summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
AgeCommit message (Collapse)Author
2025-04-11x86/alternatives: Simplify text_poke_addr_ordered()Ingo Molnar
- Use direct 'void *' pointer comparison, there's no need to force the type to 'unsigned long'. - Remove the 'tp' local variable indirection Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-42-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_sync()' to 'smp_text_poke_sync_each_cpu()'Ingo Molnar
Unlike sync_core(), text_poke_sync() is a very heavy operation, as it sends an IPI to every online CPU in the system and waits for completion. Reflect this in the name. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-41-mingo@kernel.org
2025-04-11x86/alternatives: Move text_poke_array completion from ↵Ingo Molnar
smp_text_poke_batch_finish() and smp_text_poke_batch_flush() to smp_text_poke_batch_process() Simplifies the code and improves code generation a bit: text data bss dec hex filename 14769 1017 4112 19898 4dba alternative.o.before 14742 1017 4112 19871 4d9f alternative.o.after Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-40-mingo@kernel.org
2025-04-11x86/alternatives: Add documentation for smp_text_poke_batch_add()Ingo Molnar
Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-39-mingo@kernel.org
2025-04-11x86/alternatives: Document 'smp_text_poke_single()'Ingo Molnar
Extend the documentation to better describe its purpose. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-38-mingo@kernel.org
2025-04-11x86/alternatives: Remove the mixed-patching restriction on ↵Ingo Molnar
smp_text_poke_single() At this point smp_text_poke_single(addr, opcode, len, emulate) is equivalent to: smp_text_poke_batch_add(addr, opcode, len, emulate); smp_text_poke_batch_finish(); So remove the restriction on mixing single-instruction patching with multi-instruction patching. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-37-mingo@kernel.org
2025-04-11x86/alternatives: Move the text_poke_array manipulation into ↵Ingo Molnar
text_poke_int3_loc_init() and rename it to __smp_text_poke_batch_add() This simplifies the code and code generation a bit: text data bss dec hex filename 14802 1029 4112 19943 4de7 alternative.o.before 14784 1029 4112 19925 4dd5 alternative.o.after Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-36-mingo@kernel.org
2025-04-11x86/alternatives: Simplify smp_text_poke_batch_process()Ingo Molnar
This function is now using the text_poke_array state exclusively, make that explicit by removing the redundant input parameters. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-34-mingo@kernel.org
2025-04-11x86/alternatives: Simplify smp_text_poke_int3_handler()Ingo Molnar
Remove the 'desc' local variable indirection and use text_poke_array directly. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-33-mingo@kernel.org
2025-04-11x86/alternatives: Simplify try_get_text_poke_array()Ingo Molnar
There's no need to return a pointer on success - it's always the same pointer. Return a bool instead. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-32-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'put_desc()' to 'put_text_poke_array()'Ingo Molnar
Just like with try_get_text_poke_array(), this name better reflects what the underlying code is doing, there's no 'descriptor' indirection anymore. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-31-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'try_get_desc()' to 'try_get_text_poke_array()'Ingo Molnar
This better reflects what the underlying code is doing, there's no 'descriptor' indirection anymore. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-30-mingo@kernel.org
2025-04-11x86/alternatives: Remove the tp_vec indirectionIngo Molnar
At this point we are always working out of an uptodate text_poke_array, there's no need for smp_text_poke_int3_handler() to read via the int3_vec indirection - remove it. This simplifies the code: 1 file changed, 5 insertions(+), 15 deletions(-) Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-29-mingo@kernel.org
2025-04-11x86/alternatives: Introduce 'struct smp_text_poke_array' and move tp_vec and ↵Ingo Molnar
tp_vec_nr to it struct text_poke_array is an equivalent structure to these global variables: static struct smp_text_poke_loc tp_vec[TP_VEC_MAX]; static int tp_vec_nr; Note that we intentionally mirror much of the naming of 'struct text_poke_int3_vec', which will further highlight the unecessary layering going on in this code, and will ease its removal. No change in functionality. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-28-mingo@kernel.org
