From 8757dc970f550dc399f899be0e7a2c00b7e82e8f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 20 Dec 2019 08:22:49 -0800 Subject: x86/crash: Define arch_crash_save_vmcoreinfo() if CONFIG_CRASH_CORE=y On x86 kernels configured with CONFIG_PROC_KCORE=y and CONFIG_KEXEC_CORE=n, the vmcoreinfo note in /proc/kcore is incomplete. Specifically, it is missing arch-specific information like the KASLR offset and whether 5-level page tables are enabled. This breaks applications like drgn [1] and crash [2], which need this information for live debugging via /proc/kcore. This happens because: 1. CONFIG_PROC_KCORE selects CONFIG_CRASH_CORE. 2. kernel/crash_core.c (compiled if CONFIG_CRASH_CORE=y) calls arch_crash_save_vmcoreinfo() to get the arch-specific parts of vmcoreinfo. If it is not defined, then it uses a no-op fallback. 3. x86 defines arch_crash_save_vmcoreinfo() in arch/x86/kernel/machine_kexec_*.c, which is only compiled if CONFIG_KEXEC_CORE=y. Therefore, an x86 kernel with CONFIG_CRASH_CORE=y and CONFIG_KEXEC_CORE=n uses the no-op fallback and gets incomplete vmcoreinfo data. This isn't relevant to kdump, which requires CONFIG_KEXEC_CORE. It only affects applications which read vmcoreinfo at runtime, like the ones mentioned above. Fix it by moving arch_crash_save_vmcoreinfo() into two new arch/x86/kernel/crash_core_*.c files, which are gated behind CONFIG_CRASH_CORE. 1: https://github.com/osandov/drgn/blob/73dd7def1217e24cc83d8ca95c995decbd9ba24c/libdrgn/program.c#L385 2: https://github.com/crash-utility/crash/commit/60a42d709280cdf38ab06327a5b4fa9d9208ef86 Signed-off-by: Omar Sandoval Signed-off-by: Borislav Petkov Cc: Andy Lutomirski Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kairui Song Cc: Lianbo Jiang Cc: Masahiro Yamada Cc: "Peter Zijlstra (Intel)" Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/0589961254102cca23e3618b96541b89f2b249e2.1576858905.git.osandov@fb.com --- arch/x86/kernel/Makefile | 1 + arch/x86/kernel/crash_core_32.c | 17 +++++++++++++++++ arch/x86/kernel/crash_core_64.c | 24 ++++++++++++++++++++++++ arch/x86/kernel/machine_kexec_32.c | 12 ------------ arch/x86/kernel/machine_kexec_64.c | 19 ------------------- 5 files changed, 42 insertions(+), 31 deletions(-) create mode 100644 arch/x86/kernel/crash_core_32.c create mode 100644 arch/x86/kernel/crash_core_64.c diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 6175e370ee4a..9b294c13809a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += ftrace_$(BITS).o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o +obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/crash_core_32.c new file mode 100644 index 000000000000..c0159a7bca6d --- /dev/null +++ b/arch/x86/kernel/crash_core_32.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +#include +#include + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif +#ifdef CONFIG_X86_PAE + VMCOREINFO_CONFIG(X86_PAE); +#endif +} diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/crash_core_64.c new file mode 100644 index 000000000000..845a57eb4eb7 --- /dev/null +++ b/arch/x86/kernel/crash_core_64.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +#include +#include + +void arch_crash_save_vmcoreinfo(void) +{ + u64 sme_mask = sme_me_mask; + + VMCOREINFO_NUMBER(phys_base); + VMCOREINFO_SYMBOL(init_top_pgt); + vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", + pgtable_l5_enabled()); + +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); + VMCOREINFO_NUMBER(sme_mask); +} diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 7b45e8daad22..02bddfc122a4 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -250,15 +250,3 @@ void machine_kexec(struct kimage *image) __ftrace_enabled_restore(save_ftrace_enabled); } - -void