizer) { @@ -3311,7 +3330,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; - struct ceph_auth_client *ac = mdsc->client->monc.auth; + struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth; return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len); } @@ -3320,12 +3339,12 @@ static int invalidate_authorizer(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; - struct ceph_auth_client *ac = mdsc->client->monc.auth; + struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth; if (ac->ops->invalidate_authorizer) ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS); - return ceph_monc_validate_auth(&mdsc->client->monc); + return ceph_monc_validate_auth(&mdsc->fsc->client->monc); } static const struct ceph_connection_operations mds_con_ops = { @@ -3338,7 +3357,4 @@ static const struct ceph_connection_operations mds_con_ops = { .peer_reset = peer_reset, }; - - - /* eof */ diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index c98267ce6d2a..d66d63c72355 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -8,9 +8,9 @@ #include #include -#include "types.h" -#include "messenger.h" -#include "mdsmap.h" +#include +#include +#include /* * Some lock dependencies: @@ -26,7 +26,7 @@ * */ -struct ceph_client; +struct ceph_fs_client; struct ceph_cap; /* @@ -230,7 +230,7 @@ struct ceph_mds_request { * mds client state */ struct ceph_mds_client { - struct ceph_client *client; + struct ceph_fs_client *fsc; struct mutex mutex; /* all nested structures */ struct ceph_mdsmap *mdsmap; @@ -289,11 +289,6 @@ struct ceph_mds_client { int caps_avail_count; /* unused, unreserved */ int caps_min_count; /* keep at least this many (unreserved) */ - -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs_file; -#endif - spinlock_t dentry_lru_lock; struct list_head dentry_lru; int num_dentry; @@ -316,10 +311,9 @@ extern void ceph_put_mds_session(struct ceph_mds_session *s); extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, struct ceph_msg *msg, int mds); -extern int ceph_mdsc_init(struct ceph_mds_client *mdsc, - struct ceph_client *client); +extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); -extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc); +extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc); extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 040be6d1150b..73b7d44e8a35 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -1,4 +1,4 @@ -#include "ceph_debug.h" +#include #include #include @@ -6,9 +6,9 @@ #include #include -#include "mdsmap.h" -#include "messenger.h" -#include "decode.h" +#include +#include +#include #include "super.h" @@ -117,7 +117,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) } dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n", - i+1, n, global_id, mds, inc, pr_addr(&addr.in_addr), + i+1, n, global_id, mds, inc, + ceph_pr_addr(&addr.in_addr), ceph_mds_state_name(state)); if (mds >= 0 && mds < m->m_max_mds && state > 0) { m->m_info[mds].global_id = global_id; diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h deleted file mode 100644 index 4c5cb0880bba..000000000000 --- a/fs/ceph/mdsmap.h +++ /dev/null @@ -1,62 +0,0 @@ -#ifndef _FS_CEPH_MDSMAP_H -#define _FS_CEPH_MDSMAP_H - -#include "types.h" - -/* - * mds map - describe servers in the mds cluster. - * - * we limit fields to those the client actually xcares about - */ -struct ceph_mds_info { - u64 global_id; - struct ceph_entity_addr addr; - s32 state; - int num_export_targets; - bool laggy; - u32 *export_targets; -}; - -struct ceph_mdsmap { - u32 m_epoch, m_client_epoch, m_last_failure; - u32 m_root; - u32 m_session_timeout; /* seconds */ - u32 m_session_autoclose; /* seconds */ - u64 m_max_file_size; - u32 m_max_mds; /* size of m_addr, m_state arrays */ - struct ceph_mds_info *m_info; - - /* which object pools file data can be stored in */ - int m_num_data_pg_pools; - u32 *m_data_pg_pools; - u32 m_cas_pg_pool; -}; - -static inline struct ceph_entity_addr * -ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) -{ - if (w >= m->m_max_mds) - return NULL; - return &m->m_info[w].addr; -} - -static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) -{ - BUG_ON(w < 0); - if (w >= m->m_max_mds) - return CEPH_MDS_STATE_DNE; - return m->m_info[w].state; -} - -static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) -{ - if (w >= 0 && w < m->m_max_mds) - return m->m_info[w].laggy; - return false; -} - -extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m); -extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end); -extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m); - -#endif diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c deleted file mode 100644 index 17a09b32a591..000000000000 --- a/fs/ceph/messenger.c +++ /dev/null @@ -1,2432 +0,0 @@ -#include "ceph_debug.h" - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "super.h" -#include "messenger.h" -#include "decode.h" -#include "pagelist.h" - -/* - * Ceph uses the messenger to exchange ceph_msg messages with other - * hosts in the system. The messenger provides ordered and reliable - * delivery. We tolerate TCP disconnects by reconnecting (with - * exponential backoff) in the case of a fault (disconnection, bad - * crc, protocol error). Acks allow sent messages to be discarded by - * the sender. - */ - -/* static tag bytes (protocol control messages) */ -static char tag_msg = CEPH_MSGR_TAG_MSG; -static char tag_ack = CEPH_MSGR_TAG_ACK; -static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE; - -#ifdef CONFIG_LOCKDEP -static struct lock_class_key socket_class; -#endif - - -static void queue_con(struct ceph_connection *con); -static void con_work(struct work_struct *); -static void ceph_fault(struct ceph_connection *con); - -/* - * nicely render a sockaddr as a string. - */ -#define MAX_ADDR_STR 20 -#define MAX_ADDR_STR_LEN 60 -static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN]; -static DEFINE_SPINLOCK(addr_str_lock); -static int last_addr_str; - -const char *pr_addr(const struct sockaddr_storage *ss) -{ - int i; - char *s; - struct sockaddr_in *in4 = (void *)ss; - struct sockaddr_in6 *in6 = (void *)ss; - - spin_lock(&addr_str_lock); - i = last_addr_str++; - if (last_addr_str == MAX_ADDR_STR) - last_addr_str = 0; - spin_unlock(&addr_str_lock); - s = addr_str[i]; - - switch (ss->ss_family) { - case AF_INET: - snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr, - (unsigned int)ntohs(in4->sin_port)); - break; - - case AF_INET6: - snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr, - (unsigned int)ntohs(in6->sin6_port)); - break; - - default: - sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family); - } - - return s; -} - -static void encode_my_addr(struct ceph_messenger *msgr) -{ - memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr)); - ceph_encode_addr(&msgr->my_enc_addr); -} - -/* - * work queue for all reading and writing to/from the socket. - */ -struct workqueue_struct *ceph_msgr_wq; - -int __init ceph_msgr_init(void) -{ - ceph_msgr_wq = create_workqueue("ceph-msgr"); - if (IS_ERR(ceph_msgr_wq)) { - int ret = PTR_ERR(ceph_msgr_wq); - pr_err("msgr_init failed to create workqueue: %d\n", ret); - ceph_msgr_wq = NULL; - return ret; - } - return 0; -} - -void ceph_msgr_exit(void) -{ - destroy_workqueue(ceph_msgr_wq); -} - -void ceph_msgr_flush(void) -{ - flush_workqueue(ceph_msgr_wq); -} - - -/* - * socket callback functions - */ - -/* data available on socket, or listen socket received a connect */ -static void ceph_data_ready(struct sock *sk, int count_unused) -{ - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; - if (sk->sk_state != TCP_CLOSE_WAIT) { - dout("ceph_data_ready on %p state = %lu, queueing work\n", - con, con->state); - queue_con(con); - } -} - -/* socket has buffer space for writing */ -static void ceph_write_space(struct sock *sk) -{ - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; - - /* only queue to workqueue if there is data we want to write. */ - if (test_bit(WRITE_PENDING, &con->state)) { - dout("ceph_write_space %p queueing write work\n", con); - queue_con(con); - } else { - dout("ceph_write_space %p nothing to write\n", con); - } - - /* since we have our own write_space, clear the SOCK_NOSPACE flag */ - clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -} - -/* socket's state has changed */ -static void ceph_state_change(struct sock *sk) -{ - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; - - dout("ceph_state_change %p state = %lu sk_state = %u\n", - con, con->state, sk->sk_state); - - if (test_bit(CLOSED, &con->state)) - return; - - switch (sk->sk_state) { - case TCP_CLOSE: - dout("ceph_state_change TCP_CLOSE\n"); - case TCP_CLOSE_WAIT: - dout("ceph_state_change TCP_CLOSE_WAIT\n"); - if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) { - if (test_bit(CONNECTING, &con->state)) - con->error_msg = "connection failed"; - else - con->error_msg = "socket closed"; - queue_con(con); - } - break; - case TCP_ESTABLISHED: - dout("ceph_state_change TCP_ESTABLISHED\n"); - queue_con(con); - break; - } -} - -/* - * set up socket callbacks - */ -static void set_sock_callbacks(struct socket *sock, - struct ceph_connection *con) -{ - struct sock *sk = sock->sk; - sk->sk_user_data = (void *)con; - sk->sk_data_ready = ceph_data_ready; - sk->sk_write_space = ceph_write_space; - sk->sk_state_change = ceph_state_change; -} - - -/* - * socket helpers - */ - -/* - * initiate connection to a remote socket. - */ -static struct socket *ceph_tcp_connect(struct ceph_connection *con) -{ - struct sockaddr_storage *paddr = &con->peer_addr.in_addr; - struct socket *sock; - int ret; - - BUG_ON(con->sock); - ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM, - IPPROTO_TCP, &sock); - if (ret) - return ERR_PTR(ret); - con->sock = sock; - sock->sk->sk_allocation = GFP_NOFS; - -#ifdef CONFIG_LOCKDEP - lockdep_set_class(&sock->sk->sk_lock, &socket_class); -#endif - - set_sock_callbacks(sock, con); - - dout("connect %s\n", pr_addr(&con->peer_addr.in_addr)); - - ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr), - O_NONBLOCK); - if (ret == -EINPROGRESS) { - dout("connect %s EINPROGRESS sk_state = %u\n", - pr_addr(&con->peer_addr.in_addr), - sock->sk->sk_state); - ret = 0; - } - if (ret < 0) { - pr_err("connect %s error %d\n", - pr_addr(&con->peer_addr.in_addr), ret); - sock_release(sock); - con->sock = NULL; - con->error_msg = "connect error"; - } - - if (ret < 0) - return ERR_PTR(ret); - return sock; -} - -static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) -{ - struct kvec iov = {buf, len}; - struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; - - return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); -} - -/* - * write something. @more is true if caller will be sending more data - * shortly. - */ -static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, - size_t kvlen, size_t len, int more) -{ - struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; - - if (more) - msg.msg_flags |= MSG_MORE; - else - msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - - return kernel_sendmsg(sock, &msg, iov, kvlen, len); -} - - -/* - * Shutdown/close the socket for the given connection. - */ -static int con_close_socket(struct ceph_connection *con) -{ - int rc; - - dout("con_close_socket on %p sock %p\n", con, con->sock); - if (!con->sock) - return 0; - set_bit(SOCK_CLOSED, &con->state); - rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); - sock_release(con->sock); - con->sock = NULL; - clear_bit(SOCK_CLOSED, &con->state); - return rc; -} - -/* - * Reset a connection. Discard all incoming and outgoing messages - * and clear *_seq state. - */ -static void ceph_msg_remove(struct ceph_msg *msg) -{ - list_del_init(&msg->list_head); - ceph_msg_put(msg); -} -static void ceph_msg_remove_list(struct list_head *head) -{ - while (!list_empty(head)) { - struct ceph_msg *msg = list_first_entry(head, struct ceph_msg, - list_head); - ceph_msg_remove(msg); - } -} - -static void reset_connection(struct ceph_connection *con) -{ - /* reset connection, out_queue, msg_ and connect_seq */ - /* discard existing out_queue and msg_seq */ - ceph_msg_remove_list(&con->out_queue); - ceph_msg_remove_list(&con->out_sent); - - if (con->in_msg) { - ceph_msg_put(con->in_msg); - con->in_msg = NULL; - } - - con->connect_seq = 0; - con->out_seq = 0; - if (con->out_msg) { - ceph_msg_put(con->out_msg); - con->out_msg = NULL; - } - con->out_keepalive_pending = false; - con->in_seq = 0; - con->in_seq_acked = 0; -} - -/* - * mark a peer down. drop any open connections. - */ -void ceph_con_close(struct ceph_connection *con) -{ - dout("con_close %p peer %s\n", con, pr_addr(&con->peer_addr.in_addr)); - set_bit(CLOSED, &con->state); /* in case there's queued work */ - clear_bit(STANDBY, &con->state); /* avoid connect_seq bump */ - clear_bit(LOSSYTX, &con->state); /* so we retry next connect */ - clear_bit(KEEPALIVE_PENDING, &con->state); - clear_bit(WRITE_PENDING, &con->state); - mutex_lock(&con->mutex); - reset_connection(con); - con->peer_global_seq = 0; - cancel_delayed_work(&con->work); - mutex_unlock(&con->mutex); - queue_con(con); -} - -/* - * Reopen a closed connection, with a new peer address. - */ -void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr) -{ - dout("con_open %p %s\n", con, pr_addr(&addr->in_addr)); - set_bit(OPENING, &con->state); - clear_bit(CLOSED, &con->state); - memcpy(&con->peer_addr, addr, sizeof(*addr)); - con->delay = 0; /* reset backoff memory */ - queue_con(con); -} - -/* - * return true if this connection ever successfully opened - */ -bool ceph_con_opened(struct ceph_connection *con) -{ - return con->connect_seq > 0; -} - -/* - * generic get/put - */ -struct ceph_connection *ceph_con_get(struct ceph_connection *con) -{ - dout("con_get %p nref = %d -> %d\n", con, - atomic_read(&con->nref), atomic_read(&con->nref) + 1); - if (atomic_inc_not_zero(&con->nref)) - return con; - return NULL; -} - -void ceph_con_put(struct ceph_connection *con) -{ - dout("con_put %p nref = %d -> %d\n", con, - atomic_read(&con->nref), atomic_read(&con->nref) - 1); - BUG_ON(atomic_read(&con->nref) == 0); - if (atomic_dec_and_test(&con->nref)) { - BUG_ON(con->sock); - kfree(con); - } -} - -/* - * initialize a new connection. - */ -void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con) -{ - dout("con_init %p\n", con); - memset(con, 0, sizeof(*con)); - atomic_set(&con->nref, 1); - con->msgr = msgr; - mutex_init(&con->mutex); - INIT_LIST_HEAD(&con->out_queue); - INIT_LIST_HEAD(&con->out_sent); - INIT_DELAYED_WORK(&con->work, con_work); -} - - -/* - * We maintain a global counter to order connection attempts. Get - * a unique seq greater than @gt. - */ -static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) -{ - u32 ret; - - spin_lock(&msgr->global_seq_lock); - if (msgr->global_seq < gt) - msgr->global_seq = gt; - ret = ++msgr->global_seq; - spin_unlock(&msgr->global_seq_lock); - return ret; -} - - -/* - * Prepare footer for currently outgoing message, and finish things - * off. Assumes out_kvec* are already valid.. we just add on to the end. - */ -static void prepare_write_message_footer(struct ceph_connection *con, int v) -{ - struct ceph_msg *m = con->out_msg; - - dout("prepare_write_message_footer %p\n", con); - con->out_kvec_is_msg = true; - con->out_kvec[v].iov_base = &m->footer; - con->out_kvec[v].iov_len = sizeof(m->footer); - con->out_kvec_bytes += sizeof(m->footer); - con->out_kvec_left++; - con->out_more = m->more_to_follow; - con->out_msg_done = true; -} - -/* - * Prepare headers for the next outgoing message. - */ -static void prepare_write_message(struct ceph_connection *con) -{ - struct ceph_msg *m; - int v = 0; - - con->out_kvec_bytes = 0; - con->out_kvec_is_msg = true; - con->out_msg_done = false; - - /* Sneak an ack in there first? If we can get it into the same - * TCP packet that's a good thing. */ - if (con->in_seq > con->in_seq_acked) { - con->in_seq_acked = con->in_seq; - con->out_kvec[v].iov_base = &tag_ack; - con->out_kvec[v++].iov_len = 1; - con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - con->out_kvec[v].iov_base = &con->out_temp_ack; - con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack); - con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); - } - - m = list_first_entry(&con->out_queue, - struct ceph_msg, list_head); - con->out_msg = m; - if (test_bit(LOSSYTX, &con->state)) { - list_del_init(&m->list_head); - } else { - /* put message on sent list */ - ceph_msg_get(m); - list_move_tail(&m->list_head, &con->out_sent); - } - - /* - * only assign outgoing seq # if we haven't sent this message - * yet. if it is requeued, resend with it's original seq. - */ - if (m->needs_out_seq) { - m->hdr.seq = cpu_to_le64(++con->out_seq); - m->needs_out_seq = false; - } - - dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n", - m, con->out_seq, le16_to_cpu(m->hdr.type), - le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len), - le32_to_cpu(m->hdr.data_len), - m->nr_pages); - BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len); - - /* tag + hdr + front + middle */ - con->out_kvec[v].iov_base = &tag_msg; - con->out_kvec[v++].iov_len = 1; - con->out_kvec[v].iov_base = &m->hdr; - con->out_kvec[v++].iov_len = sizeof(m->hdr); - con->out_kvec[v++] = m->front; - if (m->middle) - con->out_kvec[v++] = m->middle->vec; - con->out_kvec_left = v; - con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len + - (m->middle ? m->middle->vec.iov_len : 0); - con->out_kvec_cur = con->out_kvec; - - /* fill in crc (except data pages), footer */ - con->out_msg->hdr.crc = - cpu_to_le32(crc32c(0, (void *)&m->hdr, - sizeof(m->hdr) - sizeof(m->hdr.crc))); - con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE; - con->out_msg->footer.front_crc = - cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len)); - if (m->middle) - con->out_msg->footer.middle_crc = - cpu_to_le32(crc32c(0, m->middle->vec.iov_base, - m->middle->vec.iov_len)); - else - con->out_msg->footer.middle_crc = 0; - con->out_msg->footer.data_crc = 0; - dout("prepare_write_message front_crc %u data_crc %u\n", - le32_to_cpu(con->out_msg->footer.front_crc), - le32_to_cpu(con->out_msg->footer.middle_crc)); - - /* is there a data payload? */ - if (le32_to_cpu(m->hdr.data_len) > 0) { - /* initialize page iterator */ - con->out_msg_pos.page = 0; - if (m->pages) - con->out_msg_pos.page_pos = - le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK; - else - con->out_msg_pos.page_pos = 0; - con->out_msg_pos.data_pos = 0; - con->out_msg_pos.did_page_crc = 0; - con->out_more = 1; /* data + footer will follow */ - } else { - /* no, queue up footer too and be done */ - prepare_write_message_footer(con, v); - } - - set_bit(WRITE_PENDING, &con->state); -} - -/* - * Prepare an ack. - */ -static void prepare_write_ack(struct ceph_connection *con) -{ - dout("prepare_write_ack %p %llu -> %llu\n", con, - con->in_seq_acked, con->in_seq); - con->in_seq_acked = con->in_seq; - - con->out_kvec[0].iov_base = &tag_ack; - con->out_kvec[0].iov_len = 1; - con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - con->out_kvec[1].iov_base = &con->out_temp_ack; - con->out_kvec[1].iov_len = sizeof(con->out_temp_ack); - con->out_kvec_left = 2; - con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); - con->out_kvec_cur = con->out_kvec; - con->out_more = 1; /* more will follow.. eventually.. */ - set_bit(WRITE_PENDING, &con->state); -} - -/* - * Prepare to write keepalive byte. - */ -static void prepare_write_keepalive(struct ceph_connection *con) -{ - dout("prepare_write_keepalive %p\n", con); - con->out_kvec[0].iov_base = &tag_keepalive; - con->out_kvec[0].iov_len = 1; - con->out_kvec_left = 1; - con->out_kvec_bytes = 1; - con->out_kvec_cur = con->out_kvec; - set_bit(WRITE_PENDING, &con->state); -} - -/* - * Connection negotiation. - */ - -static void prepare_connect_authorizer(struct ceph_connection *con) -{ - void *auth_buf; - int auth_len = 0; - int auth_protocol = 0; - - mutex_unlock(&con->mutex); - if (con->ops->get_authorizer) - con->ops->get_authorizer(con, &auth_buf, &auth_len, - &auth_protocol, &con->auth_reply_buf, - &con->auth_reply_buf_len, - con->auth_retry); - mutex_lock(&con->mutex); - - con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol); - con->out_connect.authorizer_len = cpu_to_le32(auth_len); - - con->out_kvec[con->out_kvec_left].iov_base = auth_buf; - con->out_kvec[con->out_kvec_left].iov_len = auth_len; - con->out_kvec_left++; - con->out_kvec_bytes += auth_len; -} - -/* - * We connected to a peer and are saying hello. - */ -static void prepare_write_banner(struct ceph_messenger *msgr, - struct ceph_connection *con) -{ - int len = strlen(CEPH_BANNER); - - con->out_kvec[0].iov_base = CEPH_BANNER; - con->out_kvec[0].iov_len = len; - con->out_kvec[1].iov_base = &msgr->my_enc_addr; - con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr); - con->out_kvec_left = 2; - con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr); - con->out_kvec_cur = con->out_kvec; - con->out_more = 0; - set_bit(WRITE_PENDING, &con->state); -} - -static void prepare_write_connect(struct ceph_messenger *msgr, - struct ceph_connection *con, - int after_banner) -{ - unsigned global_seq = get_global_seq(con->msgr, 0); - int proto; - - switch (con->peer_name.type) { - case CEPH_ENTITY_TYPE_MON: - proto = CEPH_MONC_PROTOCOL; - break; - case CEPH_ENTITY_TYPE_OSD: - proto = CEPH_OSDC_PROTOCOL; - break; - case CEPH_ENTITY_TYPE_MDS: - proto = CEPH_MDSC_PROTOCOL; - break; - default: - BUG(); - } - - dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con, - con->connect_seq, global_seq, proto); - - con->out_connect.features = cpu_to_le64(CEPH_FEATURE_SUPPORTED); - con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT); - con->out_connect.connect_seq = cpu_to_le32(con->connect_seq); - con->out_connect.global_seq = cpu_to_le32(global_seq); - con->out_connect.protocol_version = cpu_to_le32(proto); - con->out_connect.flags = 0; - - if (!after_banner) { - con->out_kvec_left = 0; - con->out_kvec_bytes = 0; - } - con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect; - con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect); - con->out_kvec_left++; - con->out_kvec_bytes += sizeof(con->out_connect); - con->out_kvec_cur = con->out_kvec; - con->out_more = 0; - set_bit(WRITE_PENDING, &con->state); - - prepare_connect_authorizer(con); -} - - -/* - * write as much of pending kvecs to the socket as we can. - * 1 -> done - * 0 -> socket full, but more to do - * <0 -> error - */ -static int write_partial_kvec(struct ceph_connection *con) -{ - int ret; - - dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes); - while (con->out_kvec_bytes > 0) { - ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur, - con->out_kvec_left, con->out_kvec_bytes, - con->out_more); - if (ret <= 0) - goto out; - con->out_kvec_bytes -= ret; - if (con->out_kvec_bytes == 0) - break; /* done */ - while (ret > 0) { - if (ret >= con->out_kvec_cur->iov_len) { - ret -= con->out_kvec_cur->iov_len; - con->out_kvec_cur++; - con->out_kvec_left--; - } else { - con->out_kvec_cur->iov_len -= ret; - con->out_kvec_cur->iov_base += ret; - ret = 0; - break; - } - } - } - con->out_kvec_left = 0; - con->out_kvec_is_msg = false; - ret = 1; -out: - dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con, - con->out_kvec_bytes, con->out_kvec_left, ret); - return ret; /* done! */ -} - -#ifdef CONFIG_BLOCK -static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) -{ - if (!bio) { - *iter = NULL; - *seg = 0; - return; - } - *iter = bio; - *seg = bio->bi_idx; -} - -static void iter_bio_next(struct bio **bio_iter, int *seg) -{ - if (*bio_iter == NULL) - return; - - BUG_ON(*seg >= (*bio_iter)->bi_vcnt); - - (*seg)++; - if (*seg == (*bio_iter)->bi_vcnt) - init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); -} -#endif - -/* - * Write as much message data payload as we can. If we finish, queue - * up the footer. - * 1 -> done, footer is now queued in out_kvec[]. - * 0 -> socket full, but more to do - * <0 -> error - */ -static int write_partial_msg_pages(struct ceph_connection *con) -{ - struct ceph_msg *msg = con->out_msg; - unsigned data_len = le32_to_cpu(msg->hdr.data_len); - size_t len; - int crc = con->msgr->nocrc; - int ret; - int total_max_write; - int in_trail = 0; - size_t trail_len = (msg->trail ? msg->trail->length : 0); - - dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n", - con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages, - con->out_msg_pos.page_pos); - -#ifdef CONFIG_BLOCK - if (msg->bio && !msg->bio_iter) - init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); -#endif - - while (data_len > con->out_msg_pos.data_pos) { - struct page *page = NULL; - void *kaddr = NULL; - int max_write = PAGE_SIZE; - int page_shift = 0; - - total_max_write = data_len - trail_len - - con->out_msg_pos.data_pos; - - /* - * if we are calculating the data crc (the default), we need - * to map the page. if our pages[] has been revoked, use the - * zero page. - */ - - /* have we reached the trail part of the data? */ - if (con->out_msg_pos.data_pos >= data_len - trail_len) { - in_trail = 1; - - total_max_write = data_len - con->out_msg_pos.data_pos; - - page = list_first_entry(&msg->trail->head, - struct page, lru); - if (crc) - kaddr = kmap(page); - max_write = PAGE_SIZE; - } else if (msg->pages) { - page = msg->pages[con->out_msg_pos.page]; - if (crc) - kaddr = kmap(page); - } else if (msg->pagelist) { - page = list_first_entry(&msg->pagelist->head, - struct page, lru); - if (crc) - kaddr = kmap(page); -#ifdef CONFIG_BLOCK - } else if (msg->bio) { - struct bio_vec *bv; - - bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg); - page = bv->bv_page; - page_shift = bv->bv_offset; - if (crc) - kaddr = kmap(page) + page_shift; - max_write = bv->bv_len; -#endif - } else { - page = con->msgr->zero_page; - if (crc) - kaddr = page_address(con->msgr->zero_page); - } - len = min_t(int, max_write - con->out_msg_pos.page_pos, - total_max_write); - - if (crc && !con->out_msg_pos.did_page_crc) { - void *base = kaddr + con->out_msg_pos.page_pos; - u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc); - - BUG_ON(kaddr == NULL); - con->out_msg->footer.data_crc = - cpu_to_le32(crc32c(tmpcrc, base, len)); - con->out_msg_pos.did_page_crc = 1; - } - ret = kernel_sendpage(con->sock, page, - con->out_msg_pos.page_pos + page_shift, - len, - MSG_DONTWAIT | MSG_NOSIGNAL | - MSG_MORE); - - if (crc && - (msg->pages || msg->pagelist || msg->bio || in_trail)) - kunmap(page); - - if (ret <= 0) - goto out; - - con->out_msg_pos.data_pos += ret; - con->out_msg_pos.page_pos += ret; - if (ret == len) { - con->out_msg_pos.page_pos = 0; - con->out_msg_pos.page++; - con->out_msg_pos.did_page_crc = 0; - if (in_trail) - list_move_tail(&page->lru, - &msg->trail->head); - else if (msg->pagelist) - list_move_tail(&page->lru, - &msg->pagelist->head); -#ifdef CONFIG_BLOCK - else if (msg->bio) - iter_bio_next(&msg->bio_iter, &msg->bio_seg); -#endif - } - } - - dout("write_partial_msg_pages %p msg %p done\n", con, msg); - - /* prepare and queue up footer, too */ - if (!crc) - con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; - con->out_kvec_bytes = 0; - con->out_kvec_left = 0; - con->out_kvec_cur = con->out_kvec; - prepare_write_message_footer(con, 0); - ret = 1; -out: - return ret; -} - -/* - * write some zeros - */ -static int write_partial_skip(struct ceph_connection *con) -{ - int ret; - - while (con->out_skip > 0) { - struct kvec iov = { - .iov_base = page_address(con->msgr->zero_page), - .iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE) - }; - - ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1); - if (ret <= 0) - goto out; - con->out_skip -= ret; - } - ret = 1; -out: - return ret; -} - -/* - * Prepare to read connection handshake, or an ack. - */ -static void prepare_read_banner(struct ceph_connection *con) -{ - dout("prepare_read_banner %p\n", con); - con->in_base_pos = 0; -} - -static void prepare_read_connect(struct ceph_connection *con) -{ - dout("prepare_read_connect %p\n", con); - con->in_base_pos = 0; -} - -static void prepare_read_ack(struct ceph_connection *con) -{ - dout("prepare_read_ack %p\n", con); - con->in_base_pos = 0; -} - -static void prepare_read_tag(struct ceph_connection *con) -{ - dout("prepare_read_tag %p\n", con); - con->in_base_pos = 0; - con->in_tag = CEPH_MSGR_TAG_READY; -} - -/* - * Prepare to read a message. - */ -static int prepare_read_message(struct ceph_connection *con) -{ - dout("prepare_read_message %p\n", con); - BUG_ON(con->in_msg != NULL); - con->in_base_pos = 0; - con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0; - return 0; -} - - -static int read_partial(struct ceph_connection *con, - int *to, int size, void *object) -{ - *to += size; - while (con->in_base_pos < *to) { - int left = *to - con->in_base_pos; - int have = size - left; - int ret = ceph_tcp_recvmsg(con->sock, object + have, left); - if (ret <= 0) - return ret; - con->in_base_pos += ret; - } - return 1; -} - - -/* - * Read all or part of the connect-side handshake on a new connection - */ -static int read_partial_banner(struct ceph_connection *con) -{ - int ret, to = 0; - - dout("read_partial_banner %p at %d\n", con, con->in_base_pos); - - /* peer's banner */ - ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner); - if (ret <= 0) - goto out; - ret = read_partial(con, &to, sizeof(con->actual_peer_addr), - &con->actual_peer_addr); - if (ret <= 0) - goto out; - ret = read_partial(con, &to, sizeof(con->peer_addr_for_me), - &con->peer_addr_for_me); - if (ret <= 0) - goto out; -out: - return ret; -} - -static int read_partial_connect(struct ceph_connection *con) -{ - int ret, to = 0; - - dout("read_partial_connect %p at %d\n", con, con->in_base_pos); - - ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply); - if (ret <= 0) - goto out; - ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len), - con->auth_reply_buf); - if (ret <= 0) - goto out; - - dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n", - con, (int)con->in_reply.tag, - le32_to_cpu(con->in_reply.connect_seq), - le32_to_cpu(con->in_reply.global_seq)); -out: - return ret; - -} - -/* - * Verify the hello banner looks okay. - */ -static int verify_hello(struct ceph_connection *con) -{ - if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) { - pr_err("connect to %s got bad banner\n", - pr_addr(&con->peer_addr.in_addr)); - con->error_msg = "protocol error, bad banner"; - return -1; - } - return 0; -} - -static bool addr_is_blank(struct sockaddr_storage *ss) -{ - switch (ss->ss_family) { - case AF_INET: - return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0; - case AF_INET6: - return - ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 && - ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 && - ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 && - ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0; - } - return false; -} - -static int addr_port(struct sockaddr_storage *ss) -{ - switch (ss->ss_family) { - case AF_INET: - return ntohs(((struct sockaddr_in *)ss)->sin_port); - case AF_INET6: - return ntohs(((struct sockaddr_in6 *)ss)->sin6_port); - } - return 0; -} - -static void addr_set_port(struct sockaddr_storage *ss, int p) -{ - switch (ss->ss_family) { - case AF_INET: - ((struct sockaddr_in *)ss)->sin_port = htons(p); - case AF_INET6: - ((struct sockaddr_in6 *)ss)->sin6_port = htons(p); - } -} - -/* - * Parse an ip[:port] list into an addr array. Use the default - * monitor port if a port isn't specified. - */ -int ceph_parse_ips(const char *c, const char *end, - struct ceph_entity_addr *addr, - int max_count, int *count) -{ - int i; - const char *p = c; - - dout("parse_ips on '%.*s'\n", (int)(end-c), c); - for (i = 0; i < max_count; i++) { - const char *ipend; - struct sockaddr_storage *ss = &addr[i].in_addr; - struct sockaddr_in *in4 = (void *)ss; - struct sockaddr_in6 *in6 = (void *)ss; - int port; - char delim = ','; - - if (*p == '[') { - delim = ']'; - p++; - } - - memset(ss, 0, sizeof(*ss)); - if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr, - delim, &ipend)) - ss->ss_family = AF_INET; - else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr, - delim, &ipend)) - ss->ss_family = AF_INET6; - else - goto bad; - p = ipend; - - if (delim == ']') { - if (*p != ']') { - dout("missing matching ']'\n"); - goto bad; - } - p++; - } - - /* port? */ - if (p < end && *p == ':') { - port = 0; - p++; - while (p < end && *p >= '0' && *p <= '9') { - port = (port * 10) + (*p - '0'); - p++; - } - if (port > 65535 || port == 0) - goto bad; - } else { - port = CEPH_MON_PORT; - } - - addr_set_port(ss, port); - - dout("parse_ips got %s\n", pr_addr(ss)); - - if (p == end) - break; - if (*p != ',') - goto bad; - p++; - } - - if (p != end) - goto bad; - - if (count) - *count = i + 1; - return 0; - -bad: - pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); - return -EINVAL; -} - -static int process_banner(struct ceph_connection *con) -{ - dout("process_banner on %p\n", con); - - if (verify_hello(con) < 0) - return -1; - - ceph_decode_addr(&con->actual_peer_addr); - ceph_decode_addr(&con->peer_addr_for_me); - - /* - * Make sure the other end is who we wanted. note that the other - * end may not yet know their ip address, so if it's 0.0.0.0, give - * them the benefit of the doubt. - */ - if (memcmp(&con->peer_addr, &con->actual_peer_addr, - sizeof(con->peer_addr)) != 0 && - !(addr_is_blank(&con->actual_peer_addr.in_addr) && - con->actual_peer_addr.nonce == con->peer_addr.nonce)) { - pr_warning("wrong peer, want %s/%d, got %s/%d\n", - pr_addr(&con->peer_addr.in_addr), - (int)le32_to_cpu(con->peer_addr.nonce), - pr_addr(&con->actual_peer_addr.in_addr), - (int)le32_to_cpu(con->actual_peer_addr.nonce)); - con->error_msg = "wrong peer at address"; - return -1; - } - - /* - * did we learn our address? - */ - if (addr_is_blank(&con->msgr->inst.addr.in_addr)) { - int port = addr_port(&con->msgr->inst.addr.in_addr); - - memcpy(&con->msgr->inst.addr.in_addr, - &con->peer_addr_for_me.in_addr, - sizeof(con->peer_addr_for_me.in_addr)); - addr_set_port(&con->msgr->inst.addr.in_addr, port); - encode_my_addr(con->msgr); - dout("process_banner learned my addr is %s\n", - pr_addr(&con->msgr->inst.addr.in_addr)); - } - - set_bit(NEGOTIATING, &con->state); - prepare_read_connect(con); - return 0; -} - -static void fail_protocol(struct ceph_connection *con) -{ - reset_connection(con); - set_bit(CLOSED, &con->state); /* in case there's queued work */ - - mutex_unlock(&con->mutex); - if (con->ops->bad_proto) - con->ops->bad_proto(con); - mutex_lock(&con->mutex); -} - -static int process_connect(struct ceph_connection *con) -{ - u64 sup_feat = CEPH_FEATURE_SUPPORTED; - u64 req_feat = CEPH_FEATURE_REQUIRED; - u64 server_feat = le64_to_cpu(con->in_reply.features); - - dout("process_connect on %p tag %d\n", con, (int)con->in_tag); - - switch (con->in_reply.tag) { - case CEPH_MSGR_TAG_FEATURES: - pr_err("%s%lld %s feature set mismatch," - " my %llx < server's %llx, missing %llx\n", - ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr), - sup_feat, server_feat, server_feat & ~sup_feat); - con->error_msg = "missing required protocol features"; - fail_protocol(con); - return -1; - - case CEPH_MSGR_TAG_BADPROTOVER: - pr_err("%s%lld %s protocol version mismatch," - " my %d != server's %d\n", - ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr), - le32_to_cpu(con->out_connect.protocol_version), - le32_to_cpu(con->in_reply.protocol_version)); - con->error_msg = "protocol version mismatch"; - fail_protocol(con); - return -1; - - case CEPH_MSGR_TAG_BADAUTHORIZER: - con->auth_retry++; - dout("process_connect %p got BADAUTHORIZER attempt %d\n", con, - con->auth_retry); - if (con->auth_retry == 2) { - con->error_msg = "connect authorization failure"; - reset_connection(con); - set_bit(CLOSED, &con->state); - return -1; - } - con->auth_retry = 1; - prepare_write_connect(con->msgr, con, 0); - prepare_read_connect(con); - break; - - case CEPH_MSGR_TAG_RESETSESSION: - /* - * If we connected with a large connect_seq but the peer - * has no record of a session with us (no connection, or - * connect_seq == 0), they will send RESETSESION to indicate - * that they must have reset their session, and may have - * dropped messages. - */ - dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); - pr_err("%s%lld %s connection reset\n", - ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr)); - reset_connection(con); - prepare_write_connect(con->msgr, con, 0); - prepare_read_connect(con); - - /* Tell ceph about it. */ - mutex_unlock(&con->mutex); - pr_info("reset on %s%lld\n", ENTITY_NAME(con->peer_name)); - if (con->ops->peer_reset) - con->ops->peer_reset(con); - mutex_lock(&con->mutex); - break; - - case CEPH_MSGR_TAG_RETRY_SESSION: - /* - * If we sent a smaller connect_seq than the peer has, try - * again with a larger value. - */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", - le32_to_cpu(con->out_connect.connect_seq), - le32_to_cpu(con->in_connect.connect_seq)); - con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); - prepare_write_connect(con->msgr, con, 0); - prepare_read_connect(con); - break; - - case CEPH_MSGR_TAG_RETRY_GLOBAL: - /* - * If we sent a smaller global_seq than the peer has, try - * again with a larger value. - */ - dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", - con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); - get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); - prepare_write_connect(con->msgr, con, 0); - prepare_read_connect(con); - break; - - case CEPH_MSGR_TAG_READY: - if (req_feat & ~server_feat) { - pr_err("%s%lld %s protocol feature mismatch," - " my required %llx > server's %llx, need %llx\n", - ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr), - req_feat, server_feat, req_feat & ~server_feat); - con->error_msg = "missing required protocol features"; - fail_protocol(con); - return -1; - } - clear_bit(CONNECTING, &con->state); - con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); - con->connect_seq++; - con->peer_features = server_feat; - dout("process_connect got READY gseq %d cseq %d (%d)\n", - con->peer_global_seq, - le32_to_cpu(con->in_reply.connect_seq), - con->connect_seq); - WARN_ON(con->connect_seq != - le32_to_cpu(con->in_reply.connect_seq)); - - if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY) - set_bit(LOSSYTX, &con->state); - - prepare_read_tag(con); - break; - - case CEPH_MSGR_TAG_WAIT: - /* - * If there is a connection race (we are opening - * connections to each other), one of us may just have - * to WAIT. This shouldn't happen if we are the - * client. - */ - pr_err("process_connect peer connecting WAIT\n"); - - default: - pr_err("connect protocol error, will retry\n"); - con->error_msg = "protocol error, garbage tag during connect"; - return -1; - } - return 0; -} - - -/* - * read (part of) an ack - */ -static int read_partial_ack(struct ceph_connection *con) -{ - int to = 0; - - return read_partial(con, &to, sizeof(con->in_temp_ack), - &con->in_temp_ack); -} - - -/* - * We can finally discard anything that's been acked. - */ -static void process_ack(struct ceph_connection *con) -{ - struct ceph_msg *m; - u64 ack = le64_to_cpu(con->in_temp_ack); - u64 seq; - - while (!list_empty(&con->out_sent)) { - m = list_first_entry(&con->out_sent, struct ceph_msg, - list_head); - seq = le64_to_cpu(m->hdr.seq); - if (seq > ack) - break; - dout("got ack for seq %llu type %d at %p\n", seq, - le16_to_cpu(m->hdr.type), m); - ceph_msg_remove(m); - } - prepare_read_tag(con); -} - - - - -static int read_partial_message_section(struct ceph_connection *con, - struct kvec *section, - unsigned int sec_len, u32 *crc) -{ - int ret, left; - - BUG_ON(!section); - - while (section->iov_len < sec_len) { - BUG_ON(section->iov_base == NULL); - left = sec_len - section->iov_len; - ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base + - section->iov_len, left); - if (ret <= 0) - return ret; - section->iov_len += ret; - if (section->iov_len == sec_len) - *crc = crc32c(0, section->iov_base, - section->iov_len); - } - - return 1; -} - -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip); - - -static int read_partial_message_pages(struct ceph_connection *con, - struct page **pages, - unsigned data_len, int datacrc) -{ - void *p; - int ret; - int left; - - left = min((int)(data_len - con->in_msg_pos.data_pos), - (int)(PAGE_SIZE - con->in_msg_pos.page_pos)); - /* (page) data */ - BUG_ON(pages == NULL); - p = kmap(pages[con->in_msg_pos.page]); - ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, - left); - if (ret > 0 && datacrc) - con->in_data_crc = - crc32c(con->in_data_crc, - p + con->in_msg_pos.page_pos, ret); - kunmap(pages[con->in_msg_pos.page]); - if (ret <= 0) - return ret; - con->in_msg_pos.data_pos += ret; - con->in_msg_pos.page_pos += ret; - if (con->in_msg_pos.page_pos == PAGE_SIZE) { - con->in_msg_pos.page_pos = 0; - con->in_msg_pos.page++; - } - - return ret; -} - -#ifdef CONFIG_BLOCK -static int read_partial_message_bio(struct ceph_connection *con, - struct bio **bio_iter, int *bio_seg, - unsigned data_len, int datacrc) -{ - struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg); - void *p; - int ret, left; - - if (IS_ERR(bv)) - return PTR_ERR(bv); - - left = min((int)(data_len - con->in_msg_pos.data_pos), - (int)(bv->bv_len - con->in_msg_pos.page_pos)); - - p = kmap(bv->bv_page) + bv->bv_offset; - - ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, - left); - if (ret > 0 && datacrc) - con->in_data_crc = - crc32c(con->in_data_crc, - p + con->in_msg_pos.page_pos, ret); - kunmap(bv->bv_page); - if (ret <= 0) - return ret; - con->in_msg_pos.data_pos += ret; - con->in_msg_pos.page_pos += ret; - if (con->in_msg_pos.page_pos == bv->bv_len) { - con->in_msg_pos.page_pos = 0; - iter_bio_next(bio_iter, bio_seg); - } - - return ret; -} -#endif - -/* - * read (part of) a message. - */ -static int read_partial_message(struct ceph_connection *con) -{ - struct ceph_msg *m = con->in_msg; - int ret; - int to, left; - unsigned front_len, middle_len, data_len, data_off; - int datacrc = con->msgr->nocrc; - int skip; - u64 seq; - - dout("read_partial_message con %p msg %p\n", con, m); - - /* header */ - while (con->in_base_pos < sizeof(con->in_hdr)) { - left = sizeof(con->in_hdr) - con->in_base_pos; - ret = ceph_tcp_recvmsg(con->sock, - (char *)&con->in_hdr + con->in_base_pos, - left); - if (ret <= 0) - return ret; - con->in_base_pos += ret; - if (con->in_base_pos == sizeof(con->in_hdr)) { - u32 crc = crc32c(0, (void *)&con->in_hdr, - sizeof(con->in_hdr) - sizeof(con->in_hdr.crc)); - if (crc != le32_to_cpu(con->in_hdr.crc)) { - pr_err("read_partial_message bad hdr " - " crc %u != expected %u\n", - crc, con->in_hdr.crc); - return -EBADMSG; - } - } - } - front_len = le32_to_cpu(con->in_hdr.front_len); - if (front_len > CEPH_MSG_MAX_FRONT_LEN) - return -EIO; - middle_len = le32_to_cpu(con->in_hdr.middle_len); - if (middle_len > CEPH_MSG_MAX_DATA_LEN) - return -EIO; - data_len = le32_to_cpu(con->in_hdr.data_len); - if (data_len > CEPH_MSG_MAX_DATA_LEN) - return -EIO; - data_off = le16_to_cpu(con->in_hdr.data_off); - - /* verify seq# */ - seq = le64_to_cpu(con->in_hdr.seq); - if ((s64)seq - (s64)con->in_seq < 1) { - pr_info("skipping %s%lld %s seq %lld, expected %lld\n", - ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr), - seq, con->in_seq + 1); - con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); - con->in_tag = CEPH_MSGR_TAG_READY; - con->in_seq++; - return 0; - } else if ((s64)seq - (s64)con->in_seq > 1) { - pr_err("read_partial_message bad seq %lld expected %lld\n", - seq, con->in_seq + 1); - con->error_msg = "bad message sequence # for incoming message"; - return -EBADMSG; - } - - /* allocate message? */ - if (!con->in_msg) { - dout("got hdr type %d front %d data %d\n", con->in_hdr.type, - con->in_hdr.front_len, con->in_hdr.data_len); - skip = 0; - con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip); - if (skip) { - /* skip this message */ - dout("alloc_msg said skip message\n"); - BUG_ON(con->in_msg); - con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); - con->in_tag = CEPH_MSGR_TAG_READY; - con->in_seq++; - return 0; - } - if (!con->in_msg) { - con->error_msg = - "error allocating memory for incoming message"; - return -ENOMEM; - } - m = con->in_msg; - m->front.iov_len = 0; /* haven't read it yet */ - if (m->middle) - m->middle->vec.iov_len = 0; - - con->in_msg_pos.page = 0; - if (m->pages) - con->in_msg_pos.page_pos = data_off & ~PAGE_MASK; - else - con->in_msg_pos.page_pos = 0; - con->in_msg_pos.data_pos = 0; - } - - /* front */ - ret = read_partial_message_section(con, &m->front, front_len, - &con->in_front_crc); - if (ret <= 0) - return ret; - - /* middle */ - if (m->middle) { - ret = read_partial_message_section(con, &m->middle->vec, - middle_len, - &con->in_middle_crc); - if (ret <= 0) - return ret; - } -#ifdef CONFIG_BLOCK - if (m->bio && !m->bio_iter) - init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); -#endif - - /* (page) data */ - while (con->in_msg_pos.data_pos < data_len) { - if (m->pages) { - ret = read_partial_message_pages(con, m->pages, - data_len, datacrc); - if (ret <= 0) - return ret; -#ifdef CONFIG_BLOCK - } else if (m->bio) { - - ret = read_partial_message_bio(con, - &m->bio_iter, &m->bio_seg, - data_len, datacrc); - if (ret <= 0) - return ret; -#endif - } else { - BUG_ON(1); - } - } - - /* footer */ - to = sizeof(m->hdr) + sizeof(m->footer); - while (con->in_base_pos < to) { - left = to - con->in_base_pos; - ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer + - (con->in_base_pos - sizeof(m->hdr)), - left); - if (ret <= 0) - return ret; - con->in_base_pos += ret; - } - dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n", - m, front_len, m->footer.front_crc, middle_len, - m->footer.middle_crc, data_len, m->footer.data_crc); - - /* crc ok? */ - if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) { - pr_err("read_partial_message %p front crc %u != exp. %u\n", - m, con->in_front_crc, m->footer.front_crc); - return -EBADMSG; - } - if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) { - pr_err("read_partial_message %p middle crc %u != exp %u\n", - m, con->in_middle_crc, m->footer.middle_crc); - return -EBADMSG; - } - if (datacrc && - (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 && - con->in_data_crc != le32_to_cpu(m->footer.data_crc)) { - pr_err("read_partial_message %p data crc %u != exp. %u\n", m, - con->in_data_crc, le32_to_cpu(m->footer.data_crc)); - return -EBADMSG; - } - - return 1; /* done! */ -} - -/* - * Process message. This happens in the worker thread. The callback should - * be careful not to do anything that waits on other incoming messages or it - * may deadlock. - */ -static void process_message(struct ceph_connection *con) -{ - struct ceph_msg *msg; - - msg = con->in_msg; - con->in_msg = NULL; - - /* if first message, set peer_name */ - if (con->peer_name.type == 0) - con->peer_name = msg->hdr.src; - - con->in_seq++; - mutex_unlock(&con->mutex); - - dout("===== %p %llu from %s%lld %d=%s len %d+%d (%u %u %u) =====\n", - msg, le64_to_cpu(msg->hdr.seq), - ENTITY_NAME(msg->hdr.src), - le16_to_cpu(msg->hdr.type), - ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), - le32_to_cpu(msg->hdr.front_len), - le32_to_cpu(msg->hdr.data_len), - con->in_front_crc, con->in_middle_crc, con->in_data_crc); - con->ops->dispatch(con, msg); - - mutex_lock(&con->mutex); - prepare_read_tag(con); -} - - -/* - * Write something to the socket. Called in a worker thread when the - * socket appears to be writeable and we have something ready to send. - */ -static int try_write(struct ceph_connection *con) -{ - struct ceph_messenger *msgr = con->msgr; - int ret = 1; - - dout("try_write start %p state %lu nref %d\n", con, con->state, - atomic_read(&con->nref)); - -more: - dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes); - - /* open the socket first? */ - if (con->sock == NULL) { - /* - * if we were STANDBY and are reconnecting _this_ - * connection, bump connect_seq now. Always bump - * global_seq. - */ - if (test_and_clear_bit(STANDBY, &con->state)) - con->connect_seq++; - - prepare_write_banner(msgr, con); - prepare_write_connect(msgr, con, 1); - prepare_read_banner(con); - set_bit(CONNECTING, &con->state); - clear_bit(NEGOTIATING, &con->state); - - BUG_ON(con->in_msg); - con->in_tag = CEPH_MSGR_TAG_READY; - dout("try_write initiating connect on %p new state %lu\n", - con, con->state); - con->sock = ceph_tcp_connect(con); - if (IS_ERR(con->sock)) { - con->sock = NULL; - con->error_msg = "connect error"; - ret = -1; - goto out; - } - } - -more_kvec: - /* kvec data queued? */ - if (con->out_skip) { - ret = write_partial_skip(con); - if (ret <= 0) - goto done; - if (ret < 0) { - dout("try_write write_partial_skip err %d\n", ret); - goto done; - } - } - if (con->out_kvec_left) { - ret = write_partial_kvec(con); - if (ret <= 0) - goto done; - } - - /* msg pages? */ - if (con->out_msg) { - if (con->out_msg_done) { - ceph_msg_put(con->out_msg); - con->out_msg = NULL; /* we're done with this one */ - goto do_next; - } - - ret = write_partial_msg_pages(con); - if (ret == 1) - goto more_kvec; /* we need to send the footer, too! */ - if (ret == 0) - goto done; - if (ret < 0) { - dout("try_write write_partial_msg_pages err %d\n", - ret); - goto done; - } - } - -do_next: - if (!test_bit(CONNECTING, &con->state)) { - /* is anything else pending? */ - if (!list_empty(&con->out_queue)) { - prepare_write_message(con); - goto more; - } - if (con->in_seq > con->in_seq_acked) { - prepare_write_ack(con); - goto more; - } - if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) { - prepare_write_keepalive(con); - goto more; - } - } - - /* Nothing to do! */ - clear_bit(WRITE_PENDING, &con->state); - dout("try_write nothing else to write.\n"); -done: - ret = 0; -out: - dout("try_write done on %p\n", con); - return ret; -} - - - -/* - * Read what we can from the socket. - */ -static int try_read(struct ceph_connection *con) -{ - int ret = -1; - - if (!con->sock) - return 0; - - if (test_bit(STANDBY, &con->state)) - return 0; - - dout("try_read start on %p\n", con); - -more: - dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag, - con->in_base_pos); - if (test_bit(CONNECTING, &con->state)) { - if (!test_bit(NEGOTIATING, &con->state)) { - dout("try_read connecting\n"); - ret = read_partial_banner(con); - if (ret <= 0) - goto done; - if (process_banner(con) < 0) { - ret = -1; - goto out; - } - } - ret = read_partial_connect(con); - if (ret <= 0) - goto done; - if (process_connect(con) < 0) { - ret = -1; - goto out; - } - goto more; - } - - if (con->in_base_pos < 0) { - /* - * skipping + discarding content. - * - * FIXME: there must be a better way to do this! - */ - static char buf[1024]; - int skip = min(1024, -con->in_base_pos); - dout("skipping %d / %d bytes\n", skip, -con->in_base_pos); - ret = ceph_tcp_recvmsg(con->sock, buf, skip); - if (ret <= 0) - goto done; - con->in_base_pos += ret; - if (con->in_base_pos) - goto more; - } - if (con->in_tag == CEPH_MSGR_TAG_READY) { - /* - * what's next? - */ - ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1); - if (ret <= 0) - goto done; - dout("try_read got tag %d\n", (int)con->in_tag); - switch (con->in_tag) { - case CEPH_MSGR_TAG_MSG: - prepare_read_message(con); - break; - case CEPH_MSGR_TAG_ACK: - prepare_read_ack(con); - break; - case CEPH_MSGR_TAG_CLOSE: - set_bit(CLOSED, &con->state); /* fixme */ - goto done; - default: - goto bad_tag; - } - } - if (con->in_tag == CEPH_MSGR_TAG_MSG) { - ret = read_partial_message(con); - if (ret <= 0) { - switch (ret) { - case -EBADMSG: - con->error_msg = "bad crc"; - ret = -EIO; - goto out; - case -EIO: - con->error_msg = "io error"; - goto out; - default: - goto done; - } - } - if (con->in_tag == CEPH_MSGR_TAG_READY) - goto more; - process_message(con); - goto more; - } - if (con->in_tag == CEPH_MSGR_TAG_ACK) { - ret = read_partial_ack(con); - if (ret <= 0) - goto done; - process_ack(con); - goto more; - } - -done: - ret = 0; -out: - dout("try_read done on %p\n", con); - return ret; - -bad_tag: - pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag); - con->error_msg = "protocol error, garbage tag"; - ret = -1; - goto out; -} - - -/* - * Atomically queue work on a connection. Bump @con reference to - * avoid races with connection teardown. - * - * There is some trickery going on with QUEUED and BUSY because we - * only want a _single_ thread operating on each connection at any - * point in time, but we want to use all available CPUs. - * - * The worker thread only proceeds if it can atomically set BUSY. It - * clears QUEUED and does it's thing. When it thinks it's done, it - * clears BUSY, then rechecks QUEUED.. if it's set again, it loops - * (tries again to set BUSY). - * - * To queue work, we first set QUEUED, _then_ if BUSY isn't set, we - * try to queue work. If that fails (work is already queued, or BUSY) - * we give up (work also already being done or is queued) but leave QUEUED - * set so that the worker thread will loop if necessary. - */ -static void queue_con(struct ceph_connection *con) -{ - if (test_bit(DEAD, &con->state)) { - dout("queue_con %p ignoring: DEAD\n", - con); - return; - } - - if (!con->ops->get(con)) { - dout("queue_con %p ref count 0\n", con); - return; - } - - set_bit(QUEUED, &con->state); - if (test_bit(BUSY, &con->state)) { - dout("queue_con %p - already BUSY\n", con); - con->ops->put(con); - } else if (!queue_work(ceph_msgr_wq, &con->work.work)) { - dout("queue_con %p - already queued\n", con); - con->ops->put(con); - } else { - dout("queue_con %p\n", con); - } -} - -/* - * Do some work on a connection. Drop a connection ref when we're done. - */ -static void con_work(struct work_struct *work) -{ - struct ceph_connection *con = container_of(work, struct ceph_connection, - work.work); - int backoff = 0; - -more: - if (test_and_set_bit(BUSY, &con->state) != 0) { - dout("con_work %p BUSY already set\n", con); - goto out; - } - dout("con_work %p start, clearing QUEUED\n", con); - clear_bit(QUEUED, &con->state); - - mutex_lock(&con->mutex); - - if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ - dout("con_work CLOSED\n"); - con_close_socket(con); - goto done; - } - if (test_and_clear_bit(OPENING, &con->state)) { - /* reopen w/ new peer */ - dout("con_work OPENING\n"); - con_close_socket(con); - } - - if (test_and_clear_bit(SOCK_CLOSED, &con->state) || - try_read(con) < 0 || - try_write(con) < 0) { - mutex_unlock(&con->mutex); - backoff = 1; - ceph_fault(con); /* error/fault path */ - goto done_unlocked; - } - -done: - mutex_unlock(&con->mutex); - -done_unlocked: - clear_bit(BUSY, &con->state); - dout("con->state=%lu\n", con->state); - if (test_bit(QUEUED, &con->state)) { - if (!backoff || test_bit(OPENING, &con->state)) { - dout("con_work %p QUEUED reset, looping\n", con); - goto more; - } - dout("con_work %p QUEUED reset, but just faulted\n", con); - clear_bit(QUEUED, &con->state); - } - dout("con_work %p done\n", con); - -out: - con->ops->put(con); -} - - -/* - * Generic error/fault handler. A retry mechanism is used with - * exponential backoff - */ -static void ceph_fault(struct ceph_connection *con) -{ - pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), - pr_addr(&con->peer_addr.in_addr), con->error_msg); - dout("fault %p state %lu to peer %s\n", - con, con->state, pr_addr(&con->peer_addr.in_addr)); - - if (test_bit(LOSSYTX, &con->state)) { - dout("fault on LOSSYTX channel\n"); - goto out; - } - - mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state)) - goto out_unlock; - - con_close_socket(con); - - if (con->in_msg) { - ceph_msg_put(con->in_msg); - con->in_msg = NULL; - } - - /* Requeue anything that hasn't been acked */ - list_splice_init(&con->out_sent, &con->out_queue); - - /* If there are no messages in the queue, place the connection - * in a STANDBY state (i.e., don't try to reconnect just yet). */ - if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { - dout("fault setting STANDBY\n"); - set_bit(STANDBY, &con->state); - } else { - /* retry after a delay. */ - if (con->delay == 0) - con->delay = BASE_DELAY_INTERVAL; - else if (con->delay < MAX_DELAY_INTERVAL) - con->delay *= 2; - dout("fault queueing %p delay %lu\n", con, con->delay); - con->ops->get(con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay)) == 0) - con->ops->put(con); - } - -out_unlock: - mutex_unlock(&con->mutex); -out: - /* - * in case we faulted due to authentication, invalidate our - * current tickets so that we can get new ones. - */ - if (con->auth_retry && con->ops->invalidate_authorizer) { - dout("calling invalidate_authorizer()\n"); - con->ops->invalidate_authorizer(con); - } - - if (con->ops->fault) - con->ops->fault(con); -} - - - -/* - * create a new messenger instance - */ -struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr) -{ - struct ceph_messenger *msgr; - - msgr = kzalloc(sizeof(*msgr), GFP_KERNEL); - if (msgr == NULL) - return ERR_PTR(-ENOMEM); - - spin_lock_init(&msgr->global_seq_lock); - - /* the zero page is needed if a request is "canceled" while the message - * is being written over the socket */ - msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO); - if (!msgr->zero_page) { - kfree(msgr); - return ERR_PTR(-ENOMEM); - } - kmap(msgr->zero_page); - - if (myaddr) - msgr->inst.addr = *myaddr; - - /* select a random nonce */ - msgr->inst.addr.type = 0; - get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); - encode_my_addr(msgr); - - dout("messenger_create %p\n", msgr); - return msgr; -} - -void ceph_messenger_destroy(struct ceph_messenger *msgr) -{ - dout("destroy %p\n", msgr); - kunmap(msgr->zero_page); - __free_page(msgr->zero_page); - kfree(msgr); - dout("destroyed messenger %p\n", msgr); -} - -/* - * Queue up an outgoing message on the given connection. - */ -void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) -{ - if (test_bit(CLOSED, &con->state)) { - dout("con_send %p closed, dropping %p\n", con, msg); - ceph_msg_put(msg); - return; - } - - /* set src+dst */ - msg->hdr.src = con->msgr->inst.name; - - BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len)); - - msg->needs_out_seq = true; - - /* queue */ - mutex_lock(&con->mutex); - BUG_ON(!list_empty(&msg->list_head)); - list_add_tail(&msg->list_head, &con->out_queue); - dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg, - ENTITY_NAME(con->peer_name), le16_to_cpu(msg->hdr.type), - ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), - le32_to_cpu(msg->hdr.front_len), - le32_to_cpu(msg->hdr.middle_len), - le32_to_cpu(msg->hdr.data_len)); - mutex_unlock(&con->mutex); - - /* if there wasn't anything waiting to send before, queue - * new work */ - if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) - queue_con(con); -} - -/* - * Revoke a message that was previously queued for send - */ -void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) -{ - mutex_lock(&con->mutex); - if (!list_empty(&msg->list_head)) { - dout("con_revoke %p msg %p - was on queue\n", con, msg); - list_del_init(&msg->list_head); - ceph_msg_put(msg); - msg->hdr.seq = 0; - } - if (con->out_msg == msg) { - dout("con_revoke %p msg %p - was sending\n", con, msg); - con->out_msg = NULL; - if (con->out_kvec_is_msg) { - con->out_skip = con->out_kvec_bytes; - con->out_kvec_is_msg = false; - } - ceph_msg_put(msg); - msg->hdr.seq = 0; - } - mutex_unlock(&con->mutex); -} - -/* - * Revoke a message that we may be reading data into - */ -void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) -{ - mutex_lock(&con->mutex); - if (con->in_msg && con->in_msg == msg) { - unsigned front_len = le32_to_cpu(con->in_hdr.front_len); - unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len); - unsigned data_len = le32_to_cpu(con->in_hdr.data_len); - - /* skip rest of message */ - dout("con_revoke_pages %p msg %p revoked\n", con, msg); - con->in_base_pos = con->in_base_pos - - sizeof(struct ceph_msg_header) - - front_len - - middle_len - - data_len - - sizeof(struct ceph_msg_footer); - ceph_msg_put(con->in_msg); - con->in_msg = NULL; - con->in_tag = CEPH_MSGR_TAG_READY; - con->in_seq++; - } else { - dout("con_revoke_pages %p msg %p pages %p no-op\n", - con, con->in_msg, msg); - } - mutex_unlock(&con->mutex); -} - -/* - * Queue a keepalive byte to ensure the tcp connection is alive. - */ -void ceph_con_keepalive(struct ceph_connection *con) -{ - if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && - test_and_set_bit(WRITE_PENDING, &con->state) == 0) - queue_con(con); -} - - -/* - * construct a new message with given type, size - * the new msg has a ref count of 1. - */ -struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) -{ - struct ceph_msg *m; - - m = kmalloc(sizeof(*m), flags); - if (m == NULL) - goto out; - kref_init(&m->kref); - INIT_LIST_HEAD(&m->list_head); - - m->hdr.tid = 0; - m->hdr.type = cpu_to_le16(type); - m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT); - m->hdr.version = 0; - m->hdr.front_len = cpu_to_le32(front_len); - m->hdr.middle_len = 0; - m->hdr.data_len = 0; - m->hdr.data_off = 0; - m->hdr.reserved = 0; - m->footer.front_crc = 0; - m->footer.middle_crc = 0; - m->footer.data_crc = 0; - m->footer.flags = 0; - m->front_max = front_len; - m->front_is_vmalloc = false; - m->more_to_follow = false; - m->pool = NULL; - - /* front */ - if (front_len) { - if (front_len > PAGE_CACHE_SIZE) { - m->front.iov_base = __vmalloc(front_len, flags, - PAGE_KERNEL); - m->front_is_vmalloc = true; - } else { - m->front.iov_base = kmalloc(front_len, flags); - } - if (m->front.iov_base == NULL) { - pr_err("msg_new can't allocate %d bytes\n", - front_len); - goto out2; - } - } else { - m->front.iov_base = NULL; - } - m->front.iov_len = front_len; - - /* middle */ - m->middle = NULL; - - /* data */ - m->nr_pages = 0; - m->pages = NULL; - m->pagelist = NULL; - m->bio = NULL; - m->bio_iter = NULL; - m->bio_seg = 0; - m->trail = NULL; - - dout("ceph_msg_new %p front %d\n", m, front_len); - return m; - -out2: - ceph_msg_put(m); -out: - pr_err("msg_new can't create type %d front %d\n", type, front_len); - return NULL; -} - -/* - * Allocate "middle" portion of a message, if it is needed and wasn't - * allocated by alloc_msg. This allows us to read a small fixed-size - * per-type header in the front and then gracefully fail (i.e., - * propagate the error to the caller based on info in the front) when - * the middle is too large. - */ -static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg) -{ - int type = le16_to_cpu(msg->hdr.type); - int middle_len = le32_to_cpu(msg->hdr.middle_len); - - dout("alloc_middle %p type %d %s middle_len %d\n", msg, type, - ceph_msg_type_name(type), middle_len); - BUG_ON(!middle_len); - BUG_ON(msg->middle); - - msg->middle = ceph_buffer_new(middle_len, GFP_NOFS); - if (!msg->middle) - return -ENOMEM; - return 0; -} - -/* - * Generic message allocator, for incoming messages. - */ -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) -{ - int type = le16_to_cpu(hdr->type); - int front_len = le32_to_cpu(hdr->front_len); - int middle_len = le32_to_cpu(hdr->middle_len); - struct ceph_msg *msg = NULL; - int ret; - - if (con->ops->alloc_msg) { - mutex_unlock(&con->mutex); - msg = con->ops->alloc_msg(con, hdr, skip); - mutex_lock(&con->mutex); - if (!msg || *skip) - return NULL; - } - if (!msg) { - *skip = 0; - msg = ceph_msg_new(type, front_len, GFP_NOFS); - if (!msg) { - pr_err("unable to allocate msg type %d len %d\n", - type, front_len); - return NULL; - } - } - memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); - - if (middle_len && !msg->middle) { - ret = ceph_alloc_middle(con, msg); - if (ret < 0) { - ceph_msg_put(msg); - return NULL; - } - } - - return msg; -} - - -/* - * Free a generically kmalloc'd message. - */ -void ceph_msg_kfree(struct ceph_msg *m) -{ - dout("msg_kfree %p\n", m); - if (m->front_is_vmalloc) - vfree(m->front.iov_base); - else - kfree(m->front.iov_base); - kfree(m); -} - -/* - * Drop a msg ref. Destroy as needed. - */ -void ceph_msg_last_put(struct kref *kref) -{ - struct ceph_msg *m = container_of(kref, struct ceph_msg, kref); - - dout("ceph_msg_put last one on %p\n", m); - WARN_ON(!list_empty(&m->list_head)); - - /* drop middle, data, if any */ - if (m->middle) { - ceph_buffer_put(m->middle); - m->middle = NULL; - } - m->nr_pages = 0; - m->pages = NULL; - - if (m->pagelist) { - ceph_pagelist_release(m->pagelist); - kfree(m->pagelist); - m->pagelist = NULL; - } - - m->trail = NULL; - - if (m->pool) - ceph_msgpool_put(m->pool, m); - else - ceph_msg_kfree(m); -} - -void ceph_msg_dump(struct ceph_msg *msg) -{ - pr_debug("msg_dump %p (front_max %d nr_pages %d)\n", msg, - msg->front_max, msg->nr_pages); - print_hex_dump(KERN_DEBUG, "header: ", - DUMP_PREFIX_OFFSET, 16, 1, - &msg->hdr, sizeof(msg->hdr), true); - print_hex_dump(KERN_DEBUG, " front: ", - DUMP_PREFIX_OFFSET, 16, 1, - msg->front.iov_base, msg->front.iov_len, true); - if (msg->middle) - print_hex_dump(KERN_DEBUG, "middle: ", - DUMP_PREFIX_OFFSET, 16, 1, - msg->middle->vec.iov_base, - msg->middle->vec.iov_len, true); - print_hex_dump(KERN_DEBUG, "footer: ", - DUMP_PREFIX_OFFSET, 16, 1, - &msg->footer, sizeof(msg->footer), true); -} diff --git a/fs/ceph/messenger.h b/fs/ceph/messenger.h deleted file mode 100644 index 5a79450604ef..000000000000 --- a/fs/ceph/messenger.h +++ /dev/null @@ -1,257 +0,0 @@ -#ifndef __FS_CEPH_MESSENGER_H -#define __FS_CEPH_MESSENGER_H - -#include -#include -#include -#include -#include -#include -#include - -#include "types.h" -#include "buffer.h" - -struct ceph_msg; -struct ceph_connection; - -extern struct workqueue_struct *ceph_msgr_wq; /* receive work queue */ - -/* - * Ceph defines these callbacks for handling connection events. - */ -struct ceph_connection_operations { - struct ceph_connection *(*get)(struct ceph_connection *); - void (*put)(struct ceph_connection *); - - /* handle an incoming message. */ - void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m); - - /* authorize an outgoing connection */ - int (*get_authorizer) (struct ceph_connection *con, - void **buf, int *len, int *proto, - void **reply_buf, int *reply_len, int force_new); - int (*verify_authorizer_reply) (struct ceph_connection *con, int len); - int (*invalidate_authorizer)(struct ceph_connection *con); - - /* protocol version mismatch */ - void (*bad_proto) (struct ceph_connection *con); - - /* there was some error on the socket (disconnect, whatever) */ - void (*fault) (struct ceph_connection *con); - - /* a remote host as terminated a message exchange session, and messages - * we sent (or they tried to send us) may be lost. */ - void (*peer_reset) (struct ceph_connection *con); - - struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip); -}; - -/* use format string %s%d */ -#define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num) - -struct ceph_messenger { - struct ceph_entity_inst inst; /* my name+address */ - struct ceph_entity_addr my_enc_addr; - struct page *zero_page; /* used in certain error cases */ - - bool nocrc; - - /* - * the global_seq counts connections i (attempt to) initiate - * in order to disambiguate certain connect race conditions. - */ - u32 global_seq; - spinlock_t global_seq_lock; -}; - -/* - * a single message. it contains a header (src, dest, message type, etc.), - * footer (crc values, mainly), a "front" message body, and possibly a - * data payload (stored in some number of pages). - */ -struct ceph_msg { - struct ceph_msg_header hdr; /* header */ - struct ceph_msg_footer footer; /* footer */ - struct kvec front; /* unaligned blobs of message */ - struct ceph_buffer *middle; - struct page **pages; /* data payload. NOT OWNER. */ - unsigned nr_pages; /* size of page array */ - struct ceph_pagelist *pagelist; /* instead of pages */ - struct list_head list_head; - struct kref kref; - struct bio *bio; /* instead of pages/pagelist */ - struct bio *bio_iter; /* bio iterator */ - int bio_seg; /* current bio segment */ - struct ceph_pagelist *trail; /* the trailing part of the data */ - bool front_is_vmalloc; - bool more_to_follow; - bool needs_out_seq; - int front_max; - - struct ceph_msgpool *pool; -}; - -struct ceph_msg_pos { - int page, page_pos; /* which page; offset in page */ - int data_pos; /* offset in data payload */ - int did_page_crc; /* true if we've calculated crc for current page */ -}; - -/* ceph connection fault delay defaults, for exponential backoff */ -#define BASE_DELAY_INTERVAL (HZ/2) -#define MAX_DELAY_INTERVAL (5 * 60 * HZ) - -/* - * ceph_connection state bit flags - * - * QUEUED and BUSY are used together to ensure that only a single - * thread is currently opening, reading or writing data to the socket. - */ -#define LOSSYTX 0 /* we can close channel or drop messages on errors */ -#define CONNECTING 1 -#define NEGOTIATING 2 -#define KEEPALIVE_PENDING 3 -#define WRITE_PENDING 4 /* we have data ready to send */ -#define QUEUED 5 /* there is work queued on this connection */ -#define BUSY 6 /* work is being done */ -#define STANDBY 8 /* no outgoing messages, socket closed. we keep - * the ceph_connection around to maintain shared - * state with the peer. */ -#define CLOSED 10 /* we've closed the connection */ -#define SOCK_CLOSED 11 /* socket state changed to closed */ -#define OPENING 13 /* open connection w/ (possibly new) peer */ -#define DEAD 14 /* dead, about to kfree */ - -/* - * A single connection with another host. - * - * We maintain a queue of outgoing messages, and some session state to - * ensure that we can preserve the lossless, ordered delivery of - * messages in the case of a TCP disconnect. - */ -struct ceph_connection { - void *private; - atomic_t nref; - - const struct ceph_connection_operations *ops; - - struct ceph_messenger *msgr; - struct socket *sock; - unsigned long state; /* connection state (see flags above) */ - const char *error_msg; /* error message, if any */ - - struct ceph_entity_addr peer_addr; /* peer address */ - struct ceph_entity_name peer_name; /* peer name */ - struct ceph_entity_addr peer_addr_for_me; - unsigned peer_features; - u32 connect_seq; /* identify the most recent connection - attempt for this connection, client */ - u32 peer_global_seq; /* peer's global seq for this connection */ - - int auth_retry; /* true if we need a newer authorizer */ - void *auth_reply_buf; /* where to put the authorizer reply */ - int auth_reply_buf_len; - - struct mutex mutex; - - /* out queue */ - struct list_head out_queue; - struct list_head out_sent; /* sending or sent but unacked */ - u64 out_seq; /* last message queued for send */ - bool out_keepalive_pending; - - u64 in_seq, in_seq_acked; /* last message received, acked */ - - /* connection negotiation temps */ - char in_banner[CEPH_BANNER_MAX_LEN]; - union { - struct { /* outgoing connection */ - struct ceph_msg_connect out_connect; - struct ceph_msg_connect_reply in_reply; - }; - struct { /* incoming */ - struct ceph_msg_connect in_connect; - struct ceph_msg_connect_reply out_reply; - }; - }; - struct ceph_entity_addr actual_peer_addr; - - /* message out temps */ - struct ceph_msg *out_msg; /* sending message (== tail of - out_sent) */ - bool out_msg_done; - struct ceph_msg_pos out_msg_pos; - - struct kvec out_kvec[8], /* sending header/footer data */ - *out_kvec_cur; - int out_kvec_left; /* kvec's left in out_kvec */ - int out_skip; /* skip this many bytes */ - int out_kvec_bytes; /* total bytes left */ - bool out_kvec_is_msg; /* kvec refers to out_msg */ - int out_more; /* there is more data after the kvecs */ - __le64 out_temp_ack; /* for writing an ack */ - - /* message in temps */ - struct ceph_msg_header in_hdr; - struct ceph_msg *in_msg; - struct ceph_msg_pos in_msg_pos; - u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ - - char in_tag; /* protocol control byte */ - int in_base_pos; /* bytes read */ - __le64 in_temp_ack; /* for reading an ack */ - - struct delayed_work work; /* send|recv work */ - unsigned long delay; /* current delay interval */ -}; - - -extern const char *pr_addr(const struct sockaddr_storage *ss); -extern int ceph_parse_ips(const char *c, const char *end, - struct ceph_entity_addr *addr, - int max_count, int *count); - - -extern int ceph_msgr_init(void); -extern void ceph_msgr_exit(void); -extern void ceph_msgr_flush(void); - -extern struct ceph_messenger *ceph_messenger_create( - struct ceph_entity_addr *myaddr); -extern void ceph_messenger_destroy(struct ceph_messenger *); - -extern void ceph_con_init(struct ceph_messenger *msgr, - struct ceph_connection *con); -extern void ceph_con_open(struct ceph_connection *con, - struct ceph_entity_addr *addr); -extern bool ceph_con_opened(struct ceph_connection *con); -extern void ceph_con_close(struct ceph_connection *con); -extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg); -extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg); -extern void ceph_con_revoke_message(struct ceph_connection *con, - struct ceph_msg *msg); -extern void ceph_con_keepalive(struct ceph_connection *con); -extern struct ceph_connection *ceph_con_get(struct ceph_connection *con); -extern void ceph_con_put(struct ceph_connection *con); - -extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags); -extern void ceph_msg_kfree(struct ceph_msg *m); - - -static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg) -{ - kref_get(&msg->kref); - return msg; -} -extern void ceph_msg_last_put(struct kref *kref); -static inline void ceph_msg_put(struct ceph_msg *msg) -{ - kref_put(&msg->kref, ceph_msg_last_put); -} - -extern void ceph_msg_dump(struct ceph_msg *msg); - -#endif diff --git a/fs/ceph/mon_client.c b/fs/ceph/mon_client.c deleted file mode 100644 index b2a5a3e4a671..000000000000 --- a/fs/ceph/mon_client.c +++ /dev/null @@ -1,1018 +0,0 @@ -#include "ceph_debug.h" - -#include -#include -#include -#include - -#include "mon_client.h" -#include "super.h" -#include "auth.h" -#include "decode.h" - -/* - * Interact with Ceph monitor cluster. Handle requests for new map - * versions, and periodically resend as needed. Also implement - * statfs() and umount(). - * - * A small cluster of Ceph "monitors" are responsible for managing critical - * cluster configuration and state information. An odd number (e.g., 3, 5) - * of cmon daemons use a modified version of the Paxos part-time parliament - * algorithm to manage the MDS map (mds cluster membership), OSD map, and - * list of clients who have mounted the file system. - * - * We maintain an open, active session with a monitor at all times in order to - * receive timely MDSMap updates. We periodically send a keepalive byte on the - * TCP socket to ensure we detect a failure. If the connection does break, we - * randomly hunt for a new monitor. Once the connection is reestablished, we - * resend any outstanding requests. - */ - -static const struct ceph_connection_operations mon_con_ops; - -static int __validate_auth(struct ceph_mon_client *monc); - -/* - * Decode a monmap blob (e.g., during mount). - */ -struct ceph_monmap *ceph_monmap_decode(void *p, void *end) -{ - struct ceph_monmap *m = NULL; - int i, err = -EINVAL; - struct ceph_fsid fsid; - u32 epoch, num_mon; - u16 version; - u32 len; - - ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - - dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p)); - - ceph_decode_16_safe(&p, end, version, bad); - - ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad); - ceph_decode_copy(&p, &fsid, sizeof(fsid)); - epoch = ceph_decode_32(&p); - - num_mon = ceph_decode_32(&p); - ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad); - - if (num_mon >= CEPH_MAX_MON) - goto bad; - m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS); - if (m == NULL) - return ERR_PTR(-ENOMEM); - m->fsid = fsid; - m->epoch = epoch; - m->num_mon = num_mon; - ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0])); - for (i = 0; i < num_mon; i++) - ceph_decode_addr(&m->mon_inst[i].addr); - - dout("monmap_decode epoch %d, num_mon %d\n", m->epoch, - m->num_mon); - for (i = 0; i < m->num_mon; i++) - dout("monmap_decode mon%d is %s\n", i, - pr_addr(&m->mon_inst[i].addr.in_addr)); - return m; - -bad: - dout("monmap_decode failed with %d\n", err); - kfree(m); - return ERR_PTR(err); -} - -/* - * return true if *addr is included in the monmap. - */ -int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr) -{ - int i; - - for (i = 0; i < m->num_mon; i++) - if (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0) - return 1; - return 0; -} - -/* - * Send an auth request. - */ -static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) -{ - monc->pending_auth = 1; - monc->m_auth->front.iov_len = len; - monc->m_auth->hdr.front_len = cpu_to_le32(len); - ceph_con_revoke(monc->con, monc->m_auth); - ceph_msg_get(monc->m_auth); /* keep our ref */ - ceph_con_send(monc->con, monc->m_auth); -} - -/* - * Close monitor session, if any. - */ -static void __close_session(struct ceph_mon_client *monc) -{ - if (monc->con) { - dout("__close_session closing mon%d\n", monc->cur_mon); - ceph_con_revoke(monc->con, monc->m_auth); - ceph_con_close(monc->con); - monc->cur_mon = -1; - monc->pending_auth = 0; - ceph_auth_reset(monc->auth); - } -} - -/* - * Open a session with a (new) monitor. - */ -static int __open_session(struct ceph_mon_client *monc) -{ - char r; - int ret; - - if (monc->cur_mon < 0) { - get_random_bytes(&r, 