summaryrefslogtreecommitdiff
path: root/fs/gfs2/rgrp.c
AgeCommit message (Collapse)AuthorFilesLines
2018-06-13treewide: kmalloc() -> kmalloc_array()Kees Cook1-2/+3
The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-04GFS2: gfs2_free_extlen can return an extent that is too longBob Peterson1-1/+1
Function gfs2_free_extlen calculates the length of an extent of free blocks that may be reserved. The end pointer was calculated as end = start + bh->b_size but b_size is incorrect because the bitmap usually stops prior to the end of the buffer data on the last bitmap. What this means is that when you do a write, you can reserve a chunk of blocks that runs off the end of the last bitmap. For example, I've got a file system where there is only one bitmap for each rgrp, so ri_length==1. I saw cases in which iozone tried to do a big write, grabbed a large block reservation, chose rgrp 5464152, which has ri_data0 5464153 and ri_data 8188. So 5464153 + 8188 = 5472341 which is the end of the rgrp. When it grabbed a reservation it got back: 5470936, length 7229. But 5470936 + 7229 = 5478165. So the reservation starts inside the rgrp but runs 5824 blocks past the end of the bitmap. This patch fixes the calculation so it won't exceed the last bitmap. It also adds a BUG_ON to guard against overflows in the future. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2018-01-30gfs2: Add a few missing newlines in messagesAndreas Gruenbacher1-1/+1
Some of the info, warning, and error messages are missing their trailing newline. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2018-01-23GFS2: Log the reason for log flushes in every log headerBob Peterson1-1/+2
This patch just adds the capability for GFS2 to track which function called gfs2_log_flush. This should make it easier to diagnose problems based on the sequence of events found in the journals. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
2018-01-23GFS2: Introduce new gfs2_log_header_v2Bob Peterson1-1/+1
This patch adds a new structure called gfs2_log_header_v2 which is used to store expanded fields into previously unused areas of the log headers (i.e., this change is backwards compatible). Some of these are used for debug purposes so we can backtrack when problems occur. Others are reserved for future expansion. This patch is based on a prototype from Steve Whitehouse. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
2018-01-19Merge branch 'punch-hole' of ↵Bob Peterson1-0/+7
git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2.git
2018-01-17gfs2: Add gfs2_blk2rgrpd comment and fix incorrect useSteven Whitehouse1-0/+7
Document when to use gfs2_blk2rgrpd for "inexact" resource group matching. Based on that, fix an incorrect use of gfs2_blk2rgrpd in sweep_bh_for_rgrps. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-12-12gfs2: Add a crc field to resource group headersAndrew Price1-0/+5
Add the rg_crc field to store a crc32 of the gfs2_rgrp structure. This allows us to check resource group headers' integrity and removes the requirement to check them against the rindex entries in fsck. If this field is found to be zero, it should be ignored (or updated with an accurate value). Signed-off-by: Andrew Price <anprice@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-12-12gfs2: Add rindex fields to rgrp headersAndrew Price1-0/+5
Add rg_data0, rg_data and rg_bitbytes to struct gfs2_rgrp. The fields are identical to their counterparts in struct gfs2_rindex and are intended to reduce the use of the rindex. For now the fields are only written back as the in-memory equivalents in struct gfs2_rgrpd are set using values from the rindex. However, they are needed at this point so that userspace can make use of them, allowing a migration away from the rindex over time. The new fields take up previously reserved space which was explicitly zeroed on write so, in clusters with mixed kernels, these fields could get zeroed after being set and this should not be treated as an error. Signed-off-by: Andrew Price <anprice@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-12-12gfs2: Add a next-resource-group pointer to resource groupsAndrew Price1-1/+5