arch_crash_save_vmcoreinfo(void) -{ -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif -#ifdef CONFIG_X86_PAE - VMCOREINFO_CONFIG(X86_PAE); -#endif -} - diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 16e125a50b33..ad5cdd6a5f23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -398,25 +398,6 @@ void machine_kexec(struct kimage *image) __ftrace_enabled_restore(save_ftrace_enabled); } -void arch_crash_save_vmcoreinfo(void) -{ - u64 sme_mask = sme_me_mask; - - VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_top_pgt); - vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", - pgtable_l5_enabled()); - -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", - kaslr_offset()); - VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); - VMCOREINFO_NUMBER(sme_mask); -} - /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE -- cgit v1.2.3 From 538f127cd3bcf76071139f4bfe9cc3b2a46f3b3d Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Sun, 22 Dec 2019 23:34:04 +0000 Subject: x86/hyper-v: Add "polling" bit to hv_synic_sint That bit is documented in TLFS 5.0c as follows: Setting the polling bit will have the effect of unmasking an interrupt source, except that an actual interrupt is not generated. Signed-off-by: Wei Liu Signed-off-by: Thomas Gleixner Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20191222233404.1629-1-wei.liu@kernel.org --- arch/x86/include/asm/hyperv-tlfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 5f10f7f2098d..92abc1e42bfc 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -809,7 +809,8 @@ union hv_synic_sint { u64 reserved1:8; u64 masked:1; u64 auto_eoi:1; - u64 reserved2:46; + u64 polling:1; + u64 reserved2:45; } __packed; }; -- cgit v1.2.3 From b8511ccc75c033f6d54188ea4df7bf1e85778740 Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Thu, 9 Jan 2020 00:28:03 +0800 Subject: x86/resctrl: Fix use-after-free when deleting resource groups A resource group (rdtgrp) contains a reference count (rdtgrp->waitcount) that indicates how many waiters expect this rdtgrp to exist. Waiters could be waiting on rdtgroup_mutex or some work sitting on a task's workqueue for when the task returns from kernel mode or exits. The deletion of a rdtgrp is intended to have two phases: (1) while holding rdtgroup_mutex the necessary cleanup is done and rdtgrp->flags is set to RDT_DELETED, (2) after releasing the rdtgroup_mutex, the rdtgrp structure is freed only if there are no waiters and its flag is set to RDT_DELETED. Upon gaining access to rdtgroup_mutex or rdtgrp, a waiter is required to check for the RDT_DELETED flag. When unmounting the resctrl file system or deleting ctrl_mon groups, all of the subdirectories are removed and the data structure of rdtgrp is forcibly freed without checking rdtgrp->waitcount. If at this point there was a waiter on rdtgrp then a use-after-free issue occurs when the waiter starts running and accesses the rdtgrp structure it was waiting on. See kfree() calls in [1], [2] and [3] in these two call paths in following scenarios: (1) rdt_kill_sb() -> rmdir_all_sub() -> free_all_child_rdtgrp() (2) rdtgroup_rmdir() -> rdtgroup_rmdir_ctrl() -> free_all_child_rdtgrp() There are several scenarios that result in use-after-free issue in following: Scenario 1: ----------- In Thread 1, rdtgroup_tasks_write() adds a task_work callback move_myself(). If move_myself() is scheduled to execute after Thread 2 rdt_kill_sb() is finished, referring to earlier rdtgrp memory (rdtgrp->waitcount) which was already freed in Thread 2 results in use-after-free issue. Thread 1 (rdtgroup_tasks_write) Thread 2 (rdt_kill_sb) ------------------------------- ---------------------- rdtgroup_kn_lock_live atomic_inc(&rdtgrp->waitcount) mutex_lock