1); - monc->cur_mon = r % monc->monmap->num_mon; - dout("open_session num=%d r=%d -> mon%d\n", - monc->monmap->num_mon, r, monc->cur_mon); - monc->sub_sent = 0; - monc->sub_renew_after = jiffies; /* i.e., expired */ - monc->want_next_osdmap = !!monc->want_next_osdmap; - - dout("open_session mon%d opening\n", monc->cur_mon); - monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON; - monc->con->peer_name.num = cpu_to_le64(monc->cur_mon); - ceph_con_open(monc->con, - &monc->monmap->mon_inst[monc->cur_mon].addr); - - /* initiatiate authentication handshake */ - ret = ceph_auth_build_hello(monc->auth, - monc->m_auth->front.iov_base, - monc->m_auth->front_max); - __send_prepared_auth_request(monc, ret); - } else { - dout("open_session mon%d already open\n", monc->cur_mon); - } - return 0; -} - -static bool __sub_expired(struct ceph_mon_client *monc) -{ - return time_after_eq(jiffies, monc->sub_renew_after); -} - -/* - * Reschedule delayed work timer. - */ -static void __schedule_delayed(struct ceph_mon_client *monc) -{ - unsigned delay; - - if (monc->cur_mon < 0 || __sub_expired(monc)) - delay = 10 * HZ; - else - delay = 20 * HZ; - dout("__schedule_delayed after %u\n", delay); - schedule_delayed_work(&monc->delayed_work, delay); -} - -/* - * Send subscribe request for mdsmap and/or osdmap. - */ -static void __send_subscribe(struct ceph_mon_client *monc) -{ - dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n", - (unsigned)monc->sub_sent, __sub_expired(monc), - monc->want_next_osdmap); - if ((__sub_expired(monc) && !monc->sub_sent) || - monc->want_next_osdmap == 1) { - struct ceph_msg *msg = monc->m_subscribe; - struct ceph_mon_subscribe_item *i; - void *p, *end; - - p = msg->front.iov_base; - end = p + msg->front_max; - - dout("__send_subscribe to 'mdsmap' %u+\n", - (unsigned)monc->have_mdsmap); - if (monc->want_next_osdmap) { - dout("__send_subscribe to 'osdmap' %u\n", - (unsigned)monc->have_osdmap); - ceph_encode_32(&p, 3); - ceph_encode_string(&p, end, "osdmap", 6); - i = p; - i->have = cpu_to_le64(monc->have_osdmap); - i->onetime = 1; - p += sizeof(*i); - monc->want_next_osdmap = 2; /* requested */ - } else { - ceph_encode_32(&p, 2); - } - ceph_encode_string(&p, end, "mdsmap", 6); - i = p; - i->have = cpu_to_le64(monc->have_mdsmap); - i->onetime = 0; - p += sizeof(*i); - ceph_encode_string(&p, end, "monmap", 6); - i = p; - i->have = 0; - i->onetime = 0; - p += sizeof(*i); - - msg->front.iov_len = p - msg->front.iov_base; - msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); - ceph_con_revoke(monc->con, msg); - ceph_con_send(monc->con, ceph_msg_get(msg)); - - monc->sub_sent = jiffies | 1; /* never 0 */ - } -} - -static void handle_subscribe_ack(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - unsigned seconds; - struct ceph_mon_subscribe_ack *h = msg->front.iov_base; - - if (msg->front.iov_len < sizeof(*h)) - goto bad; - seconds = le32_to_cpu(h->duration); - - mutex_lock(&monc->mutex); - if (monc->hunting) { - pr_info("mon%d %s session established\n", - monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr)); - monc->hunting = false; - } - dout("handle_subscribe_ack after %d seconds\n", seconds); - monc->sub_renew_after = monc->sub_sent + (seconds >> 1)*HZ - 1; - monc->sub_sent = 0; - mutex_unlock(&monc->mutex); - return; -bad: - pr_err("got corrupt subscribe-ack msg\n"); - ceph_msg_dump(msg); -} - -/* - * Keep track of which maps we have - */ -int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got) -{ - mutex_lock(&monc->mutex); - monc->have_mdsmap = got; - mutex_unlock(&monc->mutex); - return 0; -} - -int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got) -{ - mutex_lock(&monc->mutex); - monc->have_osdmap = got; - monc->want_next_osdmap = 0; - mutex_unlock(&monc->mutex); - return 0; -} - -/* - * Register interest in the next osdmap - */ -void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc) -{ - dout("request_next_osdmap have %u\n", monc->have_osdmap); - mutex_lock(&monc->mutex); - if (!monc->want_next_osdmap) - monc->want_next_osdmap = 1; - if (monc->want_next_osdmap < 2) - __send_subscribe(monc); - mutex_unlock(&monc->mutex); -} - -/* - * - */ -int ceph_monc_open_session(struct ceph_mon_client *monc) -{ - if (!monc->con) { - monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); - if (!monc->con) - return -ENOMEM; - ceph_con_init(monc->client->msgr, monc->con); - monc->con->private = monc; - monc->con->ops = &mon_con_ops; - } - - mutex_lock(&monc->mutex); - __open_session(monc); - __schedule_delayed(monc); - mutex_unlock(&monc->mutex); - return 0; -} - -/* - * The monitor responds with mount ack indicate mount success. The - * included client ticket allows the client to talk to MDSs and OSDs. - */ -static void ceph_monc_handle_map(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - struct ceph_client *client = monc->client; - struct ceph_monmap *monmap = NULL, *old = monc->monmap; - void *p, *end; - - mutex_lock(&monc->mutex); - - dout("handle_monmap\n"); - p = msg->front.iov_base; - end = p + msg->front.iov_len; - - monmap = ceph_monmap_decode(p, end); - if (IS_ERR(monmap)) { - pr_err("problem decoding monmap, %d\n", - (int)PTR_ERR(monmap)); - goto out; - } - - if (ceph_check_fsid(monc->client, &monmap->fsid) < 0) { - kfree(monmap); - goto out; - } - - client->monc.monmap = monmap; - kfree(old); - -out: - mutex_unlock(&monc->mutex); - wake_up_all(&client->auth_wq); -} - -/* - * generic requests (e.g., statfs, poolop) - */ -static struct ceph_mon_generic_request *__lookup_generic_req( - struct ceph_mon_client *monc, u64 tid) -{ - struct ceph_mon_generic_request *req; - struct rb_node *n = monc->generic_request_tree.rb_node; - - while (n) { - req = rb_entry(n, struct ceph_mon_generic_request, node); - if (tid < req->tid) - n = n->rb_left; - else if (tid > req->tid) - n = n->rb_right; - else - return req; - } - return NULL; -} - -static void __insert_generic_request(struct ceph_mon_client *monc, - struct ceph_mon_generic_request *new) -{ - struct rb_node **p = &monc->generic_request_tree.rb_node; - struct rb_node *parent = NULL; - struct ceph_mon_generic_request *req = NULL; - - while (*p) { - parent = *p; - req = rb_entry(parent, struct ceph_mon_generic_request, node); - if (new->tid < req->tid) - p = &(*p)->rb_left; - else if (new->tid > req->tid) - p = &(*p)->rb_right; - else - BUG(); - } - - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, &monc->generic_request_tree); -} - -static void release_generic_request(struct kref *kref) -{ - struct ceph_mon_generic_request *req = - container_of(kref, struct ceph_mon_generic_request, kref); - - if (req->reply) - ceph_msg_put(req->reply); - if (req->request) - ceph_msg_put(req->request); - - kfree(req); -} - -static void put_generic_request(struct ceph_mon_generic_request *req) -{ - kref_put(&req->kref, release_generic_request); -} - -static void get_generic_request(struct ceph_mon_generic_request *req) -{ - kref_get(&req->kref); -} - -static struct ceph_msg *get_generic_reply(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) -{ - struct ceph_mon_client *monc = con->private; - struct ceph_mon_generic_request *req; - u64 tid = le64_to_cpu(hdr->tid); - struct ceph_msg *m; - - mutex_lock(&monc->mutex); - req = __lookup_generic_req(monc, tid); - if (!req) { - dout("get_generic_reply %lld dne\n", tid); - *skip = 1; - m = NULL; - } else { - dout("get_generic_reply %lld got %p\n", tid, req->reply); - m = ceph_msg_get(req->reply); - /* - * we don't need to track the connection reading into - * this reply because we only have one open connection - * at a time, ever. - */ - } - mutex_unlock(&monc->mutex); - return m; -} - -static int do_generic_request(struct ceph_mon_client *monc, - struct ceph_mon_generic_request *req) -{ - int err; - - /* register request */ - mutex_lock(&monc->mutex); - req->tid = ++monc->last_tid; - req->request->hdr.tid = cpu_to_le64(req->tid); - __insert_generic_request(monc, req); - monc->num_generic_requests++; - ceph_con_send(monc->con, ceph_msg_get(req->request)); - mutex_unlock(&monc->mutex); - - err = wait_for_completion_interruptible(&req->completion); - - mutex_lock(&monc->mutex); - rb_erase(&req->node, &monc->generic_request_tree); - monc->num_generic_requests--; - mutex_unlock(&monc->mutex); - - if (!err) - err = req->result; - return err; -} - -/* - * statfs - */ -static void handle_statfs_reply(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_statfs_reply *reply = msg->front.iov_base; - u64 tid = le64_to_cpu(msg->hdr.tid); - - if (msg->front.iov_len != sizeof(*reply)) - goto bad; - dout("handle_statfs_reply %p tid %llu\n", msg, tid); - - mutex_lock(&monc->mutex); - req = __lookup_generic_req(monc, tid); - if (req) { - *(struct ceph_statfs *)req->buf = reply->st; - req->result = 0; - get_generic_request(req); - } - mutex_unlock(&monc->mutex); - if (req) { - complete_all(&req->completion); - put_generic_request(req); - } - return; - -bad: - pr_err("corrupt generic reply, tid %llu\n", tid); - ceph_msg_dump(msg); -} - -/* - * Do a synchronous statfs(). - */ -int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_statfs *h; - int err; - - req = kzalloc(sizeof(*req), GFP_NOFS); - if (!req) - return -ENOMEM; - - kref_init(&req->kref); - req->buf = buf; - req->buf_len = sizeof(*buf); - init_completion(&req->completion); - - err = -ENOMEM; - req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS); - if (!req->request) - goto out; - req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS); - if (!req->reply) - goto out; - - /* fill out request */ - h = req->request->front.iov_base; - h->monhdr.have_version = 0; - h->monhdr.session_mon = cpu_to_le16(-1); - h->monhdr.session_mon_tid = 0; - h->fsid = monc->monmap->fsid; - - err = do_generic_request(monc, req); - -out: - kref_put(&req->kref, release_generic_request); - return err; -} - -/* - * pool ops - */ -static int get_poolop_reply_buf(const char *src, size_t src_len, - char *dst, size_t dst_len) -{ - u32 buf_len; - - if (src_len != sizeof(u32) + dst_len) - return -EINVAL; - - buf_len = le32_to_cpu(*(u32 *)src); - if (buf_len != dst_len) - return -EINVAL; - - memcpy(dst, src + sizeof(u32), dst_len); - return 0; -} - -static void handle_poolop_reply(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_poolop_reply *reply = msg->front.iov_base; - u64 tid = le64_to_cpu(msg->hdr.tid); - - if (msg->front.iov_len < sizeof(*reply)) - goto bad; - dout("handle_poolop_reply %p tid %llu\n", msg, tid); - - mutex_lock(&monc->mutex); - req = __lookup_generic_req(monc, tid); - if (req) { - if (req->buf_len && - get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply), - msg->front.iov_len - sizeof(*reply), - req->buf, req->buf_len) < 0) { - mutex_unlock(&monc->mutex); - goto bad; - } - req->result = le32_to_cpu(reply->reply_code); - get_generic_request(req); - } - mutex_unlock(&monc->mutex); - if (req) { - complete(&req->completion); - put_generic_request(req); - } - return; - -bad: - pr_err("corrupt generic reply, tid %llu\n", tid); - ceph_msg_dump(msg); -} - -/* - * Do a synchronous pool op. - */ -int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op, - u32 pool, u64 snapid, - char *buf, int len) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_poolop *h; - int err; - - req = kzalloc(sizeof(*req), GFP_NOFS); - if (!req) - return -ENOMEM; - - kref_init(&req->kref); - req->buf = buf; - req->buf_len = len; - init_completion(&req->completion); - - err = -ENOMEM; - req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS); - if (!req->request) - goto out; - req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS); - if (!req->reply) - goto out; - - /* fill out request */ - req->request->hdr.version = cpu_to_le16(2); - h = req->request->front.iov_base; - h->monhdr.have_version = 0; - h->monhdr.session_mon = cpu_to_le16(-1); - h->monhdr.session_mon_tid = 0; - h->fsid = monc->monmap->fsid; - h->pool = cpu_to_le32(pool); - h->op = cpu_to_le32(op); - h->auid = 0; - h->snapid = cpu_to_le64(snapid); - h->name_len = 0; - - err = do_generic_request(monc, req); - -out: - kref_put(&req->kref, release_generic_request); - return err; -} - -int ceph_monc_create_snapid(struct ceph_mon_client *monc, - u32 pool, u64 *snapid) -{ - return ceph_monc_do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, - pool, 0, (char *)snapid, sizeof(*snapid)); - -} - -int ceph_monc_delete_snapid(struct ceph_mon_client *monc, - u32 pool, u64 snapid) -{ - return ceph_monc_do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, - pool, snapid, 0, 0); - -} - -/* - * Resend pending generic requests. - */ -static void __resend_generic_request(struct ceph_mon_client *monc) -{ - struct ceph_mon_generic_request *req; - struct rb_node *p; - - for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) { - req = rb_entry(p, struct ceph_mon_generic_request, node); - ceph_con_revoke(monc->con, req->request); - ceph_con_send(monc->con, ceph_msg_get(req->request)); - } -} - -/* - * Delayed work. If we haven't mounted yet, retry. Otherwise, - * renew/retry subscription as needed (in case it is timing out, or we - * got an ENOMEM). And keep the monitor connection alive. - */ -static void delayed_work(struct work_struct *work) -{ - struct ceph_mon_client *monc = - container_of(work, struct ceph_mon_client, delayed_work.work); - - dout("monc delayed_work\n"); - mutex_lock(&monc->mutex); - if (monc->hunting) { - __close_session(monc); - __open_session(monc); /* continue hunting */ - } else { - ceph_con_keepalive(monc->con); - - __validate_auth(monc); - - if (monc->auth->ops->is_authenticated(monc->auth)) - __send_subscribe(monc); - } - __schedule_delayed(monc); - mutex_unlock(&monc->mutex); -} - -/* - * On startup, we build a temporary monmap populated with the IPs - * provided by mount(2). - */ -static int build_initial_monmap(struct ceph_mon_client *monc) -{ - struct ceph_mount_args *args = monc->client->mount_args; - struct ceph_entity_addr *mon_addr = args->mon_addr; - int num_mon = args->num_mon; - int i; - - /* build initial monmap */ - monc->monmap = kzalloc(sizeof(*monc->monmap) + - num_mon*sizeof(monc->monmap->mon_inst[0]), - GFP_KERNEL); - if (!monc->monmap) - return -ENOMEM; - for (i = 0; i < num_mon; i++) { - monc->monmap->mon_inst[i].addr = mon_addr[i]; - monc->monmap->mon_inst[i].addr.nonce = 0; - monc->monmap->mon_inst[i].name.type = - CEPH_ENTITY_TYPE_MON; - monc->monmap->mon_inst[i].name.num = cpu_to_le64(i); - } - monc->monmap->num_mon = num_mon; - monc->have_fsid = false; - - /* release addr memory */ - kfree(args->mon_addr); - args->mon_addr = NULL; - args->num_mon = 0; - return 0; -} - -int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) -{ - int err = 0; - - dout("init\n"); - memset(monc, 0, sizeof(*monc)); - monc->client = cl; - monc->monmap = NULL; - mutex_init(&monc->mutex); - - err = build_initial_monmap(monc); - if (err) - goto out; - - monc->con = NULL; - - /* authentication */ - monc->auth = ceph_auth_init(cl->mount_args->name, - cl->mount_args->secret); - if (IS_ERR(monc->auth)) - return PTR_ERR(monc->auth); - monc->auth->want_keys = - CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON | - CEPH_ENTITY_TYPE_OSD | CEPH_ENTITY_TYPE_MDS; - - /* msgs */ - err = -ENOMEM; - monc->m_subscribe_ack = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE_ACK, - sizeof(struct ceph_mon_subscribe_ack), - GFP_NOFS); - if (!monc->m_subscribe_ack) - goto out_monmap; - - monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS); - if (!monc->m_subscribe) - goto out_subscribe_ack; - - monc->m_auth_reply = ceph_msg_new(CEPH_MSG_AUTH_REPLY, 4096, GFP_NOFS); - if (!monc->m_auth_reply) - goto out_subscribe; - - monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, GFP_NOFS); - monc->pending_auth = 0; - if (!monc->m_auth) - goto out_auth_reply; - - monc->cur_mon = -1; - monc->hunting = true; - monc->sub_renew_after = jiffies; - monc->sub_sent = 0; - - INIT_DELAYED_WORK(&monc->delayed_work, delayed_work); - monc->generic_request_tree = RB_ROOT; - monc->num_generic_requests = 0; - monc->last_tid = 0; - - monc->have_mdsmap = 0; - monc->have_osdmap = 0; - monc->want_next_osdmap = 1; - return 0; - -out_auth_reply: - ceph_msg_put(monc->m_auth_reply); -out_subscribe: - ceph_msg_put(monc->m_subscribe); -out_subscribe_ack: - ceph_msg_put(monc->m_subscribe_ack); -out_monmap: - kfree(monc->monmap); -out: - return err; -} - -void ceph_monc_stop(struct ceph_mon_client *monc) -{ - dout("stop\n"); - cancel_delayed_work_sync(&monc->delayed_work); - - mutex_lock(&monc->mutex); - __close_session(monc); - if (monc->con) { - monc->con->private = NULL; - monc->con->ops->put(monc->con); - monc->con = NULL; - } - mutex_unlock(&monc->mutex); - - ceph_auth_destroy(monc->auth); - - ceph_msg_put(monc->m_auth); - ceph_msg_put(monc->m_auth_reply); - ceph_msg_put(monc->m_subscribe); - ceph_msg_put(monc->m_subscribe_ack); - - kfree(monc->monmap); -} - -static void handle_auth_reply(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - int ret; - int was_auth = 0; - - mutex_lock(&monc->mutex); - if (monc->auth->ops) - was_auth = monc->auth->ops->is_authenticated(monc->auth); - monc->pending_auth = 0; - ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, - msg->front.iov_len, - monc->m_auth->front.iov_base, - monc->m_auth->front_max); - if (ret < 0) { - monc->client->auth_err = ret; - wake_up_all(&monc->client->auth_wq); - } else if (ret > 0) { - __send_prepared_auth_request(monc, ret); - } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { - dout("authenticated, starting session\n"); - - monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT; - monc->client->msgr->inst.name.num = - cpu_to_le64(monc->auth->global_id); - - __send_subscribe(monc); - __resend_generic_request(monc); - } - mutex_unlock(&monc->mutex); -} - -static int __validate_auth(struct ceph_mon_client *monc) -{ - int ret; - - if (monc->pending_auth) - return 0; - - ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); - if (ret <= 0) - return ret; /* either an error, or no need to authenticate */ - __send_prepared_auth_request(monc, ret); - return 0; -} - -int ceph_monc_validate_auth(struct ceph_mon_client *monc) -{ - int ret; - - mutex_lock(&monc->mutex); - ret = __validate_auth(monc); - mutex_unlock(&monc->mutex); - return ret; -} - -/* - * handle incoming message - */ -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) -{ - struct ceph_mon_client *monc = con->private; - int type = le16_to_cpu(msg->hdr.type); - - if (!monc) - return; - - switch (type) { - case CEPH_MSG_AUTH_REPLY: - handle_auth_reply(monc, msg); - break; - - case CEPH_MSG_MON_SUBSCRIBE_ACK: - handle_subscribe_ack(monc, msg); - break; - - case CEPH_MSG_STATFS_REPLY: - handle_statfs_reply(monc, msg); - break; - - case CEPH_MSG_POOLOP_REPLY: - handle_poolop_reply(monc, msg); - break; - - case CEPH_MSG_MON_MAP: - ceph_monc_handle_map(monc, msg); - break; - - case CEPH_MSG_MDS_MAP: - ceph_mdsc_handle_map(&monc->client->mdsc, msg); - break; - - case CEPH_MSG_OSD_MAP: - ceph_osdc_handle_map(&monc->client->osdc, msg); - break; - - default: - pr_err("received unknown message type %d %s\n", type, - ceph_msg_type_name(type)); - } - ceph_msg_put(msg); -} - -/* - * Allocate memory for incoming message - */ -static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) -{ - struct ceph_mon_client *monc = con->private; - int type = le16_to_cpu(hdr->type); - int front_len = le32_to_cpu(hdr->front_len); - struct ceph_msg *m = NULL; - - *skip = 0; - - switch (type) { - case CEPH_MSG_MON_SUBSCRIBE_ACK: - m = ceph_msg_get(monc->m_subscribe_ack); - break; - case CEPH_MSG_POOLOP_REPLY: - case CEPH_MSG_STATFS_REPLY: - return get_generic_reply(con, hdr, skip); - case CEPH_MSG_AUTH_REPLY: - m = ceph_msg_get(monc->m_auth_reply); - break; - case CEPH_MSG_MON_MAP: - case CEPH_MSG_MDS_MAP: - case CEPH_MSG_OSD_MAP: - m = ceph_msg_new(type, front_len, GFP_NOFS); - break; - } - - if (!m) { - pr_info("alloc_msg unknown type %d\n", type); - *skip = 1; - } - return m; -} - -/* - * If the monitor connection resets, pick a new monitor and resubmit - * any pending requests. - */ -static void mon_fault(struct ceph_connection *con) -{ - struct ceph_mon_client *monc = con->private; - - if (!monc) - return; - - dout("mon_fault\n"); - mutex_lock(&monc->mutex); - if (!con->private) - goto out; - - if (monc->con && !monc->hunting) - pr_info("mon%d %s session lost, " - "hunting for new mon\n", monc->cur_mon, - pr_addr(&monc->con->peer_addr.in_addr)); - - __close_session(monc); - if (!monc->hunting) { - /* start hunting */ - monc->hunting = true; - __open_session(monc); - } else { - /* already hunting, let's wait a bit */ - __schedule_delayed(monc); - } -out: - mutex_unlock(&monc->mutex); -} - -static const struct ceph_connection_operations mon_con_ops = { - .get = ceph_con_get, - .put = ceph_con_put, - .dispatch = dispatch, - .fault = mon_fault, - .alloc_msg = mon_alloc_msg, -}; diff --git a/fs/ceph/mon_client.h b/fs/ceph/mon_client.h deleted file mode 100644 index 8e396f2c0963..000000000000 --- a/fs/ceph/mon_client.h +++ /dev/null @@ -1,121 +0,0 @@ -#ifndef _FS_CEPH_MON_CLIENT_H -#define _FS_CEPH_MON_CLIENT_H - -#include -#include -#include - -#include "messenger.h" - -struct ceph_client; -struct ceph_mount_args; -struct ceph_auth_client; - -/* - * The monitor map enumerates the set of all monitors. - */ -struct ceph_monmap { - struct ceph_fsid fsid; - u32 epoch; - u32 num_mon; - struct ceph_entity_inst mon_inst[0]; -}; - -struct ceph_mon_client; -struct ceph_mon_generic_request; - - -/* - * Generic mechanism for resending monitor requests. - */ -typedef void (*ceph_monc_request_func_t)(struct ceph_mon_client *monc, - int newmon); - -/* a pending monitor request */ -struct ceph_mon_request { - struct ceph_mon_client *monc; - struct delayed_work delayed_work; - unsigned long delay; - ceph_monc_request_func_t do_request; -}; - -/* - * ceph_mon_generic_request is being used for the statfs and poolop requests - * which are bening done a bit differently because we need to get data back - * to the caller - */ -struct ceph_mon_generic_request { - struct kref kref; - u64 tid; - struct rb_node node; - int result; - void *buf; - int buf_len; - struct completion completion; - struct ceph_msg *request; /* original request */ - struct ceph_msg *reply; /* and reply */ -}; - -struct ceph_mon_client { - struct ceph_client *client; - struct ceph_monmap *monmap; - - struct mutex mutex; - struct delayed_work delayed_work; - - struct ceph_auth_client *auth; - struct ceph_msg *m_auth, *m_auth_reply, *m_subscribe, *m_subscribe_ack; - int pending_auth; - - bool hunting; - int cur_mon; /* last monitor i contacted */ - unsigned long sub_sent, sub_renew_after; - struct ceph_connection *con; - bool have_fsid; - - /* pending generic requests */ - struct rb_root generic_request_tree; - int num_generic_requests; - u64 last_tid; - - /* mds/osd map */ - int want_next_osdmap; /* 1 = want, 2 = want+asked */ - u32 have_osdmap, have_mdsmap; - -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs_file; -#endif -}; - -extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end); -extern int ceph_monmap_contains(struct ceph_monmap *m, - struct ceph_entity_addr *addr); - -extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl); -extern void ceph_monc_stop(struct ceph_mon_client *monc); - -/* - * The model here is to indicate that we need a new map of at least - * epoch @want, and also call in when we receive a map. We will - * periodically rerequest the map from the monitor cluster until we - * get what we want. - */ -extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have); -extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have); - -extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc); - -extern int ceph_monc_do_statfs(struct ceph_mon_client *monc, - struct ceph_statfs *buf); - -extern int ceph_monc_open_session(struct ceph_mon_client *monc); - -extern int ceph_monc_validate_auth(struct ceph_mon_client *monc); - -extern int ceph_monc_create_snapid(struct ceph_mon_client *monc, - u32 pool, u64 *snapid); - -extern int ceph_monc_delete_snapid(struct ceph_mon_client *monc, - u32 pool, u64 snapid); - -#endif diff --git a/fs/ceph/msgpool.c b/fs/ceph/msgpool.c deleted file mode 100644 index dd65a6438131..000000000000 --- a/fs/ceph/msgpool.c +++ /dev/null @@ -1,64 +0,0 @@ -#include "ceph_debug.h" - -#include -#include -#include -#include - -#include "msgpool.h" - -static void *alloc_fn(gfp_t gfp_mask, void *arg) -{ - struct ceph_msgpool *pool = arg; - void *p; - - p = ceph_msg_new(0, pool->front_len, gfp_mask); - if (!p) - pr_err("msgpool %s alloc failed\n", pool->name); - return p; -} - -static void free_fn(void *element, void *arg) -{ - ceph_msg_put(element); -} - -int ceph_msgpool_init(struct ceph_msgpool *pool, - int front_len, int size, bool blocking, const char *name) -{ - pool->front_len = front_len; - pool->pool = mempool_create(size, alloc_fn, free_fn, pool); - if (!pool->pool) - return -ENOMEM; - pool->name = name; - return 0; -} - -void ceph_msgpool_destroy(struct ceph_msgpool *pool) -{ - mempool_destroy(pool->pool); -} - -struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, - int front_len) -{ - if (front_len > pool->front_len) { - pr_err("msgpool_get pool %s need front %d, pool size is %d\n", - pool->name, front_len, pool->front_len); - WARN_ON(1); - - /* try to alloc a fresh message */ - return ceph_msg_new(0, front_len, GFP_NOFS); - } - - return mempool_alloc(pool->pool, GFP_NOFS); -} - -void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg) -{ - /* reset msg front_len; user may have changed it */ - msg->front.iov_len = pool->front_len; - msg->hdr.front_len = cpu_to_le32(pool->front_len); - - kref_init(&msg->kref); /* retake single ref */ -} diff --git a/fs/ceph/msgpool.h b/fs/ceph/msgpool.h deleted file mode 100644 index a362605f9368..000000000000 --- a/fs/ceph/msgpool.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _FS_CEPH_MSGPOOL -#define _FS_CEPH_MSGPOOL - -#include -#include "messenger.h" - -/* - * we use memory pools for preallocating messages we may receive, to - * avoid unexpected OOM conditions. - */ -struct ceph_msgpool { - const char *name; - mempool_t *pool; - int front_len; /* preallocated payload size */ -}; - -extern int ceph_msgpool_init(struct ceph_msgpool *pool, - int front_len, int size, bool blocking, - const char *name); -extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); -extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, - int front_len); -extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); - -#endif diff --git a/fs/ceph/msgr.h b/fs/ceph/msgr.h deleted file mode 100644 index 680d3d648cac..000000000000 --- a/fs/ceph/msgr.h +++ /dev/null @@ -1,175 +0,0 @@ -#ifndef CEPH_MSGR_H -#define CEPH_MSGR_H - -/* - * Data types for message passing layer used by Ceph. - */ - -#define CEPH_MON_PORT 6789 /* default monitor port */ - -/* - * client-side processes will try to bind to ports in this - * range, simply for the benefit of tools like nmap or wireshark - * that would like to identify the protocol. - */ -#define CEPH_PORT_FIRST 6789 -#define CEPH_PORT_START 6800 /* non-monitors start here */ -#define CEPH_PORT_LAST 6900 - -/* - * tcp connection banner. include a protocol version. and adjust - * whenever the wire protocol changes. try to keep this string length - * constant. - */ -#define CEPH_BANNER "ceph v027" -#define CEPH_BANNER_MAX_LEN 30 - - -/* - * Rollover-safe type and comparator for 32-bit sequence numbers. - * Comparator returns -1, 0, or 1. - */ -typedef __u32 ceph_seq_t; - -static inline __s32 ceph_seq_cmp(__u32 a, __u32 b) -{ - return (__s32)a - (__s32)b; -} - - -/* - * entity_name -- logical name for a process participating in the - * network, e.g. 'mds0' or 'osd3'. - */ -struct ceph_entity_name { - __u8 type; /* CEPH_ENTITY_TYPE_* */ - __le64 num; -} __attribute__ ((packed)); - -#define CEPH_ENTITY_TYPE_MON 0x01 -#define CEPH_ENTITY_TYPE_MDS 0x02 -#define CEPH_ENTITY_TYPE_OSD 0x04 -#define CEPH_ENTITY_TYPE_CLIENT 0x08 -#define CEPH_ENTITY_TYPE_AUTH 0x20 - -#define CEPH_ENTITY_TYPE_ANY 0xFF - -extern const char *ceph_entity_type_name(int type); - -/* - * entity_addr -- network address - */ -struct ceph_entity_addr { - __le32 type; - __le32 nonce; /* unique id for process (e.g. pid) */ - struct sockaddr_storage in_addr; -} __attribute__ ((packed)); - -struct ceph_entity_inst { - struct ceph_entity_name name; - struct ceph_entity_addr addr; -} __attribute__ ((packed)); - - -/* used by message exchange protocol */ -#define CEPH_MSGR_TAG_READY 1 /* server->client: ready for messages */ -#define CEPH_MSGR_TAG_RESETSESSION 2 /* server->client: reset, try again */ -#define CEPH_MSGR_TAG_WAIT 3 /* server->client: wait for racing - incoming connection */ -#define CEPH_MSGR_TAG_RETRY_SESSION 4 /* server->client + cseq: try again - with higher cseq */ -#define CEPH_MSGR_TAG_RETRY_GLOBAL 5 /* server->client + gseq: try again - with higher gseq */ -#define CEPH_MSGR_TAG_CLOSE 6 /* closing pipe */ -#define CEPH_MSGR_TAG_MSG 7 /* message */ -#define CEPH_MSGR_TAG_ACK 8 /* message ack */ -#define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ -#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ -#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ -#define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ - - -/* - * connection negotiation - */ -struct ceph_msg_connect { - __le64 features; /* supported feature bits */ - __le32 host_type; /* CEPH_ENTITY_TYPE_* */ - __le32 global_seq; /* count connections initiated by this host */ - __le32 connect_seq; /* count connections initiated in this session */ - __le32 protocol_version; - __le32 authorizer_protocol; - __le32 authorizer_len; - __u8 flags; /* CEPH_MSG_CONNECT_* */ -} __attribute__ ((packed)); - -struct ceph_msg_connect_reply { - __u8 tag; - __le64 features; /* feature bits for this session */ - __le32 global_seq; - __le32 connect_seq; - __le32 protocol_version; - __le32 authorizer_len; - __u8 flags; -} __attribute__ ((packed)); - -#define CEPH_MSG_CONNECT_LOSSY 1 /* messages i send may be safely dropped */ - - -/* - * message header - */ -struct ceph_msg_header_old { - __le64 seq; /* message seq# for this session */ - __le64 tid; /* transaction id */ - __le16 type; /* message type */ - __le16 priority; /* priority. higher value == higher priority */ - __le16 version; /* version of message encoding */ - - __le32 front_len; /* bytes in main payload */ - __le32 middle_len;/* bytes in middle payload */ - __le32 data_len; /* bytes of data payload */ - __le16 data_off; /* sender: include full offset; - receiver: mask against ~PAGE_MASK */ - - struct ceph_entity_inst src, orig_src; - __le32 reserved; - __le32 crc; /* header crc32c */ -} __attribute__ ((packed)); - -struct ceph_msg_header { - __le64 seq; /* message seq# for this session */ - __le64 tid; /* transaction id */ - __le16 type; /* message type */ - __le16 priority; /* priority. higher value == higher priority */ - __le16 version; /* version of message encoding */ - - __le32 front_len; /* bytes in main payload */ - __le32 middle_len;/* bytes in middle payload */ - __le32 data_len; /* bytes of data payload */ - __le16 data_off; /* sender: include full offset; - receiver: mask against ~PAGE_MASK */ - - struct ceph_entity_name src; - __le32 reserved; - __le32 crc; /* header crc32c */ -} __attribute__ ((packed)); - -#define CEPH_MSG_PRIO_LOW 64 -#define CEPH_MSG_PRIO_DEFAULT 127 -#define CEPH_MSG_PRIO_HIGH 196 -#define CEPH_MSG_PRIO_HIGHEST 255 - -/* - * follows data payload - */ -struct ceph_msg_footer { - __le32 front_crc, middle_crc, data_crc; - __u8 flags; -} __attribute__ ((packed)); - -#define CEPH_MSG_FOOTER_COMPLETE (1<<0) /* msg wasn't aborted */ -#define CEPH_MSG_FOOTER_NOCRC (1<<1) /* no data crc */ - - -#endif diff --git a/fs/ceph/osd_client.c b/fs/ceph/osd_client.c deleted file mode 100644 index 0edb43f1ef26..000000000000 --- a/fs/ceph/osd_client.c +++ /dev/null @@ -1,1771 +0,0 @@ -#include "ceph_debug.h" - -#include -#include -#include -#include -#include -#include -#ifdef CONFIG_BLOCK -#include -#endif - -#include "super.h" -#include "osd_client.h" -#include "messenger.h" -#include "decode.h" -#include "auth.h" -#include "pagelist.h" - -#define OSD_OP_FRONT_LEN 4096 -#define OSD_OPREPLY_FRONT_LEN 512 - -static const struct ceph_connection_operations osd_con_ops; -static int __kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd); - -static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd); - -static int op_needs_trail(int op) -{ - switch (op) { - case CEPH_OSD_OP_GETXATTR: - case CEPH_OSD_OP_SETXATTR: - case CEPH_OSD_OP_CMPXATTR: - case CEPH_OSD_OP_CALL: - return 1; - default: - return 0; - } -} - -static int op_has_extent(int op) -{ - return (op == CEPH_OSD_OP_READ || - op == CEPH_OSD_OP_WRITE); -} - -void ceph_calc_raw_layout(struct ceph_osd_client *osdc, - struct ceph_file_layout *layout, - u64 snapid, - u64 off, u64 *plen, u64 *bno, - struct ceph_osd_request *req, - struct ceph_osd_req_op *op) -{ - struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; - u64 orig_len = *plen; - u64 objoff, objlen; /* extent in object */ - - reqhead->snapid = cpu_to_le64(snapid); - - /* object extent? */ - ceph_calc_file_object_mapping(layout, off, plen, bno, - &objoff, &objlen); - if (*plen < orig_len) - dout(" skipping last %llu, final file extent %llu~%llu\n", - orig_len - *plen, off, *plen); - - if (op_has_extent(op->op)) { - op->extent.offset = objoff; - op->extent.length = objlen; - } - req->r_num_pages = calc_pages_for(off, *plen); - - dout("calc_layout bno=%llx %llu~%llu (%d pages)\n", - *bno, objoff, objlen, req->r_num_pages); - -} - -/* - * Implement client access to distributed object storage cluster. - * - * All data objects are stored within a cluster/cloud of OSDs, or - * "object storage devices." (Note that Ceph OSDs have _nothing_ to - * do with the T10 OSD extensions to SCSI.) Ceph OSDs are simply - * remote daemons serving up and coordinating consistent and safe - * access to storage. - * - * Cluster membership and the mapping of data objects onto storage devices - * are described by the osd map. - * - * We keep track of pending OSD requests (read, write), resubmit - * requests to different OSDs when the cluster topology/data layout - * change, or retry the affected requests when the communications - * channel with an OSD is reset. - */ - -/* - * calculate the mapping of a file extent onto an object, and fill out the - * request accordingly. shorten extent as necessary if it crosses an - * object boundary. - * - * fill osd op in request message. - */ -static void calc_layout(struct ceph_osd_client *osdc, - struct ceph_vino vino, - struct ceph_file_layout *layout, - u64 off, u64 *plen, - struct ceph_osd_request *req, - struct ceph_osd_req_op *op) -{ - u64 bno; - - ceph_calc_raw_layout(osdc, layout, vino.snap, off, - plen, &bno, req, op); - - sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno); - req->r_oid_len = strlen(req->r_oid); -} - -/* - * requests - */ -void ceph_osdc_release_request(struct kref *kref) -{ - struct ceph_osd_request *req = container_of(kref, - struct ceph_osd_request, - r_kref); - - if (req->r_request) - ceph_msg_put(req->r_request); - if (req->r_reply) - ceph_msg_put(req->r_reply); - if (req->r_con_filling_msg) { - dout("release_request revoking pages %p from con %p\n", - req->r_pages, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, - req->r_reply); - ceph_con_put(req->r_con_filling_msg); - } - if (req->r_own_pages) - ceph_release_page_vector(req->r_pages, - req->r_num_pages); -#ifdef CONFIG_BLOCK - if (req->r_bio) - bio_put(req->r_bio); -#endif - ceph_put_snap_context(req->r_snapc); - if (req->r_trail) { - ceph_pagelist_release(req->r_trail); - kfree(req->r_trail); - } - if (req->r_mempool) - mempool_free(req, req->r_osdc->req_mempool); - else - kfree(req); -} - -static int op_needs_trail(int op) -{ - switch (op) { - case CEPH_OSD_OP_GETXATTR: - case CEPH_OSD_OP_SETXATTR: - case CEPH_OSD_OP_CMPXATTR: - case CEPH_OSD_OP_CALL: - return 1; - default: - return 0; - } -} - -static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail) -{ - int i = 0; - - if (needs_trail) - *needs_trail = 0; - while (ops[i].op) { - if (needs_trail && op_needs_trail(ops[i].op)) - *needs_trail = 1; - i++; - } - - return i; -} - -struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, - int flags, - struct ceph_snap_context *snapc, - struct ceph_osd_req_op *ops, - bool use_mempool, - gfp_t gfp_flags, - struct page **pages, - struct bio *bio) -{ - struct ceph_osd_request *req; - struct ceph_msg *msg; - int needs_trail; - int num_op = get_num_ops(ops, &needs_trail); - size_t msg_size = sizeof(struct ceph_osd_request_head); - - msg_size += num_op*sizeof(struct ceph_osd_op); - - if (use_mempool) { - req = mempool_alloc(osdc->req_mempool, gfp_flags); - memset(req, 0, sizeof(*req)); - } else { - req = kzalloc(sizeof(*req), gfp_flags); - } - if (req == NULL) - return NULL; - - req->r_osdc = osdc; - req->r_mempool = use_mempool; - - kref_init(&req->r_kref); - init_completion(&req->r_completion); - init_completion(&req->r_safe_completion); - INIT_LIST_HEAD(&req->r_unsafe_item); - req->r_flags = flags; - - WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); - - /* create reply message */ - if (use_mempool) - msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); - else - msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, - OSD_OPREPLY_FRONT_LEN, gfp_flags); - if (!msg) { - ceph_osdc_put_request(req); - return NULL; - } - req->r_reply = msg; - - /* allocate space for the trailing data */ - if (needs_trail) { - req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags); - if (!req->r_trail) { - ceph_osdc_put_request(req); - return NULL; - } - ceph_pagelist_init(req->r_trail); - } - /* create request message; allow space for oid */ - msg_size += 40; - if (snapc) - msg_size += sizeof(u64) * snapc->num_snaps; - if (use_mempool) - msg = ceph_msgpool_get(&osdc->msgpool_op, 0); - else - msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags); - if (!msg) { - ceph_osdc_put_request(req); - return NULL; - } - - msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP); - memset(msg->front.iov_base, 0, msg->front.iov_len); - - req->r_request = msg; - req->r_pages = pages; -#ifdef CONFIG_BLOCK - if (bio) { - req->r_bio = bio; - bio_get(req->r_bio); - } -#endif - - return req; -} - -static void osd_req_encode_op(struct ceph_osd_request *req, - struct ceph_osd_op *dst, - struct ceph_osd_req_op *src) -{ - dst->op = cpu_to_le16(src->op); - - switch (dst->op) { - case CEPH_OSD_OP_READ: - case CEPH_OSD_OP_WRITE: - dst->extent.offset = - cpu_to_le64(src->extent.offset); - dst->extent.length = - cpu_to_le64(src->extent.length); - dst->extent.truncate_size = - cpu_to_le64(src->extent.truncate_size); - dst->extent.truncate_seq = - cpu_to_le32(src->extent.truncate_seq); - break; - - case CEPH_OSD_OP_GETXATTR: - case CEPH_OSD_OP_SETXATTR: - case CEPH_OSD_OP_CMPXATTR: - BUG_ON(!req->r_trail); - - dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); - dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); - dst->xattr.cmp_op = src->xattr.cmp_op; - dst->xattr.cmp_mode = src->xattr.cmp_mode; - ceph_pagelist_append(req->r_trail, src->xattr.name, - src->xattr.name_len); - ceph_pagelist_append(req->r_trail, src->xattr.val, - src->xattr.value_len); - break; - case CEPH_OSD_OP_CALL: - BUG_ON(!req->r_trail); - - dst->cls.class_len = src->cls.class_len; - dst->cls.method_len = src->cls.method_len; - dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); - - ceph_pagelist_append(req->r_trail, src->cls.class_name, - src->cls.class_len); - ceph_pagelist_append(req->r_trail, src->cls.method_name, - src->cls.method_len); - ceph_pagelist_append(req->r_trail, src->cls.indata, - src->cls.indata_len); - break; - case CEPH_OSD_OP_ROLLBACK: - dst->snap.snapid = cpu_to_le64(src->snap.snapid); - break; - case CEPH_OSD_OP_STARTSYNC: - break; - default: - pr_err("unrecognized osd opcode %d\n", dst->op); - WARN_ON(1); - break; - } - dst->payload_len = cpu_to_le32(src->payload_len); -} - -/* - * build new request AND message - * - */ -void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 *plen, - struct ceph_osd_req_op *src_ops, - struct ceph_snap_context *snapc, - struct timespec *mtime, - const char *oid, - int oid_len) -{ - struct ceph_msg *msg = req->r_request; - struct ceph_osd_request_head *head; - struct ceph_osd_req_op *src_op; - struct ceph_osd_op *op; - void *p; - int num_op = get_num_ops(src_ops, NULL); - size_t msg_size = sizeof(*head) + num_op*sizeof(*op); - int flags = req->r_flags; - u64 data_len = 0; - int i; - - head = msg->front.iov_base; - op = (void *)(head + 1); - p = (void *)(op + num_op); - - req->r_snapc = ceph_get_snap_context(snapc); - - head->client_inc = cpu_to_le32(1); /* always, for now. */ - head->flags = cpu_to_le32(flags); - if (flags & CEPH_OSD_FLAG_WRITE) - ceph_encode_timespec(&head->mtime, mtime); - head->num_ops = cpu_to_le16(num_op); - - - /* fill in oid */ - head->object_len = cpu_to_le32(oid_len); - memcpy(p, oid, oid_len); - p += oid_len; - - src_op = src_ops; - while (src_op->op) { - osd_req_encode_op(req, op, src_op); - src_op++; - op++; - } - - if (req->r_trail) - data_len += req->r_trail->length; - - if (snapc) { - head->snap_seq = cpu_to_le64(snapc->seq); - head->num_snaps = cpu_to_le32(snapc->num_snaps); - for (i = 0; i < snapc->num_snaps; i++) { - put_unaligned_le64(snapc->snaps[i], p); - p += sizeof(u64); - } - } - - if (flags & CEPH_OSD_FLAG_WRITE) { - req->r_request->hdr.data_off = cpu_to_le16(off); - req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len); - } else if (data_len) { - req->r_request->hdr.data_off = 0; - req->r_request->hdr.data_len = cpu_to_le32(data_len); - } - - BUG_ON(p > msg->front.iov_base + msg->front.iov_len); - msg_size = p - msg->front.iov_base; - msg->front.iov_len = msg_size; - msg->hdr.front_len = cpu_to_le32(msg_size); - return; -} - -/* - * build new request AND message, calculate layout, and adjust file - * extent as needed. - * - * if the file was recently truncated, we include information about its - * old and new size so that the object can be updated appropriately. (we - * avoid synchronously deleting truncated objects because it's slow.) - * - * if @do_sync, include a 'startsync' command so that the osd will flush - * data quickly. - */ -struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, - struct ceph_file_layout *layout, - struct ceph_vino vino, - u64 off, u64 *plen, - int opcode, int flags, - struct ceph_snap_context *snapc, - int do_sync, - u32 truncate_seq, - u64 truncate_size, - struct timespec *mtime, - bool use_mempool, int num_reply) -{ - struct ceph_osd_req_op ops[3]; - struct ceph_osd_request *req; - - ops[0].op = opcode; - ops[0].extent.truncate_seq = truncate_seq; - ops[0].extent.truncate_size = truncate_size; - ops[0].payload_len = 0; - - if (do_sync) { - ops[1].op = CEPH_OSD_OP_STARTSYNC; - ops[1].payload_len = 0; - ops[2].op = 0; - } else - ops[1].op = 0; - - req = ceph_osdc_alloc_request(osdc, flags, - snapc, ops, - use_mempool, - GFP_NOFS, NULL, NULL); - if (IS_ERR(req)) - return req; - - /* calculate max write size */ - calc_layout(osdc, vino, layout, off, plen, req, ops); - req->r_file_layout = *layout; /* keep a copy */ - - ceph_osdc_build_request(req, off, plen, ops, - snapc, - mtime, - req->r_oid, req->r_oid_len); - - return req; -} - -/* - * We keep osd requests in an rbtree, sorted by ->r_tid. - */ -static void __insert_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *new) -{ - struct rb_node **p = &osdc->requests.rb_node; - struct rb_node *parent = NULL; - struct ceph_osd_request *req = NULL; - - while (*p) { - parent = *p; - req = rb_entry(parent, struct ceph_osd_request, r_node); - if (new->r_tid < req->r_tid) - p = &(*p)->rb_left; - else if (new->r_tid > req->r_tid) - p = &(*p)->rb_right; - else - BUG(); - } - - rb_link_node(&new->r_node, parent, p); - rb_insert_color(&new->r_node, &osdc->requests); -} - -static struct ceph_osd_request *__lookup_request(struct ceph_osd_client *osdc, - u64 tid) -{ - struct ceph_osd_request *req; - struct rb_node *n = osdc->requests.rb_node; - - while (n) { - req = rb_entry(n, struct ceph_osd_request, r_node); - if (tid < req->r_tid) - n = n->rb_left; - else if (tid > req->r_tid) - n = n->rb_right; - else - return req; - } - return NULL; -} - -static struct ceph_osd_request * -__lookup_request_ge(struct ceph_osd_client *osdc, - u64 tid) -{ - struct ceph_osd_request *req; - struct rb_node *n = osdc->requests.rb_node; - - while (n) { - req = rb_entry(n, struct ceph_osd_request, r_node); - if (tid < req->r_tid) { - if (!n->rb_left) - return req; - n = n->rb_left; - } else if (tid > req->r_tid) { - n = n->rb_right; - } else { - return req; - } - } - return NULL; -} - - -/* - * If the osd connection drops, we need to resubmit all requests. - */ -static void osd_reset(struct ceph_connection *con) -{ - struct ceph_osd *osd = con->private; - struct ceph_osd_client *osdc; - - if (!osd) - return; - dout("osd_reset osd%d\n", osd->o_osd); - osdc = osd->o_osdc; - down_read(&osdc->map_sem); - kick_requests(osdc, osd); - up_read(&osdc->map_sem); -} - -/* - * Track open sessions with osds. - */ -static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) -{ - struct ceph_osd *osd; - - osd = kzalloc(sizeof(*osd), GFP_NOFS); - if (!osd) - return NULL; - - atomic_set(&osd->o_ref, 1); - osd->o_osdc = osdc; - INIT_LIST_HEAD(&osd->o_requests); - INIT_LIST_HEAD(&osd->o_osd_lru); - osd->o_incarnation = 1; - - ceph_con_init(osdc->client->msgr, &osd->o_con); - osd->o_con.private = osd; - osd->o_con.ops = &osd_con_ops; - osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; - - INIT_LIST_HEAD(&osd->o_keepalive_item); - return osd; -} - -static struct ceph_osd *get_osd(struct ceph_osd *osd) -{ - if (atomic_inc_not_zero(&osd->o_ref)) { - dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1, - atomic_read(&osd->o_ref)); - return osd; - } else { - dout("get_osd %p FAIL\n", osd); - return NULL; - } -} - -static void put_osd(struct ceph_osd *osd) -{ - dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), - atomic_read(&osd->o_ref) - 1); - if (atomic_dec_and_test(&osd->o_ref)) { - struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - - if (osd->o_authorizer) - ac->ops->destroy_authorizer(ac, osd->o_authorizer); - kfree(osd); - } -} - -/* - * remove an osd from our map - */ -static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) -{ - dout("__remove_osd %p\n", osd); - BUG_ON(!list_empty(&osd->o_requests)); - rb_erase(&osd->o_node, &osdc->osds); - list_del_init(&osd->o_osd_lru); - ceph_con_close(&osd->o_con); - put_osd(osd); -} - -static void __move_osd_to_lru(struct ceph_osd_client *osdc, - struct ceph_osd *osd) -{ - dout("__move_osd_to_lru %p\n", osd); - BUG_ON(!list_empty(&osd->o_osd_lru)); - list_add_tail(&osd->o_osd_lru, &osdc->osd_lru); - osd->lru_ttl = jiffies + osdc->client->mount_args->osd_idle_ttl * HZ; -} - -static void __remove_osd_from_lru(struct ceph_osd *osd) -{ - dout("__remove_osd_from_lru %p\n", osd); - if (!list_empty(&osd->o_osd_lru)) - list_del_init(&osd->o_osd_lru); -} - -static void remove_old_osds(struct ceph_osd_client *osdc, int remove_all) -{ - struct ceph_osd *osd, *nosd; - - dout("__remove_old_osds %p\n", osdc); - mutex_lock(&osdc->request_mutex); - list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { - if (!remove_all && time_before(jiffies, osd->lru_ttl)) - break; - __remove_osd(osdc, osd); - } - mutex_unlock(&osdc->request_mutex); -} - -/* - * reset osd connect - */ -static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) -{ - struct ceph_osd_request *req; - int ret = 0; - - dout("__reset_osd %p osd%d\n", osd, osd->o_osd); - if (list_empty(&osd->o_requests)) { - __remove_osd(osdc, osd); - } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], - &osd->o_con.peer_addr, - sizeof(osd->o_con.peer_addr)) == 0 && - !ceph_con_opened(&osd->o_con)) { - dout(" osd addr hasn't changed and connection never opened," - " letting msgr retry"); - /* touch each r_stamp for handle_timeout()'s benfit */ - list_for_each_entry(req, &osd->o_requests, r_osd_item) - req->r_stamp = jiffies; - ret = -EAGAIN; - } else { - ceph_con_close(&osd->o_con); - ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]); - osd->o_incarnation++; - } - return ret; -} - -static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new) -{ - struct rb_node **p = &osdc->osds.rb_node; - struct rb_node *parent = NULL; - struct ceph_osd *osd = NULL; - - while (*p) { - parent = *p; - osd = rb_entry(parent, struct ceph_osd, o_node); - if (new->o_osd < osd->o_osd) - p = &(*p)->rb_left; - else if (new->o_osd > osd->o_osd) - p = &(*p)->rb_right; - else - BUG(); - } - - rb_link_node(&new->o_node, parent, p); - rb_insert_color(&new->o_node, &osdc->osds); -} - -static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o) -{ - struct ceph_osd *osd; - struct rb_node *n = osdc->osds.rb_node; - - while (n) { - osd = rb_entry(n, struct ceph_osd, o_node); - if (o < osd->o_osd) - n = n->rb_left; - else if (o > osd->o_osd) - n = n->rb_right; - else - return osd; - } - return NULL; -} - -static void __schedule_osd_timeout(struct ceph_osd_client *osdc) -{ - schedule_delayed_work(&osdc->timeout_work, - osdc->client->mount_args->osd_keepalive_timeout * HZ); -} - -static void __cancel_osd_timeout(struct ceph_osd_client *osdc) -{ - cancel_delayed_work(&osdc->timeout_work); -} - -/* - * Register request, assign tid. If this is the first request, set up - * the timeout event. - */ -static void register_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) -{ - mutex_lock(&osdc->request_mutex); - req->r_tid = ++osdc->last_tid; - req->r_request->hdr.tid = cpu_to_le64(req->r_tid); - INIT_LIST_HEAD(&req->r_req_lru_item); - - dout("register_request %p tid %lld\n", req, req->r_tid); - __insert_request(osdc, req); - ceph_osdc_get_request(req); - osdc->num_requests++; - - if (osdc->num_requests == 1) { - dout(" first request, scheduling timeout\n"); - __schedule_osd_timeout(osdc); - } - mutex_unlock(&osdc->request_mutex); -} - -/* - * called under osdc->request_mutex - */ -static void __unregister_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) -{ - dout("__unregister_request %p tid %lld\n", req, req->r_tid); - rb_erase(&req->r_node, &osdc->requests); - osdc->num_requests--; - - if (req->r_osd) { - /* make sure the original request isn't in flight. */ - ceph_con_revoke(&req->r_osd->o_con, req->r_request); - - list_del_init(&req->r_osd_item); - if (list_empty(&req->r_osd->o_requests)) - __move_osd_to_lru(osdc, req->r_osd); - req->r_osd = NULL; - } - - ceph_osdc_put_request(req); - - list_del_init(&req->r_req_lru_item); - if (osdc->num_requests == 0) { - dout(" no requests, canceling timeout\n"); - __cancel_osd_timeout(osdc); - } -} - -/* - * Cancel a previously queued request message - */ -static void __cancel_request(struct ceph_osd_request *req) -{ - if (req->r_sent && req->r_osd) { - ceph_con_revoke(&req->r_osd->o_con, req->r_request); - req->r_sent = 0; - } - list_del_init(&req->r_req_lru_item); -} - -/* - * Pick an osd (the first 'up' osd in the pg), allocate the osd struct - * (as needed), and set the request r_osd appropriately. If there is - * no up osd, set r_osd to NULL. - * - * Return 0 if unchanged, 1 if changed, or negative on error. - * - * Caller should hold map_sem for read and request_mutex. - */ -static int __map_osds(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) -{ - struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; - struct ceph_pg pgid; - int acting[CEPH_PG_MAX_SIZE]; - int o = -1, num = 0; - int err; - - dout("map_osds %p tid %lld\n", req, req->r_tid); - err = ceph_calc_object_layout(&reqhead->layout, req->r_oid, - &req->r_file_layout, osdc->osdmap); - if (err) - return err; - pgid = reqhead->layout.ol_pgid; - req->r_pgid = pgid; - - err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting); - if (err > 0) { - o = acting[0]; - num = err; - } - - if ((req->r_osd && req->r_osd->o_osd == o && - req->r_sent >= req->r_osd->o_incarnation && - req->r_num_pg_osds == num && - memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || - (req->r_osd == NULL && o == -1)) - return 0; /* no change */ - - dout("map_osds tid %llu pgid %d.%x osd%d (was osd%d)\n", - req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o, - req->r_osd ? req->r_osd->o_osd : -1); - - /* record full pg acting set */ - memcpy(req->r_pg_osds, acting, sizeof(acting[0]) * num); - req->r_num_pg_osds = num; - - if (req->r_osd) { - __cancel_request(req); - list_del_init(&req->r_osd_item); - req->r_osd = NULL; - } - - req->r_osd = __lookup_osd(osdc, o); - if (!req->r_osd && o >= 0) { - err = -ENOMEM; - req->r_osd = create_osd(osdc); - if (!req->r_osd) - goto out; - - dout("map_osds osd %p is osd%d\n", req->r_osd, o); - req->r_osd->o_osd = o; - req->r_osd->o_con.peer_name.num = cpu_to_le64(o); - __insert_osd(osdc, req->r_osd); - - ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]); - } - - if (req->r_osd) { - __remove_osd_from_lru(req->r_osd); - list_add(&req->r_osd_item, &req->r_osd->o_requests); - } - err = 1; /* osd or pg changed */ - -out: - return err; -} - -/* - * caller should hold map_sem (for read) and request_mutex - */ -static int __send_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) -{ - struct ceph_osd_request_head *reqhead; - int err; - - err = __map_osds(osdc, req); - if (err < 0) - return err; - if (req->r_osd == NULL) { - dout("send_request %p no up osds in pg\n", req); - ceph_monc_request_next_osdmap(&osdc->client->monc); - return 0; - } - - dout("send_request %p tid %llu to osd%d flags %d\n", - req, req->r_tid, req->r_osd->o_osd, req->r_flags); - - reqhead = req->r_request->front.iov_base; - reqhead->osdmap_epoch = cpu_to_le32(osdc->osdmap->epoch); - reqhead->flags |= cpu_to_le32(req->r_flags); /* e.g., RETRY */ - reqhead->reassert_version = req->r_reassert_version; - - req->r_stamp = jiffies; - list_move_tail(&req->r_req_lru_item, &osdc->req_lru); - - ceph_msg_get(req->r_request); /* send consumes a ref */ - ceph_con_send(&req->r_osd->o_con, req->r_request); - req->r_sent = req->r_osd->o_incarnation; - return 0; -} - -/* - * Timeout callback, called every N seconds when 1 or more osd - * requests has been active for more than N seconds. When this - * happens, we ping all OSDs with requests who have timed out to - * ensure any communications channel reset is detected. Reset the - * request timeouts another N seconds in the future as we go. - * Reschedule the timeout event another N seconds in future (unless - * there are no open requests). - */ -static void handle_timeout(struct work_struct *work) -{ - struct ceph_osd_client *osdc = - container_of(work, struct ceph_osd_client, timeout_work.work); - struct ceph_osd_request *req, *last_req = NULL; - struct ceph_osd *osd; - unsigned long timeout = osdc->client->mount_args->osd_timeout * HZ; - unsigned long keepalive = - osdc->client->mount_args->osd_keepalive_timeout * HZ; - unsigned long last_stamp = 0; - struct rb_node *p; - struct list_head slow_osds; - - dout("timeout\n"); - down_read(&osdc->map_sem); - - ceph_monc_request_next_osdmap(&osdc->client->monc); - - mutex_lock(&osdc->request_mutex); - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { - req = rb_entry(p, struct ceph_osd_request, r_node); - - if (req->r_resend) { - int err; - - dout("osdc resending prev failed %lld\n", req->r_tid); - err = __send_request(osdc, req); - if (err) - dout("osdc failed again on %lld\n", req->r_tid); - else - req->r_resend = false; - continue; - } - } - - /* - * reset osds that appear to be _really_ unresponsive. this - * is a failsafe measure.. we really shouldn't be getting to - * this point if the system is working properly. the monitors - * should mark the osd as failed and we should find out about - * it from an updated osd map. - */ - while (timeout && !list_empty(&osdc->req_lru)) { - req = list_entry(osdc->req_lru.next, struct ceph_osd_request, - r_req_lru_item); - - if (time_before(jiffies, req->r_stamp + timeout)) - break; - - BUG_ON(req == last_req && req->r_stamp == last_stamp); - last_req = req; - last_stamp = req->r_stamp; - - osd = req->r_osd; - BUG_ON(!osd); - pr_warning(" tid %llu timed out on osd%d, will reset osd\n", - req->r_tid, osd->o_osd); - __kick_requests(osdc, osd); - } - - /* - * ping osds that are a bit slow. this ensures that if there - * is a break in the TCP connection we will notice, and reopen - * a connection with that osd (from the fault callback). - */ - INIT_LIST_HEAD(&slow_osds); - list_for_each_entry(req, &osdc->req_lru, r_req_lru_item) { - if (time_before(jiffies, req->r_stamp + keepalive)) - break; - - osd = req->r_osd; - BUG_ON(!osd); - dout(" tid %llu is slow, will send keepalive on osd%d\n", - req->r_tid, osd->o_osd); - list_move_tail(&osd->o_keepalive_item, &slow_osds); - } - while (!list_empty(&slow_osds)) { - osd = list_entry(slow_osds.next, struct ceph_osd, - o_keepalive_item); - list_del_init(&osd->o_keepalive_item); - ceph_con_keepalive(&osd->o_con); - } - - __schedule_osd_timeout(osdc); - mutex_unlock(&osdc->request_mutex); - - up_read(&osdc->map_sem); -} - -static void handle_osds_timeout(struct work_struct *work) -{ - struct ceph_osd_client *osdc = - container_of(work, struct ceph_osd_client, - osds_timeout_work.work); - unsigned long delay = - osdc->client->mount_args->osd_idle_ttl * HZ >> 2; - - dout("osds timeout\n"); - down_read(&osdc->map_sem); - remove_old_osds(osdc, 0); - up_read(&osdc->map_sem); - - schedule_delayed_work(&osdc->osds_timeout_work, - round_jiffies_relative(delay)); -} - -/* - * handle osd op reply. either call the callback if it is specified, - * or do the completion to wake up the waiting thread. - */ -static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, - struct ceph_connection *con) -{ - struct ceph_osd_reply_head *rhead = msg->front.iov_base; - struct ceph_osd_request *req; - u64 tid; - int numops, object_len, flags; - s32 result; - - tid = le64_to_cpu(msg->hdr.tid); - if (msg->front.iov_len < sizeof(*rhead)) - goto bad; - numops = le32_to_cpu(rhead->num_ops); - object_len = le32_to_cpu(rhead->object_len); - result = le32_to_cpu(rhead->result); - if (msg->front.iov_len != sizeof(*rhead) + object_len + - numops * sizeof(struct ceph_osd_op)) - goto bad; - dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result); - - /* lookup */ - mutex_lock(&osdc->request_mutex); - req = __lookup_request(osdc, tid); - if (req == NULL) { - dout("handle_reply tid %llu dne\n", tid); - mutex_unlock(&osdc->request_mutex); - return; - } - ceph_osdc_get_request(req); - flags = le32_to_cpu(rhead->flags); - - /* - * if this connection filled our message, drop our reference now, to - * avoid a (safe but slower) revoke later. - */ - if (req->r_con_filling_msg == con && req->r_reply == msg) { - dout(" dropping con_filling_msg ref %p\n", con); - req->r_con_filling_msg = NULL; - ceph_con_put(con); - } - - if (!req->r_got_reply) { - unsigned bytes; - - req->r_result = le32_to_cpu(rhead->result); - bytes = le32_to_cpu(msg->hdr.data_len); - dout("handle_reply result %d bytes %d\n", req->r_result, - bytes); - if (req->r_result == 0) - req->r_result = bytes; - - /* in case this is a write and we need to replay, */ - req->r_reassert_version = rhead->reassert_version; - - req->r_got_reply = 1; - } else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) { - dout("handle_reply tid %llu dup ack\n", tid); - mutex_unlock(&osdc->request_mutex); - goto done; - } - - dout("handle_reply tid %llu flags %d\n", tid, flags); - - /* either this is a read, or we got the safe response */ - if (result < 0 || - (flags & CEPH_OSD_FLAG_ONDISK) || - ((flags & CEPH_OSD_FLAG_WRITE) == 0)) - __unregister_request(osdc, req); - - mutex_unlock(&osdc->request_mutex); - - if (req->r_callback) - req->r_callback(req, msg); - else - complete_all(&req->r_completion); - - if (flags & CEPH_OSD_FLAG_ONDISK) { - if (req->r_safe_callback) - req->r_safe_callback(req, msg); - complete_all(&req->r_safe_completion); /* fsync waiter */ - } - -done: - ceph_osdc_put_request(req); - return; - -bad: - pr_err("corrupt osd_op_reply got %d %d expected %d\n", - (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len), - (int)sizeof(*rhead)); - ceph_msg_dump(msg); -} - - -static int __kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) -{ - struct ceph_osd_request *req; - struct rb_node *p, *n; - int needmap = 0; - int err; - - dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1); - if (kickosd) { - err = __reset_osd(osdc, kickosd); - if (err == -EAGAIN) - return 1; - } else { - for (p = rb_first(&osdc->osds); p; p = n) { - struct ceph_osd *osd = - rb_entry(p, struct ceph_osd, o_node); - - n = rb_next(p); - if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || - memcmp(&osd->o_con.peer_addr, - ceph_osd_addr(osdc->osdmap, - osd->o_osd), - sizeof(struct ceph_entity_addr)) != 0) - __reset_osd(osdc, osd); - } - } - - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { - req = rb_entry(p, struct ceph_osd_request, r_node); - - if (req->r_resend) { - dout(" r_resend set on tid %llu\n", req->r_tid); - __cancel_request(req); - goto kick; - } - if (req->r_osd && kickosd == req->r_osd) { - __cancel_request(req); - goto kick; - } - - err = __map_osds(osdc, req); - if (err == 0) - continue; /* no change */ - if (err < 0) { - /* - * FIXME: really, we should set the request - * error and fail if this isn't a 'nofail' - * request, but that's a fair bit more - * complicated to do. So retry! - */ - dout(" setting r_resend on %llu\n", req->r_tid); - req->r_resend = true; - continue; - } - if (req->r_osd == NULL) { - dout("tid %llu maps to no valid osd\n", req->r_tid); - needmap++; /* request a newer map */ - continue; - } - -kick: - dout("kicking %p tid %llu osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - req->r_flags |= CEPH_OSD_FLAG_RETRY; - err = __send_request(osdc, req); - if (err) { - dout(" setting r_resend on %llu\n", req->r_tid); - req->r_resend = true; - } - } - - return needmap; -} - -/* - * Resubmit osd requests whose osd or osd address has changed. Request - * a new osd map if osds are down, or we are otherwise unable to determine - * how to direct a request. - * - * Close connections to down osds. - * - * If @who is specified, resubmit requests for that specific osd. - * - * Caller should hold map_sem for read and request_mutex. - */ -static void kick_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) -{ - int needmap; - - mutex_lock(&osdc->request_mutex); - needmap = __kick_requests(osdc, kickosd); - mutex_unlock(&osdc->request_mutex); - - if (needmap) { - dout("%d requests for down osds, need new map\n", needmap); - ceph_monc_request_next_osdmap(&osdc->client->monc); - } - -} -/* - * Process updated osd map. - * - * The message contains any number of incremental and full maps, normally - * indicating some sort of topology change in the cluster. Kick requests - * off to different OSDs as needed. - */ -void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) -{ - void *p, *end, *next; - u32 nr_maps, maplen; - u32 epoch; - struct ceph_osdmap *newmap = NULL, *oldmap; - int err; - struct ceph_fsid fsid; - - dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0); - p = msg->front.iov_base; - end = p + msg->front.iov_len; - - /* verify fsid */ - ceph_decode_need(&p, end, sizeof(fsid), bad); - ceph_decode_copy(&p, &fsid, sizeof(fsid)); - if (ceph_check_fsid(osdc->client, &fsid) < 0) - return; - - down_write(&osdc->map_sem); - - /* incremental maps */ - ceph_decode_32_safe(&p, end, nr_maps, bad); - dout(" %d inc maps\n", nr_maps); - while (nr_maps > 0) { - ceph_decode_need(&p, end, 2*sizeof(u32), bad); - epoch = ceph_decode_32(&p); - maplen = ceph_decode_32(&p); - ceph_decode_need(&p, end, maplen, bad); - next = p + maplen; - if (osdc->osdmap && osdc->osdmap->epoch+1 == epoch) { - dout("applying incremental map %u len %d\n", - epoch, maplen); - newmap = osdmap_apply_incremental(&p, next, - osdc->osdmap, - osdc->client->msgr); - if (IS_ERR(newmap)) { - err = PTR_ERR(newmap); - goto bad; - } - BUG_ON(!newmap); - if (newmap != osdc->osdmap) { - ceph_osdmap_destroy(osdc->osdmap); - osdc->osdmap = newmap; - } - } else { - dout("ignoring incremental map %u len %d\n", - epoch, maplen); - } - p = next; - nr_maps--; - } - if (newmap) - goto done; - - /* full maps */ - ceph_decode_32_safe(&p, end, nr_maps, bad); - dout(" %d full maps\n", nr_maps); - while (nr_maps) { - ceph_decode_need(&p, end, 2*sizeof(u32), bad); - epoch = ceph_decode_32(&p); - maplen = ceph_decode_32(&p); - ceph_decode_need(&p, end, maplen, bad); - if (nr_maps > 1) { - dout("skipping non-latest full map %u len %d\n", - epoch, maplen); - } else if (osdc->osdmap && osdc->osdmap->epoch >= epoch) { - dout("skipping full map %u len %d, " - "older than our %u\n", epoch, maplen, - osdc->osdmap->epoch); - } else { - dout("taking full map %u len %d\n", epoch, maplen); - newmap = osdmap_decode(&p, p+maplen); - if (IS_ERR(newmap)) { - err = PTR_ERR(newmap); - goto bad; - } - BUG_ON(!newmap); - oldmap = osdc->osdmap; - osdc->osdmap = newmap; - if (oldmap) - ceph_osdmap_destroy(oldmap); - } - p += maplen; - nr_maps--; - } - -done: - downgrade_write(&osdc->map_sem); - ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); - if (newmap) - kick_requests(osdc, NULL); - up_read(&osdc->map_sem); - wake_up_all(&osdc->client->auth_wq); - return; - -bad: - pr_err("osdc handle_map corrupt msg\n"); - ceph_msg_dump(msg); - up_write(&osdc->map_sem); - return; -} - -/* - * Register request, send initial attempt. - */ -int ceph_osdc_start_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req, - bool nofail) -{ - int rc = 0; - - req->r_request->pages = req->r_pages; - req->r_request->nr_pages = req->r_num_pages; -#ifdef CONFIG_BLOCK - req->r_request->bio = req->r_bio; -#endif - req->r_request->trail = req->r_trail; - - register_request(osdc, req); - - down_read(&osdc->map_sem); - mutex_lock(&osdc->request_mutex); - /* - * a racing kick_requests() may have sent the message for us - * while we dropped request_mutex above, so only send now if - * the request still han't been touched yet. - */ - if (req->r_sent == 0) { - rc = __send_request(osdc, req); - if (rc) { - if (nofail) { - dout("osdc_start_request failed send, " - " marking %lld\n", req->r_tid); - req->r_resend = true; - rc = 0; - } else { - __unregister_request(osdc, req); - } - } - } - mutex_unlock(&osdc->request_mutex); - up_read(&osdc->map_sem); - return rc; -} - -/* - * wait for a request to complete - */ -int ceph_osdc_wait_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req) -{ - int rc; - - rc = wait_for_completion_interruptible(&req->r_completion); - if (rc < 0) { - mutex_lock(&osdc->request_mutex); - __cancel_request(req); - __unregister_request(osdc, req); - mutex_unlock(&osdc->request_mutex); - dout("wait_request tid %llu canceled/timed out\n", req->r_tid); - return rc; - } - - dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result); - return req->r_result; -} - -/* - * sync - wait for all in-flight requests to flush. avoid starvation. - */ -void ceph_osdc_sync(struct ceph_osd_client *osdc) -{ - struct ceph_osd_request *req; - u64 last_tid, next_tid = 0; - - mutex_lock(&osdc->request_mutex); - last_tid = osdc->last_tid; - while (1) { - req = __lookup_request_ge(osdc, next_tid); - if (!req) - break; - if (req->r_tid > last_tid) - break; - - next_tid = req->r_tid + 1; - if ((req->r_flags & CEPH_OSD_FLAG_WRITE) == 0) - continue; - - ceph_osdc_get_request(req); - mutex_unlock(&osdc->request_mutex); - dout("sync waiting on tid %llu (last is %llu)\n", - req->r_tid, last_tid); - wait_for_completion(&req->r_safe_completion); - mutex_lock(&osdc->request_mutex); - ceph_osdc_put_request(req); - } - mutex_unlock(&osdc->request_mutex); - dout("sync done (thru tid %llu)\n", last_tid); -} - -/* - * init, shutdown - */ -int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) -{ - int err; - - dout("init\n"); - osdc->client = client; - osdc->osdmap = NULL; - init_rwsem(&osdc->map_sem); - init_completion(&osdc->map_waiters); - osdc->last_requested_map = 0; - mutex_init(&osdc->request_mutex); - osdc->last_tid = 0; - osdc->osds = RB_ROOT; - INIT_LIST_HEAD(&osdc->osd_lru); - osdc->requests = RB_ROOT; - INIT_LIST_HEAD(&osdc->req_lru); - osdc->num_requests = 0; - INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); - INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); - - schedule_delayed_work(&osdc->osds_timeout_work, - round_jiffies_relative(osdc->client->mount_args->osd_idle_ttl * HZ)); - - err = -ENOMEM; - osdc->req_mempool = mempool_create_kmalloc_pool(10, - sizeof(struct ceph_osd_request)); - if (!osdc->req_mempool) - goto out; - - err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true, - "osd_op"); - if (err < 0) - goto out_mempool; - err = ceph_msgpool_init(&osdc->msgpool_op_reply, - OSD_OPREPLY_FRONT_LEN, 10, true, - "osd_op_reply"); - if (err < 0) - goto out_msgpool; - return 0; - -out_msgpool: - ceph_msgpool_destroy(&osdc->msgpool_op); -out_mempool: - mempool_destroy(osdc->req_mempool); -out: - return err; -} - -void ceph_osdc_stop(struct ceph_osd_client *osdc) -{ - cancel_delayed_work_sync(&osdc->timeout_work); - cancel_delayed_work_sync(&osdc->osds_timeout_work); - if (osdc->osdmap) { - ceph_osdmap_destroy(osdc->osdmap); - osdc->osdmap = NULL; - } - remove_old_osds(osdc, 1); - mempool_destroy(osdc->req_mempool); - ceph_msgpool_destroy(&osdc->msgpool_op); - ceph_msgpool_destroy(&osdc->msgpool_op_reply); -} - -/* - * Read some contiguous pages. If we cross a stripe boundary, shorten - * *plen. Return number of bytes read, or error. - */ -int ceph_osdc_readpages(struct ceph_osd_client *osdc, - struct ceph_vino vino, struct ceph_file_layout *layout, - u64 off, u64 *plen, - u32 truncate_seq, u64 truncate_size, - struct page **pages, int num_pages) -{ - struct ceph_osd_request *req; - int rc = 0; - - dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino, - vino.snap, off, *plen); - req = ceph_osdc_new_request(osdc, layout, vino, off, plen, - CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, - NULL, 0, truncate_seq, truncate_size, NULL, - false, 1); - if (!req) - return -ENOMEM; - - /* it may be a short read due to an object boundary */ - req->r_pages = pages; - - dout("readpages final extent is %llu~%llu (%d pages)\n", - off, *plen, req->r_num_pages); - - rc = ceph_osdc_start_request(osdc, req, false); - if (!rc) - rc = ceph_osdc_wait_request(osdc, req); - - ceph_osdc_put_request(req); - dout("readpages result %d\n", rc); - return rc; -} - -/* - * do a synchronous write on N pages - */ -int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, - struct ceph_file_layout *layout, - struct ceph_snap_context *snapc, - u64 off, u64 len, - u32 truncate_seq, u64 truncate_size, - struct timespec *mtime, - struct page **pages, int num_pages, - int flags, int do_sync, bool nofail) -{ - struct ceph_osd_request *req; - int rc = 0; - - BUG_ON(vino.snap != CEPH_NOSNAP); - req = ceph_osdc_new_request(osdc, layout, vino, off, &len, - CEPH_OSD_OP_WRITE, - flags | CEPH_OSD_FLAG_ONDISK | - CEPH_OSD_FLAG_WRITE, - snapc, do_sync, - truncate_seq, truncate_size, mtime, - nofail, 1); - if (!req) - return -ENOMEM; - - /* it may be a short write due to an object boundary */ - req->r_pages = pages; - dout("writepages %llu~%llu (%d pages)\n", off, len, - req->r_num_pages); - - rc = ceph_osdc_start_request(osdc, req, nofail); - if (!rc) - rc = ceph_osdc_wait_request(osdc, req); - - ceph_osdc_put_request(req); - if (rc == 0) - rc = len; - dout("writepages result %d\n", rc); - return rc; -} - -/* - * handle incoming message - */ -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) -{ - struct ceph_osd *osd = con->private; - struct ceph_osd_client *osdc; - int type = le16_to_cpu(msg->hdr.type); - - if (!osd) - goto out; - osdc = osd->o_osdc; - - switch (type) { - case CEPH_MSG_OSD_MAP: - ceph_osdc_handle_map(osdc, msg); - break; - case CEPH_MSG_OSD_OPREPLY: - handle_reply(osdc, msg, con); - break; - - default: - pr_err("received unknown message type %d %s\n", type, - ceph_msg_type_name(type)); - } -out: - ceph_msg_put(msg); -} - -/* - * lookup and return message for incoming reply. set up reply message - * pages. - */ -static struct ceph_msg *get_reply(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) -{ - struct ceph_osd *osd = con->private; - struct ceph_osd_client *osdc = osd->o_osdc; - struct ceph_msg *m; - struct ceph_osd_request *req; - int front = le32_to_cpu(hdr->front_len); - int data_len = le32_to_cpu(hdr->data_len); - u64 tid; - - tid = le64_to_cpu(hdr->tid); - mutex_lock(&osdc->request_mutex); - req = __lookup_request(osdc, tid); - if (!req) { - *skip = 1; - m = NULL; - pr_info("get_reply unknown tid %llu from osd%d\n", tid, - osd->o_osd); - goto out; - } - - if (req->r_con_filling_msg) { - dout("get_reply revoking msg %p from old con %p\n", - req->r_reply, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); - ceph_con_put(req->r_con_filling_msg); - req->r_con_filling_msg = NULL; - } - - if (front > req->r_reply->front.iov_len) { - pr_warning("get_reply front %d > preallocated %d\n", - front, (int)req->r_reply->front.iov_len); - m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS); - if (!m) - goto out; - ceph_msg_put(req->r_reply); - req->r_reply = m; - } - m = ceph_msg_get(req->r_reply); - - if (data_len > 0) { - unsigned data_off = le16_to_cpu(hdr->data_off); - int want = calc_pages_for(data_off & ~PAGE_MASK, data_len); - - if (unlikely(req->r_num_pages < want)) { - pr_warning("tid %lld reply %d > expected %d pages\n", - tid, want, m->nr_pages); - *skip = 1; - ceph_msg_put(m); - m = NULL; - goto out; - } - m->pages = req->r_pages; - m->nr_pages = req->r_num_pages; -#ifdef CONFIG_BLOCK - m->bio = req->r_bio; -#endif - } - *skip = 0; - req->r_con_filling_msg = ceph_con_get(con); - dout("get_reply tid %lld %p\n", tid, m); - -out: - mutex_unlock(&osdc->request_mutex); - return m; - -} - -static struct ceph_msg *alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) -{ - struct ceph_osd *osd = con->private; - int type = le16_to_cpu(hdr->type); - int front = le32_to_cpu(hdr->front_len); - - switch (type) { - case CEPH_MSG_OSD_MAP: - return ceph_msg_new(type, front, GFP_NOFS); - case CEPH_MSG_OSD_OPREPLY: - return get_reply(con, hdr, skip); - default: - pr_info("alloc_msg unexpected msg type %d from osd%d\n", type, - osd->o_osd); - *skip = 1; - return NULL; - } -} - -/* - * Wrappers to refcount containing ceph_osd struct - */ -static struct ceph_connection *get_osd_con(struct ceph_connection *con) -{ - struct ceph_osd *osd = con->private; - if (get_osd(osd)) - return con; - return NULL; -} - -static void put_osd_con(struct ceph_connection *con) -{ - struct ceph_osd *osd = con->private; - put_osd(osd); -} - -/* - * authentication - */ -static int get_authorizer(struct ceph_connection *con, - void **buf, int *len, int *proto, - void **reply_buf, int *reply_len, int force_new) -{ - struct ceph_osd *o = con->private; - struct ceph_osd_client *osdc = o->o_osdc; - struct ceph_auth_client *ac = osdc->client->monc.auth; - int ret = 0; - - if (force_new && o->o_authorizer) { - ac->ops->destroy_authorizer(ac, o->o_authorizer); - o->o_authorizer = NULL; - } - if (o->o_authorizer == NULL) { - ret = ac->ops->create_authorizer( - ac, CEPH_ENTITY_TYPE_OSD, - &o->o_authorizer, - &o->o_authorizer_buf, - &o->o_authorizer_buf_len, - &o->o_authorizer_reply_buf, - &o->o_authorizer_reply_buf_len); - if (ret) - return ret; - } - - *proto = ac->protocol; - *buf = o->o_authorizer_buf; - *len = o->o_authorizer_buf_len; - *reply_buf = o->o_authorizer_reply_buf; - *reply_len = o->o_authorizer_reply_buf_len; - return 0; -} - - -static int verify_authorizer_reply(struct ceph_connection *con, int len) -{ - struct ceph_osd *o = con->private; - struct ceph_osd_client *osdc = o->o_osdc; - struct ceph_auth_client *ac = osdc->client->monc.auth; - - return ac->ops->verify_authorizer_reply(ac, o->o_authorizer, len); -} - -static int invalidate_authorizer(struct ceph_connection *con) -{ - struct ceph_osd *o = con->private; - struct ceph_osd_client *osdc = o->o_osdc; - struct ceph_auth_client *ac = osdc->client->monc.auth; - - if (ac->ops->invalidate_authorizer) - ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); - - return ceph_monc_validate_auth(&osdc->client->monc); -} - -static const struct ceph_connection_operations osd_con_ops = { - .get = get_osd_con, - .put = put_osd_con, - .dispatch = dispatch, - .get_authorizer = get_authorizer, - .verify_authorizer_reply = verify_authorizer_reply, - .invalidate_authorizer = invalidate_authorizer, - .alloc_msg = alloc_msg, - .fault = osd_reset, -}; diff --git a/fs/ceph/osd_client.h b/fs/ceph/osd_client.h deleted file mode 100644 index 65c9c560f1ac..000000000000 --- a/fs/ceph/osd_client.h +++ /dev/null @@ -1,233 +0,0 @@ -#ifndef _FS_CEPH_OSD_CLIENT_H -#define _FS_CEPH_OSD_CLIENT_H - -#include -#include -#include -#include - -#include "types.h" -#include "osdmap.h" -#include "messenger.h" - -struct ceph_msg; -struct ceph_snap_context; -struct ceph_osd_request; -struct ceph_osd_client; -struct ceph_authorizer; -struct ceph_pagelist; - -/* - * completion callback for async writepages - */ -typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *, - struct ceph_msg *); - -/* a given osd we're communicating with */ -struct ceph_osd { - atomic_t o_ref; - struct ceph_osd_client *o_osdc; - int o_osd; - int