Add a new rg_skip field to struct gfs2_rgrp, replacing __pad. The rg_skip field has the following meaning: - If rg_skip is zero, it is considered unset and not useful. - If rg_skip is non-zero, its value will be the number of blocks between this rgrp's address and the next rgrp's address. This can be used as a hint by fsck.gfs2 when rebuilding a bad rindex, for example. This will provide less dependency on the rindex in future, and allow tools such as fsck.gfs2 to iterate the resource groups without keeping the rindex around. The field is updated in gfs2_rgrp_out() so that existing file systems will have it set. This means that any resource groups that aren't ever written will not be updated. The final rgrp is a special case as there is no next rgrp, so it will always have a rg_skip of 0 (unless the fs is extended). Before this patch, gfs2_rgrp_out() zeroes the __pad field explicitly, so the rg_skip field can get set back to 0 in cases where nodes with and without this patch are mixed in a cluster. In some cases, the field may bounce between being set by one node and then zeroed by another which may harm performance slightly, e.g. when two nodes create many small files. In testing this situation is rare but it becomes more likely as the filesystem fills up and there are fewer resource groups to choose from. The problem goes away when all nodes are running with this patch. Dipping into the space currently occupied by the rg_reserved field would have resulted in the same problem as it is also explicitly zeroed, so unfortunately there is no other way around it. Signed-off-by: Andrew Price <anprice@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-11-27GFS2: Combine gfs2_free_di with gfs2_free_uninit_diBob Peterson1-8/+2
Before this patch, function gfs2_free_di was 4 lines of code, and one of those lines was to call gfs2_free_uninit_di. Although unlikely, if function gfs2_free_uninit_di encountered an error finding the block to be freed, the error was silently ignored by the caller, which went ahead and improperly did a quota-change operation and meta_wipe despite the error. This patch combines the two functions into one to make the code more readable and fixes the bug by returning from the combined function before it takes those next incorrect steps. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-30GFS2: Fix gl_object warningsAndreas Gruenbacher1-1/+1
The following cleanup is needed to avoid spilling the syslog with false warnings. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-09GFS2: Don't bother trying to add rgrps to the lru listBob Peterson1-1/+0
This patch removes a call to gfs2_glock_add_to_lru from function gfs2_clear_rgrpd. The call is just a waste of time because as soon as it adds it to the lru_list, the call to gfs2_glock_put takes it back off again. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-07-05gfs2: Protect gl->gl_object by spin lockAndreas Gruenbacher1-4/+2
Put all remaining accesses to gl->gl_object under the gl->gl_lockref.lock spinlock to prevent races. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-04-19GFS2: Non-recursive deleteBob Peterson1-7/+0
Implement truncate/delete as a non-recursive algorithm. The older algorithm was implemented with recursion to strip off each layer at a time (going by height, starting with the maximum height. This version tries to do the same thing but without recursion, and without needing to allocate new structures or lists in memory. For example, say you want to truncate a very large file to 1 byte, and its end-of-file metapath is: 0.505.463.428. The starting metapath would be 0.0.0.0. Since it's a truncate to non-zero, it needs to preserve that byte, and all metadata pointing to it. So it would start at 0.0.0.0, look up all its metadata buffers, then free all data blocks pointed to at the highest level. After that buffer is "swept", it moves on to 0.0.0.1, then 0.0.0.2, etc., reading in buffers and sweeping them clean. When it gets to the end of the 0.0.0 metadata buffer (for 4K blocks the last valid one is 0.0.0.508), it backs up to the previous height and starts working on 0.0.1.0, then 0.0.1.1, and so forth. After it reaches the end and sweeps 0.0.1.508, it continues with 0.0.2.0, and so on. When that height is exhausted, and it reaches 0.0.508.508 it backs up another level, to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep marching backwards and forwards through the metadata until it's all swept clean. Once it has all the data blocks freed, it lowers the strip height, and begins the process all over again, but with one less height. This time it sweeps 0.0.0 through 0.505.463. When that's clean, it lowers the strip height again and works to free 0.505. Eventually it strips the lowest height, 0. For a delete or truncate to 0, all metadata for all heights of 0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would be preserved. This isn't much different from normal integer incrementing, where an integer gets incremented from 0000 (0.0.0.0) to 3021 (3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009, then on to 0010, 0011 up to 0099, then 0100 and so forth. It's just that each "digit" goes from 0 to 508 (for a total of 509 pointers) rather than from 0 to 9. Note that the dinode will only have 483 pointers due to the dinode