Pull x86 fixes from Borislav Petkov:
- AMD's automatic IBRS doesn't enable cross-thread branch target
injection protection (STIBP) for user processes. Enable STIBP on such
systems.
- Do not delete (but put the ref instead) of AMD MCE error thresholding
sysfs kobjects when destroying them in order not to delete the kernfs
pointer prematurely
- Restore annotation in ret_from_fork_asm() in order to fix kthread
stack unwinding from being marked as unreliable and thus breaking
livepatching
* tag 'x86_urgent_for_v6.5_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Enable STIBP on AMD if Automatic IBRS is enabled
x86/MCE/AMD: Decrement threshold_bank refcount when removing threshold blocks
x86: Fix kthread unwind
Commit c4e34dd99f ("x86: simplify load_unaligned_zeropad()
implementation") changes how exceptions around load_unaligned_zeropad()
handled. The kernel now uses the fault_address in fixup_exception() to
verify the address calculations for the load_unaligned_zeropad().
It works fine for #PF, but breaks on #VE since no fault address is
passed down to fixup_exception().
Propagating ve_info.gla down to fixup_exception() resolves the issue.
See commit 1e7769653b ("x86/tdx: Handle load_unaligned_zeropad()
page-cross to a shared page") for more context.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Michael Kelley <mikelley@microsoft.com>
Fixes: c4e34dd99f ("x86: simplify load_unaligned_zeropad() implementation")
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
AMD systems from Family 10h to 16h share MCA bank 4 across multiple CPUs.
Therefore, the threshold_bank structure for bank 4, and its threshold_block
structures, will be initialized once at boot time. And the kobject for the
shared bank will be added to each of the CPUs that share it. Furthermore,
the threshold_blocks for the shared bank will be added again to the bank's
kobject. These additions will increase the refcount for the bank's kobject.
For example, a shared bank with two blocks and shared across two CPUs will
be set up like this:
CPU0 init
bank create and add; bank refcount = 1; threshold_create_bank()
block 0 init and add; bank refcount = 2; allocate_threshold_blocks()
block 1 init and add; bank refcount = 3; allocate_threshold_blocks()
CPU1 init
bank add; bank refcount = 3; threshold_create_bank()
block 0 add; bank refcount = 4; __threshold_add_blocks()
block 1 add; bank refcount = 5; __threshold_add_blocks()
Currently in threshold_remove_bank(), if the bank is shared then
__threshold_remove_blocks() is called. Here the shared bank's kobject and
the bank's blocks' kobjects are deleted. This is done on the first call
even while the structures are still shared. Subsequent calls from other
CPUs that share the structures will attempt to delete the kobjects.
During kobject_del(), kobject->sd is removed. If the kobject is not part of
a kset with default_groups, then subsequent kobject_del() calls seem safe
even with kobject->sd == NULL.
Originally, the AMD MCA thresholding structures did not use default_groups.
And so the above behavior was not apparent.
However, a recent change implemented default_groups for the thresholding
structures. Therefore, kobject_del() will go down the sysfs_remove_groups()
code path. In this case, the first kobject_del() may succeed and remove
kobject->sd. But subsequent kobject_del() calls will give a WARNing in
kernfs_remove_by_name_ns() since kobject->sd == NULL.
Use kobject_put() on the shared bank's kobject when "removing" blocks. This
decrements the bank's refcount while keeping kobjects enabled until the
bank is no longer shared. At that point, kobject_put() will be called on
the blocks which drives their refcount to 0 and deletes them and also
decrementing the bank's refcount. And finally kobject_put() will be called
on the bank driving its refcount to 0 and deleting it.
The same example above:
CPU1 shutdown
bank is shared; bank refcount = 5; threshold_remove_bank()
block 0 put parent bank; bank refcount = 4; __threshold_remove_blocks()
block 1 put parent bank; bank refcount = 3; __threshold_remove_blocks()
CPU0 shutdown
bank is no longer shared; bank refcount = 3; threshold_remove_bank()
block 0 put block; bank refcount = 2; deallocate_threshold_blocks()
block 1 put block; bank refcount = 1; deallocate_threshold_blocks()
put bank; bank refcount = 0; threshold_remove_bank()
Fixes: 7f99cb5e60 ("x86/CPU/AMD: Use default_groups in kobj_type")
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/alpine.LRH.2.02.2205301145540.25840@file01.intranet.prod.int.rdu2.redhat.com
Add a fix for the Zen2 VZEROUPPER data corruption bug where under
certain circumstances executing VZEROUPPER can cause register
corruption or leak data.
The optimal fix is through microcode but in the case the proper
microcode revision has not been applied, enable a fallback fix using
a chicken bit.
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Pull x86 CFI fixes from Peter Zijlstra:
"Fix kCFI/FineIBT weaknesses
The primary bug Alyssa noticed was that with FineIBT enabled function
prologues have a spurious ENDBR instruction:
__cfi_foo:
endbr64
subl $hash, %r10d
jz 1f
ud2
nop
1:
foo:
endbr64 <--- *sadface*
This means that any indirect call that fails to target the __cfi
symbol and instead targets (the regular old) foo+0, will succeed due
to that second ENDBR.
Fixing this led to the discovery of a single indirect call that was
still doing this: ret_from_fork(). Since that's an assembly stub the
compiler would not generate the proper kCFI indirect call magic and it
would not get patched.
Brian came up with the most comprehensive fix -- convert the thing to
C with only a very thin asm wrapper. This ensures the kernel thread
boostrap is a proper kCFI call.
While discussing all this, Kees noted that kCFI hashes could/should be
poisoned to seal all functions whose address is never taken, further
limiting the valid kCFI targets -- much like we already do for IBT.