o_incarnation; - struct rb_node o_node; - struct ceph_connection o_con; - struct list_head o_requests; - struct list_head o_osd_lru; - struct ceph_authorizer *o_authorizer; - void *o_authorizer_buf, *o_authorizer_reply_buf; - size_t o_authorizer_buf_len, o_authorizer_reply_buf_len; - unsigned long lru_ttl; - int o_marked_for_keepalive; - struct list_head o_keepalive_item; -}; - -/* an in-flight request */ -struct ceph_osd_request { - u64 r_tid; /* unique for this client */ - struct rb_node r_node; - struct list_head r_req_lru_item; - struct list_head r_osd_item; - struct ceph_osd *r_osd; - struct ceph_pg r_pgid; - int r_pg_osds[CEPH_PG_MAX_SIZE]; - int r_num_pg_osds; - - struct ceph_connection *r_con_filling_msg; - - struct ceph_msg *r_request, *r_reply; - int r_result; - int r_flags; /* any additional flags for the osd */ - u32 r_sent; /* >0 if r_request is sending/sent */ - int r_got_reply; - - struct ceph_osd_client *r_osdc; - struct kref r_kref; - bool r_mempool; - struct completion r_completion, r_safe_completion; - ceph_osdc_callback_t r_callback, r_safe_callback; - struct ceph_eversion r_reassert_version; - struct list_head r_unsafe_item; - - struct inode *r_inode; /* for use by callbacks */ - - char r_oid[40]; /* object name */ - int r_oid_len; - unsigned long r_stamp; /* send OR check time */ - bool r_resend; /* msg send failed, needs retry */ - - struct ceph_file_layout r_file_layout; - struct ceph_snap_context *r_snapc; /* snap context for writes */ - unsigned r_num_pages; /* size of page array (follows) */ - struct page **r_pages; /* pages for data payload */ - int r_pages_from_pool; - int r_own_pages; /* if true, i own page list */ -#ifdef CONFIG_BLOCK - struct bio *r_bio; /* instead of pages */ -#endif - - struct ceph_pagelist *r_trail; /* trailing part of the data */ -}; - -struct ceph_osd_client { - struct ceph_client *client; - - struct ceph_osdmap *osdmap; /* current map */ - struct rw_semaphore map_sem; - struct completion map_waiters; - u64 last_requested_map; - - struct mutex request_mutex; - struct rb_root osds; /* osds */ - struct list_head osd_lru; /* idle osds */ - u64 timeout_tid; /* tid of timeout triggering rq */ - u64 last_tid; /* tid of last request */ - struct rb_root requests; /* pending requests */ - struct list_head req_lru; /* pending requests lru */ - int num_requests; - struct delayed_work timeout_work; - struct delayed_work osds_timeout_work; -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs_file; -#endif - - mempool_t *req_mempool; - - struct ceph_msgpool msgpool_op; - struct ceph_msgpool msgpool_op_reply; -}; - -struct ceph_osd_req_op { - u16 op; /* CEPH_OSD_OP_* */ - u32 flags; /* CEPH_OSD_FLAG_* */ - union { - struct { - u64 offset, length; - u64 truncate_size; - u32 truncate_seq; - } extent; - struct { - const char *name; - u32 name_len; - const char *val; - u32 value_len; - __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ - __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ - } xattr; - struct { - const char *class_name; - __u8 class_len; - const char *method_name; - __u8 method_len; - __u8 argc; - const char *indata; - u32 indata_len; - } cls; - struct { - u64 cookie, count; - } pgls; - struct { - u64 snapid; - } snap; - }; - u32 payload_len; -}; - -extern int ceph_osdc_init(struct ceph_osd_client *osdc, - struct ceph_client *client); -extern void ceph_osdc_stop(struct ceph_osd_client *osdc); - -extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, - struct ceph_msg *msg); -extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, - struct ceph_msg *msg); - -extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc, - struct ceph_file_layout *layout, - u64 snapid, - u64 off, u64 *plen, u64 *bno, - struct ceph_osd_request *req, - struct ceph_osd_req_op *op); - -extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, - int flags, - struct ceph_snap_context *snapc, - struct ceph_osd_req_op *ops, - bool use_mempool, - gfp_t gfp_flags, - struct page **pages, - struct bio *bio); - -extern void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 *plen, - struct ceph_osd_req_op *src_ops, - struct ceph_snap_context *snapc, - struct timespec *mtime, - const char *oid, - int oid_len); - -extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, - struct ceph_file_layout *layout, - struct ceph_vino vino, - u64 offset, u64 *len, int op, int flags, - struct ceph_snap_context *snapc, - int do_sync, u32 truncate_seq, - u64 truncate_size, - struct timespec *mtime, - bool use_mempool, int num_reply); - -static inline void ceph_osdc_get_request(struct ceph_osd_request *req) -{ - kref_get(&req->r_kref); -} -extern void ceph_osdc_release_request(struct kref *kref); -static inline void ceph_osdc_put_request(struct ceph_osd_request *req) -{ - kref_put(&req->r_kref, ceph_osdc_release_request); -} - -extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req, - bool nofail); -extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req); -extern void ceph_osdc_sync(struct ceph_osd_client *osdc); - -extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, - struct ceph_vino vino, - struct ceph_file_layout *layout, - u64 off, u64 *plen, - u32 truncate_seq, u64 truncate_size, - struct page **pages, int nr_pages); - -extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, - struct ceph_vino vino, - struct ceph_file_layout *layout, - struct ceph_snap_context *sc, - u64 off, u64 len, - u32 truncate_seq, u64 truncate_size, - struct timespec *mtime, - struct page **pages, int nr_pages, - int flags, int do_sync, bool nofail); - -#endif - diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c deleted file mode 100644 index 3ccd11761cb6..000000000000 --- a/fs/ceph/osdmap.c +++ /dev/null @@ -1,1123 +0,0 @@ - -#include "ceph_debug.h" - -#include -#include - -#include "super.h" -#include "osdmap.h" -#include "crush/hash.h" -#include "crush/mapper.h" -#include "decode.h" - -char *ceph_osdmap_state_str(char *str, int len, int state) -{ - int flag = 0; - - if (!len) - goto done; - - *str = '\0'; - if (state) { - if (state & CEPH_OSD_EXISTS) { - snprintf(str, len, "exists"); - flag = 1; - } - if (state & CEPH_OSD_UP) { - snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""), - "up"); - flag = 1; - } - } else { - snprintf(str, len, "doesn't exist"); - } -done: - return str; -} - -/* maps */ - -static int calc_bits_of(unsigned t) -{ - int b = 0; - while (t) { - t = t >> 1; - b++; - } - return b; -} - -/* - * the foo_mask is the smallest value 2^n-1 that is >= foo. - */ -static void calc_pg_masks(struct ceph_pg_pool_info *pi) -{ - pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1; - pi->pgp_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1; - pi->lpg_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1; - pi->lpgp_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1; -} - -/* - * decode crush map - */ -static int crush_decode_uniform_bucket(void **p, void *end, - struct crush_bucket_uniform *b) -{ - dout("crush_decode_uniform_bucket %p to %p\n", *p, end); - ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad); - b->item_weight = ceph_decode_32(p); - return 0; -bad: - return -EINVAL; -} - -static int crush_decode_list_bucket(void **p, void *end, - struct crush_bucket_list *b) -{ - int j; - dout("crush_decode_list_bucket %p to %p\n", *p, end); - b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); - if (b->item_weights == NULL) - return -ENOMEM; - b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); - if (b->sum_weights == NULL) - return -ENOMEM; - ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); - for (j = 0; j < b->h.size; j++) { - b->item_weights[j] = ceph_decode_32(p); - b->sum_weights[j] = ceph_decode_32(p); - } - return 0; -bad: - return -EINVAL; -} - -static int crush_decode_tree_bucket(void **p, void *end, - struct crush_bucket_tree *b) -{ - int j; - dout("crush_decode_tree_bucket %p to %p\n", *p, end); - ceph_decode_32_safe(p, end, b->num_nodes, bad); - b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS); - if (b->node_weights == NULL) - return -ENOMEM; - ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad); - for (j = 0; j < b->num_nodes; j++) - b->node_weights[j] = ceph_decode_32(p); - return 0; -bad: - return -EINVAL; -} - -static int crush_decode_straw_bucket(void **p, void *end, - struct crush_bucket_straw *b) -{ - int j; - dout("crush_decode_straw_bucket %p to %p\n", *p, end); - b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); - if (b->item_weights == NULL) - return -ENOMEM; - b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); - if (b->straws == NULL) - return -ENOMEM; - ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); - for (j = 0; j < b->h.size; j++) { - b->item_weights[j] = ceph_decode_32(p); - b->straws[j] = ceph_decode_32(p); - } - return 0; -bad: - return -EINVAL; -} - -static struct crush_map *crush_decode(void *pbyval, void *end) -{ - struct crush_map *c; - int err = -EINVAL; - int i, j; - void **p = &pbyval; - void *start = pbyval; - u32 magic; - - dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); - - c = kzalloc(sizeof(*c), GFP_NOFS); - if (c == NULL) - return ERR_PTR(-ENOMEM); - - ceph_decode_need(p, end, 4*sizeof(u32), bad); - magic = ceph_decode_32(p); - if (magic != CRUSH_MAGIC) { - pr_err("crush_decode magic %x != current %x\n", - (unsigned)magic, (unsigned)CRUSH_MAGIC); - goto bad; - } - c->max_buckets = ceph_decode_32(p); - c->max_rules = ceph_decode_32(p); - c->max_devices = ceph_decode_32(p); - - c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS); - if (c->device_parents == NULL) - goto badmem; - c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS); - if (c->bucket_parents == NULL) - goto badmem; - - c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS); - if (c->buckets == NULL) - goto badmem; - c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS); - if (c->rules == NULL) - goto badmem; - - /* buckets */ - for (i = 0; i < c->max_buckets; i++) { - int size = 0; - u32 alg; - struct crush_bucket *b; - - ceph_decode_32_safe(p, end, alg, bad); - if (alg == 0) { - c->buckets[i] = NULL; - continue; - } - dout("crush_decode bucket %d off %x %p to %p\n", - i, (int)(*p-start), *p, end); - - switch (alg) { - case CRUSH_BUCKET_UNIFORM: - size = sizeof(struct crush_bucket_uniform); - break; - case CRUSH_BUCKET_LIST: - size = sizeof(struct crush_bucket_list); - break; - case CRUSH_BUCKET_TREE: - size = sizeof(struct crush_bucket_tree); - break; - case CRUSH_BUCKET_STRAW: - size = sizeof(struct crush_bucket_straw); - break; - default: - err = -EINVAL; - goto bad; - } - BUG_ON(size == 0); - b = c->buckets[i] = kzalloc(size, GFP_NOFS); - if (b == NULL) - goto badmem; - - ceph_decode_need(p, end, 4*sizeof(u32), bad); - b->id = ceph_decode_32(p); - b->type = ceph_decode_16(p); - b->alg = ceph_decode_8(p); - b->hash = ceph_decode_8(p); - b->weight = ceph_decode_32(p); - b->size = ceph_decode_32(p); - - dout("crush_decode bucket size %d off %x %p to %p\n", - b->size, (int)(*p-start), *p, end); - - b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); - if (b->items == NULL) - goto badmem; - b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS); - if (b->perm == NULL) - goto badmem; - b->perm_n = 0; - - ceph_decode_need(p, end, b->size*sizeof(u32), bad); - for (j = 0; j < b->size; j++) - b->items[j] = ceph_decode_32(p); - - switch (b->alg) { - case CRUSH_BUCKET_UNIFORM: - err = crush_decode_uniform_bucket(p, end, - (struct crush_bucket_uniform *)b); - if (err < 0) - goto bad; - break; - case CRUSH_BUCKET_LIST: - err = crush_decode_list_bucket(p, end, - (struct crush_bucket_list *)b); - if (err < 0) - goto bad; - break; - case CRUSH_BUCKET_TREE: - err = crush_decode_tree_bucket(p, end, - (struct crush_bucket_tree *)b); - if (err < 0) - goto bad; - break; - case CRUSH_BUCKET_STRAW: - err = crush_decode_straw_bucket(p, end, - (struct crush_bucket_straw *)b); - if (err < 0) - goto bad; - break; - } - } - - /* rules */ - dout("rule vec is %p\n", c->rules); - for (i = 0; i < c->max_rules; i++) { - u32 yes; - struct crush_rule *r; - - ceph_decode_32_safe(p, end, yes, bad); - if (!yes) { - dout("crush_decode NO rule %d off %x %p to %p\n", - i, (int)(*p-start), *p, end); - c->rules[i] = NULL; - continue; - } - - dout("crush_decode rule %d off %x %p to %p\n", - i, (int)(*p-start), *p, end); - - /* len */ - ceph_decode_32_safe(p, end, yes, bad); -#if BITS_PER_LONG == 32 - err = -EINVAL; - if (yes > ULONG_MAX / sizeof(struct crush_rule_step)) - goto bad; -#endif - r = c->rules[i] = kmalloc(sizeof(*r) + - yes*sizeof(struct crush_rule_step), - GFP_NOFS); - if (r == NULL) - goto badmem; - dout(" rule %d is at %p\n", i, r); - r->len = yes; - ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */ - ceph_decode_need(p, end, r->len*3*sizeof(u32), bad); - for (j = 0; j < r->len; j++) { - r->steps[j].op = ceph_decode_32(p); - r->steps[j].arg1 = ceph_decode_32(p); - r->steps[j].arg2 = ceph_decode_32(p); - } - } - - /* ignore trailing name maps. */ - - dout("crush_decode success\n"); - return c; - -badmem: - err = -ENOMEM; -bad: - dout("crush_decode fail %d\n", err); - crush_destroy(c); - return ERR_PTR(err); -} - -/* - * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid - * to a set of osds) - */ -static int pgid_cmp(struct ceph_pg l, struct ceph_pg r) -{ - u64 a = *(u64 *)&l; - u64 b = *(u64 *)&r; - - if (a < b) - return -1; - if (a > b) - return 1; - return 0; -} - -static int __insert_pg_mapping(struct ceph_pg_mapping *new, - struct rb_root *root) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct ceph_pg_mapping *pg = NULL; - int c; - - while (*p) { - parent = *p; - pg = rb_entry(parent, struct ceph_pg_mapping, node); - c = pgid_cmp(new->pgid, pg->pgid); - if (c < 0) - p = &(*p)->rb_left; - else if (c > 0) - p = &(*p)->rb_right; - else - return -EEXIST; - } - - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, root); - return 0; -} - -static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, - struct ceph_pg pgid) -{ - struct rb_node *n = root->rb_node; - struct ceph_pg_mapping *pg; - int c; - - while (n) { - pg = rb_entry(n, struct ceph_pg_mapping, node); - c = pgid_cmp(pgid, pg->pgid); - if (c < 0) - n = n->rb_left; - else if (c > 0) - n = n->rb_right; - else - return pg; - } - return NULL; -} - -/* - * rbtree of pg pool info - */ -static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct ceph_pg_pool_info *pi = NULL; - - while (*p) { - parent = *p; - pi = rb_entry(parent, struct ceph_pg_pool_info, node); - if (new->id < pi->id) - p = &(*p)->rb_left; - else if (new->id > pi->id) - p = &(*p)->rb_right; - else - return -EEXIST; - } - - rb_link_node(&new->node, parent, p); - rb_insert_color(&new->node, root); - return 0; -} - -static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) -{ - struct ceph_pg_pool_info *pi; - struct rb_node *n = root->rb_node; - - while (n) { - pi = rb_entry(n, struct ceph_pg_pool_info, node); - if (id < pi->id) - n = n->rb_left; - else if (id > pi->id) - n = n->rb_right; - else - return pi; - } - return NULL; -} - -int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) -{ - struct rb_node *rbp; - - for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) { - struct ceph_pg_pool_info *pi = - rb_entry(rbp, struct ceph_pg_pool_info, node); - if (pi->name && strcmp(pi->name, name) == 0) - return pi->id; - } - return -ENOENT; -} - -static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) -{ - rb_erase(&pi->node, root); - kfree(pi->name); - kfree(pi); -} - -static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) -{ - unsigned n, m; - - ceph_decode_copy(p, &pi->v, sizeof(pi->v)); - calc_pg_masks(pi); - - /* num_snaps * snap_info_t */ - n = le32_to_cpu(pi->v.num_snaps); - while (n--) { - ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) + - sizeof(struct ceph_timespec), bad); - *p += sizeof(u64) + /* key */ - 1 + sizeof(u64) + /* u8, snapid */ - sizeof(struct ceph_timespec); - m = ceph_decode_32(p); /* snap name */ - *p += m; - } - - *p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2; - return 0; - -bad: - return -EINVAL; -} - -static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) -{ - struct ceph_pg_pool_info *pi; - u32 num, len, pool; - - ceph_decode_32_safe(p, end, num, bad); - dout(" %d pool names\n", num); - while (num--) { - ceph_decode_32_safe(p, end, pool, bad); - ceph_decode_32_safe(p, end, len, bad); - dout(" pool %d len %d\n", pool, len); - pi = __lookup_pg_pool(&map->pg_pools, pool); - if (pi) { - kfree(pi->name); - pi->name = kmalloc(len + 1, GFP_NOFS); - if (pi->name) { - memcpy(pi->name, *p, len); - pi->name[len] = '\0'; - dout(" name is %s\n", pi->name); - } - } - *p += len; - } - return 0; - -bad: - return -EINVAL; -} - -/* - * osd map - */ -void ceph_osdmap_destroy(struct ceph_osdmap *map) -{ - dout("osdmap_destroy %p\n", map); - if (map->crush) - crush_destroy(map->crush); - while (!RB_EMPTY_ROOT(&map->pg_temp)) { - struct ceph_pg_mapping *pg = - rb_entry(rb_first(&map->pg_temp), - struct ceph_pg_mapping, node); - rb_erase(&pg->node, &map->pg_temp); - kfree(pg); - } - while (!RB_EMPTY_ROOT(&map->pg_pools)) { - struct ceph_pg_pool_info *pi = - rb_entry(rb_first(&map->pg_pools), - struct ceph_pg_pool_info, node); - __remove_pg_pool(&map->pg_pools, pi); - } - kfree(map->osd_state); - kfree(map->osd_weight); - kfree(map->osd_addr); - kfree(map); -} - -/* - * adjust max osd value. reallocate arrays. - */ -static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) -{ - u8 *state; - struct ceph_entity_addr *addr; - u32 *weight; - - state = kcalloc(max, sizeof(*state), GFP_NOFS); - addr = kcalloc(max, sizeof(*addr), GFP_NOFS); - weight = kcalloc(max, sizeof(*weight), GFP_NOFS); - if (state == NULL || addr == NULL || weight == NULL) { - kfree(state); - kfree(addr); - kfree(weight); - return -ENOMEM; - } - - /* copy old? */ - if (map->osd_state) { - memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); - memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); - memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); - kfree(map->osd_state); - kfree(map->osd_addr); - kfree(map->osd_weight); - } - - map->osd_state = state; - map->osd_weight = weight; - map->osd_addr = addr; - map->max_osd = max; - return 0; -} - -/* - * decode a full map. - */ -struct ceph_osdmap *osdmap_decode(void **p, void *end) -{ - struct ceph_osdmap *map; - u16 version; - u32 len, max, i; - u8 ev; - int err = -EINVAL; - void *start = *p; - struct ceph_pg_pool_info *pi; - - dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p)); - - map = kzalloc(sizeof(*map), GFP_NOFS); - if (map == NULL) - return ERR_PTR(-ENOMEM); - map->pg_temp = RB_ROOT; - - ceph_decode_16_safe(p, end, version, bad); - if (version > CEPH_OSDMAP_VERSION) { - pr_warning("got unknown v %d > %d of osdmap\n", version, - CEPH_OSDMAP_VERSION); - goto bad; - } - - ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad); - ceph_decode_copy(p, &map->fsid, sizeof(map->fsid)); - map->epoch = ceph_decode_32(p); - ceph_decode_copy(p, &map->created, sizeof(map->created)); - ceph_decode_copy(p, &map->modified, sizeof(map->modified)); - - ceph_decode_32_safe(p, end, max, bad); - while (max--) { - ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) - goto bad; - pi->id = ceph_decode_32(p); - ev = ceph_decode_8(p); /* encoding version */ - if (ev > CEPH_PG_POOL_VERSION) { - pr_warning("got unknown v %d > %d of ceph_pg_pool\n", - ev, CEPH_PG_POOL_VERSION); - kfree(pi); - goto bad; - } - err = __decode_pool(p, end, pi); - if (err < 0) - goto bad; - __insert_pg_pool(&map->pg_pools, pi); - } - - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; - - ceph_decode_32_safe(p, end, map->pool_max, bad); - - ceph_decode_32_safe(p, end, map->flags, bad); - - max = ceph_decode_32(p); - - /* (re)alloc osd arrays */ - err = osdmap_set_max_osd(map, max); - if (err < 0) - goto bad; - dout("osdmap_decode max_osd = %d\n", map->max_osd); - - /* osds */ - err = -EINVAL; - ceph_decode_need(p, end, 3*sizeof(u32) + - map->max_osd*(1 + sizeof(*map->osd_weight) + - sizeof(*map->osd_addr)), bad); - *p += 4; /* skip length field (should match max) */ - ceph_decode_copy(p, map->osd_state, map->max_osd); - - *p += 4; /* skip length field (should match max) */ - for (i = 0; i < map->max_osd; i++) - map->osd_weight[i] = ceph_decode_32(p); - - *p += 4; /* skip length field (should match max) */ - ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr)); - for (i = 0; i < map->max_osd; i++) - ceph_decode_addr(&map->osd_addr[i]); - - /* pg_temp */ - ceph_decode_32_safe(p, end, len, bad); - for (i = 0; i < len; i++) { - int n, j; - struct ceph_pg pgid; - struct ceph_pg_mapping *pg; - - ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); - ceph_decode_copy(p, &pgid, sizeof(pgid)); - n = ceph_decode_32(p); - ceph_decode_need(p, end, n * sizeof(u32), bad); - err = -ENOMEM; - pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); - if (!pg) - goto bad; - pg->pgid = pgid; - pg->len = n; - for (j = 0; j < n; j++) - pg->osds[j] = ceph_decode_32(p); - - err = __insert_pg_mapping(pg, &map->pg_temp); - if (err) - goto bad; - dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len); - } - - /* crush */ - ceph_decode_32_safe(p, end, len, bad); - dout("osdmap_decode crush len %d from off 0x%x\n", len, - (int)(*p - start)); - ceph_decode_need(p, end, len, bad); - map->crush = crush_decode(*p, end); - *p += len; - if (IS_ERR(map->crush)) { - err = PTR_ERR(map->crush); - map->crush = NULL; - goto bad; - } - - /* ignore the rest of the map */ - *p = end; - - dout("osdmap_decode done %p %p\n", *p, end); - return map; - -bad: - dout("osdmap_decode fail\n"); - ceph_osdmap_destroy(map); - return ERR_PTR(err); -} - -/* - * decode and apply an incremental map update. - */ -struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, - struct ceph_osdmap *map, - struct ceph_messenger *msgr) -{ - struct crush_map *newcrush = NULL; - struct ceph_fsid fsid; - u32 epoch = 0; - struct ceph_timespec modified; - u32 len, pool; - __s32 new_pool_max, new_flags, max; - void *start = *p; - int err = -EINVAL; - u16 version; - struct rb_node *rbp; - - ceph_decode_16_safe(p, end, version, bad); - if (version > CEPH_OSDMAP_INC_VERSION) { - pr_warning("got unknown v %d > %d of inc osdmap\n", version, - CEPH_OSDMAP_INC_VERSION); - goto bad; - } - - ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32), - bad); - ceph_decode_copy(p, &fsid, sizeof(fsid)); - epoch = ceph_decode_32(p); - BUG_ON(epoch != map->epoch+1); - ceph_decode_copy(p, &modified, sizeof(modified)); - new_pool_max = ceph_decode_32(p); - new_flags = ceph_decode_32(p); - - /* full map? */ - ceph_decode_32_safe(p, end, len, bad); - if (len > 0) { - dout("apply_incremental full map len %d, %p to %p\n", - len, *p, end); - return osdmap_decode(p, min(*p+len, end)); - } - - /* new crush? */ - ceph_decode_32_safe(p, end, len, bad); - if (len > 0) { - dout("apply_incremental new crush map len %d, %p to %p\n", - len, *p, end); - newcrush = crush_decode(*p, min(*p+len, end)); - if (IS_ERR(newcrush)) - return ERR_CAST(newcrush); - *p += len; - } - - /* new flags? */ - if (new_flags >= 0) - map->flags = new_flags; - if (new_pool_max >= 0) - map->pool_max = new_pool_max; - - ceph_decode_need(p, end, 5*sizeof(u32), bad); - - /* new max? */ - max = ceph_decode_32(p); - if (max >= 0) { - err = osdmap_set_max_osd(map, max); - if (err < 0) - goto bad; - } - - map->epoch++; - map->modified = map->modified; - if (newcrush) { - if (map->crush) - crush_destroy(map->crush); - map->crush = newcrush; - newcrush = NULL; - } - - /* new_pool */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - __u8 ev; - struct ceph_pg_pool_info *pi; - - ceph_decode_32_safe(p, end, pool, bad); - ceph_decode_need(p, end, 1 + sizeof(pi->v), bad); - ev = ceph_decode_8(p); /* encoding version */ - if (ev > CEPH_PG_POOL_VERSION) { - pr_warning("got unknown v %d > %d of ceph_pg_pool\n", - ev, CEPH_PG_POOL_VERSION); - goto bad; - } - pi = __lookup_pg_pool(&map->pg_pools, pool); - if (!pi) { - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) { - err = -ENOMEM; - goto bad; - } - pi->id = pool; - __insert_pg_pool(&map->pg_pools, pi); - } - err = __decode_pool(p, end, pi); - if (err < 0) - goto bad; - } - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; - - /* old_pool */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_pool_info *pi; - - ceph_decode_32_safe(p, end, pool, bad); - pi = __lookup_pg_pool(&map->pg_pools, pool); - if (pi) - __remove_pg_pool(&map->pg_pools, pi); - } - - /* new_up */ - err = -EINVAL; - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd; - struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, bad); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad); - ceph_decode_addr(&addr); - pr_info("osd%d up\n", osd); - BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP; - map->osd_addr[osd] = addr; - } - - /* new_down */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd; - ceph_decode_32_safe(p, end, osd, bad); - (*p)++; /* clean flag */ - pr_info("osd%d down\n", osd); - if (osd < map->max_osd) - map->osd_state[osd] &= ~CEPH_OSD_UP; - } - - /* new_weight */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, bad); - osd = ceph_decode_32(p); - off = ceph_decode_32(p); - pr_info("osd%d weight 0x%x %s\n", osd, off, - off == CEPH_OSD_IN ? "(in)" : - (off == CEPH_OSD_OUT ? "(out)" : "")); - if (osd < map->max_osd) - map->osd_weight[osd] = off; - } - - /* new_pg_temp */ - rbp = rb_first(&map->pg_temp); - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_mapping *pg; - int j; - struct ceph_pg pgid; - u32 pglen; - ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); - ceph_decode_copy(p, &pgid, sizeof(pgid)); - pglen = ceph_decode_32(p); - - /* remove any? */ - while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping, - node)->pgid, pgid) <= 0) { - struct ceph_pg_mapping *cur = - rb_entry(rbp, struct ceph_pg_mapping, node); - - rbp = rb_next(rbp); - dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid); - rb_erase(&cur->node, &map->pg_temp); - kfree(cur); - } - - if (pglen) { - /* insert */ - ceph_decode_need(p, end, pglen*sizeof(u32), bad); - pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); - if (!pg) { - err = -ENOMEM; - goto bad; - } - pg->pgid = pgid; - pg->len = pglen; - for (j = 0; j < pglen; j++) - pg->osds[j] = ceph_decode_32(p); - err = __insert_pg_mapping(pg, &map->pg_temp); - if (err) { - kfree(pg); - goto bad; - } - dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, - pglen); - } - } - while (rbp) { - struct ceph_pg_mapping *cur = - rb_entry(rbp, struct ceph_pg_mapping, node); - - rbp = rb_next(rbp); - dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid); - rb_erase(&cur->node, &map->pg_temp); - kfree(cur); - } - - /* ignore the rest */ - *p = end; - return map; - -bad: - pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n", - epoch, (int)(*p - start), *p, start, end); - print_hex_dump(KERN_DEBUG, "osdmap: ", - DUMP_PREFIX_OFFSET, 16, 1, - start, end - start, true); - if (newcrush) - crush_destroy(newcrush); - return ERR_PTR(err); -} - - - - -/* - * calculate file layout from given offset, length. - * fill in correct oid, logical length, and object extent - * offset, length. - * - * for now, we write only a single su, until we can - * pass a stride back to the caller. - */ -void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 *plen, - u64 *ono, - u64 *oxoff, u64 *oxlen) -{ - u32 osize = le32_to_cpu(layout->fl_object_size); - u32 su = le32_to_cpu(layout->fl_stripe_unit); - u32 sc = le32_to_cpu(layout->fl_stripe_count); - u32 bl, stripeno, stripepos, objsetno; - u32 su_per_object; - u64 t, su_offset; - - dout("mapping %llu~%llu osize %u fl_su %u\n", off, *plen, - osize, su); - su_per_object = osize / su; - dout("osize %u / su %u = su_per_object %u\n", osize, su, - su_per_object); - - BUG_ON((su & ~PAGE_MASK) != 0); - /* bl = *off / su; */ - t = off; - do_div(t, su); - bl = t; - dout("off %llu / su %u = bl %u\n", off, su, bl); - - stripeno = bl / sc; - stripepos = bl % sc; - objsetno = stripeno / su_per_object; - - *ono = objsetno * sc + stripepos; - dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono); - - /* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ - t = off; - su_offset = do_div(t, su); - *oxoff = su_offset + (stripeno % su_per_object) * su; - - /* - * Calculate the length of the extent being written to the selected - * object. This is the minimum of the full length requested (plen) or - * the remainder of the current stripe being written to. - */ - *oxlen = min_t(u64, *plen, su - su_offset); - *plen = *oxlen; - - dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); -} - -/* - * calculate an object layout (i.e. pgid) from an oid, - * file_layout, and osdmap - */ -int ceph_calc_object_layout(struct ceph_object_layout *ol, - const char *oid, - struct ceph_file_layout *fl, - struct ceph_osdmap *osdmap) -{ - unsigned num, num_mask; - struct ceph_pg pgid; - s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred); - int poolid = le32_to_cpu(fl->fl_pg_pool); - struct ceph_pg_pool_info *pool; - unsigned ps; - - BUG_ON(!osdmap); - - pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); - if (!pool) - return -EIO; - ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid)); - if (preferred >= 0) { - ps += preferred; - num = le32_to_cpu(pool->v.lpg_num); - num_mask = pool->lpg_num_mask; - } else { - num = le32_to_cpu(pool->v.pg_num); - num_mask = pool->pg_num_mask; - } - - pgid.ps = cpu_to_le16(ps); - pgid.preferred = cpu_to_le16(preferred); - pgid.pool = fl->fl_pg_pool; - if (preferred >= 0) - dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps, - (int)preferred); - else - dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps); - - ol->ol_pgid = pgid; - ol->ol_stripe_unit = fl->fl_object_stripe_unit; - return 0; -} - -/* - * Calculate raw osd vector for the given pgid. Return pointer to osd - * array, or NULL on failure. - */ -static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *osds, int *num) -{ - struct ceph_pg_mapping *pg; - struct ceph_pg_pool_info *pool; - int ruleno; - unsigned poolid, ps, pps; - int preferred; - - /* pg_temp? */ - pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); - if (pg) { - *num = pg->len; - return pg->osds; - } - - /* crush */ - poolid = le32_to_cpu(pgid.pool); - ps = le16_to_cpu(pgid.ps); - preferred = (s16)le16_to_cpu(pgid.preferred); - - /* don't forcefeed bad device ids to crush */ - if (preferred >= osdmap->max_osd || - preferred >= osdmap->crush->max_devices) - preferred = -1; - - pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); - if (!pool) - return NULL; - ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset, - pool->v.type, pool->v.size); - if (ruleno < 0) { - pr_err("no crush rule pool %d ruleset %d type %d size %d\n", - poolid, pool->v.crush_ruleset, pool->v.type, - pool->v.size); - return NULL; - } - - if (preferred >= 0) - pps = ceph_stable_mod(ps, - le32_to_cpu(pool->v.lpgp_num), - pool->lpgp_num_mask); - else - pps = ceph_stable_mod(ps, - le32_to_cpu(pool->v.pgp_num), - pool->pgp_num_mask); - pps += poolid; - *num = crush_do_rule(osdmap->crush, ruleno, pps, osds, - min_t(int, pool->v.size, *num), - preferred, osdmap->osd_weight); - return osds; -} - -/* - * Return acting set for given pgid. - */ -int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *acting) -{ - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, o, num = CEPH_PG_MAX_SIZE; - - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) - return -1; - - /* primary is first up osd */ - o = 0; - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - acting[o++] = osds[i]; - return o; -} - -/* - * Return primary osd for given pgid, or -1 if none. - */ -int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid) -{ - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, num = CEPH_PG_MAX_SIZE; - - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) - return -1; - - /* primary is first up osd */ - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - return osds[i]; - return -1; -} diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h deleted file mode 100644 index a592b211be39..000000000000 --- a/fs/ceph/osdmap.h +++ /dev/null @@ -1,130 +0,0 @@ -#ifndef _FS_CEPH_OSDMAP_H -#define _FS_CEPH_OSDMAP_H - -#include -#include "types.h" -#include "ceph_fs.h" -#include "crush/crush.h" - -/* - * The osd map describes the current membership of the osd cluster and - * specifies the mapping of objects to placement groups and placement - * groups to (sets of) osds. That is, it completely specifies the - * (desired) distribution of all data objects in the system at some - * point in time. - * - * Each map version is identified by an epoch, which increases monotonically. - * - * The map can be updated either via an incremental map (diff) describing - * the change between two successive epochs, or as a fully encoded map. - */ -struct ceph_pg_pool_info { - struct rb_node node; - int id; - struct ceph_pg_pool v; - int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; - char *name; -}; - -struct ceph_pg_mapping { - struct rb_node node; - struct ceph_pg pgid; - int len; - int osds[]; -}; - -struct ceph_osdmap { - struct ceph_fsid fsid; - u32 epoch; - u32 mkfs_epoch; - struct ceph_timespec created, modified; - - u32 flags; /* CEPH_OSDMAP_* */ - - u32 max_osd; /* size of osd_state, _offload, _addr arrays */ - u8 *osd_state; /* CEPH_OSD_* */ - u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ - struct ceph_entity_addr *osd_addr; - - struct rb_root pg_temp; - struct rb_root pg_pools; - u32 pool_max; - - /* the CRUSH map specifies the mapping of placement groups to - * the list of osds that store+replicate them. */ - struct crush_map *crush; -}; - -/* - * file layout helpers - */ -#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) -#define ceph_file_layout_stripe_count(l) \ - ((__s32)le32_to_cpu((l).fl_stripe_count)) -#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) -#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) -#define ceph_file_layout_object_su(l) \ - ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) -#define ceph_file_layout_pg_preferred(l) \ - ((__s32)le32_to_cpu((l).fl_pg_preferred)) -#define ceph_file_layout_pg_pool(l) \ - ((__s32)le32_to_cpu((l).fl_pg_pool)) - -static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_stripe_unit) * - le32_to_cpu(l->fl_stripe_count); -} - -/* "period" == bytes before i start on a new set of objects */ -static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_object_size) * - le32_to_cpu(l->fl_stripe_count); -} - - -static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) -{ - return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); -} - -static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag) -{ - return map && (map->flags & flag); -} - -extern char *ceph_osdmap_state_str(char *str, int len, int state); - -static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, - int osd) -{ - if (osd >= map->max_osd) - return NULL; - return &map->osd_addr[osd]; -} - -extern struct ceph_osdmap *osdmap_decode(void **p, void *end); -extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, - struct ceph_osdmap *map, - struct ceph_messenger *msgr); -extern void ceph_osdmap_destroy(struct ceph_osdmap *map); - -/* calculate mapping of a file extent to an object */ -extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 *plen, - u64 *bno, u64 *oxoff, u64 *oxlen); - -/* calculate mapping of object to a placement group */ -extern int ceph_calc_object_layout(struct ceph_object_layout *ol, - const char *oid, - struct ceph_file_layout *fl, - struct ceph_osdmap *osdmap); -extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *acting); -extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, - struct ceph_pg pgid); - -extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); - -#endif diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c deleted file mode 100644 index 326e1c04176f..000000000000 --- a/fs/ceph/pagelist.c +++ /dev/null @@ -1,63 +0,0 @@ - -#include -#include -#include - -#include "pagelist.h" - -static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl) -{ - struct page *page = list_entry(pl->head.prev, struct page, - lru); - kunmap(page); -} - -int ceph_pagelist_release(struct ceph_pagelist *pl) -{ - if (pl->mapped_tail) - ceph_pagelist_unmap_tail(pl); - - while (!list_empty(&pl->head)) { - struct page *page = list_first_entry(&pl->head, struct page, - lru); - list_del(&page->lru); - __free_page(page); - } - return 0; -} - -static int ceph_pagelist_addpage(struct ceph_pagelist *pl) -{ - struct page *page = __page_cache_alloc(GFP_NOFS); - if (!page) - return -ENOMEM; - pl->room += PAGE_SIZE; - list_add_tail(&page->lru, &pl->head); - if (pl->mapped_tail) - ceph_pagelist_unmap_tail(pl); - pl->mapped_tail = kmap(page); - return 0; -} - -int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) -{ - while (pl->room < len) { - size_t bit = pl->room; - int ret; - - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), - buf, bit); - pl->length += bit; - pl->room -= bit; - buf += bit; - len -= bit; - ret = ceph_pagelist_addpage(pl); - if (ret) - return ret; - } - - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len); - pl->length += len; - pl->room -= len; - return 0; -} diff --git a/fs/ceph/pagelist.h b/fs/ceph/pagelist.h deleted file mode 100644 index cc9327aa1c98..000000000000 --- a/fs/ceph/pagelist.h +++ /dev/null @@ -1,54 +0,0 @@ -#ifndef __FS_CEPH_PAGELIST_H -#define __FS_CEPH_PAGELIST_H - -#include - -struct ceph_pagelist { - struct list_head head; - void *mapped_tail; - size_t length; - size_t room; -}; - -static inline void ceph_pagelist_init(struct ceph_pagelist *pl) -{ - INIT_LIST_HEAD(&pl->head); - pl->mapped_tail = NULL; - pl->length = 0; - pl->room = 0; -} -extern int ceph_pagelist_release(struct ceph_pagelist *pl); - -extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l); - -static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v) -{ - __le64 ev = cpu_to_le64(v); - return ceph_pagelist_append(pl, &ev, sizeof(ev)); -} -static inline int ceph_pagelist_encode_32(struct ceph_pagelist *pl, u32 v) -{ - __le32 ev = cpu_to_le32(v); - return ceph_pagelist_append(pl, &ev, sizeof(ev)); -} -static inline int ceph_pagelist_encode_16(struct ceph_pagelist *pl, u16 v) -{ - __le16 ev = cpu_to_le16(v); - return ceph_pagelist_append(pl, &ev, sizeof(ev)); -} -static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v) -{ - return ceph_pagelist_append(pl, &v, 1); -} -static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl, - char *s, size_t len) -{ - int ret = ceph_pagelist_encode_32(pl, len); - if (ret) - return ret; - if (len) - return ceph_pagelist_append(pl, s, len); - return 0; -} - -#endif diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h deleted file mode 100644 index 6d5247f2e81b..000000000000 --- a/fs/ceph/rados.h +++ /dev/null @@ -1,405 +0,0 @@ -#ifndef CEPH_RADOS_H -#define CEPH_RADOS_H - -/* - * Data types for the Ceph distributed object storage layer RADOS - * (Reliable Autonomic Distributed Object Store). - */ - -#include "msgr.h" - -/* - * osdmap encoding versions - */ -#define CEPH_OSDMAP_INC_VERSION 5 -#define CEPH_OSDMAP_INC_VERSION_EXT 5 -#define CEPH_OSDMAP_VERSION 5 -#define CEPH_OSDMAP_VERSION_EXT 5 - -/* - * fs id - */ -struct ceph_fsid { - unsigned char fsid[16]; -}; - -static inline int ceph_fsid_compare(const struct ceph_fsid *a, - const struct ceph_fsid *b) -{ - return memcmp(a, b, sizeof(*a)); -} - -/* - * ino, object, etc. - */ -typedef __le64 ceph_snapid_t; -#define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */ -#define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */ -#define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */ - -struct ceph_timespec { - __le32 tv_sec; - __le32 tv_nsec; -} __attribute__ ((packed)); - - -/* - * object layout - how objects are mapped into PGs - */ -#define CEPH_OBJECT_LAYOUT_HASH 1 -#define CEPH_OBJECT_LAYOUT_LINEAR 2 -#define CEPH_OBJECT_LAYOUT_HASHINO 3 - -/* - * pg layout -- how PGs are mapped onto (sets of) OSDs - */ -#define CEPH_PG_LAYOUT_CRUSH 0 -#define CEPH_PG_LAYOUT_HASH 1 -#define CEPH_PG_LAYOUT_LINEAR 2 -#define CEPH_PG_LAYOUT_HYBRID 3 - -#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */ - -/* - * placement group. - * we encode this into one __le64. - */ -struct ceph_pg { - __le16 preferred; /* preferred primary osd */ - __le16 ps; /* placement seed */ - __le32 pool; /* object pool */ -} __attribute__ ((packed)); - -/* - * pg_pool is a set of pgs storing a pool of objects - * - * pg_num -- base number of pseudorandomly placed pgs - * - * pgp_num -- effective number when calculating pg placement. this - * is used for pg_num increases. new pgs result in data being "split" - * into new pgs. for this to proceed smoothly, new pgs are intiially - * colocated with their parents; that is, pgp_num doesn't increase - * until the new pgs have successfully split. only _then_ are the new - * pgs placed independently. - * - * lpg_num -- localized pg count (per device). replicas are randomly - * selected. - * - * lpgp_num -- as above. - */ -#define CEPH_PG_TYPE_REP 1 -#define CEPH_PG_TYPE_RAID4 2 -#define CEPH_PG_POOL_VERSION 2 -struct ceph_pg_pool { - __u8 type; /* CEPH_PG_TYPE_* */ - __u8 size; /* number of osds in each pg */ - __u8 crush_ruleset; /* crush placement rule */ - __u8 object_hash; /* hash mapping object name to ps */ - __le32 pg_num, pgp_num; /* number of pg's */ - __le32 lpg_num, lpgp_num; /* number of localized pg's */ - __le32 last_change; /* most recent epoch changed */ - __le64 snap_seq; /* seq for per-pool snapshot */ - __le32 snap_epoch; /* epoch of last snap */ - __le32 num_snaps; - __le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */ - __le64 auid; /* who owns the pg */ -} __attribute__ ((packed)); - -/* - * stable_mod func is used to control number of placement groups. - * similar to straight-up modulo, but produces a stable mapping as b - * increases over time. b is the number of bins, and bmask is the - * containing power of 2 minus 1. - * - * b <= bmask and bmask=(2**n)-1 - * e.g., b=12 -> bmask=15, b=123 -> bmask=127 - */ -static inline int ceph_stable_mod(int x, int b, int bmask) -{ - if ((x & bmask) < b) - return x & bmask; - else - return x & (bmask >> 1); -} - -/* - * object layout - how a given object should be stored. - */ -struct ceph_object_layout { - struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */ - __le32 ol_stripe_unit; /* for per-object parity, if any */ -} __attribute__ ((packed)); - -/* - * compound epoch+version, used by storage layer to serialize mutations - */ -struct ceph_eversion { - __le32 epoch; - __le64 version; -} __attribute__ ((packed)); - -/* - * osd map bits - */ - -/* status bits */ -#define CEPH_OSD_EXISTS 1 -#define CEPH_OSD_UP 2 - -/* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ -#define CEPH_OSD_IN 0x10000 -#define CEPH_OSD_OUT 0 - - -/* - * osd map flag bits - */ -#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */ -#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */ -#define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ -#define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ -#define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ - -/* - * osd ops - */ -#define CEPH_OSD_OP_MODE 0xf000 -#define CEPH_OSD_OP_MODE_RD 0x1000 -#define CEPH_OSD_OP_MODE_WR 0x2000 -#define CEPH_OSD_OP_MODE_RMW 0x3000 -#define CEPH_OSD_OP_MODE_SUB 0x4000 - -#define CEPH_OSD_OP_TYPE 0x0f00 -#define CEPH_OSD_OP_TYPE_LOCK 0x0100 -#define CEPH_OSD_OP_TYPE_DATA 0x0200 -#define CEPH_OSD_OP_TYPE_ATTR 0x0300 -#define CEPH_OSD_OP_TYPE_EXEC 0x0400 -#define CEPH_OSD_OP_TYPE_PG 0x0500 - -enum { - /** data **/ - /* read */ - CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1, - CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2, - - /* fancy read */ - CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4, - - /* write */ - CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1, - CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2, - CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3, - CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4, - CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5, - - /* fancy write */ - CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6, - CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7, - CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8, - CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9, - - CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10, - CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11, - CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12, - - CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13, - CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14, - - /** attrs **/ - /* read */ - CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1, - CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2, - CEPH_OSD_OP_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3, - - /* write */ - CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1, - CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2, - CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3, - CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4, - - /** subop **/ - CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB | 1, - CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB | 2, - CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB | 3, - CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4, - CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB | 5, - - /** lock **/ - CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1, - CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2, - CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3, - CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4, - CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5, - CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6, - - /** exec **/ - CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1, - - /** pg **/ - CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1, -}; - -static inline int ceph_osd_op_type_lock(int op) -{ - return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK; -} -static inline int ceph_osd_op_type_data(int op) -{ - return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA; -} -static inline int ceph_osd_op_type_attr(int op) -{ - return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR; -} -static inline int ceph_osd_op_type_exec(int op) -{ - return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC; -} -static inline int ceph_osd_op_type_pg(int op) -{ - return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG; -} - -static inline int ceph_osd_op_mode_subop(int op) -{ - return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB; -} -static inline int ceph_osd_op_mode_read(int op) -{ - return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD; -} -static inline int ceph_osd_op_mode_modify(int op) -{ - return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR; -} - -/* - * note that the following tmap stuff is also defined in the ceph librados.h - * any modification here needs to be updated there - */ -#define CEPH_OSD_TMAP_HDR 'h' -#define CEPH_OSD_TMAP_SET 's' -#define CEPH_OSD_TMAP_RM 'r' - -extern const char *ceph_osd_op_name(int op); - - -/* - * osd op flags - * - * An op may be READ, WRITE, or READ|WRITE. - */ -enum { - CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */ - CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */ - CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */ - CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */ - CEPH_OSD_FLAG_READ = 16, /* op may read */ - CEPH_OSD_FLAG_WRITE = 32, /* op may write */ - CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */ - CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */ - CEPH_OSD_FLAG_BALANCE_READS = 256, - CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */ - CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */ - CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */ - CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */ -}; - -enum { - CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ -}; - -#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ -#define EBLACKLISTED ESHUTDOWN /* blacklisted */ - -/* xattr comparison */ -enum { - CEPH_OSD_CMPXATTR_OP_NOP = 0, - CEPH_OSD_CMPXATTR_OP_EQ = 1, - CEPH_OSD_CMPXATTR_OP_NE = 2, - CEPH_OSD_CMPXATTR_OP_GT = 3, - CEPH_OSD_CMPXATTR_OP_GTE = 4, - CEPH_OSD_CMPXATTR_OP_LT = 5, - CEPH_OSD_CMPXATTR_OP_LTE = 6 -}; - -enum { - CEPH_OSD_CMPXATTR_MODE_STRING = 1, - CEPH_OSD_CMPXATTR_MODE_U64 = 2 -}; - -/* - * an individual object operation. each may be accompanied by some data - * payload - */ -struct ceph_osd_op { - __le16 op; /* CEPH_OSD_OP_* */ - __le32 flags; /* CEPH_OSD_FLAG_* */ - union { - struct { - __le64 offset, length; - __le64 truncate_size; - __le32 truncate_seq; - } __attribute__ ((packed)) extent; - struct { - __le32 name_len; - __le32 value_len; - __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ - __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ - } __attribute__ ((packed)) xattr; - struct { - __u8 class_len; - __u8 method_len; - __u8 argc; - __le32 indata_len; - } __attribute__ ((packed)) cls; - struct { - __le64 cookie, count; - } __attribute__ ((packed)) pgls; - struct { - __le64 snapid; - } __attribute__ ((packed)) snap; - }; - __le32 payload_len; -} __attribute__ ((packed)); - -/* - * osd request message header. each request may include multiple - * ceph_osd_op object operations. - */ -struct ceph_osd_request_head { - __le32 client_inc; /* client incarnation */ - struct ceph_object_layout layout; /* pgid */ - __le32 osdmap_epoch; /* client's osdmap epoch */ - - __le32 flags; - - struct ceph_timespec mtime; /* for mutations only */ - struct ceph_eversion reassert_version; /* if we are replaying op */ - - __le32 object_len; /* length of object name */ - - __le64 snapid; /* snapid to read */ - __le64 snap_seq; /* writer's snap context */ - __le32 num_snaps; - - __le16 num_ops; - struct ceph_osd_op ops[]; /* followed by ops[], obj, ticket, snaps */ -} __attribute__ ((packed)); - -struct ceph_osd_reply_head { - __le32 client_inc; /* client incarnation */ - __le32 flags; - struct ceph_object_layout layout; - __le32 osdmap_epoch; - struct ceph_eversion reassert_version; /* for replaying uncommitted */ - - __le32 result; /* result code */ - - __le32 object_len; /* length of object name */ - __le32 num_ops; - struct ceph_osd_op ops[0]; /* ops[], object */ -} __attribute__ ((packed)); - - -#endif diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 190b6c4a6f2b..39c243acd062 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1,10 +1,12 @@ -#include "ceph_debug.h" +#include #include #include #include "super.h" -#include "decode.h" +#include "mds_client.h" + +#include /* * Snapshots in ceph are driven in large part by cooperation from the @@ -526,7 +528,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap *capsnap) { struct inode *inode = &ci->vfs_inode; - struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; BUG_ON(capsnap->writing); capsnap->size = inode->i_size; @@ -747,7 +749,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg) { - struct super_block *sb = mdsc->client->sb; + struct super_block *sb = mdsc->fsc->sb; int mds = session->s_mds; u64 split; int op; diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c new file mode 100644 index 000000000000..cd5097d7c804 --- /dev/null +++ b/fs/ceph/strings.c @@ -0,0 +1,117 @@ +/* + * Ceph fs string constants + */ +#include +#include + + +const char *ceph_mds_state_name(int s) +{ + switch (s) { + /* down and out */ + case CEPH_MDS_STATE_DNE: return "down:dne"; + case CEPH_MDS_STATE_STOPPED: return "down:stopped"; + /* up and out */ + case CEPH_MDS_STATE_BOOT: return "up:boot"; + case CEPH_MDS_STATE_STANDBY: return "up:standby"; + case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay"; + case CEPH_MDS_STATE_CREATING: return "up:creating"; + case CEPH_MDS_STATE_STARTING: return "up:starting"; + /* up and in */ + case CEPH_MDS_STATE_REPLAY: return "up:replay"; + case CEPH_MDS_STATE_RESOLVE: return "up:resolve"; + case CEPH_MDS_STATE_RECONNECT: return "up:reconnect"; + case CEPH_MDS_STATE_REJOIN: return "up:rejoin"; + case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay"; + case CEPH_MDS_STATE_ACTIVE: return "up:active"; + case CEPH_MDS_STATE_STOPPING: return "up:stopping"; + } + return "???"; +} + +const char *ceph_session_op_name(int op) +{ + switch (op) { + case CEPH_SESSION_REQUEST_OPEN: return "request_open"; + case CEPH_SESSION_OPEN: return "open"; + case CEPH_SESSION_REQUEST_CLOSE: return "request_close"; + case CEPH_SESSION_CLOSE: return "close"; + case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps"; + case CEPH_SESSION_RENEWCAPS: return "renewcaps"; + case CEPH_SESSION_STALE: return "stale"; + case CEPH_SESSION_RECALL_STATE: return "recall_state"; + } + return "???"; +} + +const char *ceph_mds_op_name(int op) +{ + switch (op) { + case CEPH_MDS_OP_LOOKUP: return "lookup"; + case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash"; + case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent"; + case CEPH_MDS_OP_GETATTR: return "getattr"; + case CEPH_MDS_OP_SETXATTR: return "setxattr"; + case CEPH_MDS_OP_SETATTR: return "setattr"; + case CEPH_MDS_OP_RMXATTR: return "rmxattr"; + case CEPH_MDS_OP_READDIR: return "readdir"; + case CEPH_MDS_OP_MKNOD: return "mknod"; + case CEPH_MDS_OP_LINK: return "link"; + case CEPH_MDS_OP_UNLINK: return "unlink"; + case CEPH_MDS_OP_RENAME: return "rename"; + case CEPH_MDS_OP_MKDIR: return "mkdir"; + case CEPH_MDS_OP_RMDIR: return "rmdir"; + case CEPH_MDS_OP_SYMLINK: return "symlink"; + case CEPH_MDS_OP_CREATE: return "create"; + case CEPH_MDS_OP_OPEN: return "open"; + case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap"; + case CEPH_MDS_OP_LSSNAP: return "lssnap"; + case CEPH_MDS_OP_MKSNAP: return "mksnap"; + case CEPH_MDS_OP_RMSNAP: return "rmsnap"; + case CEPH_MDS_OP_SETFILELOCK: return "setfilelock"; + case CEPH_MDS_OP_GETFILELOCK: return "getfilelock"; + } + return "???"; +} + +const char *ceph_cap_op_name(int op) +{ + switch (op) { + case CEPH_CAP_OP_GRANT: return "grant"; + case CEPH_CAP_OP_REVOKE: return "revoke"; + case CEPH_CAP_OP_TRUNC: return "trunc"; + case CEPH_CAP_OP_EXPORT: return "export"; + case CEPH_CAP_OP_IMPORT: return "import"; + case CEPH_CAP_OP_UPDATE: return "update"; + case CEPH_CAP_OP_DROP: return "drop"; + case CEPH_CAP_OP_FLUSH: return "flush"; + case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack"; + case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap"; + case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack"; + case CEPH_CAP_OP_RELEASE: return "release"; + case CEPH_CAP_OP_RENEW: return "renew"; + } + return "???"; +} + +const char *ceph_lease_op_name(int o) +{ + switch (o) { + case CEPH_MDS_LEASE_REVOKE: return "revoke"; + case CEPH_MDS_LEASE_RELEASE: return "release"; + case CEPH_MDS_LEASE_RENEW: return "renew"; + case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack"; + } + return "???"; +} + +const char *ceph_snap_op_name(int o) +{ + switch (o) { + case CEPH_SNAP_OP_UPDATE: return "update"; + case CEPH_SNAP_OP_CREATE: return "create"; + case CEPH_SNAP_OP_DESTROY: return "destroy"; + case CEPH_SNAP_OP_SPLIT: return "split"; + } + return "???"; +} diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 9922628532b2..d6e0e0421891 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1,5 +1,5 @@ -#include "ceph_debug.h" +#include #include #include @@ -15,10 +15,13 @@ #include #include -#include "decode.h" #include "super.h" -#include "mon_client.h" -#include "auth.h" +#include "mds_client.h" + +#include +#include +#include +#include /* * Ceph superblock operations @@ -26,36 +29,22 @@ * Handle the basics of mounting, unmounting. */ - -/* - * find filename portion of a path (/foo/bar/baz -> baz) - */ -const char *ceph_file_part(const char *s, int len) -{ - const char *e = s + len; - - while (e != s && *(e-1) != '/') - e--; - return e; -} - - /* * super ops */ static void ceph_put_super(struct super_block *s) { - struct ceph_client *client = ceph_sb_to_client(s); + struct ceph_fs_client *fsc = ceph_sb_to_client(s); dout("put_super\n"); - ceph_mdsc_close_sessions(&client->mdsc); + ceph_mdsc_close_sessions(fsc->mdsc); /* * ensure we release the bdi before put_anon_super releases * the device name. */ - if (s->s_bdi == &client->backing_dev_info) { - bdi_unregister(&client->backing_dev_info); + if (s->s_bdi == &fsc->backing_dev_info) { + bdi_unregister(&fsc->backing_dev_info); s->s_bdi = NULL; } @@ -64,14 +53,14 @@ static void ceph_put_super(struct super_block *s) static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct ceph_client *client = ceph_inode_to_client(dentry->d_inode); - struct ceph_monmap *monmap = client->monc.monmap; + struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode); + struct ceph_monmap *monmap = fsc->client->monc.monmap; struct ceph_statfs st; u64 fsid; int err; dout("statfs\n"); - err = ceph_monc_do_statfs(&client->monc, &st); + err = ceph_monc_do_statfs(&fsc->client->monc, &st); if (err < 0) return err; @@ -104,238 +93,28 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) static int ceph_sync_fs(struct super_block *sb, int wait) { - struct ceph_client *client = ceph_sb_to_client(sb); + struct ceph_fs_client *fsc = ceph_sb_to_client(sb); if (!wait) { dout("sync_fs (non-blocking)\n"); - ceph_flush_dirty_caps(&client->mdsc); + ceph_flush_dirty_caps(fsc->mdsc); dout("sync_fs (non-blocking) done\n"); return 0; } dout("sync_fs (blocking)\n"); - ceph_osdc_sync(&ceph_sb_to_client(sb)->osdc); - ceph_mdsc_sync(&ceph_sb_to_client(sb)->mdsc); + ceph_osdc_sync(&fsc->client->osdc); + ceph_mdsc_sync(fsc->mdsc); dout("sync_fs (blocking) done\n"); return 0; } -static int default_congestion_kb(void) -{ - int congestion_kb; - - /* - * Copied from NFS - * - * congestion size, scale with available memory. - * - * 64MB: 8192k - * 128MB: 11585k - * 256MB: 16384k - * 512MB: 23170k - * 1GB: 32768k - * 2GB: 46340k - * 4GB: 65536k - * 8GB: 92681k - * 16GB: 131072k - * - * This allows larger machines to have larger/more transfers. - * Limit the default to 256M - */ - congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10); - if (congestion_kb > 256*1024) - congestion_kb = 256*1024; - - return congestion_kb; -} - -/** - * ceph_show_options - Show mount options in /proc/mounts - * @m: seq_file to write to - * @mnt: mount descriptor - */ -static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt) -{ - struct ceph_client *client = ceph_sb_to_client(mnt->mnt_sb); - struct ceph_mount_args *args = client->mount_args; - - if (args->flags & CEPH_OPT_FSID) - seq_printf(m, ",fsid=%pU", &args->fsid); - if (args->flags & CEPH_OPT_NOSHARE) - seq_puts(m, ",noshare"); - if (args->flags & CEPH_OPT_DIRSTAT) - seq_puts(m, ",dirstat"); - if ((args->flags & CEPH_OPT_RBYTES) == 0) - seq_puts(m, ",norbytes"); - if (args->flags & CEPH_OPT_NOCRC) - seq_puts(m, ",nocrc"); - if (args->flags & CEPH_OPT_NOASYNCREADDIR) - seq_puts(m, ",noasyncreaddir"); - - if (args->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) - seq_printf(m, ",mount_timeout=%d", args->mount_timeout); - if (args->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT) - seq_printf(m, ",osd_idle_ttl=%d", args->osd_idle_ttl); - if (args->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT) - seq_printf(m, ",osdtimeout=%d", args->osd_timeout); - if (args->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) - seq_printf(m, ",osdkeepalivetimeout=%d", - args->osd_keepalive_timeout); - if (args->wsize) - seq_printf(m, ",wsize=%d", args->wsize); - if (args->rsize != CEPH_MOUNT_RSIZE_DEFAULT) - seq_printf(m, ",rsize=%d", args->rsize); - if (args->congestion_kb != default_congestion_kb()) - seq_printf(m, ",write_congestion_kb=%d", args->congestion_kb); - if (args->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT) - seq_printf(m, ",caps_wanted_delay_min=%d", - args->caps_wanted_delay_min); - if (args->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT) - seq_printf(m, ",caps_wanted_delay_max=%d", - args->caps_wanted_delay_max); - if (args->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT) - seq_printf(m, ",cap_release_safety=%d", - args->cap_release_safety); - if (args->max_readdir != CEPH_MAX_READDIR_DEFAULT) - seq_printf(m, ",readdir_max_entries=%d", args->max_readdir); - if (args->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT) - seq_printf(m, ",readdir_max_bytes=%d", args->max_readdir_bytes); - if (strcmp(args->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT)) - seq_printf(m, ",snapdirname=%s", args->snapdir_name); - if (args->name) - seq_printf(m, ",name=%s", args->name); - if (args->secret) - seq_puts(m, ",secret="); - return 0; -} - -/* - * caches - */ -struct kmem_cache *ceph_inode_cachep; -struct kmem_cache *ceph_cap_cachep; -struct kmem_cache *ceph_dentry_cachep; -struct kmem_cache *ceph_file_cachep; - -static void ceph_inode_init_once(void *foo) -{ - struct ceph_inode_info *ci = foo; - inode_init_once(&ci->vfs_inode); -} - -static int __init init_caches(void) -{ - ceph_inode_cachep = kmem_cache_create("ceph_inode_info", - sizeof(struct ceph_inode_info), - __alignof__(struct ceph_inode_info), - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), - ceph_inode_init_once); - if (ceph_inode_cachep == NULL) - return -ENOMEM; - - ceph_cap_cachep = KMEM_CACHE(ceph_cap, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_cap_cachep == NULL) - goto bad_cap; - - ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_dentry_cachep == NULL) - goto bad_dentry; - - ceph_file_cachep = KMEM_CACHE(ceph_file_info, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_file_cachep == NULL) - goto bad_file; - - return 0; - -bad_file: - kmem_cache_destroy(ceph_dentry_cachep); -bad_dentry: - kmem_cache_destroy(ceph_cap_cachep); -bad_cap: - kmem_cache_destroy(ceph_inode_cachep); - return -ENOMEM; -} - -static void destroy_caches(void) -{ - kmem_cache_destroy(ceph_inode_cachep); - kmem_cache_destroy(ceph_cap_cachep); - kmem_cache_destroy(ceph_dentry_cachep); - kmem_cache_destroy(ceph_file_cachep); -} - - -/* - * ceph_umount_begin - initiate forced umount. Tear down down the - * mount, skipping steps that may hang while waiting for server(s). - */ -static void ceph_umount_begin(struct super_block *sb) -{ - struct ceph_client *client = ceph_sb_to_client(sb); - - dout("ceph_umount_begin - starting forced umount\n"); - if (!client) - return; - client->mount_state = CEPH_MOUNT_SHUTDOWN; - return; -} - -static const struct super_operations ceph_super_ops = { - .alloc_inode = ceph_alloc_inode, - .destroy_inode = ceph_destroy_inode, - .write_inode = ceph_write_inode, - .sync_fs = ceph_sync_fs, - .put_super = ceph_put_super, - .show_options = ceph_show_options, - .statfs = ceph_statfs, - .umount_begin = ceph_umount_begin, -}; - - -const char *ceph_msg_type_name(int type) -{ - switch (type) { - case CEPH_MSG_SHUTDOWN: return "shutdown"; - case CEPH_MSG_PING: return "ping"; - case CEPH_MSG_AUTH: return "auth"; - case CEPH_MSG_AUTH_REPLY: return "auth_reply"; - case CEPH_MSG_MON_MAP: return "mon_map"; - case CEPH_MSG_MON_GET_MAP: return "mon_get_map"; - case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe"; - case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack"; - case CEPH_MSG_STATFS: return "statfs"; - case CEPH_MSG_STATFS_REPLY: return "statfs_reply"; - case CEPH_MSG_MDS_MAP: return "mds_map"; - case CEPH_MSG_CLIENT_SESSION: return "client_session"; - case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect"; - case CEPH_MSG_CLIENT_REQUEST: return "client_request"; - case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward"; - case CEPH_MSG_CLIENT_REPLY: return "client_reply"; - case CEPH_MSG_CLIENT_CAPS: return "client_caps"; - case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release"; - case CEPH_MSG_CLIENT_SNAP: return "client_snap"; - case CEPH_MSG_CLIENT_LEASE: return "client_lease"; - case CEPH_MSG_OSD_MAP: return "osd_map"; - case CEPH_MSG_OSD_OP: return "osd_op"; - case CEPH_MSG_OSD_OPREPLY: return "osd_opreply"; - default: return "unknown"; - } -} - - /* * mount options */ enum { Opt_wsize, Opt_rsize, - Opt_osdtimeout, - Opt_osdkeepalivetimeout, - Opt_mount_timeout, - Opt_osd_idle_ttl, Opt_caps_wanted_delay_min, Opt_caps_wanted_delay_max, Opt_cap_release_safety, @@ -344,29 +123,19 @@ enum { Opt_congestion_kb, Opt_last_int, /* int args above */ - Opt_fsid, Opt_snapdirname, - Opt_name, - Opt_secret, Opt_last_string, /* string args above */ - Opt_ip, - Opt_noshare, Opt_dirstat, Opt_nodirstat, Opt_rbytes, Opt_norbytes, - Opt_nocrc, Opt_noasyncreaddir, }; -static match_table_t arg_tokens = { +static match_table_t fsopt_tokens = { {Opt_wsize, "wsize=%d"}, {Opt_rsize, "rsize=%d"}, - {Opt_osdtimeout, "osdtimeout=%d"}, - {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, - {Opt_mount_timeout, "mount_timeout=%d"}, - {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"}, {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"}, {Opt_cap_release_safety, "cap_release_safety=%d"}, @@ -374,403 +143,459 @@ static match_table_t arg_tokens = { {Opt_readdir_max_bytes, "readdir_max_bytes=%d"}, {Opt_congestion_kb, "write_congestion_kb=%d"}, /* int args above */ - {Opt_fsid, "fsid=%s"}, {Opt_snapdirname, "snapdirname=%s"}, - {Opt_name, "name=%s"}, - {Opt_secret, "secret=%s"}, /* string args above */ - {Opt_ip, "ip=%s"}, - {Opt_noshare, "noshare"}, {Opt_dirstat, "dirstat"}, {Opt_nodirstat, "nodirstat"}, {Opt_rbytes, "rbytes"}, {Opt_norbytes, "norbytes"}, - {Opt_nocrc, "nocrc"}, {Opt_noasyncreaddir, "noasyncreaddir"}, {-1, NULL} }; -static int parse_fsid(const char *str, struct ceph_fsid *fsid) +static int parse_fsopt_token(char *c, void *private) { - int i = 0; - char tmp[3]; - int err = -EINVAL; - int d; - - dout("parse_fsid '%s'\n", str); - tmp[2] = 0; - while (*str && i < 16) { - if (ispunct(*str)) { - str++; - continue; + struct ceph_mount_options *fsopt = private; + substring_t argstr[MAX_OPT_ARGS]; + int token, intval, ret; + + token = match_token((char *)c, fsopt_tokens, argstr); + if (token < 0) + return -EINVAL; + + if (token < Opt_last_int) { + ret = match_int(&argstr[0], &intval); + if (ret < 0) { + pr_err("bad mount option arg (not int) " + "at '%s'\n", c); + return ret; } - if (!isxdigit(str[0]) || !isxdigit(str[1])) - break; - tmp[0] = str[0]; - tmp[1] = str[1]; - if (sscanf(tmp, "%x", &d) < 1) - break; - fsid->fsid[i] = d & 0xff; - i++; - str += 2; + dout("got int token %d val %d\n", token, intval); + } else if (token > Opt_last_int && token < Opt_last_string) { + dout("got string token %d val %s\n", token, + argstr[0].from); + } else { + dout("got token %d\n", token); } - if (i == 16) - err = 0; - dout("parse_fsid ret %d got fsid %pU", err, fsid); - return err; + switch (token) { + case Opt_snapdirname: + kfree(fsopt->snapdir_name); + fsopt->snapdir_name = kstrndup(argstr[0].from, + argstr[0].to-argstr[0].from, + GFP_KERNEL); + if (!fsopt->snapdir_name) + return -ENOMEM; + break; + + /* misc */ + case Opt_wsize: + fsopt->wsize = intval; + break; + case Opt_rsize: + fsopt->rsize = intval; + break; + case Opt_caps_wanted_delay_min: + fsopt->caps_wanted_delay_min = intval; + break; + case Opt_caps_wanted_delay_max: + fsopt->caps_wanted_delay_max = intval; + break; + case Opt_readdir_max_entries: + fsopt->max_readdir = intval; + break; + case Opt_readdir_max_bytes: + fsopt->max_readdir_bytes = intval; + break; + case Opt_congestion_kb: + fsopt->congestion_kb = intval; + break; + case Opt_dirstat: + fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; + break; + case Opt_nodirstat: + fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; + break; + case Opt_rbytes: + fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; + break; + case Opt_norbytes: + fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; + break; + case Opt_noasyncreaddir: + fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; + break; + default: + BUG_ON(token); + } + return 0; } -static struct ceph_mount_args *parse_mount_args(int flags, char *options, - const char *dev_name, - const char **path) +static void destroy_mount_options(struct ceph_mount_options *args) { - struct ceph_mount_args *args; - const char *c; - int err = -ENOMEM; - substring_t argstr[MAX_OPT_ARGS]; + dout("destroy_mount_options %p\n", args); + kfree(args->snapdir_name); + kfree(args); +} - args = kzalloc(sizeof(*args), GFP_KERNEL); - if (!args) - return ERR_PTR(-ENOMEM); - args->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*args->mon_addr), - GFP_KERNEL); - if (!args->mon_addr) - goto out; +static int strcmp_null(const char *s1, const char *s2) +{ + if (!s1 && !s2) + return 0; + if (s1 && !s2) + return -1; + if (!s1 && s2) + return 1; + return strcmp(s1, s2); +} - dout("parse_mount_args %p, dev_name '%s'\n", args, dev_name); - - /* start with defaults */ - args->sb_flags = flags; - args->flags = CEPH_OPT_DEFAULT; - args->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT; - args->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; - args->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */ - args->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; /* seconds */ - args->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; - args->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; - args->rsize = CEPH_MOUNT_RSIZE_DEFAULT; - args->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); - args->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; - args->max_readdir = CEPH_MAX_READDIR_DEFAULT; - args->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; - args->congestion_kb = default_congestion_kb(); - - /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */ - err = -EINVAL; - if (!dev_name) - goto out; - *path = strstr(dev_name, ":/"); - if (*path == NULL) { - pr_err("device name is missing path (no :/ in %s)\n", - dev_name); - goto out; - } +static int compare_mount_options(struct ceph_mount_options *new_fsopt, + struct ceph_options *new_opt, + struct ceph_fs_client *fsc) +{ + struct ceph_mount_options *fsopt1 = new_fsopt; + struct ceph_mount_options *fsopt2 = fsc->mount_options; + int ofs = offsetof(struct ceph_mount_options, snapdir_name); + int ret; - /* get mon ip(s) */ - err = ceph_parse_ips(dev_name, *path, args->mon_addr, - CEPH_MAX_MON, &args->num_mon); - if (err < 0) - goto out; + ret = memcmp(fsopt1, fsopt2, ofs); + if (ret) + return ret; + + ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name); + if (ret) + return ret; + + return ceph_compare_options(new_opt, fsc->client); +} + +static int parse_mount_options(struct ceph_mount_options **pfsopt, + struct ceph_options **popt, + int flags, char *options, + const char *dev_name, + const char **path) +{ + struct ceph_mount_options *fsopt; + const char *dev_name_end; + int err = -ENOMEM; + + fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL); + if (!fsopt) + return -ENOMEM; + + dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name); + + fsopt->sb_flags = flags; + fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; + + fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT; + fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); + fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; + fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; + fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; + fsopt->congestion_kb = default_congestion_kb(); + + /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */ + err = -EINVAL; + if (!dev_name) + goto out; + *path = strstr(dev_name, ":/"); + if (*path == NULL) { + pr_err("device name is missing path (no :/ in %s)\n", + dev_name); + goto out; + } + dev_name_end = *path; + dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); /* path on server */ *path += 2; dout("server path '%s'\n", *path); - /* parse mount options */ - while ((c = strsep(&options, ",")) != NULL) { - int token, intval, ret; - if (!