2025-04-11x86/alternatives: Assert input parameters in smp_text_poke_batch_process()Ingo Molnar
At this point the 'tp' input parameter must always be the global 'tp_vec' array, and 'nr_entries' must always be equal to 'tp_vec_nr'. Assert these conditions - which will allow the removal of a layer of indirection between these values. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-27-mingo@kernel.org
2025-04-11x86/alternatives: Assert that smp_text_poke_int3_handler() can only ever ↵Ingo Molnar
handle 'tp_vec[]' based requests Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-26-mingo@kernel.org
2025-04-11x86/alternatives: Simplify smp_text_poke_single() by using tp_vec and ↵Ingo Molnar
existing APIs Instead of constructing a vector on-stack, just use the already available batch-patching vector - which should always be empty at this point. This will allow subsequent simplifications. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-25-mingo@kernel.org
2025-04-11x86/alternatives: Remove the 'addr == NULL means forced-flush' hack from ↵Ingo Molnar
smp_text_poke_batch_finish()/smp_text_poke_batch_flush()/text_poke_addr_ordered() There's this weird hack used by smp_text_poke_batch_finish() to indicate a 'forced flush': smp_text_poke_batch_flush(NULL); Just open-code the vector-flush in a straightforward fashion: smp_text_poke_batch_process(tp_vec, tp_vec_nr); tp_vec_nr = 0; And get rid of !addr hack from text_poke_addr_ordered(). Leave a WARN_ON_ONCE(), just in case some external code learned to rely on this behavior. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-24-mingo@kernel.org
2025-04-11x86/alternatives: Use non-inverted logic instead of 'tp_order_fail()'Ingo Molnar
tp_order_fail() uses inverted logic: it returns true in case something is false, which is only a plus at the IOCCC. Instead rename it to regular parity as 'text_poke_addr_ordered()', and adjust the code accordingly. Also add a comment explaining how the address ordering should be understood. No change in functionality intended. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-23-mingo@kernel.org
2025-04-11x86/alternatives: Add text_mutex) assert to smp_text_poke_batch_flush()Ingo Molnar
It's possible to escape the text_mutex-held assert in smp_text_poke_batch_process() if the caller uses a properly batched and sorted series of patch requests, so add an explicit lockdep_assert_held() to make sure it's held by all callers. All text_poke_int3_*() APIs will call either smp_text_poke_batch_process() or smp_text_poke_batch_flush() internally. The text_mutex must be held, because tp_vec and tp_vec_nr et al are all globals, and the INT3 patching machinery itself relies on external serialization. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-22-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'int3_desc' to 'int3_vec'Ingo Molnar
Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-21-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'struct text_poke_loc' to 'struct smp_text_poke_loc'Ingo Molnar
Make it clear that this structure is part of the INT3 based SMP patching facility, not the regular text_poke*() MM-switch based facility. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-19-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_loc_init()' to 'text_poke_int3_loc_init()'Ingo Molnar
This name is actively confusing as well, because the simple text_poke*() APIs use MM-switching based code patching, while text_poke_loc_init() is part of the INT3 based text_poke_int3_*() machinery that is an additional layer of functionality on top of regular text_poke*() functionality. Rename it to text_poke_int3_loc_init() to make it clear which layer it belongs to. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-18-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_queue()' to 'smp_text_poke_batch_add()'Ingo Molnar
This name is actively confusing as well, because the simple text_poke*() APIs use MM-switching based code patching, while text_poke_queue() is part of the INT3 based text_poke_int3_*() machinery that is an additional layer of functionality on top of regular text_poke*() functionality. Rename it to smp_text_poke_batch_add() to make it clear which layer it belongs to. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-17-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_finish()' to 'smp_text_poke_batch_finish()'Ingo Molnar