So what was a 'simple' observation and fix cascaded into a bunch of
inter-related CFI infrastructure fixes"
* tag 'x86_urgent_for_6.5_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cfi: Only define poison_cfi() if CONFIG_X86_KERNEL_IBT=y
x86/fineibt: Poison ENDBR at +0
x86: Rewrite ret_from_fork() in C
x86/32: Remove schedule_tail_wrapper()
x86/cfi: Extend ENDBR sealing to kCFI
x86/alternative: Rename apply_ibt_endbr()
x86/cfi: Extend {JMP,CAKK}_NOSPEC comment
poison_cfi() was introduced in:
9831c6253a ("x86/cfi: Extend ENDBR sealing to kCFI")
... but it's only ever used under CONFIG_X86_KERNEL_IBT=y,
and if that option is disabled, we get:
arch/x86/kernel/alternative.c:1243:13: error: ‘poison_cfi’ defined but not used [-Werror=unused-function]
Guard the definition with CONFIG_X86_KERNEL_IBT.
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Alyssa noticed that when building the kernel with CFI_CLANG+IBT and
booting on IBT enabled hardware to obtain FineIBT, the indirect
functions look like:
__cfi_foo:
endbr64
subl $hash, %r10d
jz 1f
ud2
nop
1:
foo:
endbr64
This is because the compiler generates code for kCFI+IBT. In that case
the caller does the hash check and will jump to +0, so there must be
an ENDBR there. The compiler doesn't know about FineIBT at all; also
it is possible to actually use kCFI+IBT when booting with 'cfi=kcfi'
on IBT enabled hardware.
Having this second ENDBR however makes it possible to elide the CFI
check. Therefore, we should poison this second ENDBR when switching to
FineIBT mode.
Fixes: 931ab63664 ("x86/ibt: Implement FineIBT")
Reported-by: "Milburn, Alyssa" <alyssa.milburn@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20230615193722.194131053@infradead.org
Kees noted that IBT sealing could be extended to kCFI.
Fundamentally it is the list of functions that do not have their
address taken and are thus never called indirectly. It doesn't matter
that objtool uses IBT infrastructure to determine this list, once we
have it it can also be used to clobber kCFI hashes and avoid kCFI
indirect calls.
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lkml.kernel.org/r/20230622144321.494426891%40infradead.org
Pull x86 fix from Thomas Gleixner:
"A single fix for the mechanism to park CPUs with an INIT IPI.
On shutdown or kexec, the kernel tries to park the non-boot CPUs with
an INIT IPI. But the same code path is also used by the crash utility.
If the CPU which panics is not the boot CPU then it sends an INIT IPI
to the boot CPU which resets the machine.
Prevent this by validating that the CPU which runs the stop mechanism
is the boot CPU. If not, leave the other CPUs in HLT"
* tag 'x86-core-2023-07-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/smp: Don't send INIT to boot CPU
Parking CPUs in INIT works well, except for the crash case when the CPU
which invokes smp_park_other_cpus_in_init() is not the boot CPU. Sending
INIT to the boot CPU resets the whole machine.
Prevent this by validating that this runs on the boot CPU. If not fall back
and let CPUs hang in HLT.
Fixes: 45e34c8af5 ("x86/smp: Put CPUs into INIT on shutdown if possible")
Reported-by: Baokun Li <libaokun1@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Baokun Li <libaokun1@huawei.com>
Link: https://lore.kernel.org/r/87ttui91jo.ffs@tglx
Pull tracing updates from Steven Rostedt:
- Add new feature to have function graph tracer record the return
value. Adds a new option: funcgraph-retval ; when set, will show the
return value of a function in the function graph tracer.
- Also add the option: funcgraph-retval-hex where if it is not set, and
the return value is an error code, then it will return the decimal of
the error code, otherwise it still reports the hex value.
- Add the file /sys/kernel/tracing/osnoise/per_cpu/cpu<cpu>/timerlat_fd
That when a application opens it, it becomes the task that the timer
lat tracer traces. The application can also read this file to find
out how it's being interrupted.
- Add the file /sys/kernel/tracing/available_filter_functions_addrs
that works just the same as available_filter_functions but also shows
the addresses of the functions like kallsyms, except that it gives
the address of where the fentry/mcount jump/nop is. This is used by
BPF to make it easier to attach BPF programs to ftrace hooks.
- Replace strlcpy with strscpy in the tracing boot code.
* tag 'trace-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing: Fix warnings when building htmldocs for function graph retval
riscv: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
tracing/boot: Replace strlcpy with strscpy
tracing/timerlat: Add user-space interface
tracing/osnoise: Skip running osnoise if all instances are off
tracing/osnoise: Switch from PF_NO_SETAFFINITY to migrate_disable
ftrace: Show all functions with addresses in available_filter_functions_addrs
selftests/ftrace: Add funcgraph-retval test case
LoongArch: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
x86/ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
arm64: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
tracing: Add documentation for funcgraph-retval and funcgraph-retval-hex
function_graph: Support recording and printing the return value of function
fgraph: Add declaration of "struct fgraph_ret_regs"
Pull mm updates from Andrew Morton:
- Yosry Ahmed brought back some cgroup v1 stats in OOM logs
- Yosry has also eliminated cgroup's atomic rstat flushing
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning
- Lorenzo Stoakes has done some maintanance work on the
get_user_pages() interface
- Liam Howlett continues with cleanups and maintenance work to the
maple tree code. Peng Zhang also does some work on maple tree
- Johannes Weiner has done some cleanup work on the compaction code
- David Hildenbrand has contributed additional selftests for
get_user_pages()
- Thomas Gleixner has contributed some maintenance and optimization
work for the vmalloc code
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting
- Christoph Hellwig has some cleanups for the filemap/directio code
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the
provided APIs rather than open-coding accesses
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings
- John Hubbard has a series of fixes to the MM selftesting code
- ZhangPeng continues the folio conversion campaign
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
from 128 to 8
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code
- Vishal Moola also has done some folio conversion work
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch
* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
mm/hugetlb: remove hugetlb_set_page_subpool()
mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
hugetlb: revert use of page_cache_next_miss()
Revert "page cache: fix page_cache_next/prev_miss off by one"
mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
mm: memcg: rename and document global_reclaim()
mm: kill [add|del]_page_to_lru_list()
mm: compaction: convert to use a folio in isolate_migratepages_block()
mm: zswap: fix double invalidate with exclusive loads
mm: remove unnecessary pagevec includes
mm: remove references to pagevec
mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
mm: remove struct pagevec
net: convert sunrpc from pagevec to folio_batch
i915: convert i915_gpu_error to use a folio_batch
pagevec: rename fbatch_count()
mm: remove check_move_unevictable_pages()
drm: convert drm_gem_put_pages() to use a folio_batch
i915: convert shmem_sg_free_table() to use a folio_batch
scatterlist: add sg_set_folio()
...