*c) - continue; - err = -EINVAL; - token = match_token((char *)c, arg_tokens, argstr); - if (token < 0) { - pr_err("bad mount option at '%s'\n", c); - goto out; - } - if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad mount option arg (not int) " - "at '%s'\n", c); - continue; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); - } else { - dout("got token %d\n", token); - } - switch (token) { - case Opt_ip: - err = ceph_parse_ips(argstr[0].from, - argstr[0].to, - &args->my_addr, - 1, NULL); - if (err < 0) - goto out; - args->flags |= CEPH_OPT_MYIP; - break; - - case Opt_fsid: - err = parse_fsid(argstr[0].from, &args->fsid); - if (err == 0) - args->flags |= CEPH_OPT_FSID; - break; - case Opt_snapdirname: - kfree(args->snapdir_name); - args->snapdir_name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - break; - case Opt_name: - args->name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - break; - case Opt_secret: - args->secret = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - break; - - /* misc */ - case Opt_wsize: - args->wsize = intval; - break; - case Opt_rsize: - args->rsize = intval; - break; - case Opt_osdtimeout: - args->osd_timeout = intval; - break; - case Opt_osdkeepalivetimeout: - args->osd_keepalive_timeout = intval; - break; - case Opt_osd_idle_ttl: - args->osd_idle_ttl = intval; - break; - case Opt_mount_timeout: - args->mount_timeout = intval; - break; - case Opt_caps_wanted_delay_min: - args->caps_wanted_delay_min = intval; - break; - case Opt_caps_wanted_delay_max: - args->caps_wanted_delay_max = intval; - break; - case Opt_readdir_max_entries: - args->max_readdir = intval; - break; - case Opt_readdir_max_bytes: - args->max_readdir_bytes = intval; - break; - case Opt_congestion_kb: - args->congestion_kb = intval; - break; - - case Opt_noshare: - args->flags |= CEPH_OPT_NOSHARE; - break; - - case Opt_dirstat: - args->flags |= CEPH_OPT_DIRSTAT; - break; - case Opt_nodirstat: - args->flags &= ~CEPH_OPT_DIRSTAT; - break; - case Opt_rbytes: - args->flags |= CEPH_OPT_RBYTES; - break; - case Opt_norbytes: - args->flags &= ~CEPH_OPT_RBYTES; - break; - case Opt_nocrc: - args->flags |= CEPH_OPT_NOCRC; - break; - case Opt_noasyncreaddir: - args->flags |= CEPH_OPT_NOASYNCREADDIR; - break; - - default: - BUG_ON(token); - } - } - return args; + err = ceph_parse_options(popt, options, dev_name, dev_name_end, + parse_fsopt_token, (void *)fsopt); + if (err) + goto out; + + /* success */ + *pfsopt = fsopt; + return 0; out: - kfree(args->mon_addr); - kfree(args); - return ERR_PTR(err); + destroy_mount_options(fsopt); + return err; } -static void destroy_mount_args(struct ceph_mount_args *args) +/** + * ceph_show_options - Show mount options in /proc/mounts + * @m: seq_file to write to + * @mnt: mount descriptor + */ +static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt) { - dout("destroy_mount_args %p\n", args); - kfree(args->snapdir_name); - args->snapdir_name = NULL; - kfree(args->name); - args->name = NULL; - kfree(args->secret); - args->secret = NULL; - kfree(args); + struct ceph_fs_client *fsc = ceph_sb_to_client(mnt->mnt_sb); + struct ceph_mount_options *fsopt = fsc->mount_options; + struct ceph_options *opt = fsc->client->options; + + if (opt->flags & CEPH_OPT_FSID) + seq_printf(m, ",fsid=%pU", &opt->fsid); + if (opt->flags & CEPH_OPT_NOSHARE) + seq_puts(m, ",noshare"); + if (opt->flags & CEPH_OPT_NOCRC) + seq_puts(m, ",nocrc"); + + if (opt->name) + seq_printf(m, ",name=%s", opt->name); + if (opt->secret) + seq_puts(m, ",secret="); + + if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) + seq_printf(m, ",mount_timeout=%d", opt->mount_timeout); + if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT) + seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl); + if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT) + seq_printf(m, ",osdtimeout=%d", opt->osd_timeout); + if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) + seq_printf(m, ",osdkeepalivetimeout=%d", + opt->osd_keepalive_timeout); + + if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT) + seq_puts(m, ",dirstat"); + if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0) + seq_puts(m, ",norbytes"); + if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR) + seq_puts(m, ",noasyncreaddir"); + + if (fsopt->wsize) + seq_printf(m, ",wsize=%d", fsopt->wsize); + if (fsopt->rsize != CEPH_MOUNT_RSIZE_DEFAULT) + seq_printf(m, ",rsize=%d", fsopt->rsize); + if (fsopt->congestion_kb != default_congestion_kb()) + seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb); + if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT) + seq_printf(m, ",caps_wanted_delay_min=%d", + fsopt->caps_wanted_delay_min); + if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT) + seq_printf(m, ",caps_wanted_delay_max=%d", + fsopt->caps_wanted_delay_max); + if (fsopt->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT) + seq_printf(m, ",cap_release_safety=%d", + fsopt->cap_release_safety); + if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT) + seq_printf(m, ",readdir_max_entries=%d", fsopt->max_readdir); + if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT) + seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes); + if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT)) + seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name); + return 0; } /* - * create a fresh client instance + * handle any mon messages the standard library doesn't understand. + * return error if we don't either. */ -static struct ceph_client *ceph_create_client(struct ceph_mount_args *args) +static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) { - struct ceph_client *client; + struct ceph_fs_client *fsc = client->private; + int type = le16_to_cpu(msg->hdr.type); + + switch (type) { + case CEPH_MSG_MDS_MAP: + ceph_mdsc_handle_map(fsc->mdsc, msg); + return 0; + + default: + return -1; + } +} + +/* + * create a new fs client + */ +struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, + struct ceph_options *opt) +{ + struct ceph_fs_client *fsc; int err = -ENOMEM; - client = kzalloc(sizeof(*client), GFP_KERNEL); - if (client == NULL) + fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); + if (!fsc) return ERR_PTR(-ENOMEM); - mutex_init(&client->mount_mutex); - - init_waitqueue_head(&client->auth_wq); + fsc->client = ceph_create_client(opt, fsc); + if (IS_ERR(fsc->client)) { + err = PTR_ERR(fsc->client); + goto fail; + } + fsc->client->extra_mon_dispatch = extra_mon_dispatch; + fsc->client->supported_features |= CEPH_FEATURE_FLOCK; + fsc->client->monc.want_mdsmap = 1; - client->sb = NULL; - client->mount_state = CEPH_MOUNT_MOUNTING; - client->mount_args = args; + fsc->mount_options = fsopt; - client->msgr = NULL; + fsc->sb = NULL; + fsc->mount_state = CEPH_MOUNT_MOUNTING; - client->auth_err = 0; - atomic_long_set(&client->writeback_count, 0); + atomic_long_set(&fsc->writeback_count, 0); - err = bdi_init(&client->backing_dev_info); + err = bdi_init(&fsc->backing_dev_info); if (err < 0) - goto fail; + goto fail_client; err = -ENOMEM; - client->wb_wq = create_workqueue("ceph-writeback"); - if (client->wb_wq == NULL) + fsc->wb_wq = create_workqueue("ceph-writeback"); + if (fsc->wb_wq == NULL) goto fail_bdi; - client->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid"); - if (client->pg_inv_wq == NULL) + fsc->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid"); + if (fsc->pg_inv_wq == NULL) goto fail_wb_wq; - client->trunc_wq = create_singlethread_workqueue("ceph-trunc"); - if (client->trunc_wq == NULL) + fsc->trunc_wq = create_singlethread_workqueue("ceph-trunc"); + if (fsc->trunc_wq == NULL) goto fail_pg_inv_wq; /* set up mempools */ err = -ENOMEM; - client->wb_pagevec_pool = mempool_create_kmalloc_pool(10, - client->mount_args->wsize >> PAGE_CACHE_SHIFT); - if (!client->wb_pagevec_pool) + fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, + fsc->mount_options->wsize >> PAGE_CACHE_SHIFT); + if (!fsc->wb_pagevec_pool) goto fail_trunc_wq; /* caps */ - client->min_caps = args->max_readdir; + fsc->min_caps = fsopt->max_readdir; + + return fsc; - /* subsystems */ - err = ceph_monc_init(&client->monc, client); - if (err < 0) - goto fail_mempool; - err = ceph_osdc_init(&client->osdc, client); - if (err < 0) - goto fail_monc; - err = ceph_mdsc_init(&client->mdsc, client); - if (err < 0) - goto fail_osdc; - return client; - -fail_osdc: - ceph_osdc_stop(&client->osdc); -fail_monc: - ceph_monc_stop(&client->monc); -fail_mempool: - mempool_destroy(client->wb_pagevec_pool); fail_trunc_wq: - destroy_workqueue(client->trunc_wq); + destroy_workqueue(fsc->trunc_wq); fail_pg_inv_wq: - destroy_workqueue(client->pg_inv_wq); + destroy_workqueue(fsc->pg_inv_wq); fail_wb_wq: - destroy_workqueue(client->wb_wq); + destroy_workqueue(fsc->wb_wq); fail_bdi: - bdi_destroy(&client->backing_dev_info); + bdi_destroy(&fsc->backing_dev_info); +fail_client: + ceph_destroy_client(fsc->client); fail: - kfree(client); + kfree(fsc); return ERR_PTR(err); } -static void ceph_destroy_client(struct ceph_client *client) +void destroy_fs_client(struct ceph_fs_client *fsc) { - dout("destroy_client %p\n", client); + dout("destroy_fs_client %p\n", fsc); - /* unmount */ - ceph_mdsc_stop(&client->mdsc); - ceph_osdc_stop(&client->osdc); + destroy_workqueue(fsc->wb_wq); + destroy_workqueue(fsc->pg_inv_wq); + destroy_workqueue(fsc->trunc_wq); - /* - * make sure mds and osd connections close out before destroying - * the auth module, which is needed to free those connections' - * ceph_authorizers. - */ - ceph_msgr_flush(); - - ceph_monc_stop(&client->monc); + bdi_destroy(&fsc->backing_dev_info); - ceph_debugfs_client_cleanup(client); - destroy_workqueue(client->wb_wq); - destroy_workqueue(client->pg_inv_wq); - destroy_workqueue(client->trunc_wq); + mempool_destroy(fsc->wb_pagevec_pool); - bdi_destroy(&client->backing_dev_info); + destroy_mount_options(fsc->mount_options); - if (client->msgr) - ceph_messenger_destroy(client->msgr); - mempool_destroy(client->wb_pagevec_pool); + ceph_fs_debugfs_cleanup(fsc); - destroy_mount_args(client->mount_args); + ceph_destroy_client(fsc->client); - kfree(client); - dout("destroy_client %p done\n", client); + kfree(fsc); + dout("destroy_fs_client %p done\n", fsc); } /* - * Initially learn our fsid, or verify an fsid matches. + * caches */ -int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) +struct kmem_cache *ceph_inode_cachep; +struct kmem_cache *ceph_cap_cachep; +struct kmem_cache *ceph_dentry_cachep; +struct kmem_cache *ceph_file_cachep; + +static void ceph_inode_init_once(void *foo) { - if (client->have_fsid) { - if (ceph_fsid_compare(&client->fsid, fsid)) { - pr_err("bad fsid, had %pU got %pU", - &client->fsid, fsid); - return -1; - } - } else { - pr_info("client%lld fsid %pU\n", client->monc.auth->global_id, - fsid); - memcpy(&client->fsid, fsid, sizeof(*fsid)); - ceph_debugfs_client_init(client); - client->have_fsid = true; - } + struct ceph_inode_info *ci = foo; + inode_init_once(&ci->vfs_inode); +} + +static int __init init_caches(void) +{ + ceph_inode_cachep = kmem_cache_create("ceph_inode_info", + sizeof(struct ceph_inode_info), + __alignof__(struct ceph_inode_info), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), + ceph_inode_init_once); + if (ceph_inode_cachep == NULL) + return -ENOMEM; + + ceph_cap_cachep = KMEM_CACHE(ceph_cap, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); + if (ceph_cap_cachep == NULL) + goto bad_cap; + + ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); + if (ceph_dentry_cachep == NULL) + goto bad_dentry; + + ceph_file_cachep = KMEM_CACHE(ceph_file_info, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); + if (ceph_file_cachep == NULL) + goto bad_file; + return 0; + +bad_file: + kmem_cache_destroy(ceph_dentry_cachep); +bad_dentry: + kmem_cache_destroy(ceph_cap_cachep); +bad_cap: + kmem_cache_destroy(ceph_inode_cachep); + return -ENOMEM; } +static void destroy_caches(void) +{ + kmem_cache_destroy(ceph_inode_cachep); + kmem_cache_destroy(ceph_cap_cachep); + kmem_cache_destroy(ceph_dentry_cachep); + kmem_cache_destroy(ceph_file_cachep); +} + + /* - * true if we have the mon map (and have thus joined the cluster) + * ceph_umount_begin - initiate forced umount. Tear down down the + * mount, skipping steps that may hang while waiting for server(s). */ -static int have_mon_and_osd_map(struct ceph_client *client) +static void ceph_umount_begin(struct super_block *sb) { - return client->monc.monmap && client->monc.monmap->epoch && - client->osdc.osdmap && client->osdc.osdmap->epoch; + struct ceph_fs_client *fsc = ceph_sb_to_client(sb); + + dout("ceph_umount_begin - starting forced umount\n"); + if (!fsc) + return; + fsc->mount_state = CEPH_MOUNT_SHUTDOWN; + return; } +static const struct super_operations ceph_super_ops = { + .alloc_inode = ceph_alloc_inode, + .destroy_inode = ceph_destroy_inode, + .write_inode = ceph_write_inode, + .sync_fs = ceph_sync_fs, + .put_super = ceph_put_super, + .show_options = ceph_show_options, + .statfs = ceph_statfs, + .umount_begin = ceph_umount_begin, +}; + /* * Bootstrap mount by opening the root directory. Note the mount * @started time from caller, and time out if this takes too long. */ -static struct dentry *open_root_dentry(struct ceph_client *client, +static struct dentry *open_root_dentry(struct ceph_fs_client *fsc, const char *path, unsigned long started) { - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req = NULL; int err; struct dentry *root; @@ -784,14 +609,14 @@ static struct dentry *open_root_dentry(struct ceph_client *client, req->r_ino1.ino = CEPH_INO_ROOT; req->r_ino1.snap = CEPH_NOSNAP; req->r_started = started; - req->r_timeout = client->mount_args->mount_timeout * HZ; + req->r_timeout = fsc->client->options->mount_timeout * HZ; req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE); req->r_num_caps = 2; err = ceph_mdsc_do_request(mdsc, NULL, req); if (err == 0) { dout("open_root_inode success\n"); if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT && - client->sb->s_root == NULL) + fsc->sb->s_root == NULL) root = d_alloc_root(req->r_target_inode); else root = d_obtain_alias(req->r_target_inode); @@ -804,105 +629,86 @@ static struct dentry *open_root_dentry(struct ceph_client *client, return root; } + + + /* * mount: join the ceph cluster, and open root directory. */ -static int ceph_mount(struct ceph_client *client, struct vfsmount *mnt, +static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt, const char *path) { - struct ceph_entity_addr *myaddr = NULL; int err; - unsigned long timeout = client->mount_args->mount_timeout * HZ; unsigned long started = jiffies; /* note the start time */ struct dentry *root; + int first = 0; /* first vfsmount for this super_block */ dout("mount start\n"); - mutex_lock(&client->mount_mutex); - - /* initialize the messenger */ - if (client->msgr == NULL) { - if (ceph_test_opt(client, MYIP)) - myaddr = &client->mount_args->my_addr; - client->msgr = ceph_messenger_create(myaddr); - if (IS_ERR(client->msgr)) { - err = PTR_ERR(client->msgr); - client->msgr = NULL; - goto out; - } - client->msgr->nocrc = ceph_test_opt(client, NOCRC); - } + mutex_lock(&fsc->client->mount_mutex); - /* open session, and wait for mon, mds, and osd maps */ - err = ceph_monc_open_session(&client->monc); + err = __ceph_open_session(fsc->client, started); if (err < 0) goto out; - while (!have_mon_and_osd_map(client)) { - err = -EIO; - if (timeout && time_after_eq(jiffies, started + timeout)) - goto out; - - /* wait */ - dout("mount waiting for mon_map\n"); - err = wait_event_interruptible_timeout(client->auth_wq, - have_mon_and_osd_map(client) || (client->auth_err < 0), - timeout); - if (err == -EINTR || err == -ERESTARTSYS) - goto out; - if (client->auth_err < 0) { - err = client->auth_err; - goto out; - } - } - dout("mount opening root\n"); - root = open_root_dentry(client, "", started); + root = open_root_dentry(fsc, "", started); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; } - if (client->sb->s_root) + if (fsc->sb->s_root) { dput(root); - else - client->sb->s_root = root; + } else { + fsc->sb->s_root = root; + first = 1; + + err = ceph_fs_debugfs_init(fsc); + if (err < 0) + goto fail; + } if (path[0] == 0) { dget(root); } else { dout("mount opening base mountpoint\n"); - root = open_root_dentry(client, path, started); + root = open_root_dentry(fsc, path, started); if (IS_ERR(root)) { err = PTR_ERR(root); - dput(client->sb->s_root); - client->sb->s_root = NULL; - goto out; + goto fail; } } mnt->mnt_root = root; - mnt->mnt_sb = client->sb; + mnt->mnt_sb = fsc->sb; - client->mount_state = CEPH_MOUNT_MOUNTED; + fsc->mount_state = CEPH_MOUNT_MOUNTED; dout("mount success\n"); err = 0; out: - mutex_unlock(&client->mount_mutex); + mutex_unlock(&fsc->client->mount_mutex); return err; + +fail: + if (first) { + dput(fsc->sb->s_root); + fsc->sb->s_root = NULL; + } + goto out; } static int ceph_set_super(struct super_block *s, void *data) { - struct ceph_client *client = data; + struct ceph_fs_client *fsc = data; int ret; dout("set_super %p data %p\n", s, data); - s->s_flags = client->mount_args->sb_flags; + s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */ - s->s_fs_info = client; - client->sb = s; + s->s_fs_info = fsc; + fsc->sb = s; s->s_op = &ceph_super_ops; s->s_export_op = &ceph_export_ops; @@ -917,7 +723,7 @@ static int ceph_set_super(struct super_block *s, void *data) fail: s->s_fs_info = NULL; - client->sb = NULL; + fsc->sb = NULL; return ret; } @@ -926,30 +732,23 @@ fail: */ static int ceph_compare_super(struct super_block *sb, void *data) { - struct ceph_client *new = data; - struct ceph_mount_args *args = new->mount_args; - struct ceph_client *other = ceph_sb_to_client(sb); - int i; + struct ceph_fs_client *new = data; + struct ceph_mount_options *fsopt = new->mount_options; + struct ceph_options *opt = new->client->options; + struct ceph_fs_client *other = ceph_sb_to_client(sb); dout("ceph_compare_super %p\n", sb); - if (args->flags & CEPH_OPT_FSID) { - if (ceph_fsid_compare(&args->fsid, &other->fsid)) { - dout("fsid doesn't match\n"); - return 0; - } - } else { - /* do we share (a) monitor? */ - for (i = 0; i < new->monc.monmap->num_mon; i++) - if (ceph_monmap_contains(other->monc.monmap, - &new->monc.monmap->mon_inst[i].addr)) - break; - if (i == new->monc.monmap->num_mon) { - dout("mon ip not part of monmap\n"); - return 0; - } - dout("mon ip matches existing sb %p\n", sb); + + if (compare_mount_options(fsopt, opt, other)) { + dout("monitor(s)/mount options don't match\n"); + return 0; } - if (args->sb_flags != other->mount_args->sb_flags) { + if ((opt->flags & CEPH_OPT_FSID) && + ceph_fsid_compare(&opt->fsid, &other->client->fsid)) { + dout("fsid doesn't match\n"); + return 0; + } + if (fsopt->sb_flags != other->mount_options->sb_flags) { dout("flags differ\n"); return 0; } @@ -961,19 +760,20 @@ static int ceph_compare_super(struct super_block *sb, void *data) */ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); -static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client) +static int ceph_register_bdi(struct super_block *sb, + struct ceph_fs_client *fsc) { int err; /* set ra_pages based on rsize mount option? */ - if (client->mount_args->rsize >= PAGE_CACHE_SIZE) - client->backing_dev_info.ra_pages = - (client->mount_args->rsize + PAGE_CACHE_SIZE - 1) + if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) + fsc->backing_dev_info.ra_pages = + (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_SHIFT; - err = bdi_register(&client->backing_dev_info, NULL, "ceph-%d", + err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d", atomic_long_inc_return(&bdi_seq)); if (!err) - sb->s_bdi = &client->backing_dev_info; + sb->s_bdi = &fsc->backing_dev_info; return err; } @@ -982,46 +782,52 @@ static int ceph_get_sb(struct file_system_type *fs_type, struct vfsmount *mnt) { struct super_block *sb; - struct ceph_client *client; + struct ceph_fs_client *fsc; int err; int (*compare_super)(struct super_block *, void *) = ceph_compare_super; const char *path = NULL; - struct ceph_mount_args *args; + struct ceph_mount_options *fsopt = NULL; + struct ceph_options *opt = NULL; dout("ceph_get_sb\n"); - args = parse_mount_args(flags, data, dev_name, &path); - if (IS_ERR(args)) { - err = PTR_ERR(args); + err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path); + if (err < 0) goto out_final; - } /* create client (which we may/may not use) */ - client = ceph_create_client(args); - if (IS_ERR(client)) { - err = PTR_ERR(client); + fsc = create_fs_client(fsopt, opt); + if (IS_ERR(fsc)) { + err = PTR_ERR(fsc); + kfree(fsopt); + kfree(opt); goto out_final; } - if (client->mount_args->flags & CEPH_OPT_NOSHARE) + err = ceph_mdsc_init(fsc); + if (err < 0) + goto out; + + if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; - sb = sget(fs_type, compare_super, ceph_set_super, client); + sb = sget(fs_type, compare_super, ceph_set_super, fsc); if (IS_ERR(sb)) { err = PTR_ERR(sb); goto out; } - if (ceph_sb_to_client(sb) != client) { - ceph_destroy_client(client); - client = ceph_sb_to_client(sb); - dout("get_sb got existing client %p\n", client); + if (ceph_sb_to_client(sb) != fsc) { + ceph_mdsc_destroy(fsc); + destroy_fs_client(fsc); + fsc = ceph_sb_to_client(sb); + dout("get_sb got existing client %p\n", fsc); } else { - dout("get_sb using new client %p\n", client); - err = ceph_register_bdi(sb, client); + dout("get_sb using new client %p\n", fsc); + err = ceph_register_bdi(sb, fsc); if (err < 0) goto out_splat; } - err = ceph_mount(client, mnt, path); + err = ceph_mount(fsc, mnt, path); if (err < 0) goto out_splat; dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root, @@ -1029,12 +835,13 @@ static int ceph_get_sb(struct file_system_type *fs_type, return 0; out_splat: - ceph_mdsc_close_sessions(&client->mdsc); + ceph_mdsc_close_sessions(fsc->mdsc); deactivate_locked_super(sb); goto out_final; out: - ceph_destroy_client(client); + ceph_mdsc_destroy(fsc); + destroy_fs_client(fsc); out_final: dout("ceph_get_sb fail %d\n", err); return err; @@ -1042,11 +849,12 @@ out_final: static void ceph_kill_sb(struct super_block *s) { - struct ceph_client *client = ceph_sb_to_client(s); + struct ceph_fs_client *fsc = ceph_sb_to_client(s); dout("kill_sb %p\n", s); - ceph_mdsc_pre_umount(&client->mdsc); + ceph_mdsc_pre_umount(fsc->mdsc); kill_anon_super(s); /* will call put_super after sb is r/o */ - ceph_destroy_client(client); + ceph_mdsc_destroy(fsc); + destroy_fs_client(fsc); } static struct file_system_type ceph_fs_type = { @@ -1062,36 +870,20 @@ static struct file_system_type ceph_fs_type = { static int __init init_ceph(void) { - int ret = 0; - - ret = ceph_debugfs_init(); - if (ret < 0) - goto out; - - ret = ceph_msgr_init(); - if (ret < 0) - goto out_debugfs; - - ret = init_caches(); + int ret = init_caches(); if (ret) - goto out_msgr; + goto out; ret = register_filesystem(&ceph_fs_type); if (ret) goto out_icache; - pr_info("loaded (mon/mds/osd proto %d/%d/%d, osdmap %d/%d %d/%d)\n", - CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL, - CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT, - CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT); + pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL); + return 0; out_icache: destroy_caches(); -out_msgr: - ceph_msgr_exit(); -out_debugfs: - ceph_debugfs_cleanup(); out: return ret; } @@ -1101,8 +893,6 @@ static void __exit exit_ceph(void) dout("exit_ceph\n"); unregister_filesystem(&ceph_fs_type); destroy_caches(); - ceph_msgr_exit(); - ceph_debugfs_cleanup(); } module_init(init_ceph); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b87638e84c4b..e2e904442ce2 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1,7 +1,7 @@ #ifndef _FS_CEPH_SUPER_H #define _FS_CEPH_SUPER_H -#include "ceph_debug.h" +#include #include #include @@ -14,13 +14,7 @@ #include #include -#include "types.h" -#include "messenger.h" -#include "msgpool.h" -#include "mon_client.h" -#include "mds_client.h" -#include "osd_client.h" -#include "ceph_fs.h" +#include /* f_type in struct statfs */ #define CEPH_SUPER_MAGIC 0x00c36400 @@ -30,42 +24,25 @@ #define CEPH_BLOCK_SHIFT 20 /* 1 MB */ #define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT) -/* - * Supported features - */ -#define CEPH_FEATURE_SUPPORTED CEPH_FEATURE_NOSRCADDR | CEPH_FEATURE_FLOCK -#define CEPH_FEATURE_REQUIRED CEPH_FEATURE_NOSRCADDR +#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */ +#define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */ +#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */ -/* - * mount options - */ -#define CEPH_OPT_FSID (1<<0) -#define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ -#define CEPH_OPT_MYIP (1<<2) /* specified my ip */ -#define CEPH_OPT_DIRSTAT (1<<4) /* funky `cat dirname` for stats */ -#define CEPH_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */ -#define CEPH_OPT_NOCRC (1<<6) /* no data crc on writes */ -#define CEPH_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */ +#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES) -#define CEPH_OPT_DEFAULT (CEPH_OPT_RBYTES) +#define ceph_set_mount_opt(fsc, opt) \ + (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt; +#define ceph_test_mount_opt(fsc, opt) \ + (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) -#define ceph_set_opt(client, opt) \ - (client)->mount_args->flags |= CEPH_OPT_##opt; -#define ceph_test_opt(client, opt) \ - (!!((client)->mount_args->flags & CEPH_OPT_##opt)) +#define CEPH_MAX_READDIR_DEFAULT 1024 +#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) +#define CEPH_SNAPDIRNAME_DEFAULT ".snap" - -struct ceph_mount_args { - int sb_flags; +struct ceph_mount_options { int flags; - struct ceph_fsid fsid; - struct ceph_entity_addr my_addr; - int num_mon; - struct ceph_entity_addr *mon_addr; - int mount_timeout; - int osd_idle_ttl; - int osd_timeout; - int osd_keepalive_timeout; + int sb_flags; + int wsize; int rsize; /* max readahead */ int congestion_kb; /* max writeback in flight */ @@ -73,82 +50,25 @@ struct ceph_mount_args { int cap_release_safety; int max_readdir; /* max readdir result (entires) */ int max_readdir_bytes; /* max readdir result (bytes) */ - char *snapdir_name; /* default ".snap" */ - char *name; - char *secret; -}; - -/* - * defaults - */ -#define CEPH_MOUNT_TIMEOUT_DEFAULT 60 -#define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */ -#define CEPH_OSD_KEEPALIVE_DEFAULT 5 -#define CEPH_OSD_IDLE_TTL_DEFAULT 60 -#define CEPH_MOUNT_RSIZE_DEFAULT (512*1024) /* readahead */ -#define CEPH_MAX_READDIR_DEFAULT 1024 -#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) - -#define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) - -#define CEPH_SNAPDIRNAME_DEFAULT ".snap" -#define CEPH_AUTH_NAME_DEFAULT "guest" -/* - * Delay telling the MDS we no longer want caps, in case we reopen - * the file. Delay a minimum amount of time, even if we send a cap - * message for some other reason. Otherwise, take the oppotunity to - * update the mds to avoid sending another message later. - */ -#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ -#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ - -#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4) - -/* mount state */ -enum { - CEPH_MOUNT_MOUNTING, - CEPH_MOUNT_MOUNTED, - CEPH_MOUNT_UNMOUNTING, - CEPH_MOUNT_UNMOUNTED, - CEPH_MOUNT_SHUTDOWN, -}; -/* - * subtract jiffies - */ -static inline unsigned long time_sub(unsigned long a, unsigned long b) -{ - BUG_ON(time_after(b, a)); - return (long)a - (long)b; -} - -/* - * per-filesystem client state - * - * possibly shared by multiple mount points, if they are - * mounting the same ceph filesystem/cluster. - */ -struct ceph_client { - struct ceph_fsid fsid; - bool have_fsid; + /* + * everything above this point can be memcmp'd; everything below + * is handled in compare_mount_options() + */ - struct mutex mount_mutex; /* serialize mount attempts */ - struct ceph_mount_args *mount_args; + char *snapdir_name; /* default ".snap" */ +}; +struct ceph_fs_client { struct super_block *sb; - unsigned long mount_state; - wait_queue_head_t auth_wq; - - int auth_err; + struct ceph_mount_options *mount_options; + struct ceph_client *client; + unsigned long mount_state; int min_caps; /* min caps i added */ - struct ceph_messenger *msgr; /* messenger instance */ - struct ceph_mon_client monc; - struct ceph_mds_client mdsc; - struct ceph_osd_client osdc; + struct ceph_mds_client *mdsc; /* writeback */ mempool_t *wb_pagevec_pool; @@ -160,14 +80,14 @@ struct ceph_client { struct backing_dev_info backing_dev_info; #ifdef CONFIG_DEBUG_FS - struct dentry *debugfs_monmap; - struct dentry *debugfs_mdsmap, *debugfs_osdmap; - struct dentry *debugfs_dir, *debugfs_dentry_lru, *debugfs_caps; + struct dentry *debugfs_dentry_lru, *debugfs_caps; struct dentry *debugfs_congestion_kb; struct dentry *debugfs_bdi; + struct dentry *debugfs_mdsc, *debugfs_mdsmap; #endif }; + /* * File i/o capability. This tracks shared state with the metadata * server that allows us to cache or writeback attributes or to read @@ -275,6 +195,20 @@ struct ceph_inode_xattr { int should_free_val; }; +/* + * Ceph dentry state + */ +struct ceph_dentry_info { + struct ceph_mds_session *lease_session; + u32 lease_gen, lease_shared_gen; + u32 lease_seq; + unsigned long lease_renew_after, lease_renew_from; + struct list_head lru; + struct dentry *dentry; + u64 time; + u64 offset; +}; + struct ceph_inode_xattrs_info { /* * (still encoded) xattr blob. we avoid the overhead of parsing @@ -296,11 +230,6 @@ struct ceph_inode_xattrs_info { /* * Ceph inode. */ -#define CEPH_I_COMPLETE 1 /* we have complete directory cached */ -#define CEPH_I_NODELAY 4 /* do not delay cap release */ -#define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */ -#define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */ - struct ceph_inode_info { struct ceph_vino i_vino; /* ceph ino + snap */ @@ -391,6 +320,63 @@ static inline struct ceph_inode_info *ceph_inode(struct inode *inode) return container_of(inode, struct ceph_inode_info, vfs_inode); } +static inline struct ceph_vino ceph_vino(struct inode *inode) +{ + return ceph_inode(inode)->i_vino; +} + +/* + * ino_t is <64 bits on many architectures, blech. + * + * don't include snap in ino hash, at least for now. + */ +static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) +{ + ino_t ino = (ino_t)vino.ino; /* ^ (vino.snap << 20); */ +#if BITS_PER_LONG == 32 + ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8; + if (!ino) + ino = 1; +#endif + return ino; +} + +/* for printf-style formatting */ +#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap + +static inline u64 ceph_ino(struct inode *inode) +{ + return ceph_inode(inode)->i_vino.ino; +} +static inline u64 ceph_snap(struct inode *inode) +{ + return ceph_inode(inode)->i_vino.snap; +} + +static inline int ceph_ino_compare(struct inode *inode, void *data) +{ + struct ceph_vino *pvino = (struct ceph_vino *)data; + struct ceph_inode_info *ci = ceph_inode(inode); + return ci->i_vino.ino == pvino->ino && + ci->i_vino.snap == pvino->snap; +} + +static inline struct inode *ceph_find_inode(struct super_block *sb, + struct ceph_vino vino) +{ + ino_t t = ceph_vino_to_ino(vino); + return ilookup5(sb, t, ceph_ino_compare, &vino); +} + + +/* + * Ceph inode. + */ +#define CEPH_I_COMPLETE 1 /* we have complete directory cached */ +#define CEPH_I_NODELAY 4 /* do not delay cap release */ +#define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */ +#define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */ + static inline void ceph_i_clear(struct inode *inode, unsigned mask) { struct ceph_inode_info *ci = ceph_inode(inode); @@ -432,20 +418,6 @@ extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, struct ceph_inode_frag *pfrag, int *found); -/* - * Ceph dentry state - */ -struct ceph_dentry_info { - struct ceph_mds_session *lease_session; - u32 lease_gen, lease_shared_gen; - u32 lease_seq; - unsigned long lease_renew_after, lease_renew_from; - struct list_head lru; - struct dentry *dentry; - u64 time; - u64 offset; -}; - static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry) { return (struct ceph_dentry_info *)dentry->d_fsdata; @@ -456,22 +428,6 @@ static inline loff_t ceph_make_fpos(unsigned frag, unsigned off) return ((loff_t)frag << 32) | (loff_t)off; } -/* - * ino_t is <64 bits on many architectures, blech. - * - * don't include snap in ino hash, at least for now. - */ -static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) -{ - ino_t ino = (ino_t)vino.ino; /* ^ (vino.snap << 20); */ -#if BITS_PER_LONG == 32 - ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8; - if (!ino) - ino = 1; -#endif - return ino; -} - static inline int ceph_set_ino_cb(struct inode *inode, void *data) { ceph_inode(inode)->i_vino = *(struct ceph_vino *)data; @@ -479,39 +435,6 @@ static inline int ceph_set_ino_cb(struct inode *inode, void *data) return 0; } -static inline struct ceph_vino ceph_vino(struct inode *inode) -{ - return ceph_inode(inode)->i_vino; -} - -/* for printf-style formatting */ -#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap - -static inline u64 ceph_ino(struct inode *inode) -{ - return ceph_inode(inode)->i_vino.ino; -} -static inline u64 ceph_snap(struct inode *inode) -{ - return ceph_inode(inode)->i_vino.snap; -} - -static inline int ceph_ino_compare(struct inode *inode, void *data) -{ - struct ceph_vino *pvino = (struct ceph_vino *)data; - struct ceph_inode_info *ci = ceph_inode(inode); - return ci->i_vino.ino == pvino->ino && - ci->i_vino.snap == pvino->snap; -} - -static inline struct inode *ceph_find_inode(struct super_block *sb, - struct ceph_vino vino) -{ - ino_t t = ceph_vino_to_ino(vino); - return ilookup5(sb, t, ceph_ino_compare, &vino); -} - - /* * caps helpers */ @@ -576,18 +499,18 @@ extern int ceph_reserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx, int need); extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); -extern void ceph_reservation_status(struct ceph_client *client, +extern void ceph_reservation_status(struct ceph_fs_client *client, int *total, int *avail, int *used, int *reserved, int *min); -static inline struct ceph_client *ceph_inode_to_client(struct inode *inode) +static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode) { - return (struct ceph_client *)inode->i_sb->s_fs_info; + return (struct ceph_fs_client *)inode->i_sb->s_fs_info; } -static inline struct ceph_client *ceph_sb_to_client(struct super_block *sb) +static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb) { - return (struct ceph_client *)sb->s_fs_info; + return (struct ceph_fs_client *)sb->s_fs_info; } @@ -616,51 +539,6 @@ struct ceph_file_info { -/* - * snapshots - */ - -/* - * A "snap context" is the set of existing snapshots when we - * write data. It is used by the OSD to guide its COW behavior. - * - * The ceph_snap_context is refcounted, and attached to each dirty - * page, indicating which context the dirty data belonged when it was - * dirtied. - */ -struct ceph_snap_context { - atomic_t nref; - u64 seq; - int num_snaps; - u64 snaps[]; -}; - -static inline struct ceph_snap_context * -ceph_get_snap_context(struct ceph_snap_context *sc) -{ - /* - printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)+1); - */ - if (sc) - atomic_inc(&sc->nref); - return sc; -} - -static inline void ceph_put_snap_context(struct ceph_snap_context *sc) -{ - if (!sc) - return; - /* - printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)-1); - */ - if (atomic_dec_and_test(&sc->nref)) { - /*printk(" deleting snap_context %p\n", sc);*/ - kfree(sc); - } -} - /* * A "snap realm" describes a subset of the file hierarchy sharing * the same set of snapshots that apply to it. The realms themselves @@ -699,16 +577,33 @@ struct ceph_snap_realm { spinlock_t inodes_with_caps_lock; }; - - -/* - * calculate the number of pages a given length and offset map onto, - * if we align the data. - */ -static inline int calc_pages_for(u64 off, u64 len) +static inline int default_congestion_kb(void) { - return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - - (off >> PAGE_CACHE_SHIFT); + int congestion_kb; + + /* + * Copied from NFS + * + * congestion size, scale with available memory. + * + * 64MB: 8192k + * 128MB: 11585k + * 256MB: 16384k + * 512MB: 23170k + * 1GB: 32768k + * 2GB: 46340k + * 4GB: 65536k + * 8GB: 92681k + * 16GB: 131072k + * + * This allows larger machines to have larger/more transfers. + * Limit the default to 256M + */ + congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10); + if (congestion_kb > 256*1024) + congestion_kb = 256*1024; + + return congestion_kb; } @@ -741,16 +636,6 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci) ci_item)->writing; } - -/* super.c */ -extern struct kmem_cache *ceph_inode_cachep; -extern struct kmem_cache *ceph_cap_cachep; -extern struct kmem_cache *ceph_dentry_cachep; -extern struct kmem_cache *ceph_file_cachep; - -extern const char *ceph_msg_type_name(int type); -extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); - /* inode.c */ extern const struct inode_operations ceph_file_iops; @@ -857,12 +742,18 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); /* file.c */ extern const struct file_operations ceph_file_fops; extern const struct address_space_operations ceph_aops; +extern int ceph_copy_to_page_vector(struct page **pages, + const char *data, + loff_t off, size_t len); +extern int ceph_copy_from_page_vector(struct page **pages, + char *data, + loff_t off, size_t len); +extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_open(struct inode *inode, struct file *file); extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd, int mode, int locked_dir); extern int ceph_release(struct inode *inode, struct file *filp); -extern void ceph_release_page_vector(struct page **pages, int num_pages); /* dir.c */ extern const struct file_operations ceph_dir_fops; @@ -892,12 +783,6 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* export.c */ extern const struct export_operations ceph_export_ops; -/* debugfs.c */ -extern int ceph_debugfs_init(void); -extern void ceph_debugfs_cleanup(void); -extern int ceph_debugfs_client_init(struct ceph_client *client); -extern void ceph_debugfs_client_cleanup(struct ceph_client *client); - /* locks.c */ extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl); extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl); @@ -914,4 +799,8 @@ static inline struct inode *get_dentry_parent_inode(struct dentry *dentry) return NULL; } +/* debugfs.c */ +extern int ceph_fs_debugfs_init(struct ceph_fs_client *client); +extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client); + #endif /* _FS_CEPH_SUPER_H */ diff --git a/fs/ceph/types.h b/fs/ceph/types.h deleted file mode 100644 index 28b35a005ec2..000000000000 --- a/fs/ceph/types.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef _FS_CEPH_TYPES_H -#define _FS_CEPH_TYPES_H - -/* needed before including ceph_fs.h */ -#include -#include -#include -#include - -#include "ceph_fs.h" -#include "ceph_frag.h" -#include "ceph_hash.h" - -/* - * Identify inodes by both their ino AND snapshot id (a u64). - */ -struct ceph_vino { - u64 ino; - u64 snap; -}; - - -/* context for the caps reservation mechanism */ -struct ceph_cap_reservation { - int count; -}; - - -#endif diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 9578af610b73..70e919960acb 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1,6 +1,9 @@ -#include "ceph_debug.h" +#include + #include "super.h" -#include "decode.h" +#include "mds_client.h" + +#include #include #include @@ -620,12 +623,12 @@ out: static int ceph_sync_setxattr(struct dentry *dentry, const char *name, const char *value, size_t size, int flags) { - struct ceph_client *client = ceph_sb_to_client(dentry->d_sb); + struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); struct inode *inode = dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); struct inode *parent_inode = dentry->d_parent->d_inode; struct ceph_mds_request *req; - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_mds_client *mdsc = fsc->mdsc; int err; int i, nr_pages; struct page **pages = NULL; @@ -777,8 +780,8 @@ out: static int ceph_send_removexattr(struct dentry *dentry, const char *name) { - struct ceph_client *client = ceph_sb_to_client(dentry->d_sb); - struct ceph_mds_client *mdsc = &client->mdsc; + struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = dentry->d_inode; struct inode *parent_inode = dentry->d_parent->d_inode; struct ceph_mds_request *req; diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h new file mode 100644 index 000000000000..7fff521d7eb5 --- /dev/null +++ b/include/linux/ceph/auth.h @@ -0,0 +1,92 @@ +#ifndef _FS_CEPH_AUTH_H +#define _FS_CEPH_AUTH_H + +#include +#include + +/* + * Abstract interface for communicating with the authenticate module. + * There is some handshake that takes place between us and the monitor + * to acquire the necessary keys. These are used to generate an + * 'authorizer' that we use when connecting to a service (mds, osd). + */ + +struct ceph_auth_client; +struct ceph_authorizer; + +struct ceph_auth_client_ops { + const char *name; + + /* + * true if we are authenticated and can connect to + * services. + */ + int (*is_authenticated)(struct ceph_auth_client *ac); + + /* + * true if we should (re)authenticate, e.g., when our tickets + * are getting old and crusty. + */ + int (*should_authenticate)(struct ceph_auth_client *ac); + + /* + * build requests and process replies during monitor + * handshake. if handle_reply returns -EAGAIN, we build + * another request. + */ + int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end); + int (*handle_reply)(struct ceph_auth_client *ac, int result, + void *buf, void *end); + + /* + * Create authorizer for connecting to a service, and verify + * the response to authenticate the service. + */ + int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type, + struct ceph_authorizer **a, + void **buf, size_t *len, + void **reply_buf, size_t *reply_len); + int (*verify_authorizer_reply)(struct ceph_auth_client *ac, + struct ceph_authorizer *a, size_t len); + void (*destroy_authorizer)(struct ceph_auth_client *ac, + struct ceph_authorizer *a); + void (*invalidate_authorizer)(struct ceph_auth_client *ac, + int peer_type); + + /* reset when we (re)connect to a monitor */ + void (*reset)(struct ceph_auth_client *ac); + + void (*destroy)(struct ceph_auth_client *ac); +}; + +struct ceph_auth_client { + u32 protocol; /* CEPH_AUTH_* */ + void *private; /* for use by protocol implementation */ + const struct ceph_auth_client_ops *ops; /* null iff protocol==0 */ + + bool negotiating; /* true if negotiating protocol */ + const char *name; /* entity name */ + u64 global_id; /* our unique id in system */ + const char *secret; /* our secret key */ + unsigned want_keys; /* which services we want */ +}; + +extern struct ceph_auth_client *ceph_auth_init(const char *name, + const char *secret); +extern void ceph_auth_destroy(struct ceph_auth_client *ac); + +extern void ceph_auth_reset(struct ceph_auth_client *ac); + +extern int ceph_auth_build_hello(struct ceph_auth_client *ac, + void *buf, size_t len); +extern int ceph_handle_auth_reply(struct ceph_auth_client *ac, + void *buf, size_t len, + void *reply_buf, size_t reply_len); +extern int ceph_entity_name_encode(const char *name, void **p, void *end); + +extern int ceph_build_auth(struct ceph_auth_client *ac, + void *msg_buf, size_t msg_len); + +extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); + +#endif diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h new file mode 100644 index 000000000000..58d19014068f --- /dev/null +++ b/include/linux/ceph/buffer.h @@ -0,0 +1,39 @@ +#ifndef __FS_CEPH_BUFFER_H +#define __FS_CEPH_BUFFER_H + +#include +#include +#include +#include +#include + +/* + * a simple reference counted buffer. + * + * use kmalloc for small sizes (<= one page), vmalloc for larger + * sizes. + */ +struct ceph_buffer { + struct kref kref; + struct kvec vec; + size_t alloc_len; + bool is_vmalloc; +}; + +extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp); +extern void ceph_buffer_release(struct kref *kref); + +static inline struct ceph_buffer *ceph_buffer_get(struct ceph_buffer *b) +{ + kref_get(&b->kref); + return b; +} + +static inline void ceph_buffer_put(struct ceph_buffer *b) +{ + kref_put(&b->kref, ceph_buffer_release); +} + +extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end); + +#endif diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h new file mode 100644 index 000000000000..aa2e19182d99 --- /dev/null +++ b/include/linux/ceph/ceph_debug.h @@ -0,0 +1,38 @@ +#ifndef _FS_CEPH_DEBUG_H +#define _FS_CEPH_DEBUG_H + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG + +/* + * wrap pr_debug to include a filename:lineno prefix on each line. + * this incurs some overhead (kernel size and execution time) due to + * the extra function call at each call site. + */ + +# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) +extern const char *ceph_file_part(const char *s, int len); +# define dout(fmt, ...) \ + pr_debug("%.*s %12.12s:%-4d : " fmt, \ + 8 - (int)sizeof(KBUILD_MODNAME), " ", \ + ceph_file_part(__FILE__, sizeof(__FILE__)), \ + __LINE__, ##__VA_ARGS__) +# else +/* faux printk call just to see any compiler warnings. */ +# define dout(fmt, ...) do { \ + if (0) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + } while (0) +# endif + +#else + +/* + * or, just wrap pr_debug + */ +# define dout(fmt, ...) pr_debug(" " fmt, ##__VA_ARGS__) + +#endif + +#endif diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h new file mode 100644 index 000000000000..5babb8e95352 --- /dev/null +++ b/include/linux/ceph/ceph_frag.h @@ -0,0 +1,109 @@ +#ifndef FS_CEPH_FRAG_H +#define FS_CEPH_FRAG_H + +/* + * "Frags" are a way to describe a subset of a 32-bit number space, + * using a mask and a value to match against that mask. Any given frag + * (subset of the number space) can be partitioned into 2^n sub-frags. + * + * Frags are encoded into a 32-bit word: + * 8 upper bits = "bits" + * 24 lower bits = "value" + * (We could go to 5+27 bits, but who cares.) + * + * We use the _most_ significant bits of the 24 bit value. This makes + * values logically sort. + * + * Unfortunately, because the "bits" field is still in the high bits, we + * can't sort encoded frags numerically. However, it does allow you + * to feed encoded frags as values into frag_contains_value. + */ +static inline __u32 ceph_frag_make(__u32 b, __u32 v) +{ + return (b << 24) | + (v & (0xffffffu << (24-b)) & 0xffffffu); +} +static inline __u32 ceph_frag_bits(__u32 f) +{ + return f >> 24; +} +static inline __u32 ceph_frag_value(__u32 f) +{ + return f & 0xffffffu; +} +static inline __u32 ceph_frag_mask(__u32 f) +{ + return (0xffffffu << (24-ceph_frag_bits(f))) & 0xffffffu; +} +static inline __u32 ceph_frag_mask_shift(__u32 f) +{ + return 24 - ceph_frag_bits(f); +} + +static inline int ceph_frag_contains_value(__u32 f, __u32 v) +{ + return (v & ceph_frag_mask(f)) == ceph_frag_value(f); +} +static inline int ceph_frag_contains_frag(__u32 f, __u32 sub) +{ + /* is sub as specific as us, and contained by us? */ + return ceph_frag_bits(sub) >= ceph_frag_bits(f) && + (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f); +} + +static inline __u32 ceph_frag_parent(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f) - 1, + ceph_frag_value(f) & (ceph_frag_mask(f) << 1)); +} +static inline int ceph_frag_is_left_child(__u32 f) +{ + return ceph_frag_bits(f) > 0 && + (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0; +} +static inline int ceph_frag_is_right_child(__u32 f) +{ + return ceph_frag_bits(f) > 0 && + (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1; +} +static inline __u32 ceph_frag_sibling(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f), + ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f))); +} +static inline __u32 ceph_frag_left_child(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f)); +} +static inline __u32 ceph_frag_right_child(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f)+1, + ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f)))); +} +static inline __u32 ceph_frag_make_child(__u32 f, int by, int i) +{ + int newbits = ceph_frag_bits(f) + by; + return ceph_frag_make(newbits, + ceph_frag_value(f) | (i << (24 - newbits))); +} +static inline int ceph_frag_is_leftmost(__u32 f) +{ + return ceph_frag_value(f) == 0; +} +static inline int ceph_frag_is_rightmost(__u32 f) +{ + return ceph_frag_value(f) == ceph_frag_mask(f); +} +static inline __u32 ceph_frag_next(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f), + ceph_frag_value(f) + (0x1000000 >> ceph_frag_bits(f))); +} + +/* + * comparator to sort frags logically, as when traversing the + * number space in ascending order... + */ +int ceph_frag_compare(__u32 a, __u32 b); + +#endif diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h new file mode 100644 index 000000000000..d5619ac86711 --- /dev/null +++ b/include/linux/ceph/ceph_fs.h @@ -0,0 +1,728 @@ +/* + * ceph_fs.h - Ceph constants and data types to share between kernel and + * user space. + * + * Most types in this file are defined as little-endian, and are + * primarily intended to describe data structures that pass over the + * wire or that are stored on disk. + * + * LGPL2 + */ + +#ifndef CEPH_FS_H +#define CEPH_FS_H + +#include "msgr.h" +#include "rados.h" + +/* + * subprotocol versions. when specific messages types or high-level + * protocols change, bump the affected components. we keep rev + * internal cluster protocols separately from the public, + * client-facing protocol. + */ +#define CEPH_OSD_PROTOCOL 8 /* cluster internal */ +#define CEPH_MDS_PROTOCOL 12 /* cluster internal */ +#define CEPH_MON_PROTOCOL 5 /* cluster internal */ +#define CEPH_OSDC_PROTOCOL 24 /* server/client */ +#define CEPH_MDSC_PROTOCOL 32 /* server/client */ +#define CEPH_MONC_PROTOCOL 15 /* server/client */ + + +#define CEPH_INO_ROOT 1 +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ + +/* arbitrary limit on max # of monitors (cluster of 3 is typical) */ +#define CEPH_MAX_MON 31 + + +/* + * feature bits + */ +#define CEPH_FEATURE_UID (1<<0) +#define CEPH_FEATURE_NOSRCADDR (1<<1) +#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) +#define CEPH_FEATURE_FLOCK (1<<3) + + +/* + * ceph_file_layout - describe data layout for a file/inode + */ +struct ceph_file_layout { + /* file -> object mapping */ + __le32 fl_stripe_unit; /* stripe unit, in bytes. must be multiple + of page size. */ + __le32 fl_stripe_count; /* over this many objects */ + __le32 fl_object_size; /* until objects are this big, then move to + new objects */ + __le32 fl_cas_hash; /* 0 = none; 1 = sha256 */ + + /* pg -> disk layout */ + __le32 fl_object_stripe_unit; /* for per-object parity, if any */ + + /* object -> pg layout */ + __le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */ + __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ +} __attribute__ ((packed)); + +#define CEPH_MIN_STRIPE_UNIT 65536 + +int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); + + +/* crypto algorithms */ +#define CEPH_CRYPTO_NONE 0x0 +#define CEPH_CRYPTO_AES 0x1 + +#define CEPH_AES_IV "cephsageyudagreg" + +/* security/authentication protocols */ +#define CEPH_AUTH_UNKNOWN 0x0 +#define CEPH_AUTH_NONE 0x1 +#define CEPH_AUTH_CEPHX 0x2 + +#define CEPH_AUTH_UID_DEFAULT ((__u64) -1) + + +/********************************************* + * message layer + */ + +/* + * message types + */ + +/* misc */ +#define CEPH_MSG_SHUTDOWN 1 +#define CEPH_MSG_PING 2 + +/* client <-> monitor */ +#define CEPH_MSG_MON_MAP 4 +#define CEPH_MSG_MON_GET_MAP 5 +#define CEPH_MSG_STATFS 13 +#define CEPH_MSG_STATFS_REPLY 14 +#define CEPH_MSG_MON_SUBSCRIBE 15 +#define CEPH_MSG_MON_SUBSCRIBE_ACK 16 +#define CEPH_MSG_AUTH 17 +#define CEPH_MSG_AUTH_REPLY 18 + +/* client <-> mds */ +#define CEPH_MSG_MDS_MAP 21 + +#define CEPH_MSG_CLIENT_SESSION 22 +#define CEPH_MSG_CLIENT_RECONNECT 23 + +#define CEPH_MSG_CLIENT_REQUEST 24 +#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25 +#define CEPH_MSG_CLIENT_REPLY 26 +#define CEPH_MSG_CLIENT_CAPS 0x310 +#define CEPH_MSG_CLIENT_LEASE 0x311 +#define CEPH_MSG_CLIENT_SNAP 0x312 +#define CEPH_MSG_CLIENT_CAPRELEASE 0x313 + +/* pool ops */ +#define CEPH_MSG_POOLOP_REPLY 48 +#define CEPH_MSG_POOLOP 49 + + +/* osd */ +#define CEPH_MSG_OSD_MAP 41 +#define CEPH_MSG_OSD_OP 42 +#define CEPH_MSG_OSD_OPREPLY 43 + +/* pool operations */ +enum { + POOL_OP_CREATE = 0x01, + POOL_OP_DELETE = 0x02, + POOL_OP_AUID_CHANGE = 0x03, + POOL_OP_CREATE_SNAP = 0x11, + POOL_OP_DELETE_SNAP = 0x12, + POOL_OP_CREATE_UNMANAGED_SNAP = 0x21, + POOL_OP_DELETE_UNMANAGED_SNAP = 0x22, +}; + +struct ceph_mon_request_header { + __le64 have_version; + __le16 session_mon; + __le64 session_mon_tid; +} __attribute__ ((packed)); + +struct ceph_mon_statfs { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +struct ceph_statfs { + __le64 kb, kb_used, kb_avail; + __le64 num_objects; +} __attribute__ ((packed)); + +struct ceph_mon_statfs_reply { + struct ceph_fsid fsid; + __le64 version; + struct ceph_statfs st; +} __attribute__ ((packed)); + +const char *ceph_pool_op_name(int op); + +struct ceph_mon_poolop { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 pool; + __le32 op; + __le64 auid; + __le64 snapid; + __le32 name_len; +} __attribute__ ((packed)); + +struct ceph_mon_poolop_reply { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 reply_code; + __le32 epoch; + char has_data; + char data[0]; +} __attribute__ ((packed)); + +struct ceph_mon_unmanaged_snap { + __le64 snapid; +} __attribute__ ((packed)); + +struct ceph_osd_getmap { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 start; +} __attribute__ ((packed)); + +struct ceph_mds_getmap { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +struct ceph_client_mount { + struct ceph_mon_request_header monhdr; +} __attribute__ ((packed)); + +struct ceph_mon_subscribe_item { + __le64 have_version; __le64 have; + __u8 onetime; +} __attribute__ ((packed)); + +struct ceph_mon_subscribe_ack { + __le32 duration; /* seconds */ + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +/* + * mds states + * > 0 -> in + * <= 0 -> out + */ +#define CEPH_MDS_STATE_DNE 0 /* down, does not exist. */ +#define CEPH_MDS_STATE_STOPPED -1 /* down, once existed, but no subtrees. + empty log. */ +#define CEPH_MDS_STATE_BOOT -4 /* up, boot announcement. */ +#define CEPH_MDS_STATE_STANDBY -5 /* up, idle. waiting for assignment. */ +#define CEPH_MDS_STATE_CREATING -6 /* up, creating MDS instance. */ +#define CEPH_MDS_STATE_STARTING -7 /* up, starting previously stopped mds */ +#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */ + +#define CEPH_MDS_STATE_REPLAY 8 /* up, replaying journal. */ +#define CEPH_MDS_STATE_RESOLVE 9 /* up, disambiguating distributed + operations (import, rename, etc.) */ +#define CEPH_MDS_STATE_RECONNECT 10 /* up, reconnect to clients */ +#define CEPH_MDS_STATE_REJOIN 11 /* up, rejoining distributed cache */ +#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */ +#define CEPH_MDS_STATE_ACTIVE 13 /* up, active */ +#define CEPH_MDS_STATE_STOPPING 14 /* up, but exporting metadata */ + +extern const char *ceph_mds_state_name(int s); + + +/* + * metadata lock types. + * - these are bitmasks.. we can compose them + * - they also define the lock ordering by the MDS + * - a few of these are internal to the mds + */ +#define CEPH_LOCK_DVERSION 1 +#define CEPH_LOCK_DN 2 +#define CEPH_LOCK_ISNAP 16 +#define CEPH_LOCK_IVERSION 32 /* mds internal */ +#define CEPH_LOCK_IFILE 64 +#define CEPH_LOCK_IAUTH 128 +#define CEPH_LOCK_ILINK 256 +#define CEPH_LOCK_IDFT 512 /* dir frag tree */ +#define CEPH_LOCK_INEST 1024 /* mds internal */ +#define CEPH_LOCK_IXATTR 2048 +#define CEPH_LOCK_IFLOCK 4096 /* advisory file locks */ +#define CEPH_LOCK_INO 8192 /* immutable inode bits; not a lock */ + +/* client_session ops */ +enum { + CEPH_SESSION_REQUEST_OPEN, + CEPH_SESSION_OPEN, + CEPH_SESSION_REQUEST_CLOSE, + CEPH_SESSION_CLOSE, + CEPH_SESSION_REQUEST_RENEWCAPS, + CEPH_SESSION_RENEWCAPS, + CEPH_SESSION_STALE, + CEPH_SESSION_RECALL_STATE, +}; + +extern const char *ceph_session_op_name(int op); + +struct ceph_mds_session_head { + __le32 op; + __le64 seq; + struct ceph_timespec stamp; + __le32 max_caps, max_leases; +} __attribute__ ((packed)); + +/* client_request */ +/* + * metadata ops. + * & 0x001000 -> write op + * & 0x010000 -> follow symlink (e.g. stat(), not lstat()). + & & 0x100000 -> use weird ino/path trace + */ +#define CEPH_MDS_OP_WRITE 0x001000 +enum { + CEPH_MDS_OP_LOOKUP = 0x00100, + CEPH_MDS_OP_GETATTR = 0x00101, + CEPH_MDS_OP_LOOKUPHASH = 0x00102, + CEPH_MDS_OP_LOOKUPPARENT = 0x00103, + + CEPH_MDS_OP_SETXATTR = 0x01105, + CEPH_MDS_OP_RMXATTR = 0x01106, + CEPH_MDS_OP_SETLAYOUT = 0x01107, + CEPH_MDS_OP_SETATTR = 0x01108, + CEPH_MDS_OP_SETFILELOCK= 0x01109, + CEPH_MDS_OP_GETFILELOCK= 0x00110, + + CEPH_MDS_OP_MKNOD = 0x01201, + CEPH_MDS_OP_LINK = 0x01202, + CEPH_MDS_OP_UNLINK = 0x01203, + CEPH_MDS_OP_RENAME = 0x01204, + CEPH_MDS_OP_MKDIR = 0x01220, + CEPH_MDS_OP_RMDIR = 0x01221, + CEPH_MDS_OP_SYMLINK = 0x01222, + + CEPH_MDS_OP_CREATE = 0x01301, + CEPH_MDS_OP_OPEN = 0x00302, + CEPH_MDS_OP_READDIR = 0x00305, + + CEPH_MDS_OP_LOOKUPSNAP = 0x00400, + CEPH_MDS_OP_MKSNAP = 0x01400, + CEPH_MDS_OP_RMSNAP = 0x01401, + CEPH_MDS_OP_LSSNAP = 0x00402, +}; + +extern const char *ceph_mds_op_name(int op); + + +#define CEPH_SETATTR_MODE 1 +#define CEPH_SETATTR_UID 2 +#define CEPH_SETATTR_GID 4 +#define CEPH_SETATTR_MTIME 8 +#define CEPH_SETATTR_ATIME 16 +#define CEPH_SETATTR_SIZE 32 +#define CEPH_SETATTR_CTIME 64 + +union ceph_mds_request_args { + struct { + __le32 mask; /* CEPH_CAP_* */ + } __attribute__ ((packed)) getattr; + struct { + __le32 mode; + __le32 uid; + __le32 gid; + struct ceph_timespec mtime; + struct ceph_timespec atime; + __le64 size, old_size; /* old_size needed by truncate */ + __le32 mask; /* CEPH_SETATTR_* */ + } __attribute__ ((packed)) setattr; + struct { + __le32 frag; /* which dir fragment */ + __le32 max_entries; /* how many dentries to grab */ + __le32 max_bytes; + } __attribute__ ((packed)) readdir; + struct { + __le32 mode; + __le32 rdev; + } __attribute__ ((packed)) mknod; + struct { + __le32 mode; + } __attribute__ ((packed)) mkdir; + struct { + __le32 flags; + __le32 mode; + __le32 stripe_unit; /* layout for newly created file */ + __le32 stripe_count; /* ... */ + __le32 object_size; + __le32 file_replication; + __le32 preferred; + } __attribute__ ((packed)) open; + struct { + __le32 flags; + } __attribute__ ((packed)) setxattr; + struct { + struct ceph_file_layout layout; + } __attribute__ ((packed)) setlayout; + struct { + __u8 rule; /* currently fcntl or flock */ + __u8 type; /* shared, exclusive, remove*/ + __le64 pid; /* process id requesting the lock */ + __le64 pid_namespace; + __le64 start; /* initial location to lock */ + __le64 length; /* num bytes to lock from start */ + __u8 wait; /* will caller wait for lock to become available? */ + } __attribute__ ((packed)) filelock_change; +} __attribute__ ((packed)); + +#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ +#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */ + +struct ceph_mds_request_head { + __le64 oldest_client_tid; + __le32 mdsmap_epoch; /* on client */ + __le32 flags; /* CEPH_MDS_FLAG_* */ + __u8 num_retry, num_fwd; /* count retry, fwd attempts */ + __le16 num_releases; /* # include cap/lease release records */ + __le32 op; /* mds op code */ + __le32 caller_uid, caller_gid; + __le64 ino; /* use this ino for openc, mkdir, mknod, + etc. (if replaying) */ + union ceph_mds_request_args args; +} __attribute__ ((packed)); + +/* cap/lease release record */ +struct ceph_mds_request_release { + __le64 ino, cap_id; /* ino and unique cap id */ + __le32 caps, wanted; /* new issued, wanted */ + __le32 seq, issue_seq, mseq; + __le32 dname_seq; /* if releasing a dentry lease, a */ + __le32 dname_len; /* string follows. */ +} __attribute__ ((packed)); + +/* client reply */ +struct ceph_mds_reply_head { + __le32 op; + __le32 result; + __le32 mdsmap_epoch; + __u8 safe; /* true if committed to disk */ + __u8 is_dentry, is_target; /* true if dentry, target inode records + are included with reply */ +} __attribute__ ((packed)); + +/* one for each node split */ +struct ceph_frag_tree_split { + __le32 frag; /* this frag splits... */ + __le32 by; /* ...by this many bits */ +} __attribute__ ((packed)); + +struct ceph_frag_tree_head { + __le32 nsplits; /* num ceph_frag_tree_split records */ + struct ceph_frag_tree_split splits[]; +} __attribute__ ((packed)); + +/* capability issue, for bundling with mds reply */ +struct ceph_mds_reply_cap { + __le32 caps, wanted; /* caps issued, wanted */ + __le64 cap_id; + __le32 seq, mseq; + __le64 realm; /* snap realm */ + __u8 flags; /* CEPH_CAP_FLAG_* */ +} __attribute__ ((packed)); + +#define CEPH_CAP_FLAG_AUTH 1 /* cap is issued by auth mds */ + +/* inode record, for bundling with mds reply */ +struct ceph_mds_reply_inode { + __le64 ino; + __le64 snapid; + __le32 rdev; + __le64 version; /* inode version */ + __le64 xattr_version; /* version for xattr blob */ + struct ceph_mds_reply_cap cap; /* caps issued for this inode */ + struct ceph_file_layout layout; + struct ceph_timespec ctime, mtime, atime; + __le32 time_warp_seq; + __le64 size, max_size, truncate_size; + __le32 truncate_seq; + __le32 mode, uid, gid; + __le32 nlink; + __le64 files, subdirs, rbytes, rfiles, rsubdirs; /* dir stats */ + struct ceph_timespec rctime; + struct ceph_frag_tree_head fragtree; /* (must be at end of struct) */ +} __attribute__ ((packed)); +/* followed by frag array, then symlink string, then xattr blob */ + +/* reply_lease follows dname, and reply_inode */ +struct ceph_mds_reply_lease { + __le16 mask; /* lease type(s) */ + __le32 duration_ms; /* lease duration */ + __le32 seq; +} __attribute__ ((packed)); + +struct ceph_mds_reply_dirfrag { + __le32 frag; /* fragment */ + __le32 auth; /* auth mds, if this is a delegation point */ + __le32 ndist; /* number of mds' this is replicated on */ + __le32 dist[]; +} __attribute__ ((packed)); + +#define CEPH_LOCK_FCNTL 1 +#define CEPH_LOCK_FLOCK 2 + +#define CEPH_LOCK_SHARED 1 +#define CEPH_LOCK_EXCL 2 +#define CEPH_LOCK_UNLOCK 4 + +struct ceph_filelock { + __le64 start;/* file offset to start lock at */ + __le64 length; /* num bytes to lock; 0 for all following start */ + __le64 client; /* which client holds the lock */ + __le64 pid; /* process id holding the lock on the client */ + __le64 pid_namespace; + __u8 type; /* shared lock, exclusive lock, or unlock */ +} __attribute__ ((packed)); + + +/* file access modes */ +#define CEPH_FILE_MODE_PIN 0 +#define CEPH_FILE_MODE_RD 1 +#define CEPH_FILE_MODE_WR 2 +#define CEPH_FILE_MODE_RDWR 3 /* RD | WR */ +#define CEPH_FILE_MODE_LAZY 4 /* lazy io */ +#define CEPH_FILE_MODE_NUM 8 /* bc these are bit fields.. mostly */ + +int ceph_flags_to_mode(int flags); + + +/* capability bits */ +#define CEPH_CAP_PIN 1 /* no specific capabilities beyond the pin */ + +/* generic cap bits */ +#define CEPH_CAP_GSHARED 1 /* client can reads */ +#define CEPH_CAP_GEXCL 2 /* client can read and update */ +#define CEPH_CAP_GCACHE 4 /* (file) client can cache reads */ +#define CEPH_CAP_GRD 8 /* (file) client can read */ +#define CEPH_CAP_GWR 16 /* (file) client can write */ +#define CEPH_CAP_GBUFFER 32 /* (file) client can buffer writes */ +#define CEPH_CAP_GWREXTEND 64 /* (file) client can extend EOF */ +#define CEPH_CAP_GLAZYIO 128 /* (file) client can perform lazy io */ + +/* per-lock shift */ +#define CEPH_CAP_SAUTH 2 +#define CEPH_CAP_SLINK 4 +#define CEPH_CAP_SXATTR 6 +#define CEPH_CAP_SFILE 8 +#define CEPH_CAP_SFLOCK 20 + +#define CEPH_CAP_BITS 22 + +/* composed values */ +#define CEPH_CAP_AUTH_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SAUTH) +#define CEPH_CAP_AUTH_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SAUTH) +#define CEPH_CAP_LINK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SLINK) +#define CEPH_CAP_LINK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SLINK) +#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SXATTR) +#define CEPH_CAP_XATTR_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SXATTR) +#define CEPH_CAP_FILE(x) (x << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_CACHE (CEPH_CAP_GCACHE << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_RD (CEPH_CAP_GRD << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_WR (CEPH_CAP_GWR << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_BUFFER (CEPH_CAP_GBUFFER << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_LAZYIO (CEPH_CAP_GLAZYIO << CEPH_CAP_SFILE) +#define CEPH_CAP_FLOCK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFLOCK) +#define CEPH_CAP_FLOCK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFLOCK) + + +/* cap masks (for getattr) */ +#define CEPH_STAT_CAP_INODE CEPH_CAP_PIN +#define CEPH_STAT_CAP_TYPE CEPH_CAP_PIN /* mode >> 12 */ +#define CEPH_STAT_CAP_SYMLINK CEPH_CAP_PIN +#define CEPH_STAT_CAP_UID CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_GID CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_MODE CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_NLINK CEPH_CAP_LINK_SHARED +#define CEPH_STAT_CAP_LAYOUT CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_MTIME CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_SIZE CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_ATIME CEPH_CAP_FILE_SHARED /* fixme */ +#define CEPH_STAT_CAP_XATTR CEPH_CAP_XATTR_SHARED +#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN | \ + CEPH_CAP_AUTH_SHARED | \ + CEPH_CAP_LINK_SHARED | \ + CEPH_CAP_FILE_SHARED | \ + CEPH_CAP_XATTR_SHARED) + +#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \ + CEPH_CAP_LINK_SHARED | \ + CEPH_CAP_XATTR_SHARED | \ + CEPH_CAP_FILE_SHARED) +#define CEPH_CAP_ANY_RD (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD | \ + CEPH_CAP_FILE_CACHE) + +#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL | \ + CEPH_CAP_LINK_EXCL | \ + CEPH_CAP_XATTR_EXCL | \ + CEPH_CAP_FILE_EXCL) +#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | \ + CEPH_CAP_FILE_EXCL) +#define CEPH_CAP_ANY_WR (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR) +#define CEPH_CAP_ANY (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \ + CEPH_CAP_ANY_FILE_WR | CEPH_CAP_FILE_LAZYIO | \ + CEPH_CAP_PIN) + +#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \ + CEPH_LOCK_IXATTR) + +int ceph_caps_for_mode(int mode); + +enum { + CEPH_CAP_OP_GRANT, /* mds->client grant */ + CEPH_CAP_OP_REVOKE, /* mds->client revoke */ + CEPH_CAP_OP_TRUNC, /* mds->client trunc notify */ + CEPH_CAP_OP_EXPORT, /* mds has exported the cap */ + CEPH_CAP_OP_IMPORT, /* mds has imported the cap */ + CEPH_CAP_OP_UPDATE, /* client->mds update */ + CEPH_CAP_OP_DROP, /* client->mds drop cap bits */ + CEPH_CAP_OP_FLUSH, /* client->mds cap writeback */ + CEPH_CAP_OP_FLUSH_ACK, /* mds->client flushed */ + CEPH_CAP_OP_FLUSHSNAP, /* client->mds flush snapped metadata */ + CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed snapped metadata */ + CEPH_CAP_OP_RELEASE, /* client->mds release (clean) cap */ + CEPH_CAP_OP_RENEW, /* client->mds renewal request */ +}; + +extern const char *ceph_cap_op_name(int op); + +/* + * caps message, used for capability callbacks, acks, requests, etc. + */ +struct ceph_mds_caps { + __le32 op; /* CEPH_CAP_OP_* */ + __le64 ino, realm; + __le64 cap_id; + __le32 seq, issue_seq; + __le32 caps, wanted, dirty; /* latest issued/wanted/dirty */ + __le32 migrate_seq; + __le64 snap_follows; + __le32 snap_trace_len; + + /* authlock */ + __le32 uid, gid, mode; + + /* linklock */ + __le32 nlink; + + /* xattrlock */ + __le32 xattr_len; + __le64 xattr_version; + + /* filelock */ + __le64 size, max_size, truncate_size; + __le32 truncate_seq; + struct ceph_timespec mtime, atime, ctime; + struct ceph_file_layout layout; + __le32 time_warp_seq; +} __attribute__ ((packed)); + +/* cap release msg head */ +struct ceph_mds_cap_release { + __le32 num; /* number of cap_items that follow */ +} __attribute__ ((packed)); + +struct ceph_mds_cap_item { + __le64 ino; + __le64 cap_id; + __le32 migrate_seq, seq; +} __attribute__ ((packed)); + +#define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */ +#define CEPH_MDS_LEASE_RELEASE 2 /* client -> mds */ +#define CEPH_MDS_LEASE_RENEW 3 /* client <-> mds */ +#define CEPH_MDS_LEASE_REVOKE_ACK 4 /* client -> mds */ + +extern const char *ceph_lease_op_name(int o); + +/* lease msg header */ +struct ceph_mds_lease { + __u8 action; /* CEPH_MDS_LEASE_* */ + __le16 mask; /* which lease */ + __le64 ino; + __le64 first, last; /* snap range */ + __le32 seq; + __le32 duration_ms; /* duration of renewal */ +} __attribute__ ((packed)); +/* followed by a __le32+string for dname */ + +/* client reconnect */ +struct ceph_mds_cap_reconnect { + __le64 cap_id; + __le32 wanted; + __le32 issued; + __le64 snaprealm; + __le64 pathbase; /* base ino for our path to this ino */ + __le32 flock_len; /* size of flock state blob, if any */ +} __attribute__ ((packed)); +/* followed by flock blob */ + +struct ceph_mds_cap_reconnect_v1 { + __le64 cap_id; + __le32 wanted; + __le32 issued; + __le64 size; + struct ceph_timespec mtime, atime; + __le64 snaprealm; + __le64 pathbase; /* base ino for our path to this ino */ +} __attribute__ ((packed)); + +struct ceph_mds_snaprealm_reconnect { + __le64 ino; /* snap realm base */ + __le64 seq; /* snap seq for this snap realm */ + __le64 parent; /* parent realm */ +} __attribute__ ((packed)); + +/* + * snaps + */ +enum { + CEPH_SNAP_OP_UPDATE, /* CREATE or DESTROY */ + CEPH_SNAP_OP_CREATE, + CEPH_SNAP_OP_DESTROY, + CEPH_SNAP_OP_SPLIT, +}; + +extern const char *ceph_snap_op_name(int o); + +/* snap msg header */ +struct ceph_mds_snap_head { + __le32 op; /* CEPH_SNAP_OP_* */ + __le64 split; /* ino to split off, if any */ + __le32 num_split_inos; /* # inos belonging to new child realm */ + __le32 num_split_realms; /* # child realms udner new child realm */ + __le32 trace_len; /* size of snap trace blob */ +} __attribute__ ((packed)); +/* followed by split ino list, then split realms, then the trace blob */ + +/* + * encode info about a snaprealm, as viewed by a client + */ +struct ceph_mds_snap_realm { + __le64 ino; /* ino */ + __le64 created; /* snap: when created */ + __le64 parent; /* ino: parent realm */ + __le64 parent_since; /* snap: same parent since */ + __le64 seq; /* snap: version */ + __le32 num_snaps; + __le32 num_prior_parent_snaps; +} __attribute__ ((packed)); +/* followed by my snap list, then prior parent snap list */ + +#endif diff --git a/include/linux/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h new file mode 100644 index 000000000000..d099c3f90236 --- /dev/null +++ b/include/linux/ceph/ceph_hash.h @@ -0,0 +1,13 @@ +#ifndef FS_CEPH_HASH_H +#define FS_CEPH_HASH_H + +#define CEPH_STR_HASH_LINUX 0x1 /* linux dcache hash */ +#define CEPH_STR_HASH_RJENKINS 0x2 /* robert jenkins' */ + +extern unsigned ceph_str_hash_linux(const char *s, unsigned len); +extern unsigned ceph_str_hash_rjenkins(const char *s, unsigned len); + +extern unsigned ceph_str_hash(int type, const char *s, unsigned len); +extern const char *ceph_str_hash_name(int type); + +#endif diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h new file mode 100644 index 000000000000..2a79702e092b --- /dev/null +++ b/include/linux/ceph/debugfs.h @@ -0,0 +1,33 @@ +#ifndef _FS_CEPH_DEBUGFS_H +#define _FS_CEPH_DEBUGFS_H + +#include "ceph_debug.h" +#include "types.h" + +#define CEPH_DEFINE_SHOW_FUNC(name) \ +static int name##_open(struct inode *inode, struct file *file) \ +{ \ + struct seq_file *sf; \ + int ret; \ + \ + ret = single_open(file, name, NULL); \ + sf = file->private_data; \ + sf->private = inode->i_private; \ + return ret; \ +} \ + \ +static const struct file_operations name##_fops = { \ + .open = name##_open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +}; + +/* debugfs.c */ +extern int ceph_debugfs_init(void); +extern void ceph_debugfs_cleanup(void); +extern int ceph_debugfs_client_init(struct ceph_client *client); +extern void ceph_debugfs_client_cleanup(struct ceph_client *client); + +#endif + diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h new file mode 100644 index 000000000000..c5b6939fb32a --- /dev/null +++ b/include/linux/ceph/decode.h @@ -0,0 +1,201 @@ +#ifndef __CEPH_DECODE_H +#define __CEPH_DECODE_H + +#include +#include + +#include "types.h" + +/* + * in all cases, + * void **p pointer to position pointer + * void *end pointer to end of buffer (last byte + 1) + */ + +static inline u64 ceph_decode_64(void **p) +{ + u64 v = get_unaligned_le64(*p); + *p += sizeof(u64); + return v; +} +static inline u32 ceph_decode_32(void **p) +{ + u32 v = get_unaligned_le32(*p); + *p += sizeof(u32); + return v; +} +static inline u16 ceph_decode_16(void **p) +{ + u16 v = get_unaligned_le16(*p); + *p += sizeof(u16); + return v; +} +static inline u8 ceph_decode_8(void **p) +{ + u8 v = *(u8 *)*p; + (*p)++; + return v; +} +static inline void ceph_decode_copy(void **p, void *pv, size_t n) +{ + memcpy(pv, *p, n); + *p += n; +} + +/* + * bounds check input. + */ +#define ceph_decode_need(p, end, n, bad) \ + do { \ + if (unlikely(*(p) + (n) > (end))) \ + goto bad; \ + } while (0) + +#define ceph_decode_64_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u64), bad); \ + v = ceph_decode_64(p); \ + } while (0) +#define ceph_decode_32_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u32), bad); \ + v = ceph_decode_32(p); \ + } while (0) +#define ceph_decode_16_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u16), bad); \ + v = ceph_decode_16(p); \ + } while (0) +#define ceph_decode_8_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u8), bad); \ + v = ceph_decode_8(p); \ + } while (0) + +#define ceph_decode_copy_safe(p, end, pv, n, bad) \ + do { \ + ceph_decode_need(p, end, n, bad); \ + ceph_decode_copy(p, pv, n); \ + } while (0) + +/* + * struct ceph_timespec <-> struct timespec + */ +static inline void ceph_decode_timespec(struct timespec *ts, + const struct ceph_timespec *tv) +{ + ts->tv_sec = le32_to_cpu(tv->tv_sec); + ts->tv_nsec = le32_to_cpu(tv->tv_nsec); +} +static inline void ceph_encode_timespec(struct ceph_timespec *tv, + const struct timespec *ts) +{ + tv->tv_sec = cpu_to_le32(ts->tv_sec); + tv->tv_nsec = cpu_to_le32(ts->tv_nsec); +} + +/* + * sockaddr_storage <-> ceph_sockaddr + */ +static inline void ceph_encode_addr(struct ceph_entity_addr *a) +{ + __be16 ss_family = htons(a->in_addr.ss_family); + a->in_addr.ss_family = *(__u16 *)&ss_family; +} +static inline void ceph_decode_addr(struct ceph_entity_addr *a) +{ + __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; + a->in_addr.ss_family = ntohs(ss_family); + WARN_ON(a->in_addr.ss_family == 512); +} + +/* + * encoders + */ +static inline void ceph_encode_64(void **p, u64 v) +{ + put_unaligned_le64(v, (__le64 *)*p); + *p += sizeof(u64); +} +static inline void ceph_encode_32(void **p, u32 v) +{ + put_unaligned_le32(v, (__le32 *)*p); + *p += sizeof(u32); +} +static inline void ceph_encode_16(void **p, u16 v) +{ + put_unaligned_le16(v, (__le16 *)*p); + *p += sizeof(u16); +} +static inline void ceph_encode_8(void **p, u8 v) +{ + *(u8 *)*p = v; + (*p)++; +} +static inline void ceph_encode_copy(void **p, const void *s, int len) +{ + memcpy(*p, s, len); + *p += len; +} + +/* + * filepath, string encoders + */ +static inline void ceph_encode_filepath(void **p, void *end, + u64 ino, const char *path) +{ + u32 len = path ? strlen(path) : 0; + BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end); + ceph_encode_8(p, 1); + ceph_encode_64(p, ino); + ceph_encode_32(p, len); + if (len) + memcpy(*p, path, len); + *p += len; +} + +static inline void ceph_encode_string(void **p, void *end, + const char *s, u32 len) +{ + BUG_ON(*p + sizeof(len) + len > end); + ceph_encode_32(p, len); + if (len) + memcpy(*p, s, len); + *p += len; +} + +#define ceph_encode_need(p, end, n, bad) \ + do { \ + if (unlikely(*(p) + (n) > (end))) \ + goto bad; \ + } while (0) + +#define ceph_encode_64_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u64), bad); \ + ceph_encode_64(p, v); \ + } while (0) +#define ceph_encode_32_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u32), bad); \ + ceph_encode_32(p, v); \ + } while (0) +#define ceph_encode_16_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u16), bad); \ + ceph_encode_16(p, v); \ + } while (0) + +#define ceph_encode_copy_safe(p, end, pv, n, bad) \ + do { \ + ceph_encode_need(p, end, n, bad); \ + ceph_encode_copy(p, pv, n); \ + } while (0) +#define ceph_encode_string_safe(p, end, s, n, bad) \ + do { \ + ceph_encode_need(p, end, n, bad); \ + ceph_encode_string(p, end, s, n); \ + } while (0) + + +#endif diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h new file mode 100644 index 000000000000..f22b2e941686 --- /dev/null +++ b/include/linux/ceph/libceph.h @@ -0,0 +1,249 @@ +#ifndef _FS_CEPH_LIBCEPH_H +#define _FS_CEPH_LIBCEPH_H + +#include "ceph_debug.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "types.h" +#include "messenger.h" +#include "msgpool.h" +#include "mon_client.h" +#include "osd_client.h" +#include "ceph_fs.h" + +/* + * Supported features + */ +#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR +#define CEPH_FEATURE_REQUIRED_DEFAULT CEPH_FEATURE_NOSRCADDR + +/* + * mount options + */ +#define CEPH_OPT_FSID (1<<0) +#define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ +#define CEPH_OPT_MYIP (1<<2) /* specified my ip */ +#define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ + +#define CEPH_OPT_DEFAULT (0); + +#define ceph_set_opt(client, opt) \ + (client)->options->flags |= CEPH_OPT_##opt; +#define ceph_test_opt(client, opt) \ + (!!