structure itself. Also note: this is just an example. These numbers (509 and 483) are based on a standard 4K block size. Smaller block sizes will yield smaller numbers of indirect pointers accordingly. The truncation process is accomplished with the help of two major functions and a few helper functions. Functions do_strip and recursive_scan are obsolete, so removed. New function sweep_bh_for_rgrps cleans a buffer_head pointed to by the given metapath and height. By cleaning, I mean it frees all blocks starting at the offset passed in metapath. It starts at the first block in the buffer pointed to by the metapath and identifies its resource group (rgrp). From there it frees all subsequent block pointers that lie within that rgrp. If it's already inside a transaction, it stays within it as long as it can. In other words, it doesn't close a transaction until it knows it's freed what it can from the resource group. In this way, multiple buffers may be cleaned in a single transaction, as long as those blocks in the buffer all lie within the same rgrp. If it's not in a transaction, it starts one. If the buffer_head has references to blocks within multiple rgrps, it frees all the blocks inside the first rgrp it finds, then closes the transaction. Then it repeats the cycle: identifies the next unfreed block, uses it to find its rgrp, then starts a new transaction for that set. It repeats this process repeatedly until the buffer_head contains no more references to any blocks past the given metapath. Function trunc_dealloc has been reworked into a finite state automaton. It has basically 3 active states: DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP: The DEALLOC_MP_FULL state implies the metapath has a full set of buffers out to the "shrink height", and therefore, it can call function sweep_bh_for_rgrps to free the blocks within the highest height of the metapath. If it's just swept the lowest level (or an error has occurred) the state machine is ended. Otherwise it proceeds to the DEALLOC_MP_LOWER state. The DEALLOC_MP_LOWER state implies we are finished with a given buffer_head, which may now be released, and therefore we are then missing some buffer information from the metapath. So we need to find more buffers to read in. In most cases, this is just a matter of releasing the buffer_head and moving to the next pointer from the previous height, so it may be read in and swept as well. If it can't find another non-null pointer to process, it checks whether it's reached the end of a height and needs to lower the strip height, or whether it still needs move forward through the previous height's metadata. In this state, all zero-pointers are skipped. From this state, it can only loop around (once more backing up another height) or, once a valid metapath is found (one that has non-zero pointers), proceed to state DEALLOC_FILL_MP. The DEALLOC_FILL_MP state implies that we have a metapath but not all its buffers are read in. So we must proceed to read in buffer_heads until the metapath has a valid buffer for every height. If the previous state backed us up 3 heights, we may need to read in a buffer, increment the height, then repeat the process until buffers have been read in for all required heights. If it's successful reading a buffer, and it's at the highest height we need, it proceeds back to the DEALLOC_MP_FULL state. If it's unable to fill in a buffer, (encounters a hole, etc.) it tries to find another non-zero block pointer. If they're all zero, it lowers the height and returns to the DEALLOC_MP_LOWER state. If it finds a good non-null pointer, it loops around and reads it in, while keeping the metapath in lock-step with the pointers it examines. The state machine runs until the truncation request is satisfied. Then any transactions are ended, the quota and statfs data are updated, and the function is complete. Helper function metaptr1 was introduced to be an easy way to determine the start of a buffer_head's indirect pointers. Helper function lookup_mp_height was introduced to find a metapath index and read in the buffer that corresponds to it. In this way, function lookup_metapath becomes a simple loop to call it for every height. Helper function fillup_metapath is similar to lookup_metapath except it can do partial lookups. If the state machine backed up multiple levels (like 2999 wrapping to 3000) it needs to find out the next starting point and start issuing metadata reads at that point. Helper function hptrs is a shortcut to determine how many pointers should be expected in a buffer. Height 0 is the dinode which has fewer pointers than the others. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2016-07-12GFS2: Check rs_free with rd_rsspin protectionBob Peterson1-3/+2