Pull xen updates from Juergen Gross:
- three patches adding missing prototypes
- a fix for finding the iBFT in a Xen dom0 for supporting diskless
iSCSI boot
* tag 'for-linus-6.5-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
x86: xen: add missing prototypes
x86/xen: add prototypes for paravirt mmu functions
iscsi_ibft: Fix finding the iBFT under Xen Dom 0
xen: xen_debug_interrupt prototype to global header
Pull objtool updates from Ingo Molar:
"Build footprint & performance improvements:
- Reduce memory usage with CONFIG_DEBUG_INFO=y
In the worst case of an allyesconfig+CONFIG_DEBUG_INFO=y kernel,
DWARF creates almost 200 million relocations, ballooning objtool's
peak heap usage to 53GB. These patches reduce that to 25GB.
On a distro-type kernel with kernel IBT enabled, they reduce
objtool's peak heap usage from 4.2GB to 2.8GB.
These changes also improve the runtime significantly.
Debuggability improvements:
- Add the unwind_debug command-line option, for more extend unwinding
debugging output
- Limit unreachable warnings to once per function
- Add verbose option for disassembling affected functions
- Include backtrace in verbose mode
- Detect missing __noreturn annotations
- Ignore exc_double_fault() __noreturn warnings
- Remove superfluous global_noreturns entries
- Move noreturn function list to separate file
- Add __kunit_abort() to noreturns
Unwinder improvements:
- Allow stack operations in UNWIND_HINT_UNDEFINED regions
- drm/vmwgfx: Add unwind hints around RBP clobber
Cleanups:
- Move the x86 entry thunk restore code into thunk functions
- x86/unwind/orc: Use swap() instead of open coding it
- Remove unnecessary/unused variables
Fixes for modern stack canary handling"
* tag 'objtool-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
x86/orc: Make the is_callthunk() definition depend on CONFIG_BPF_JIT=y
objtool: Skip reading DWARF section data
objtool: Free insns when done
objtool: Get rid of reloc->rel[a]
objtool: Shrink elf hash nodes
objtool: Shrink reloc->sym_reloc_entry
objtool: Get rid of reloc->jump_table_start
objtool: Get rid of reloc->addend
objtool: Get rid of reloc->type
objtool: Get rid of reloc->offset
objtool: Get rid of reloc->idx
objtool: Get rid of reloc->list
objtool: Allocate relocs in advance for new rela sections
objtool: Add for_each_reloc()
objtool: Don't free memory in elf_close()
objtool: Keep GElf_Rel[a] structs synced
objtool: Add elf_create_section_pair()
objtool: Add mark_sec_changed()
objtool: Fix reloc_hash size
objtool: Consolidate rel/rela handling
...
Pull locking updates from Ingo Molnar:
- Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()
The cmpxchg128() family of functions is basically & functionally the
same as cmpxchg_double(), but with a saner interface.
Instead of a 6-parameter horror that forced u128 - u64/u64-halves
layout details on the interface and exposed users to complexity,
fragility & bugs, use a natural 3-parameter interface with u128
types.
- Restructure the generated atomic headers, and add kerneldoc comments
for all of the generic atomic{,64,_long}_t operations.
The generated definitions are much cleaner now, and come with
documentation.
- Implement lock_set_cmp_fn() on lockdep, for defining an ordering when
taking multiple locks of the same type.
This gets rid of one use of lockdep_set_novalidate_class() in the
bcache code.
- Fix raw_cpu_generic_try_cmpxchg() bug due to an unintended variable
shadowing generating garbage code on Clang on certain ARM builds.
* tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
locking/atomic: scripts: fix ${atomic}_dec_if_positive() kerneldoc
percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg()
locking/atomic: treewide: delete arch_atomic_*() kerneldoc
locking/atomic: docs: Add atomic operations to the driver basic API documentation
locking/atomic: scripts: generate kerneldoc comments
docs: scripts: kernel-doc: accept bitwise negation like ~@var
locking/atomic: scripts: simplify raw_atomic*() definitions
locking/atomic: scripts: simplify raw_atomic_long*() definitions
locking/atomic: scripts: split pfx/name/sfx/order
locking/atomic: scripts: restructure fallback ifdeffery
locking/atomic: scripts: build raw_atomic_long*() directly
locking/atomic: treewide: use raw_atomic*_<op>()
locking/atomic: scripts: add trivial raw_atomic*_<op>()
locking/atomic: scripts: factor out order template generation
locking/atomic: scripts: remove leftover "${mult}"
locking/atomic: scripts: remove bogus order parameter
locking/atomic: xtensa: add preprocessor symbols
locking/atomic: x86: add preprocessor symbols
locking/atomic: sparc: add preprocessor symbols
locking/atomic: sh: add preprocessor symbols
...
Pull scheduler updates from Ingo Molnar:
"Scheduler SMP load-balancer improvements:
- Avoid unnecessary migrations within SMT domains on hybrid systems.
Problem:
On hybrid CPU systems, (processors with a mixture of
higher-frequency SMT cores and lower-frequency non-SMT cores),
under the old code lower-priority CPUs pulled tasks from the
higher-priority cores if more than one SMT sibling was busy -
resulting in many unnecessary task migrations.
Solution:
The new code improves the load balancer to recognize SMT cores
with more than one busy sibling and allows lower-priority CPUs
to pull tasks, which avoids superfluous migrations and lets
lower-priority cores inspect all SMT siblings for the busiest
queue.