((client)->options->flags & CEPH_OPT_##opt)) + +struct ceph_options { + int flags; + struct ceph_fsid fsid; + struct ceph_entity_addr my_addr; + int mount_timeout; + int osd_idle_ttl; + int osd_timeout; + int osd_keepalive_timeout; + + /* + * any type that can't be simply compared or doesn't need need + * to be compared should go beyond this point, + * ceph_compare_options() should be updated accordingly + */ + + struct ceph_entity_addr *mon_addr; /* should be the first + pointer type of args */ + int num_mon; + char *name; + char *secret; +}; + +/* + * defaults + */ +#define CEPH_MOUNT_TIMEOUT_DEFAULT 60 +#define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */ +#define CEPH_OSD_KEEPALIVE_DEFAULT 5 +#define CEPH_OSD_IDLE_TTL_DEFAULT 60 +#define CEPH_MOUNT_RSIZE_DEFAULT (512*1024) /* readahead */ + +#define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) +#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +#define CEPH_AUTH_NAME_DEFAULT "guest" + +/* + * Delay telling the MDS we no longer want caps, in case we reopen + * the file. Delay a minimum amount of time, even if we send a cap + * message for some other reason. Otherwise, take the oppotunity to + * update the mds to avoid sending another message later. + */ +#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ +#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ + +#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4) + +/* mount state */ +enum { + CEPH_MOUNT_MOUNTING, + CEPH_MOUNT_MOUNTED, + CEPH_MOUNT_UNMOUNTING, + CEPH_MOUNT_UNMOUNTED, + CEPH_MOUNT_SHUTDOWN, +}; + +/* + * subtract jiffies + */ +static inline unsigned long time_sub(unsigned long a, unsigned long b) +{ + BUG_ON(time_after(b, a)); + return (long)a - (long)b; +} + +struct ceph_mds_client; + +/* + * per client state + * + * possibly shared by multiple mount points, if they are + * mounting the same ceph filesystem/cluster. + */ +struct ceph_client { + struct ceph_fsid fsid; + bool have_fsid; + + void *private; + + struct ceph_options *options; + + struct mutex mount_mutex; /* serialize mount attempts */ + wait_queue_head_t auth_wq; + int auth_err; + + int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *); + + u32 supported_features; + u32 required_features; + + struct ceph_messenger *msgr; /* messenger instance */ + struct ceph_mon_client monc; + struct ceph_osd_client osdc; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_dir; + struct dentry *debugfs_monmap; + struct dentry *debugfs_osdmap; +#endif +}; + + + +/* + * snapshots + */ + +/* + * A "snap context" is the set of existing snapshots when we + * write data. It is used by the OSD to guide its COW behavior. + * + * The ceph_snap_context is refcounted, and attached to each dirty + * page, indicating which context the dirty data belonged when it was + * dirtied. + */ +struct ceph_snap_context { + atomic_t nref; + u64 seq; + int num_snaps; + u64 snaps[]; +}; + +static inline struct ceph_snap_context * +ceph_get_snap_context(struct ceph_snap_context *sc) +{ + /* + printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), + atomic_read(&sc->nref)+1); + */ + if (sc) + atomic_inc(&sc->nref); + return sc; +} + +static inline void ceph_put_snap_context(struct ceph_snap_context *sc) +{ + if (!sc) + return; + /* + printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), + atomic_read(&sc->nref)-1); + */ + if (atomic_dec_and_test(&sc->nref)) { + /*printk(" deleting snap_context %p\n", sc);*/ + kfree(sc); + } +} + +/* + * calculate the number of pages a given length and offset map onto, + * if we align the data. + */ +static inline int calc_pages_for(u64 off, u64 len) +{ + return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - + (off >> PAGE_CACHE_SHIFT); +} + +/* ceph_common.c */ +extern const char *ceph_msg_type_name(int type); +extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); +extern struct kmem_cache *ceph_inode_cachep; +extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_dentry_cachep; +extern struct kmem_cache *ceph_file_cachep; + +extern int ceph_parse_options(struct ceph_options **popt, char *options, + const char *dev_name, const char *dev_name_end, + int (*parse_extra_token)(char *c, void *private), + void *private); +extern void ceph_destroy_options(struct ceph_options *opt); +extern int ceph_compare_options(struct ceph_options *new_opt, + struct ceph_client *client); +extern struct ceph_client *ceph_create_client(struct ceph_options *opt, + void *private); +extern u64 ceph_client_id(struct ceph_client *client); +extern void ceph_destroy_client(struct ceph_client *client); +extern int __ceph_open_session(struct ceph_client *client, + unsigned long started); +extern int ceph_open_session(struct ceph_client *client); + +/* pagevec.c */ +extern void ceph_release_page_vector(struct page **pages, int num_pages); + +extern struct page **ceph_get_direct_page_vector(const char __user *data, + int num_pages, + loff_t off, size_t len); +extern void ceph_put_page_vector(struct page **pages, int num_pages); +extern void ceph_release_page_vector(struct page **pages, int num_pages); +extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); +extern int ceph_copy_user_to_page_vector(struct page **pages, + const char __user *data, + loff_t off, size_t len); +extern int ceph_copy_to_page_vector(struct page **pages, + const char *data, + loff_t off, size_t len); +extern int ceph_copy_from_page_vector(struct page **pages, + char *data, + loff_t off, size_t len); +extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data, + loff_t off, size_t len); +extern void ceph_zero_page_vector_range(int off, int len, struct page **pages); + + +#endif /* _FS_CEPH_SUPER_H */ diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h new file mode 100644 index 000000000000..4c5cb0880bba --- /dev/null +++ b/include/linux/ceph/mdsmap.h @@ -0,0 +1,62 @@ +#ifndef _FS_CEPH_MDSMAP_H +#define _FS_CEPH_MDSMAP_H + +#include "types.h" + +/* + * mds map - describe servers in the mds cluster. + * + * we limit fields to those the client actually xcares about + */ +struct ceph_mds_info { + u64 global_id; + struct ceph_entity_addr addr; + s32 state; + int num_export_targets; + bool laggy; + u32 *export_targets; +}; + +struct ceph_mdsmap { + u32 m_epoch, m_client_epoch, m_last_failure; + u32 m_root; + u32 m_session_timeout; /* seconds */ + u32 m_session_autoclose; /* seconds */ + u64 m_max_file_size; + u32 m_max_mds; /* size of m_addr, m_state arrays */ + struct ceph_mds_info *m_info; + + /* which object pools file data can be stored in */ + int m_num_data_pg_pools; + u32 *m_data_pg_pools; + u32 m_cas_pg_pool; +}; + +static inline struct ceph_entity_addr * +ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) +{ + if (w >= m->m_max_mds) + return NULL; + return &m->m_info[w].addr; +} + +static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) +{ + BUG_ON(w < 0); + if (w >= m->m_max_mds) + return CEPH_MDS_STATE_DNE; + return m->m_info[w].state; +} + +static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) +{ + if (w >= 0 && w < m->m_max_mds) + return m->m_info[w].laggy; + return false; +} + +extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m); +extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end); +extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m); + +#endif diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h new file mode 100644 index 000000000000..5956d62c3057 --- /dev/null +++ b/include/linux/ceph/messenger.h @@ -0,0 +1,261 @@ +#ifndef __FS_CEPH_MESSENGER_H +#define __FS_CEPH_MESSENGER_H + +#include +#include +#include +#include +#include +#include +#include + +#include "types.h" +#include "buffer.h" + +struct ceph_msg; +struct ceph_connection; + +extern struct workqueue_struct *ceph_msgr_wq; /* receive work queue */ + +/* + * Ceph defines these callbacks for handling connection events. + */ +struct ceph_connection_operations { + struct ceph_connection *(*get)(struct ceph_connection *); + void (*put)(struct ceph_connection *); + + /* handle an incoming message. */ + void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m); + + /* authorize an outgoing connection */ + int (*get_authorizer) (struct ceph_connection *con, + void **buf, int *len, int *proto, + void **reply_buf, int *reply_len, int force_new); + int (*verify_authorizer_reply) (struct ceph_connection *con, int len); + int (*invalidate_authorizer)(struct ceph_connection *con); + + /* protocol version mismatch */ + void (*bad_proto) (struct ceph_connection *con); + + /* there was some error on the socket (disconnect, whatever) */ + void (*fault) (struct ceph_connection *con); + + /* a remote host as terminated a message exchange session, and messages + * we sent (or they tried to send us) may be lost. */ + void (*peer_reset) (struct ceph_connection *con); + + struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip); +}; + +/* use format string %s%d */ +#define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num) + +struct ceph_messenger { + struct ceph_entity_inst inst; /* my name+address */ + struct ceph_entity_addr my_enc_addr; + struct page *zero_page; /* used in certain error cases */ + + bool nocrc; + + /* + * the global_seq counts connections i (attempt to) initiate + * in order to disambiguate certain connect race conditions. + */ + u32 global_seq; + spinlock_t global_seq_lock; + + u32 supported_features; + u32 required_features; +}; + +/* + * a single message. it contains a header (src, dest, message type, etc.), + * footer (crc values, mainly), a "front" message body, and possibly a + * data payload (stored in some number of pages). + */ +struct ceph_msg { + struct ceph_msg_header hdr; /* header */ + struct ceph_msg_footer footer; /* footer */ + struct kvec front; /* unaligned blobs of message */ + struct ceph_buffer *middle; + struct page **pages; /* data payload. NOT OWNER. */ + unsigned nr_pages; /* size of page array */ + struct ceph_pagelist *pagelist; /* instead of pages */ + struct list_head list_head; + struct kref kref; + struct bio *bio; /* instead of pages/pagelist */ + struct bio *bio_iter; /* bio iterator */ + int bio_seg; /* current bio segment */ + struct ceph_pagelist *trail; /* the trailing part of the data */ + bool front_is_vmalloc; + bool more_to_follow; + bool needs_out_seq; + int front_max; + + struct ceph_msgpool *pool; +}; + +struct ceph_msg_pos { + int page, page_pos; /* which page; offset in page */ + int data_pos; /* offset in data payload */ + int did_page_crc; /* true if we've calculated crc for current page */ +}; + +/* ceph connection fault delay defaults, for exponential backoff */ +#define BASE_DELAY_INTERVAL (HZ/2) +#define MAX_DELAY_INTERVAL (5 * 60 * HZ) + +/* + * ceph_connection state bit flags + * + * QUEUED and BUSY are used together to ensure that only a single + * thread is currently opening, reading or writing data to the socket. + */ +#define LOSSYTX 0 /* we can close channel or drop messages on errors */ +#define CONNECTING 1 +#define NEGOTIATING 2 +#define KEEPALIVE_PENDING 3 +#define WRITE_PENDING 4 /* we have data ready to send */ +#define QUEUED 5 /* there is work queued on this connection */ +#define BUSY 6 /* work is being done */ +#define STANDBY 8 /* no outgoing messages, socket closed. we keep + * the ceph_connection around to maintain shared + * state with the peer. */ +#define CLOSED 10 /* we've closed the connection */ +#define SOCK_CLOSED 11 /* socket state changed to closed */ +#define OPENING 13 /* open connection w/ (possibly new) peer */ +#define DEAD 14 /* dead, about to kfree */ + +/* + * A single connection with another host. + * + * We maintain a queue of outgoing messages, and some session state to + * ensure that we can preserve the lossless, ordered delivery of + * messages in the case of a TCP disconnect. + */ +struct ceph_connection { + void *private; + atomic_t nref; + + const struct ceph_connection_operations *ops; + + struct ceph_messenger *msgr; + struct socket *sock; + unsigned long state; /* connection state (see flags above) */ + const char *error_msg; /* error message, if any */ + + struct ceph_entity_addr peer_addr; /* peer address */ + struct ceph_entity_name peer_name; /* peer name */ + struct ceph_entity_addr peer_addr_for_me; + unsigned peer_features; + u32 connect_seq; /* identify the most recent connection + attempt for this connection, client */ + u32 peer_global_seq; /* peer's global seq for this connection */ + + int auth_retry; /* true if we need a newer authorizer */ + void *auth_reply_buf; /* where to put the authorizer reply */ + int auth_reply_buf_len; + + struct mutex mutex; + + /* out queue */ + struct list_head out_queue; + struct list_head out_sent; /* sending or sent but unacked */ + u64 out_seq; /* last message queued for send */ + bool out_keepalive_pending; + + u64 in_seq, in_seq_acked; /* last message received, acked */ + + /* connection negotiation temps */ + char in_banner[CEPH_BANNER_MAX_LEN]; + union { + struct { /* outgoing connection */ + struct ceph_msg_connect out_connect; + struct ceph_msg_connect_reply in_reply; + }; + struct { /* incoming */ + struct ceph_msg_connect in_connect; + struct ceph_msg_connect_reply out_reply; + }; + }; + struct ceph_entity_addr actual_peer_addr; + + /* message out temps */ + struct ceph_msg *out_msg; /* sending message (== tail of + out_sent) */ + bool out_msg_done; + struct ceph_msg_pos out_msg_pos; + + struct kvec out_kvec[8], /* sending header/footer data */ + *out_kvec_cur; + int out_kvec_left; /* kvec's left in out_kvec */ + int out_skip; /* skip this many bytes */ + int out_kvec_bytes; /* total bytes left */ + bool out_kvec_is_msg; /* kvec refers to out_msg */ + int out_more; /* there is more data after the kvecs */ + __le64 out_temp_ack; /* for writing an ack */ + + /* message in temps */ + struct ceph_msg_header in_hdr; + struct ceph_msg *in_msg; + struct ceph_msg_pos in_msg_pos; + u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ + + char in_tag; /* protocol control byte */ + int in_base_pos; /* bytes read */ + __le64 in_temp_ack; /* for reading an ack */ + + struct delayed_work work; /* send|recv work */ + unsigned long delay; /* current delay interval */ +}; + + +extern const char *ceph_pr_addr(const struct sockaddr_storage *ss); +extern int ceph_parse_ips(const char *c, const char *end, + struct ceph_entity_addr *addr, + int max_count, int *count); + + +extern int ceph_msgr_init(void); +extern void ceph_msgr_exit(void); +extern void ceph_msgr_flush(void); + +extern struct ceph_messenger *ceph_messenger_create( + struct ceph_entity_addr *myaddr, + u32 features, u32 required); +extern void ceph_messenger_destroy(struct ceph_messenger *); + +extern void ceph_con_init(struct ceph_messenger *msgr, + struct ceph_connection *con); +extern void ceph_con_open(struct ceph_connection *con, + struct ceph_entity_addr *addr); +extern bool ceph_con_opened(struct ceph_connection *con); +extern void ceph_con_close(struct ceph_connection *con); +extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg); +extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg); +extern void ceph_con_revoke_message(struct ceph_connection *con, + struct ceph_msg *msg); +extern void ceph_con_keepalive(struct ceph_connection *con); +extern struct ceph_connection *ceph_con_get(struct ceph_connection *con); +extern void ceph_con_put(struct ceph_connection *con); + +extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags); +extern void ceph_msg_kfree(struct ceph_msg *m); + + +static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg) +{ + kref_get(&msg->kref); + return msg; +} +extern void ceph_msg_last_put(struct kref *kref); +static inline void ceph_msg_put(struct ceph_msg *msg) +{ + kref_put(&msg->kref, ceph_msg_last_put); +} + +extern void ceph_msg_dump(struct ceph_msg *msg); + +#endif diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h new file mode 100644 index 000000000000..545f85917780 --- /dev/null +++ b/include/linux/ceph/mon_client.h @@ -0,0 +1,122 @@ +#ifndef _FS_CEPH_MON_CLIENT_H +#define _FS_CEPH_MON_CLIENT_H + +#include +#include +#include + +#include "messenger.h" + +struct ceph_client; +struct ceph_mount_args; +struct ceph_auth_client; + +/* + * The monitor map enumerates the set of all monitors. + */ +struct ceph_monmap { + struct ceph_fsid fsid; + u32 epoch; + u32 num_mon; + struct ceph_entity_inst mon_inst[0]; +}; + +struct ceph_mon_client; +struct ceph_mon_generic_request; + + +/* + * Generic mechanism for resending monitor requests. + */ +typedef void (*ceph_monc_request_func_t)(struct ceph_mon_client *monc, + int newmon); + +/* a pending monitor request */ +struct ceph_mon_request { + struct ceph_mon_client *monc; + struct delayed_work delayed_work; + unsigned long delay; + ceph_monc_request_func_t do_request; +}; + +/* + * ceph_mon_generic_request is being used for the statfs and poolop requests + * which are bening done a bit differently because we need to get data back + * to the caller + */ +struct ceph_mon_generic_request { + struct kref kref; + u64 tid; + struct rb_node node; + int result; + void *buf; + int buf_len; + struct completion completion; + struct ceph_msg *request; /* original request */ + struct ceph_msg *reply; /* and reply */ +}; + +struct ceph_mon_client { + struct ceph_client *client; + struct ceph_monmap *monmap; + + struct mutex mutex; + struct delayed_work delayed_work; + + struct ceph_auth_client *auth; + struct ceph_msg *m_auth, *m_auth_reply, *m_subscribe, *m_subscribe_ack; + int pending_auth; + + bool hunting; + int cur_mon; /* last monitor i contacted */ + unsigned long sub_sent, sub_renew_after; + struct ceph_connection *con; + bool have_fsid; + + /* pending generic requests */ + struct rb_root generic_request_tree; + int num_generic_requests; + u64 last_tid; + + /* mds/osd map */ + int want_mdsmap; + int want_next_osdmap; /* 1 = want, 2 = want+asked */ + u32 have_osdmap, have_mdsmap; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_file; +#endif +}; + +extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end); +extern int ceph_monmap_contains(struct ceph_monmap *m, + struct ceph_entity_addr *addr); + +extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl); +extern void ceph_monc_stop(struct ceph_mon_client *monc); + +/* + * The model here is to indicate that we need a new map of at least + * epoch @want, and also call in when we receive a map. We will + * periodically rerequest the map from the monitor cluster until we + * get what we want. + */ +extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have); +extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have); + +extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc); + +extern int ceph_monc_do_statfs(struct ceph_mon_client *monc, + struct ceph_statfs *buf); + +extern int ceph_monc_open_session(struct ceph_mon_client *monc); + +extern int ceph_monc_validate_auth(struct ceph_mon_client *monc); + +extern int ceph_monc_create_snapid(struct ceph_mon_client *monc, + u32 pool, u64 *snapid); + +extern int ceph_monc_delete_snapid(struct ceph_mon_client *monc, + u32 pool, u64 snapid); + +#endif diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h new file mode 100644 index 000000000000..a362605f9368 --- /dev/null +++ b/include/linux/ceph/msgpool.h @@ -0,0 +1,25 @@ +#ifndef _FS_CEPH_MSGPOOL +#define _FS_CEPH_MSGPOOL + +#include +#include "messenger.h" + +/* + * we use memory pools for preallocating messages we may receive, to + * avoid unexpected OOM conditions. + */ +struct ceph_msgpool { + const char *name; + mempool_t *pool; + int front_len; /* preallocated payload size */ +}; + +extern int ceph_msgpool_init(struct ceph_msgpool *pool, + int front_len, int size, bool blocking, + const char *name); +extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); +extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, + int front_len); +extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); + +#endif diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h new file mode 100644 index 000000000000..680d3d648cac --- /dev/null +++ b/include/linux/ceph/msgr.h @@ -0,0 +1,175 @@ +#ifndef CEPH_MSGR_H +#define CEPH_MSGR_H + +/* + * Data types for message passing layer used by Ceph. + */ + +#define CEPH_MON_PORT 6789 /* default monitor port */ + +/* + * client-side processes will try to bind to ports in this + * range, simply for the benefit of tools like nmap or wireshark + * that would like to identify the protocol. + */ +#define CEPH_PORT_FIRST 6789 +#define CEPH_PORT_START 6800 /* non-monitors start here */ +#define CEPH_PORT_LAST 6900 + +/* + * tcp connection banner. include a protocol version. and adjust + * whenever the wire protocol changes. try to keep this string length + * constant. + */ +#define CEPH_BANNER "ceph v027" +#define CEPH_BANNER_MAX_LEN 30 + + +/* + * Rollover-safe type and comparator for 32-bit sequence numbers. + * Comparator returns -1, 0, or 1. + */ +typedef __u32 ceph_seq_t; + +static inline __s32 ceph_seq_cmp(__u32 a, __u32 b) +{ + return (__s32)a - (__s32)b; +} + + +/* + * entity_name -- logical name for a process participating in the + * network, e.g. 'mds0' or 'osd3'. + */ +struct ceph_entity_name { + __u8 type; /* CEPH_ENTITY_TYPE_* */ + __le64 num; +} __attribute__ ((packed)); + +#define CEPH_ENTITY_TYPE_MON 0x01 +#define CEPH_ENTITY_TYPE_MDS 0x02 +#define CEPH_ENTITY_TYPE_OSD 0x04 +#define CEPH_ENTITY_TYPE_CLIENT 0x08 +#define CEPH_ENTITY_TYPE_AUTH 0x20 + +#define CEPH_ENTITY_TYPE_ANY 0xFF + +extern const char *ceph_entity_type_name(int type); + +/* + * entity_addr -- network address + */ +struct ceph_entity_addr { + __le32 type; + __le32 nonce; /* unique id for process (e.g. pid) */ + struct sockaddr_storage in_addr; +} __attribute__ ((packed)); + +struct ceph_entity_inst { + struct ceph_entity_name name; + struct ceph_entity_addr addr; +} __attribute__ ((packed)); + + +/* used by message exchange protocol */ +#define CEPH_MSGR_TAG_READY 1 /* server->client: ready for messages */ +#define CEPH_MSGR_TAG_RESETSESSION 2 /* server->client: reset, try again */ +#define CEPH_MSGR_TAG_WAIT 3 /* server->client: wait for racing + incoming connection */ +#define CEPH_MSGR_TAG_RETRY_SESSION 4 /* server->client + cseq: try again + with higher cseq */ +#define CEPH_MSGR_TAG_RETRY_GLOBAL 5 /* server->client + gseq: try again + with higher gseq */ +#define CEPH_MSGR_TAG_CLOSE 6 /* closing pipe */ +#define CEPH_MSGR_TAG_MSG 7 /* message */ +#define CEPH_MSGR_TAG_ACK 8 /* message ack */ +#define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ +#define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ + + +/* + * connection negotiation + */ +struct ceph_msg_connect { + __le64 features; /* supported feature bits */ + __le32 host_type; /* CEPH_ENTITY_TYPE_* */ + __le32 global_seq; /* count connections initiated by this host */ + __le32 connect_seq; /* count connections initiated in this session */ + __le32 protocol_version; + __le32 authorizer_protocol; + __le32 authorizer_len; + __u8 flags; /* CEPH_MSG_CONNECT_* */ +} __attribute__ ((packed)); + +struct ceph_msg_connect_reply { + __u8 tag; + __le64 features; /* feature bits for this session */ + __le32 global_seq; + __le32 connect_seq; + __le32 protocol_version; + __le32 authorizer_len; + __u8 flags; +} __attribute__ ((packed)); + +#define CEPH_MSG_CONNECT_LOSSY 1 /* messages i send may be safely dropped */ + + +/* + * message header + */ +struct ceph_msg_header_old { + __le64 seq; /* message seq# for this session */ + __le64 tid; /* transaction id */ + __le16 type; /* message type */ + __le16 priority; /* priority. higher value == higher priority */ + __le16 version; /* version of message encoding */ + + __le32 front_len; /* bytes in main payload */ + __le32 middle_len;/* bytes in middle payload */ + __le32 data_len; /* bytes of data payload */ + __le16 data_off; /* sender: include full offset; + receiver: mask against ~PAGE_MASK */ + + struct ceph_entity_inst src, orig_src; + __le32 reserved; + __le32 crc; /* header crc32c */ +} __attribute__ ((packed)); + +struct ceph_msg_header { + __le64 seq; /* message seq# for this session */ + __le64 tid; /* transaction id */ + __le16 type; /* message type */ + __le16 priority; /* priority. higher value == higher priority */ + __le16 version; /* version of message encoding */ + + __le32 front_len; /* bytes in main payload */ + __le32 middle_len;/* bytes in middle payload */ + __le32 data_len; /* bytes of data payload */ + __le16 data_off; /* sender: include full offset; + receiver: mask against ~PAGE_MASK */ + + struct ceph_entity_name src; + __le32 reserved; + __le32 crc; /* header crc32c */ +} __attribute__ ((packed)); + +#define CEPH_MSG_PRIO_LOW 64 +#define CEPH_MSG_PRIO_DEFAULT 127 +#define CEPH_MSG_PRIO_HIGH 196 +#define CEPH_MSG_PRIO_HIGHEST 255 + +/* + * follows data payload + */ +struct ceph_msg_footer { + __le32 front_crc, middle_crc, data_crc; + __u8 flags; +} __attribute__ ((packed)); + +#define CEPH_MSG_FOOTER_COMPLETE (1<<0) /* msg wasn't aborted */ +#define CEPH_MSG_FOOTER_NOCRC (1<<1) /* no data crc */ + + +#endif diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h new file mode 100644 index 000000000000..6c91fb032c39 --- /dev/null +++ b/include/linux/ceph/osd_client.h @@ -0,0 +1,234 @@ +#ifndef _FS_CEPH_OSD_CLIENT_H +#define _FS_CEPH_OSD_CLIENT_H + +#include +#include +#include +#include + +#include "types.h" +#include "osdmap.h" +#include "messenger.h" + +struct ceph_msg; +struct ceph_snap_context; +struct ceph_osd_request; +struct ceph_osd_client; +struct ceph_authorizer; +struct ceph_pagelist; + +/* + * completion callback for async writepages + */ +typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *, + struct ceph_msg *); + +/* a given osd we're communicating with */ +struct ceph_osd { + atomic_t o_ref; + struct ceph_osd_client *o_osdc; + int o_osd; + int o_incarnation; + struct rb_node o_node; + struct ceph_connection o_con; + struct list_head o_requests; + struct list_head o_osd_lru; + struct ceph_authorizer *o_authorizer; + void *o_authorizer_buf, *o_authorizer_reply_buf; + size_t o_authorizer_buf_len, o_authorizer_reply_buf_len; + unsigned long lru_ttl; + int o_marked_for_keepalive; + struct list_head o_keepalive_item; +}; + +/* an in-flight request */ +struct ceph_osd_request { + u64 r_tid; /* unique for this client */ + struct rb_node r_node; + struct list_head r_req_lru_item; + struct list_head r_osd_item; + struct ceph_osd *r_osd; + struct ceph_pg r_pgid; + int r_pg_osds[CEPH_PG_MAX_SIZE]; + int r_num_pg_osds; + + struct ceph_connection *r_con_filling_msg; + + struct ceph_msg *r_request, *r_reply; + int r_result; + int r_flags; /* any additional flags for the osd */ + u32 r_sent; /* >0 if r_request is sending/sent */ + int r_got_reply; + + struct ceph_osd_client *r_osdc; + struct kref r_kref; + bool r_mempool; + struct completion r_completion, r_safe_completion; + ceph_osdc_callback_t r_callback, r_safe_callback; + struct ceph_eversion r_reassert_version; + struct list_head r_unsafe_item; + + struct inode *r_inode; /* for use by callbacks */ + void *r_priv; /* ditto */ + + char r_oid[40]; /* object name */ + int r_oid_len; + unsigned long r_stamp; /* send OR check time */ + bool r_resend; /* msg send failed, needs retry */ + + struct ceph_file_layout r_file_layout; + struct ceph_snap_context *r_snapc; /* snap context for writes */ + unsigned r_num_pages; /* size of page array (follows) */ + struct page **r_pages; /* pages for data payload */ + int r_pages_from_pool; + int r_own_pages; /* if true, i own page list */ +#ifdef CONFIG_BLOCK + struct bio *r_bio; /* instead of pages */ +#endif + + struct ceph_pagelist *r_trail; /* trailing part of the data */ +}; + +struct ceph_osd_client { + struct ceph_client *client; + + struct ceph_osdmap *osdmap; /* current map */ + struct rw_semaphore map_sem; + struct completion map_waiters; + u64 last_requested_map; + + struct mutex request_mutex; + struct rb_root osds; /* osds */ + struct list_head osd_lru; /* idle osds */ + u64 timeout_tid; /* tid of timeout triggering rq */ + u64 last_tid; /* tid of last request */ + struct rb_root requests; /* pending requests */ + struct list_head req_lru; /* pending requests lru */ + int num_requests; + struct delayed_work timeout_work; + struct delayed_work osds_timeout_work; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_file; +#endif + + mempool_t *req_mempool; + + struct ceph_msgpool msgpool_op; + struct ceph_msgpool msgpool_op_reply; +}; + +struct ceph_osd_req_op { + u16 op; /* CEPH_OSD_OP_* */ + u32 flags; /* CEPH_OSD_FLAG_* */ + union { + struct { + u64 offset, length; + u64 truncate_size; + u32 truncate_seq; + } extent; + struct { + const char *name; + u32 name_len; + const char *val; + u32 value_len; + __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ + __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ + } xattr; + struct { + const char *class_name; + __u8 class_len; + const char *method_name; + __u8 method_len; + __u8 argc; + const char *indata; + u32 indata_len; + } cls; + struct { + u64 cookie, count; + } pgls; + struct { + u64 snapid; + } snap; + }; + u32 payload_len; +}; + +extern int ceph_osdc_init(struct ceph_osd_client *osdc, + struct ceph_client *client); +extern void ceph_osdc_stop(struct ceph_osd_client *osdc); + +extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, + struct ceph_msg *msg); +extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, + struct ceph_msg *msg); + +extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc, + struct ceph_file_layout *layout, + u64 snapid, + u64 off, u64 *plen, u64 *bno, + struct ceph_osd_request *req, + struct ceph_osd_req_op *op); + +extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, + int flags, + struct ceph_snap_context *snapc, + struct ceph_osd_req_op *ops, + bool use_mempool, + gfp_t gfp_flags, + struct page **pages, + struct bio *bio); + +extern void ceph_osdc_build_request(struct ceph_osd_request *req, + u64 off, u64 *plen, + struct ceph_osd_req_op *src_ops, + struct ceph_snap_context *snapc, + struct timespec *mtime, + const char *oid, + int oid_len); + +extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, + struct ceph_file_layout *layout, + struct ceph_vino vino, + u64 offset, u64 *len, int op, int flags, + struct ceph_snap_context *snapc, + int do_sync, u32 truncate_seq, + u64 truncate_size, + struct timespec *mtime, + bool use_mempool, int num_reply); + +static inline void ceph_osdc_get_request(struct ceph_osd_request *req) +{ + kref_get(&req->r_kref); +} +extern void ceph_osdc_release_request(struct kref *kref); +static inline void ceph_osdc_put_request(struct ceph_osd_request *req) +{ + kref_put(&req->r_kref, ceph_osdc_release_request); +} + +extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req, + bool nofail); +extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); +extern void ceph_osdc_sync(struct ceph_osd_client *osdc); + +extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + u64 off, u64 *plen, + u32 truncate_seq, u64 truncate_size, + struct page **pages, int nr_pages); + +extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + struct ceph_snap_context *sc, + u64 off, u64 len, + u32 truncate_seq, u64 truncate_size, + struct timespec *mtime, + struct page **pages, int nr_pages, + int flags, int do_sync, bool nofail); + +#endif + diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h new file mode 100644 index 000000000000..ba4c205cbb01 --- /dev/null +++ b/include/linux/ceph/osdmap.h @@ -0,0 +1,130 @@ +#ifndef _FS_CEPH_OSDMAP_H +#define _FS_CEPH_OSDMAP_H + +#include +#include "types.h" +#include "ceph_fs.h" +#include + +/* + * The osd map describes the current membership of the osd cluster and + * specifies the mapping of objects to placement groups and placement + * groups to (sets of) osds. That is, it completely specifies the + * (desired) distribution of all data objects in the system at some + * point in time. + * + * Each map version is identified by an epoch, which increases monotonically. + * + * The map can be updated either via an incremental map (diff) describing + * the change between two successive epochs, or as a fully encoded map. + */ +struct ceph_pg_pool_info { + struct rb_node node; + int id; + struct ceph_pg_pool v; + int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; + char *name; +}; + +struct ceph_pg_mapping { + struct rb_node node; + struct ceph_pg pgid; + int len; + int osds[]; +}; + +struct ceph_osdmap { + struct ceph_fsid fsid; + u32 epoch; + u32 mkfs_epoch; + struct ceph_timespec created, modified; + + u32 flags; /* CEPH_OSDMAP_* */ + + u32 max_osd; /* size of osd_state, _offload, _addr arrays */ + u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ + struct ceph_entity_addr *osd_addr; + + struct rb_root pg_temp; + struct rb_root pg_pools; + u32 pool_max; + + /* the CRUSH map specifies the mapping of placement groups to + * the list of osds that store+replicate them. */ + struct crush_map *crush; +}; + +/* + * file layout helpers + */ +#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) +#define ceph_file_layout_stripe_count(l) \ + ((__s32)le32_to_cpu((l).fl_stripe_count)) +#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) +#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) +#define ceph_file_layout_object_su(l) \ + ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) +#define ceph_file_layout_pg_preferred(l) \ + ((__s32)le32_to_cpu((l).fl_pg_preferred)) +#define ceph_file_layout_pg_pool(l) \ + ((__s32)le32_to_cpu((l).fl_pg_pool)) + +static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_stripe_unit) * + le32_to_cpu(l->fl_stripe_count); +} + +/* "period" == bytes before i start on a new set of objects */ +static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_object_size) * + le32_to_cpu(l->fl_stripe_count); +} + + +static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) +{ + return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); +} + +static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag) +{ + return map && (map->flags & flag); +} + +extern char *ceph_osdmap_state_str(char *str, int len, int state); + +static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, + int osd) +{ + if (osd >= map->max_osd) + return NULL; + return &map->osd_addr[osd]; +} + +extern struct ceph_osdmap *osdmap_decode(void **p, void *end); +extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, + struct ceph_osdmap *map, + struct ceph_messenger *msgr); +extern void ceph_osdmap_destroy(struct ceph_osdmap *map); + +/* calculate mapping of a file extent to an object */ +extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, + u64 off, u64 *plen, + u64 *bno, u64 *oxoff, u64 *oxlen); + +/* calculate mapping of object to a placement group */ +extern int ceph_calc_object_layout(struct ceph_object_layout *ol, + const char *oid, + struct ceph_file_layout *fl, + struct ceph_osdmap *osdmap); +extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, + int *acting); +extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, + struct ceph_pg pgid); + +extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); + +#endif diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h new file mode 100644 index 000000000000..cc9327aa1c98 --- /dev/null +++ b/include/linux/ceph/pagelist.h @@ -0,0 +1,54 @@ +#ifndef __FS_CEPH_PAGELIST_H +#define __FS_CEPH_PAGELIST_H + +#include + +struct ceph_pagelist { + struct list_head head; + void *mapped_tail; + size_t length; + size_t room; +}; + +static inline void ceph_pagelist_init(struct ceph_pagelist *pl) +{ + INIT_LIST_HEAD(&pl->head); + pl->mapped_tail = NULL; + pl->length = 0; + pl->room = 0; +} +extern int ceph_pagelist_release(struct ceph_pagelist *pl); + +extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l); + +static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v) +{ + __le64 ev = cpu_to_le64(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_32(struct ceph_pagelist *pl, u32 v) +{ + __le32 ev = cpu_to_le32(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_16(struct ceph_pagelist *pl, u16 v) +{ + __le16 ev = cpu_to_le16(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v) +{ + return ceph_pagelist_append(pl, &v, 1); +} +static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl, + char *s, size_t len) +{ + int ret = ceph_pagelist_encode_32(pl, len); + if (ret) + return ret; + if (len) + return ceph_pagelist_append(pl, s, len); + return 0; +} + +#endif diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h new file mode 100644 index 000000000000..6d5247f2e81b --- /dev/null +++ b/include/linux/ceph/rados.h @@ -0,0 +1,405 @@ +#ifndef CEPH_RADOS_H +#define CEPH_RADOS_H + +/* + * Data types for the Ceph distributed object storage layer RADOS + * (Reliable Autonomic Distributed Object Store). + */ + +#include "msgr.h" + +/* + * osdmap encoding versions + */ +#define CEPH_OSDMAP_INC_VERSION 5 +#define CEPH_OSDMAP_INC_VERSION_EXT 5 +#define CEPH_OSDMAP_VERSION 5 +#define CEPH_OSDMAP_VERSION_EXT 5 + +/* + * fs id + */ +struct ceph_fsid { + unsigned char fsid[16]; +}; + +static inline int ceph_fsid_compare(const struct ceph_fsid *a, + const struct ceph_fsid *b) +{ + return memcmp(a, b, sizeof(*a)); +} + +/* + * ino, object, etc. + */ +typedef __le64 ceph_snapid_t; +#define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */ +#define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */ +#define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */ + +struct ceph_timespec { + __le32 tv_sec; + __le32 tv_nsec; +} __attribute__ ((packed)); + + +/* + * object layout - how objects are mapped into PGs + */ +#define CEPH_OBJECT_LAYOUT_HASH 1 +#define CEPH_OBJECT_LAYOUT_LINEAR 2 +#define CEPH_OBJECT_LAYOUT_HASHINO 3 + +/* + * pg layout -- how PGs are mapped onto (sets of) OSDs + */ +#define CEPH_PG_LAYOUT_CRUSH 0 +#define CEPH_PG_LAYOUT_HASH 1 +#define CEPH_PG_LAYOUT_LINEAR 2 +#define CEPH_PG_LAYOUT_HYBRID 3 + +#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */ + +/* + * placement group. + * we encode this into one __le64. + */ +struct ceph_pg { + __le16 preferred; /* preferred primary osd */ + __le16 ps; /* placement seed */ + __le32 pool; /* object pool */ +} __attribute__ ((packed)); + +/* + * pg_pool is a set of pgs storing a pool of objects + * + * pg_num -- base number of pseudorandomly placed pgs + * + * pgp_num -- effective number when calculating pg placement. this + * is used for pg_num increases. new pgs result in data being "split" + * into new pgs. for this to proceed smoothly, new pgs are intiially + * colocated with their parents; that is, pgp_num doesn't increase + * until the new pgs have successfully split. only _then_ are the new + * pgs placed independently. + * + * lpg_num -- localized pg count (per device). replicas are randomly + * selected. + * + * lpgp_num -- as above. + */ +#define CEPH_PG_TYPE_REP 1 +#define CEPH_PG_TYPE_RAID4 2 +#define CEPH_PG_POOL_VERSION 2 +struct ceph_pg_pool { + __u8 type; /* CEPH_PG_TYPE_* */ + __u8 size; /* number of osds in each pg */ + __u8 crush_ruleset; /* crush placement rule */ + __u8 object_hash; /* hash mapping object name to ps */ + __le32 pg_num, pgp_num; /* number of pg's */ + __le32 lpg_num, lpgp_num; /* number of localized pg's */ + __le32 last_change; /* most recent epoch changed */ + __le64 snap_seq; /* seq for per-pool snapshot */ + __le32 snap_epoch; /* epoch of last snap */ + __le32 num_snaps; + __le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */ + __le64 auid; /* who owns the pg */ +} __attribute__ ((packed)); + +/* + * stable_mod func is used to control number of placement groups. + * similar to straight-up modulo, but produces a stable mapping as b + * increases over time. b is the number of bins, and bmask is the + * containing power of 2 minus 1. + * + * b <= bmask and bmask=(2**n)-1 + * e.g., b=12 -> bmask=15, b=123 -> bmask=127 + */ +static inline int ceph_stable_mod(int x, int b, int bmask) +{ + if ((x & bmask) < b) + return x & bmask; + else + return x & (bmask >> 1); +} + +/* + * object layout - how a given object should be stored. + */ +struct ceph_object_layout { + struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */ + __le32 ol_stripe_unit; /* for per-object parity, if any */ +} __attribute__ ((packed)); + +/* + * compound epoch+version, used by storage layer to serialize mutations + */ +struct ceph_eversion { + __le32 epoch; + __le64 version; +} __attribute__ ((packed)); + +/* + * osd map bits + */ + +/* status bits */ +#define CEPH_OSD_EXISTS 1 +#define CEPH_OSD_UP 2 + +/* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ +#define CEPH_OSD_IN 0x10000 +#define CEPH_OSD_OUT 0 + + +/* + * osd map flag bits + */ +#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */ +#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */ +#define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ +#define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ +#define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ + +/* + * osd ops + */ +#define CEPH_OSD_OP_MODE 0xf000 +#define CEPH_OSD_OP_MODE_RD 0x1000 +#define CEPH_OSD_OP_MODE_WR 0x2000 +#define CEPH_OSD_OP_MODE_RMW 0x3000 +#define CEPH_OSD_OP_MODE_SUB 0x4000 + +#define CEPH_OSD_OP_TYPE 0x0f00 +#define CEPH_OSD_OP_TYPE_LOCK 0x0100 +#define CEPH_OSD_OP_TYPE_DATA 0x0200 +#define CEPH_OSD_OP_TYPE_ATTR 0x0300 +#define CEPH_OSD_OP_TYPE_EXEC 0x0400 +#define CEPH_OSD_OP_TYPE_PG 0x0500 + +enum { + /** data **/ + /* read */ + CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1, + CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2, + + /* fancy read */ + CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4, + + /* write */ + CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1, + CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2, + CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3, + CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4, + CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5, + + /* fancy write */ + CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6, + CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7, + CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8, + CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9, + + CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10, + CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11, + CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12, + + CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13, + CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14, + + /** attrs **/ + /* read */ + CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1, + CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2, + CEPH_OSD_OP_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3, + + /* write */ + CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1, + CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2, + CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3, + CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4, + + /** subop **/ + CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB | 1, + CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB | 2, + CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB | 3, + CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4, + CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB | 5, + + /** lock **/ + CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1, + CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2, + CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3, + CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4, + CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5, + CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6, + + /** exec **/ + CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1, + + /** pg **/ + CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1, +}; + +static inline int ceph_osd_op_type_lock(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK; +} +static inline int ceph_osd_op_type_data(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA; +} +static inline int ceph_osd_op_type_attr(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR; +} +static inline int ceph_osd_op_type_exec(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC; +} +static inline int ceph_osd_op_type_pg(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG; +} + +static inline int ceph_osd_op_mode_subop(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB; +} +static inline int ceph_osd_op_mode_read(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD; +} +static inline int ceph_osd_op_mode_modify(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR; +} + +/* + * note that the following tmap stuff is also defined in the ceph librados.h + * any modification here needs to be updated there + */ +#define CEPH_OSD_TMAP_HDR 'h' +#define CEPH_OSD_TMAP_SET 's' +#define CEPH_OSD_TMAP_RM 'r' + +extern const char *ceph_osd_op_name(int op); + + +/* + * osd op flags + * + * An op may be READ, WRITE, or READ|WRITE. + */ +enum { + CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */ + CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */ + CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */ + CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */ + CEPH_OSD_FLAG_READ = 16, /* op may read */ + CEPH_OSD_FLAG_WRITE = 32, /* op may write */ + CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */ + CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */ + CEPH_OSD_FLAG_BALANCE_READS = 256, + CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */ + CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */ + CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */ + CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */ +}; + +enum { + CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ +}; + +#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ +#define EBLACKLISTED ESHUTDOWN /* blacklisted */ + +/* xattr comparison */ +enum { + CEPH_OSD_CMPXATTR_OP_NOP = 0, + CEPH_OSD_CMPXATTR_OP_EQ = 1, + CEPH_OSD_CMPXATTR_OP_NE = 2, + CEPH_OSD_CMPXATTR_OP_GT = 3, + CEPH_OSD_CMPXATTR_OP_GTE = 4, + CEPH_OSD_CMPXATTR_OP_LT = 5, + CEPH_OSD_CMPXATTR_OP_LTE = 6 +}; + +enum { + CEPH_OSD_CMPXATTR_MODE_STRING = 1, + CEPH_OSD_CMPXATTR_MODE_U64 = 2 +}; + +/* + * an individual object operation. each may be accompanied by some data + * payload + */ +struct ceph_osd_op { + __le16 op; /* CEPH_OSD_OP_* */ + __le32 flags; /* CEPH_OSD_FLAG_* */ + union { + struct { + __le64 offset, length; + __le64 truncate_size; + __le32 truncate_seq; + } __attribute__ ((packed)) extent; + struct { + __le32 name_len; + __le32 value_len; + __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ + __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ + } __attribute__ ((packed)) xattr; + struct { + __u8 class_len; + __u8 method_len; + __u8 argc; + __le32 indata_len; + } __attribute__ ((packed)) cls; + struct { + __le64 cookie, count; + } __attribute__ ((packed)) pgls; + struct { + __le64 snapid; + } __attribute__ ((packed)) snap; + }; + __le32 payload_len; +} __attribute__ ((packed)); + +/* + * osd request message header. each request may include multiple + * ceph_osd_op object operations. + */ +struct ceph_osd_request_head { + __le32 client_inc; /* client incarnation */ + struct ceph_object_layout layout; /* pgid */ + __le32 osdmap_epoch; /* client's osdmap epoch */ + + __le32 flags; + + struct ceph_timespec mtime; /* for mutations only */ + struct ceph_eversion reassert_version; /* if we are replaying op */ + + __le32 object_len; /* length of object name */ + + __le64 snapid; /* snapid to read */ + __le64 snap_seq; /* writer's snap context */ + __le32 num_snaps; + + __le16 num_ops; + struct ceph_osd_op ops[]; /* followed by ops[], obj, ticket, snaps */ +} __attribute__ ((packed)); + +struct ceph_osd_reply_head { + __le32 client_inc; /* client incarnation */ + __le32 flags; + struct ceph_object_layout layout; + __le32 osdmap_epoch; + struct ceph_eversion reassert_version; /* for replaying uncommitted */ + + __le32 result; /* result code */ + + __le32 object_len; /* length of object name */ + __le32 num_ops; + struct ceph_osd_op ops[0]; /* ops[], object */ +} __attribute__ ((packed)); + + +#endif diff --git a/include/linux/ceph/types.h b/include/linux/ceph/types.h new file mode 100644 index 000000000000..28b35a005ec2 --- /dev/null +++ b/include/linux/ceph/types.h @@ -0,0 +1,29 @@ +#ifndef _FS_CEPH_TYPES_H +#define _FS_CEPH_TYPES_H + +/* needed before including ceph_fs.h */ +#include +#include +#include +#include + +#include "ceph_fs.h" +#include "ceph_frag.h" +#include "ceph_hash.h" + +/* + * Identify inodes by both their ino AND snapshot id (a u64). + */ +struct ceph_vino { + u64 ino; + u64 snap; +}; + + +/* context for the caps reservation mechanism */ +struct ceph_cap_reservation { + int count; +}; + + +#endif diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h new file mode 100644 index 000000000000..97e435b191f4 --- /dev/null +++ b/include/linux/crush/crush.h @@ -0,0 +1,180 @@ +#ifndef CEPH_CRUSH_CRUSH_H +#define CEPH_CRUSH_CRUSH_H + +#include + +/* + * CRUSH is a pseudo-random data distribution algorithm that + * efficiently distributes input values (typically, data objects) + * across a heterogeneous, structured storage cluster. + * + * The algorithm was originally described in detail in this paper + * (although the algorithm has evolved somewhat since then): + * + * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf + * + * LGPL2 + */ + + +#define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ + + +#define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ +#define CRUSH_MAX_SET 10 /* max size of a mapping result */ + + +/* + * CRUSH uses user-defined "rules" to describe how inputs should be + * mapped to devices. A rule consists of sequence of steps to perform + * to generate the set of output devices. + */ +struct crush_rule_step { + __u32 op; + __s32 arg1; + __s32 arg2; +}; + +/* step op codes */ +enum { + CRUSH_RULE_NOOP = 0, + CRUSH_RULE_TAKE = 1, /* arg1 = value to start with */ + CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */ + /* arg2 = type */ + CRUSH_RULE_CHOOSE_INDEP = 3, /* same */ + CRUSH_RULE_EMIT = 4, /* no args */ + CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, + CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, +}; + +/* + * for specifying choose num (arg1) relative to the max parameter + * passed to do_rule + */ +#define CRUSH_CHOOSE_N 0 +#define CRUSH_CHOOSE_N_MINUS(x) (-(x)) + +/* + * The rule mask is used to describe what the rule is intended for. + * Given a ruleset and size of output set, we search through the + * rule list for a matching rule_mask. + */ +struct crush_rule_mask { + __u8 ruleset; + __u8 type; + __u8 min_size; + __u8 max_size; +}; + +struct crush_rule { + __u32 len; + struct crush_rule_mask mask; + struct crush_rule_step steps[0]; +}; + +#define crush_rule_size(len) (sizeof(struct crush_rule) + \ + (len)*sizeof(struct crush_rule_step)) + + + +/* + * A bucket is a named container of other items (either devices or + * other buckets). Items within a bucket are chosen using one of a + * few different algorithms. The table summarizes how the speed of + * each option measures up against mapping stability when items are + * added or removed. + * + * Bucket Alg Speed Additions Removals + * ------------------------------------------------ + * uniform O(1) poor poor + * list O(n) optimal poor + * tree O(log n) good good + * straw O(n) optimal optimal + */ +enum { + CRUSH_BUCKET_UNIFORM = 1, + CRUSH_BUCKET_LIST = 2, + CRUSH_BUCKET_TREE = 3, + CRUSH_BUCKET_STRAW = 4 +}; +extern const char *crush_bucket_alg_name(int alg); + +struct crush_bucket { + __s32 id; /* this'll be negative */ + __u16 type; /* non-zero; type=0 is reserved for devices */ + __u8 alg; /* one of CRUSH_BUCKET_* */ + __u8 hash; /* which hash function to use, CRUSH_HASH_* */ + __u32 weight; /* 16-bit fixed point */ + __u32 size; /* num items */ + __s32 *items; + + /* + * cached random permutation: used for uniform bucket and for + * the linear search fallback for the other bucket types. + */ + __u32 perm_x; /* @x for which *perm is defined */ + __u32 perm_n; /* num elements of *perm that are permuted/defined */ + __u32 *perm; +}; + +struct crush_bucket_uniform { + struct crush_bucket h; + __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ +}; + +struct crush_bucket_list { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *sum_weights; /* 16-bit fixed point. element i is sum + of weights 0..i, inclusive */ +}; + +struct crush_bucket_tree { + struct crush_bucket h; /* note: h.size is _tree_ size, not number of + actual items */ + __u8 num_nodes; + __u32 *node_weights; +}; + +struct crush_bucket_straw { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *straws; /* 16-bit fixed point */ +}; + + + +/* + * CRUSH map includes all buckets, rules, etc. + */ +struct crush_map { + struct crush_bucket **buckets; + struct crush_rule **rules; + + /* + * Parent pointers to identify the parent bucket a device or + * bucket in the hierarchy. If an item appears more than + * once, this is the _last_ time it appeared (where buckets + * are processed in bucket id order, from -1 on down to + * -max_buckets. + */ + __u32 *bucket_parents; + __u32 *device_parents; + + __s32 max_buckets; + __u32 max_rules; + __s32 max_devices; +}; + + +/* crush.c */ +extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos); +extern void crush_calc_parents(struct crush_map *map); +extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b); +extern void crush_destroy_bucket_list(struct crush_bucket_list *b); +extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b); +extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b); +extern void crush_destroy_bucket(struct crush_bucket *b); +extern void crush_destroy(struct crush_map *map); + +#endif diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h new file mode 100644 index 000000000000..91e884230d5d --- /dev/null +++ b/include/linux/crush/hash.h @@ -0,0 +1,17 @@ +#ifndef CEPH_CRUSH_HASH_H +#define CEPH_CRUSH_HASH_H + +#define CRUSH_HASH_RJENKINS1 0 + +#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 + +extern const char *crush_hash_name(int type); + +extern __u32 crush_hash32(int type, __u32 a); +extern __u32 crush_hash32_2(int type, __u32 a, __u32 b); +extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c); +extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d); +extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, + __u32 e); + +#endif diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h new file mode 100644 index 000000000000..c46b99c18bb0 --- /dev/null +++ b/include/linux/crush/mapper.h @@ -0,0 +1,20 @@ +#ifndef CEPH_CRUSH_MAPPER_H +#define CEPH_CRUSH_MAPPER_H + +/* + * CRUSH functions for find rules and then mapping an input to an + * output set. + * + * LGPL2 + */ + +#include "crush.h" + +extern int crush_find_rule(struct crush_map *map, int pool, int type, int size); +extern int crush_do_rule(struct crush_map *map, + int ruleno, + int x, int *result, int result_max, + int forcefeed, /* -1 for none */ + __u32 *weights); + +#endif diff --git a/net/Kconfig b/net/Kconfig index e926884c1675..55fd82e9ffd9 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -293,6 +293,7 @@ source "net/wimax/Kconfig" source "net/rfkill/Kconfig" source "net/9p/Kconfig" source "net/caif/Kconfig" +source "net/ceph/Kconfig" endif # if NET diff --git a/net/Makefile b/net/Makefile index ea60fbce9b1b..6b7bfd7f1416 100644 --- a/net/Makefile +++ b/net/Makefile @@ -68,3 +68,4 @@ obj-$(CONFIG_SYSCTL) += sysctl_net.o endif obj-$(CONFIG_WIMAX) += wimax/ obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/ +obj-$(CONFIG_CEPH_LIB) += ceph/ diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig new file mode 100644 index 000000000000..ad424049b0cf --- /dev/null +++ b/net/ceph/Kconfig @@ -0,0 +1,28 @@ +config CEPH_LIB + tristate "Ceph core library (EXPERIMENTAL)" + depends on INET && EXPERIMENTAL + select LIBCRC32C + select CRYPTO_AES + select CRYPTO + default n + help + Choose Y or M here to include cephlib, which provides the + common functionality to both the Ceph filesystem and + to the rados block device (rbd). + + More information at http://ceph.newdream.net/. + + If unsure, say N. + +config CEPH_LIB_PRETTYDEBUG + bool "Include file:line in ceph debug output" + depends on CEPH_LIB + default n + help + If you say Y here, debug output will include a filename and + line to aid debugging. This increases kernel size and slows + execution slightly when debug call sites are enabled (e.g., + via CONFIG_DYNAMIC_DEBUG). + + If unsure, say N. + diff --git a/net/ceph/Makefile b/net/ceph/Makefile new file mode 100644 index 000000000000..aab1cabb8035 --- /dev/null +++ b/net/ceph/Makefile @@ -0,0 +1,37 @@ +# +# Makefile for CEPH filesystem. +# + +ifneq ($(KERNELRELEASE),) + +obj-$(CONFIG_CEPH_LIB) += libceph.o + +libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ + mon_client.o \ + osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \ + debugfs.o \ + auth.o auth_none.o \ + crypto.o armor.o \ + auth_x.o \ + ceph_fs.o ceph_strings.o ceph_hash.o \ + pagevec.o + +else +#Otherwise we were called directly from the command +# line; invoke the kernel build system. + +KERNELDIR ?= /lib/modules/$(shell uname -r)/build +PWD := $(shell pwd) + +default: all + +all: + $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules + +modules_install: + $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install + +clean: + $(MAKE) -C $(KERNELDIR) M=$(PWD) clean + +endif diff --git a/net/ceph/armor.c b/net/ceph/armor.c new file mode 100644 index 000000000000..eb2a666b0be7 --- /dev/null +++ b/net/ceph/armor.c @@ -0,0 +1,103 @@ + +#include + +int ceph_armor(char *dst, const char *src, const char *end); +int ceph_unarmor(char *dst, const char *src, const char *end); + +/* + * base64 encode/decode. + */ + +static const char *pem_key = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; + +static int encode_bits(int c) +{ + return pem_key[c]; +} + +static int decode_bits(char c) +{ + if (c >= 'A' && c <= 'Z') + return c - 'A'; + if (c >= 'a' && c <= 'z') + return c - 'a' + 26; + if (c >= '0' && c <= '9') + return c - '0' + 52; + if (c == '+') + return 62; + if (c == '/') + return 63; + if (c == '=') + return 0; /* just non-negative, please */ + return -EINVAL; +} + +int ceph_armor(char *dst, const char *src, const char *end) +{ + int olen = 0; + int line = 0; + + while (src < end) { + unsigned char a, b, c; + + a = *src++; + *dst++ = encode_bits(a >> 2); + if (src < end) { + b = *src++; + *dst++ = encode_bits(((a & 3) << 4) | (b >> 4)); + if (src < end) { + c = *src++; + *dst++ = encode_bits(((b & 15) << 2) | + (c >> 6)); + *dst++ = encode_bits(c & 63); + } else { + *dst++ = encode_bits((b & 15) << 2); + *dst++ = '='; + } + } else { + *dst++ = encode_bits(((a & 3) << 4)); + *dst++ = '='; + *dst++ = '='; + } + olen += 4; + line += 4; + if (line == 64) { + line = 0; + *(dst++) = '\n'; + olen++; + } + } + return olen; +} + +int ceph_unarmor(char *dst, const char *src, const char *end) +{ + int olen = 0; + + while (src < end) { + int a, b, c, d; + + if (src < end && src[0] == '\n') + src++; + if (src + 4 > end) + return -EINVAL; + a = decode_bits(src[0]); + b = decode_bits(src[1]); + c = decode_bits(src[2]); + d = decode_bits(src[3]); + if (a < 0 || b < 0 || c < 0 || d < 0) + return -EINVAL; + + *dst++ = (a << 2) | (b >> 4); + if (src[2] == '=') + return olen + 1; + *dst++ = ((b & 15) << 4) | (c >> 2); + if (src[3] == '=') + return olen + 2; + *dst++ = ((c & 3) << 6) | d; + olen += 3; + src += 4; + } + return olen; +} diff --git a/net/ceph/auth.c b/net/ceph/auth.c new file mode 100644 index 000000000000..549c1f43e1d5 --- /dev/null +++ b/net/ceph/auth.c @@ -0,0 +1,259 @@ +#include + +#include +#include +#include + +#include +#include +#include +#include +#include "auth_none.h" +#include "auth_x.h" + + +/* + * get protocol handler + */ +static u32 supported_protocols[] = { + CEPH_AUTH_NONE, + CEPH_AUTH_CEPHX +}; + +static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol) +{ + switch (protocol) { + case CEPH_AUTH_NONE: + return ceph_auth_none_init(ac); + case CEPH_AUTH_CEPHX: + return ceph_x_init(ac); + default: + return -ENOENT; + } +} + +/* + * setup, teardown. + */ +struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) +{ + struct ceph_auth_client *ac; + int ret; + + dout("auth_init name '%s' secret '%s'\n", name, secret); + + ret = -ENOMEM; + ac = kzalloc(sizeof(*ac), GFP_NOFS); + if (!ac) + goto out; + + ac->negotiating = true; + if (name) + ac->name = name; + else + ac->name = CEPH_AUTH_NAME_DEFAULT; + dout("auth_init name %s secret %s\n", ac->name, secret); + ac->secret = secret; + return ac; + +out: + return ERR_PTR(ret); +} + +void ceph_auth_destroy(struct ceph_auth_client *ac) +{ + dout("auth_destroy %p\n", ac); + if (ac->ops) + ac->ops->destroy(ac); + kfree(ac); +} + +/* + * Reset occurs when reconnecting to the monitor. + */ +void ceph_auth_reset(struct ceph_auth_client *ac) +{ + dout("auth_reset %p\n", ac); + if (ac->ops && !ac->negotiating) + ac->ops->reset(ac); + ac->negotiating = true; +} + +int ceph_entity_name_encode(const char *name, void **p, void *end) +{ + int len = strlen(name); + + if (*p + 2*sizeof(u32) + len > end) + return -ERANGE; + ceph_encode_32(p, CEPH_ENTITY_TYPE_CLIENT); + ceph_encode_32(p, len); + ceph_encode_copy(p, name, len); + return 0; +} + +/* + * Initiate protocol negotiation with monitor. Include entity name + * and list supported protocols. + */ +int ceph_auth_build_hello(struct ceph_auth_client *ac, void *buf, size_t len) +{ + struct ceph_mon_request_header *monhdr = buf; + void *p = monhdr + 1, *end = buf + len, *lenp; + int i, num; + int ret; + + dout("auth_build_hello\n"); + monhdr->have_version = 0; + monhdr->session_mon = cpu_to_le16(-1); + monhdr->session_mon_tid = 0; + + ceph_encode_32(&p, 0); /* no protocol, yet */ + + lenp = p; + p += sizeof(u32); + + ceph_decode_need(&p, end, 1 + sizeof(u32), bad); + ceph_encode_8(&p, 1); + num = ARRAY_SIZE(supported_protocols); + ceph_encode_32(&p, num); + ceph_decode_need(&p, end, num * sizeof(u32), bad); + for (i = 0; i < num; i++) + ceph_encode_32(&p, supported_protocols[i]); + + ret = ceph_entity_name_encode(ac->name, &p, end); + if (ret < 0) + return ret; + ceph_decode_need(&p, end, sizeof(u64), bad); + ceph_encode_64(&p, ac->global_id); + + ceph_encode_32(&lenp, p - lenp - sizeof(u32)); + return p - buf; + +bad: + return -ERANGE; +} + +static int ceph_build_auth_request(struct ceph_auth_client *ac, + void *msg_buf, size_t msg_len) +{ + struct ceph_mon_request_header *monhdr = msg_buf; + void *p = monhdr + 1; + void *end = msg_buf + msg_len; + int ret; + + monhdr->have_version = 0; + monhdr->session_mon = cpu_to_le16(-1); + monhdr->session_mon_tid = 0; + + ceph_encode_32(&p, ac->protocol); + + ret = ac->ops->build_request(ac, p + sizeof(u32), end); + if (ret < 0) { + pr_err("error %d building auth method %s request\n", ret, + ac->ops->name); + return ret; + } + dout(" built request %d bytes\n", ret); + ceph_encode_32(&p, ret); + return p + ret - msg_buf; +} + +/* + * Handle auth message from monitor. + */ +int ceph_handle_auth_reply(struct ceph_auth_client *ac, + void *buf, size_t len, + void *reply_buf, size_t reply_len) +{ + void *p = buf; + void *end = buf + len; + int protocol; + s32 result; + u64 global_id; + void *payload, *payload_end; + int payload_len; + char *result_msg; + int result_msg_len; + int ret = -EINVAL; + + dout("handle_auth_reply %p %p\n", p, end); + ceph_decode_need(&p, end, sizeof(u32) * 3 + sizeof(u64), bad); + protocol = ceph_decode_32(&p); + result = ceph_decode_32(&p); + global_id = ceph_decode_64(&p); + payload_len = ceph_decode_32(&p); + payload = p; + p += payload_len; + ceph_decode_need(&p, end, sizeof(u32), bad); + result_msg_len = ceph_decode_32(&p); + result_msg = p; + p += result_msg_len; + if (p != end) + goto bad; + + dout(" result %d '%.*s' gid %llu len %d\n", result, result_msg_len, + result_msg, global_id, payload_len); + + payload_end = payload + payload_len; + + if (global_id && ac->global_id != global_id) { + dout(" set global_id %lld -> %lld\n", ac->global_id, global_id); + ac->global_id = global_id; + } + + if (ac->negotiating) { + /* server does not support our protocols? */ + if (!protocol && result < 0) { + ret = result; + goto out; + } + /* set up (new) protocol handler? */ + if (ac->protocol && ac->protocol != protocol) { + ac->ops->destroy(ac); + ac->protocol = 0; + ac->ops = NULL; + } + if (ac->protocol != protocol) { + ret = ceph_auth_init_protocol(ac, protocol); + if (ret) { + pr_err("error %d on auth protocol %d init\n", + ret, protocol); + goto out; + } + } + + ac->negotiating = false; + } + + ret = ac->ops->handle_reply(ac, result, payload, payload_end); + if (ret == -EAGAIN) { + return ceph_build_auth_request(ac, reply_buf, reply_len); + } else if (ret) { + pr_err("auth method '%s' error %d\n", ac->ops->name, ret); + return ret; + } + return 0; + +bad: + pr_err("failed to decode auth msg\n"); +out: + return ret; +} + +int ceph_build_auth(struct ceph_auth_client *ac, + void *msg_buf, size_t msg_len) +{ + if (!ac->protocol) + return ceph_auth_build_hello(ac, msg_buf, msg_len); + BUG_ON(!ac->ops); + if (ac->ops->should_authenticate(ac)) + return ceph_build_auth_request(ac, msg_buf, msg_len); + return 0; +} + +int ceph_auth_is_authenticated(struct ceph_auth_client *ac) +{ + if (!ac->ops) + return 0; + return ac->ops->is_authenticated(ac); +} diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c new file mode 100644 index 000000000000..214c2bb43d62 --- /dev/null +++ b/net/ceph/auth_none.c @@ -0,0 +1,132 @@ + +#include + +#include +#include +#include +#include + +#include +#include + +#include "auth_none.h" + +static void reset(struct ceph_auth_client *ac) +{ + struct ceph_auth_none_info *xi = ac->private; + + xi->starting = true; + xi->built_authorizer = false; +} + +static void destroy(struct ceph_auth_client *ac) +{ + kfree(ac->private); + ac->private = NULL; +} + +static int is_authenticated(struct ceph_auth_client *ac) +{ + struct ceph_auth_none_info *xi = ac->private; + + return !xi->starting; +} + +static int should_authenticate(struct ceph_auth_client *ac) +{ + struct ceph_auth_none_info *xi = ac->private; + + return xi->starting; +} + +/* + * the generic auth code decode the global_id, and we carry no actual + * authenticate state, so nothing happens here. + */ +static int handle_reply(struct ceph_auth_client *ac, int result, + void *buf, void *end) +{ + struct ceph_auth_none_info *xi = ac->private; + + xi->starting = false; + return result; +} + +/* + * build an 'authorizer' with our entity_name and global_id. we can + * reuse a single static copy since it is identical for all services + * we connect to. + */ +static int ceph_auth_none_create_authorizer( + struct ceph_auth_client *ac, int peer_type, + struct ceph_authorizer **a, + void **buf, size_t *len, + void **reply_buf, size_t *reply_len) +{ + struct ceph_auth_none_info *ai = ac->private; + struct ceph_none_authorizer *au = &ai->au; + void *p, *end; + int ret; + + if (!ai->built_authorizer) { + p = au->buf; + end = p + sizeof(au->buf); + ceph_encode_8(&p, 1); + ret = ceph_entity_name_encode(ac->name, &p, end - 8); + if (ret < 0) + goto bad; + ceph_decode_need(&p, end, sizeof(u64), bad2); + ceph_encode_64(&p, ac->global_id); + au->buf_len = p - (void *)au->buf; + ai->built_authorizer = true; + dout("built authorizer len %d\n", au->buf_len); + } + + *a = (struct ceph_authorizer *)au; + *buf = au->buf; + *len = au->buf_len; + *reply_buf = au->reply_buf; + *reply_len = sizeof(au->reply_buf); + return 0; + +bad2: + ret = -ERANGE; +bad: + return ret; +} + +static void ceph_auth_none_destroy_authorizer(struct ceph_auth_client *ac, + struct ceph_authorizer *a) +{ + /* nothing to do */ +} + +static const struct ceph_auth_client_ops ceph_auth_none_ops = { + .name = "none", + .reset = reset, + .destroy = destroy, + .is_authenticated = is_authenticated, + .should_authenticate = should_authenticate, + .handle_reply = handle_reply, + .create_authorizer = ceph_auth_none_create_authorizer, + .destroy_authorizer = ceph_auth_none_destroy_authorizer, +}; + +int ceph_auth_none_init(struct ceph_auth_client *ac) +{ + struct ceph_auth_none_info *xi; + + dout("ceph_auth_none_init %p\n", ac); + xi = kzalloc(sizeof(*xi), GFP_NOFS); + if (!xi) + return -ENOMEM; + + xi->starting = true; + xi->built_authorizer = false; + + ac->protocol = CEPH_AUTH_NONE; + ac->private = xi; + ac->ops = &ceph_auth_none_ops; + return 0; +} + diff --git a/net/ceph/auth_none.h b/net/ceph/auth_none.h new file mode 100644 index 000000000000..ed7d088b1bc9 --- /dev/null +++ b/net/ceph/auth_none.h @@ -0,0 +1,29 @@ +#ifndef _FS_CEPH_AUTH_NONE_H +#define _FS_CEPH_AUTH_NONE_H + +#include +#include + +/* + * null security mode. + * + * we use a single static authorizer that simply encodes our entity name + * and global id. + */ + +struct ceph_none_authorizer { + char buf[128]; + int buf_len; + char reply_buf[0]; +}; + +struct ceph_auth_none_info { + bool starting; + bool built_authorizer; + struct ceph_none_authorizer au; /* we only need one; it's static */ +}; + +extern int ceph_auth_none_init(struct ceph_auth_client *ac); + +#endif + diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c new file mode 100644 index 000000000000..7fd5dfcf6e18 --- /dev/null +++ b/net/ceph/auth_x.c @@ -0,0 +1,688 @@ + +#include + +#include +#include +#include +#include + +#include +#include + +#include "crypto.h" +#include "auth_x.h" +#include "auth_x_protocol.h" + +#define TEMP_TICKET_BUF_LEN 256 + +static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed); + +static int ceph_x_is_authenticated(struct ceph_auth_client *ac) +{ + struct ceph_x_info *xi = ac->private; + int need; + + ceph_x_validate_tickets(ac, &need); + dout("ceph_x_is_authenticated want=%d need=%d have=%d\n", + ac->want_keys, need, xi->have_keys); + return (ac->want_keys & xi->have_keys) == ac->want_keys; +} + +static int ceph_x_should_authenticate(struct ceph_auth_client *ac) +{ + struct ceph_x_info *xi = ac->private; + int need; + + ceph_x_validate_tickets(ac, &need); + dout("ceph_x_should_authenticate want=%d need=%d have=%d\n", + ac->want_keys, need, xi->have_keys); + return need != 0; +} + +static int ceph_x_encrypt_buflen(int ilen) +{ + return sizeof(struct ceph_x_encrypt_header) + ilen + 16 + + sizeof(u32); +} + +static int ceph_x_encrypt(struct ceph_crypto_key *secret, + void *ibuf, int ilen, void *obuf, size_t olen) +{ + struct ceph_x_encrypt_header head = { + .struct_v = 1, + .magic = cpu_to_le64(CEPHX_ENC_MAGIC) + }; + size_t len = olen - sizeof(u32); + int ret; + + ret = ceph_encrypt2(secret, obuf + sizeof(u32), &len, + &head, sizeof(head), ibuf, ilen); + if (ret) + return ret; + ceph_encode_32(&obuf, len); + return len + sizeof(u32); +} + +static int ceph_x_decrypt(struct ceph_crypto_key *secret, + void **p, void *end, void *obuf, size_t olen) +{ + struct ceph_x_encrypt_header head; + size_t head_len = sizeof(head); + int len, ret; + + len = ceph_decode_32(p); + if (*p + len > end) + return -EINVAL; + + dout("ceph_x_decrypt len %d\n", len); + ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen, + *p, len); + if (ret) + return ret; + if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC) + return -EPERM; + *p += len; + return olen; +} + +/* + * get existing (or insert new) ticket handler + */ +static struct ceph_x_ticket_handler * +get_ticket_handler(struct ceph_auth_client *ac, int service) +{ + struct ceph_x_ticket_handler *th; + struct ceph_x_info *xi = ac->private; + struct rb_node *parent = NULL, **p = &xi->ticket_handlers.rb_node; + + while (*p) { + parent = *p; + th = rb_entry(parent, struct ceph_x_ticket_handler, node); + if (service < th->service) + p = &(*p)->rb_left; + else if (service > th->service) + p = &(*p)->rb_right; + else + return th; + } + + /* add it */ + th = kzalloc(sizeof(*th), GFP_NOFS); + if (!th) + return ERR_PTR(-ENOMEM); + th->service = service; + rb_link_node(&th->node, parent, p); + rb_insert_color(&th->node, &xi->ticket_handlers); + return th; +} + +static void remove_ticket_handler(struct ceph_auth_client *ac, + struct ceph_x_ticket_handler *th) +{ + struct ceph_x_info *xi = ac->private; + + dout("remove_ticket_handler %p %d\n", th, th->service); + rb_erase(&th->node, &xi->ticket_handlers); + ceph_crypto_key_destroy(&th->session_key); + if (th->ticket_blob) + ceph_buffer_put(th->ticket_blob); + kfree(th); +} + +static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void *buf, void *end) +{ + struct ceph_x_info *xi = ac->private; + int num; + void *p = buf; + int ret; + char *dbuf; + char *ticket_buf; + u8 reply_struct_v; + + dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); + if (!dbuf) + return -ENOMEM; + + ret = -ENOMEM; + ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); + if (!ticket_buf) + goto out_dbuf; + + ceph_decode_need(&p, end, 1 + sizeof(u32), bad); + reply_struct_v = ceph_decode_8(&p); + if (reply_struct_v != 1) + goto bad; + num = ceph_decode_32(&p); + dout("%d tickets\n", num); + while (num--) { + int type; + u8 tkt_struct_v, blob_struct_v; + struct ceph_x_ticket_handler *th; + void *dp, *dend; + int dlen; + char is_enc; + struct timespec validity; + struct ceph_crypto_key old_key; + void *tp, *tpend; + struct ceph_timespec new_validity; + struct ceph_crypto_key new_session_key; + struct ceph_buffer *new_ticket_blob; + unsigned long new_expires, new_renew_after; + u64 new_secret_id; + + ceph_decode_need(&p, end, sizeof(u32) + 1, bad); + + type = ceph_decode_32(&p); + dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); + + tkt_struct_v = ceph_decode_8(&p); + if (tkt_struct_v != 1) + goto bad; + + th = get_ticket_handler(ac, type); + if (IS_ERR(th)) { + ret = PTR_ERR(th); + goto out; + } + + /* blob for me */ + dlen = ceph_x_decrypt(secret, &p, end, dbuf, + TEMP_TICKET_BUF_LEN); + if (dlen <= 0) { + ret = dlen; + goto out; + } + dout(" decrypted %d bytes\n", dlen); + dend = dbuf + dlen; + dp = dbuf; + + tkt_struct_v = ceph_decode_8(&dp); + if (tkt_struct_v != 1) + goto bad; + + memcpy(&old_key, &th->session_key, sizeof(old_key)); + ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); + if (ret) + goto out; + + ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); + ceph_decode_timespec(&validity, &new_validity); + new_expires = get_seconds() + validity.tv_sec; + new_renew_after = new_expires - (validity.tv_sec / 4); + dout(" expires=%lu renew_after=%lu\n", new_expires, + new_renew_after); + + /* ticket blob for service */ + ceph_decode_8_safe(&p, end, is_enc, bad); + tp = ticket_buf; + if (is_enc) { + /* encrypted */ + dout(" encrypted ticket\n"); + dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf, + TEMP_TICKET_BUF_LEN); + if (dlen < 0) { + ret = dlen; + goto out; + } + dlen = ceph_decode_32(&tp); + } else { + /* unencrypted */ + ceph_decode_32_safe(&p, end, dlen, bad); + ceph_decode_need(&p, end, dlen, bad); + ceph_decode_copy(&p, ticket_buf, dlen); + } + tpend = tp + dlen; + dout(" ticket blob is %d bytes\n", dlen); + ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); + blob_struct_v = ceph_decode_8(&tp); + new_secret_id = ceph_decode_64(&tp); + ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); + if (ret) + goto out; + + /* all is well, update our ticket */ + ceph_crypto_key_destroy(&th->session_key); + if (th->ticket_blob) + ceph_buffer_put(th->ticket_blob); + th->session_key = new_session_key; + th->ticket_blob = new_ticket_blob; + th->validity = new_validity; + th->secret_id = new_secret_id; + th->expires = new_expires; + th->renew_after = new_renew_after; + dout(" got ticket service %d (%s) secret_id %lld len %d\n", + type, ceph_entity_type_name(type), th->secret_id, + (int)th->ticket_blob->vec.iov_len); + xi->have_keys |= th->service; + } + + ret = 0; +out: + kfree(ticket_buf); +out_dbuf: + kfree(dbuf); + return ret; + +bad: + ret = -EINVAL; + goto out; +} + +static int ceph_x_build_authorizer(struct ceph_auth_client *ac, + struct ceph_x_ticket_handler *th, + struct ceph_x_authorizer *au) +{ + int maxlen; + struct ceph_x_authorize_a *msg_a; + struct ceph_x_authorize_b msg_b; + void *p, *end; + int ret; + int ticket_blob_len = + (th->ticket_blob ? th->ticket_blob->vec.iov_len : 0); + + dout("build_authorizer for %s %p\n", + ceph_entity_type_name(th->service), au); + + maxlen = sizeof(*msg_a) + sizeof(msg_b) + + ceph_x_encrypt_buflen(ticket_blob_len); + dout(" need len %d\n", maxlen); + if (au->buf && au->buf->alloc_len < maxlen) { + ceph_buffer_put(au->buf); + au->buf = NULL; + } + if (!au->buf) { + au->buf = ceph_buffer_new(maxlen, GFP_NOFS); + if (!au->buf) + return -ENOMEM; + } + au->service = th->service; + + msg_a = au->buf->vec.iov_base; + msg_a->struct_v = 1; + msg_a->global_id = cpu_to_le64(ac->global_id); + msg_a->service_id = cpu_to_le32(th->service); + msg_a->ticket_blob.struct_v = 1; + msg_a->ticket_blob.secret_id = cpu_to_le64(th->secret_id); + msg_a->ticket_blob.blob_len = cpu_to_le32(ticket_blob_len); + if (ticket_blob_len) { + memcpy(msg_a->ticket_blob.blob, th->ticket_blob->vec.iov_base, + th->ticket_blob->vec.iov_len); + } + dout(" th %p secret_id %lld %lld\n", th, th->secret_id, + le64_to_cpu(msg_a->ticket_blob.secret_id)); + + p = msg_a + 1; + p += ticket_blob_len; + end = au->buf->vec.iov_base + au->buf->vec.iov_len; + + get_random_bytes(&au->nonce, sizeof(au->nonce)); + msg_b.struct_v = 1; + msg_b.nonce = cpu_to_le64(au->nonce); + ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b), + p, end - p); + if (ret < 0) + goto out_buf; + p += ret; + au->buf->vec.iov_len = p - au->buf->vec.iov_base; + dout(" built authorizer nonce %llx len %d\n", au->nonce, + (int)au->buf->vec.iov_len); + BUG_ON(au->buf->vec.iov_len > maxlen); + return 0; + +out_buf: + ceph_buffer_put(au->buf); + au->buf = NULL; + return ret; +} + +static int ceph_x_encode_ticket(struct ceph_x_ticket_handler *th, + void **p, void *end) +{ + ceph_decode_need(p, end, 1 + sizeof(u64), bad); + ceph_encode_8(p, 1); + ceph_encode_64(p, th->secret_id); + if (th->ticket_blob) { + const char *buf = th->ticket_blob->vec.iov_base; + u32 len = th->ticket_blob->vec.iov_len; + + ceph_encode_32_safe(p, end, len, bad); + ceph_encode_copy_safe(p, end, buf, len, bad); + } else { + ceph_encode_32_safe(p, end, 0, bad); + } + + return 0; +bad: + return -ERANGE; +} + +static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed) +{ + int want = ac->want_keys; + struct ceph_x_info *xi = ac->private; + int service; + + *pneed = ac->want_keys & ~(xi->have_keys); + + for (service = 1; service <= want; service <<= 1) { + struct ceph_x_ticket_handler *th; + + if (!