rdtgroup_move_task __rdtgroup_move_task /* * Take an extra refcount, so rdtgrp cannot be freed * before the call back move_myself has been invoked */ atomic_inc(&rdtgrp->waitcount) /* Callback move_myself will be scheduled for later */ task_work_add(move_myself) rdtgroup_kn_unlock mutex_unlock atomic_dec_and_test(&rdtgrp->waitcount) && (flags & RDT_DELETED) mutex_lock rmdir_all_sub /* * sentry and rdtgrp are freed * without checking refcount */ free_all_child_rdtgrp kfree(sentry)*[1] kfree(rdtgrp)*[2] mutex_unlock /* * Callback is scheduled to execute * after rdt_kill_sb is finished */ move_myself /* * Use-after-free: refer to earlier rdtgrp * memory which was freed in [1] or [2]. */ atomic_dec_and_test(&rdtgrp->waitcount) && (flags & RDT_DELETED) kfree(rdtgrp) Scenario 2: ----------- In Thread 1, rdtgroup_tasks_write() adds a task_work callback move_myself(). If move_myself() is scheduled to execute after Thread 2 rdtgroup_rmdir() is finished, referring to earlier rdtgrp memory (rdtgrp->waitcount) which was already freed in Thread 2 results in use-after-free issue. Thread 1 (rdtgroup_tasks_write) Thread 2 (rdtgroup_rmdir) ------------------------------- ------------------------- rdtgroup_kn_lock_live atomic_inc(&rdtgrp->waitcount) mutex_lock rdtgroup_move_task __rdtgroup_move_task /* * Take an extra refcount, so rdtgrp cannot be freed * before the call back move_myself has been invoked */ atomic_inc(&rdtgrp->waitcount) /* Callback move_myself will be scheduled for later */ task_work_add(move_myself) rdtgroup_kn_unlock mutex_unlock atomic_dec_and_test(&rdtgrp->waitcount) && (flags & RDT_DELETED) rdtgroup_kn_lock_live atomic_inc(&rdtgrp->waitcount) mutex_lock rdtgroup_rmdir_ctrl free_all_child_rdtgrp /* * sentry is freed without * checking refcount */ kfree(sentry)*[3] rdtgroup_ctrl_remove rdtgrp->flags = RDT_DELETED rdtgroup_kn_unlock mutex_unlock atomic_dec_and_test( &rdtgrp->waitcount) && (flags & RDT_DELETED) kfree(rdtgrp) /* * Callback is scheduled to execute * after rdt_kill_sb is finished */ move_myself /* * Use-after-free: refer to earlier rdtgrp * memory which was freed in [3]. */ atomic_dec_and_test(&rdtgrp->waitcount) && (flags & RDT_DELETED) kfree(rdtgrp) If CONFIG_DEBUG_SLAB=y, Slab corruption on kmalloc-2k can be observed like following. Note that "0x6b" is POISON_FREE after kfree(). The corrupted bits "0x6a", "0x64" at offset 0x424 correspond to waitcount member of struct rdtgroup which was freed: Slab corruption (Not tainted): kmalloc-2k start=ffff9504c5b0d000, len=2048 420: 6b 6b 6b 6b 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkjkkkkkkkkkkk Single bit error detected. Probably bad RAM. Run memtest86+ or a similar memory test tool. Next obj: start=ffff9504c5b0d800, len=2048 000: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 010: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Slab corruption (Not tainted): kmalloc-2k start=ffff9504c58ab800, len=2048 420: 6b 6b 6b 6b 64 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkdkkkkkkkkkkk Prev obj: start=ffff9504c58ab000, len=2048 000: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 010: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Fix this by taking reference count (waitcount) of rdtgrp into account in the two call paths that currently do not do so. Instead of always freeing the resource group it will only be freed if there are no waiters on it. If there are waiters, the resource group will have its flags set to RDT_DELETED. It will be left to the waiter to free the resource group when it starts running and finding that it was the last waiter and the resource group has been removed (rdtgrp->flags & RDT_DELETED) since. (1) rdt_kill_sb() -> rmdir_all_sub() -> free_all_child_rdtgrp() (2) rdtgroup_rmdir() -> rdtgroup_rmdir_ctrl() -> free_all_child_rdtgrp() Fixes: f3cbeacaa06e ("x86/intel_rdt/cqm: Add rmdir support") Fixes: 60cf5e101fd4 ("x86/intel_rdt: Add mkdir to resctrl file system") Suggested-by: Reinette Chatre Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Reviewed-by: Tony Luck Acked-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1578500886-21771-2-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index dac7209a0708..23904ab55c65 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2205,7 +2205,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { free_rmid(sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); - kfree(sentry); + + if (atomic_read(&sentry->waitcount) != 0) + sentry->flags = RDT_DELETED; + else + kfree(sentry); } } @@ -2243,7 +2247,11 @@ static void rmdir_all_sub(void) kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); - kfree(rdtgrp); + + if (atomic_read(&rdtgrp->waitcount) != 0) + rdtgrp->flags = RDT_DELETED; + else + kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); -- cgit v1.2.3 From 074fadee59ee7a9d2b216e9854bd4efb5dad679f Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Thu, 9 Jan 2020 00:28:04 +0800 Subject: x86/resctrl: Fix use-after-free due to inaccurate refcount of rdtgroup There is a race condition in the following scenario which results in an use-after-free issue when reading a monitoring file and deleting the parent ctrl_mon group concurrently: Thread 1 calls atomic_inc() to take refcount of rdtgrp and then calls kernfs_break_active_protection() to drop the active reference of kernfs node in rdtgroup_kn_lock_live(). In Thread 2, kernfs_remove() is a blocking routine. It waits on all sub kernfs nodes to drop the active reference when removing all subtree kernfs nodes recursively. Thread 2 could block on kernfs_remove() until Thread 1 calls kernfs_break_active_protection(). Only after kernfs_remove() completes the refcount of rdtgrp could be trusted. Before Thread 1 calls atomic_inc() and kernfs_break_active_protection(), Thread 2 could call kfree() when the refcount of rdtgrp (sentry) is 0 instead of 1 due to the race. In Thread 1, in rdtgroup_kn_unlock(), referring to earlier rdtgrp memory (rdtgrp->waitcount) which was already freed in Thread 2 results in use-after-free issue. Thread 1 (rdtgroup_mondata_show) Thread 2 (rdtgroup_rmdir) -------------------------------- ------------------------- rdtgroup_kn_lock_live /* * kn active protection until * kernfs_break_active_protection(kn) */ rdtgrp = kernfs_to_rdtgroup(kn) rdtgroup_kn_lock_live atomic_inc(&rdtgrp->waitcount) mutex_lock rdtgroup_rmdir_ctrl free_all_child_rdtgrp /* * sentry->waitcount should be 1 * but is 0 now due to the race. */ kfree(sentry)*[1] /* * Only after kernfs_remove() * completes, the refcount of * rdtgrp could be trusted. */ atomic_inc(&rdtgrp->waitcount) /* kn->active-- */ kernfs_break_active_protection(kn) rdtgroup_ctrl_remove rdtgrp->flags = RDT_DELETED /* * Blocking routine, wait for * all sub kernfs nodes to drop * active reference in * kernfs_break_active_protection. */ kernfs_remove(rdtgrp->kn) rdtgroup_kn_unlock mutex_unlock atomic_dec_and_test( &rdtgrp->waitcount) && (flags & RDT_DELETED) kernfs_unbreak_active_protection(kn) kfree(rdtgrp) mutex_lock mon_event_read rdtgroup_kn_unlock mutex_unlock /* * Use-after-free: refer to earlier rdtgrp * memory which was freed in [1]. */ atomic_dec_and_test(&rdtgrp->waitcount) && (flags & RDT_DELETED) /* kn->active++ */ kernfs_unbreak_active_protection(kn) kfree(rdtgrp) Fix it by moving free_all_child_rdtgrp() to after kernfs_remove() in rdtgroup_rmdir_ctrl() to ensure it has the accurate refcount of rdtgrp. Fixes: f3cbeacaa06e ("x86/intel_rdt/cqm: Add rmdir support") Suggested-by: Reinette Chatre Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Reviewed-by: Tony Luck Acked-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1578500886-21771-3-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 23904ab55c65..caab397287ff 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2960,13 +2960,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); + rdtgroup_ctrl_remove(kn, rdtgrp); + /* * Free all the child monitor group rmids. */ free_all_child_rdtgrp(rdtgrp); - rdtgroup_ctrl_remove(kn, rdtgrp); - return 0; } -- cgit v1.2.3 From 334b0f4e9b1b4a1d475f803419d202f6c5e4d18e Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Thu, 9 Jan 2020 00:28:05 +0800 Subject: x86/resctrl: Fix a deadlock due to inaccurate reference There is a race condition which results in a deadlock when rmdir and mkdir execute concurrently: $ ls /sys/fs/resctrl/c1/mon_groups/m1/ cpus cpus_list mon_data tasks Thread 1: rmdir /sys/fs/resctrl/c1 Thread 2: mkdir /sys/fs/resctrl/c1/mon_groups/m1 3 locks held by mkdir/48649: #0: (sb_writers#17){.+.+}, at: [] mnt_want_write+0x20/0x50 #1: (&type->i_mutex_dir_key#8/1){+.+.}, at: [] filename_create+0x7b/0x170 #2: (rdtgroup_mutex){+.+.}, at: [] rdtgroup_kn_lock_live+0x3d/0x70 4 locks held by rmdir/48652: #0: (sb_writers#17){.+.+}, at: [] mnt_want_write+0x20/0x50 #1: (&type->i_mutex_dir_key#8/1){+.+.}, at: [] do_rmdir+0x13f/0x1e0 #2: (&type->i_mutex_dir_key#8){++++}, at: [] vfs_rmdir+0x4d/0x120 #3: (rdtgroup_mutex){+.+.}, at: [] rdtgroup_kn_lock_live+0x3d/0x70 Thread 1 is deleting control group "c1". Holding rdtgroup_mutex, kernfs_remove() removes all kernfs nodes under directory "c1" recursively, then waits for sub kernfs node "mon_groups" to drop active reference. Thread 2 is trying to create a subdirectory "m1" in the "mon_groups" directory. The wrapper kernfs_iop_mkdir() takes an active reference to the "mon_groups" directory but the code drops the active reference to the parent directory "c1" instead. As a result, Thread 1 is blocked on waiting for active reference to drop and never release rdtgroup_mutex, while Thread 2 is also blocked on trying to get rdtgroup_mutex. Thread 1 (rdtgroup_rmdir) Thread 2 (rdtgroup_mkdir) (rmdir /sys/fs/resctrl/c1) (mkdir /sys/fs/resctrl/c1/mon_groups/m1) ------------------------- ------------------------- kernfs_iop_mkdir /* * kn: "m1", parent_kn: "mon_groups", * prgrp_kn: parent_kn->parent: "c1", * * "mon_groups", parent_kn->active++: 1 */ kernfs_get_active(parent_kn) kernfs_iop_rmdir /* "c1", kn->active++ */ kernfs_get_active(kn) rdtgroup_kn_lock_live atomic_inc(&rdtgrp->waitcount) /* "c1", kn->active-- */ kernfs_break_active_protection(kn) mutex_lock rdtgroup_rmdir_ctrl free_all_child_rdtgrp sentry->flags = RDT_DELETED rdtgroup_ctrl_remove rdtgrp->flags = RDT_DELETED kernfs_get(kn) kernfs_remove(rdtgrp->kn) __kernfs_remove /* "mon_groups", sub_kn */ atomic_add(KN_DEACTIVATED_BIAS, &sub_kn->active) kernfs_drain(sub_kn) /* * sub_kn->active == KN_DEACTIVATED_BIAS + 1, * waiting on sub_kn->active to drop, but it * never drops in Thread 2 which is blocked * on getting rdtgroup_mutex. */ Thread 1 hangs here ----> wait_event(sub_kn->active == KN_DEACTIVATED_BIAS) ... rdtgroup_mkdir rdtgroup_mkdir_mon(parent_kn, prgrp_kn) mkdir_rdt_prepare(parent_kn, prgrp_kn) rdtgroup_kn_lock_live(prgrp_kn) atomic_inc(&rdtgrp->waitcount) /* * "c1", prgrp_kn->active-- * * The active reference on "c1" is * dropped, but not matching the * actual active reference taken * on "mon_groups", thus causing * Thread 1 to wait forever while * holding rdtgroup_mutex. */ kernfs_break_active_protection( prgrp_kn) /* * Trying to get rdtgroup_mutex * which is held by Thread 