- Implement the 'runnable boosting' feature in the EAS balancer:
consider CPU contention in frequency, EAS max util & load-balance
busiest CPU selection.
This improves CPU utilization for certain workloads, while leaves
other key workloads unchanged.
Scheduler infrastructure improvements:
- Rewrite the scheduler topology setup code by consolidating it into
the build_sched_topology() helper function and building it
dynamically on the fly.
- Resolve the local_clock() vs. noinstr complications by rewriting
the code: provide separate sched_clock_noinstr() and
local_clock_noinstr() functions to be used in instrumentation code,
and make sure it is all instrumentation-safe.
Fixes:
- Fix a kthread_park() race with wait_woken()
- Fix misc wait_task_inactive() bugs unearthed by the -rt merge:
- Fix UP PREEMPT bug by unifying the SMP and UP implementations
- Fix task_struct::saved_state handling
- Fix various rq clock update bugs, unearthed by turning on the rq
clock debugging code.
- Fix the PSI WINDOW_MIN_US trigger limit, which was easy to trigger
by creating enough cgroups, by removing the warnign and restricting
window size triggers to PSI file write-permission or
CAP_SYS_RESOURCE.
- Propagate SMT flags in the topology when removing degenerate domain
- Fix grub_reclaim() calculation bug in the deadline scheduler code
- Avoid resetting the min update period when it is unnecessary, in
psi_trigger_destroy().
- Don't balance a task to its current running CPU in load_balance(),
which was possible on certain NUMA topologies with overlapping
groups.
- Fix the sched-debug printing of rq->nr_uninterruptible
Cleanups:
- Address various -Wmissing-prototype warnings, as a preparation to
(maybe) enable this warning in the future.
- Remove unused code
- Mark more functions __init
- Fix shadow-variable warnings"
* tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()
sched/core: Fixed missing rq clock update before calling set_rq_offline()
sched/deadline: Update GRUB description in the documentation
sched/deadline: Fix bandwidth reclaim equation in GRUB
sched/wait: Fix a kthread_park race with wait_woken()
sched/topology: Mark set_sched_topology() __init
sched/fair: Rename variable cpu_util eff_util
arm64/arch_timer: Fix MMIO byteswap
sched/fair, cpufreq: Introduce 'runnable boosting'
sched/fair: Refactor CPU utilization functions
cpuidle: Use local_clock_noinstr()
sched/clock: Provide local_clock_noinstr()
x86/tsc: Provide sched_clock_noinstr()
clocksource: hyper-v: Provide noinstr sched_clock()
clocksource: hyper-v: Adjust hv_read_tsc_page_tsc() to avoid special casing U64_MAX
x86/vdso: Fix gettimeofday masking
math64: Always inline u128 version of mul_u64_u64_shr()
s390/time: Provide sched_clock_noinstr()
loongarch: Provide noinstr sched_clock_read()
...
Pull SGX update from Borislav Petkov:
- A fix to avoid using a list iterator variable after the loop it is
used in
* tag 'x86_sgx_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/sgx: Avoid using iterator after loop in sgx_mmu_notifier_release()
Pull x86 SEV updates from Borislav Petkov:
- Some SEV and CC platform helpers cleanup and simplifications now that
the usage patterns are becoming apparent
[ I'm sure I'm the only one that has gets confused by all the TLAs, but
in case there are others: here SEV is AMD's "Secure Encrypted
Virtualization" and CC is generic "Confidential Computing".
There's also Intel SGX (Software Guard Extensions) and TDX (Trust
Domain Extensions), along with all the vendor memory encryption
extensions (SME, TSME, TME, and WTF).
And then we have arm64 with RMA and CCA, and I probably forgot another
dozen or so related acronyms - Linus ]
* tag 'x86_sev_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/coco: Get rid of accessor functions
x86/sev: Get rid of special sev_es_enable_key
x86/coco: Mark cc_platform_has() and descendants noinstr
Pull x86 mtrr updates from Borislav Petkov:
"A serious scrubbing of the MTRR code including adding a new map
mechanism in order to look up the memory type of a region easily.
Also address memory range lookup issues like returning an invalid
memory type. Furthermore, this handles the decoupling of PAT from MTRR
more naturally.
All work by Juergen Gross"
* tag 'x86_mtrr_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/xen: Set default memory type for PV guests to WB
x86/mtrr: Unify debugging printing
x86/mtrr: Remove unused code
x86/mm: Only check uniform after calling mtrr_type_lookup()
x86/mtrr: Don't let mtrr_type_lookup() return MTRR_TYPE_INVALID
x86/mtrr: Use new cache_map in mtrr_type_lookup()
x86/mtrr: Add mtrr=debug command line option
x86/mtrr: Construct a memory map with cache modes
x86/mtrr: Add get_effective_type() service function
x86/mtrr: Allocate mtrr_value array dynamically
x86/mtrr: Move 32-bit code from mtrr.c to legacy.c
x86/mtrr: Have only one set_mtrr() variant
x86/mtrr: Replace vendor tests in MTRR code
x86/xen: Set MTRR state when running as Xen PV initial domain
x86/hyperv: Set MTRR state when running as SEV-SNP Hyper-V guest
x86/mtrr: Support setting MTRR state for software defined MTRRs
x86/mtrr: Replace size_or_mask and size_and_mask with a much easier concept
x86/mtrr: Remove physical address size calculation
Pull x86 microcode loader updates from Borislav Petkov:
- Load late on both SMT threads on AMD, just like it is being done in
the early loading procedure
- Cleanups
* tag 'x86_microcode_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/microcode/AMD: Load late on both threads too
x86/microcode/amd: Remove unneeded pointer arithmetic
x86/microcode/AMD: Get rid of __find_equiv_id()
Pull x86 cleanups from Dave Hansen:
"As usual, these are all over the map. The biggest cluster is work from
Arnd to eliminate -Wmissing-prototype warnings:
- Address -Wmissing-prototype warnings
- Remove repeated 'the' in comments
- Remove unused current_untag_mask()
- Document urgent tip branch timing
- Clean up MSR kernel-doc notation
- Clean up paravirt_ops doc
- Update Srivatsa S. Bhat's maintained areas
- Remove unused extern declaration acpi_copy_wakeup_routine()"
* tag 'x86_cleanups_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
x86/acpi: Remove unused extern declaration acpi_copy_wakeup_routine()
Documentation: virt: Clean up paravirt_ops doc
x86/mm: Remove unused current_untag_mask()
x86/mm: Remove repeated word in comments
x86/lib/msr: Clean up kernel-doc notation
x86/platform: Avoid missing-prototype warnings for OLPC
x86/mm: Add early_memremap_pgprot_adjust() prototype
x86/usercopy: Include arch_wb_cache_pmem() declaration
x86/vdso: Include vdso/processor.h
x86/mce: Add copy_mc_fragile_handle_tail() prototype
x86/fbdev: Include asm/fb.h as needed
x86/hibernate: Declare global functions in suspend.h
x86/entry: Add do_SYSENTER_32() prototype
x86/quirks: Include linux/pnp.h for arch_pnpbios_disabled()
x86/mm: Include asm/numa.h for set_highmem_pages_init()
x86: Avoid missing-prototype warnings for doublefault code
x86/fpu: Include asm/fpu/regset.h
x86: Add dummy prototype for mk_early_pgtbl_32()
x86/pci: Mark local functions as 'static'
x86/ftrace: Move prepare_ftrace_return prototype to header
...
