# git rev-parse -q --verify d1dc87763f406d4e67caf16dbe438a5647692395^{commit} d1dc87763f406d4e67caf16dbe438a5647692395 already have revision, skipping fetch # git checkout -q -f -B kisskb d1dc87763f406d4e67caf16dbe438a5647692395 # git clean -qxdf # < git log -1 # commit d1dc87763f406d4e67caf16dbe438a5647692395 # Author: Stephen Brennan # Date: Thu May 19 09:50:30 2022 +0100 # # assoc_array: Fix BUG_ON during garbage collect # # A rare BUG_ON triggered in assoc_array_gc: # # [3430308.818153] kernel BUG at lib/assoc_array.c:1609! # # Which corresponded to the statement currently at line 1593 upstream: # # BUG_ON(assoc_array_ptr_is_meta(p)); # # Using the data from the core dump, I was able to generate a userspace # reproducer[1] and determine the cause of the bug. # # [1]: https://github.com/brenns10/kernel_stuff/tree/master/assoc_array_gc # # After running the iterator on the entire branch, an internal tree node # looked like the following: # # NODE (nr_leaves_on_branch: 3) # SLOT [0] NODE (2 leaves) # SLOT [1] NODE (1 leaf) # SLOT [2..f] NODE (empty) # # In the userspace reproducer, the pr_devel output when compressing this # node was: # # -- compress node 0x5607cc089380 -- # free=0, leaves=0 # [0] retain node 2/1 [nx 0] # [1] fold node 1/1 [nx 0] # [2] fold node 0/1 [nx 2] # [3] fold node 0/2 [nx 2] # [4] fold node 0/3 [nx 2] # [5] fold node 0/4 [nx 2] # [6] fold node 0/5 [nx 2] # [7] fold node 0/6 [nx 2] # [8] fold node 0/7 [nx 2] # [9] fold node 0/8 [nx 2] # [10] fold node 0/9 [nx 2] # [11] fold node 0/10 [nx 2] # [12] fold node 0/11 [nx 2] # [13] fold node 0/12 [nx 2] # [14] fold node 0/13 [nx 2] # [15] fold node 0/14 [nx 2] # after: 3 # # At slot 0, an internal node with 2 leaves could not be folded into the # node, because there was only one available slot (slot 0). Thus, the # internal node was retained. At slot 1, the node had one leaf, and was # able to be folded in successfully. The remaining nodes had no leaves, # and so were removed. By the end of the compression stage, there were 14 # free slots, and only 3 leaf nodes. The tree was ascended and then its # parent node was compressed. When this node was seen, it could not be # folded, due to the internal node it contained. # # The invariant for compression in this function is: whenever # nr_leaves_on_branch < ASSOC_ARRAY_FAN_OUT, the node should contain all # leaf nodes. The compression step currently cannot guarantee this, given # the corner case shown above. # # To fix this issue, retry compression whenever we have retained a node, # and yet nr_leaves_on_branch < ASSOC_ARRAY_FAN_OUT. This second # compression will then allow the node in slot 1 to be folded in, # satisfying the invariant. Below is the output of the reproducer once the # fix is applied: # # -- compress node 0x560e9c562380 -- # free=0, leaves=0 # [0] retain node 2/1 [nx 0] # [1] fold node 1/1 [nx 0] # [2] fold node 0/1 [nx 2] # [3] fold node 0/2 [nx 2] # [4] fold node 0/3 [nx 2] # [5] fold node 0/4 [nx 2] # [6] fold node 0/5 [nx 2] # [7] fold node 0/6 [nx 2] # [8] fold node 0/7 [nx 2] # [9] fold node 0/8 [nx 2] # [10] fold node 0/9 [nx 2] # [11] fold node 0/10 [nx 2] # [12] fold node 0/11 [nx 2] # [13] fold node 0/12 [nx 2] # [14] fold node 0/13 [nx 2] # [15] fold node 0/14 [nx 2] # internal nodes remain despite enough space, retrying # -- compress node 0x560e9c562380 -- # free=14, leaves=1 # [0] fold node 2/15 [nx 0] # after: 3 # # Changes # ======= # DH: # - Use false instead of 0. # - Reorder the inserted lines in a couple of places to put retained before # next_slot. # # ver #2) # - Fix typo in pr_devel, correct comparison to "<=" # # Fixes: 3cb989501c26 ("Add a generic associative array implementation.") # Cc: # Signed-off-by: Stephen Brennan # Signed-off-by: David Howells # cc: Andrew Morton # cc: keyrings@vger.kernel.org # Link: https://lore.kernel.org/r/20220511225517.407935-1-stephen.s.brennan@oracle.com/ # v1 # Link: https://lore.kernel.org/r/20220512215045.489140-1-stephen.s.brennan@oracle.com/ # v2 # Reviewed-by: Jarkko Sakkinen # Signed-off-by: Linus Torvalds # < /opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux-gcc --version # < /opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux-ld --version # < git log --format=%s --max-count=1 d1dc87763f406d4e67caf16dbe438a5647692395 # < make -s -j 24 ARCH=um O=/kisskb/build/linus_um-allmodconfig_um-x86_64 CROSS_COMPILE=/opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux- SUBARCH=x86_64 allmodconfig # Added to kconfig CONFIG_STANDALONE=y # Added to kconfig CONFIG_KCOV=n # Added to kconfig CONFIG_GCC_PLUGINS=n # Added to kconfig CONFIG_GCC_PLUGIN_CYC_COMPLEXITY=n # Added to kconfig CONFIG_GCC_PLUGIN_SANCOV=n # Added to kconfig CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n # Added to kconfig CONFIG_GCC_PLUGIN_STRUCTLEAK=n # Added to kconfig CONFIG_GCC_PLUGIN_RANDSTRUCT=n # Added to kconfig CONFIG_UML_NET=n # Added to kconfig CONFIG_UML_NET_ETHERTAP=n # Added to kconfig CONFIG_UML_NET_TUNTAP=n # Added to kconfig CONFIG_UML_NET_SLIP=n # Added to kconfig CONFIG_UML_NET_DAEMON=n # Added to kconfig CONFIG_UML_NET_VDE=n # Added to kconfig CONFIG_UML_NET_MCAST=n # Added to kconfig CONFIG_UML_NET_PCAP=n # Added to kconfig CONFIG_UML_NET_SLIRP=n # Added to kconfig CONFIG_GCOV_KERNEL=n # Added to kconfig CONFIG_DEBUG_INFO_BTF=n # Added to kconfig CONFIG_BPF_PRELOAD=n # < make -s -j 24 ARCH=um O=/kisskb/build/linus_um-allmodconfig_um-x86_64 CROSS_COMPILE=/opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux- SUBARCH=x86_64 help # make -s -j 24 ARCH=um O=/kisskb/build/linus_um-allmodconfig_um-x86_64 CROSS_COMPILE=/opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux- SUBARCH=x86_64 olddefconfig .config:12342:warning: override: reassigning to symbol GCC_PLUGIN_SANCOV .config:12347:warning: override: reassigning to symbol UML_NET_ETHERTAP .config:12349:warning: override: reassigning to symbol UML_NET_SLIP .config:12352:warning: override: reassigning to symbol UML_NET_MCAST .config:12354:warning: override: reassigning to symbol UML_NET_SLIRP # make -s -j 24 ARCH=um O=/kisskb/build/linus_um-allmodconfig_um-x86_64 CROSS_COMPILE=/opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux- SUBARCH=x86_64 In file included from /kisskb/src/arch/x86/um/asm/processor.h:41:0, from /kisskb/src/include/linux/mutex.h:19, from /kisskb/src/include/linux/kernfs.h:11, from /kisskb/src/include/linux/sysfs.h:16, from /kisskb/src/include/linux/kobject.h:20, from /kisskb/src/include/linux/pci.h:35, from /kisskb/src/drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:26: /kisskb/src/drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c: In function 'kfd_cpumask_to_apic_id': /kisskb/src/arch/um/include/asm/processor-generic.h:103:18: error: called object is not a function or function pointer #define cpu_data (&boot_cpu_data) ^ /kisskb/src/drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1620:9: note: in expansion of macro 'cpu_data' return cpu_data(first_cpu_of_numa_node).apicid; ^ /kisskb/src/drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1624:1: error: control reaches end of non-void function [-Werror=return-type] } ^ cc1: all warnings being treated as errors make[5]: *** [/kisskb/src/scripts/Makefile.build:271: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.o] Error 1 make[5]: *** Waiting for unfinished jobs.... make[4]: *** [/kisskb/src/scripts/Makefile.build:500: drivers/gpu/drm/amd/amdgpu] Error 2 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [/kisskb/src/scripts/Makefile.build:500: drivers/gpu/drm] Error 2 make[2]: *** [/kisskb/src/scripts/Makefile.build:500: drivers/gpu] Error 2 make[2]: *** Waiting for unfinished jobs.... make[1]: *** [/kisskb/src/Makefile:1839: drivers] Error 2 make: *** [Makefile:219: __sub-make] Error 2 Command 'make -s -j 24 ARCH=um O=/kisskb/build/linus_um-allmodconfig_um-x86_64 CROSS_COMPILE=/opt/cross/kisskb/fe-x86-64-core-i7-2017.05/bin/x86_64-linux- SUBARCH=x86_64 ' returned non-zero exit status 2 # rm -rf /kisskb/build/linus_um-allmodconfig_um-x86_64 # Build took: 0:16:23.068267