(ac->want_keys & service)) + continue; + + if (*pneed & service) + continue; + + th = get_ticket_handler(ac, service); + + if (IS_ERR(th)) { + *pneed |= service; + continue; + } + + if (get_seconds() >= th->renew_after) + *pneed |= service; + if (get_seconds() >= th->expires) + xi->have_keys &= ~service; + } +} + + +static int ceph_x_build_request(struct ceph_auth_client *ac, + void *buf, void *end) +{ + struct ceph_x_info *xi = ac->private; + int need; + struct ceph_x_request_header *head = buf; + int ret; + struct ceph_x_ticket_handler *th = + get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH); + + if (IS_ERR(th)) + return PTR_ERR(th); + + ceph_x_validate_tickets(ac, &need); + + dout("build_request want %x have %x need %x\n", + ac->want_keys, xi->have_keys, need); + + if (need & CEPH_ENTITY_TYPE_AUTH) { + struct ceph_x_authenticate *auth = (void *)(head + 1); + void *p = auth + 1; + struct ceph_x_challenge_blob tmp; + char tmp_enc[40]; + u64 *u; + + if (p > end) + return -ERANGE; + + dout(" get_auth_session_key\n"); + head->op = cpu_to_le16(CEPHX_GET_AUTH_SESSION_KEY); + + /* encrypt and hash */ + get_random_bytes(&auth->client_challenge, sizeof(u64)); + tmp.client_challenge = auth->client_challenge; + tmp.server_challenge = cpu_to_le64(xi->server_challenge); + ret = ceph_x_encrypt(&xi->secret, &tmp, sizeof(tmp), + tmp_enc, sizeof(tmp_enc)); + if (ret < 0) + return ret; + + auth->struct_v = 1; + auth->key = 0; + for (u = (u64 *)tmp_enc; u + 1 <= (u64 *)(tmp_enc + ret); u++) + auth->key ^= *(__le64 *)u; + dout(" server_challenge %llx client_challenge %llx key %llx\n", + xi->server_challenge, le64_to_cpu(auth->client_challenge), + le64_to_cpu(auth->key)); + + /* now encode the old ticket if exists */ + ret = ceph_x_encode_ticket(th, &p, end); + if (ret < 0) + return ret; + + return p - buf; + } + + if (need) { + void *p = head + 1; + struct ceph_x_service_ticket_request *req; + + if (p > end) + return -ERANGE; + head->op = cpu_to_le16(CEPHX_GET_PRINCIPAL_SESSION_KEY); + + ret = ceph_x_build_authorizer(ac, th, &xi->auth_authorizer); + if (ret) + return ret; + ceph_encode_copy(&p, xi->auth_authorizer.buf->vec.iov_base, + xi->auth_authorizer.buf->vec.iov_len); + + req = p; + req->keys = cpu_to_le32(need); + p += sizeof(*req); + return p - buf; + } + + return 0; +} + +static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result, + void *buf, void *end) +{ + struct ceph_x_info *xi = ac->private; + struct ceph_x_reply_header *head = buf; + struct ceph_x_ticket_handler *th; + int len = end - buf; + int op; + int ret; + + if (result) + return result; /* XXX hmm? */ + + if (xi->starting) { + /* it's a hello */ + struct ceph_x_server_challenge *sc = buf; + + if (len != sizeof(*sc)) + return -EINVAL; + xi->server_challenge = le64_to_cpu(sc->server_challenge); + dout("handle_reply got server challenge %llx\n", + xi->server_challenge); + xi->starting = false; + xi->have_keys &= ~CEPH_ENTITY_TYPE_AUTH; + return -EAGAIN; + } + + op = le16_to_cpu(head->op); + result = le32_to_cpu(head->result); + dout("handle_reply op %d result %d\n", op, result); + switch (op) { + case CEPHX_GET_AUTH_SESSION_KEY: + /* verify auth key */ + ret = ceph_x_proc_ticket_reply(ac, &xi->secret, + buf + sizeof(*head), end); + break; + + case CEPHX_GET_PRINCIPAL_SESSION_KEY: + th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH); + if (IS_ERR(th)) + return PTR_ERR(th); + ret = ceph_x_proc_ticket_reply(ac, &th->session_key, + buf + sizeof(*head), end); + break; + + default: + return -EINVAL; + } + if (ret) + return ret; + if (ac->want_keys == xi->have_keys) + return 0; + return -EAGAIN; +} + +static int ceph_x_create_authorizer( + struct ceph_auth_client *ac, int peer_type, + struct ceph_authorizer **a, + void **buf, size_t *len, + void **reply_buf, size_t *reply_len) +{ + struct ceph_x_authorizer *au; + struct ceph_x_ticket_handler *th; + int ret; + + th = get_ticket_handler(ac, peer_type); + if (IS_ERR(th)) + return PTR_ERR(th); + + au = kzalloc(sizeof(*au), GFP_NOFS); + if (!au) + return -ENOMEM; + + ret = ceph_x_build_authorizer(ac, th, au); + if (ret) { + kfree(au); + return ret; + } + + *a = (struct ceph_authorizer *)au; + *buf = au->buf->vec.iov_base; + *len = au->buf->vec.iov_len; + *reply_buf = au->reply_buf; + *reply_len = sizeof(au->reply_buf); + return 0; +} + +static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, + struct ceph_authorizer *a, size_t len) +{ + struct ceph_x_authorizer *au = (void *)a; + struct ceph_x_ticket_handler *th; + int ret = 0; + struct ceph_x_authorize_reply reply; + void *p = au->reply_buf; + void *end = p + sizeof(au->reply_buf); + + th = get_ticket_handler(ac, au->service); + if (IS_ERR(th)) + return PTR_ERR(th); + ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply)); + if (ret < 0) + return ret; + if (ret != sizeof(reply)) + return -EPERM; + + if (au->nonce + 1 != le64_to_cpu(reply.nonce_plus_one)) + ret = -EPERM; + else + ret = 0; + dout("verify_authorizer_reply nonce %llx got %llx ret %d\n", + au->nonce, le64_to_cpu(reply.nonce_plus_one), ret); + return ret; +} + +static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, + struct ceph_authorizer *a) +{ + struct ceph_x_authorizer *au = (void *)a; + + ceph_buffer_put(au->buf); + kfree(au); +} + + +static void ceph_x_reset(struct ceph_auth_client *ac) +{ + struct ceph_x_info *xi = ac->private; + + dout("reset\n"); + xi->starting = true; + xi->server_challenge = 0; +} + +static void ceph_x_destroy(struct ceph_auth_client *ac) +{ + struct ceph_x_info *xi = ac->private; + struct rb_node *p; + + dout("ceph_x_destroy %p\n", ac); + ceph_crypto_key_destroy(&xi->secret); + + while ((p = rb_first(&xi->ticket_handlers)) != NULL) { + struct ceph_x_ticket_handler *th = + rb_entry(p, struct ceph_x_ticket_handler, node); + remove_ticket_handler(ac, th); + } + + if (xi->auth_authorizer.buf) + ceph_buffer_put(xi->auth_authorizer.buf); + + kfree(ac->private); + ac->private = NULL; +} + +static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac, + int peer_type) +{ + struct ceph_x_ticket_handler *th; + + th = get_ticket_handler(ac, peer_type); + if (!IS_ERR(th)) + remove_ticket_handler(ac, th); +} + + +static const struct ceph_auth_client_ops ceph_x_ops = { + .name = "x", + .is_authenticated = ceph_x_is_authenticated, + .should_authenticate = ceph_x_should_authenticate, + .build_request = ceph_x_build_request, + .handle_reply = ceph_x_handle_reply, + .create_authorizer = ceph_x_create_authorizer, + .verify_authorizer_reply = ceph_x_verify_authorizer_reply, + .destroy_authorizer = ceph_x_destroy_authorizer, + .invalidate_authorizer = ceph_x_invalidate_authorizer, + .reset = ceph_x_reset, + .destroy = ceph_x_destroy, +}; + + +int ceph_x_init(struct ceph_auth_client *ac) +{ + struct ceph_x_info *xi; + int ret; + + dout("ceph_x_init %p\n", ac); + ret = -ENOMEM; + xi = kzalloc(sizeof(*xi), GFP_NOFS); + if (!xi) + goto out; + + ret = -EINVAL; + if (!ac->secret) { + pr_err("no secret set (for auth_x protocol)\n"); + goto out_nomem; + } + + ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret); + if (ret) + goto out_nomem; + + xi->starting = true; + xi->ticket_handlers = RB_ROOT; + + ac->protocol = CEPH_AUTH_CEPHX; + ac->private = xi; + ac->ops = &ceph_x_ops; + return 0; + +out_nomem: + kfree(xi); +out: + return ret; +} + + diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h new file mode 100644 index 000000000000..e02da7a5c5a1 --- /dev/null +++ b/net/ceph/auth_x.h @@ -0,0 +1,50 @@ +#ifndef _FS_CEPH_AUTH_X_H +#define _FS_CEPH_AUTH_X_H + +#include + +#include + +#include "crypto.h" +#include "auth_x_protocol.h" + +/* + * Handle ticket for a single service. + */ +struct ceph_x_ticket_handler { + struct rb_node node; + unsigned service; + + struct ceph_crypto_key session_key; + struct ceph_timespec validity; + + u64 secret_id; + struct ceph_buffer *ticket_blob; + + unsigned long renew_after, expires; +}; + + +struct ceph_x_authorizer { + struct ceph_buffer *buf; + unsigned service; + u64 nonce; + char reply_buf[128]; /* big enough for encrypted blob */ +}; + +struct ceph_x_info { + struct ceph_crypto_key secret; + + bool starting; + u64 server_challenge; + + unsigned have_keys; + struct rb_root ticket_handlers; + + struct ceph_x_authorizer auth_authorizer; +}; + +extern int ceph_x_init(struct ceph_auth_client *ac); + +#endif + diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h new file mode 100644 index 000000000000..671d30576c4f --- /dev/null +++ b/net/ceph/auth_x_protocol.h @@ -0,0 +1,90 @@ +#ifndef __FS_CEPH_AUTH_X_PROTOCOL +#define __FS_CEPH_AUTH_X_PROTOCOL + +#define CEPHX_GET_AUTH_SESSION_KEY 0x0100 +#define CEPHX_GET_PRINCIPAL_SESSION_KEY 0x0200 +#define CEPHX_GET_ROTATING_KEY 0x0400 + +/* common bits */ +struct ceph_x_ticket_blob { + __u8 struct_v; + __le64 secret_id; + __le32 blob_len; + char blob[]; +} __attribute__ ((packed)); + + +/* common request/reply headers */ +struct ceph_x_request_header { + __le16 op; +} __attribute__ ((packed)); + +struct ceph_x_reply_header { + __le16 op; + __le32 result; +} __attribute__ ((packed)); + + +/* authenticate handshake */ + +/* initial hello (no reply header) */ +struct ceph_x_server_challenge { + __u8 struct_v; + __le64 server_challenge; +} __attribute__ ((packed)); + +struct ceph_x_authenticate { + __u8 struct_v; + __le64 client_challenge; + __le64 key; + /* ticket blob */ +} __attribute__ ((packed)); + +struct ceph_x_service_ticket_request { + __u8 struct_v; + __le32 keys; +} __attribute__ ((packed)); + +struct ceph_x_challenge_blob { + __le64 server_challenge; + __le64 client_challenge; +} __attribute__ ((packed)); + + + +/* authorize handshake */ + +/* + * The authorizer consists of two pieces: + * a - service id, ticket blob + * b - encrypted with session key + */ +struct ceph_x_authorize_a { + __u8 struct_v; + __le64 global_id; + __le32 service_id; + struct ceph_x_ticket_blob ticket_blob; +} __attribute__ ((packed)); + +struct ceph_x_authorize_b { + __u8 struct_v; + __le64 nonce; +} __attribute__ ((packed)); + +struct ceph_x_authorize_reply { + __u8 struct_v; + __le64 nonce_plus_one; +} __attribute__ ((packed)); + + +/* + * encyption bundle + */ +#define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull + +struct ceph_x_encrypt_header { + __u8 struct_v; + __le64 magic; +} __attribute__ ((packed)); + +#endif diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c new file mode 100644 index 000000000000..53d8abfa25d5 --- /dev/null +++ b/net/ceph/buffer.c @@ -0,0 +1,68 @@ + +#include + +#include +#include + +#include +#include + +struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) +{ + struct ceph_buffer *b; + + b = kmalloc(sizeof(*b), gfp); + if (!b) + return NULL; + + b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN); + if (b->vec.iov_base) { + b->is_vmalloc = false; + } else { + b->vec.iov_base = __vmalloc(len, gfp, PAGE_KERNEL); + if (!b->vec.iov_base) { + kfree(b); + return NULL; + } + b->is_vmalloc = true; + } + + kref_init(&b->kref); + b->alloc_len = len; + b->vec.iov_len = len; + dout("buffer_new %p\n", b); + return b; +} +EXPORT_SYMBOL(ceph_buffer_new); + +void ceph_buffer_release(struct kref *kref) +{ + struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref); + + dout("buffer_release %p\n", b); + if (b->vec.iov_base) { + if (b->is_vmalloc) + vfree(b->vec.iov_base); + else + kfree(b->vec.iov_base); + } + kfree(b); +} +EXPORT_SYMBOL(ceph_buffer_release); + +int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end) +{ + size_t len; + + ceph_decode_need(p, end, sizeof(u32), bad); + len = ceph_decode_32(p); + dout("decode_buffer len %d\n", (int)len); + ceph_decode_need(p, end, len, bad); + *b = ceph_buffer_new(len, GFP_NOFS); + if (!*b) + return -ENOMEM; + ceph_decode_copy(p, (*b)->vec.iov_base, len); + return 0; +bad: + return -EINVAL; +} diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c new file mode 100644 index 000000000000..f6f2eebc0767 --- /dev/null +++ b/net/ceph/ceph_common.c @@ -0,0 +1,529 @@ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#include +#include +#include +#include +#include + + + +/* + * find filename portion of a path (/foo/bar/baz -> baz) + */ +const char *ceph_file_part(const char *s, int len) +{ + const char *e = s + len; + + while (e != s && *(e-1) != '/') + e--; + return e; +} +EXPORT_SYMBOL(ceph_file_part); + +const char *ceph_msg_type_name(int type) +{ + switch (type) { + case CEPH_MSG_SHUTDOWN: return "shutdown"; + case CEPH_MSG_PING: return "ping"; + case CEPH_MSG_AUTH: return "auth"; + case CEPH_MSG_AUTH_REPLY: return "auth_reply"; + case CEPH_MSG_MON_MAP: return "mon_map"; + case CEPH_MSG_MON_GET_MAP: return "mon_get_map"; + case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe"; + case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack"; + case CEPH_MSG_STATFS: return "statfs"; + case CEPH_MSG_STATFS_REPLY: return "statfs_reply"; + case CEPH_MSG_MDS_MAP: return "mds_map"; + case CEPH_MSG_CLIENT_SESSION: return "client_session"; + case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect"; + case CEPH_MSG_CLIENT_REQUEST: return "client_request"; + case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward"; + case CEPH_MSG_CLIENT_REPLY: return "client_reply"; + case CEPH_MSG_CLIENT_CAPS: return "client_caps"; + case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release"; + case CEPH_MSG_CLIENT_SNAP: return "client_snap"; + case CEPH_MSG_CLIENT_LEASE: return "client_lease"; + case CEPH_MSG_OSD_MAP: return "osd_map"; + case CEPH_MSG_OSD_OP: return "osd_op"; + case CEPH_MSG_OSD_OPREPLY: return "osd_opreply"; + default: return "unknown"; + } +} +EXPORT_SYMBOL(ceph_msg_type_name); + +/* + * Initially learn our fsid, or verify an fsid matches. + */ +int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) +{ + if (client->have_fsid) { + if (ceph_fsid_compare(&client->fsid, fsid)) { + pr_err("bad fsid, had %pU got %pU", + &client->fsid, fsid); + return -1; + } + } else { + pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); + memcpy(&client->fsid, fsid, sizeof(*fsid)); + ceph_debugfs_client_init(client); + client->have_fsid = true; + } + return 0; +} +EXPORT_SYMBOL(ceph_check_fsid); + +static int strcmp_null(const char *s1, const char *s2) +{ + if (!s1 && !s2) + return 0; + if (s1 && !s2) + return -1; + if (!s1 && s2) + return 1; + return strcmp(s1, s2); +} + +int ceph_compare_options(struct ceph_options *new_opt, + struct ceph_client *client) +{ + struct ceph_options *opt1 = new_opt; + struct ceph_options *opt2 = client->options; + int ofs = offsetof(struct ceph_options, mon_addr); + int i; + int ret; + + ret = memcmp(opt1, opt2, ofs); + if (ret) + return ret; + + ret = strcmp_null(opt1->name, opt2->name); + if (ret) + return ret; + + ret = strcmp_null(opt1->secret, opt2->secret); + if (ret) + return ret; + + /* any matching mon ip implies a match */ + for (i = 0; i < opt1->num_mon; i++) { + if (ceph_monmap_contains(client->monc.monmap, + &opt1->mon_addr[i])) + return 0; + } + return -1; +} +EXPORT_SYMBOL(ceph_compare_options); + + +static int parse_fsid(const char *str, struct ceph_fsid *fsid) +{ + int i = 0; + char tmp[3]; + int err = -EINVAL; + int d; + + dout("parse_fsid '%s'\n", str); + tmp[2] = 0; + while (*str && i < 16) { + if (ispunct(*str)) { + str++; + continue; + } + if (!isxdigit(str[0]) || !isxdigit(str[1])) + break; + tmp[0] = str[0]; + tmp[1] = str[1]; + if (sscanf(tmp, "%x", &d) < 1) + break; + fsid->fsid[i] = d & 0xff; + i++; + str += 2; + } + + if (i == 16) + err = 0; + dout("parse_fsid ret %d got fsid %pU", err, fsid); + return err; +} + +/* + * ceph options + */ +enum { + Opt_osdtimeout, + Opt_osdkeepalivetimeout, + Opt_mount_timeout, + Opt_osd_idle_ttl, + Opt_last_int, + /* int args above */ + Opt_fsid, + Opt_name, + Opt_secret, + Opt_ip, + Opt_last_string, + /* string args above */ + Opt_noshare, + Opt_nocrc, +}; + +static match_table_t opt_tokens = { + {Opt_osdtimeout, "osdtimeout=%d"}, + {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, + {Opt_mount_timeout, "mount_timeout=%d"}, + {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, + /* int args above */ + {Opt_fsid, "fsid=%s"}, + {Opt_name, "name=%s"}, + {Opt_secret, "secret=%s"}, + {Opt_ip, "ip=%s"}, + /* string args above */ + {Opt_noshare, "noshare"}, + {Opt_nocrc, "nocrc"}, + {-1, NULL} +}; + +void ceph_destroy_options(struct ceph_options *opt) +{ + dout("destroy_options %p\n", opt); + kfree(opt->name); + kfree(opt->secret); + kfree(opt); +} +EXPORT_SYMBOL(ceph_destroy_options); + +int ceph_parse_options(struct ceph_options **popt, char *options, + const char *dev_name, const char *dev_name_end, + int (*parse_extra_token)(char *c, void *private), + void *private) +{ + struct ceph_options *opt; + const char *c; + int err = -ENOMEM; + substring_t argstr[MAX_OPT_ARGS]; + + opt = kzalloc(sizeof(*opt), GFP_KERNEL); + if (!opt) + return err; + opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), + GFP_KERNEL); + if (!opt->mon_addr) + goto out; + + dout("parse_options %p options '%s' dev_name '%s'\n", opt, options, + dev_name); + + /* start with defaults */ + opt->flags = CEPH_OPT_DEFAULT; + opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT; + opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; + opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */ + opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; /* seconds */ + + /* get mon ip(s) */ + /* ip1[:port1][,ip2[:port2]...] */ + err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr, + CEPH_MAX_MON, &opt->num_mon); + if (err < 0) + goto out; + + /* parse mount options */ + while ((c = strsep(&options, ",")) != NULL) { + int token, intval, ret; + if (!*c) + continue; + err = -EINVAL; + token = match_token((char *)c, opt_tokens, argstr); + if (token < 0) { + /* extra? */ + err = parse_extra_token((char *)c, private); + if (err < 0) { + pr_err("bad option at '%s'\n", c); + goto out; + } + continue; + } + if (token < Opt_last_int) { + ret = match_int(&argstr[0], &intval); + if (ret < 0) { + pr_err("bad mount option arg (not int) " + "at '%s'\n", c); + continue; + } + dout("got int token %d val %d\n", token, intval); + } else if (token > Opt_last_int && token < Opt_last_string) { + dout("got string token %d val %s\n", token, + argstr[0].from); + } else { + dout("got token %d\n", token); + } + switch (token) { + case Opt_ip: + err = ceph_parse_ips(argstr[0].from, + argstr[0].to, + &opt->my_addr, + 1, NULL); + if (err < 0) + goto out; + opt->flags |= CEPH_OPT_MYIP; + break; + + case Opt_fsid: + err = parse_fsid(argstr[0].from, &opt->fsid); + if (err == 0) + opt->flags |= CEPH_OPT_FSID; + break; + case Opt_name: + opt->name = kstrndup(argstr[0].from, + argstr[0].to-argstr[0].from, + GFP_KERNEL); + break; + case Opt_secret: + opt->secret = kstrndup(argstr[0].from, + argstr[0].to-argstr[0].from, + GFP_KERNEL); + break; + + /* misc */ + case Opt_osdtimeout: + opt->osd_timeout = intval; + break; + case Opt_osdkeepalivetimeout: + opt->osd_keepalive_timeout = intval; + break; + case Opt_osd_idle_ttl: + opt->osd_idle_ttl = intval; + break; + case Opt_mount_timeout: + opt->mount_timeout = intval; + break; + + case Opt_noshare: + opt->flags |= CEPH_OPT_NOSHARE; + break; + + case Opt_nocrc: + opt->flags |= CEPH_OPT_NOCRC; + break; + + default: + BUG_ON(token); + } + } + + /* success */ + *popt = opt; + return 0; + +out: + ceph_destroy_options(opt); + return err; +} +EXPORT_SYMBOL(ceph_parse_options); + +u64 ceph_client_id(struct ceph_client *client) +{ + return client->monc.auth->global_id; +} +EXPORT_SYMBOL(ceph_client_id); + +/* + * create a fresh client instance + */ +struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) +{ + struct ceph_client *client; + int err = -ENOMEM; + + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (client == NULL) + return ERR_PTR(-ENOMEM); + + client->private = private; + client->options = opt; + + mutex_init(&client->mount_mutex); + init_waitqueue_head(&client->auth_wq); + client->auth_err = 0; + + client->extra_mon_dispatch = NULL; + client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT; + client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT; + + client->msgr = NULL; + + /* subsystems */ + err = ceph_monc_init(&client->monc, client); + if (err < 0) + goto fail; + err = ceph_osdc_init(&client->osdc, client); + if (err < 0) + goto fail_monc; + + return client; + +fail_monc: + ceph_monc_stop(&client->monc); +fail: + kfree(client); + return ERR_PTR(err); +} +EXPORT_SYMBOL(ceph_create_client); + +void ceph_destroy_client(struct ceph_client *client) +{ + dout("destroy_client %p\n", client); + + /* unmount */ + ceph_osdc_stop(&client->osdc); + + /* + * make sure mds and osd connections close out before destroying + * the auth module, which is needed to free those connections' + * ceph_authorizers. + */ + ceph_msgr_flush(); + + ceph_monc_stop(&client->monc); + + ceph_debugfs_client_cleanup(client); + + if (client->msgr) + ceph_messenger_destroy(client->msgr); + + ceph_destroy_options(client->options); + + kfree(client); + dout("destroy_client %p done\n", client); +} +EXPORT_SYMBOL(ceph_destroy_client); + +/* + * true if we have the mon map (and have thus joined the cluster) + */ +static int have_mon_and_osd_map(struct ceph_client *client) +{ + return client->monc.monmap && client->monc.monmap->epoch && + client->osdc.osdmap && client->osdc.osdmap->epoch; +} + +/* + * mount: join the ceph cluster, and open root directory. + */ +int __ceph_open_session(struct ceph_client *client, unsigned long started) +{ + struct ceph_entity_addr *myaddr = NULL; + int err; + unsigned long timeout = client->options->mount_timeout * HZ; + + /* initialize the messenger */ + if (client->msgr == NULL) { + if (ceph_test_opt(client, MYIP)) + myaddr = &client->options->my_addr; + client->msgr = ceph_messenger_create(myaddr, + client->supported_features, + client->required_features); + if (IS_ERR(client->msgr)) { + client->msgr = NULL; + return PTR_ERR(client->msgr); + } + client->msgr->nocrc = ceph_test_opt(client, NOCRC); + } + + /* open session, and wait for mon and osd maps */ + err = ceph_monc_open_session(&client->monc); + if (err < 0) + return err; + + while (!have_mon_and_osd_map(client)) { + err = -EIO; + if (timeout && time_after_eq(jiffies, started + timeout)) + return err; + + /* wait */ + dout("mount waiting for mon_map\n"); + err = wait_event_interruptible_timeout(client->auth_wq, + have_mon_and_osd_map(client) || (client->auth_err < 0), + timeout); + if (err == -EINTR || err == -ERESTARTSYS) + return err; + if (client->auth_err < 0) + return client->auth_err; + } + + return 0; +} +EXPORT_SYMBOL(__ceph_open_session); + + +int ceph_open_session(struct ceph_client *client) +{ + int ret; + unsigned long started = jiffies; /* note the start time */ + + dout("open_session start\n"); + mutex_lock(&client->mount_mutex); + + ret = __ceph_open_session(client, started); + + mutex_unlock(&client->mount_mutex); + return ret; +} +EXPORT_SYMBOL(ceph_open_session); + + +static int __init init_ceph_lib(void) +{ + int ret = 0; + + ret = ceph_debugfs_init(); + if (ret < 0) + goto out; + + ret = ceph_msgr_init(); + if (ret < 0) + goto out_debugfs; + + pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n", + CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL, + CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT, + CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT); + + return 0; + +out_debugfs: + ceph_debugfs_cleanup(); +out: + return ret; +} + +static void __exit exit_ceph_lib(void) +{ + dout("exit_ceph_lib\n"); + ceph_msgr_exit(); + ceph_debugfs_cleanup(); +} + +module_init(init_ceph_lib); +module_exit(exit_ceph_lib); + +MODULE_AUTHOR("Sage Weil "); +MODULE_AUTHOR("Yehuda Sadeh "); +MODULE_AUTHOR("Patience Warnick "); +MODULE_DESCRIPTION("Ceph filesystem for Linux"); +MODULE_LICENSE("GPL"); diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c new file mode 100644 index 000000000000..a3a3a31d3c37 --- /dev/null +++ b/net/ceph/ceph_fs.c @@ -0,0 +1,75 @@ +/* + * Some non-inline ceph helpers + */ +#include +#include + +/* + * return true if @layout appears to be valid + */ +int ceph_file_layout_is_valid(const struct ceph_file_layout *layout) +{ + __u32 su = le32_to_cpu(layout->fl_stripe_unit); + __u32 sc = le32_to_cpu(layout->fl_stripe_count); + __u32 os = le32_to_cpu(layout->fl_object_size); + + /* stripe unit, object size must be non-zero, 64k increment */ + if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1))) + return 0; + if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1))) + return 0; + /* object size must be a multiple of stripe unit */ + if (os < su || os % su) + return 0; + /* stripe count must be non-zero */ + if (!sc) + return 0; + return 1; +} + + +int ceph_flags_to_mode(int flags) +{ + int mode; + +#ifdef O_DIRECTORY /* fixme */ + if ((flags & O_DIRECTORY) == O_DIRECTORY) + return CEPH_FILE_MODE_PIN; +#endif + if ((flags & O_APPEND) == O_APPEND) + flags |= O_WRONLY; + + if ((flags & O_ACCMODE) == O_RDWR) + mode = CEPH_FILE_MODE_RDWR; + else if ((flags & O_ACCMODE) == O_WRONLY) + mode = CEPH_FILE_MODE_WR; + else + mode = CEPH_FILE_MODE_RD; + +#ifdef O_LAZY + if (flags & O_LAZY) + mode |= CEPH_FILE_MODE_LAZY; +#endif + + return mode; +} +EXPORT_SYMBOL(ceph_flags_to_mode); + +int ceph_caps_for_mode(int mode) +{ + int caps = CEPH_CAP_PIN; + + if (mode & CEPH_FILE_MODE_RD) + caps |= CEPH_CAP_FILE_SHARED | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE; + if (mode & CEPH_FILE_MODE_WR) + caps |= CEPH_CAP_FILE_EXCL | + CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | + CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL; + if (mode & CEPH_FILE_MODE_LAZY) + caps |= CEPH_CAP_FILE_LAZYIO; + + return caps; +} +EXPORT_SYMBOL(ceph_caps_for_mode); diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c new file mode 100644 index 000000000000..815ef8826796 --- /dev/null +++ b/net/ceph/ceph_hash.c @@ -0,0 +1,118 @@ + +#include + +/* + * Robert Jenkin's hash function. + * http://burtleburtle.net/bob/hash/evahash.html + * This is in the public domain. + */ +#define mix(a, b, c) \ + do { \ + a = a - b; a = a - c; a = a ^ (c >> 13); \ + b = b - c; b = b - a; b = b ^ (a << 8); \ + c = c - a; c = c - b; c = c ^ (b >> 13); \ + a = a - b; a = a - c; a = a ^ (c >> 12); \ + b = b - c; b = b - a; b = b ^ (a << 16); \ + c = c - a; c = c - b; c = c ^ (b >> 5); \ + a = a - b; a = a - c; a = a ^ (c >> 3); \ + b = b - c; b = b - a; b = b ^ (a << 10); \ + c = c - a; c = c - b; c = c ^ (b >> 15); \ + } while (0) + +unsigned ceph_str_hash_rjenkins(const char *str, unsigned length) +{ + const unsigned char *k = (const unsigned char *)str; + __u32 a, b, c; /* the internal state */ + __u32 len; /* how many key bytes still need mixing */ + + /* Set up the internal state */ + len = length; + a = 0x9e3779b9; /* the golden ratio; an arbitrary value */ + b = a; + c = 0; /* variable initialization of internal state */ + + /* handle most of the key */ + while (len >= 12) { + a = a + (k[0] + ((__u32)k[1] << 8) + ((__u32)k[2] << 16) + + ((__u32)k[3] << 24)); + b = b + (k[4] + ((__u32)k[5] << 8) + ((__u32)k[6] << 16) + + ((__u32)k[7] << 24)); + c = c + (k[8] + ((__u32)k[9] << 8) + ((__u32)k[10] << 16) + + ((__u32)k[11] << 24)); + mix(a, b, c); + k = k + 12; + len = len - 12; + } + + /* handle the last 11 bytes */ + c = c + length; + switch (len) { /* all the case statements fall through */ + case 11: + c = c + ((__u32)k[10] << 24); + case 10: + c = c + ((__u32)k[9] << 16); + case 9: + c = c + ((__u32)k[8] << 8); + /* the first byte of c is reserved for the length */ + case 8: + b = b + ((__u32)k[7] << 24); + case 7: + b = b + ((__u32)k[6] << 16); + case 6: + b = b + ((__u32)k[5] << 8); + case 5: + b = b + k[4]; + case 4: + a = a + ((__u32)k[3] << 24); + case 3: + a = a + ((__u32)k[2] << 16); + case 2: + a = a + ((__u32)k[1] << 8); + case 1: + a = a + k[0]; + /* case 0: nothing left to add */ + } + mix(a, b, c); + + return c; +} + +/* + * linux dcache hash + */ +unsigned ceph_str_hash_linux(const char *str, unsigned length) +{ + unsigned long hash = 0; + unsigned char c; + + while (length--) { + c = *str++; + hash = (hash + (c << 4) + (c >> 4)) * 11; + } + return hash; +} + + +unsigned ceph_str_hash(int type, const char *s, unsigned len) +{ + switch (type) { + case CEPH_STR_HASH_LINUX: + return ceph_str_hash_linux(s, len); + case CEPH_STR_HASH_RJENKINS: + return ceph_str_hash_rjenkins(s, len); + default: + return -1; + } +} + +const char *ceph_str_hash_name(int type) +{ + switch (type) { + case CEPH_STR_HASH_LINUX: + return "linux"; + case CEPH_STR_HASH_RJENKINS: + return "rjenkins"; + default: + return "unknown"; + } +} diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c new file mode 100644 index 000000000000..3fbda04de29c --- /dev/null +++ b/net/ceph/ceph_strings.c @@ -0,0 +1,84 @@ +/* + * Ceph string constants + */ +#include +#include + +const char *ceph_entity_type_name(int type) +{ + switch (type) { + case CEPH_ENTITY_TYPE_MDS: return "mds"; + case CEPH_ENTITY_TYPE_OSD: return "osd"; + case CEPH_ENTITY_TYPE_MON: return "mon"; + case CEPH_ENTITY_TYPE_CLIENT: return "client"; + case CEPH_ENTITY_TYPE_AUTH: return "auth"; + default: return "unknown"; + } +} + +const char *ceph_osd_op_name(int op) +{ + switch (op) { + case CEPH_OSD_OP_READ: return "read"; + case CEPH_OSD_OP_STAT: return "stat"; + + case CEPH_OSD_OP_MASKTRUNC: return "masktrunc"; + + case CEPH_OSD_OP_WRITE: return "write"; + case CEPH_OSD_OP_DELETE: return "delete"; + case CEPH_OSD_OP_TRUNCATE: return "truncate"; + case CEPH_OSD_OP_ZERO: return "zero"; + case CEPH_OSD_OP_WRITEFULL: return "writefull"; + case CEPH_OSD_OP_ROLLBACK: return "rollback"; + + case CEPH_OSD_OP_APPEND: return "append"; + case CEPH_OSD_OP_STARTSYNC: return "startsync"; + case CEPH_OSD_OP_SETTRUNC: return "settrunc"; + case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc"; + + case CEPH_OSD_OP_TMAPUP: return "tmapup"; + case CEPH_OSD_OP_TMAPGET: return "tmapget"; + case CEPH_OSD_OP_TMAPPUT: return "tmapput"; + + case CEPH_OSD_OP_GETXATTR: return "getxattr"; + case CEPH_OSD_OP_GETXATTRS: return "getxattrs"; + case CEPH_OSD_OP_SETXATTR: return "setxattr"; + case CEPH_OSD_OP_SETXATTRS: return "setxattrs"; + case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs"; + case CEPH_OSD_OP_RMXATTR: return "rmxattr"; + case CEPH_OSD_OP_CMPXATTR: return "cmpxattr"; + + case CEPH_OSD_OP_PULL: return "pull"; + case CEPH_OSD_OP_PUSH: return "push"; + case CEPH_OSD_OP_BALANCEREADS: return "balance-reads"; + case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads"; + case CEPH_OSD_OP_SCRUB: return "scrub"; + + case CEPH_OSD_OP_WRLOCK: return "wrlock"; + case CEPH_OSD_OP_WRUNLOCK: return "wrunlock"; + case CEPH_OSD_OP_RDLOCK: return "rdlock"; + case CEPH_OSD_OP_RDUNLOCK: return "rdunlock"; + case CEPH_OSD_OP_UPLOCK: return "uplock"; + case CEPH_OSD_OP_DNLOCK: return "dnlock"; + + case CEPH_OSD_OP_CALL: return "call"; + + case CEPH_OSD_OP_PGLS: return "pgls"; + } + return "???"; +} + + +const char *ceph_pool_op_name(int op) +{ + switch (op) { + case POOL_OP_CREATE: return "create"; + case POOL_OP_DELETE: return "delete"; + case POOL_OP_AUID_CHANGE: return "auid change"; + case POOL_OP_CREATE_SNAP: return "create snap"; + case POOL_OP_DELETE_SNAP: return "delete snap"; + case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap"; + case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap"; + } + return "???"; +} diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c new file mode 100644 index 000000000000..d6ebb13a18a4 --- /dev/null +++ b/net/ceph/crush/crush.c @@ -0,0 +1,151 @@ + +#ifdef __KERNEL__ +# include +#else +# include +# include +# define kfree(x) do { if (x) free(x); } while (0) +# define BUG_ON(x) assert(!(x)) +#endif + +#include + +const char *crush_bucket_alg_name(int alg) +{ + switch (alg) { + case CRUSH_BUCKET_UNIFORM: return "uniform"; + case CRUSH_BUCKET_LIST: return "list"; + case CRUSH_BUCKET_TREE: return "tree"; + case CRUSH_BUCKET_STRAW: return "straw"; + default: return "unknown"; + } +} + +/** + * crush_get_bucket_item_weight - Get weight of an item in given bucket + * @b: bucket pointer + * @p: item index in bucket + */ +int crush_get_bucket_item_weight(struct crush_bucket *b, int p) +{ + if (p >= b->size) + return 0; + + switch (b->alg) { + case CRUSH_BUCKET_UNIFORM: + return ((struct crush_bucket_uniform *)b)->item_weight; + case CRUSH_BUCKET_LIST: + return ((struct crush_bucket_list *)b)->item_weights[p]; + case CRUSH_BUCKET_TREE: + if (p & 1) + return ((struct crush_bucket_tree *)b)->node_weights[p]; + return 0; + case CRUSH_BUCKET_STRAW: + return ((struct crush_bucket_straw *)b)->item_weights[p]; + } + return 0; +} + +/** + * crush_calc_parents - Calculate parent vectors for the given crush map. + * @map: crush_map pointer + */ +void crush_calc_parents(struct crush_map *map) +{ + int i, b, c; + + for (b = 0; b < map->max_buckets; b++) { + if (map->buckets[b] == NULL) + continue; + for (i = 0; i < map->buckets[b]->size; i++) { + c = map->buckets[b]->items[i]; + BUG_ON(c >= map->max_devices || + c < -map->max_buckets); + if (c >= 0) + map->device_parents[c] = map->buckets[b]->id; + else + map->bucket_parents[-1-c] = map->buckets[b]->id; + } + } +} + +void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b) +{ + kfree(b->h.perm); + kfree(b->h.items); + kfree(b); +} + +void crush_destroy_bucket_list(struct crush_bucket_list *b) +{ + kfree(b->item_weights); + kfree(b->sum_weights); + kfree(b->h.perm); + kfree(b->h.items); + kfree(b); +} + +void crush_destroy_bucket_tree(struct crush_bucket_tree *b) +{ + kfree(b->node_weights); + kfree(b); +} + +void crush_destroy_bucket_straw(struct crush_bucket_straw *b) +{ + kfree(b->straws); + kfree(b->item_weights); + kfree(b->h.perm); + kfree(b->h.items); + kfree(b); +} + +void crush_destroy_bucket(struct crush_bucket *b) +{ + switch (b->alg) { + case CRUSH_BUCKET_UNIFORM: + crush_destroy_bucket_uniform((struct crush_bucket_uniform *)b); + break; + case CRUSH_BUCKET_LIST: + crush_destroy_bucket_list((struct crush_bucket_list *)b); + break; + case CRUSH_BUCKET_TREE: + crush_destroy_bucket_tree((struct crush_bucket_tree *)b); + break; + case CRUSH_BUCKET_STRAW: + crush_destroy_bucket_straw((struct crush_bucket_straw *)b); + break; + } +} + +/** + * crush_destroy - Destroy a crush_map + * @map: crush_map pointer + */ +void crush_destroy(struct crush_map *map) +{ + int b; + + /* buckets */ + if (map->buckets) { + for (b = 0; b < map->max_buckets; b++) { + if (map->buckets[b] == NULL) + continue; + crush_destroy_bucket(map->buckets[b]); + } + kfree(map->buckets); + } + + /* rules */ + if (map->rules) { + for (b = 0; b < map->max_rules; b++) + kfree(map->rules[b]); + kfree(map->rules); + } + + kfree(map->bucket_parents); + kfree(map->device_parents); + kfree(map); +} + + diff --git a/net/ceph/crush/hash.c b/net/ceph/crush/hash.c new file mode 100644 index 000000000000..5bb63e37a8a1 --- /dev/null +++ b/net/ceph/crush/hash.c @@ -0,0 +1,149 @@ + +#include +#include + +/* + * Robert Jenkins' function for mixing 32-bit values + * http://burtleburtle.net/bob/hash/evahash.html + * a, b = random bits, c = input and output + */ +#define crush_hashmix(a, b, c) do { \ + a = a-b; a = a-c; a = a^(c>>13); \ + b = b-c; b = b-a; b = b^(a<<8); \ + c = c-a; c = c-b; c = c^(b>>13); \ + a = a-b; a = a-c; a = a^(c>>12); \ + b = b-c; b = b-a; b = b^(a<<16); \ + c = c-a; c = c-b; c = c^(b>>5); \ + a = a-b; a = a-c; a = a^(c>>3); \ + b = b-c; b = b-a; b = b^(a<<10); \ + c = c-a; c = c-b; c = c^(b>>15); \ + } while (0) + +#define crush_hash_seed 1315423911 + +static __u32 crush_hash32_rjenkins1(__u32 a) +{ + __u32 hash = crush_hash_seed ^ a; + __u32 b = a; + __u32 x = 231232; + __u32 y = 1232; + crush_hashmix(b, x, hash); + crush_hashmix(y, a, hash); + return hash; +} + +static __u32 crush_hash32_rjenkins1_2(__u32 a, __u32 b) +{ + __u32 hash = crush_hash_seed ^ a ^ b; + __u32 x = 231232; + __u32 y = 1232; + crush_hashmix(a, b, hash); + crush_hashmix(x, a, hash); + crush_hashmix(b, y, hash); + return hash; +} + +static __u32 crush_hash32_rjenkins1_3(__u32 a, __u32 b, __u32 c) +{ + __u32 hash = crush_hash_seed ^ a ^ b ^ c; + __u32 x = 231232; + __u32 y = 1232; + crush_hashmix(a, b, hash); + crush_hashmix(c, x, hash); + crush_hashmix(y, a, hash); + crush_hashmix(b, x, hash); + crush_hashmix(y, c, hash); + return hash; +} + +static __u32 crush_hash32_rjenkins1_4(__u32 a, __u32 b, __u32 c, __u32 d) +{ + __u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d; + __u32 x = 231232; + __u32 y = 1232; + crush_hashmix(a, b, hash); + crush_hashmix(c, d, hash); + crush_hashmix(a, x, hash); + crush_hashmix(y, b, hash); + crush_hashmix(c, x, hash); + crush_hashmix(y, d, hash); + return hash; +} + +static __u32 crush_hash32_rjenkins1_5(__u32 a, __u32 b, __u32 c, __u32 d, + __u32 e) +{ + __u32 hash = crush_hash_seed ^ a ^ b ^ c ^ d ^ e; + __u32 x = 231232; + __u32 y = 1232; + crush_hashmix(a, b, hash); + crush_hashmix(c, d, hash); + crush_hashmix(e, x, hash); + crush_hashmix(y, a, hash); + crush_hashmix(b, x, hash); + crush_hashmix(y, c, hash); + crush_hashmix(d, x, hash); + crush_hashmix(y, e, hash); + return hash; +} + + +__u32 crush_hash32(int type, __u32 a) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return crush_hash32_rjenkins1(a); + default: + return 0; + } +} + +__u32 crush_hash32_2(int type, __u32 a, __u32 b) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return crush_hash32_rjenkins1_2(a, b); + default: + return 0; + } +} + +__u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return crush_hash32_rjenkins1_3(a, b, c); + default: + return 0; + } +} + +__u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return crush_hash32_rjenkins1_4(a, b, c, d); + default: + return 0; + } +} + +__u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, __u32 e) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return crush_hash32_rjenkins1_5(a, b, c, d, e); + default: + return 0; + } +} + +const char *crush_hash_name(int type) +{ + switch (type) { + case CRUSH_HASH_RJENKINS1: + return "rjenkins1"; + default: + return "unknown"; + } +} diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c new file mode 100644 index 000000000000..42599e31dcad --- /dev/null +++ b/net/ceph/crush/mapper.c @@ -0,0 +1,609 @@ + +#ifdef __KERNEL__ +# include +# include +# include +# include +# ifndef dprintk +# define dprintk(args...) +# endif +#else +# include +# include +# include +# include +# define BUG_ON(x) assert(!(x)) +# define dprintk(args...) /* printf(args) */ +# define kmalloc(x, f) malloc(x) +# define kfree(x) free(x) +#endif + +#include +#include + +/* + * Implement the core CRUSH mapping algorithm. + */ + +/** + * crush_find_rule - find a crush_rule id for a given ruleset, type, and size. + * @map: the crush_map + * @ruleset: the storage ruleset id (user defined) + * @type: storage ruleset type (user defined) + * @size: output set size + */ +int crush_find_rule(struct crush_map *map, int ruleset, int type, int size) +{ + int i; + + for (i = 0; i < map->max_rules; i++) { + if (map->rules[i] && + map->rules[i]->mask.ruleset == ruleset && + map->rules[i]->mask.type == type && + map->rules[i]->mask.min_size <= size && + map->rules[i]->mask.max_size >= size) + return i; + } + return -1; +} + + +/* + * bucket choose methods + * + * For each bucket algorithm, we have a "choose" method that, given a + * crush input @x and replica position (usually, position in output set) @r, + * will produce an item in the bucket. + */ + +/* + * Choose based on a random permutation of the bucket. + * + * We used to use some prime number arithmetic to do this, but it + * wasn't very random, and had some other bad behaviors. Instead, we + * calculate an actual random permutation of the bucket members. + * Since this is expensive, we optimize for the r=0 case, which + * captures the vast majority of calls. + */ +static int bucket_perm_choose(struct crush_bucket *bucket, + int x, int r) +{ + unsigned pr = r % bucket->size; + unsigned i, s; + + /* start a new permutation if @x has changed */ + if (bucket->perm_x != x || bucket->perm_n == 0) { + dprintk("bucket %d new x=%d\n", bucket->id, x); + bucket->perm_x = x; + + /* optimize common r=0 case */ + if (pr == 0) { + s = crush_hash32_3(bucket->hash, x, bucket->id, 0) % + bucket->size; + bucket->perm[0] = s; + bucket->perm_n = 0xffff; /* magic value, see below */ + goto out; + } + + for (i = 0; i < bucket->size; i++) + bucket->perm[i] = i; + bucket->perm_n = 0; + } else if (bucket->perm_n == 0xffff) { + /* clean up after the r=0 case above */ + for (i = 1; i < bucket->size; i++) + bucket->perm[i] = i; + bucket->perm[bucket->perm[0]] = 0; + bucket->perm_n = 1; + } + + /* calculate permutation up to pr */ + for (i = 0; i < bucket->perm_n; i++) + dprintk(" perm_choose have %d: %d\n", i, bucket->perm[i]); + while (bucket->perm_n <= pr) { + unsigned p = bucket->perm_n; + /* no point in swapping the final entry */ + if (p < bucket->size - 1) { + i = crush_hash32_3(bucket->hash, x, bucket->id, p) % + (bucket->size - p); + if (i) { + unsigned t = bucket->perm[p + i]; + bucket->perm[p + i] = bucket->perm[p]; + bucket->perm[p] = t; + } + dprintk(" perm_choose swap %d with %d\n", p, p+i); + } + bucket->perm_n++; + } + for (i = 0; i < bucket->size; i++) + dprintk(" perm_choose %d: %d\n", i, bucket->perm[i]); + + s = bucket->perm[pr]; +out: + dprintk(" perm_choose %d sz=%d x=%d r=%d (%d) s=%d\n", bucket->id, + bucket->size, x, r, pr, s); + return bucket->items[s]; +} + +/* uniform */ +static int bucket_uniform_choose(struct crush_bucket_uniform *bucket, + int x, int r) +{ + return bucket_perm_choose(&bucket->h, x, r); +} + +/* list */ +static int bucket_list_choose(struct crush_bucket_list *bucket, + int x, int r) +{ + int i; + + for (i = bucket->h.size-1; i >= 0; i--) { + __u64 w = crush_hash32_4(bucket->h.hash,x, bucket->h.items[i], + r, bucket->h.id); + w &= 0xffff; + dprintk("list_choose i=%d x=%d r=%d item %d weight %x " + "sw %x rand %llx", + i, x, r, bucket->h.items[i], bucket->item_weights[i], + bucket->sum_weights[i], w); + w *= bucket->sum_weights[i]; + w = w >> 16; + /*dprintk(" scaled %llx\n", w);*/ + if (w < bucket->item_weights[i]) + return bucket->h.items[i]; + } + + BUG_ON(1); + return 0; +} + + +/* (binary) tree */ +static int height(int n) +{ + int h = 0; + while ((n & 1) == 0) { + h++; + n = n >> 1; + } + return h; +} + +static int left(int x) +{ + int h = height(x); + return x - (1 << (h-1)); +} + +static int right(int x) +{ + int h = height(x); + return x + (1 << (h-1)); +} + +static int terminal(int x) +{ + return x & 1; +} + +static int bucket_tree_choose(struct crush_bucket_tree *bucket, + int x, int r) +{ + int n, l; + __u32 w; + __u64 t; + + /* start at root */ + n = bucket->num_nodes >> 1; + + while (!terminal(n)) { + /* pick point in [0, w) */ + w = bucket->node_weights[n]; + t = (__u64)crush_hash32_4(bucket->h.hash, x, n, r, + bucket->h.id) * (__u64)w; + t = t >> 32; + + /* descend to the left or right? */ + l = left(n); + if (t < bucket->node_weights[l]) + n = l; + else + n = right(n); + } + + return bucket->h.items[n >> 1]; +} + + +/* straw */ + +static int bucket_straw_choose(struct crush_bucket_straw *bucket, + int x, int r) +{ + int i; + int high = 0; + __u64 high_draw = 0; + __u64 draw; + + for (i = 0; i < bucket->h.size; i++) { + draw = crush_hash32_3(bucket->h.hash, x, bucket->h.items[i], r); + draw &= 0xffff; + draw *= bucket->straws[i]; + if (i == 0 || draw > high_draw) { + high = i; + high_draw = draw; + } + } + return bucket->h.items[high]; +} + +static int crush_bucket_choose(struct crush_bucket *in, int x, int r) +{ + dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r); + switch (in->alg) { + case CRUSH_BUCKET_UNIFORM: + return bucket_uniform_choose((struct crush_bucket_uniform *)in, + x, r); + case CRUSH_BUCKET_LIST: + return bucket_list_choose((struct crush_bucket_list *)in, + x, r); + case CRUSH_BUCKET_TREE: + return bucket_tree_choose((struct crush_bucket_tree *)in, + x, r); + case CRUSH_BUCKET_STRAW: + return bucket_straw_choose((struct crush_bucket_straw *)in, + x, r); + default: + BUG_ON(1); + return in->items[0]; + } +} + +/* + * true if device is marked "out" (failed, fully offloaded) + * of the cluster + */ +static int is_out(struct crush_map *map, __u32 *weight, int item, int x) +{ + if (weight[item] >= 0x10000) + return 0; + if (weight[item] == 0) + return 1; + if ((crush_hash32_2(CRUSH_HASH_RJENKINS1, x, item) & 0xffff) + < weight[item]) + return 0; + return 1; +} + +/** + * crush_choose - choose numrep distinct items of given type + * @map: the crush_map + * @bucket: the bucket we are choose an item from + * @x: crush input value + * @numrep: the number of items to choose + * @type: the type of item to choose + * @out: pointer to output vector + * @outpos: our position in that vector + * @firstn: true if choosing "first n" items, false if choosing "indep" + * @recurse_to_leaf: true if we want one device under each item of given type + * @out2: second output vector for leaf items (if @recurse_to_leaf) + */ +static int crush_choose(struct crush_map *map, + struct crush_bucket *bucket, + __u32 *weight, + int x, int numrep, int type, + int *out, int outpos, + int firstn, int recurse_to_leaf, + int *out2) +{ + int rep; + int ftotal, flocal; + int retry_descent, retry_bucket, skip_rep; + struct crush_bucket *in = bucket; + int r; + int i; + int item = 0; + int itemtype; + int collide, reject; + const int orig_tries = 5; /* attempts before we fall back to search */ + + dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", + bucket->id, x, outpos, numrep); + + for (rep = outpos; rep < numrep; rep++) { + /* keep trying until we get a non-out, non-colliding item */ + ftotal = 0; + skip_rep = 0; + do { + retry_descent = 0; + in = bucket; /* initial bucket */ + + /* choose through intervening buckets */ + flocal = 0; + do { + collide = 0; + retry_bucket = 0; + r = rep; + if (in->alg == CRUSH_BUCKET_UNIFORM) { + /* be careful */ + if (firstn || numrep >= in->size) + /* r' = r + f_total */ + r += ftotal; + else if (in->size % numrep == 0) + /* r'=r+(n+1)*f_local */ + r += (numrep+1) * + (flocal+ftotal); + else + /* r' = r + n*f_local */ + r += numrep * (flocal+ftotal); + } else { + if (firstn) + /* r' = r + f_total */ + r += ftotal; + else + /* r' = r + n*f_local */ + r += numrep * (flocal+ftotal); + } + + /* bucket choose */ + if (in->size == 0) { + reject = 1; + goto reject; + } + if (flocal >= (in->size>>1) && + flocal > orig_tries) + item = bucket_perm_choose(in, x, r); + else + item = crush_bucket_choose(in, x, r); + BUG_ON(item >= map->max_devices); + + /* desired type? */ + if (item < 0) + itemtype = map->buckets[-1-item]->type; + else + itemtype = 0; + dprintk(" item %d type %d\n", item, itemtype); + + /* keep going? */ + if (itemtype != type) { + BUG_ON(item >= 0 || + (-1-item) >= map->max_buckets); + in = map->buckets[-1-item]; + retry_bucket = 1; + continue; + } + + /* collision? */ + for (i = 0; i < outpos; i++) { + if (out[i] == item) { + collide = 1; + break; + } + } + + reject = 0; + if (recurse_to_leaf) { + if (item < 0) { + if (crush_choose(map, + map->buckets[-1-item], + weight, + x, outpos+1, 0, + out2, outpos, + firstn, 0, + NULL) <= outpos) + /* didn't get leaf */ + reject = 1; + } else { + /* we already have a leaf! */ + out2[outpos] = item; + } + } + + if (!reject) { + /* out? */ + if (itemtype == 0) + reject = is_out(map, weight, + item, x); + else + reject = 0; + } + +reject: + if (reject || collide) { + ftotal++; + flocal++; + + if (collide && flocal < 3) + /* retry locally a few times */ + retry_bucket = 1; + else if (flocal < in->size + orig_tries) + /* exhaustive bucket search */ + retry_bucket = 1; + else if (ftotal < 20) + /* then retry descent */ + retry_descent = 1; + else + /* else give up */ + skip_rep = 1; + dprintk(" reject %d collide %d " + "ftotal %d flocal %d\n", + reject, collide, ftotal, + flocal); + } + } while (retry_bucket); + } while (retry_descent); + + if (skip_rep) { + dprintk("skip rep\n"); + continue; + } + + dprintk("CHOOSE got %d\n", item); + out[outpos] = item; + outpos++; + } + + dprintk("CHOOSE returns %d\n", outpos); + return outpos; +} + + +/** + * crush_do_rule - calculate a mapping with the given input and rule + * @map: the crush_map + * @ruleno: the rule id + * @x: hash input + * @result: pointer to result vector + * @result_max: maximum result size + * @force: force initial replica choice; -1 for none + */ +int crush_do_rule(struct crush_map *map, + int ruleno, int x, int *result, int result_max, + int force, __u32 *weight) +{ + int result_len; + int force_context[CRUSH_MAX_DEPTH]; + int force_pos = -1; + int a[CRUSH_MAX_SET]; + int b[CRUSH_MAX_SET]; + int c[CRUSH_MAX_SET]; + int recurse_to_leaf; + int *w; + int wsize = 0; + int *o; + int osize; + int *tmp; + struct crush_rule *rule; + int step; + int i, j; + int numrep; + int firstn; + int rc = -1; + + BUG_ON(ruleno >= map->max_rules); + + rule = map->rules[ruleno]; + result_len = 0; + w = a; + o = b; + + /* + * determine hierarchical context of force, if any. note + * that this may or may not correspond to the specific types + * referenced by the crush rule. + */ + if (force >= 0) { + if (force >= map->max_devices || + map->device_parents[force] == 0) { + /*dprintk("CRUSH: forcefed device dne\n");*/ + rc = -1; /* force fed device dne */ + goto out; + } + if (!is_out(map, weight, force, x)) { + while (1) { + force_context[++force_pos] = force; + if (force >= 0) + force = map->device_parents[force]; + else + force = map->bucket_parents[-1-force]; + if (force == 0) + break; + } + } + } + + for (step = 0; step < rule->len; step++) { + firstn = 0; + switch (rule->steps[step].op) { + case CRUSH_RULE_TAKE: + w[0] = rule->steps[step].arg1; + if (force_pos >= 0) { + BUG_ON(force_context[force_pos] != w[0]); + force_pos--; + } + wsize = 1; + break; + + case CRUSH_RULE_CHOOSE_LEAF_FIRSTN: + case CRUSH_RULE_CHOOSE_FIRSTN: + firstn = 1; + case CRUSH_RULE_CHOOSE_LEAF_INDEP: + case CRUSH_RULE_CHOOSE_INDEP: + BUG_ON(wsize == 0); + + recurse_to_leaf = + rule->steps[step].op == + CRUSH_RULE_CHOOSE_LEAF_FIRSTN || + rule->steps[step].op == + CRUSH_RULE_CHOOSE_LEAF_INDEP; + + /* reset output */ + osize = 0; + + for (i = 0; i < wsize; i++) { + /* + * see CRUSH_N, CRUSH_N_MINUS macros. + * basically, numrep <= 0 means relative to + * the provided result_max + */ + numrep = rule->steps[step].arg1; + if (numrep <= 0) { + numrep += result_max; + if (numrep <= 0) + continue; + } + j = 0; + if (osize == 0 && force_pos >= 0) { + /* skip any intermediate types */ + while (force_pos && + force_context[force_pos] < 0 && + rule->steps[step].arg2 != + map->buckets[-1 - + force_context[force_pos]]->type) + force_pos--; + o[osize] = force_context[force_pos]; + if (recurse_to_leaf) + c[osize] = force_context[0]; + j++; + force_pos--; + } + osize += crush_choose(map, + map->buckets[-1-w[i]], + weight, + x, numrep, + rule->steps[step].arg2, + o+osize, j, + firstn, + recurse_to_leaf, c+osize); + } + + if (recurse_to_leaf) + /* copy final _leaf_ values to output set */ + memcpy(o, c, osize*sizeof(*o)); + + /* swap t and w arrays */ + tmp = o; + o = w; + w = tmp; + wsize = osize; + break; + + + case CRUSH_RULE_EMIT: + for (i = 0; i < wsize && result_len < result_max; i++) { + result[result_len] = w[i]; + result_len++; + } + wsize = 0; + break; + + default: + BUG_ON(1); + } + } + rc = result_len; + +out: + return rc; +} + + diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c new file mode 100644 index 000000000000..7b505b0c983f --- /dev/null +++ b/net/ceph/crypto.c @@ -0,0 +1,412 @@ + +#include + +#include +#include +#include +#include + +#include +#include "crypto.h" + +int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end) +{ + if (*p + sizeof(u16) + sizeof(key->created) + + sizeof(u16) + key->len > end) + return -ERANGE; + ceph_encode_16(p, key->type); + ceph_encode_copy(p, &key->created, sizeof(key->created)); + ceph_encode_16(p, key->len); + ceph_encode_copy(p, key->key, key->len); + return 0; +} + +int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end) +{ + ceph_decode_need(p, end, 2*sizeof(u16) + sizeof(key->created), bad); + key->type = ceph_decode_16(p); + ceph_decode_copy(p, &key->created, sizeof(key->created)); + key->len = ceph_decode_16(p); + ceph_decode_need(p, end, key->len, bad); + key->key = kmalloc(key->len, GFP_NOFS); + if (!key->key) + return -ENOMEM; + ceph_decode_copy(p, key->key, key->len); + return 0; + +bad: + dout("failed to decode crypto key\n"); + return -EINVAL; +} + +int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey) +{ + int inlen = strlen(inkey); + int blen = inlen * 3 / 4; + void *buf, *p; + int ret; + + dout("crypto_key_unarmor %s\n", inkey); + buf = kmalloc(blen, GFP_NOFS); + if (!buf) + return -ENOMEM; + blen = ceph_unarmor(buf, inkey, inkey+inlen); + if (blen < 0) { + kfree(buf); + return blen; + } + + p = buf; + ret = ceph_crypto_key_decode(key, &p, p + blen); + kfree(buf); + if (ret) + return ret; + dout("crypto_key_unarmor key %p type %d len %d\n", key, + key->type, key->len); + return 0; +} + + + +#define AES_KEY_SIZE 16 + +static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) +{ + return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC); +} + +static const u8 *aes_iv = (u8 *)CEPH_AES_IV; + +static int ceph_aes_encrypt(const void *key, int key_len, + void *dst, size_t *dst_len, + const void *src, size_t src_len) +{ + struct scatterlist sg_in[2], sg_out[1]; + struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); + struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; + int ret; + void *iv; + int ivsize; + size_t zero_padding = (0x10 - (src_len & 0x0f)); + char pad[16]; + + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + memset(pad, zero_padding, zero_padding); + + *dst_len = src_len + zero_padding; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); + sg_init_table(sg_in, 2); + sg_set_buf(&sg_in[0], src, src_len); + sg_set_buf(&sg_in[1], pad, zero_padding); + sg_init_table(sg_out, 1); + sg_set_buf(sg_out, dst, *dst_len); + iv = crypto_blkcipher_crt(tfm)->iv; + ivsize = crypto_blkcipher_ivsize(tfm); + + memcpy(iv, aes_iv, ivsize); + /* + print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, + key, key_len, 1); + print_hex_dump(KERN_ERR, "enc src: ", DUMP_PREFIX_NONE, 16, 1, + src, src_len, 1); + print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, + pad, zero_padding, 1); + */ + ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + src_len + zero_padding); + crypto_free_blkcipher(tfm); + if (ret < 0) + pr_err("ceph_aes_crypt failed %d\n", ret); + /* + print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, + dst, *dst_len, 1); + */ + return 0; +} + +static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, + size_t *dst_len, + const void *src1, size_t src1_len, + const void *src2, size_t src2_len) +{ + struct scatterlist sg_in[3], sg_out[1]; + struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); + struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; + int ret; + void *iv; + int ivsize; + size_t zero_padding = (0x10 - ((src1_len + src2_len) & 0x0f)); + char pad[16]; + + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + memset(pad, zero_padding, zero_padding); + + *dst_len = src1_len + src2_len + zero_padding; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); + sg_init_table(sg_in, 3); + sg_set_buf(&sg_in[0], src1, src1_len); + sg_set_buf(&sg_in[1], src2, src2_len); + sg_set_buf(&sg_in[2], pad, zero_padding); + sg_init_table(sg_out, 1); + sg_set_buf(sg_out, dst, *dst_len); + iv = crypto_blkcipher_crt(tfm)->iv; + ivsize = crypto_blkcipher_ivsize(tfm); + + memcpy(iv, aes_iv, ivsize); + /* + print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, + key, key_len, 1); + print_hex_dump(KERN_ERR, "enc src1: ", DUMP_PREFIX_NONE, 16, 1, + src1, src1_len, 1); + print_hex_dump(KERN_ERR, "enc src2: ", DUMP_PREFIX_NONE, 16, 1, + src2, src2_len, 1); + print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, + pad, zero_padding, 1); + */ + ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + src1_len + src2_len + zero_padding); + crypto_free_blkcipher(tfm); + if (ret < 0) + pr_err("ceph_aes_crypt2 failed %d\n", ret); + /* + print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, + dst, *dst_len, 1); + */ + return 0; +} + +static int ceph_aes_decrypt(const void *key, int key_len, + void *dst, size_t *dst_len, + const void *src, size_t src_len) +{ + struct scatterlist sg_in[1], sg_out[2]; + struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); + struct blkcipher_desc desc = { .tfm = tfm }; + char pad[16]; + void *iv; + int ivsize; + int ret; + int last_byte; + + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + crypto_blkcipher_setkey((void *)tfm, key, key_len); + sg_init_table(sg_in, 1); + sg_init_table(sg_out, 2); + sg_set_buf(sg_in, src, src_len); + sg_set_buf(&sg_out[0], dst, *dst_len); + sg_set_buf(&sg_out[1], pad, sizeof(pad)); + + iv = crypto_blkcipher_crt(tfm)->iv; + ivsize = crypto_blkcipher_ivsize(tfm); + + memcpy(iv, aes_iv, ivsize); + + /* + print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1, + key, key_len, 1); + print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, + src, src_len, 1); + */ + + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); + crypto_free_blkcipher(tfm); + if (ret < 0) { + pr_err("ceph_aes_decrypt failed %d\n", ret); + return ret; + } + + if (src_len <= *dst_len) + last_byte = ((char *)dst)[src_len - 1]; + else + last_byte = pad[src_len - *dst_len - 1]; + if (last_byte <= 16 && src_len >= last_byte) { + *dst_len = src_len - last_byte; + } else { + pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n", + last_byte, (int)src_len); + return -EPERM; /* bad padding */ + } + /* + print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, + dst, *dst_len, 1); + */ + return 0; +} + +static int ceph_aes_decrypt2(const void *key, int key_len, + void *dst1, size_t *dst1_len, + void *dst2, size_t *dst2_len, + const void *src, size_t src_len) +{ + struct scatterlist sg_in[1], sg_out[3]; + struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); + struct blkcipher_desc desc = { .tfm = tfm }; + char pad[16]; + void *iv; + int ivsize; + int ret; + int last_byte; + + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + sg_init_table(sg_in, 1); + sg_set_buf(sg_in, src, src_len); + sg_init_table(sg_out, 3); + sg_set_buf(&sg_out[0], dst1, *dst1_len); + sg_set_buf(&sg_out[1], dst2, *dst2_len); + sg_set_buf(&sg_out[2], pad, sizeof(pad)); + + crypto_blkcipher_setkey((void *)tfm, key, key_len); + iv = crypto_blkcipher_crt(tfm)->iv; + ivsize = crypto_blkcipher_ivsize(tfm); + + memcpy(iv, aes_iv, ivsize); + + /* + print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1, + key, key_len, 1); + print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, + src, src_len, 1); + */ + + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); + crypto_free_blkcipher(tfm); + if (ret < 0) { + pr_err("ceph_aes_decrypt failed %d\n", ret); + return ret; + } + + if (src_len <= *dst1_len) + last_byte = ((char *)dst1)[src_len - 1]; + else if (src_len <= *dst1_len + *dst2_len) + last_byte = ((char *)dst2)[src_len - *dst1_len - 1]; + else + last_byte = pad[src_len - *dst1_len - *dst2_len - 1]; + if (last_byte <= 16 && src_len >= last_byte) { + src_len -= last_byte; + } else { + pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n", + last_byte, (int)src_len); + return -EPERM; /* bad padding */ + } + + if (src_len < *dst1_len) { + *dst1_len = src_len; + *dst2_len = 0; + } else { + *dst2_len = src_len - *dst1_len; + } + /* + print_hex_dump(KERN_ERR, "dec out1: ", DUMP_PREFIX_NONE, 16, 1, + dst1, *dst1_len, 1); + print_hex_dump(KERN_ERR, "dec out2: ", DUMP_PREFIX_NONE, 16, 1, + dst2, *dst2_len, 1); + */ + + return 0; +} + + +int ceph_decrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, + const void *src, size_t src_len) +{ + switch (secret->type) { + case CEPH_CRYPTO_NONE: + if (*dst_len < src_len) + return -ERANGE; + memcpy(dst, src, src_len); + *dst_len = src_len; + return 0; + + case CEPH_CRYPTO_AES: + return ceph_aes_decrypt(secret->key, secret->len, dst, + dst_len, src, src_len); + + default: + return -EINVAL; + } +} + +int ceph_decrypt2(struct ceph_crypto_key *secret, + void *dst1, size_t *dst1_len, + void *dst2, size_t *dst2_len, + const void *src, size_t src_len) +{ + size_t t; + + switch (secret->type) { + case CEPH_CRYPTO_NONE: + if (*dst1_len + *dst2_len < src_len) + return -ERANGE; + t = min(*dst1_len, src_len); + memcpy(dst1, src, t); + *dst1_len = t; + src += t; + src_len -= t; + if (src_len) { + t = min(*dst2_len, src_len); + memcpy(dst2, src, t); + *dst2_len = t; + } + return 0; + + case CEPH_CRYPTO_AES: + return ceph_aes_decrypt2(secret->key, secret->len, + dst1, dst1_len, dst2, dst2_len, + src, src_len); + + default: + return -EINVAL; + } +} + +int ceph_encrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, + const void *src, size_t src_len) +{ + switch (secret->type) { + case CEPH_CRYPTO_NONE: + if (*dst_len < src_len) + return -ERANGE; + memcpy(dst, src, src_len); + *dst_len = src_len; + return 0; + + case CEPH_CRYPTO_AES: + return ceph_aes_encrypt(secret->key, secret->len, dst, + dst_len, src, src_len); + + default: + return -EINVAL; + } +} + +int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, + const void *src1, size_t src1_len, + const void *src2, size_t src2_len) +{ + switch (secret->type) { + case CEPH_CRYPTO_NONE: + if (*dst_len < src1_len + src2_len) + return -ERANGE; + memcpy(dst, src1, src1_len); + memcpy(dst + src1_len, src2, src2_len); + *dst_len = src1_len + src2_len; + return 0; + + case CEPH_CRYPTO_AES: + return ceph_aes_encrypt2(secret->key, secret->len, dst, dst_len, + src1, src1_len, src2, src2_len); + + default: + return -EINVAL; + } +} diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h new file mode 100644 index 000000000000..f9eccace592b --- /dev/null +++ b/net/ceph/crypto.h @@ -0,0 +1,48 @@ +#ifndef _FS_CEPH_CRYPTO_H +#define _FS_CEPH_CRYPTO_H + +#include +#include + +/* + * cryptographic secret + */ +struct ceph_crypto_key { + int type; + struct ceph_timespec created; + int len; + void *key; +}; + +static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) +{ + kfree(key->key); +} + +extern int ceph_crypto_key_encode(struct ceph_crypto_key *key, + void **p, void *end); +extern int ceph_crypto_key_decode(struct ceph_crypto_key *key, + void **p, void *end); +extern int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *in); + +/* crypto.c */ +extern int ceph_decrypt(struct ceph_crypto_key *secret, + void *dst, size_t *dst_len, + const void *src, size_t src_len); +extern int ceph_encrypt(struct ceph_crypto_key *secret, + void *dst, size_t *dst_len, + const void *src, size_t src_len); +extern int ceph_decrypt2(struct ceph_crypto_key *secret, + void *dst1, size_t *dst1_len, + void *dst2, size_t *dst2_len, + const void *src, size_t src_len); +extern int ceph_encrypt2(struct ceph_crypto_key *secret, + void *dst, size_t *dst_len, + const void *src1, size_t src1_len, + const void *src2, size_t src2_len); + +/* armor.c */ +extern int ceph_armor(char *dst, const char *src, const char *end); +extern int ceph_unarmor(char *dst, const char *src, const char *end); + +#endif diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c new file mode 100644 index 000000000000..33d04999f4f2 --- /dev/null +++ b/net/ceph/debugfs.c @@ -0,0 +1,268 @@ +#include + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#ifdef CONFIG_DEBUG_FS + +/* + * Implement /sys/kernel/debug/ceph fun + * + * /sys/kernel/debug/ceph/client* - an instance of the ceph client + * .../osdmap - current osdmap + * .../monmap - current monmap + * .../osdc - active osd requests + * .../monc - mon client state + * .../dentry_lru - dump contents of dentry lru + * .../caps - expose cap (reservation) stats + * .../bdi - symlink to ../../bdi/something + */ + +static struct dentry *ceph_debugfs_dir; + +static int monmap_show(struct seq_file *s, void *p) +{ + int i; + struct ceph_client *client = s->private; + + if (client->monc.monmap == NULL) + return 0; + + seq_printf(s, "epoch %d\n", client->monc.monmap->epoch); + for (i = 0; i < client->monc.monmap->num_mon; i++) { + struct ceph_entity_inst *inst = + &client->monc.monmap->mon_inst[i]; + + seq_printf(s, "\t%s%lld\t%s\n", + ENTITY_NAME(inst->name), + ceph_pr_addr(&inst->addr.in_addr)); + } + return 0; +} + +static int osdmap_show(struct seq_file *s, void *p) +{ + int i; + struct ceph_client *client = s->private; + struct rb_node *n; + + if (client->osdc.osdmap == NULL) + return 0; + seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch); + seq_printf(s, "flags%s%s\n", + (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ? + " NEARFULL" : "", + (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ? + " FULL" : ""); + for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) { + struct ceph_pg_pool_info *pool = + rb_entry(n, struct ceph_pg_pool_info, node); + seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n", + pool->id, pool->v.pg_num, pool->pg_num_mask, + pool->v.lpg_num, pool->lpg_num_mask); + } + for (i = 0; i < client->osdc.osdmap->max_osd; i++) { + struct ceph_entity_addr *addr = + &client->osdc.osdmap->osd_addr[i]; + int state = client->osdc.osdmap->osd_state[i]; + char sb[64]; + + seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n", + i, ceph_pr_addr(&addr->in_addr), + ((client->osdc.osdmap->osd_weight[i]*100) >> 16), + ceph_osdmap_state_str(sb, sizeof(sb), state)); + } + return 0; +} + +static int monc_show(struct seq_file *s, void *p) +{ + struct ceph_client *client = s->private; + struct ceph_mon_generic_request *req; + struct ceph_mon_client *monc = &client->monc; + struct rb_node *rp; + + mutex_lock(&monc->mutex); + + if (monc->have_mdsmap) + seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap); + if (monc->have_osdmap) + seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap); + if (monc->want_next_osdmap) + seq_printf(s, "want next osdmap\n"); + + for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) { + __u16 op; + req = rb_entry(rp, struct ceph_mon_generic_request, node); + op = le16_to_cpu(req->request->hdr.type); + if (op == CEPH_MSG_STATFS) + seq_printf(s, "%lld statfs\n", req->tid); + else + seq_printf(s, "%lld unknown\n", req->tid); + } + + mutex_unlock(&monc->mutex); + return 0; +} + +static int osdc_show(struct seq_file *s, void *pp) +{ + struct ceph_client *client = s->private; + struct ceph_osd_client *osdc = &client->osdc; + struct rb_node *p; + + mutex_lock(&osdc->request_mutex); + for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { + struct ceph_osd_request *req; + struct ceph_osd_request_head *head; + struct ceph_osd_op *op; + int num_ops; + int opcode, olen; + int i; + + req = rb_entry(p, struct ceph_osd_request, r_node); + + seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1, + le32_to_cpu(req->r_pgid.pool), + le16_to_cpu(req->r_pgid.ps)); + + head = req->r_request->front.iov_base; + op = (void *)(head + 1); + + num_ops = le16_to_cpu(head->num_ops); + olen = le32_to_cpu(head->object_len); + seq_printf(s, "%.*s", olen, + (const char *)(head->ops + num_ops)); + + if (req->r_reassert_version.epoch) + seq_printf(s, "\t%u'%llu", + (unsigned)le32_to_cpu(req->r_reassert_version.epoch), + le64_to_cpu(req->r_reassert_version.version)); + else + seq_printf(s, "\t"); + + for (i = 0; i < num_ops; i++) { + opcode = le16_to_cpu(op->op); + seq_printf(s, "\t%s", ceph_osd_op_name(opcode)); + op++; + } + + seq_printf(s, "\n"); + } + mutex_unlock(&osdc->request_mutex); + return 0; +} + +CEPH_DEFINE_SHOW_FUNC(monmap_show) +CEPH_DEFINE_SHOW_FUNC(osdmap_show) +CEPH_DEFINE_SHOW_FUNC(monc_show) +CEPH_DEFINE_SHOW_FUNC(osdc_show) + +int ceph_debugfs_init(void) +{ + ceph_debugfs_dir = debugfs_create_dir("ceph", NULL); + if (!ceph_debugfs_dir) + return -ENOMEM; + return 0; +} + +void ceph_debugfs_cleanup(void) +{ + debugfs_remove(ceph_debugfs_dir); +} + +int ceph_debugfs_client_init(struct ceph_client *client) +{ + int ret = -ENOMEM; + char name[80]; + + snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid, + client->monc.auth->global_id); + + client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir); + if (!client->debugfs_dir) + goto out; + + client->monc.debugfs_file = debugfs_create_file("monc", + 0600, + client->debugfs_dir, + client, + &monc_show_fops); + if (!client->monc.debugfs_file) + goto out; + + client->osdc.debugfs_file = debugfs_create_file("osdc", + 0600, + client->debugfs_dir, + client, + &osdc_show_fops); + if (!client->osdc.debugfs_file) + goto out; + + client->debugfs_monmap = debugfs_create_file("monmap", + 0600, + client->debugfs_dir, + client, + &monmap_show_fops); + if (!client->debugfs_monmap) + goto out; + + client->debugfs_osdmap = debugfs_create_file("osdmap", + 0600, + client->debugfs_dir, + client, + &osdmap_show_fops); + if (!client->debugfs_osdmap) + goto out; + + return 0; + +out: + ceph_debugfs_client_cleanup(client); + return ret; +} + +void ceph_debugfs_client_cleanup(struct ceph_client *client) +{ + debugfs_remove(client->debugfs_osdmap); + debugfs_remove(client->debugfs_monmap); + debugfs_remove(client->osdc.debugfs_file); + debugfs_remove(client->monc.debugfs_file); + debugfs_remove(client->debugfs_dir); +} + +#else /* CONFIG_DEBUG_FS */ + +int ceph_debugfs_init(void) +{ + return 0; +} + +void ceph_debugfs_cleanup(void) +{ +} + +int ceph_debugfs_client_init(struct ceph_client *client, + int (*module_debugfs_init)(struct ceph_client *)) +{ + return 0; +} + +void ceph_debugfs_client_cleanup(struct ceph_client *client) +{ +} + +#endif /* CONFIG_DEBUG_FS */ + +EXPORT_SYMBOL(ceph_debugfs_init); +EXPORT_SYMBOL(ceph_debugfs_cleanup); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c new file mode 100644 index 000000000000..0e8157ee5d43 --- /dev/null +++ b/net/ceph/messenger.c @@ -0,0 +1,2453 @@ +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* + * Ceph uses the messenger to exchange ceph_msg messages with other + * hosts in the system. The messenger provides ordered and reliable + * delivery. We tolerate TCP disconnects by reconnecting (with + * exponential backoff) in the case of a fault (disconnection, bad + * crc, protocol error). Acks allow sent messages to be discarded by + * the sender. + */ + +/* static tag bytes (protocol control messages) */ +static char tag_msg = CEPH_MSGR_TAG_MSG; +static char tag_ack = CEPH_MSGR_TAG_ACK; +static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE; + +#ifdef CONFIG_LOCKDEP +static struct lock_class_key socket_class; +#endif + + +static void queue_con(struct ceph_connection *con); +static void con_work(struct work_struct *); +static void ceph_fault(struct ceph_connection *con); + +/* + * nicely render a sockaddr as a string. + */ +#define MAX_ADDR_STR 20 +#define MAX_ADDR_STR_LEN 60 +static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN]; +static DEFINE_SPINLOCK(addr_str_lock); +static int last_addr_str; + +const char *ceph_pr_addr(const struct sockaddr_storage *ss) +{ + int i; + char *s; + struct sockaddr_in *in4 = (void *)ss; + struct sockaddr_in6 *in6 = (void *)ss; + + spin_lock(&addr_str_lock); + i = last_addr_str++; + if (last_addr_str == MAX_ADDR_STR) + last_addr_str = 0; + spin_unlock(&addr_str_lock); + s = addr_str[i]; + + switch (ss->ss_family) { + case AF_INET: + snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr, + (unsigned int)ntohs(in4->sin_port)); + break; + + case AF_INET6: + snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr, + (unsigned int)ntohs(in6->sin6_port)); + break; + + default: + sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family); + } + + return s; +} +EXPORT_SYMBOL(ceph_pr_addr); + +static void encode_my_addr(struct ceph_messenger *msgr) +{ + memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr)); + ceph_encode_addr(&msgr->my_enc_addr); +} + +/* + * work queue for all reading and writing to/from the socket. + */ +struct workqueue_struct *ceph_msgr_wq; + +int ceph_msgr_init(void) +{ + ceph_msgr_wq = create_workqueue("ceph-msgr"); + if (IS_ERR(ceph_msgr_wq)) { + int ret = PTR_ERR(ceph_msgr_wq); + pr_err("msgr_init failed to create workqueue: %d\n", ret); + ceph_msgr_wq = NULL; + return ret; + } + return 0; +} +EXPORT_SYMBOL(ceph_msgr_init); + +void ceph_msgr_exit(void) +{ + destroy_workqueue(ceph_msgr_wq); +} +EXPORT_SYMBOL(ceph_msgr_exit); + +void ceph_msgr_flush(void) +{ + flush_workqueue(ceph_msgr_wq); +} +EXPORT_SYMBOL(ceph_msgr_flush); + + +/* + * socket callback functions + */ + +/* data available on socket, or listen socket received a connect */ +static void ceph_data_ready(struct sock *sk, int count_unused) +{ + struct ceph_connection *con = + (struct ceph_connection *)sk->sk_user_data; + if (sk->sk_state != TCP_CLOSE_WAIT) { + dout("ceph_data_ready on %p state = %lu, queueing work\n", + con, con->state); + queue_con(con); + } +} + +/* socket has buffer space for writing */ +static void ceph_write_space(struct sock *sk) +{ + struct ceph_connection *con = + (struct ceph_connection *)sk->sk_user_data; + + /* only queue to workqueue if there is data we want to write. */ + if (test_bit(WRITE_PENDING, &con->state)) { + dout("ceph_write_space %p queueing write work\n", con); + queue_con(con); + } else { + dout("ceph_write_space %p nothing to write\n", con); + } + + /* since we have our own write_space, clear the SOCK_NOSPACE flag */ + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +} + +/* socket's state has changed */ +static void ceph_state_change(struct sock *sk) +{ + struct ceph_connection *con = + (struct ceph_connection *)sk->sk_user_data; + + dout("ceph_state_change %p state = %lu sk_state = %u\n", + con, con->state, sk->sk_state); + + if (test_bit(CLOSED, &con->state)) + return; + + switch (sk->sk_state) { + case TCP_CLOSE: + dout("ceph_state_change TCP_CLOSE\n"); + case TCP_CLOSE_WAIT: + dout("ceph_state_change TCP_CLOSE_WAIT\n"); + if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) { + if (test_bit(CONNECTING, &con->state)) + con->error_msg = "connection failed"; + else + con->error_msg = "socket closed"; + queue_con(con); + } + break; + case TCP_ESTABLISHED: + dout("ceph_state_change TCP_ESTABLISHED\n"); + queue_con(con); + break; + } +} + +/* + * set up socket callbacks + */ +static void set_sock_callbacks(struct socket *sock, + struct ceph_connection *con) +{ + struct sock *sk = sock->sk; + sk->sk_user_data = (void *)con; + sk->sk_data_ready = ceph_data_ready; + sk->sk_write_space = ceph_write_space; + sk->sk_state_change = ceph_state_change; +} + + +/* + * socket helpers + */ + +/* + * initiate connection to a remote socket. + */ +static struct socket *ceph_tcp_connect(struct ceph_connection *con) +{ + struct sockaddr_storage *paddr = &con->peer_addr.in_addr; + struct socket *sock; + int ret; + + BUG_ON(con->sock); + ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM, + IPPROTO_TCP, &sock); + if (ret) + return ERR_PTR(ret); + con->sock = sock; + sock->sk->sk_allocation = GFP_NOFS; + +#ifdef CONFIG_LOCKDEP + lockdep_set_class(&sock->sk->sk_lock, &socket_class); +#endif + + set_sock_callbacks(sock, con); + + dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr)); + + ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr), + O_NONBLOCK); + if (ret == -EINPROGRESS) { + dout("connect %s EINPROGRESS sk_state = %u\n", + ceph_pr_addr(&con->peer_addr.in_addr), + sock->sk->sk_state); + ret = 0; + } + if (ret < 0) { + pr_err("connect %s error %d\n", + ceph_pr_addr(&con->peer_addr.in_addr), ret); + sock_release(sock); + con->sock = NULL; + con->error_msg = "connect error"; + } + + if (ret < 0) + return ERR_PTR(ret); + return sock; +} + +static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) +{ + struct kvec iov = {buf, len}; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + + return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); +} + +/* + * write something. @more is true if caller will be sending more data + * shortly. + */ +static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, + size_t kvlen, size_t len, int more) +{ + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + + if (more) + msg.msg_flags |= MSG_MORE; + else + msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ + + return kernel_sendmsg(sock, &msg, iov, kvlen, len); +} + + +/* + * Shutdown/close the socket for the given connection. + */ +static int con_close_socket(struct ceph_connection *con) +{ + int rc; + + dout("con_close_socket on %p sock %p\n", con, con->sock); + if (!con->sock) + return 0; + set_bit(SOCK_CLOSED, &con->state); + rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); + sock_release(con->sock); + con->sock = NULL; + clear_bit(SOCK_CLOSED, &con->state); + return rc; +} + +/* + * Reset a connection. Discard all incoming and outgoing messages + * and clear *_seq state. + */ +static void ceph_msg_remove(struct ceph_msg *msg) +{ + list_del_init(&msg->list_head); + ceph_msg_put(msg); +} +static void ceph_msg_remove_list(struct list_head *head) +{ + while (!list_empty(head)) { + struct ceph_msg *msg = list_first_entry(head, struct ceph_msg, + list_head); + ceph_msg_remove(msg); + } +} + +static void reset_connection(struct ceph_connection *con) +{ + /* reset connection, out_queue, msg_ and connect_seq */ + /* discard existing out_queue and msg_seq */ + ceph_msg_remove_list(&con->out_queue); + ceph_msg_remove_list(&con->out_sent); + + if (con->in_msg) { + ceph_msg_put(con->in_msg); + con->in_msg = NULL; + } + + con->connect_seq = 0; + con->out_seq = 0; + if (con->out_msg) { + ceph_msg_put(con->out_msg); + con->out_msg = NULL; + } + con->out_keepalive_pending = false; + con->in_seq = 0; + con->in_seq_acked = 0; +} + +/* + * mark a peer down. drop any open connections. + */ +void ceph_con_close(struct ceph_connection *con) +{ + dout("con_close %p peer %s\n", con, + ceph_pr_addr(&con->peer_addr.in_addr)); + set_bit(CLOSED, &con->state); /* in case there's queued work */ + clear_bit(STANDBY, &con->state); /* avoid connect_seq bump */ + clear_bit(LOSSYTX, &con->state); /* so we retry next connect */ + clear_bit(KEEPALIVE_PENDING, &con->state); + clear_bit(WRITE_PENDING, &con->state); + mutex_lock(&con->mutex); + reset_connection(con); + con->peer_global_seq = 0; + cancel_delayed_work(&con->work); + mutex_unlock(&con->mutex); + queue_con(con); +} +EXPORT_SYMBOL(ceph_con_close); + +/* + * Reopen a closed connection, with a new peer address. + */ +void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr) +{ + dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr)); + set_bit(OPENING, &con->state); + clear_bit(CLOSED, &con->state); + memcpy(&con->peer_addr, addr, sizeof(*addr)); + con->delay = 0; /* reset backoff memory */ + queue_con(con); +} +EXPORT_SYMBOL(ceph_con_open); + +/* + * return true if this connection ever successfully opened + */ +bool ceph_con_opened(struct ceph_connection *con) +{ + return con->connect_seq > 0; +} + +/* + * generic get/put + */ +struct ceph_connection *ceph_con_get(struct ceph_connection *con) +{ + dout("con_get %p nref = %d -> %d\n", con, + atomic_read(&con->nref), atomic_read(&con->nref) + 1); + if (atomic_inc_not_zero(&con->nref)) + return con; + return NULL; +} + +void ceph_con_put(struct ceph_connection *con) +{ + dout("con_put %p nref = %d -> %d\n", con, + atomic_read(&con->nref), atomic_read(&con->nref) - 1); + BUG_ON(atomic_read(&con->nref) == 0); + if (atomic_dec_and_test(&con->nref)) { + BUG_ON(con->sock); + kfree(con); + } +} + +/* + * initialize a new connection. + */ +void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con) +{ + dout("con_init %p\n", con); + memset(con, 0, sizeof(*con)); + atomic_set(&con->nref, 1); + con->msgr = msgr; + mutex_init(&con->mutex); + INIT_LIST_HEAD(&con->out_queue); + INIT_LIST_HEAD(&con->out_sent); + INIT_DELAYED_WORK(&con->work, con_work); +} +EXPORT_SYMBOL(ceph_con_init); + + +/* + * We maintain a global counter to order connection attempts. Get + * a unique seq greater than @gt. + */ +static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) +{ + u32 ret; + + spin_lock(&msgr->global_seq_lock); + if (msgr->global_seq < gt) + msgr->global_seq = gt; + ret = ++msgr->global_seq; + spin_unlock(&msgr->global_seq_lock); + return ret; +} + + +/* + * Prepare footer for currently outgoing message, and finish things + * off. Assumes out_kvec* are already valid.. we just add on to the end. + */ +static void prepare_write_message_footer(struct ceph_connection *con, int v) +{ + struct ceph_msg *m = con->out_msg; + + dout("prepare_write_message_footer %p\n", con); + con->out_kvec_is_msg = true; + con->out_kvec[v].iov_base = &m->footer; + con->out_kvec[v].iov_len = sizeof(m->footer); + con->out_kvec_bytes += sizeof(m->footer); + con->out_kvec_left++; + con->out_more = m->more_to_follow; + con->out_msg_done = true; +} + +/* + * Prepare headers for the next outgoing message. + */ +static void prepare_write_message(struct ceph_connection *con) +{ + struct ceph_msg *m; + int v = 0; + + con->out_kvec_bytes = 0; + con->out_kvec_is_msg = true; + con->out_msg_done = false; + + /* Sneak an ack in there first? If we can get it into the same + * TCP packet that's