Pull x86 tdx updates from Dave Hansen:
- Fix a race window where load_unaligned_zeropad() could cause a fatal
shutdown during TDX private<=>shared conversion
The race has never been observed in practice but might allow
load_unaligned_zeropad() to catch a TDX page in the middle of its
conversion process which would lead to a fatal and unrecoverable
guest shutdown.
- Annotate sites where VM "exit reasons" are reused as hypercall
numbers.
* tag 'x86_tdx_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Fix enc_status_change_finish_noop()
x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()
x86/mm: Allow guest.enc_status_change_prepare() to fail
x86/tdx: Wrap exit reason with hcall_func()
Pull x86 platform updates from Dave Hansen:
"Allow CPUs in SGX/HPE Ultraviolet to start using Sub-NUMA clustering
(SNC) mode. SNC has been around outside the UV world for a while but
evidently never worked on UV systems.
SNC is rather notorious for breaking bad assumptions of a 1:1
relationship between physical sockets and NUMA nodes. The UV code was
rather prolific with these assumptions and took quite a bit of
refactoring to remove them"
* tag 'x86_platform_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/platform/uv: Update UV[23] platform code for SNC
x86/platform/uv: Remove remaining BUG_ON() and BUG() calls
x86/platform/uv: UV support for sub-NUMA clustering
x86/platform/uv: Helper functions for allocating and freeing conversion tables
x86/platform/uv: When searching for minimums, start at INT_MAX not 99999
x86/platform/uv: Fix printed information in calc_mmioh_map
x86/platform/uv: Introduce helper function uv_pnode_to_socket.
x86/platform/uv: Add platform resolving #defines for misc GAM_MMIOH_REDIRECT*
Pull x86 irq updates from Dave Hansen:
"Add Hyper-V interrupts to /proc/stat"
* tag 'x86_irq_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/irq: Add hardcoded hypervisor interrupts to /proc/stat
Pull x86 cpu updates from Borislav Petkov:
- Compute the purposeful misalignment of zen_untrain_ret automatically
and assert __x86_return_thunk's alignment so that future changes to
the symbol macros do not accidentally break them.
- Remove CONFIG_X86_FEATURE_NAMES Kconfig option as its existence is
pointless
* tag 'x86_cpu_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/retbleed: Add __x86_return_thunk alignment checks
x86/cpu: Remove X86_FEATURE_NAMES
x86/Kconfig: Make X86_FEATURE_NAMES non-configurable in prompt
Pull x86 confidential computing update from Borislav Petkov:
- Add support for unaccepted memory as specified in the UEFI spec v2.9.
The gist of it all is that Intel TDX and AMD SEV-SNP confidential
computing guests define the notion of accepting memory before using
it and thus preventing a whole set of attacks against such guests
like memory replay and the like.
There are a couple of strategies of how memory should be accepted -
the current implementation does an on-demand way of accepting.
* tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
virt: sevguest: Add CONFIG_CRYPTO dependency
x86/efi: Safely enable unaccepted memory in UEFI
x86/sev: Add SNP-specific unaccepted memory support
x86/sev: Use large PSC requests if applicable
x86/sev: Allow for use of the early boot GHCB for PSC requests
x86/sev: Put PSC struct on the stack in prep for unaccepted memory support
x86/sev: Fix calculation of end address based on number of pages
x86/tdx: Add unaccepted memory support
x86/tdx: Refactor try_accept_one()
x86/tdx: Make _tdx_hypercall() and __tdx_module_call() available in boot stub
efi/unaccepted: Avoid load_unaligned_zeropad() stepping into unaccepted memory
efi: Add unaccepted memory support
x86/boot/compressed: Handle unaccepted memory
efi/libstub: Implement support for unaccepted memory
efi/x86: Get full memory map in allocate_e820()
mm: Add support for unaccepted memory
Pull x86 resource control updates from Borislav Petkov:
- Implement a rename operation in resctrlfs to facilitate handling of
application containers with dynamically changing task lists
- When reading the tasks file, show the tasks' pid which are only in
the current namespace as opposed to showing the pids from the init
namespace too
- Other fixes and improvements
* tag 'x86_cache_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
Documentation/x86: Documentation for MON group move feature
x86/resctrl: Implement rename op for mon groups
x86/resctrl: Factor rdtgroup lock for multi-file ops
x86/resctrl: Only show tasks' pid in current pid namespace
Pull x86 instruction alternatives updates from Borislav Petkov:
- Up until now the Fast Short Rep Mov optimizations implied the
presence of the ERMS CPUID flag. AMD decoupled them with a BIOS
setting so decouple that dependency in the kernel code too
- Teach the alternatives machinery to handle relocations
- Make debug_alternative accept flags in order to see only that set of
patching done one is interested in
- Other fixes, cleanups and optimizations to the patching code
* tag 'x86_alternatives_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/alternative: PAUSE is not a NOP
x86/alternatives: Add cond_resched() to text_poke_bp_batch()
x86/nospec: Shorten RESET_CALL_DEPTH
x86/alternatives: Add longer 64-bit NOPs
x86/alternatives: Fix section mismatch warnings
x86/alternative: Optimize returns patching
x86/alternative: Complicate optimize_nops() some more
x86/alternative: Rewrite optimize_nops() some
x86/lib/memmove: Decouple ERMS from FSRM
x86/alternative: Support relocations in alternatives
x86/alternative: Make debug-alternative selective
Pull RAS updates from Borislav Petkov:
- Add initial support for RAS hardware found on AMD server GPUs (MI200).