1. */ Thread 2 hangs here ----> mutex_lock ... The problem is that the creation of a subdirectory in the "mon_groups" directory incorrectly releases the active protection of its parent directory instead of itself before it starts waiting for rdtgroup_mutex. This is triggered by the rdtgroup_mkdir() flow calling rdtgroup_kn_lock_live()/rdtgroup_kn_unlock() with kernfs node of the parent control group ("c1") as argument. It should be called with kernfs node "mon_groups" instead. What is currently missing is that the kn->priv of "mon_groups" is NULL instead of pointing to the rdtgrp. Fix it by pointing kn->priv to rdtgrp when "mon_groups" is created. Then it could be passed to rdtgroup_kn_lock_live()/rdtgroup_kn_unlock() instead. And then it operates on the same rdtgroup structure but handles the active reference of kernfs node "mon_groups" to prevent deadlock. The same changes are also made to the "mon_data" directories. This results in some unused function parameters that will be cleaned up in follow-up patch as the focus here is on the fix only in support of backporting efforts. Fixes: c7d9aac61311 ("x86/intel_rdt/cqm: Add mkdir support for RDT monitoring") Suggested-by: Reinette Chatre Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Reviewed-by: Tony Luck Acked-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1578500886-21771-4-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index caab397287ff..954fd048ad9b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1970,7 +1970,7 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, - NULL, "mon_groups", + &rdtgroup_default, "mon_groups", &kn_mongrp); if (ret < 0) goto out_info; @@ -2454,7 +2454,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, /* * Create the mon_data directory first. */ - ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn); if (ret) return ret; @@ -2653,7 +2653,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, uint files = 0; int ret; - prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); + prdtgrp = rdtgroup_kn_lock_live(parent_kn); if (!prdtgrp) { ret = -ENODEV; goto out_unlock; @@ -2726,7 +2726,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kernfs_activate(kn); /* - * The caller unlocks the prgrp_kn upon success. + * The caller unlocks the parent_kn upon success. */ return 0; @@ -2737,7 +2737,7 @@ out_destroy: out_free_rgrp: kfree(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2775,7 +2775,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2818,7 +2818,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. */ - ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; @@ -2834,7 +2834,7 @@ out_id_free: out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } -- cgit v1.2.3 From 32ada3b9e04c6f6d4916967bd8bbe2450ad5bc5e Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Thu, 9 Jan 2020 00:28:06 +0800 Subject: x86/resctrl: Clean up unused function parameter in mkdir path Commit 334b0f4e9b1b ("x86/resctrl: Fix a deadlock due to inaccurate reference") changed the argument to rdtgroup_kn_lock_live()/rdtgroup_kn_unlock() within mkdir_rdt_prepare(). That change resulted in an unused function parameter to mkdir_rdt_prepare(). Clean up the unused function parameter in mkdir_rdt_prepare() and its callers rdtgroup_mkdir_mon() and rdtgroup_mkdir_ctrl_mon(). Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Reviewed-by: Tony Luck Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1578500886-21771-5-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 954fd048ad9b..2804562dbe0f 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2644,7 +2644,6 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) { @@ -2754,15 +2753,12 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) * to monitor a subset of tasks and cpus in its parent ctrl_mon group. */ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, - const char *name, - umode_t mode) + const char *name, umode_t mode) { struct rdtgroup *rdtgrp, *prgrp; int ret; - ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP, - &rdtgrp); + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp); if (ret) return ret; @@ -2784,7 +2780,6 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, * to allocate and monitor resources. */ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, const char *name, umode_t mode) { struct rdtgroup *rdtgrp; @@ -2792,8 +2787,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, u32 closid; int ret; - ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP, - &rdtgrp); + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp); if (ret) return ret; @@ -2867,14 +2861,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, * subdirectory */ if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) - return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode); + return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); /* * If RDT monitoring is supported and the parent directory is a valid * "mon_groups" directory, add a monitoring subdirectory. */ if (rdt_mon_capable && is_mon_groups(parent_kn, name)) - return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode); + return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; } -- cgit v1.2.3 From 8b7e20a7ba54836076ff35a28349dabea4cec48f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 22 Jan 2020 13:11:54 +0900 Subject: x86/decoder: Add TEST opcode to Group3-2 Add TEST opcode to Group3-2 reg=001b as same as Group3-1 does. Commit 12a78d43de76 ("x86/decoder: Add new TEST instruction pattern") added a TEST opcode assignment to f6 XX/001/XXX (Group 3-1), but did not add f7 XX/001/XXX (Group 3-2). Actually, this TEST opcode variant (ModRM.reg /1) is not described in the Intel SDM Vol2 but in AMD64 Architecture Programmer's Manual Vol.3, Appendix A.2 Table A-6. ModRM.reg Extensions for the Primary Opcode Map. Without this fix, Randy found a warning by insn_decoder_test related to this issue as below. HOSTCC arch/x86/tools/insn_decoder_test HOSTCC arch/x86/tools/insn_sanity TEST posttest arch/x86/tools/insn_decoder_test: warning: Found an x86 instruction decoder bug, please report this. arch/x86/tools/insn_decoder_test: warning: ffffffff81000bf1: f7 0b 00 01 08 00 testl $0x80100,(%rbx) arch/x86/tools/insn_decoder_test: warning: objdump says 6 bytes, but insn_get_length() says 2 arch/x86/tools/insn_decoder_test: warning: Decoded and checked 11913894 instructions with 1 failures TEST posttest arch/x86/tools/insn_sanity: Success: decoded and checked 1000000 random instructions with 0 errors (seed:0x871ce29c) To fix this error, add the TEST opcode according to AMD64 APM Vol.3. [ bp: Massage commit message. ] Reported-by: Randy Dunlap Signed-off-by: Masami Hiramatsu Signed-off-by: Borislav Petkov Acked-by: Randy Dunlap Tested-by: Randy Dunlap Link: https://lkml.kernel.org/r/157966631413.9580.10311036595431878351.stgit@devnote2 --- arch/x86/lib/x86-opcode-map.txt | 2 +- tools/arch/x86/lib/x86-opcode-map.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 8908c58bd6cd..53adc1762ec0 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -929,7 +929,7 @@ EndTable GrpTable: Grp3_2 0: TEST Ev,Iz -1: +1: TEST Ev,Iz 2: NOT Ev 3: NEG Ev 4: MUL rAX,Ev diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 8908c58bd6cd..53adc1762ec0 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -929,7 +929,7 @@ EndTable GrpTable: Grp3_2 0: TEST Ev,Iz -1: +1: TEST Ev,Iz 2: NOT Ev 3: NEG Ev 4: MUL rAX,Ev -- cgit v1.2.3