a good thing. */ + if (con->in_seq > con->in_seq_acked) { + con->in_seq_acked = con->in_seq; + con->out_kvec[v].iov_base = &tag_ack; + con->out_kvec[v++].iov_len = 1; + con->out_temp_ack = cpu_to_le64(con->in_seq_acked); + con->out_kvec[v].iov_base = &con->out_temp_ack; + con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack); + con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); + } + + m = list_first_entry(&con->out_queue, + struct ceph_msg, list_head); + con->out_msg = m; + if (test_bit(LOSSYTX, &con->state)) { + list_del_init(&m->list_head); + } else { + /* put message on sent list */ + ceph_msg_get(m); + list_move_tail(&m->list_head, &con->out_sent); + } + + /* + * only assign outgoing seq # if we haven't sent this message + * yet. if it is requeued, resend with it's original seq. + */ + if (m->needs_out_seq) { + m->hdr.seq = cpu_to_le64(++con->out_seq); + m->needs_out_seq = false; + } + + dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n", + m, con->out_seq, le16_to_cpu(m->hdr.type), + le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len), + le32_to_cpu(m->hdr.data_len), + m->nr_pages); + BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len); + + /* tag + hdr + front + middle */ + con->out_kvec[v].iov_base = &tag_msg; + con->out_kvec[v++].iov_len = 1; + con->out_kvec[v].iov_base = &m->hdr; + con->out_kvec[v++].iov_len = sizeof(m->hdr); + con->out_kvec[v++] = m->front; + if (m->middle) + con->out_kvec[v++] = m->middle->vec; + con->out_kvec_left = v; + con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len + + (m->middle ? m->middle->vec.iov_len : 0); + con->out_kvec_cur = con->out_kvec; + + /* fill in crc (except data pages), footer */ + con->out_msg->hdr.crc = + cpu_to_le32(crc32c(0, (void *)&m->hdr, + sizeof(m->hdr) - sizeof(m->hdr.crc))); + con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE; + con->out_msg->footer.front_crc = + cpu_to_le32(crc32c(0, m->front.iov_base, m->front.iov_len)); + if (m->middle) + con->out_msg->footer.middle_crc = + cpu_to_le32(crc32c(0, m->middle->vec.iov_base, + m->middle->vec.iov_len)); + else + con->out_msg->footer.middle_crc = 0; + con->out_msg->footer.data_crc = 0; + dout("prepare_write_message front_crc %u data_crc %u\n", + le32_to_cpu(con->out_msg->footer.front_crc), + le32_to_cpu(con->out_msg->footer.middle_crc)); + + /* is there a data payload? */ + if (le32_to_cpu(m->hdr.data_len) > 0) { + /* initialize page iterator */ + con->out_msg_pos.page = 0; + if (m->pages) + con->out_msg_pos.page_pos = + le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK; + else + con->out_msg_pos.page_pos = 0; + con->out_msg_pos.data_pos = 0; + con->out_msg_pos.did_page_crc = 0; + con->out_more = 1; /* data + footer will follow */ + } else { + /* no, queue up footer too and be done */ + prepare_write_message_footer(con, v); + } + + set_bit(WRITE_PENDING, &con->state); +} + +/* + * Prepare an ack. + */ +static void prepare_write_ack(struct ceph_connection *con) +{ + dout("prepare_write_ack %p %llu -> %llu\n", con, + con->in_seq_acked, con->in_seq); + con->in_seq_acked = con->in_seq; + + con->out_kvec[0].iov_base = &tag_ack; + con->out_kvec[0].iov_len = 1; + con->out_temp_ack = cpu_to_le64(con->in_seq_acked); + con->out_kvec[1].iov_base = &con->out_temp_ack; + con->out_kvec[1].iov_len = sizeof(con->out_temp_ack); + con->out_kvec_left = 2; + con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); + con->out_kvec_cur = con->out_kvec; + con->out_more = 1; /* more will follow.. eventually.. */ + set_bit(WRITE_PENDING, &con->state); +} + +/* + * Prepare to write keepalive byte. + */ +static void prepare_write_keepalive(struct ceph_connection *con) +{ + dout("prepare_write_keepalive %p\n", con); + con->out_kvec[0].iov_base = &tag_keepalive; + con->out_kvec[0].iov_len = 1; + con->out_kvec_left = 1; + con->out_kvec_bytes = 1; + con->out_kvec_cur = con->out_kvec; + set_bit(WRITE_PENDING, &con->state); +} + +/* + * Connection negotiation. + */ + +static void prepare_connect_authorizer(struct ceph_connection *con) +{ + void *auth_buf; + int auth_len = 0; + int auth_protocol = 0; + + mutex_unlock(&con->mutex); + if (con->ops->get_authorizer) + con->ops->get_authorizer(con, &auth_buf, &auth_len, + &auth_protocol, &con->auth_reply_buf, + &con->auth_reply_buf_len, + con->auth_retry); + mutex_lock(&con->mutex); + + con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol); + con->out_connect.authorizer_len = cpu_to_le32(auth_len); + + con->out_kvec[con->out_kvec_left].iov_base = auth_buf; + con->out_kvec[con->out_kvec_left].iov_len = auth_len; + con->out_kvec_left++; + con->out_kvec_bytes += auth_len; +} + +/* + * We connected to a peer and are saying hello. + */ +static void prepare_write_banner(struct ceph_messenger *msgr, + struct ceph_connection *con) +{ + int len = strlen(CEPH_BANNER); + + con->out_kvec[0].iov_base = CEPH_BANNER; + con->out_kvec[0].iov_len = len; + con->out_kvec[1].iov_base = &msgr->my_enc_addr; + con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr); + con->out_kvec_left = 2; + con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr); + con->out_kvec_cur = con->out_kvec; + con->out_more = 0; + set_bit(WRITE_PENDING, &con->state); +} + +static void prepare_write_connect(struct ceph_messenger *msgr, + struct ceph_connection *con, + int after_banner) +{ + unsigned global_seq = get_global_seq(con->msgr, 0); + int proto; + + switch (con->peer_name.type) { + case CEPH_ENTITY_TYPE_MON: + proto = CEPH_MONC_PROTOCOL; + break; + case CEPH_ENTITY_TYPE_OSD: + proto = CEPH_OSDC_PROTOCOL; + break; + case CEPH_ENTITY_TYPE_MDS: + proto = CEPH_MDSC_PROTOCOL; + break; + default: + BUG(); + } + + dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con, + con->connect_seq, global_seq, proto); + + con->out_connect.features = cpu_to_le64(msgr->supported_features); + con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT); + con->out_connect.connect_seq = cpu_to_le32(con->connect_seq); + con->out_connect.global_seq = cpu_to_le32(global_seq); + con->out_connect.protocol_version = cpu_to_le32(proto); + con->out_connect.flags = 0; + + if (!after_banner) { + con->out_kvec_left = 0; + con->out_kvec_bytes = 0; + } + con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect; + con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect); + con->out_kvec_left++; + con->out_kvec_bytes += sizeof(con->out_connect); + con->out_kvec_cur = con->out_kvec; + con->out_more = 0; + set_bit(WRITE_PENDING, &con->state); + + prepare_connect_authorizer(con); +} + + +/* + * write as much of pending kvecs to the socket as we can. + * 1 -> done + * 0 -> socket full, but more to do + * <0 -> error + */ +static int write_partial_kvec(struct ceph_connection *con) +{ + int ret; + + dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes); + while (con->out_kvec_bytes > 0) { + ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur, + con->out_kvec_left, con->out_kvec_bytes, + con->out_more); + if (ret <= 0) + goto out; + con->out_kvec_bytes -= ret; + if (con->out_kvec_bytes == 0) + break; /* done */ + while (ret > 0) { + if (ret >= con->out_kvec_cur->iov_len) { + ret -= con->out_kvec_cur->iov_len; + con->out_kvec_cur++; + con->out_kvec_left--; + } else { + con->out_kvec_cur->iov_len -= ret; + con->out_kvec_cur->iov_base += ret; + ret = 0; + break; + } + } + } + con->out_kvec_left = 0; + con->out_kvec_is_msg = false; + ret = 1; +out: + dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con, + con->out_kvec_bytes, con->out_kvec_left, ret); + return ret; /* done! */ +} + +#ifdef CONFIG_BLOCK +static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +{ + if (!bio) { + *iter = NULL; + *seg = 0; + return; + } + *iter = bio; + *seg = bio->bi_idx; +} + +static void iter_bio_next(struct bio **bio_iter, int *seg) +{ + if (*bio_iter == NULL) + return; + + BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + + (*seg)++; + if (*seg == (*bio_iter)->bi_vcnt) + init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); +} +#endif + +/* + * Write as much message data payload as we can. If we finish, queue + * up the footer. + * 1 -> done, footer is now queued in out_kvec[]. + * 0 -> socket full, but more to do + * <0 -> error + */ +static int write_partial_msg_pages(struct ceph_connection *con) +{ + struct ceph_msg *msg = con->out_msg; + unsigned data_len = le32_to_cpu(msg->hdr.data_len); + size_t len; + int crc = con->msgr->nocrc; + int ret; + int total_max_write; + int in_trail = 0; + size_t trail_len = (msg->trail ? msg->trail->length : 0); + + dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n", + con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages, + con->out_msg_pos.page_pos); + +#ifdef CONFIG_BLOCK + if (msg->bio && !msg->bio_iter) + init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); +#endif + + while (data_len > con->out_msg_pos.data_pos) { + struct page *page = NULL; + void *kaddr = NULL; + int max_write = PAGE_SIZE; + int page_shift = 0; + + total_max_write = data_len - trail_len - + con->out_msg_pos.data_pos; + + /* + * if we are calculating the data crc (the default), we need + * to map the page. if our pages[] has been revoked, use the + * zero page. + */ + + /* have we reached the trail part of the data? */ + if (con->out_msg_pos.data_pos >= data_len - trail_len) { + in_trail = 1; + + total_max_write = data_len - con->out_msg_pos.data_pos; + + page = list_first_entry(&msg->trail->head, + struct page, lru); + if (crc) + kaddr = kmap(page); + max_write = PAGE_SIZE; + } else if (msg->pages) { + page = msg->pages[con->out_msg_pos.page]; + if (crc) + kaddr = kmap(page); + } else if (msg->pagelist) { + page = list_first_entry(&msg->pagelist->head, + struct page, lru); + if (crc) + kaddr = kmap(page); +#ifdef CONFIG_BLOCK + } else if (msg->bio) { + struct bio_vec *bv; + + bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg); + page = bv->bv_page; + page_shift = bv->bv_offset; + if (crc) + kaddr = kmap(page) + page_shift; + max_write = bv->bv_len; +#endif + } else { + page = con->msgr->zero_page; + if (crc) + kaddr = page_address(con->msgr->zero_page); + } + len = min_t(int, max_write - con->out_msg_pos.page_pos, + total_max_write); + + if (crc && !con->out_msg_pos.did_page_crc) { + void *base = kaddr + con->out_msg_pos.page_pos; + u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc); + + BUG_ON(kaddr == NULL); + con->out_msg->footer.data_crc = + cpu_to_le32(crc32c(tmpcrc, base, len)); + con->out_msg_pos.did_page_crc = 1; + } + ret = kernel_sendpage(con->sock, page, + con->out_msg_pos.page_pos + page_shift, + len, + MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_MORE); + + if (crc && + (msg->pages || msg->pagelist || msg->bio || in_trail)) + kunmap(page); + + if (ret <= 0) + goto out; + + con->out_msg_pos.data_pos += ret; + con->out_msg_pos.page_pos += ret; + if (ret == len) { + con->out_msg_pos.page_pos = 0; + con->out_msg_pos.page++; + con->out_msg_pos.did_page_crc = 0; + if (in_trail) + list_move_tail(&page->lru, + &msg->trail->head); + else if (msg->pagelist) + list_move_tail(&page->lru, + &msg->pagelist->head); +#ifdef CONFIG_BLOCK + else if (msg->bio) + iter_bio_next(&msg->bio_iter, &msg->bio_seg); +#endif + } + } + + dout("write_partial_msg_pages %p msg %p done\n", con, msg); + + /* prepare and queue up footer, too */ + if (!crc) + con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; + con->out_kvec_bytes = 0; + con->out_kvec_left = 0; + con->out_kvec_cur = con->out_kvec; + prepare_write_message_footer(con, 0); + ret = 1; +out: + return ret; +} + +/* + * write some zeros + */ +static int write_partial_skip(struct ceph_connection *con) +{ + int ret; + + while (con->out_skip > 0) { + struct kvec iov = { + .iov_base = page_address(con->msgr->zero_page), + .iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE) + }; + + ret = ceph_tcp_sendmsg(con->sock, &iov, 1, iov.iov_len, 1); + if (ret <= 0) + goto out; + con->out_skip -= ret; + } + ret = 1; +out: + return ret; +} + +/* + * Prepare to read connection handshake, or an ack. + */ +static void prepare_read_banner(struct ceph_connection *con) +{ + dout("prepare_read_banner %p\n", con); + con->in_base_pos = 0; +} + +static void prepare_read_connect(struct ceph_connection *con) +{ + dout("prepare_read_connect %p\n", con); + con->in_base_pos = 0; +} + +static void prepare_read_ack(struct ceph_connection *con) +{ + dout("prepare_read_ack %p\n", con); + con->in_base_pos = 0; +} + +static void prepare_read_tag(struct ceph_connection *con) +{ + dout("prepare_read_tag %p\n", con); + con->in_base_pos = 0; + con->in_tag = CEPH_MSGR_TAG_READY; +} + +/* + * Prepare to read a message. + */ +static int prepare_read_message(struct ceph_connection *con) +{ + dout("prepare_read_message %p\n", con); + BUG_ON(con->in_msg != NULL); + con->in_base_pos = 0; + con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0; + return 0; +} + + +static int read_partial(struct ceph_connection *con, + int *to, int size, void *object) +{ + *to += size; + while (con->in_base_pos < *to) { + int left = *to - con->in_base_pos; + int have = size - left; + int ret = ceph_tcp_recvmsg(con->sock, object + have, left); + if (ret <= 0) + return ret; + con->in_base_pos += ret; + } + return 1; +} + + +/* + * Read all or part of the connect-side handshake on a new connection + */ +static int read_partial_banner(struct ceph_connection *con) +{ + int ret, to = 0; + + dout("read_partial_banner %p at %d\n", con, con->in_base_pos); + + /* peer's banner */ + ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner); + if (ret <= 0) + goto out; + ret = read_partial(con, &to, sizeof(con->actual_peer_addr), + &con->actual_peer_addr); + if (ret <= 0) + goto out; + ret = read_partial(con, &to, sizeof(con->peer_addr_for_me), + &con->peer_addr_for_me); + if (ret <= 0) + goto out; +out: + return ret; +} + +static int read_partial_connect(struct ceph_connection *con) +{ + int ret, to = 0; + + dout("read_partial_connect %p at %d\n", con, con->in_base_pos); + + ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply); + if (ret <= 0) + goto out; + ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len), + con->auth_reply_buf); + if (ret <= 0) + goto out; + + dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n", + con, (int)con->in_reply.tag, + le32_to_cpu(con->in_reply.connect_seq), + le32_to_cpu(con->in_reply.global_seq)); +out: + return ret; + +} + +/* + * Verify the hello banner looks okay. + */ +static int verify_hello(struct ceph_connection *con) +{ + if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) { + pr_err("connect to %s got bad banner\n", + ceph_pr_addr(&con->peer_addr.in_addr)); + con->error_msg = "protocol error, bad banner"; + return -1; + } + return 0; +} + +static bool addr_is_blank(struct sockaddr_storage *ss) +{ + switch (ss->ss_family) { + case AF_INET: + return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0; + case AF_INET6: + return + ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 && + ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 && + ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 && + ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0; + } + return false; +} + +static int addr_port(struct sockaddr_storage *ss) +{ + switch (ss->ss_family) { + case AF_INET: + return ntohs(((struct sockaddr_in *)ss)->sin_port); + case AF_INET6: + return ntohs(((struct sockaddr_in6 *)ss)->sin6_port); + } + return 0; +} + +static void addr_set_port(struct sockaddr_storage *ss, int p) +{ + switch (ss->ss_family) { + case AF_INET: + ((struct sockaddr_in *)ss)->sin_port = htons(p); + case AF_INET6: + ((struct sockaddr_in6 *)ss)->sin6_port = htons(p); + } +} + +/* + * Parse an ip[:port] list into an addr array. Use the default + * monitor port if a port isn't specified. + */ +int ceph_parse_ips(const char *c, const char *end, + struct ceph_entity_addr *addr, + int max_count, int *count) +{ + int i; + const char *p = c; + + dout("parse_ips on '%.*s'\n", (int)(end-c), c); + for (i = 0; i < max_count; i++) { + const char *ipend; + struct sockaddr_storage *ss = &addr[i].in_addr; + struct sockaddr_in *in4 = (void *)ss; + struct sockaddr_in6 *in6 = (void *)ss; + int port; + char delim = ','; + + if (*p == '[') { + delim = ']'; + p++; + } + + memset(ss, 0, sizeof(*ss)); + if (in4_pton(p, end - p, (u8 *)&in4->sin_addr.s_addr, + delim, &ipend)) + ss->ss_family = AF_INET; + else if (in6_pton(p, end - p, (u8 *)&in6->sin6_addr.s6_addr, + delim, &ipend)) + ss->ss_family = AF_INET6; + else + goto bad; + p = ipend; + + if (delim == ']') { + if (*p != ']') { + dout("missing matching ']'\n"); + goto bad; + } + p++; + } + + /* port? */ + if (p < end && *p == ':') { + port = 0; + p++; + while (p < end && *p >= '0' && *p <= '9') { + port = (port * 10) + (*p - '0'); + p++; + } + if (port > 65535 || port == 0) + goto bad; + } else { + port = CEPH_MON_PORT; + } + + addr_set_port(ss, port); + + dout("parse_ips got %s\n", ceph_pr_addr(ss)); + + if (p == end) + break; + if (*p != ',') + goto bad; + p++; + } + + if (p != end) + goto bad; + + if (count) + *count = i + 1; + return 0; + +bad: + pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); + return -EINVAL; +} +EXPORT_SYMBOL(ceph_parse_ips); + +static int process_banner(struct ceph_connection *con) +{ + dout("process_banner on %p\n", con); + + if (verify_hello(con) < 0) + return -1; + + ceph_decode_addr(&con->actual_peer_addr); + ceph_decode_addr(&con->peer_addr_for_me); + + /* + * Make sure the other end is who we wanted. note that the other + * end may not yet know their ip address, so if it's 0.0.0.0, give + * them the benefit of the doubt. + */ + if (memcmp(&con->peer_addr, &con->actual_peer_addr, + sizeof(con->peer_addr)) != 0 && + !(addr_is_blank(&con->actual_peer_addr.in_addr) && + con->actual_peer_addr.nonce == con->peer_addr.nonce)) { + pr_warning("wrong peer, want %s/%d, got %s/%d\n", + ceph_pr_addr(&con->peer_addr.in_addr), + (int)le32_to_cpu(con->peer_addr.nonce), + ceph_pr_addr(&con->actual_peer_addr.in_addr), + (int)le32_to_cpu(con->actual_peer_addr.nonce)); + con->error_msg = "wrong peer at address"; + return -1; + } + + /* + * did we learn our address? + */ + if (addr_is_blank(&con->msgr->inst.addr.in_addr)) { + int port = addr_port(&con->msgr->inst.addr.in_addr); + + memcpy(&con->msgr->inst.addr.in_addr, + &con->peer_addr_for_me.in_addr, + sizeof(con->peer_addr_for_me.in_addr)); + addr_set_port(&con->msgr->inst.addr.in_addr, port); + encode_my_addr(con->msgr); + dout("process_banner learned my addr is %s\n", + ceph_pr_addr(&con->msgr->inst.addr.in_addr)); + } + + set_bit(NEGOTIATING, &con->state); + prepare_read_connect(con); + return 0; +} + +static void fail_protocol(struct ceph_connection *con) +{ + reset_connection(con); + set_bit(CLOSED, &con->state); /* in case there's queued work */ + + mutex_unlock(&con->mutex); + if (con->ops->bad_proto) + con->ops->bad_proto(con); + mutex_lock(&con->mutex); +} + +static int process_connect(struct ceph_connection *con) +{ + u64 sup_feat = con->msgr->supported_features; + u64 req_feat = con->msgr->required_features; + u64 server_feat = le64_to_cpu(con->in_reply.features); + + dout("process_connect on %p tag %d\n", con, (int)con->in_tag); + + switch (con->in_reply.tag) { + case CEPH_MSGR_TAG_FEATURES: + pr_err("%s%lld %s feature set mismatch," + " my %llx < server's %llx, missing %llx\n", + ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), + sup_feat, server_feat, server_feat & ~sup_feat); + con->error_msg = "missing required protocol features"; + fail_protocol(con); + return -1; + + case CEPH_MSGR_TAG_BADPROTOVER: + pr_err("%s%lld %s protocol version mismatch," + " my %d != server's %d\n", + ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), + le32_to_cpu(con->out_connect.protocol_version), + le32_to_cpu(con->in_reply.protocol_version)); + con->error_msg = "protocol version mismatch"; + fail_protocol(con); + return -1; + + case CEPH_MSGR_TAG_BADAUTHORIZER: + con->auth_retry++; + dout("process_connect %p got BADAUTHORIZER attempt %d\n", con, + con->auth_retry); + if (con->auth_retry == 2) { + con->error_msg = "connect authorization failure"; + reset_connection(con); + set_bit(CLOSED, &con->state); + return -1; + } + con->auth_retry = 1; + prepare_write_connect(con->msgr, con, 0); + prepare_read_connect(con); + break; + + case CEPH_MSGR_TAG_RESETSESSION: + /* + * If we connected with a large connect_seq but the peer + * has no record of a session with us (no connection, or + * connect_seq == 0), they will send RESETSESION to indicate + * that they must have reset their session, and may have + * dropped messages. + */ + dout("process_connect got RESET peer seq %u\n", + le32_to_cpu(con->in_connect.connect_seq)); + pr_err("%s%lld %s connection reset\n", + ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr)); + reset_connection(con); + prepare_write_connect(con->msgr, con, 0); + prepare_read_connect(con); + + /* Tell ceph about it. */ + mutex_unlock(&con->mutex); + pr_info("reset on %s%lld\n", ENTITY_NAME(con->peer_name)); + if (con->ops->peer_reset) + con->ops->peer_reset(con); + mutex_lock(&con->mutex); + break; + + case CEPH_MSGR_TAG_RETRY_SESSION: + /* + * If we sent a smaller connect_seq than the peer has, try + * again with a larger value. + */ + dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + le32_to_cpu(con->out_connect.connect_seq), + le32_to_cpu(con->in_connect.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); + prepare_write_connect(con->msgr, con, 0); + prepare_read_connect(con); + break; + + case CEPH_MSGR_TAG_RETRY_GLOBAL: + /* + * If we sent a smaller global_seq than the peer has, try + * again with a larger value. + */ + dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", + con->peer_global_seq, + le32_to_cpu(con->in_connect.global_seq)); + get_global_seq(con->msgr, + le32_to_cpu(con->in_connect.global_seq)); + prepare_write_connect(con->msgr, con, 0); + prepare_read_connect(con); + break; + + case CEPH_MSGR_TAG_READY: + if (req_feat & ~server_feat) { + pr_err("%s%lld %s protocol feature mismatch," + " my required %llx > server's %llx, need %llx\n", + ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), + req_feat, server_feat, req_feat & ~server_feat); + con->error_msg = "missing required protocol features"; + fail_protocol(con); + return -1; + } + clear_bit(CONNECTING, &con->state); + con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); + con->connect_seq++; + con->peer_features = server_feat; + dout("process_connect got READY gseq %d cseq %d (%d)\n", + con->peer_global_seq, + le32_to_cpu(con->in_reply.connect_seq), + con->connect_seq); + WARN_ON(con->connect_seq != + le32_to_cpu(con->in_reply.connect_seq)); + + if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY) + set_bit(LOSSYTX, &con->state); + + prepare_read_tag(con); + break; + + case CEPH_MSGR_TAG_WAIT: + /* + * If there is a connection race (we are opening + * connections to each other), one of us may just have + * to WAIT. This shouldn't happen if we are the + * client. + */ + pr_err("process_connect peer connecting WAIT\n"); + + default: + pr_err("connect protocol error, will retry\n"); + con->error_msg = "protocol error, garbage tag during connect"; + return -1; + } + return 0; +} + + +/* + * read (part of) an ack + */ +static int read_partial_ack(struct ceph_connection *con) +{ + int to = 0; + + return read_partial(con, &to, sizeof(con->in_temp_ack), + &con->in_temp_ack); +} + + +/* + * We can finally discard anything that's been acked. + */ +static void process_ack(struct ceph_connection *con) +{ + struct ceph_msg *m; + u64 ack = le64_to_cpu(con->in_temp_ack); + u64 seq; + + while (!list_empty(&con->out_sent)) { + m = list_first_entry(&con->out_sent, struct ceph_msg, + list_head); + seq = le64_to_cpu(m->hdr.seq); + if (seq > ack) + break; + dout("got ack for seq %llu type %d at %p\n", seq, + le16_to_cpu(m->hdr.type), m); + ceph_msg_remove(m); + } + prepare_read_tag(con); +} + + + + +static int read_partial_message_section(struct ceph_connection *con, + struct kvec *section, + unsigned int sec_len, u32 *crc) +{ + int ret, left; + + BUG_ON(!section); + + while (section->iov_len < sec_len) { + BUG_ON(section->iov_base == NULL); + left = sec_len - section->iov_len; + ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base + + section->iov_len, left); + if (ret <= 0) + return ret; + section->iov_len += ret; + if (section->iov_len == sec_len) + *crc = crc32c(0, section->iov_base, + section->iov_len); + } + + return 1; +} + +static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip); + + +static int read_partial_message_pages(struct ceph_connection *con, + struct page **pages, + unsigned data_len, int datacrc) +{ + void *p; + int ret; + int left; + + left = min((int)(data_len - con->in_msg_pos.data_pos), + (int)(PAGE_SIZE - con->in_msg_pos.page_pos)); + /* (page) data */ + BUG_ON(pages == NULL); + p = kmap(pages[con->in_msg_pos.page]); + ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, + left); + if (ret > 0 && datacrc) + con->in_data_crc = + crc32c(con->in_data_crc, + p + con->in_msg_pos.page_pos, ret); + kunmap(pages[con->in_msg_pos.page]); + if (ret <= 0) + return ret; + con->in_msg_pos.data_pos += ret; + con->in_msg_pos.page_pos += ret; + if (con->in_msg_pos.page_pos == PAGE_SIZE) { + con->in_msg_pos.page_pos = 0; + con->in_msg_pos.page++; + } + + return ret; +} + +#ifdef CONFIG_BLOCK +static int read_partial_message_bio(struct ceph_connection *con, + struct bio **bio_iter, int *bio_seg, + unsigned data_len, int datacrc) +{ + struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg); + void *p; + int ret, left; + + if (IS_ERR(bv)) + return PTR_ERR(bv); + + left = min((int)(data_len - con->in_msg_pos.data_pos), + (int)(bv->bv_len - con->in_msg_pos.page_pos)); + + p = kmap(bv->bv_page) + bv->bv_offset; + + ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, + left); + if (ret > 0 && datacrc) + con->in_data_crc = + crc32c(con->in_data_crc, + p + con->in_msg_pos.page_pos, ret); + kunmap(bv->bv_page); + if (ret <= 0) + return ret; + con->in_msg_pos.data_pos += ret; + con->in_msg_pos.page_pos += ret; + if (con->in_msg_pos.page_pos == bv->bv_len) { + con->in_msg_pos.page_pos = 0; + iter_bio_next(bio_iter, bio_seg); + } + + return ret; +} +#endif + +/* + * read (part of) a message. + */ +static int read_partial_message(struct ceph_connection *con) +{ + struct ceph_msg *m = con->in_msg; + int ret; + int to, left; + unsigned front_len, middle_len, data_len, data_off; + int datacrc = con->msgr->nocrc; + int skip; + u64 seq; + + dout("read_partial_message con %p msg %p\n", con, m); + + /* header */ + while (con->in_base_pos < sizeof(con->in_hdr)) { + left = sizeof(con->in_hdr) - con->in_base_pos; + ret = ceph_tcp_recvmsg(con->sock, + (char *)&con->in_hdr + con->in_base_pos, + left); + if (ret <= 0) + return ret; + con->in_base_pos += ret; + if (con->in_base_pos == sizeof(con->in_hdr)) { + u32 crc = crc32c(0, (void *)&con->in_hdr, + sizeof(con->in_hdr) - sizeof(con->in_hdr.crc)); + if (crc != le32_to_cpu(con->in_hdr.crc)) { + pr_err("read_partial_message bad hdr " + " crc %u != expected %u\n", + crc, con->in_hdr.crc); + return -EBADMSG; + } + } + } + front_len = le32_to_cpu(con->in_hdr.front_len); + if (front_len > CEPH_MSG_MAX_FRONT_LEN) + return -EIO; + middle_len = le32_to_cpu(con->in_hdr.middle_len); + if (middle_len > CEPH_MSG_MAX_DATA_LEN) + return -EIO; + data_len = le32_to_cpu(con->in_hdr.data_len); + if (data_len > CEPH_MSG_MAX_DATA_LEN) + return -EIO; + data_off = le16_to_cpu(con->in_hdr.data_off); + + /* verify seq# */ + seq = le64_to_cpu(con->in_hdr.seq); + if ((s64)seq - (s64)con->in_seq < 1) { + pr_info("skipping %s%lld %s seq %lld, expected %lld\n", + ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), + seq, con->in_seq + 1); + con->in_base_pos = -front_len - middle_len - data_len - + sizeof(m->footer); + con->in_tag = CEPH_MSGR_TAG_READY; + con->in_seq++; + return 0; + } else if ((s64)seq - (s64)con->in_seq > 1) { + pr_err("read_partial_message bad seq %lld expected %lld\n", + seq, con->in_seq + 1); + con->error_msg = "bad message sequence # for incoming message"; + return -EBADMSG; + } + + /* allocate message? */ + if (!con->in_msg) { + dout("got hdr type %d front %d data %d\n", con->in_hdr.type, + con->in_hdr.front_len, con->in_hdr.data_len); + skip = 0; + con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip); + if (skip) { + /* skip this message */ + dout("alloc_msg said skip message\n"); + BUG_ON(con->in_msg); + con->in_base_pos = -front_len - middle_len - data_len - + sizeof(m->footer); + con->in_tag = CEPH_MSGR_TAG_READY; + con->in_seq++; + return 0; + } + if (!con->in_msg) { + con->error_msg = + "error allocating memory for incoming message"; + return -ENOMEM; + } + m = con->in_msg; + m->front.iov_len = 0; /* haven't read it yet */ + if (m->middle) + m->middle->vec.iov_len = 0; + + con->in_msg_pos.page = 0; + if (m->pages) + con->in_msg_pos.page_pos = data_off & ~PAGE_MASK; + else + con->in_msg_pos.page_pos = 0; + con->in_msg_pos.data_pos = 0; + } + + /* front */ + ret = read_partial_message_section(con, &m->front, front_len, + &con->in_front_crc); + if (ret <= 0) + return ret; + + /* middle */ + if (m->middle) { + ret = read_partial_message_section(con, &m->middle->vec, + middle_len, + &con->in_middle_crc); + if (ret <= 0) + return ret; + } +#ifdef CONFIG_BLOCK + if (m->bio && !m->bio_iter) + init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); +#endif + + /* (page) data */ + while (con->in_msg_pos.data_pos < data_len) { + if (m->pages) { + ret = read_partial_message_pages(con, m->pages, + data_len, datacrc); + if (ret <= 0) + return ret; +#ifdef CONFIG_BLOCK + } else if (m->bio) { + + ret = read_partial_message_bio(con, + &m->bio_iter, &m->bio_seg, + data_len, datacrc); + if (ret <= 0) + return ret; +#endif + } else { + BUG_ON(1); + } + } + + /* footer */ + to = sizeof(m->hdr) + sizeof(m->footer); + while (con->in_base_pos < to) { + left = to - con->in_base_pos; + ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer + + (con->in_base_pos - sizeof(m->hdr)), + left); + if (ret <= 0) + return ret; + con->in_base_pos += ret; + } + dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n", + m, front_len, m->footer.front_crc, middle_len, + m->footer.middle_crc, data_len, m->footer.data_crc); + + /* crc ok? */ + if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) { + pr_err("read_partial_message %p front crc %u != exp. %u\n", + m, con->in_front_crc, m->footer.front_crc); + return -EBADMSG; + } + if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) { + pr_err("read_partial_message %p middle crc %u != exp %u\n", + m, con->in_middle_crc, m->footer.middle_crc); + return -EBADMSG; + } + if (datacrc && + (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 && + con->in_data_crc != le32_to_cpu(m->footer.data_crc)) { + pr_err("read_partial_message %p data crc %u != exp. %u\n", m, + con->in_data_crc, le32_to_cpu(m->footer.data_crc)); + return -EBADMSG; + } + + return 1; /* done! */ +} + +/* + * Process message. This happens in the worker thread. The callback should + * be careful not to do anything that waits on other incoming messages or it + * may deadlock. + */ +static void process_message(struct ceph_connection *con) +{ + struct ceph_msg *msg; + + msg = con->in_msg; + con->in_msg = NULL; + + /* if first message, set peer_name */ + if (con->peer_name.type == 0) + con->peer_name = msg->hdr.src; + + con->in_seq++; + mutex_unlock(&con->mutex); + + dout("===== %p %llu from %s%lld %d=%s len %d+%d (%u %u %u) =====\n", + msg, le64_to_cpu(msg->hdr.seq), + ENTITY_NAME(msg->hdr.src), + le16_to_cpu(msg->hdr.type), + ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), + le32_to_cpu(msg->hdr.front_len), + le32_to_cpu(msg->hdr.data_len), + con->in_front_crc, con->in_middle_crc, con->in_data_crc); + con->ops->dispatch(con, msg); + + mutex_lock(&con->mutex); + prepare_read_tag(con); +} + + +/* + * Write something to the socket. Called in a worker thread when the + * socket appears to be writeable and we have something ready to send. + */ +static int try_write(struct ceph_connection *con) +{ + struct ceph_messenger *msgr = con->msgr; + int ret = 1; + + dout("try_write start %p state %lu nref %d\n", con, con->state, + atomic_read(&con->nref)); + +more: + dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes); + + /* open the socket first? */ + if (con->sock == NULL) { + /* + * if we were STANDBY and are reconnecting _this_ + * connection, bump connect_seq now. Always bump + * global_seq. + */ + if (test_and_clear_bit(STANDBY, &con->state)) + con->connect_seq++; + + prepare_write_banner(msgr, con); + prepare_write_connect(msgr, con, 1); + prepare_read_banner(con); + set_bit(CONNECTING, &con->state); + clear_bit(NEGOTIATING, &con->state); + + BUG_ON(con->in_msg); + con->in_tag = CEPH_MSGR_TAG_READY; + dout("try_write initiating connect on %p new state %lu\n", + con, con->state); + con->sock = ceph_tcp_connect(con); + if (IS_ERR(con->sock)) { + con->sock = NULL; + con->error_msg = "connect error"; + ret = -1; + goto out; + } + } + +more_kvec: + /* kvec data queued? */ + if (con->out_skip) { + ret = write_partial_skip(con); + if (ret <= 0) + goto done; + if (ret < 0) { + dout("try_write write_partial_skip err %d\n", ret); + goto done; + } + } + if (con->out_kvec_left) { + ret = write_partial_kvec(con); + if (ret <= 0) + goto done; + } + + /* msg pages? */ + if (con->out_msg) { + if (con->out_msg_done) { + ceph_msg_put(con->out_msg); + con->out_msg = NULL; /* we're done with this one */ + goto do_next; + } + + ret = write_partial_msg_pages(con); + if (ret == 1) + goto more_kvec; /* we need to send the footer, too! */ + if (ret == 0) + goto done; + if (ret < 0) { + dout("try_write write_partial_msg_pages err %d\n", + ret); + goto done; + } + } + +do_next: + if (!test_bit(CONNECTING, &con->state)) { + /* is anything else pending? */ + if (!list_empty(&con->out_queue)) { + prepare_write_message(con); + goto more; + } + if (con->in_seq > con->in_seq_acked) { + prepare_write_ack(con); + goto more; + } + if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) { + prepare_write_keepalive(con); + goto more; + } + } + + /* Nothing to do! */ + clear_bit(WRITE_PENDING, &con->state); + dout("try_write nothing else to write.\n"); +done: + ret = 0; +out: + dout("try_write done on %p\n", con); + return ret; +} + + + +/* + * Read what we can from the socket. + */ +static int try_read(struct ceph_connection *con) +{ + int ret = -1; + + if (!con->sock) + return 0; + + if (test_bit(STANDBY, &con->state)) + return 0; + + dout("try_read start on %p\n", con); + +more: + dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag, + con->in_base_pos); + if (test_bit(CONNECTING, &con->state)) { + if (!test_bit(NEGOTIATING, &con->state)) { + dout("try_read connecting\n"); + ret = read_partial_banner(con); + if (ret <= 0) + goto done; + if (process_banner(con) < 0) { + ret = -1; + goto out; + } + } + ret = read_partial_connect(con); + if (ret <= 0) + goto done; + if (process_connect(con) < 0) { + ret = -1; + goto out; + } + goto more; + } + + if (con->in_base_pos < 0) { + /* + * skipping + discarding content. + * + * FIXME: there must be a better way to do this! + */ + static char buf[1024]; + int skip = min(1024, -con->in_base_pos); + dout("skipping %d / %d bytes\n", skip, -con->in_base_pos); + ret = ceph_tcp_recvmsg(con->sock, buf, skip); + if (ret <= 0) + goto done; + con->in_base_pos += ret; + if (con->in_base_pos) + goto more; + } + if (con->in_tag == CEPH_MSGR_TAG_READY) { + /* + * what's next? + */ + ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1); + if (ret <= 0) + goto done; + dout("try_read got tag %d\n", (int)con->in_tag); + switch (con->in_tag) { + case CEPH_MSGR_TAG_MSG: + prepare_read_message(con); + break; + case CEPH_MSGR_TAG_ACK: + prepare_read_ack(con); + break; + case CEPH_MSGR_TAG_CLOSE: + set_bit(CLOSED, &con->state); /* fixme */ + goto done; + default: + goto bad_tag; + } + } + if (con->in_tag == CEPH_MSGR_TAG_MSG) { + ret = read_partial_message(con); + if (ret <= 0) { + switch (ret) { + case -EBADMSG: + con->error_msg = "bad crc"; + ret = -EIO; + goto out; + case -EIO: + con->error_msg = "io error"; + goto out; + default: + goto done; + } + } + if (con->in_tag == CEPH_MSGR_TAG_READY) + goto more; + process_message(con); + goto more; + } + if (con->in_tag == CEPH_MSGR_TAG_ACK) { + ret = read_partial_ack(con); + if (ret <= 0) + goto done; + process_ack(con); + goto more; + } + +done: + ret = 0; +out: + dout("try_read done on %p\n", con); + return ret; + +bad_tag: + pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag); + con->error_msg = "protocol error, garbage tag"; + ret = -1; + goto out; +} + + +/* + * Atomically queue work on a connection. Bump @con reference to + * avoid races with connection teardown. + * + * There is some trickery going on with QUEUED and BUSY because we + * only want a _single_ thread operating on each connection at any + * point in time, but we want to use all available CPUs. + * + * The worker thread only proceeds if it can atomically set BUSY. It + * clears QUEUED and does it's thing. When it thinks it's done, it + * clears BUSY, then rechecks QUEUED.. if it's set again, it loops + * (tries again to set BUSY). + * + * To queue work, we first set QUEUED, _then_ if BUSY isn't set, we + * try to queue work. If that fails (work is already queued, or BUSY) + * we give up (work also already being done or is queued) but leave QUEUED + * set so that the worker thread will loop if necessary. + */ +static void queue_con(struct ceph_connection *con) +{ + if (test_bit(DEAD, &con->state)) { + dout("queue_con %p ignoring: DEAD\n", + con); + return; + } + + if (!con->ops->get(con)) { + dout("queue_con %p ref count 0\n", con); + return; + } + + set_bit(QUEUED, &con->state); + if (test_bit(BUSY, &con->state)) { + dout("queue_con %p - already BUSY\n", con); + con->ops->put(con); + } else if (!queue_work(ceph_msgr_wq, &con->work.work)) { + dout("queue_con %p - already queued\n", con); + con->ops->put(con); + } else { + dout("queue_con %p\n", con); + } +} + +/* + * Do some work on a connection. Drop a connection ref when we're done. + */ +static void con_work(struct work_struct *work) +{ + struct ceph_connection *con = container_of(work, struct ceph_connection, + work.work); + int backoff = 0; + +more: + if (test_and_set_bit(BUSY, &con->state) != 0) { + dout("con_work %p BUSY already set\n", con); + goto out; + } + dout("con_work %p start, clearing QUEUED\n", con); + clear_bit(QUEUED, &con->state); + + mutex_lock(&con->mutex); + + if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ + dout("con_work CLOSED\n"); + con_close_socket(con); + goto done; + } + if (test_and_clear_bit(OPENING, &con->state)) { + /* reopen w/ new peer */ + dout("con_work OPENING\n"); + con_close_socket(con); + } + + if (test_and_clear_bit(SOCK_CLOSED, &con->state) || + try_read(con) < 0 || + try_write(con) < 0) { + mutex_unlock(&con->mutex); + backoff = 1; + ceph_fault(con); /* error/fault path */ + goto done_unlocked; + } + +done: + mutex_unlock(&con->mutex); + +done_unlocked: + clear_bit(BUSY, &con->state); + dout("con->state=%lu\n", con->state); + if (test_bit(QUEUED, &con->state)) { + if (!backoff || test_bit(OPENING, &con->state)) { + dout("con_work %p QUEUED reset, looping\n", con); + goto more; + } + dout("con_work %p QUEUED reset, but just faulted\n", con); + clear_bit(QUEUED, &con->state); + } + dout("con_work %p done\n", con); + +out: + con->ops->put(con); +} + + +/* + * Generic error/fault handler. A retry mechanism is used with + * exponential backoff + */ +static void ceph_fault(struct ceph_connection *con) +{ + pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); + dout("fault %p state %lu to peer %s\n", + con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); + + if (test_bit(LOSSYTX, &con->state)) { + dout("fault on LOSSYTX channel\n"); + goto out; + } + + mutex_lock(&con->mutex); + if (test_bit(CLOSED, &con->state)) + goto out_unlock; + + con_close_socket(con); + + if (con->in_msg) { + ceph_msg_put(con->in_msg); + con->in_msg = NULL; + } + + /* Requeue anything that hasn't been acked */ + list_splice_init(&con->out_sent, &con->out_queue); + + /* If there are no messages in the queue, place the connection + * in a STANDBY state (i.e., don't try to reconnect just yet). */ + if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { + dout("fault setting STANDBY\n"); + set_bit(STANDBY, &con->state); + } else { + /* retry after a delay. */ + if (con->delay == 0) + con->delay = BASE_DELAY_INTERVAL; + else if (con->delay < MAX_DELAY_INTERVAL) + con->delay *= 2; + dout("fault queueing %p delay %lu\n", con, con->delay); + con->ops->get(con); + if (queue_delayed_work(ceph_msgr_wq, &con->work, + round_jiffies_relative(con->delay)) == 0) + con->ops->put(con); + } + +out_unlock: + mutex_unlock(&con->mutex); +out: + /* + * in case we faulted due to authentication, invalidate our + * current tickets so that we can get new ones. + */ + if (con->auth_retry && con->ops->invalidate_authorizer) { + dout("calling invalidate_authorizer()\n"); + con->ops->invalidate_authorizer(con); + } + + if (con->ops->fault) + con->ops->fault(con); +} + + + +/* + * create a new messenger instance + */ +struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, + u32 supported_features, + u32 required_features) +{ + struct ceph_messenger *msgr; + + msgr = kzalloc(sizeof(*msgr), GFP_KERNEL); + if (msgr == NULL) + return ERR_PTR(-ENOMEM); + + msgr->supported_features = supported_features; + msgr->required_features = required_features; + + spin_lock_init(&msgr->global_seq_lock); + + /* the zero page is needed if a request is "canceled" while the message + * is being written over the socket */ + msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO); + if (!msgr->zero_page) { + kfree(msgr); + return ERR_PTR(-ENOMEM); + } + kmap(msgr->zero_page); + + if (myaddr) + msgr->inst.addr = *myaddr; + + /* select a random nonce */ + msgr->inst.addr.type = 0; + get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); + encode_my_addr(msgr); + + dout("messenger_create %p\n", msgr); + return msgr; +} +EXPORT_SYMBOL(ceph_messenger_create); + +void ceph_messenger_destroy(struct ceph_messenger *msgr) +{ + dout("destroy %p\n", msgr); + kunmap(msgr->zero_page); + __free_page(msgr->zero_page); + kfree(msgr); + dout("destroyed messenger %p\n", msgr); +} +EXPORT_SYMBOL(ceph_messenger_destroy); + +/* + * Queue up an outgoing message on the given connection. + */ +void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) +{ + if (test_bit(CLOSED, &con->state)) { + dout("con_send %p closed, dropping %p\n", con, msg); + ceph_msg_put(msg); + return; + } + + /* set src+dst */ + msg->hdr.src = con->msgr->inst.name; + + BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len)); + + msg->needs_out_seq = true; + + /* queue */ + mutex_lock(&con->mutex); + BUG_ON(!list_empty(&msg->list_head)); + list_add_tail(&msg->list_head, &con->out_queue); + dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg, + ENTITY_NAME(con->peer_name), le16_to_cpu(msg->hdr.type), + ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), + le32_to_cpu(msg->hdr.front_len), + le32_to_cpu(msg->hdr.middle_len), + le32_to_cpu(msg->hdr.data_len)); + mutex_unlock(&con->mutex); + + /* if there wasn't anything waiting to send before, queue + * new work */ + if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) + queue_con(con); +} +EXPORT_SYMBOL(ceph_con_send); + +/* + * Revoke a message that was previously queued for send + */ +void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) +{ + mutex_lock(&con->mutex); + if (!list_empty(&msg->list_head)) { + dout("con_revoke %p msg %p - was on queue\n", con, msg); + list_del_init(&msg->list_head); + ceph_msg_put(msg); + msg->hdr.seq = 0; + } + if (con->out_msg == msg) { + dout("con_revoke %p msg %p - was sending\n", con, msg); + con->out_msg = NULL; + if (con->out_kvec_is_msg) { + con->out_skip = con->out_kvec_bytes; + con->out_kvec_is_msg = false; + } + ceph_msg_put(msg); + msg->hdr.seq = 0; + } + mutex_unlock(&con->mutex); +} + +/* + * Revoke a message that we may be reading data into + */ +void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) +{ + mutex_lock(&con->mutex); + if (con->in_msg && con->in_msg == msg) { + unsigned front_len = le32_to_cpu(con->in_hdr.front_len); + unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len); + unsigned data_len = le32_to_cpu(con->in_hdr.data_len); + + /* skip rest of message */ + dout("con_revoke_pages %p msg %p revoked\n", con, msg); + con->in_base_pos = con->in_base_pos - + sizeof(struct ceph_msg_header) - + front_len - + middle_len - + data_len - + sizeof(struct ceph_msg_footer); + ceph_msg_put(con->in_msg); + con->in_msg = NULL; + con->in_tag = CEPH_MSGR_TAG_READY; + con->in_seq++; + } else { + dout("con_revoke_pages %p msg %p pages %p no-op\n", + con, con->in_msg, msg); + } + mutex_unlock(&con->mutex); +} + +/* + * Queue a keepalive byte to ensure the tcp connection is alive. + */ +void ceph_con_keepalive(struct ceph_connection *con) +{ + if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && + test_and_set_bit(WRITE_PENDING, &con->state) == 0) + queue_con(con); +} +EXPORT_SYMBOL(ceph_con_keepalive); + + +/* + * construct a new message with given type, size + * the new msg has a ref count of 1. + */ +struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) +{ + struct ceph_msg *m; + + m = kmalloc(sizeof(*m), flags); + if (m == NULL) + goto out; + kref_init(&m->kref); + INIT_LIST_HEAD(&m->list_head); + + m->hdr.tid = 0; + m->hdr.type = cpu_to_le16(type); + m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT); + m->hdr.version = 0; + m->hdr.front_len = cpu_to_le32(front_len); + m->hdr.middle_len = 0; + m->hdr.data_len = 0; + m->hdr.data_off = 0; + m->hdr.reserved = 0; + m->footer.front_crc = 0; + m->footer.middle_crc = 0; + m->footer.data_crc = 0; + m->footer.flags = 0; + m->front_max = front_len; + m->front_is_vmalloc = false; + m->more_to_follow = false; + m->pool = NULL; + + /* front */ + if (front_len) { + if (front_len > PAGE_CACHE_SIZE) { + m->front.iov_base = __vmalloc(front_len, flags, + PAGE_KERNEL); + m->front_is_vmalloc = true; + } else { + m->front.iov_base = kmalloc(front_len, flags); + } + if (m->front.iov_base == NULL) { + pr_err("msg_new can't allocate %d bytes\n", + front_len); + goto out2; + } + } else { + m->front.iov_base = NULL; + } + m->front.iov_len = front_len; + + /* middle */ + m->middle = NULL; + + /* data */ + m->nr_pages = 0; + m->pages = NULL; + m->pagelist = NULL; + m->bio = NULL; + m->bio_iter = NULL; + m->bio_seg = 0; + m->trail = NULL; + + dout("ceph_msg_new %p front %d\n", m, front_len); + return m; + +out2: + ceph_msg_put(m); +out: + pr_err("msg_new can't create type %d front %d\n", type, front_len); + return NULL; +} +EXPORT_SYMBOL(ceph_msg_new); + +/* + * Allocate "middle" portion of a message, if it is needed and wasn't + * allocated by alloc_msg. This allows us to read a small fixed-size + * per-type header in the front and then gracefully fail (i.e., + * propagate the error to the caller based on info in the front) when + * the middle is too large. + */ +static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg) +{ + int type = le16_to_cpu(msg->hdr.type); + int middle_len = le32_to_cpu(msg->hdr.middle_len); + + dout("alloc_middle %p type %d %s middle_len %d\n", msg, type, + ceph_msg_type_name(type), middle_len); + BUG_ON(!middle_len); + BUG_ON(msg->middle); + + msg->middle = ceph_buffer_new(middle_len, GFP_NOFS); + if (!msg->middle) + return -ENOMEM; + return 0; +} + +/* + * Generic message allocator, for incoming messages. + */ +static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) +{ + int type = le16_to_cpu(hdr->type); + int front_len = le32_to_cpu(hdr->front_len); + int middle_len = le32_to_cpu(hdr->middle_len); + struct ceph_msg *msg = NULL; + int ret; + + if (con->ops->alloc_msg) { + mutex_unlock(&con->mutex); + msg = con->ops->alloc_msg(con, hdr, skip); + mutex_lock(&con->mutex); + if (!msg || *skip) + return NULL; + } + if (!msg) { + *skip = 0; + msg = ceph_msg_new(type, front_len, GFP_NOFS); + if (!msg) { + pr_err("unable to allocate msg type %d len %d\n", + type, front_len); + return NULL; + } + } + memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); + + if (middle_len && !msg->middle) { + ret = ceph_alloc_middle(con, msg); + if (ret < 0) { + ceph_msg_put(msg); + return NULL; + } + } + + return msg; +} + + +/* + * Free a generically kmalloc'd message. + */ +void ceph_msg_kfree(struct ceph_msg *m) +{ + dout("msg_kfree %p\n", m); + if (m->front_is_vmalloc) + vfree(m->front.iov_base); + else + kfree(m->front.iov_base); + kfree(m); +} + +/* + * Drop a msg ref. Destroy as needed. + */ +void ceph_msg_last_put(struct kref *kref) +{ + struct ceph_msg *m = container_of(kref, struct ceph_msg, kref); + + dout("ceph_msg_put last one on %p\n", m); + WARN_ON(!list_empty(&m->list_head)); + + /* drop middle, data, if any */ + if (m->middle) { + ceph_buffer_put(m->middle); + m->middle = NULL; + } + m->nr_pages = 0; + m->pages = NULL; + + if (m->pagelist) { + ceph_pagelist_release(m->pagelist); + kfree(m->pagelist); + m->pagelist = NULL; + } + + m->trail = NULL; + + if (m->pool) + ceph_msgpool_put(m->pool, m); + else + ceph_msg_kfree(m); +} +EXPORT_SYMBOL(ceph_msg_last_put); + +void ceph_msg_dump(struct ceph_msg *msg) +{ + pr_debug("msg_dump %p (front_max %d nr_pages %d)\n", msg, + msg->front_max, msg->nr_pages); + print_hex_dump(KERN_DEBUG, "header: ", + DUMP_PREFIX_OFFSET, 16, 1, + &msg->hdr, sizeof(msg->hdr), true); + print_hex_dump(KERN_DEBUG, " front: ", + DUMP_PREFIX_OFFSET, 16, 1, + msg->front.iov_base, msg->front.iov_len, true); + if (msg->middle) + print_hex_dump(KERN_DEBUG, "middle: ", + DUMP_PREFIX_OFFSET, 16, 1, + msg->middle->vec.iov_base, + msg->middle->vec.iov_len, true); + print_hex_dump(KERN_DEBUG, "footer: ", + DUMP_PREFIX_OFFSET, 16, 1, + &msg->footer, sizeof(msg->footer), true); +} +EXPORT_SYMBOL(ceph_msg_dump); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c new file mode 100644 index 000000000000..8a079399174a --- /dev/null +++ b/net/ceph/mon_client.c @@ -0,0 +1,1027 @@ +#include + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +/* + * Interact with Ceph monitor cluster. Handle requests for new map + * versions, and periodically resend as needed. Also implement + * statfs() and umount(). + * + * A small cluster of Ceph "monitors" are responsible for managing critical + * cluster configuration and state information. An odd number (e.g., 3, 5) + * of cmon daemons use a modified version of the Paxos part-time parliament + * algorithm to manage the MDS map (mds cluster membership), OSD map, and + * list of clients who have mounted the file system. + * + * We maintain an open, active session with a monitor at all times in order to + * receive timely MDSMap updates. We periodically send a keepalive byte on the + * TCP socket to ensure we detect a failure. If the connection does break, we + * randomly hunt for a new monitor. Once the connection is reestablished, we + * resend any outstanding requests. + */ + +static const struct ceph_connection_operations mon_con_ops; + +static int __validate_auth(struct ceph_mon_client *monc); + +/* + * Decode a monmap blob (e.g., during mount). + */ +struct ceph_monmap *ceph_monmap_decode(void *p, void *end) +{ + struct ceph_monmap *m = NULL; + int i, err = -EINVAL; + struct ceph_fsid fsid; + u32 epoch, num_mon; + u16 version; + u32 len; + + ceph_decode_32_safe(&p, end, len, bad); + ceph_decode_need(&p, end, len, bad); + + dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p)); + + ceph_decode_16_safe(&p, end, version, bad); + + ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad); + ceph_decode_copy(&p, &fsid, sizeof(fsid)); + epoch = ceph_decode_32(&p); + + num_mon = ceph_decode_32(&p); + ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad); + + if (num_mon >= CEPH_MAX_MON) + goto bad; + m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS); + if (m == NULL) + return ERR_PTR(-ENOMEM); + m->fsid = fsid; + m->epoch = epoch; + m->num_mon = num_mon; + ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0])); + for (i = 0; i < num_mon; i++) + ceph_decode_addr(&m->mon_inst[i].addr); + + dout("monmap_decode epoch %d, num_mon %d\n", m->epoch, + m->num_mon); + for (i = 0; i < m->num_mon; i++) + dout("monmap_decode mon%d is %s\n", i, + ceph_pr_addr(&m->mon_inst[i].addr.in_addr)); + return m; + +bad: + dout("monmap_decode failed with %d\n", err); + kfree(m); + return ERR_PTR(err); +} + +/* + * return true if *addr is included in the monmap. + */ +int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr) +{ + int i; + + for (i = 0; i < m->num_mon; i++) + if (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0) + return 1; + return 0; +} + +/* + * Send an auth request. + */ +static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) +{ + monc->pending_auth = 1; + monc->m_auth->front.iov_len = len; + monc->m_auth->hdr.front_len = cpu_to_le32(len); + ceph_con_revoke(monc->con, monc->m_auth); + ceph_msg_get(monc->m_auth); /* keep our ref */ + ceph_con_send(monc->con, monc->m_auth); +} + +/* + * Close monitor session, if any. + */ +static void __close_session(struct ceph_mon_client *monc) +{ + if (monc->con) { + dout("__close_session closing mon%d\n", monc->cur_mon); + ceph_con_revoke(monc->con, monc->m_auth); + ceph_con_close(monc->con); + monc->cur_mon = -1; + monc->pending_auth = 0; + ceph_auth_reset(monc->auth); + } +} + +/* + * Open a session with a (new) monitor. + */ +static int __open_session(struct ceph_mon_client *monc) +{ + char r; + int ret; + + if (monc->cur_mon < 0) { + get_random_bytes(&r, 1); + monc->cur_mon = r % monc->monmap->num_mon; + dout("open_session num=%d r=%d -> mon%d\n", + monc->monmap->num_mon, r, monc->cur_mon); + monc->sub_sent = 0; + monc->sub_renew_after = jiffies; /* i.e., expired */ + monc->want_next_osdmap = !!monc->want_next_osdmap; + + dout("open_session mon%d opening\n", monc->cur_mon); + monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON; + monc->con->peer_name.num = cpu_to_le64(monc->cur_mon); + ceph_con_open(monc->con, + &monc->monmap->mon_inst[monc->cur_mon].addr); + + /* initiatiate authentication handshake */ + ret = ceph_auth_build_hello(monc->auth, + monc->m_auth->front.iov_base, + monc->m_auth->front_max); + __send_prepared_auth_request(monc, ret); + } else { + dout("open_session mon%d already open\n", monc->cur_mon); + } + return 0; +} + +static bool __sub_expired(struct ceph_mon_client *monc) +{ + return time_after_eq(jiffies, monc->sub_renew_after); +} + +/* + * Reschedule delayed work timer. + */ +static void __schedule_delayed(struct ceph_mon_client *monc) +{ + unsigned delay; + + if (monc->cur_mon < 0 || __sub_expired(monc)) + delay = 10 * HZ; + else + delay = 20 * HZ; + dout("__schedule_delayed after %u\n", delay); + schedule_delayed_work(&monc->delayed_work, delay); +} + +/* + * Send subscribe request for mdsmap and/or osdmap. + */ +static void __send_subscribe(struct ceph_mon_client *monc) +{ + dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n", + (unsigned)monc->sub_sent, __sub_expired(monc), + monc->want_next_osdmap); + if ((__sub_expired(monc) && !monc->sub_sent) || + monc->want_next_osdmap == 1) { + struct ceph_msg *msg = monc->m_subscribe; + struct ceph_mon_subscribe_item *i; + void *p, *end; + int num; + + p = msg->front.iov_base; + end = p + msg->front_max; + + num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap; + ceph_encode_32(&p, num); + + if (monc->want_next_osdmap) { + dout("__send_subscribe to 'osdmap' %u\n", + (unsigned)monc->have_osdmap); + ceph_encode_string(&p, end, "osdmap", 6); + i = p; + i->have = cpu_to_le64(monc->have_osdmap); + i->onetime = 1; + p += sizeof(*i); + monc->want_next_osdmap = 2; /* requested */ + } + if (monc->want_mdsmap) { + dout("__send_subscribe to 'mdsmap' %u+\n", + (unsigned)monc->have_mdsmap); + ceph_encode_string(&p, end, "mdsmap", 6); + i = p; + i->have = cpu_to_le64(monc->have_mdsmap); + i->onetime = 0; + p += sizeof(*i); + } + ceph_encode_string(&p, end, "monmap", 6); + i = p; + i->have = 0; + i->onetime = 0; + p += sizeof(*i); + + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + ceph_con_revoke(monc->con, msg); + ceph_con_send(monc->con, ceph_msg_get(msg)); + + monc->sub_sent = jiffies | 1; /* never 0 */ + } +} + +static void handle_subscribe_ack(struct ceph_mon_client *monc, + struct ceph_msg *msg) +{ + unsigned seconds; + struct ceph_mon_subscribe_ack *h = msg->front.iov_base; + + if (msg->front.iov_len < sizeof(*h)) + goto bad; + seconds = le32_to_cpu(h->duration); + + mutex_lock(&monc->mutex); + if (monc->hunting) { + pr_info("mon%d %s session established\n", + monc->cur_mon, + ceph_pr_addr(&monc->con->peer_addr.in_addr)); + monc->hunting = false; + } + dout("handle_subscribe_ack after %d seconds\n", seconds); + monc->sub_renew_after = monc->sub_sent + (seconds >> 1)*HZ - 1; + monc->sub_sent = 0; + mutex_unlock(&monc->mutex); + return; +bad: + pr_err("got corrupt subscribe-ack msg\n"); + ceph_msg_dump(msg); +} + +/* + * Keep track of which maps we have + */ +int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got) +{ + mutex_lock(&monc->mutex); + monc->have_mdsmap = got; + mutex_unlock(&monc->mutex); + return 0; +} +EXPORT_SYMBOL(ceph_monc_got_mdsmap); + +int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got) +{ + mutex_lock(&monc->mutex); + monc->have_osdmap = got; + monc->want_next_osdmap = 0; + mutex_unlock(&monc->mutex); + return 0; +} + +/* + * Register interest in the next osdmap + */ +void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc) +{ + dout("request_next_osdmap have %u\n", monc->have_osdmap); + mutex_lock(&monc->mutex); + if (!monc->want_next_osdmap) + monc->want_next_osdmap = 1; + if (monc->want_next_osdmap < 2) + __send_subscribe(monc); + mutex_unlock(&monc->mutex); +} + +/* + * + */ +int ceph_monc_open_session(struct ceph_mon_client *monc) +{ + if (!monc->con) { + monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); + if (!monc->con) + return -ENOMEM; + ceph_con_init(monc->client->msgr, monc->con); + monc->con->private = monc; + monc->con->ops = &mon_con_ops; + } + + mutex_lock(&monc->mutex); + __open_session(monc); + __schedule_delayed(monc); + mutex_unlock(&monc->mutex); + return 0; +} +EXPORT_SYMBOL(ceph_monc_open_session); + +/* + * The monitor responds with mount ack indicate mount success. The + * included client ticket allows the client to talk to MDSs and OSDs. + */ +static void ceph_monc_handle_map(struct ceph_mon_client *monc, + struct ceph_msg *msg) +{ + struct ceph_client *client = monc->client; + struct ceph_monmap *monmap = NULL, *old = monc->monmap; + void *p, *end; + + mutex_lock(&monc->mutex); + + dout("handle_monmap\n"); + p = msg->front.iov_base; + end = p + msg->front.iov_len; + + monmap = ceph_monmap_decode(p, end); + if (IS_ERR(monmap)) { + pr_err("problem decoding monmap, %d\n", + (int)PTR_ERR(monmap)); + goto out; + } + + if (ceph_check_fsid(monc->client, &monmap->fsid) < 0) { + kfree(monmap); + goto out; + } + + client->monc.monmap = monmap; + kfree(old); + +out: + mutex_unlock(&monc->mutex); + wake_up_all(&client->auth_wq); +} + +/* + * generic requests (e.g., statfs, poolop) + */ +static struct ceph_mon_generic_request *__lookup_generic_req( + struct ceph_mon_client *monc, u64 tid) +{ + struct ceph_mon_generic_request *req; + struct rb_node *n = monc->generic_request_tree.rb_node; + + while (n) { + req = rb_entry(n, struct ceph_mon_generic_request, node); + if (tid < req->tid) + n = n->rb_left; + else if (tid > req->tid) + n = n->rb_right; + else + return req; + } + return NULL; +} + +static void __insert_generic_request(struct ceph_mon_client *monc, + struct ceph_mon_generic_request *new) +{ + struct rb_node **p = &monc->generic_request_tree.rb_node; + struct rb_node *parent = NULL; + struct ceph_mon_generic_request *req = NULL; + + while (*p) { + parent = *p; + req = rb_entry(parent, struct ceph_mon_generic_request, node); + if (new->tid < req->tid) + p = &(*p)->rb_left; + else if (new->tid > req->tid) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&new->node, parent, p); + rb_insert_color(&new->node, &monc->generic_request_tree); +} + +static void release_generic_request(struct kref *kref) +{ + struct ceph_mon_generic_request *req = + container_of(kref, struct ceph_mon_generic_request, kref); + + if (req->reply) + ceph_msg_put(req->reply); + if (req->request) + ceph_msg_put(req->request); + + kfree(req); +} + +static void put_generic_request(struct ceph_mon_generic_request *req) +{ + kref_put(&req->kref, release_generic_request); +} + +static void get_generic_request(struct ceph_mon_generic_request *req) +{ + kref_get(&req->kref); +} + +static struct ceph_msg *get_generic_reply(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) +{ + struct ceph_mon_client *monc = con->private; + struct ceph_mon_generic_request *req; + u64 tid = le64_to_cpu(hdr->tid); + struct ceph_msg *m; + + mutex_lock(&monc->mutex); + req = __lookup_generic_req(monc, tid); + if (!req) { + dout("get_generic_reply %lld dne\n", tid); + *skip = 1; + m = NULL; + } else { + dout("get_generic_reply %lld got %p\n", tid, req->reply); + m = ceph_msg_get(req->reply); + /* + * we don't need to track the connection reading into + * this reply because we only have one open connection + * at a time, ever. + */ + } + mutex_unlock(&monc->mutex); + return m; +} + +static int do_generic_request(struct ceph_mon_client *monc, + struct ceph_mon_generic_request *req) +{ + int err; + + /* register request */ + mutex_lock(&monc->mutex); + req->tid = ++monc->last_tid; + req->request->hdr.tid = cpu_to_le64(req->tid); + __insert_generic_request(monc, req); + monc->num_generic_requests++; + ceph_con_send(monc->con, ceph_msg_get(req->request)); + mutex_unlock(&monc->mutex); + + err = wait_for_completion_interruptible(&req->completion); + + mutex_lock(&monc->mutex); + rb_erase(&req->node, &monc->generic_request_tree); + monc->num_generic_requests--; + mutex_unlock(&monc->mutex); + + if (!err) + err = req->result; + return err; +} + +/* + * statfs + */ +static void handle_statfs_reply(struct ceph_mon_client *monc, + struct ceph_msg *msg) +{ + struct ceph_mon_generic_request *req; + struct ceph_mon_statfs_reply *reply = msg->front.iov_base; + u64 tid = le64_to_cpu(msg->hdr.tid); + + if (msg->front.iov_len != sizeof(*reply)) + goto bad; + dout("handle_statfs_reply %p tid %llu\n", msg, tid); + + mutex_lock(&monc->mutex); + req = __lookup_generic_req(monc, tid); + if (req) { + *(struct ceph_statfs *)req->buf = reply->st; + req->result = 0; + get_generic_request(req); + } + mutex_unlock(&monc->mutex); + if (req) { + complete_all(&req->completion); + put_generic_request(req); + } + return; + +bad: + pr_err("corrupt generic reply, tid %llu\n", tid); + ceph_msg_dump(msg); +} + +/* + * Do a synchronous statfs(). + */ +int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf) +{ + struct ceph_mon_generic_request *req; + struct ceph_mon_statfs *h; + int err; + + req = kzalloc(sizeof(*req), GFP_NOFS); + if (!req) + return -ENOMEM; + + kref_init(&req->kref); + req->buf = buf; + req->buf_len = sizeof(*buf); + init_completion(&req->completion); + + err = -ENOMEM; + req->request = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), GFP_NOFS); + if (!req->request) + goto out; + req->reply = ceph_msg_new(CEPH_MSG_STATFS_REPLY, 1024, GFP_NOFS); + if (!req->reply) + goto out; + + /* fill out request */ + h = req->request->front.iov_base; + h->monhdr.have_version = 0; + h->monhdr.session_mon = cpu_to_le16(-1); + h->monhdr.session_mon_tid = 0; + h->fsid = monc->monmap->fsid; + + err = do_generic_request(monc, req); + +out: + kref_put(&req->kref, release_generic_request); + return err; +} +EXPORT_SYMBOL(ceph_monc_do_statfs); + +/* + * pool ops + */ +static int get_poolop_reply_buf(const char *src, size_t src_len, + char *dst, size_t dst_len) +{ + u32 buf_len; + + if (src_len != sizeof(u32) + dst_len) + return -EINVAL; + + buf_len = le32_to_cpu(*(u32 *)src); + if (buf_len != dst_len) + return -EINVAL; + + memcpy(dst, src + sizeof(u32), dst_len); + return 0; +} + +static void handle_poolop_reply(struct ceph_mon_client *monc, + struct ceph_msg *msg) +{ + struct ceph_mon_generic_request *req; + struct ceph_mon_poolop_reply *reply = msg->front.iov_base; + u64 tid = le64_to_cpu(msg->hdr.tid); + + if (msg->front.iov_len < sizeof(*reply)) + goto bad; + dout("handle_poolop_reply %p tid %llu\n", msg, tid); + + mutex_lock(&monc->mutex); + req = __lookup_generic_req(monc, tid); + if (req) { + if (req->buf_len && + get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply), + msg->front.iov_len - sizeof(*reply), + req->buf, req->buf_len) < 0) { + mutex_unlock(&monc->mutex); + goto bad; + } + req->result = le32_to_cpu(reply->reply_code); + get_generic_request(req); + } + mutex_unlock(&monc->mutex); + if (req) { + complete(&req->completion); + put_generic_request(req); + } + return; + +bad: + pr_err("corrupt generic reply, tid %llu\n", tid); + ceph_msg_dump(msg); +} + +/* + * Do a synchronous pool op. + */ +int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op, + u32 pool, u64 snapid, + char *buf, int len) +{ + struct ceph_mon_generic_request *req; + struct ceph_mon_poolop *h; + int err; + + req = kzalloc(sizeof(*req), GFP_NOFS); + if (!req) + return -ENOMEM; + + kref_init(&req->kref); + req->buf = buf; + req->buf_len = len; + init_completion(&req->completion); + + err = -ENOMEM; + req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS); + if (!req->request) + goto out; + req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS); + if (!req->reply) + goto out; + + /* fill out request */ + req->request->hdr.version = cpu_to_le16(2); + h = req->request->front.iov_base; + h->monhdr.have_version = 0; + h->monhdr.session_mon = cpu_to_le16(-1); + h->monhdr.session_mon_tid = 0; + h->fsid = monc->monmap->fsid; + h->pool = cpu_to_le32(pool); + h->op = cpu_to_le32(op); + h->auid = 0; + h->snapid = cpu_to_le64(snapid); + h->name_len = 0; + + err = do_generic_request(monc, req); + +out: + kref_put(&req->kref, release_generic_request); + return err; +} + +int ceph_monc_create_snapid(struct ceph_mon_client *monc, + u32 pool, u64 *snapid) +{ + return ceph_monc_do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, + pool, 0, (char *)snapid, sizeof(*snapid)); + +} +EXPORT_SYMBOL(ceph_monc_create_snapid); + +int ceph_monc_delete_snapid(struct ceph_mon_client *monc, + u32 pool, u64 snapid) +{ + return ceph_monc_do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, + pool, snapid, 0, 0); + +} + +/* + * Resend pending generic requests. + */ +static void __resend_generic_request(struct ceph_mon_client *monc) +{ + struct ceph_mon_generic_request *req; + struct rb_node *p; + + for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) { + req = rb_entry(p, struct ceph_mon_generic_request, node); + ceph_con_revoke(monc->con, req->request); + ceph_con_send(monc->con, ceph_msg_get(req->request)); + } +} + +/* + * Delayed work. If we haven't mounted yet, retry. Otherwise, + * renew/retry subscription as needed (in case it is timing out, or we + * got an ENOMEM). And keep the monitor connection alive. + */ +static void delayed_work(struct work_struct *work) +{ + struct ceph_mon_client *monc = + container_of(work, struct ceph_mon_client, delayed_work.work); + + dout("monc delayed_work\n"); + mutex_lock(&monc->mutex); + if (monc->hunting) { + __close_session(monc); + __open_session(monc); /* continue hunting */ + } else { + ceph_con_keepalive(monc->con); + + __validate_auth(monc); + + if (monc->auth->ops->is_authenticated(monc->auth)) + __send_subscribe(monc); + } + __schedule_delayed(monc); + mutex_unlock(&monc->mutex); +} + +/* + * On startup, we build a temporary monmap populated with the IPs + * provided by mount(2). + */ +static int build_initial_monmap(struct ceph_mon_client *monc) +{ + struct ceph_options *opt = monc->client->options; + struct ceph_entity_addr *mon_addr = opt->mon_addr; + int num_mon = opt->num_mon; + int i; + + /* build initial monmap */ + monc->monmap = kzalloc(sizeof(*monc->monmap) + + num_mon*sizeof(monc->monmap->mon_inst[0]), + GFP_KERNEL); + if (!monc->monmap) + return -ENOMEM; + for (i = 0; i < num_mon; i++) { + monc->monmap->mon_inst[i].addr = mon_addr[i]; + monc->monmap->mon_inst[i].addr.nonce = 0; + monc->monmap->mon_inst[i].name.type = + CEPH_ENTITY_TYPE_MON; + monc->monmap->mon_inst[i].name.num = cpu_to_le64(i); + } + monc->monmap->num_mon = num_mon; + monc->have_fsid = false; + return 0; +} + +int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) +{ + int err = 0; + + dout("init\n"); + memset(monc, 0, sizeof(*monc)); + monc->client = cl; + monc->monmap = NULL; + mutex_init(&monc->mutex); + + err = build_initial_monmap(monc); + if (err) + goto out; + + monc->con = NULL; + + /* authentication */ + monc->auth = ceph_auth_init(cl->options->name, + cl->options->secret); + if (IS_ERR(monc->auth)) + return PTR_ERR(monc->auth); + monc->auth->want_keys = + CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON | + CEPH_ENTITY_TYPE_OSD | CEPH_ENTITY_TYPE_MDS; + + /* msgs */ + err = -ENOMEM; + monc->m_subscribe_ack = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE_ACK, + sizeof(struct ceph_mon_subscribe_ack), + GFP_NOFS); + if (!monc->m_subscribe_ack) + goto out_monmap; + + monc->m_subscribe = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, GFP_NOFS); + if (!monc->m_subscribe) + goto out_subscribe_ack; + + monc->m_auth_reply = ceph_msg_new(CEPH_MSG_AUTH_REPLY, 4096, GFP_NOFS); + if (!monc->m_auth_reply) + goto out_subscribe; + + monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, GFP_NOFS); + monc->pending_auth = 0; + if (!monc->m_auth) + goto out_auth_reply; + + monc->cur_mon = -1; + monc->hunting = true; + monc->sub_renew_after = jiffies; + monc->sub_sent = 0; + + INIT_DELAYED_WORK(&monc->delayed_work, delayed_work); + monc->generic_request_tree = RB_ROOT; + monc->num_generic_requests = 0; + monc->last_tid = 0; + + monc->have_mdsmap = 0; + monc->have_osdmap = 0; + monc->want_next_osdmap = 1; + return 0; + +out_auth_reply: + ceph_msg_put(monc->m_auth_reply); +out_subscribe: + ceph_msg_put(monc->m_subscribe); +out_subscribe_ack: + ceph_msg_put(monc->m_subscribe_ack); +out_monmap: + kfree(monc->monmap); +out: + return err; +} +EXPORT_SYMBOL(ceph_monc_init); + +void ceph_monc_stop(struct ceph_mon_client *monc) +{ + dout("stop\n"); + cancel_delayed_work_sync(&monc->delayed_work); + + mutex_lock(&monc->mutex); + __close_session(monc); + if (monc->con) { + monc->con->private = NULL; + monc->con->ops->put(monc->con); + monc->con = NULL; + } + mutex_unlock(&monc->mutex); + + ceph_auth_destroy(monc->auth); + + ceph_msg_put(monc->m_auth); + ceph_msg_put(monc->m_auth_reply); + ceph_msg_put(monc->m_subscribe); + ceph_msg_put(monc->m_subscribe_ack); + + kfree(monc->monmap); +} +EXPORT_SYMBOL(ceph_monc_stop); + +static void handle_auth_reply(struct ceph_mon_client *monc, + struct ceph_msg *msg) +{ + int ret; + int was_auth = 0; + + mutex_lock(&monc->mutex); + if (monc->auth->ops) + was_auth = monc->auth->ops->is_authenticated(monc->auth); + monc->pending_auth = 0; + ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, + msg->front.iov_len, + monc->m_auth->front.iov_base, + monc->m_auth->front_max); + if (ret < 0) { + monc->client->auth_err = ret; + wake_up_all(&monc->client->auth_wq); + } else if (ret > 0) { + __send_prepared_auth_request(monc, ret); + } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { + dout("authenticated, starting session\n"); + + monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT; + monc->client->msgr->inst.name.num = + cpu_to_le64(monc->auth->global_id); + + __send_subscribe(monc); + __resend_generic_request(monc); + } + mutex_unlock(&monc->mutex); +} + +static int __validate_auth(struct ceph_mon_client *monc) +{ + int ret; + + if (monc->pending_auth) + return 0; + + ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base, + monc->m_auth->front_max); + if (ret <= 0) + return ret; /* either an error, or no need to authenticate */ + __send_prepared_auth_request(monc, ret); + return 0; +} + +int ceph_monc_validate_auth(struct ceph_mon_client *monc) +{ + int ret; + + mutex_lock(&monc->mutex); + ret = __validate_auth(monc); + mutex_unlock(&monc->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_monc_validate_auth); + +/* + * handle incoming message + */ +static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_mon_client *monc = con->private; + int type = le16_to_cpu(msg->hdr.type); + + if (!monc) + return; + + switch (type) { + case CEPH_MSG_AUTH_REPLY: + handle_auth_reply(monc, msg); + break; + + case CEPH_MSG_MON_SUBSCRIBE_ACK: + handle_subscribe_ack(monc, msg); + break; + + case CEPH_MSG_STATFS_REPLY: + handle_statfs_reply(monc, msg); + break; + + case CEPH_MSG_POOLOP_REPLY: + handle_poolop_reply(monc, msg); + break; + + case CEPH_MSG_MON_MAP: + ceph_monc_handle_map(monc, msg); + break; + + case CEPH_MSG_OSD_MAP: + ceph_osdc_handle_map(&monc->client->osdc, msg); + break; + + default: + /* can the chained handler handle it? */ + if (monc->client->extra_mon_dispatch && + monc->client->extra_mon_dispatch(monc->client, msg) == 0) + break; + + pr_err("received unknown message type %d %s\n", type, + ceph_msg_type_name(type)); + } + ceph_msg_put(msg); +} + +/* + * Allocate memory for incoming message + */ +static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) +{ + struct ceph_mon_client *monc = con->private; + int type = le16_to_cpu(hdr->type); + int front_len = le32_to_cpu(hdr->front_len); + struct ceph_msg *m = NULL; + + *skip = 0; + + switch (type) { + case CEPH_MSG_MON_SUBSCRIBE_ACK: + m = ceph_msg_get(monc->m_subscribe_ack); + break; + case CEPH_MSG_POOLOP_REPLY: + case CEPH_MSG_STATFS_REPLY: + return get_generic_reply(con, hdr, skip); + case CEPH_MSG_AUTH_REPLY: + m = ceph_msg_get(monc->m_auth_reply); + break; + case CEPH_MSG_MON_MAP: + case CEPH_MSG_MDS_MAP: + case CEPH_MSG_OSD_MAP: + m = ceph_msg_new(type, front_len, GFP_NOFS); + break; + } + + if (!m) { + pr_info("alloc_msg unknown type %d\n", type); + *skip = 1; + } + return m; +} + +/* + * If the monitor connection resets, pick a new monitor and resubmit + * any pending requests. + */ +static void mon_fault(struct ceph_connection *con) +{ + struct ceph_mon_client *monc = con->private; + + if (!monc) + return; + + dout("mon_fault\n"); + mutex_lock(&monc->mutex); + if (!con->private) + goto out; + + if (monc->con && !monc->hunting) + pr_info("mon%d %s session lost, " + "hunting for new mon\n", monc->cur_mon, + ceph_pr_addr(&monc->con->peer_addr.in_addr)); + + __close_session(monc); + if (!monc->hunting) { + /* start hunting */ + monc->hunting = true; + __open_session(monc); + } else { + /* already hunting, let's wait a bit */ + __schedule_delayed(monc); + } +out: + mutex_unlock(&monc->mutex); +} + +static const struct ceph_connection_operations mon_con_ops = { + .get = ceph_con_get, + .put = ceph_con_put, + .dispatch = dispatch, + .fault = mon_fault, + .alloc_msg = mon_alloc_msg, +}; diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c new file mode 100644 index 000000000000..d5f2d97ac05c --- /dev/null +++ b/net/ceph/msgpool.c @@ -0,0 +1,64 @@ +#include + +#include +#include +#include +#include + +#include + +static void *alloc_fn(gfp_t gfp_mask, void *arg) +{ + struct ceph_msgpool *pool = arg; + void *p; + + p = ceph_msg_new(0, pool->front_len, gfp_mask); + if (!p) + pr_err("msgpool %s alloc failed\n", pool->name); + return p; +} + +static void free_fn(void *element, void *arg) +{ + ceph_msg_put(element); +} + +int ceph_msgpool_init(struct ceph_msgpool *pool, + int front_len, int size, bool blocking, const char *name) +{ + pool->front_len = front_len; + pool->pool = mempool_create(size, alloc_fn, free_fn, pool); + if (!pool->pool) + return -ENOMEM; + pool->name = name; + return 0; +} + +void ceph_msgpool_destroy(struct ceph_msgpool *pool) +{ + mempool_destroy(pool->pool); +} + +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, + int front_len) +{ + if (front_len > pool->front_len) { + pr_err("msgpool_get pool %s need front %d, pool size is %d\n", + pool->name, front_len, pool->front_len); + WARN_ON(1); + + /* try to alloc a fresh message */ + return ceph_msg_new(0, front_len, GFP_NOFS); + } + + return mempool_alloc(pool->pool, GFP_NOFS); +} + +void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg) +{ + /* reset msg front_len; user may have changed it */ + msg->front.iov_len = pool->front_len; + msg->hdr.front_len = cpu_to_le32(pool->front_len); + + kref_init(&msg->kref); /* retake single ref */ +} diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c new file mode 100644 index 000000000000..79391994b3ed --- /dev/null +++ b/net/ceph/osd_client.c @@ -0,0 +1,1773 @@ +#include + +#include +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_BLOCK +#include +#endif + +#include +#include +#include +#include +#include +#include + +#define OSD_OP_FRONT_LEN 4096 +#define OSD_OPREPLY_FRONT_LEN 512 + +static const struct ceph_connection_operations osd_con_ops; +static int __kick_requests(struct ceph_osd_client *osdc, + struct ceph_osd *kickosd); + +static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd); + +static int op_needs_trail(int op) +{ + switch (op) { + case CEPH_OSD_OP_GETXATTR: + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_CMPXATTR: + case CEPH_OSD_OP_CALL: + return 