Those GPUs and CPUs are connected together through the coherent
fabric and the GPU memory controllers report errors through x86's MCA
so EDAC needs to support them. The amd64_edac driver supports now HBM
(High Bandwidth Memory) and thus such heterogeneous memory controller
systems
- Other small cleanups and improvements
* tag 'ras_core_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
EDAC/amd64: Cache and use GPU node map
EDAC/amd64: Add support for AMD heterogeneous Family 19h Model 30h-3Fh
EDAC/amd64: Document heterogeneous system enumeration
x86/MCE/AMD, EDAC/mce_amd: Decode UMC_V2 ECC errors
x86/amd_nb: Re-sort and re-indent PCI defines
x86/amd_nb: Add MI200 PCI IDs
ras/debugfs: Fix error checking for debugfs_create_dir()
x86/MCE: Check a hw error's address to determine proper recovery action
Pull x86 core updates from Thomas Gleixner:
"A set of fixes for kexec(), reboot and shutdown issues:
- Ensure that the WBINVD in stop_this_cpu() has been completed before
the control CPU proceedes.
stop_this_cpu() is used for kexec(), reboot and shutdown to park
the APs in a HLT loop.
The control CPU sends an IPI to the APs and waits for their CPU
online bits to be cleared. Once they all are marked "offline" it
proceeds.
But stop_this_cpu() clears the CPU online bit before issuing
WBINVD, which means there is no guarantee that the AP has reached
the HLT loop.
This was reported to cause intermittent reboot/shutdown failures
due to some dubious interaction with the firmware.
This is not only a problem of WBINVD. The code to actually "stop"
the CPU which runs between clearing the online bit and reaching the
HLT loop can cause large enough delays on its own (think
virtualization). That's especially dangerous for kexec() as kexec()
expects that all APs are in a safe state and not executing code
while the boot CPU jumps to the new kernel. There are more issues
vs kexec() which are addressed separately.
Cure this by implementing an explicit synchronization point right
before the AP reaches HLT. This guarantees that the AP has
completed the full stop proceedure.
- Fix the condition for WBINVD in stop_this_cpu().
The WBINVD in stop_this_cpu() is required for ensuring that when
switching to or from memory encryption no dirty data is left in the
cache lines which might cause a write back in the wrong more later.
This checks CPUID directly because the feature bit might have been
cleared due to a command line option.
But that CPUID check accesses leaf 0x8000001f::EAX unconditionally.
Intel CPUs return the content of the highest supported leaf when a
non-existing leaf is read, while AMD CPUs return all zeros for
unsupported leafs.
So the result of the test on Intel CPUs is lottery and on AMD its
just correct by chance.
While harmless it's incorrect and causes the conditional wbinvd()
to be issued where not required, which caused the above issue to be
unearthed.
- Make kexec() robust against AP code execution
Ashok observed triple faults when doing kexec() on a system which
had been booted with "nosmt".
It turned out that the SMT siblings which had been brought up
partially are parked in mwait_play_dead() to enable power savings.
mwait_play_dead() is monitoring the thread flags of the AP's idle
task, which has been chosen as it's unlikely to be written to.
But kexec() can overwrite the previous kernel text and data
including page tables etc. When it overwrites the cache lines
monitored by an AP that AP resumes execution after the MWAIT on
eventually overwritten text, stack and page tables, which obviously
might end up in a triple fault easily.
Make this more robust in several steps:
1) Use an explicit per CPU cache line for monitoring.
2) Write a command to these cache lines to kick APs out of MWAIT
before proceeding with kexec(), shutdown or reboot.
The APs confirm the wakeup by writing status back and then
enter a HLT loop.
3) If the system uses INIT/INIT/STARTUP for AP bringup, park the
APs in INIT state.
HLT is not a guarantee that an AP won't wake up and resume
execution. HLT is woken up by NMI and SMI. SMI puts the CPU
back into HLT (+/- firmware bugs), but NMI is delivered to the
CPU which executes the NMI handler. Same issue as the MWAIT
scenario described above.
Sending an INIT/INIT sequence to the APs puts them into wait
for STARTUP state, which is safe against NMI.
There is still an issue remaining which can't be fixed: #MCE
If the AP sits in HLT and receives a broadcast #MCE it will try to
handle it with the obvious consequences.
INIT/INIT clears CR4.MCE in the AP which will cause a broadcast
#MCE to shut down the machine.
So there is a choice between fire (HLT) and frying pan (INIT).
Frying pan has been chosen as it's at least preventing the NMI
issue.
On systems which are not using INIT/INIT/STARTUP there is not much
which can be done right now, but at least the obvious and easy to
trigger MWAIT issue has been addressed"
* tag 'x86-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/smp: Put CPUs into INIT on shutdown if possible
x86/smp: Split sending INIT IPI out into a helper function
x86/smp: Cure kexec() vs. mwait_play_dead() breakage
x86/smp: Use dedicated cache-line for mwait_play_dead()
x86/smp: Remove pointless wmb()s from native_stop_other_cpus()
x86/smp: Dont access non-existing CPUID leaf
x86/smp: Make stop_other_cpus() more robust
Pull SMP updates from Thomas Gleixner:
"A large update for SMP management:
- Parallel CPU bringup
The reason why people are interested in parallel bringup is to
shorten the (kexec) reboot time of cloud servers to reduce the
downtime of the VM tenants.