For the last process to close a file opened for write, function gfs2_rsqa_delete was deleting the file's inode's block reservation out of the rgrp reservations tree. Then it was checking to make sure rs_free was 0, but it was performing the check outside the protection of rd_rsspin spin_lock. The rd_rsspin spin_lock protection is needed to prevent a race between the process freeing the reservation and another who is allocating a new set of blocks inside the same rgrp for the same inode, thus changing its value. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2016-06-27gfs2: Lock holder cleanupAndreas Gruenbacher1-2/+2
Make the code more readable by cleaning up the different ways of initializing lock holders and checking for initialized lock holders: mark lock holders as uninitialized by setting the holder's glock to NULL (gfs2_holder_mark_uninitialized) instead of zeroing out the entire object or using a separate flag. Recognize initialized holders by their non-NULL glock (gfs2_holder_initialized). Don't zero out holder objects which are immeditiately initialized via gfs2_holder_init or gfs2_glock_nq_init. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2016-06-10GFS2: don't set rgrp gl_object until it's inserted into rgrp treeBob Peterson1-4/+8
Before this patch, function read_rindex_entry would set a rgrp glock's gl_object pointer to itself before inserting the rgrp into the rgrp rbtree. The problem is: if another process was also reading the rgrp in, and had already inserted its newly created rgrp, then the second call to read_rindex_entry would overwrite that value, then return a bad return code to the caller. Later, other functions would reference the now-freed rgrp memory by way of gl_object. In some cases, that could result in gfs2_rgrp_brelse being called twice for the same rgrp: once for the failed attempt and once for the "real" rgrp release. Eventually the kernel would panic. There are also a number of other things that could go wrong when a kernel module is accessing freed storage. For example, this could result in rgrp corruption because the fake rgrp would point to a fake bitmap in memory too, causing gfs2_inplace_reserve to search some random memory for free blocks, and find some, since we were never setting rgd->rd_bits to NULL before freeing it. This patch fixes the problem by not setting gl_object until we have successfully inserted the rgrp into the rbtree. Also, it sets rd_bits to NULL as it frees them, which will ensure any accidental access to the wrong rgrp will result in a kernel panic rather than file system corruption, which is preferred. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2016-05-21Merge tag 'gfs2-4.7.fixes' of ↵Linus Torvalds1-10/+6
git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2 Pull GFS2 updates from Bob Peterson: "We've got nine patches this time: - Abhi Das has two patches that fix a GFS2 splice issue (and an adjustment). - Ben Marzinski has a patch which allows the proper unmount of a GFS2 file system after hitting a withdraw error. - I have a patch to fix a problem where GFS2 would dereference an error value, plus three cosmetic / refactoring patches. - Daniel DeFreez has a patch to fix two glock reference count problems, where GFS2 was not properly "uninitializing" its glock holder on error paths. - Denys Vlasenko has a patch to change a function to not be inlined, thus reducing the memory footprint of the GFS2 module" * tag 'gfs2-4.7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: GFS2: Refactor gfs2_remove_from_journal GFS2: Remove allocation parms from gfs2_rbm_find gfs2: use inode_lock/unlock instead of accessing i_mutex directly GFS2: Add calls to gfs2_holder_uninit in two error handlers GFS2: Don't dereference inode in gfs2_inode_lookup until it's valid GFS2: fs/gfs2/glock.c: Deinline do_error, save 1856 bytes gfs2: Use gfs2 wrapper to sync inode before calling generic_file_splice_read() GFS2: Get rid of dead code in inode_go_demote_ok GFS2: ignore unlock failures after withdraw
2016-05-02GFS2: Remove allocation parms from gfs2_rbm_findBob Peterson1-10/+6
Struct gfs2_alloc_parms ap is never referenced in function gfs2_rbm_find, so this patch removes it. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2016-04-04mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macrosKirill A. Shutemov1-3/+2
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-12-18GFS2: Always use iopen glock for gl_deletesBob Peterson1-1/+1