1; + default: + return 0; + } +} + +static int op_has_extent(int op) +{ + return (op == CEPH_OSD_OP_READ || + op == CEPH_OSD_OP_WRITE); +} + +void ceph_calc_raw_layout(struct ceph_osd_client *osdc, + struct ceph_file_layout *layout, + u64 snapid, + u64 off, u64 *plen, u64 *bno, + struct ceph_osd_request *req, + struct ceph_osd_req_op *op) +{ + struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; + u64 orig_len = *plen; + u64 objoff, objlen; /* extent in object */ + + reqhead->snapid = cpu_to_le64(snapid); + + /* object extent? */ + ceph_calc_file_object_mapping(layout, off, plen, bno, + &objoff, &objlen); + if (*plen < orig_len) + dout(" skipping last %llu, final file extent %llu~%llu\n", + orig_len - *plen, off, *plen); + + if (op_has_extent(op->op)) { + op->extent.offset = objoff; + op->extent.length = objlen; + } + req->r_num_pages = calc_pages_for(off, *plen); + if (op->op == CEPH_OSD_OP_WRITE) + op->payload_len = *plen; + + dout("calc_layout bno=%llx %llu~%llu (%d pages)\n", + *bno, objoff, objlen, req->r_num_pages); + +} +EXPORT_SYMBOL(ceph_calc_raw_layout); + +/* + * Implement client access to distributed object storage cluster. + * + * All data objects are stored within a cluster/cloud of OSDs, or + * "object storage devices." (Note that Ceph OSDs have _nothing_ to + * do with the T10 OSD extensions to SCSI.) Ceph OSDs are simply + * remote daemons serving up and coordinating consistent and safe + * access to storage. + * + * Cluster membership and the mapping of data objects onto storage devices + * are described by the osd map. + * + * We keep track of pending OSD requests (read, write), resubmit + * requests to different OSDs when the cluster topology/data layout + * change, or retry the affected requests when the communications + * channel with an OSD is reset. + */ + +/* + * calculate the mapping of a file extent onto an object, and fill out the + * request accordingly. shorten extent as necessary if it crosses an + * object boundary. + * + * fill osd op in request message. + */ +static void calc_layout(struct ceph_osd_client *osdc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + u64 off, u64 *plen, + struct ceph_osd_request *req, + struct ceph_osd_req_op *op) +{ + u64 bno; + + ceph_calc_raw_layout(osdc, layout, vino.snap, off, + plen, &bno, req, op); + + sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno); + req->r_oid_len = strlen(req->r_oid); +} + +/* + * requests + */ +void ceph_osdc_release_request(struct kref *kref) +{ + struct ceph_osd_request *req = container_of(kref, + struct ceph_osd_request, + r_kref); + + if (req->r_request) + ceph_msg_put(req->r_request); + if (req->r_reply) + ceph_msg_put(req->r_reply); + if (req->r_con_filling_msg) { + dout("release_request revoking pages %p from con %p\n", + req->r_pages, req->r_con_filling_msg); + ceph_con_revoke_message(req->r_con_filling_msg, + req->r_reply); + ceph_con_put(req->r_con_filling_msg); + } + if (req->r_own_pages) + ceph_release_page_vector(req->r_pages, + req->r_num_pages); +#ifdef CONFIG_BLOCK + if (req->r_bio) + bio_put(req->r_bio); +#endif + ceph_put_snap_context(req->r_snapc); + if (req->r_trail) { + ceph_pagelist_release(req->r_trail); + kfree(req->r_trail); + } + if (req->r_mempool) + mempool_free(req, req->r_osdc->req_mempool); + else + kfree(req); +} +EXPORT_SYMBOL(ceph_osdc_release_request); + +static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail) +{ + int i = 0; + + if (needs_trail) + *needs_trail = 0; + while (ops[i].op) { + if (needs_trail && op_needs_trail(ops[i].op)) + *needs_trail = 1; + i++; + } + + return i; +} + +struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, + int flags, + struct ceph_snap_context *snapc, + struct ceph_osd_req_op *ops, + bool use_mempool, + gfp_t gfp_flags, + struct page **pages, + struct bio *bio) +{ + struct ceph_osd_request *req; + struct ceph_msg *msg; + int needs_trail; + int num_op = get_num_ops(ops, &needs_trail); + size_t msg_size = sizeof(struct ceph_osd_request_head); + + msg_size += num_op*sizeof(struct ceph_osd_op); + + if (use_mempool) { + req = mempool_alloc(osdc->req_mempool, gfp_flags); + memset(req, 0, sizeof(*req)); + } else { + req = kzalloc(sizeof(*req), gfp_flags); + } + if (req == NULL) + return NULL; + + req->r_osdc = osdc; + req->r_mempool = use_mempool; + + kref_init(&req->r_kref); + init_completion(&req->r_completion); + init_completion(&req->r_safe_completion); + INIT_LIST_HEAD(&req->r_unsafe_item); + req->r_flags = flags; + + WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); + + /* create reply message */ + if (use_mempool) + msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); + else + msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, + OSD_OPREPLY_FRONT_LEN, gfp_flags); + if (!msg) { + ceph_osdc_put_request(req); + return NULL; + } + req->r_reply = msg; + + /* allocate space for the trailing data */ + if (needs_trail) { + req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags); + if (!req->r_trail) { + ceph_osdc_put_request(req); + return NULL; + } + ceph_pagelist_init(req->r_trail); + } + /* create request message; allow space for oid */ + msg_size += 40; + if (snapc) + msg_size += sizeof(u64) * snapc->num_snaps; + if (use_mempool) + msg = ceph_msgpool_get(&osdc->msgpool_op, 0); + else + msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags); + if (!msg) { + ceph_osdc_put_request(req); + return NULL; + } + + msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP); + memset(msg->front.iov_base, 0, msg->front.iov_len); + + req->r_request = msg; + req->r_pages = pages; +#ifdef CONFIG_BLOCK + if (bio) { + req->r_bio = bio; + bio_get(req->r_bio); + } +#endif + + return req; +} +EXPORT_SYMBOL(ceph_osdc_alloc_request); + +static void osd_req_encode_op(struct ceph_osd_request *req, + struct ceph_osd_op *dst, + struct ceph_osd_req_op *src) +{ + dst->op = cpu_to_le16(src->op); + + switch (dst->op) { + case CEPH_OSD_OP_READ: + case CEPH_OSD_OP_WRITE: + dst->extent.offset = + cpu_to_le64(src->extent.offset); + dst->extent.length = + cpu_to_le64(src->extent.length); + dst->extent.truncate_size = + cpu_to_le64(src->extent.truncate_size); + dst->extent.truncate_seq = + cpu_to_le32(src->extent.truncate_seq); + break; + + case CEPH_OSD_OP_GETXATTR: + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_CMPXATTR: + BUG_ON(!req->r_trail); + + dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); + dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); + dst->xattr.cmp_op = src->xattr.cmp_op; + dst->xattr.cmp_mode = src->xattr.cmp_mode; + ceph_pagelist_append(req->r_trail, src->xattr.name, + src->xattr.name_len); + ceph_pagelist_append(req->r_trail, src->xattr.val, + src->xattr.value_len); + break; + case CEPH_OSD_OP_CALL: + BUG_ON(!req->r_trail); + + dst->cls.class_len = src->cls.class_len; + dst->cls.method_len = src->cls.method_len; + dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); + + ceph_pagelist_append(req->r_trail, src->cls.class_name, + src->cls.class_len); + ceph_pagelist_append(req->r_trail, src->cls.method_name, + src->cls.method_len); + ceph_pagelist_append(req->r_trail, src->cls.indata, + src->cls.indata_len); + break; + case CEPH_OSD_OP_ROLLBACK: + dst->snap.snapid = cpu_to_le64(src->snap.snapid); + break; + case CEPH_OSD_OP_STARTSYNC: + break; + default: + pr_err("unrecognized osd opcode %d\n", dst->op); + WARN_ON(1); + break; + } + dst->payload_len = cpu_to_le32(src->payload_len); +} + +/* + * build new request AND message + * + */ +void ceph_osdc_build_request(struct ceph_osd_request *req, + u64 off, u64 *plen, + struct ceph_osd_req_op *src_ops, + struct ceph_snap_context *snapc, + struct timespec *mtime, + const char *oid, + int oid_len) +{ + struct ceph_msg *msg = req->r_request; + struct ceph_osd_request_head *head; + struct ceph_osd_req_op *src_op; + struct ceph_osd_op *op; + void *p; + int num_op = get_num_ops(src_ops, NULL); + size_t msg_size = sizeof(*head) + num_op*sizeof(*op); + int flags = req->r_flags; + u64 data_len = 0; + int i; + + head = msg->front.iov_base; + op = (void *)(head + 1); + p = (void *)(op + num_op); + + req->r_snapc = ceph_get_snap_context(snapc); + + head->client_inc = cpu_to_le32(1); /* always, for now. */ + head->flags = cpu_to_le32(flags); + if (flags & CEPH_OSD_FLAG_WRITE) + ceph_encode_timespec(&head->mtime, mtime); + head->num_ops = cpu_to_le16(num_op); + + + /* fill in oid */ + head->object_len = cpu_to_le32(oid_len); + memcpy(p, oid, oid_len); + p += oid_len; + + src_op = src_ops; + while (src_op->op) { + osd_req_encode_op(req, op, src_op); + src_op++; + op++; + } + + if (req->r_trail) + data_len += req->r_trail->length; + + if (snapc) { + head->snap_seq = cpu_to_le64(snapc->seq); + head->num_snaps = cpu_to_le32(snapc->num_snaps); + for (i = 0; i < snapc->num_snaps; i++) { + put_unaligned_le64(snapc->snaps[i], p); + p += sizeof(u64); + } + } + + if (flags & CEPH_OSD_FLAG_WRITE) { + req->r_request->hdr.data_off = cpu_to_le16(off); + req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len); + } else if (data_len) { + req->r_request->hdr.data_off = 0; + req->r_request->hdr.data_len = cpu_to_le32(data_len); + } + + BUG_ON(p > msg->front.iov_base + msg->front.iov_len); + msg_size = p - msg->front.iov_base; + msg->front.iov_len = msg_size; + msg->hdr.front_len = cpu_to_le32(msg_size); + return; +} +EXPORT_SYMBOL(ceph_osdc_build_request); + +/* + * build new request AND message, calculate layout, and adjust file + * extent as needed. + * + * if the file was recently truncated, we include information about its + * old and new size so that the object can be updated appropriately. (we + * avoid synchronously deleting truncated objects because it's slow.) + * + * if @do_sync, include a 'startsync' command so that the osd will flush + * data quickly. + */ +struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, + struct ceph_file_layout *layout, + struct ceph_vino vino, + u64 off, u64 *plen, + int opcode, int flags, + struct ceph_snap_context *snapc, + int do_sync, + u32 truncate_seq, + u64 truncate_size, + struct timespec *mtime, + bool use_mempool, int num_reply) +{ + struct ceph_osd_req_op ops[3]; + struct ceph_osd_request *req; + + ops[0].op = opcode; + ops[0].extent.truncate_seq = truncate_seq; + ops[0].extent.truncate_size = truncate_size; + ops[0].payload_len = 0; + + if (do_sync) { + ops[1].op = CEPH_OSD_OP_STARTSYNC; + ops[1].payload_len = 0; + ops[2].op = 0; + } else + ops[1].op = 0; + + req = ceph_osdc_alloc_request(osdc, flags, + snapc, ops, + use_mempool, + GFP_NOFS, NULL, NULL); + if (IS_ERR(req)) + return req; + + /* calculate max write size */ + calc_layout(osdc, vino, layout, off, plen, req, ops); + req->r_file_layout = *layout; /* keep a copy */ + + ceph_osdc_build_request(req, off, plen, ops, + snapc, + mtime, + req->r_oid, req->r_oid_len); + + return req; +} +EXPORT_SYMBOL(ceph_osdc_new_request); + +/* + * We keep osd requests in an rbtree, sorted by ->r_tid. + */ +static void __insert_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *new) +{ + struct rb_node **p = &osdc->requests.rb_node; + struct rb_node *parent = NULL; + struct ceph_osd_request *req = NULL; + + while (*p) { + parent = *p; + req = rb_entry(parent, struct ceph_osd_request, r_node); + if (new->r_tid < req->r_tid) + p = &(*p)->rb_left; + else if (new->r_tid > req->r_tid) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&new->r_node, parent, p); + rb_insert_color(&new->r_node, &osdc->requests); +} + +static struct ceph_osd_request *__lookup_request(struct ceph_osd_client *osdc, + u64 tid) +{ + struct ceph_osd_request *req; + struct rb_node *n = osdc->requests.rb_node; + + while (n) { + req = rb_entry(n, struct ceph_osd_request, r_node); + if (tid < req->r_tid) + n = n->rb_left; + else if (tid > req->r_tid) + n = n->rb_right; + else + return req; + } + return NULL; +} + +static struct ceph_osd_request * +__lookup_request_ge(struct ceph_osd_client *osdc, + u64 tid) +{ + struct ceph_osd_request *req; + struct rb_node *n = osdc->requests.rb_node; + + while (n) { + req = rb_entry(n, struct ceph_osd_request, r_node); + if (tid < req->r_tid) { + if (!n->rb_left) + return req; + n = n->rb_left; + } else if (tid > req->r_tid) { + n = n->rb_right; + } else { + return req; + } + } + return NULL; +} + + +/* + * If the osd connection drops, we need to resubmit all requests. + */ +static void osd_reset(struct ceph_connection *con) +{ + struct ceph_osd *osd = con->private; + struct ceph_osd_client *osdc; + + if (!osd) + return; + dout("osd_reset osd%d\n", osd->o_osd); + osdc = osd->o_osdc; + down_read(&osdc->map_sem); + kick_requests(osdc, osd); + up_read(&osdc->map_sem); +} + +/* + * Track open sessions with osds. + */ +static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) +{ + struct ceph_osd *osd; + + osd = kzalloc(sizeof(*osd), GFP_NOFS); + if (!osd) + return NULL; + + atomic_set(&osd->o_ref, 1); + osd->o_osdc = osdc; + INIT_LIST_HEAD(&osd->o_requests); + INIT_LIST_HEAD(&osd->o_osd_lru); + osd->o_incarnation = 1; + + ceph_con_init(osdc->client->msgr, &osd->o_con); + osd->o_con.private = osd; + osd->o_con.ops = &osd_con_ops; + osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; + + INIT_LIST_HEAD(&osd->o_keepalive_item); + return osd; +} + +static struct ceph_osd *get_osd(struct ceph_osd *osd) +{ + if (atomic_inc_not_zero(&osd->o_ref)) { + dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1, + atomic_read(&osd->o_ref)); + return osd; + } else { + dout("get_osd %p FAIL\n", osd); + return NULL; + } +} + +static void put_osd(struct ceph_osd *osd) +{ + dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), + atomic_read(&osd->o_ref) - 1); + if (atomic_dec_and_test(&osd->o_ref)) { + struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; + + if (osd->o_authorizer) + ac->ops->destroy_authorizer(ac, osd->o_authorizer); + kfree(osd); + } +} + +/* + * remove an osd from our map + */ +static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + dout("__remove_osd %p\n", osd); + BUG_ON(!list_empty(&osd->o_requests)); + rb_erase(&osd->o_node, &osdc->osds); + list_del_init(&osd->o_osd_lru); + ceph_con_close(&osd->o_con); + put_osd(osd); +} + +static void __move_osd_to_lru(struct ceph_osd_client *osdc, + struct ceph_osd *osd) +{ + dout("__move_osd_to_lru %p\n", osd); + BUG_ON(!list_empty(&osd->o_osd_lru)); + list_add_tail(&osd->o_osd_lru, &osdc->osd_lru); + osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ; +} + +static void __remove_osd_from_lru(struct ceph_osd *osd) +{ + dout("__remove_osd_from_lru %p\n", osd); + if (!list_empty(&osd->o_osd_lru)) + list_del_init(&osd->o_osd_lru); +} + +static void remove_old_osds(struct ceph_osd_client *osdc, int remove_all) +{ + struct ceph_osd *osd, *nosd; + + dout("__remove_old_osds %p\n", osdc); + mutex_lock(&osdc->request_mutex); + list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { + if (!remove_all && time_before(jiffies, osd->lru_ttl)) + break; + __remove_osd(osdc, osd); + } + mutex_unlock(&osdc->request_mutex); +} + +/* + * reset osd connect + */ +static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + struct ceph_osd_request *req; + int ret = 0; + + dout("__reset_osd %p osd%d\n", osd, osd->o_osd); + if (list_empty(&osd->o_requests)) { + __remove_osd(osdc, osd); + } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], + &osd->o_con.peer_addr, + sizeof(osd->o_con.peer_addr)) == 0 && + !ceph_con_opened(&osd->o_con)) { + dout(" osd addr hasn't changed and connection never opened," + " letting msgr retry"); + /* touch each r_stamp for handle_timeout()'s benfit */ + list_for_each_entry(req, &osd->o_requests, r_osd_item) + req->r_stamp = jiffies; + ret = -EAGAIN; + } else { + ceph_con_close(&osd->o_con); + ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]); + osd->o_incarnation++; + } + return ret; +} + +static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new) +{ + struct rb_node **p = &osdc->osds.rb_node; + struct rb_node *parent = NULL; + struct ceph_osd *osd = NULL; + + while (*p) { + parent = *p; + osd = rb_entry(parent, struct ceph_osd, o_node); + if (new->o_osd < osd->o_osd) + p = &(*p)->rb_left; + else if (new->o_osd > osd->o_osd) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&new->o_node, parent, p); + rb_insert_color(&new->o_node, &osdc->osds); +} + +static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o) +{ + struct ceph_osd *osd; + struct rb_node *n = osdc->osds.rb_node; + + while (n) { + osd = rb_entry(n, struct ceph_osd, o_node); + if (o < osd->o_osd) + n = n->rb_left; + else if (o > osd->o_osd) + n = n->rb_right; + else + return osd; + } + return NULL; +} + +static void __schedule_osd_timeout(struct ceph_osd_client *osdc) +{ + schedule_delayed_work(&osdc->timeout_work, + osdc->client->options->osd_keepalive_timeout * HZ); +} + +static void __cancel_osd_timeout(struct ceph_osd_client *osdc) +{ + cancel_delayed_work(&osdc->timeout_work); +} + +/* + * Register request, assign tid. If this is the first request, set up + * the timeout event. + */ +static void register_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + mutex_lock(&osdc->request_mutex); + req->r_tid = ++osdc->last_tid; + req->r_request->hdr.tid = cpu_to_le64(req->r_tid); + INIT_LIST_HEAD(&req->r_req_lru_item); + + dout("register_request %p tid %lld\n", req, req->r_tid); + __insert_request(osdc, req); + ceph_osdc_get_request(req); + osdc->num_requests++; + + if (osdc->num_requests == 1) { + dout(" first request, scheduling timeout\n"); + __schedule_osd_timeout(osdc); + } + mutex_unlock(&osdc->request_mutex); +} + +/* + * called under osdc->request_mutex + */ +static void __unregister_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + dout("__unregister_request %p tid %lld\n", req, req->r_tid); + rb_erase(&req->r_node, &osdc->requests); + osdc->num_requests--; + + if (req->r_osd) { + /* make sure the original request isn't in flight. */ + ceph_con_revoke(&req->r_osd->o_con, req->r_request); + + list_del_init(&req->r_osd_item); + if (list_empty(&req->r_osd->o_requests)) + __move_osd_to_lru(osdc, req->r_osd); + req->r_osd = NULL; + } + + ceph_osdc_put_request(req); + + list_del_init(&req->r_req_lru_item); + if (osdc->num_requests == 0) { + dout(" no requests, canceling timeout\n"); + __cancel_osd_timeout(osdc); + } +} + +/* + * Cancel a previously queued request message + */ +static void __cancel_request(struct ceph_osd_request *req) +{ + if (req->r_sent && req->r_osd) { + ceph_con_revoke(&req->r_osd->o_con, req->r_request); + req->r_sent = 0; + } + list_del_init(&req->r_req_lru_item); +} + +/* + * Pick an osd (the first 'up' osd in the pg), allocate the osd struct + * (as needed), and set the request r_osd appropriately. If there is + * no up osd, set r_osd to NULL. + * + * Return 0 if unchanged, 1 if changed, or negative on error. + * + * Caller should hold map_sem for read and request_mutex. + */ +static int __map_osds(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; + struct ceph_pg pgid; + int acting[CEPH_PG_MAX_SIZE]; + int o = -1, num = 0; + int err; + + dout("map_osds %p tid %lld\n", req, req->r_tid); + err = ceph_calc_object_layout(&reqhead->layout, req->r_oid, + &req->r_file_layout, osdc->osdmap); + if (err) + return err; + pgid = reqhead->layout.ol_pgid; + req->r_pgid = pgid; + + err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting); + if (err > 0) { + o = acting[0]; + num = err; + } + + if ((req->r_osd && req->r_osd->o_osd == o && + req->r_sent >= req->r_osd->o_incarnation && + req->r_num_pg_osds == num && + memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || + (req->r_osd == NULL && o == -1)) + return 0; /* no change */ + + dout("map_osds tid %llu pgid %d.%x osd%d (was osd%d)\n", + req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o, + req->r_osd ? req->r_osd->o_osd : -1); + + /* record full pg acting set */ + memcpy(req->r_pg_osds, acting, sizeof(acting[0]) * num); + req->r_num_pg_osds = num; + + if (req->r_osd) { + __cancel_request(req); + list_del_init(&req->r_osd_item); + req->r_osd = NULL; + } + + req->r_osd = __lookup_osd(osdc, o); + if (!req->r_osd && o >= 0) { + err = -ENOMEM; + req->r_osd = create_osd(osdc); + if (!req->r_osd) + goto out; + + dout("map_osds osd %p is osd%d\n", req->r_osd, o); + req->r_osd->o_osd = o; + req->r_osd->o_con.peer_name.num = cpu_to_le64(o); + __insert_osd(osdc, req->r_osd); + + ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]); + } + + if (req->r_osd) { + __remove_osd_from_lru(req->r_osd); + list_add(&req->r_osd_item, &req->r_osd->o_requests); + } + err = 1; /* osd or pg changed */ + +out: + return err; +} + +/* + * caller should hold map_sem (for read) and request_mutex + */ +static int __send_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + struct ceph_osd_request_head *reqhead; + int err; + + err = __map_osds(osdc, req); + if (err < 0) + return err; + if (req->r_osd == NULL) { + dout("send_request %p no up osds in pg\n", req); + ceph_monc_request_next_osdmap(&osdc->client->monc); + return 0; + } + + dout("send_request %p tid %llu to osd%d flags %d\n", + req, req->r_tid, req->r_osd->o_osd, req->r_flags); + + reqhead = req->r_request->front.iov_base; + reqhead->osdmap_epoch = cpu_to_le32(osdc->osdmap->epoch); + reqhead->flags |= cpu_to_le32(req->r_flags); /* e.g., RETRY */ + reqhead->reassert_version = req->r_reassert_version; + + req->r_stamp = jiffies; + list_move_tail(&req->r_req_lru_item, &osdc->req_lru); + + ceph_msg_get(req->r_request); /* send consumes a ref */ + ceph_con_send(&req->r_osd->o_con, req->r_request); + req->r_sent = req->r_osd->o_incarnation; + return 0; +} + +/* + * Timeout callback, called every N seconds when 1 or more osd + * requests has been active for more than N seconds. When this + * happens, we ping all OSDs with requests who have timed out to + * ensure any communications channel reset is detected. Reset the + * request timeouts another N seconds in the future as we go. + * Reschedule the timeout event another N seconds in future (unless + * there are no open requests). + */ +static void handle_timeout(struct work_struct *work) +{ + struct ceph_osd_client *osdc = + container_of(work, struct ceph_osd_client, timeout_work.work); + struct ceph_osd_request *req, *last_req = NULL; + struct ceph_osd *osd; + unsigned long timeout = osdc->client->options->osd_timeout * HZ; + unsigned long keepalive = + osdc->client->options->osd_keepalive_timeout * HZ; + unsigned long last_stamp = 0; + struct rb_node *p; + struct list_head slow_osds; + + dout("timeout\n"); + down_read(&osdc->map_sem); + + ceph_monc_request_next_osdmap(&osdc->client->monc); + + mutex_lock(&osdc->request_mutex); + for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { + req = rb_entry(p, struct ceph_osd_request, r_node); + + if (req->r_resend) { + int err; + + dout("osdc resending prev failed %lld\n", req->r_tid); + err = __send_request(osdc, req); + if (err) + dout("osdc failed again on %lld\n", req->r_tid); + else + req->r_resend = false; + continue; + } + } + + /* + * reset osds that appear to be _really_ unresponsive. this + * is a failsafe measure.. we really shouldn't be getting to + * this point if the system is working properly. the monitors + * should mark the osd as failed and we should find out about + * it from an updated osd map. + */ + while (timeout && !list_empty(&osdc->req_lru)) { + req = list_entry(osdc->req_lru.next, struct ceph_osd_request, + r_req_lru_item); + + if (time_before(jiffies, req->r_stamp + timeout)) + break; + + BUG_ON(req == last_req && req->r_stamp == last_stamp); + last_req = req; + last_stamp = req->r_stamp; + + osd = req->r_osd; + BUG_ON(!osd); + pr_warning(" tid %llu timed out on osd%d, will reset osd\n", + req->r_tid, osd->o_osd); + __kick_requests(osdc, osd); + } + + /* + * ping osds that are a bit slow. this ensures that if there + * is a break in the TCP connection we will notice, and reopen + * a connection with that osd (from the fault callback). + */ + INIT_LIST_HEAD(&slow_osds); + list_for_each_entry(req, &osdc->req_lru, r_req_lru_item) { + if (time_before(jiffies, req->r_stamp + keepalive)) + break; + + osd = req->r_osd; + BUG_ON(!osd); + dout(" tid %llu is slow, will send keepalive on osd%d\n", + req->r_tid, osd->o_osd); + list_move_tail(&osd->o_keepalive_item, &slow_osds); + } + while (!list_empty(&slow_osds)) { + osd = list_entry(slow_osds.next, struct ceph_osd, + o_keepalive_item); + list_del_init(&osd->o_keepalive_item); + ceph_con_keepalive(&osd->o_con); + } + + __schedule_osd_timeout(osdc); + mutex_unlock(&osdc->request_mutex); + + up_read(&osdc->map_sem); +} + +static void handle_osds_timeout(struct work_struct *work) +{ + struct ceph_osd_client *osdc = + container_of(work, struct ceph_osd_client, + osds_timeout_work.work); + unsigned long delay = + osdc->client->options->osd_idle_ttl * HZ >> 2; + + dout("osds timeout\n"); + down_read(&osdc->map_sem); + remove_old_osds(osdc, 0); + up_read(&osdc->map_sem); + + schedule_delayed_work(&osdc->osds_timeout_work, + round_jiffies_relative(delay)); +} + +/* + * handle osd op reply. either call the callback if it is specified, + * or do the completion to wake up the waiting thread. + */ +static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, + struct ceph_connection *con) +{ + struct ceph_osd_reply_head *rhead = msg->front.iov_base; + struct ceph_osd_request *req; + u64 tid; + int numops, object_len, flags; + s32 result; + + tid = le64_to_cpu(msg->hdr.tid); + if (msg->front.iov_len < sizeof(*rhead)) + goto bad; + numops = le32_to_cpu(rhead->num_ops); + object_len = le32_to_cpu(rhead->object_len); + result = le32_to_cpu(rhead->result); + if (msg->front.iov_len != sizeof(*rhead) + object_len + + numops * sizeof(struct ceph_osd_op)) + goto bad; + dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result); + + /* lookup */ + mutex_lock(&osdc->request_mutex); + req = __lookup_request(osdc, tid); + if (req == NULL) { + dout("handle_reply tid %llu dne\n", tid); + mutex_unlock(&osdc->request_mutex); + return; + } + ceph_osdc_get_request(req); + flags = le32_to_cpu(rhead->flags); + + /* + * if this connection filled our message, drop our reference now, to + * avoid a (safe but slower) revoke later. + */ + if (req->r_con_filling_msg == con && req->r_reply == msg) { + dout(" dropping con_filling_msg ref %p\n", con); + req->r_con_filling_msg = NULL; + ceph_con_put(con); + } + + if (!req->r_got_reply) { + unsigned bytes; + + req->r_result = le32_to_cpu(rhead->result); + bytes = le32_to_cpu(msg->hdr.data_len); + dout("handle_reply result %d bytes %d\n", req->r_result, + bytes); + if (req->r_result == 0) + req->r_result = bytes; + + /* in case this is a write and we need to replay, */ + req->r_reassert_version = rhead->reassert_version; + + req->r_got_reply = 1; + } else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) { + dout("handle_reply tid %llu dup ack\n", tid); + mutex_unlock(&osdc->request_mutex); + goto done; + } + + dout("handle_reply tid %llu flags %d\n", tid, flags); + + /* either this is a read, or we got the safe response */ + if (result < 0 || + (flags & CEPH_OSD_FLAG_ONDISK) || + ((flags & CEPH_OSD_FLAG_WRITE) == 0)) + __unregister_request(osdc, req); + + mutex_unlock(&osdc->request_mutex); + + if (req->r_callback) + req->r_callback(req, msg); + else + complete_all(&req->r_completion); + + if (flags & CEPH_OSD_FLAG_ONDISK) { + if (req->r_safe_callback) + req->r_safe_callback(req, msg); + complete_all(&req->r_safe_completion); /* fsync waiter */ + } + +done: + ceph_osdc_put_request(req); + return; + +bad: + pr_err("corrupt osd_op_reply got %d %d expected %d\n", + (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len), + (int)sizeof(*rhead)); + ceph_msg_dump(msg); +} + + +static int __kick_requests(struct ceph_osd_client *osdc, + struct ceph_osd *kickosd) +{ + struct ceph_osd_request *req; + struct rb_node *p, *n; + int needmap = 0; + int err; + + dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1); + if (kickosd) { + err = __reset_osd(osdc, kickosd); + if (err == -EAGAIN) + return 1; + } else { + for (p = rb_first(&osdc->osds); p; p = n) { + struct ceph_osd *osd = + rb_entry(p, struct ceph_osd, o_node); + + n = rb_next(p); + if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || + memcmp(&osd->o_con.peer_addr, + ceph_osd_addr(osdc->osdmap, + osd->o_osd), + sizeof(struct ceph_entity_addr)) != 0) + __reset_osd(osdc, osd); + } + } + + for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { + req = rb_entry(p, struct ceph_osd_request, r_node); + + if (req->r_resend) { + dout(" r_resend set on tid %llu\n", req->r_tid); + __cancel_request(req); + goto kick; + } + if (req->r_osd && kickosd == req->r_osd) { + __cancel_request(req); + goto kick; + } + + err = __map_osds(osdc, req); + if (err == 0) + continue; /* no change */ + if (err < 0) { + /* + * FIXME: really, we should set the request + * error and fail if this isn't a 'nofail' + * request, but that's a fair bit more + * complicated to do. So retry! + */ + dout(" setting r_resend on %llu\n", req->r_tid); + req->r_resend = true; + continue; + } + if (req->r_osd == NULL) { + dout("tid %llu maps to no valid osd\n", req->r_tid); + needmap++; /* request a newer map */ + continue; + } + +kick: + dout("kicking %p tid %llu osd%d\n", req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + req->r_flags |= CEPH_OSD_FLAG_RETRY; + err = __send_request(osdc, req); + if (err) { + dout(" setting r_resend on %llu\n", req->r_tid); + req->r_resend = true; + } + } + + return needmap; +} + +/* + * Resubmit osd requests whose osd or osd address has changed. Request + * a new osd map if osds are down, or we are otherwise unable to determine + * how to direct a request. + * + * Close connections to down osds. + * + * If @who is specified, resubmit requests for that specific osd. + * + * Caller should hold map_sem for read and request_mutex. + */ +static void kick_requests(struct ceph_osd_client *osdc, + struct ceph_osd *kickosd) +{ + int needmap; + + mutex_lock(&osdc->request_mutex); + needmap = __kick_requests(osdc, kickosd); + mutex_unlock(&osdc->request_mutex); + + if (needmap) { + dout("%d requests for down osds, need new map\n", needmap); + ceph_monc_request_next_osdmap(&osdc->client->monc); + } + +} +/* + * Process updated osd map. + * + * The message contains any number of incremental and full maps, normally + * indicating some sort of topology change in the cluster. Kick requests + * off to different OSDs as needed. + */ +void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) +{ + void *p, *end, *next; + u32 nr_maps, maplen; + u32 epoch; + struct ceph_osdmap *newmap = NULL, *oldmap; + int err; + struct ceph_fsid fsid; + + dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0); + p = msg->front.iov_base; + end = p + msg->front.iov_len; + + /* verify fsid */ + ceph_decode_need(&p, end, sizeof(fsid), bad); + ceph_decode_copy(&p, &fsid, sizeof(fsid)); + if (ceph_check_fsid(osdc->client, &fsid) < 0) + return; + + down_write(&osdc->map_sem); + + /* incremental maps */ + ceph_decode_32_safe(&p, end, nr_maps, bad); + dout(" %d inc maps\n", nr_maps); + while (nr_maps > 0) { + ceph_decode_need(&p, end, 2*sizeof(u32), bad); + epoch = ceph_decode_32(&p); + maplen = ceph_decode_32(&p); + ceph_decode_need(&p, end, maplen, bad); + next = p + maplen; + if (osdc->osdmap && osdc->osdmap->epoch+1 == epoch) { + dout("applying incremental map %u len %d\n", + epoch, maplen); + newmap = osdmap_apply_incremental(&p, next, + osdc->osdmap, + osdc->client->msgr); + if (IS_ERR(newmap)) { + err = PTR_ERR(newmap); + goto bad; + } + BUG_ON(!newmap); + if (newmap != osdc->osdmap) { + ceph_osdmap_destroy(osdc->osdmap); + osdc->osdmap = newmap; + } + } else { + dout("ignoring incremental map %u len %d\n", + epoch, maplen); + } + p = next; + nr_maps--; + } + if (newmap) + goto done; + + /* full maps */ + ceph_decode_32_safe(&p, end, nr_maps, bad); + dout(" %d full maps\n", nr_maps); + while (nr_maps) { + ceph_decode_need(&p, end, 2*sizeof(u32), bad); + epoch = ceph_decode_32(&p); + maplen = ceph_decode_32(&p); + ceph_decode_need(&p, end, maplen, bad); + if (nr_maps > 1) { + dout("skipping non-latest full map %u len %d\n", + epoch, maplen); + } else if (osdc->osdmap && osdc->osdmap->epoch >= epoch) { + dout("skipping full map %u len %d, " + "older than our %u\n", epoch, maplen, + osdc->osdmap->epoch); + } else { + dout("taking full map %u len %d\n", epoch, maplen); + newmap = osdmap_decode(&p, p+maplen); + if (IS_ERR(newmap)) { + err = PTR_ERR(newmap); + goto bad; + } + BUG_ON(!newmap); + oldmap = osdc->osdmap; + osdc->osdmap = newmap; + if (oldmap) + ceph_osdmap_destroy(oldmap); + } + p += maplen; + nr_maps--; + } + +done: + downgrade_write(&osdc->map_sem); + ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); + if (newmap) + kick_requests(osdc, NULL); + up_read(&osdc->map_sem); + wake_up_all(&osdc->client->auth_wq); + return; + +bad: + pr_err("osdc handle_map corrupt msg\n"); + ceph_msg_dump(msg); + up_write(&osdc->map_sem); + return; +} + +/* + * Register request, send initial attempt. + */ +int ceph_osdc_start_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req, + bool nofail) +{ + int rc = 0; + + req->r_request->pages = req->r_pages; + req->r_request->nr_pages = req->r_num_pages; +#ifdef CONFIG_BLOCK + req->r_request->bio = req->r_bio; +#endif + req->r_request->trail = req->r_trail; + + register_request(osdc, req); + + down_read(&osdc->map_sem); + mutex_lock(&osdc->request_mutex); + /* + * a racing kick_requests() may have sent the message for us + * while we dropped request_mutex above, so only send now if + * the request still han't been touched yet. + */ + if (req->r_sent == 0) { + rc = __send_request(osdc, req); + if (rc) { + if (nofail) { + dout("osdc_start_request failed send, " + " marking %lld\n", req->r_tid); + req->r_resend = true; + rc = 0; + } else { + __unregister_request(osdc, req); + } + } + } + mutex_unlock(&osdc->request_mutex); + up_read(&osdc->map_sem); + return rc; +} +EXPORT_SYMBOL(ceph_osdc_start_request); + +/* + * wait for a request to complete + */ +int ceph_osdc_wait_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + int rc; + + rc = wait_for_completion_interruptible(&req->r_completion); + if (rc < 0) { + mutex_lock(&osdc->request_mutex); + __cancel_request(req); + __unregister_request(osdc, req); + mutex_unlock(&osdc->request_mutex); + dout("wait_request tid %llu canceled/timed out\n", req->r_tid); + return rc; + } + + dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result); + return req->r_result; +} +EXPORT_SYMBOL(ceph_osdc_wait_request); + +/* + * sync - wait for all in-flight requests to flush. avoid starvation. + */ +void ceph_osdc_sync(struct ceph_osd_client *osdc) +{ + struct ceph_osd_request *req; + u64 last_tid, next_tid = 0; + + mutex_lock(&osdc->request_mutex); + last_tid = osdc->last_tid; + while (1) { + req = __lookup_request_ge(osdc, next_tid); + if (!req) + break; + if (req->r_tid > last_tid) + break; + + next_tid = req->r_tid + 1; + if ((req->r_flags & CEPH_OSD_FLAG_WRITE) == 0) + continue; + + ceph_osdc_get_request(req); + mutex_unlock(&osdc->request_mutex); + dout("sync waiting on tid %llu (last is %llu)\n", + req->r_tid, last_tid); + wait_for_completion(&req->r_safe_completion); + mutex_lock(&osdc->request_mutex); + ceph_osdc_put_request(req); + } + mutex_unlock(&osdc->request_mutex); + dout("sync done (thru tid %llu)\n", last_tid); +} +EXPORT_SYMBOL(ceph_osdc_sync); + +/* + * init, shutdown + */ +int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) +{ + int err; + + dout("init\n"); + osdc->client = client; + osdc->osdmap = NULL; + init_rwsem(&osdc->map_sem); + init_completion(&osdc->map_waiters); + osdc->last_requested_map = 0; + mutex_init(&osdc->request_mutex); + osdc->last_tid = 0; + osdc->osds = RB_ROOT; + INIT_LIST_HEAD(&osdc->osd_lru); + osdc->requests = RB_ROOT; + INIT_LIST_HEAD(&osdc->req_lru); + osdc->num_requests = 0; + INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); + INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); + + schedule_delayed_work(&osdc->osds_timeout_work, + round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ)); + + err = -ENOMEM; + osdc->req_mempool = mempool_create_kmalloc_pool(10, + sizeof(struct ceph_osd_request)); + if (!osdc->req_mempool) + goto out; + + err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true, + "osd_op"); + if (err < 0) + goto out_mempool; + err = ceph_msgpool_init(&osdc->msgpool_op_reply, + OSD_OPREPLY_FRONT_LEN, 10, true, + "osd_op_reply"); + if (err < 0) + goto out_msgpool; + return 0; + +out_msgpool: + ceph_msgpool_destroy(&osdc->msgpool_op); +out_mempool: + mempool_destroy(osdc->req_mempool); +out: + return err; +} +EXPORT_SYMBOL(ceph_osdc_init); + +void ceph_osdc_stop(struct ceph_osd_client *osdc) +{ + cancel_delayed_work_sync(&osdc->timeout_work); + cancel_delayed_work_sync(&osdc->osds_timeout_work); + if (osdc->osdmap) { + ceph_osdmap_destroy(osdc->osdmap); + osdc->osdmap = NULL; + } + remove_old_osds(osdc, 1); + mempool_destroy(osdc->req_mempool); + ceph_msgpool_destroy(&osdc->msgpool_op); + ceph_msgpool_destroy(&osdc->msgpool_op_reply); +} +EXPORT_SYMBOL(ceph_osdc_stop); + +/* + * Read some contiguous pages. If we cross a stripe boundary, shorten + * *plen. Return number of bytes read, or error. + */ +int ceph_osdc_readpages(struct ceph_osd_client *osdc, + struct ceph_vino vino, struct ceph_file_layout *layout, + u64 off, u64 *plen, + u32 truncate_seq, u64 truncate_size, + struct page **pages, int num_pages) +{ + struct ceph_osd_request *req; + int rc = 0; + + dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino, + vino.snap, off, *plen); + req = ceph_osdc_new_request(osdc, layout, vino, off, plen, + CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, + NULL, 0, truncate_seq, truncate_size, NULL, + false, 1); + if (!req) + return -ENOMEM; + + /* it may be a short read due to an object boundary */ + req->r_pages = pages; + + dout("readpages final extent is %llu~%llu (%d pages)\n", + off, *plen, req->r_num_pages); + + rc = ceph_osdc_start_request(osdc, req, false); + if (!rc) + rc = ceph_osdc_wait_request(osdc, req); + + ceph_osdc_put_request(req); + dout("readpages result %d\n", rc); + return rc; +} +EXPORT_SYMBOL(ceph_osdc_readpages); + +/* + * do a synchronous write on N pages + */ +int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, + struct ceph_file_layout *layout, + struct ceph_snap_context *snapc, + u64 off, u64 len, + u32 truncate_seq, u64 truncate_size, + struct timespec *mtime, + struct page **pages, int num_pages, + int flags, int do_sync, bool nofail) +{ + struct ceph_osd_request *req; + int rc = 0; + + BUG_ON(vino.snap != CEPH_NOSNAP); + req = ceph_osdc_new_request(osdc, layout, vino, off, &len, + CEPH_OSD_OP_WRITE, + flags | CEPH_OSD_FLAG_ONDISK | + CEPH_OSD_FLAG_WRITE, + snapc, do_sync, + truncate_seq, truncate_size, mtime, + nofail, 1); + if (!req) + return -ENOMEM; + + /* it may be a short write due to an object boundary */ + req->r_pages = pages; + dout("writepages %llu~%llu (%d pages)\n", off, len, + req->r_num_pages); + + rc = ceph_osdc_start_request(osdc, req, nofail); + if (!rc) + rc = ceph_osdc_wait_request(osdc, req); + + ceph_osdc_put_request(req); + if (rc == 0) + rc = len; + dout("writepages result %d\n", rc); + return rc; +} +EXPORT_SYMBOL(ceph_osdc_writepages); + +/* + * handle incoming message + */ +static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_osd *osd = con->private; + struct ceph_osd_client *osdc; + int type = le16_to_cpu(msg->hdr.type); + + if (!osd) + goto out; + osdc = osd->o_osdc; + + switch (type) { + case CEPH_MSG_OSD_MAP: + ceph_osdc_handle_map(osdc, msg); + break; + case CEPH_MSG_OSD_OPREPLY: + handle_reply(osdc, msg, con); + break; + + default: + pr_err("received unknown message type %d %s\n", type, + ceph_msg_type_name(type)); + } +out: + ceph_msg_put(msg); +} + +/* + * lookup and return message for incoming reply. set up reply message + * pages. + */ +static struct ceph_msg *get_reply(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) +{ + struct ceph_osd *osd = con->private; + struct ceph_osd_client *osdc = osd->o_osdc; + struct ceph_msg *m; + struct ceph_osd_request *req; + int front = le32_to_cpu(hdr->front_len); + int data_len = le32_to_cpu(hdr->data_len); + u64 tid; + + tid = le64_to_cpu(hdr->tid); + mutex_lock(&osdc->request_mutex); + req = __lookup_request(osdc, tid); + if (!req) { + *skip = 1; + m = NULL; + pr_info("get_reply unknown tid %llu from osd%d\n", tid, + osd->o_osd); + goto out; + } + + if (req->r_con_filling_msg) { + dout("get_reply revoking msg %p from old con %p\n", + req->r_reply, req->r_con_filling_msg); + ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); + ceph_con_put(req->r_con_filling_msg); + req->r_con_filling_msg = NULL; + } + + if (front > req->r_reply->front.iov_len) { + pr_warning("get_reply front %d > preallocated %d\n", + front, (int)req->r_reply->front.iov_len); + m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS); + if (!m) + goto out; + ceph_msg_put(req->r_reply); + req->r_reply = m; + } + m = ceph_msg_get(req->r_reply); + + if (data_len > 0) { + unsigned data_off = le16_to_cpu(hdr->data_off); + int want = calc_pages_for(data_off & ~PAGE_MASK, data_len); + + if (unlikely(req->r_num_pages < want)) { + pr_warning("tid %lld reply %d > expected %d pages\n", + tid, want, m->nr_pages); + *skip = 1; + ceph_msg_put(m); + m = NULL; + goto out; + } + m->pages = req->r_pages; + m->nr_pages = req->r_num_pages; +#ifdef CONFIG_BLOCK + m->bio = req->r_bio; +#endif + } + *skip = 0; + req->r_con_filling_msg = ceph_con_get(con); + dout("get_reply tid %lld %p\n", tid, m); + +out: + mutex_unlock(&osdc->request_mutex); + return m; + +} + +static struct ceph_msg *alloc_msg(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) +{ + struct ceph_osd *osd = con->private; + int type = le16_to_cpu(hdr->type); + int front = le32_to_cpu(hdr->front_len); + + switch (type) { + case CEPH_MSG_OSD_MAP: + return ceph_msg_new(type, front, GFP_NOFS); + case CEPH_MSG_OSD_OPREPLY: + return get_reply(con, hdr, skip); + default: + pr_info("alloc_msg unexpected msg type %d from osd%d\n", type, + osd->o_osd); + *skip = 1; + return NULL; + } +} + +/* + * Wrappers to refcount containing ceph_osd struct + */ +static struct ceph_connection *get_osd_con(struct ceph_connection *con) +{ + struct ceph_osd *osd = con->private; + if (get_osd(osd)) + return con; + return NULL; +} + +static void put_osd_con(struct ceph_connection *con) +{ + struct ceph_osd *osd = con->private; + put_osd(osd); +} + +/* + * authentication + */ +static int get_authorizer(struct ceph_connection *con, + void **buf, int *len, int *proto, + void **reply_buf, int *reply_len, int force_new) +{ + struct ceph_osd *o = con->private; + struct ceph_osd_client *osdc = o->o_osdc; + struct ceph_auth_client *ac = osdc->client->monc.auth; + int ret = 0; + + if (force_new && o->o_authorizer) { + ac->ops->destroy_authorizer(ac, o->o_authorizer); + o->o_authorizer = NULL; + } + if (o->o_authorizer == NULL) { + ret = ac->ops->create_authorizer( + ac, CEPH_ENTITY_TYPE_OSD, + &o->o_authorizer, + &o->o_authorizer_buf, + &o->o_authorizer_buf_len, + &o->o_authorizer_reply_buf, + &o->o_authorizer_reply_buf_len); + if (ret) + return ret; + } + + *proto = ac->protocol; + *buf = o->o_authorizer_buf; + *len = o->o_authorizer_buf_len; + *reply_buf = o->o_authorizer_reply_buf; + *reply_len = o->o_authorizer_reply_buf_len; + return 0; +} + + +static int verify_authorizer_reply(struct ceph_connection *con, int len) +{ + struct ceph_osd *o = con->private; + struct ceph_osd_client *osdc = o->o_osdc; + struct ceph_auth_client *ac = osdc->client->monc.auth; + + return ac->ops->verify_authorizer_reply(ac, o->o_authorizer, len); +} + +static int invalidate_authorizer(struct ceph_connection *con) +{ + struct ceph_osd *o = con->private; + struct ceph_osd_client *osdc = o->o_osdc; + struct ceph_auth_client *ac = osdc->client->monc.auth; + + if (ac->ops->invalidate_authorizer) + ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); + + return ceph_monc_validate_auth(&osdc->client->monc); +} + +static const struct ceph_connection_operations osd_con_ops = { + .get = get_osd_con, + .put = put_osd_con, + .dispatch = dispatch, + .get_authorizer = get_authorizer, + .verify_authorizer_reply = verify_authorizer_reply, + .invalidate_authorizer = invalidate_authorizer, + .alloc_msg = alloc_msg, + .fault = osd_reset, +}; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c new file mode 100644 index 000000000000..d73f3f6efa36 --- /dev/null +++ b/net/ceph/osdmap.c @@ -0,0 +1,1128 @@ + +#include + +#include +#include +#include + +#include +#include +#include +#include +#include + +char *ceph_osdmap_state_str(char *str, int len, int state) +{ + int flag = 0; + + if (!len) + goto done; + + *str = '\0'; + if (state) { + if (state & CEPH_OSD_EXISTS) { + snprintf(str, len, "exists"); + flag = 1; + } + if (state & CEPH_OSD_UP) { + snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""), + "up"); + flag = 1; + } + } else { + snprintf(str, len, "doesn't exist"); + } +done: + return str; +} + +/* maps */ + +static int calc_bits_of(unsigned t) +{ + int b = 0; + while (t) { + t = t >> 1; + b++; + } + return b; +} + +/* + * the foo_mask is the smallest value 2^n-1 that is >= foo. + */ +static void calc_pg_masks(struct ceph_pg_pool_info *pi) +{ + pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1; + pi->pgp_num_mask = + (1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1; + pi->lpg_num_mask = + (1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1; + pi->lpgp_num_mask = + (1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1; +} + +/* + * decode crush map + */ +static int crush_decode_uniform_bucket(void **p, void *end, + struct crush_bucket_uniform *b) +{ + dout("crush_decode_uniform_bucket %p to %p\n", *p, end); + ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad); + b->item_weight = ceph_decode_32(p); + return 0; +bad: + return -EINVAL; +} + +static int crush_decode_list_bucket(void **p, void *end, + struct crush_bucket_list *b) +{ + int j; + dout("crush_decode_list_bucket %p to %p\n", *p, end); + b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->item_weights == NULL) + return -ENOMEM; + b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->sum_weights == NULL) + return -ENOMEM; + ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); + for (j = 0; j < b->h.size; j++) { + b->item_weights[j] = ceph_decode_32(p); + b->sum_weights[j] = ceph_decode_32(p); + } + return 0; +bad: + return -EINVAL; +} + +static int crush_decode_tree_bucket(void **p, void *end, + struct crush_bucket_tree *b) +{ + int j; + dout("crush_decode_tree_bucket %p to %p\n", *p, end); + ceph_decode_32_safe(p, end, b->num_nodes, bad); + b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS); + if (b->node_weights == NULL) + return -ENOMEM; + ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad); + for (j = 0; j < b->num_nodes; j++) + b->node_weights[j] = ceph_decode_32(p); + return 0; +bad: + return -EINVAL; +} + +static int crush_decode_straw_bucket(void **p, void *end, + struct crush_bucket_straw *b) +{ + int j; + dout("crush_decode_straw_bucket %p to %p\n", *p, end); + b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->item_weights == NULL) + return -ENOMEM; + b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->straws == NULL) + return -ENOMEM; + ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); + for (j = 0; j < b->h.size; j++) { + b->item_weights[j] = ceph_decode_32(p); + b->straws[j] = ceph_decode_32(p); + } + return 0; +bad: + return -EINVAL; +} + +static struct crush_map *crush_decode(void *pbyval, void *end) +{ + struct crush_map *c; + int err = -EINVAL; + int i, j; + void **p = &pbyval; + void *start = pbyval; + u32 magic; + + dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); + + c = kzalloc(sizeof(*c), GFP_NOFS); + if (c == NULL) + return ERR_PTR(-ENOMEM); + + ceph_decode_need(p, end, 4*sizeof(u32), bad); + magic = ceph_decode_32(p); + if (magic != CRUSH_MAGIC) { + pr_err("crush_decode magic %x != current %x\n", + (unsigned)magic, (unsigned)CRUSH_MAGIC); + goto bad; + } + c->max_buckets = ceph_decode_32(p); + c->max_rules = ceph_decode_32(p); + c->max_devices = ceph_decode_32(p); + + c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS); + if (c->device_parents == NULL) + goto badmem; + c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS); + if (c->bucket_parents == NULL) + goto badmem; + + c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS); + if (c->buckets == NULL) + goto badmem; + c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS); + if (c->rules == NULL) + goto badmem; + + /* buckets */ + for (i = 0; i < c->max_buckets; i++) { + int size = 0; + u32 alg; + struct crush_bucket *b; + + ceph_decode_32_safe(p, end, alg, bad); + if (alg == 0) { + c->buckets[i] = NULL; + continue; + } + dout("crush_decode bucket %d off %x %p to %p\n", + i, (int)(*p-start), *p, end); + + switch (alg) { + case CRUSH_BUCKET_UNIFORM: + size = sizeof(struct crush_bucket_uniform); + break; + case CRUSH_BUCKET_LIST: + size = sizeof(struct crush_bucket_list); + break; + case CRUSH_BUCKET_TREE: + size = sizeof(struct crush_bucket_tree); + break; + case CRUSH_BUCKET_STRAW: + size = sizeof(struct crush_bucket_straw); + break; + default: + err = -EINVAL; + goto bad; + } + BUG_ON(size == 0); + b = c->buckets[i] = kzalloc(size, GFP_NOFS); + if (b == NULL) + goto badmem; + + ceph_decode_need(p, end, 4*sizeof(u32), bad); + b->id = ceph_decode_32(p); + b->type = ceph_decode_16(p); + b->alg = ceph_decode_8(p); + b->hash = ceph_decode_8(p); + b->weight = ceph_decode_32(p); + b->size = ceph_decode_32(p); + + dout("crush_decode bucket size %d off %x %p to %p\n", + b->size, (int)(*p-start), *p, end); + + b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); + if (b->items == NULL) + goto badmem; + b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS); + if (b->perm == NULL) + goto badmem; + b->perm_n = 0; + + ceph_decode_need(p, end, b->size*sizeof(u32), bad); + for (j = 0; j < b->size; j++) + b->items[j] = ceph_decode_32(p); + + switch (b->alg) { + case CRUSH_BUCKET_UNIFORM: + err = crush_decode_uniform_bucket(p, end, + (struct crush_bucket_uniform *)b); + if (err < 0) + goto bad; + break; + case CRUSH_BUCKET_LIST: + err = crush_decode_list_bucket(p, end, + (struct crush_bucket_list *)b); + if (err < 0) + goto bad; + break; + case CRUSH_BUCKET_TREE: + err = crush_decode_tree_bucket(p, end, + (struct crush_bucket_tree *)b); + if (err < 0) + goto bad; + break; + case CRUSH_BUCKET_STRAW: + err = crush_decode_straw_bucket(p, end, + (struct crush_bucket_straw *)b); + if (err < 0) + goto bad; + break; + } + } + + /* rules */ + dout("rule vec is %p\n", c->rules); + for (i = 0; i < c->max_rules; i++) { + u32 yes; + struct crush_rule *r; + + ceph_decode_32_safe(p, end, yes, bad); + if (!yes) { + dout("crush_decode NO rule %d off %x %p to %p\n", + i, (int)(*p-start), *p, end); + c->rules[i] = NULL; + continue; + } + + dout("crush_decode rule %d off %x %p to %p\n", + i, (int)(*p-start), *p, end); + + /* len */ + ceph_decode_32_safe(p, end, yes, bad); +#if BITS_PER_LONG == 32 + err = -EINVAL; + if (yes > ULONG_MAX / sizeof(struct crush_rule_step)) + goto bad; +#endif + r = c->rules[i] = kmalloc(sizeof(*r) + + yes*sizeof(struct crush_rule_step), + GFP_NOFS); + if (r == NULL) + goto badmem; + dout(" rule %d is at %p\n", i, r); + r->len = yes; + ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */ + ceph_decode_need(p, end, r->len*3*sizeof(u32), bad); + for (j = 0; j < r->len; j++) { + r->steps[j].op = ceph_decode_32(p); + r->steps[j].arg1 = ceph_decode_32(p); + r->steps[j].arg2 = ceph_decode_32(p); + } + } + + /* ignore trailing name maps. */ + + dout("crush_decode success\n"); + return c; + +badmem: + err = -ENOMEM; +bad: + dout("crush_decode fail %d\n", err); + crush_destroy(c); + return ERR_PTR(err); +} + +/* + * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid + * to a set of osds) + */ +static int pgid_cmp(struct ceph_pg l, struct ceph_pg r) +{ + u64 a = *(u64 *)&l; + u64 b = *(u64 *)&r; + + if (a < b) + return -1; + if (a > b) + return 1; + return 0; +} + +static int __insert_pg_mapping(struct ceph_pg_mapping *new, + struct rb_root *root) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct ceph_pg_mapping *pg = NULL; + int c; + + while (*p) { + parent = *p; + pg = rb_entry(parent, struct ceph_pg_mapping, node); + c = pgid_cmp(new->pgid, pg->pgid); + if (c < 0) + p = &(*p)->rb_left; + else if (c > 0) + p = &(*p)->rb_right; + else + return -EEXIST; + } + + rb_link_node(&new->node, parent, p); + rb_insert_color(&new->node, root); + return 0; +} + +static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, + struct ceph_pg pgid) +{ + struct rb_node *n = root->rb_node; + struct ceph_pg_mapping *pg; + int c; + + while (n) { + pg = rb_entry(n, struct ceph_pg_mapping, node); + c = pgid_cmp(pgid, pg->pgid); + if (c < 0) + n = n->rb_left; + else if (c > 0) + n = n->rb_right; + else + return pg; + } + return NULL; +} + +/* + * rbtree of pg pool info + */ +static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct ceph_pg_pool_info *pi = NULL; + + while (*p) { + parent = *p; + pi = rb_entry(parent, struct ceph_pg_pool_info, node); + if (new->id < pi->id) + p = &(*p)->rb_left; + else if (new->id > pi->id) + p = &(*p)->rb_right; + else + return -EEXIST; + } + + rb_link_node(&new->node, parent, p); + rb_insert_color(&new->node, root); + return 0; +} + +static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) +{ + struct ceph_pg_pool_info *pi; + struct rb_node *n = root->rb_node; + + while (n) { + pi = rb_entry(n, struct ceph_pg_pool_info, node); + if (id < pi->id) + n = n->rb_left; + else if (id > pi->id) + n = n->rb_right; + else + return pi; + } + return NULL; +} + +int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) +{ + struct rb_node *rbp; + + for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) { + struct ceph_pg_pool_info *pi = + rb_entry(rbp, struct ceph_pg_pool_info, node); + if (pi->name && strcmp(pi->name, name) == 0) + return pi->id; + } + return -ENOENT; +} +EXPORT_SYMBOL(ceph_pg_poolid_by_name); + +static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) +{ + rb_erase(&pi->node, root); + kfree(pi->name); + kfree(pi); +} + +static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) +{ + unsigned n, m; + + ceph_decode_copy(p, &pi->v, sizeof(pi->v)); + calc_pg_masks(pi); + + /* num_snaps * snap_info_t */ + n = le32_to_cpu(pi->v.num_snaps); + while (n--) { + ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) + + sizeof(struct ceph_timespec), bad); + *p += sizeof(u64) + /* key */ + 1 + sizeof(u64) + /* u8, snapid */ + sizeof(struct ceph_timespec); + m = ceph_decode_32(p); /* snap name */ + *p += m; + } + + *p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2; + return 0; + +bad: + return -EINVAL; +} + +static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) +{ + struct ceph_pg_pool_info *pi; + u32 num, len, pool; + + ceph_decode_32_safe(p, end, num, bad); + dout(" %d pool names\n", num); + while (num--) { + ceph_decode_32_safe(p, end, pool, bad); + ceph_decode_32_safe(p, end, len, bad); + dout(" pool %d len %d\n", pool, len); + pi = __lookup_pg_pool(&map->pg_pools, pool); + if (pi) { + kfree(pi->name); + pi->name = kmalloc(len + 1, GFP_NOFS); + if (pi->name) { + memcpy(pi->name, *p, len); + pi->name[len] = '\0'; + dout(" name is %s\n", pi->name); + } + } + *p += len; + } + return 0; + +bad: + return -EINVAL; +} + +/* + * osd map + */ +void ceph_osdmap_destroy(struct ceph_osdmap *map) +{ + dout("osdmap_destroy %p\n", map); + if (map->crush) + crush_destroy(map->crush); + while (!RB_EMPTY_ROOT(&map->pg_temp)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_temp), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_temp); + kfree(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_pools)) { + struct ceph_pg_pool_info *pi = + rb_entry(rb_first(&map->pg_pools), + struct ceph_pg_pool_info, node); + __remove_pg_pool(&map->pg_pools, pi); + } + kfree(map->osd_state); + kfree(map->osd_weight); + kfree(map->osd_addr); + kfree(map); +} + +/* + * adjust max osd value. reallocate arrays. + */ +static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) +{ + u8 *state; + struct ceph_entity_addr *addr; + u32 *weight; + + state = kcalloc(max, sizeof(*state), GFP_NOFS); + addr = kcalloc(max, sizeof(*addr), GFP_NOFS); + weight = kcalloc(max, sizeof(*weight), GFP_NOFS); + if (state == NULL || addr == NULL || weight == NULL) { + kfree(state); + kfree(addr); + kfree(weight); + return -ENOMEM; + } + + /* copy old? */ + if (map->osd_state) { + memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); + memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); + memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); + kfree(map->osd_state); + kfree(map->osd_addr); + kfree(map->osd_weight); + } + + map->osd_state = state; + map->osd_weight = weight; + map->osd_addr = addr; + map->max_osd = max; + return 0; +} + +/* + * decode a full map. + */ +struct ceph_osdmap *osdmap_decode(void **p, void *end) +{ + struct ceph_osdmap *map; + u16 version; + u32 len, max, i; + u8 ev; + int err = -EINVAL; + void *start = *p; + struct ceph_pg_pool_info *pi; + + dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p)); + + map = kzalloc(sizeof(*map), GFP_NOFS); + if (map == NULL) + return ERR_PTR(-ENOMEM); + map->pg_temp = RB_ROOT; + + ceph_decode_16_safe(p, end, version, bad); + if (version > CEPH_OSDMAP_VERSION) { + pr_warning("got unknown v %d > %d of osdmap\n", version, + CEPH_OSDMAP_VERSION); + goto bad; + } + + ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad); + ceph_decode_copy(p, &map->fsid, sizeof(map->fsid)); + map->epoch = ceph_decode_32(p); + ceph_decode_copy(p, &map->created, sizeof(map->created)); + ceph_decode_copy(p, &map->modified, sizeof(map->modified)); + + ceph_decode_32_safe(p, end, max, bad); + while (max--) { + ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); + pi = kzalloc(sizeof(*pi), GFP_NOFS); + if (!pi) + goto bad; + pi->id = ceph_decode_32(p); + ev = ceph_decode_8(p); /* encoding version */ + if (ev > CEPH_PG_POOL_VERSION) { + pr_warning("got unknown v %d > %d of ceph_pg_pool\n", + ev, CEPH_PG_POOL_VERSION); + kfree(pi); + goto bad; + } + err = __decode_pool(p, end, pi); + if (err < 0) + goto bad; + __insert_pg_pool(&map->pg_pools, pi); + } + + if (version >= 5 && __decode_pool_names(p, end, map) < 0) + goto bad; + + ceph_decode_32_safe(p, end, map->pool_max, bad); + + ceph_decode_32_safe(p, end, map->flags, bad); + + max = ceph_decode_32(p); + + /* (re)alloc osd arrays */ + err = osdmap_set_max_osd(map, max); + if (err < 0) + goto bad; + dout("osdmap_decode max_osd = %d\n", map->max_osd); + + /* osds */ + err = -EINVAL; + ceph_decode_need(p, end, 3*sizeof(u32) + + map->max_osd*(1 + sizeof(*map->osd_weight) + + sizeof(*map->osd_addr)), bad); + *p += 4; /* skip length field (should match max) */ + ceph_decode_copy(p, map->osd_state, map->max_osd); + + *p += 4; /* skip length field (should match max) */ + for (i = 0; i < map->max_osd; i++) + map->osd_weight[i] = ceph_decode_32(p); + + *p += 4; /* skip length field (should match max) */ + ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr)); + for (i = 0; i < map->max_osd; i++) + ceph_decode_addr(&map->osd_addr[i]); + + /* pg_temp */ + ceph_decode_32_safe(p, end, len, bad); + for (i = 0; i < len; i++) { + int n, j; + struct ceph_pg pgid; + struct ceph_pg_mapping *pg; + + ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); + ceph_decode_copy(p, &pgid, sizeof(pgid)); + n = ceph_decode_32(p); + ceph_decode_need(p, end, n * sizeof(u32), bad); + err = -ENOMEM; + pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); + if (!pg) + goto bad; + pg->pgid = pgid; + pg->len = n; + for (j = 0; j < n; j++) + pg->osds[j] = ceph_decode_32(p); + + err = __insert_pg_mapping(pg, &map->pg_temp); + if (err) + goto bad; + dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len); + } + + /* crush */ + ceph_decode_32_safe(p, end, len, bad); + dout("osdmap_decode crush len %d from off 0x%x\n", len, + (int)(*p - start)); + ceph_decode_need(p, end, len, bad); + map->crush = crush_decode(*p, end); + *p += len; + if (IS_ERR(map->crush)) { + err = PTR_ERR(map->crush); + map->crush = NULL; + goto bad; + } + + /* ignore the rest of the map */ + *p = end; + + dout("osdmap_decode done %p %p\n", *p, end); + return map; + +bad: + dout("osdmap_decode fail\n"); + ceph_osdmap_destroy(map); + return ERR_PTR(err); +} + +/* + * decode and apply an incremental map update. + */ +struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, + struct ceph_osdmap *map, + struct ceph_messenger *msgr) +{ + struct crush_map *newcrush = NULL; + struct ceph_fsid fsid; + u32 epoch = 0; + struct ceph_timespec modified; + u32 len, pool; + __s32 new_pool_max, new_flags, max; + void *start = *p; + int err = -EINVAL; + u16 version; + struct rb_node *rbp; + + ceph_decode_16_safe(p, end, version, bad); + if (version > CEPH_OSDMAP_INC_VERSION) { + pr_warning("got unknown v %d > %d of inc osdmap\n", version, + CEPH_OSDMAP_INC_VERSION); + goto bad; + } + + ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32), + bad); + ceph_decode_copy(p, &fsid, sizeof(fsid)); + epoch = ceph_decode_32(p); + BUG_ON(epoch != map->epoch+1); + ceph_decode_copy(p, &modified, sizeof(modified)); + new_pool_max = ceph_decode_32(p); + new_flags = ceph_decode_32(p); + + /* full map? */ + ceph_decode_32_safe(p, end, len, bad); + if (len > 0) { + dout("apply_incremental full map len %d, %p to %p\n", + len, *p, end); + return osdmap_decode(p, min(*p+len, end)); + } + + /* new crush? */ + ceph_decode_32_safe(p, end, len, bad); + if (len > 0) { + dout("apply_incremental new crush map len %d, %p to %p\n", + len, *p, end); + newcrush = crush_decode(*p, min(*p+len, end)); + if (IS_ERR(newcrush)) + return ERR_CAST(newcrush); + *p += len; + } + + /* new flags? */ + if (new_flags >= 0) + map->flags = new_flags; + if (new_pool_max >= 0) + map->pool_max = new_pool_max; + + ceph_decode_need(p, end, 5*sizeof(u32), bad); + + /* new max? */ + max = ceph_decode_32(p); + if (max >= 0) { + err = osdmap_set_max_osd(map, max); + if (err < 0) + goto bad; + } + + map->epoch++; + map->modified = map->modified; + if (newcrush) { + if (map->crush) + crush_destroy(map->crush); + map->crush = newcrush; + newcrush = NULL; + } + + /* new_pool */ + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + __u8 ev; + struct ceph_pg_pool_info *pi; + + ceph_decode_32_safe(p, end, pool, bad); + ceph_decode_need(p, end, 1 + sizeof(pi->v), bad); + ev = ceph_decode_8(p); /* encoding version */ + if (ev > CEPH_PG_POOL_VERSION) { + pr_warning("got unknown v %d > %d of ceph_pg_pool\n", + ev, CEPH_PG_POOL_VERSION); + goto bad; + } + pi = __lookup_pg_pool(&map->pg_pools, pool); + if (!pi) { + pi = kzalloc(sizeof(*pi), GFP_NOFS); + if (!pi) { + err = -ENOMEM; + goto bad; + } + pi->id = pool; + __insert_pg_pool(&map->pg_pools, pi); + } + err = __decode_pool(p, end, pi); + if (err < 0) + goto bad; + } + if (version >= 5 && __decode_pool_names(p, end, map) < 0) + goto bad; + + /* old_pool */ + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + struct ceph_pg_pool_info *pi; + + ceph_decode_32_safe(p, end, pool, bad); + pi = __lookup_pg_pool(&map->pg_pools, pool); + if (pi) + __remove_pg_pool(&map->pg_pools, pi); + } + + /* new_up */ + err = -EINVAL; + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + u32 osd; + struct ceph_entity_addr addr; + ceph_decode_32_safe(p, end, osd, bad); + ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad); + ceph_decode_addr(&addr); + pr_info("osd%d up\n", osd); + BUG_ON(osd >= map->max_osd); + map->osd_state[osd] |= CEPH_OSD_UP; + map->osd_addr[osd] = addr; + } + + /* new_down */ + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + u32 osd; + ceph_decode_32_safe(p, end, osd, bad); + (*p)++; /* clean flag */ + pr_info("osd%d down\n", osd); + if (osd < map->max_osd) + map->osd_state[osd] &= ~CEPH_OSD_UP; + } + + /* new_weight */ + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + u32 osd, off; + ceph_decode_need(p, end, sizeof(u32)*2, bad); + osd = ceph_decode_32(p); + off = ceph_decode_32(p); + pr_info("osd%d weight 0x%x %s\n", osd, off, + off == CEPH_OSD_IN ? "(in)" : + (off == CEPH_OSD_OUT ? "(out)" : "")); + if (osd < map->max_osd) + map->osd_weight[osd] = off; + } + + /* new_pg_temp */ + rbp = rb_first(&map->pg_temp); + ceph_decode_32_safe(p, end, len, bad); + while (len--) { + struct ceph_pg_mapping *pg; + int j; + struct ceph_pg pgid; + u32 pglen; + ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); + ceph_decode_copy(p, &pgid, sizeof(pgid)); + pglen = ceph_decode_32(p); + + /* remove any? */ + while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping, + node)->pgid, pgid) <= 0) { + struct ceph_pg_mapping *cur = + rb_entry(rbp, struct ceph_pg_mapping, node); + + rbp = rb_next(rbp); + dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid); + rb_erase(&cur->node, &map->pg_temp); + kfree(cur); + } + + if (pglen) { + /* insert */ + ceph_decode_need(p, end, pglen*sizeof(u32), bad); + pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); + if (!pg) { + err = -ENOMEM; + goto bad; + } + pg->pgid = pgid; + pg->len = pglen; + for (j = 0; j < pglen; j++) + pg->osds[j] = ceph_decode_32(p); + err = __insert_pg_mapping(pg, &map->pg_temp); + if (err) { + kfree(pg); + goto bad; + } + dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, + pglen); + } + } + while (rbp) { + struct ceph_pg_mapping *cur = + rb_entry(rbp, struct ceph_pg_mapping, node); + + rbp = rb_next(rbp); + dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid); + rb_erase(&cur->node, &map->pg_temp); + kfree(cur); + } + + /* ignore the rest */ + *p = end; + return map; + +bad: + pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n", + epoch, (int)(*p - start), *p, start, end); + print_hex_dump(KERN_DEBUG, "osdmap: ", + DUMP_PREFIX_OFFSET, 16, 1, + start, end - start, true); + if (newcrush) + crush_destroy(newcrush); + return ERR_PTR(err); +} + + + + +/* + * calculate file layout from given offset, length. + * fill in correct oid, logical length, and object extent + * offset, length. + * + * for now, we write only a single su, until we can + * pass a stride back to the caller. + */ +void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, + u64 off, u64 *plen, + u64 *ono, + u64 *oxoff, u64 *oxlen) +{ + u32 osize = le32_to_cpu(layout->fl_object_size); + u32 su = le32_to_cpu(layout->fl_stripe_unit); + u32 sc = le32_to_cpu(layout->fl_stripe_count); + u32 bl, stripeno, stripepos, objsetno; + u32 su_per_object; + u64 t, su_offset; + + dout("mapping %llu~%llu osize %u fl_su %u\n", off, *plen, + osize, su); + su_per_object = osize / su; + dout("osize %u / su %u = su_per_object %u\n", osize, su, + su_per_object); + + BUG_ON((su & ~PAGE_MASK) != 0); + /* bl = *off / su; */ + t = off; + do_div(t, su); + bl = t; + dout("off %llu / su %u = bl %u\n", off, su, bl); + + stripeno = bl / sc; + stripepos = bl % sc; + objsetno = stripeno / su_per_object; + + *ono = objsetno * sc + stripepos; + dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono); + + /* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ + t = off; + su_offset = do_div(t, su); + *oxoff = su_offset + (stripeno % su_per_object) * su; + + /* + * Calculate the length of the extent being written to the selected + * object. This is the minimum of the full length requested (plen) or + * the remainder of the current stripe being written to. + */ + *oxlen = min_t(u64, *plen, su - su_offset); + *plen = *oxlen; + + dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); +} +EXPORT_SYMBOL(ceph_calc_file_object_mapping); + +/* + * calculate an object layout (i.e. pgid) from an oid, + * file_layout, and osdmap + */ +int ceph_calc_object_layout(struct ceph_object_layout *ol, + const char *oid, + struct ceph_file_layout *fl, + struct ceph_osdmap *osdmap) +{ + unsigned num, num_mask; + struct ceph_pg pgid; + s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred); + int poolid = le32_to_cpu(fl->fl_pg_pool); + struct ceph_pg_pool_info *pool; + unsigned ps; + + BUG_ON(!osdmap); + + pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); + if (!pool) + return -EIO; + ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid)); + if (preferred >= 0) { + ps += preferred; + num = le32_to_cpu(pool->v.lpg_num); + num_mask = pool->lpg_num_mask; + } else { + num = le32_to_cpu(pool->v.pg_num); + num_mask = pool->pg_num_mask; + } + + pgid.ps = cpu_to_le16(ps); + pgid.preferred = cpu_to_le16(preferred); + pgid.pool = fl->fl_pg_pool; + if (preferred >= 0) + dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps, + (int)preferred); + else + dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps); + + ol->ol_pgid = pgid; + ol->ol_stripe_unit = fl->fl_object_stripe_unit; + return 0; +} +EXPORT_SYMBOL(ceph_calc_object_layout); + +/* + * Calculate raw osd vector for the given pgid. Return pointer to osd + * array, or NULL on failure. + */ +static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, + int *osds, int *num) +{ + struct ceph_pg_mapping *pg; + struct ceph_pg_pool_info *pool; + int ruleno; + unsigned poolid, ps, pps; + int preferred; + + /* pg_temp? */ + pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); + if (pg) { + *num = pg->len; + return pg->osds; + } + + /* crush */ + poolid = le32_to_cpu(pgid.pool); + ps = le16_to_cpu(pgid.ps); + preferred = (s16)le16_to_cpu(pgid.preferred); + + /* don't forcefeed bad device ids to crush */ + if (preferred >= osdmap->max_osd || + preferred >= osdmap->crush->max_devices) + preferred = -1; + + pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); + if (!pool) + return NULL; + ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset, + pool->v.type, pool->v.size); + if (ruleno < 0) { + pr_err("no crush rule pool %d ruleset %d type %d size %d\n", + poolid, pool->v.crush_ruleset, pool->v.type, + pool->v.size); + return NULL; + } + + if (preferred >= 0) + pps = ceph_stable_mod(ps, + le32_to_cpu(pool->v.lpgp_num), + pool->lpgp_num_mask); + else + pps = ceph_stable_mod(ps, + le32_to_cpu(pool->v.pgp_num), + pool->pgp_num_mask); + pps += poolid; + *num = crush_do_rule(osdmap->crush, ruleno, pps, osds, + min_t(int, pool->v.size, *num), + preferred, osdmap->osd_weight); + return osds; +} + +/* + * Return acting set for given pgid. + */ +int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, + int *acting) +{ + int rawosds[CEPH_PG_MAX_SIZE], *osds; + int i, o, num = CEPH_PG_MAX_SIZE; + + osds = calc_pg_raw(osdmap, pgid, rawosds, &num); + if (!osds) + return -1; + + /* primary is first up osd */ + o = 0; + for (i = 0; i < num; i++) + if (ceph_osd_is_up(osdmap, osds[i])) + acting[o++] = osds[i]; + return o; +} + +/* + * Return primary osd for given pgid, or -1 if none. + */ +int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid) +{ + int rawosds[CEPH_PG_MAX_SIZE], *osds; + int i, num = CEPH_PG_MAX_SIZE; + + osds = calc_pg_raw(osdmap, pgid, rawosds, &num); + if (!osds) + return -1; + + /* primary is first up osd */ + for (i = 0; i < num; i++) + if (ceph_osd_is_up(osdmap, osds[i])) + return osds[i]; + return -1; +} +EXPORT_SYMBOL(ceph_calc_pg_primary); diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c new file mode 100644 index 000000000000..3b146cfac182 --- /dev/null +++ b/net/ceph/pagelist.c @@ -0,0 +1,65 @@ + +#include +#include +#include +#include +#include + +static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl) +{ + struct page *page = list_entry(pl->head.prev, struct page, + lru); + kunmap(page); +} + +int ceph_pagelist_release(struct ceph_pagelist *pl) +{ + if (pl->mapped_tail) + ceph_pagelist_unmap_tail(pl); + + while (!list_empty(&pl->head)) { + struct page *page = list_first_entry(&pl->head, struct page, + lru); + list_del(&page->lru); + __free_page(page); + } + return 0; +} +EXPORT_SYMBOL(ceph_pagelist_release); + +static int ceph_pagelist_addpage(struct ceph_pagelist *pl) +{ + struct page *page = __page_cache_alloc(GFP_NOFS); + if (!page) + return -ENOMEM; + pl->room += PAGE_SIZE; + list_add_tail(&page->lru, &pl->head); + if (pl->mapped_tail) + ceph_pagelist_unmap_tail(pl); + pl->mapped_tail = kmap(page); + return 0; +} + +int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) +{ + while (pl->room < len) { + size_t bit = pl->room; + int ret; + + memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), + buf, bit); + pl->length += bit; + pl->room -= bit; + buf += bit; + len -= bit; + ret = ceph_pagelist_addpage(pl); + if (ret) + return ret; + } + + memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len); + pl->length += len; + pl->room -= len; + return 0; +} +EXPORT_SYMBOL(ceph_pagelist_append); diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c new file mode 100644 index 000000000000..54caf0687155 --- /dev/null +++ b/net/ceph/pagevec.c @@ -0,0 +1,223 @@ +#include + +#include +#include +#include +#include +#include +#include + +#include + +/* + * build a vector of user pages + */ +struct page **ceph_get_direct_page_vector(const char __user *data, + int num_pages, + loff_t off, size_t len) +{ + struct page **pages; + int rc; + + pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS); + if (!pages) + return ERR_PTR(-ENOMEM); + + down_read(¤t->mm->mmap_sem); + rc = get_user_pages(current, current->mm, (unsigned long)data, + num_pages, 0, 0, pages, NULL); + up_read(¤t->mm->mmap_sem); + if (rc < 0) + goto fail; + return pages; + +fail: + kfree(pages); + return ERR_PTR(rc); +} +EXPORT_SYMBOL(ceph_get_direct_page_vector); + +void ceph_put_page_vector(struct page **pages, int num_pages) +{ + int i; + + for (i = 0; i < num_pages; i++) + put_page(pages[i]); + kfree(pages); +} +EXPORT_SYMBOL(ceph_put_page_vector); + +void ceph_release_page_vector(struct page **pages, int num_pages) +{ + int i; + + for (i = 0; i < num_pages; i++) + __free_pages(pages[i], 0); + kfree(pages); +} +EXPORT_SYMBOL(ceph_release_page_vector); + +/* + * allocate a vector new pages + */ +struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags) +{ + struct page **pages; + int i; + + pages = kmalloc(sizeof(*pages) * num_pages, flags); + if (!pages) + return ERR_PTR(-ENOMEM); + for (i = 0; i < num_pages; i++) { + pages[i] = __page_cache_alloc(flags); + if (pages[i] == NULL) { + ceph_release_page_vector(pages, i); + return ERR_PTR(-ENOMEM); + } + } + return pages; +} +EXPORT_SYMBOL(ceph_alloc_page_vector); + +/* + * copy user data into a page vector + */ +int ceph_copy_user_to_page_vector(struct page **pages, + const char __user *data, + loff_t off, size_t len) +{ + int i = 0; + int po = off & ~PAGE_CACHE_MASK; + int left = len; + int l, bad; + + while (left > 0) { + l = min_t(int, PAGE_CACHE_SIZE-po, left); + bad = copy_from_user(page_address(pages[i]) + po, data, l); + if (bad == l) + return -EFAULT; + data += l - bad; + left -= l - bad; + po += l - bad; + if (po == PAGE_CACHE_SIZE) { + po = 0; + i++; + } + } + return len; +} +EXPORT_SYMBOL(ceph_copy_user_to_page_vector); + +int ceph_copy_to_page_vector(struct page **pages, + const char *data, + loff_t off, size_t len) +{ + int i = 0; + size_t po = off & ~PAGE_CACHE_MASK; + size_t left = len; + size_t l; + + while (left > 0) { + l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + memcpy(page_address(pages[i]) + po, data, l); + data += l; + left -= l; + po += l; + if (po == PAGE_CACHE_SIZE) { + po = 0; + i++; + } + } + return len; +} +EXPORT_SYMBOL(ceph_copy_to_page_vector); + +int ceph_copy_from_page_vector(struct page **pages, + char *data, + loff_t off, size_t len) +{ + int i = 0; + size_t po = off & ~PAGE_CACHE_MASK; + size_t left = len; + size_t l; + + while (left > 0) { + l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + memcpy(data, page_address(pages[i]) + po, l); + data += l; + left -= l; + po += l; + if (po == PAGE_CACHE_SIZE) { + po = 0; + i++; + } + } + return len; +} +EXPORT_SYMBOL(ceph_copy_from_page_vector); + +/* + * copy user data from a page vector into a user pointer + */ +int ceph_copy_page_vector_to_user(struct page **pages, + char __user *data, + loff_t off, size_t len) +{ + int i = 0; + int po = off & ~PAGE_CACHE_MASK; + int left = len; + int l, bad; + + while (left > 0) { + l = min_t(int, left, PAGE_CACHE_SIZE-po); + bad = copy_to_user(data, page_address(pages[i]) + po, l); + if (bad == l) + return -EFAULT; + data += l - bad; + left -= l - bad; + if (po) { + po += l - bad; + if (po == PAGE_CACHE_SIZE) + po = 0; + } + i++; + } + return len; +} +EXPORT_SYMBOL(ceph_copy_page_vector_to_user); + +/* + * Zero an extent within a page vector. Offset is relative to the + * start of the first page. + */ +void ceph_zero_page_vector_range(int off, int len, struct page **pages) +{ + int i = off >> PAGE_CACHE_SHIFT; + + off &= ~PAGE_CACHE_MASK; + + dout("zero_page_vector_page %u~%u\n", off, len); + + /* leading partial page? */ + if (off) { + int end = min((int)PAGE_CACHE_SIZE, off + len); + dout("zeroing %d %p head from %d\n", i, pages[i], + (int)off); + zero_user_segment(pages[i], off, end); + len -= (end - off); + i++; + } + while (len >= PAGE_CACHE_SIZE) { + dout("zeroing %d %p len=%d\n", i, pages[i], len); + zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); + len -= PAGE_CACHE_SIZE; + i++; + } + /* trailing partial page? */ + if (len) { + dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len); + zero_user_segment(pages[i], 0, len); + } +} +EXPORT_SYMBOL(ceph_zero_page_vector_range); + -- cgit v1.2.3