The current fully serialized bringup does the following per AP:
1) Prepare callbacks (allocate, intialize, create threads)
2) Kick the AP alive (e.g. INIT/SIPI on x86)
3) Wait for the AP to report alive state
4) Let the AP continue through the atomic bringup
5) Let the AP run the threaded bringup to full online state
There are two significant delays:
#3 The time for an AP to report alive state in start_secondary()
on x86 has been measured in the range between 350us and 3.5ms
depending on vendor and CPU type, BIOS microcode size etc.
#4 The atomic bringup does the microcode update. This has been
measured to take up to ~8ms on the primary threads depending
on the microcode patch size to apply.
On a two socket SKL server with 56 cores (112 threads) the boot CPU
spends on current mainline about 800ms busy waiting for the APs to
come up and apply microcode. That's more than 80% of the actual
onlining procedure.
This can be reduced significantly by splitting the bringup
mechanism into two parts:
1) Run the prepare callbacks and kick the AP alive for each AP
which needs to be brought up.
The APs wake up, do their firmware initialization and run the
low level kernel startup code including microcode loading in
parallel up to the first synchronization point. (#1 and #2
above)
2) Run the rest of the bringup code strictly serialized per CPU
(#3 - #5 above) as it's done today.
Parallelizing that stage of the CPU bringup might be possible
in theory, but it's questionable whether required surgery
would be justified for a pretty small gain.
If the system is large enough the first AP is already waiting at
the first synchronization point when the boot CPU finished the
wake-up of the last AP. That reduces the AP bringup time on that
SKL from ~800ms to ~80ms, i.e. by a factor ~10x.
The actual gain varies wildly depending on the system, CPU,
microcode patch size and other factors. There are some
opportunities to reduce the overhead further, but that needs some
deep surgery in the x86 CPU bringup code.
For now this is only enabled on x86, but the core functionality
obviously works for all SMP capable architectures.
- Enhancements for SMP function call tracing so it is possible to
locate the scheduling and the actual execution points. That allows
to measure IPI delivery time precisely"
* tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
trace,smp: Add tracepoints for scheduling remotelly called functions
trace,smp: Add tracepoints around remotelly called functions
MAINTAINERS: Add CPU HOTPLUG entry
x86/smpboot: Fix the parallel bringup decision
x86/realmode: Make stack lock work in trampoline_compat()
x86/smp: Initialize cpu_primary_thread_mask late
cpu/hotplug: Fix off by one in cpuhp_bringup_mask()
x86/apic: Fix use of X{,2}APIC_ENABLE in asm with older binutils
x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it
x86/smpboot: Support parallel startup of secondary CPUs
x86/smpboot: Implement a bit spinlock to protect the realmode stack
x86/apic: Save the APIC virtual base address
cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE
x86/apic: Provide cpu_primary_thread mask
x86/smpboot: Enable split CPU startup
cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism
cpu/hotplug: Reset task stack state in _cpu_up()
cpu/hotplug: Remove unused state functions
riscv: Switch to hotplug core state synchronization
parisc: Switch to hotplug core state synchronization
...
Pull x86 boot updates from Thomas Gleixner:
"Initialize FPU late.
Right now FPU is initialized very early during boot. There is no real
requirement to do so. The only requirement is to have it done before
alternatives are patched.
That's done in check_bugs() which does way more than what the function
name suggests.
So first rename check_bugs() to arch_cpu_finalize_init() which makes
it clear what this is about.
Move the invocation of arch_cpu_finalize_init() earlier in
start_kernel() as it has to be done before fork_init() which needs to
know the FPU register buffer size.
With those prerequisites the FPU initialization can be moved into
arch_cpu_finalize_init(), which removes it from the early and fragile
part of the x86 bringup"
* tag 'x86-boot-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mem_encrypt: Unbreak the AMD_MEM_ENCRYPT=n build
x86/fpu: Move FPU initialization into arch_cpu_finalize_init()
x86/fpu: Mark init functions __init
x86/fpu: Remove cpuinfo argument from init functions
x86/init: Initialize signal frame size late
init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init()
init: Invoke arch_cpu_finalize_init() earlier
init: Remove check_bugs() leftovers
um/cpu: Switch to arch_cpu_finalize_init()
sparc/cpu: Switch to arch_cpu_finalize_init()
sh/cpu: Switch to arch_cpu_finalize_init()
mips/cpu: Switch to arch_cpu_finalize_init()
m68k/cpu: Switch to arch_cpu_finalize_init()
loongarch/cpu: Switch to arch_cpu_finalize_init()
ia64/cpu: Switch to arch_cpu_finalize_init()
ARM: cpu: Switch to arch_cpu_finalize_init()
x86/cpu: Switch to arch_cpu_finalize_init()
init: Provide arch_cpu_finalize_init()
To facilitate diskless iSCSI boot, the firmware can place a table of
configuration details in memory called the iBFT. The presence of this
table is not specified, nor is the precise location (and it's not in the
E820) so the kernel has to search for a magic marker to find it.
When running under Xen, Dom 0 does not have access to the entire host's
memory, only certain regions which are identity-mapped which means that
the pseudo-physical address in Dom0 == real host physical address.
Add the iBFT search bounds as a reserved region which causes it to be
identity-mapped in xen_set_identity_and_remap_chunk() which allows Dom0
access to the specific physical memory to correctly search for the iBFT
magic marker (and later access the full table).
This necessitates moving the call to reserve_ibft_region() somewhat
later so that it is called after e820__memory_setup() which is when the
Xen identity mapping adjustments are applied. The precise location of
the call is not too important so I've put it alongside dmi_setup() which
does similar scanning of memory for configuration tables.