Before this patch, when function try_rgrp_unlink queued a glock for delete_work to reclaim the space, it used the inode glock to do so. That's different from the iopen callback which uses the iopen glock for the same purpose. We should be consistent and always use the iopen glock. This may also save us reference counting problems with the inode glock, since clear_glock does an extra glock_put() for the inode glock. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-12-14GFS2: Make rgrp reservations part of the gfs2_inode structureBob Peterson1-38/+14
Before this patch, multi-block reservation structures were allocated from a special slab. This patch folds the structure into the gfs2_inode structure. The disadvantage is that the gfs2_inode needs more memory, even when a file is opened read-only. The advantages are: (a) we don't need the special slab and the extra time it takes to allocate and deallocate from it. (b) we no longer need to worry that the structure exists for things like quota management. (c) This also allows us to remove the calls to get_write_access and put_write_access since we know the structure will exist. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-11-24GFS2: Extract quota data from reservations structure (revert 5407e24)Bob Peterson1-4/+13
This patch basically reverts the majority of patch 5407e24. That patch eliminated the gfs2_qadata structure in favor of just using the reservations structure. The problem with doing that is that it increases the size of the reservations structure. That is not an issue until it comes time to fold the reservations structure into the inode in memory so we know it's always there. By separating out the quota structure again, we aren't punishing the non-quota users by making all the inodes bigger, requiring more slab space. This patch creates a new slab area to allocate the quota stuff so it's managed a little more sanely. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-11-16gfs2: Extended attribute readaheadAndreas Gruenbacher1-1/+1
When gfs2 allocates an inode and its extended attribute block next to each other at inode create time, the inode's directory entry indicates that in de_rahead. In that case, we can readahead the extended attribute block when we read in the inode. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-11-09GFS2: Fix rgrp end rounding problem for bsize < page sizeBob Peterson1-2/+3
This patch fixes a bug introduced by commit 7005c3e. That patch tries to map a vm range for resource groups, but the calculation breaks down when the block size is less than the page size. Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-10-29gfs2: Remove gl_spin defineAndreas Gruenbacher1-2/+2
Commit e66cf161 replaced the gl_spin spinlock in struct gfs2_glock with a gl_lockref lockref and defined gl_spin as gl_lockref.lock (the spinlock in gl_lockref). Remove that define to make the references to gl_lockref.lock more obvious. Signed-off-by: Andreas Gruenbacher <andreas.gruenbacher@gmail.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-09-03gfs2: Make statistics unsigned, suitable for use with do_div()Ben Hutchings1-4/+4
None of these statistics can meaningfully be negative, and the numerator for do_div() must have the type u64. The generic implementation of do_div() used on some 32-bit architectures asserts that, resulting in a compiler error in gfs2_rgrp_congested(). Fixes: 0166b197c2ed ("GFS2: Average in only non-zero round-trip times ...") Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Bob Peterson <rpeterso@redhat.com> Acked-by: Andreas Gruenbacher <agruenba@redhat.com>
2015-09-03GFS2: Move glock superblock pointer to field gl_nameBob Peterson1-1/+1
What uniquely identifies a glock in the glock hash table is not gl_name, but gl_name and its superblock pointer. This patch makes the gl_name field correspond to a unique glock identifier. That will allow us to simplify hashing with a future patch, since the hash algorithm can then take the gl_name and hash its components in one operation. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com>
2015-06-19GFS2: Don't brelse rgrp buffer_heads every allocationBob Peterson1-4/+19
This patch allows the block allocation code to retain the buffers for the resource groups so they don't need to be re-read from buffer cache with every request. This is a performance improvement that's especially noticeable when resource groups are very large. For example, with 2GB resource groups and 4K blocks, there can be 33 blocks for every resource group. This patch allows those 33 buffers to be kept around and not read in and thrown away with every operation. The buffers are released when the resource group is either synced or invalidated. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Reviewed-by: Steven Whitehouse <swhiteho@redhat.com> Reviewed-by: Benjamin Marzinski <bmarzins@redhat.com>
2015-05-18gfs2: fix shadow warning in gfs2_rbm_find()Fabian Frederick1-3/+1