Finally in the iBFT find code, instead of using isa_bus_to_virt() which
doesn't do the right thing under Xen, use early_memremap() like the
dmi_setup() code does.
The result of these changes is that it is possible to boot a diskless
Xen + Dom0 running off an iSCSI disk whereas previously it would fail to
find the iBFT and consequently, the iSCSI root disk.
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: Konrad Rzeszutek Wilk <konrad@darnok.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com> # for x86
Link: https://lore.kernel.org/r/20230605102840.1521549-1-ross.lagerwall@citrix.com
Signed-off-by: Juergen Gross <jgross@suse.com>
Pull objtool fix from Borislav Petkov:
- Add a ORC format hash to vmlinux and modules in order for other tools
which use it, to detect changes to it and adapt accordingly
* tag 'objtool_urgent_for_v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/unwind/orc: Add ELF section with ORC version identifier
Pull x86 fixes from Borislav Petkov:
- Do not use set_pgd() when updating the KASLR trampoline pgd entry
because that updates the user PGD too on KPTI builds, resulting in
memory corruption
- Prevent a panic in the IO-APIC setup code due to conflicting command
line parameters
* tag 'x86_urgent_for_v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/apic: Fix kernel panic when booting with intremap=off and x2apic_phys
x86/mm: Avoid using set_pgd() outside of real PGD pages
The previous patch ("function_graph: Support recording and printing
the return value of function") has laid the groundwork for the for
the funcgraph-retval, and this modification makes it available on
the x86 platform.
We introduce a new structure called fgraph_ret_regs for the x86
platform to hold return registers and the frame pointer. We then
fill its content in the return_to_handler and pass its address
to the function ftrace_return_to_handler to record the return
value.
Link: https://lkml.kernel.org/r/53a506f0f18ff4b7aeb0feb762f1c9a5e9b83ee9.1680954589.git.pengdonglin@sangfor.com.cn
Signed-off-by: Donglin Peng <pengdonglin@sangfor.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Parking CPUs in a HLT loop is not completely safe vs. kexec() as HLT can
resume execution due to NMI, SMI and MCE, which has the same issue as the
MWAIT loop.
Kicking the secondary CPUs into INIT makes this safe against NMI and SMI.
A broadcast MCE will take the machine down, but a broadcast MCE which makes
HLT resume and execute overwritten text, pagetables or data will end up in
a disaster too.
So chose the lesser of two evils and kick the secondary CPUs into INIT
unless the system has installed special wakeup mechanisms which are not
using INIT.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230615193330.608657211@linutronix.de
TLDR: It's a mess.
When kexec() is executed on a system with offline CPUs, which are parked in
mwait_play_dead() it can end up in a triple fault during the bootup of the
kexec kernel or cause hard to diagnose data corruption.
The reason is that kexec() eventually overwrites the previous kernel's text,
page tables, data and stack. If it writes to the cache line which is
monitored by a previously offlined CPU, MWAIT resumes execution and ends
up executing the wrong text, dereferencing overwritten page tables or
corrupting the kexec kernels data.
Cure this by bringing the offlined CPUs out of MWAIT into HLT.
Write to the monitored cache line of each offline CPU, which makes MWAIT
resume execution. The written control word tells the offlined CPUs to issue
HLT, which does not have the MWAIT problem.
That does not help, if a stray NMI, MCE or SMI hits the offlined CPUs as
those make it come out of HLT.
A follow up change will put them into INIT, which protects at least against
NMI and SMI.
Fixes: ea53069231 ("x86, hotplug: Use mwait to offline a processor, fix the legacy case")
Reported-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615193330.492257119@linutronix.de
Monitoring idletask::thread_info::flags in mwait_play_dead() has been an
obvious choice as all what is needed is a cache line which is not written
by other CPUs.
But there is a use case where a "dead" CPU needs to be brought out of
MWAIT: kexec().
This is required as kexec() can overwrite text, pagetables, stacks and the
monitored cacheline of the original kernel. The latter causes MWAIT to
resume execution which obviously causes havoc on the kexec kernel which
results usually in triple faults.
Use a dedicated per CPU storage to prepare for that.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615193330.434553750@linutronix.de
Tony reported intermittent lockups on poweroff. His analysis identified the
wbinvd() in stop_this_cpu() as the culprit. This was added to ensure that
on SME enabled machines a kexec() does not leave any stale data in the
caches when switching from encrypted to non-encrypted mode or vice versa.
That wbinvd() is conditional on the SME feature bit which is read directly
from CPUID. But that readout does not check whether the CPUID leaf is
available or not. If it's not available the CPU will return the value of
the highest supported leaf instead. Depending on the content the "SME" bit
might be set or not.
That's incorrect but harmless. Making the CPUID readout conditional makes
the observed hangs go away, but it does not fix the underlying problem:
CPU0 CPU1
stop_other_cpus()
send_IPIs(REBOOT); stop_this_cpu()
while (num_online_cpus() > 1); set_online(false);
proceed... -> hang
wbinvd()
WBINVD is an expensive operation and if multiple CPUs issue it at the same
time the resulting delays are even larger.
But CPU0 already observed num_online_cpus() going down to 1 and proceeds
which causes the system to hang.
This issue exists independent of WBINVD, but the delays caused by WBINVD
make it more prominent.
Make this more robust by adding a cpumask which is initialized to the
online CPU mask before sending the IPIs and CPUs clear their bit in
stop_this_cpu() after the WBINVD completed. Check for that cpumask to
become empty in stop_other_cpus() instead of watching num_online_cpus().
The cpumask cannot plug all holes either, but it's better than a raw
counter and allows to restrict the NMI fallback IPI to be sent only the
CPUs which have not reported within the timeout window.
Fixes: 08f253ec37 ("x86/cpu: Clear SME feature flag when not in use")
Reported-by: Tony Battersby <tonyb@cybernetics.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/3817d810-e0f1-8ef8-0bbd-663b919ca49b@cybernetics.com
Link: https://lore.kernel.org/r/87h6r770bv.ffs@tglx