bi was already declared and initialized globally in gfs2_rbm_find() Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-05-05gfs2: handle NULL rgd in set_rgrp_preferencesAbhi Das1-2/+2
The function set_rgrp_preferences() does not handle the (rarely returned) NULL value from gfs2_rgrpd_get_next() and this patch fixes that. The fs image in question is only 150MB in size which allows for only 1 rgrp to be created. The in-memory rb tree has only 1 node and when gfs2_rgrpd_get_next() is called on this sole rgrp, it returns NULL. (Default behavior is to wrap around the rb tree and return the first node to give the illusion of a circular linked list. In the case of only 1 rgrp, we can't have gfs2_rgrpd_get_next() return the same rgrp (first, last, next all point to the same rgrp)... that would cause unintended consequences and infinite loops.) Signed-off-by: Abhi Das <adas@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2015-04-24GFS2: Average in only non-zero round-trip times for congestion statsBob Peterson1-3/+7
This patch changes function gfs2_rgrp_congested so that it only factors in non-zero values into its average round trip time. If the round-trip time is zero for a particular cpu, that cpu has obviously never dealt with bouncing the resource group in question, so factoring in a zero value will only skew the numbers. It also fixes a compile error on some arches related to division. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com>
2015-04-24GFS2: Use average srttb value in congestion calculationsBob Peterson1-4/+9
This patch changes function gfs2_rgrp_congested so that it uses an average srttb (smoothed round trip time for blocking rgrp glocks) rather than the CPU-specific value. If we use the CPU-specific value it can incorrectly report no contention when there really is contention due to the glock processing occurring on a different CPU. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com>
2015-03-18gfs2: allow quota_check and inplace_reserve to return available blocksAbhi Das1-5/+15
struct gfs2_alloc_parms is passed to gfs2_quota_check() and gfs2_inplace_reserve() with ap->target containing the number of blocks being requested for allocation in the current operation. We add a new field to struct gfs2_alloc_parms called 'allowed'. gfs2_quota_check() and gfs2_inplace_reserve() return the max blocks allowed by quota and the max blocks allowed by the chosen rgrp respectively in 'allowed'. A new field 'min_target', when non-zero, tells gfs2_quota_check() and gfs2_inplace_reserve() to not return -EDQUOT/-ENOSPC when there are atleast 'min_target' blocks allowable/available. The assumption is that the caller is ok with just 'min_target' blocks and will likely proceed with allocating them. Signed-off-by: Abhi Das <adas@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com>
2014-11-03GFS2: If we use up our block reservation, request more next timeBob Peterson1-0/+3
If we run out of blocks for a given multi-block allocation, we obviously did not reserve enough. We should reserve more blocks for the next reservation to reduce fragmentation. This patch increases the size hint for reservations when they run out. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-11-03GFS2: Set of distributed preferences for rgrpsBob Peterson1-5/+61
This patch tries to use the journal numbers to evenly distribute which node prefers which resource group for block allocations. This is to help performance. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-10-03GFS2: Use gfs2_rbm_incr in rgblk_freeBob Peterson1-9/+13
This patch speeds up GFS2 unlink operations by using function gfs2_rbm_incr rather than continuously calculating the rbm. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-09-19GFS2: fix bad inode i_goal values during block allocationAbhi Das1-0/+8
This patch checks if i_goal is either zero or if doesn't exist within any rgrp (i.e gfs2_blk2rgrpd() returns NULL). If so, it assigns the ip->i_no_addr block as the i_goal. There are two scenarios where a bad i_goal can result in a -EBADSLT error. 1. Attempting to allocate to an existing inode: Control reaches gfs2_inplace_reserve() and ip->i_goal is bad. We need to fix i_goal here. 2. A new inode is created in a directory whose i_goal is hosed: In this case, the parent dir's i_goal is copied onto the new inode. Since the new inode is not yet created, the ip->i_no_addr field is invalid and so, the fix in gfs2_inplace_reserve() as per 1) won't work in this scenario. We need to catch and fix it sooner in the parent dir itself (gfs2_create_inode()), before it is copied to the new inode. Signed-off-by: Abhi Das <adas@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-07-18GFS2: fs/gfs2/rgrp.c: kernel-doc warning fixesFabian Frederick1-2/+2
Cc: cluster-devel@redhat.com Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-14GFS2: remove transaction glockBenjamin Marzinski1-1/+1
GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-03-07GFS2: Use pr_<level> more consistentlyJoe Perches1-11/+13
Add pr_fmt, remove embedded "GFS2: " prefixes. This now consistently emits lower case "gfs2: " for each message. Other miscellanea around these changes: o Add missing newlines o Coalesce formats o Realign arguments Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-03-06GFS2: global conversion to pr_foo()Fabian Frederick1-9/+9
-All printk(KERN_foo converted to pr_foo(). -Messages updated to fit in 80 columns. -fs_macros converted as well. -fs_printk removed. Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-02-10GFS2: Mark functions as static in gfs2/rgrp.cRashika Kheria1-2/+2
Mark functions as static in gfs2/rgrp.c because they are not used outside this file. This eliminates the following warning in gfs2/rgrp.c: fs/gfs2/rgrp.c:1092:5: warning: no previous prototype for ‘gfs2_rgrp_bh_get’ [-Wmissing-prototypes] fs/gfs2/rgrp.c:1157:5: warning: no previous prototype for ‘update_rgrp_lvb’ [-Wmissing-prototypes] Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-02-04GFS2: Allocate block for xattr at inode alloc time, if requiredSteven Whitehouse1-1/+1
This is another step towards improving the allocation of xattr blocks at inode allocation time. Here we take advantage of Christoph's recent work on ACLs to allocate a block for the xattrs early if we know that we will be adding ACLs to the inode later on. The advantage of that is that it is much more likely that we'll get a contiguous run of two blocks where the first is the inode and the second is the xattr block. We still have to fall back to the original system in case we don't get the requested two contiguous blocks, or in case the ACLs are too large to fit into the block. Future patches will move more of the ACL setting code further up the gfs2_inode_create() function. Also, I'd like to be able to do the same thing with the xattrs from LSMs in due course, too. That way we should be able to slowly reduce the number of independent transactions, at least in the most common cases. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-01-16GFS2: Small cleanupBob Peterson1-1/+1
This is a small cleanup to function gfs2_rgrp_go_lock so that it uses rgd instead of its more complicated twin. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-01-16GFS2: Don't use ENOBUFS when ENOMEM is the correct error codeSteven Whitehouse1-3/+2
Al Viro has tactfully pointed out that we are using the incorrect error code in some cases. This patch fixes that, and also removes the (unused) return value for glock dumping. > * gfs2_iget() - ENOBUFS instead of ENOMEM. ENOBUFS is > "No buffer space available (POSIX.1 (XSI STREAMS option))" and since > we don't support STREAMS it's probably fair game, but... what the hell? Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk>
2014-01-03GFS2: Use range based functions for rgrp sync/invalidationSteven Whitehouse1-0/+3
Each rgrp header is represented as a single extent on disk, so we can calculate the position within the address space, since we are using address spaces mapped 1:1 to the disk. This means that it is possible to use the range based versions of filemap_fdatawrite/wait and for invalidating the page cache. Our eventual intent is to then be able to merge the address spaces used for rgrps into a single address space, rather than to have one for each glock, saving memory and reducing complexity. Since during umount, the rgrp structures are disposed of before the glocks, we need to store the extent information in the glock so that is is available for a final invalidation. This patch uses a field which is otherwise unused in rgrp glocks to do that, so that we do not have to expand the size of a glock. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-01-03GFS2: Remove test which is always trueSteven Whitehouse1-1/+1
Since gfs2_inplace_reserve() is always called with a valid alloc parms structure, there is no need to test for this within the function itself - and in any case, after we've all ready dereferenced it anyway. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-01-03GFS2: Implement a "rgrp has no extents longer than X" schemeBob Peterson1-6/+26
With the preceding patch, we started accepting block reservations smaller than the ideal size, which requires a lot more parsing of the bitmaps. To reduce the amount of bitmap searching, this patch implements a scheme whereby each rgrp keeps track of the point at this multi-block reservations will fail. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-08 05:02:08 +0300