This name is actively confusing as well, because the simple text_poke*() APIs use MM-switching based code patching, while text_poke_finish() is part of the INT3 based text_poke_int3_*() machinery that is an additional layer of functionality on top of regular text_poke*() functionality. Rename it to smp_text_poke_batch_finish() to make it clear which layer it belongs to. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-16-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_flush()' to 'smp_text_poke_batch_flush()'Ingo Molnar
This name is actually actively confusing, because the simple text_poke*() APIs use MM-switching based code patching, while text_poke_flush() is part of the INT3 based text_poke_int3_*() machinery that is an additional layer of functionality on top of regular text_poke*() functionality. Rename it to smp_text_poke_batch_flush() to make it clear which layer it belongs to. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-15-mingo@kernel.org
2025-04-11x86/alternatives: Remove the confusing, inaccurate & unnecessary ↵Ingo Molnar
'temp_mm_state_t' abstraction So the temp_mm_state_t abstraction used by use_temporary_mm() and unuse_temporary_mm() is super confusing: - The whole machinery is about temporarily switching to the text_poke_mm utility MM that got allocated during bootup for text-patching purposes alone: temp_mm_state_t prev; /* * Loading the temporary mm behaves as a compiler barrier, which * guarantees that the PTE will be set at the time memcpy() is done. */ prev = use_temporary_mm(text_poke_mm); - Yet the value that gets saved in the temp_mm_state_t variable is not the temporary MM ... but the previous MM... - Ie. we temporarily put the non-temporary MM into a variable that has the temp_mm_state_t type. This makes no sense whatsoever. - The confusion continues in unuse_temporary_mm(): static inline void unuse_temporary_mm(temp_mm_state_t prev_state) Here we unuse an MM that is ... not the temporary MM, but the previous MM. :-/ Fix up all this confusion by removing the unnecessary layer of abstraction and using a bog-standard 'struct mm_struct *prev_mm' variable to save the MM to. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-14-mingo@kernel.org
2025-04-11x86/alternatives: Remove duplicate 'text_poke_early()' prototypeIngo Molnar
It's declared in <asm/text-patching.h> already. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-12-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'bp_desc' to 'int3_desc'Ingo Molnar
Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-11-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'poking_addr' to 'text_poke_mm_addr'Ingo Molnar
Put it into the text_poke_* namespace of <asm/text-patching.h>. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-10-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'poking_mm' to 'text_poke_mm'Ingo Molnar
Put it into the text_poke_* namespace of <asm/text-patching.h>. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-9-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'poke_int3_handler()' to 'smp_text_poke_int3_handler()'Ingo Molnar
All related functions in this subsystem already have a text_poke_int3_ prefix - add it to the trap handler as well. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-8-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_bp()' to 'smp_text_poke_single()'Ingo Molnar
Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-7-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'text_poke_bp_batch()' to ↵Ingo Molnar
'smp_text_poke_batch_process()' Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-6-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'bp_refs' to 'text_poke_array_refs'Ingo Molnar
Make it clear that these reference counts lock access to text_poke_array. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-5-mingo@kernel.org
2025-04-11x86/alternatives: Rename 'struct bp_patching_desc' to 'struct ↵Ingo Molnar
text_poke_int3_vec' Follow the INT3 text-poking nomenclature, and also adopt the 'vector' name for the entire object, instead of the rather opaque 'descriptor' naming. Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20250411054105.2341982-4-mingo@kernel.org
2025-04-11x86/alternatives: Document the text_poke_bp_batch() synchronization rules a ↵Peter Zijlstra
bit more Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Dumazet <edumazet@google.com> Cc: Brian Gerst <brgerst@gmail.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/r/20250411054105.2341982-3-mingo@kernel.org
2025-04-11x86/alternatives: Improve code-patching scalability by removing false ↵Eric Dumazet
sharing in poke_int3_handler() eBPF programs can be run 50,000,000 times per second on busy servers. Whenever /proc/sys/kernel/bpf_stats_enabled is turned off, hundreds of calls sites are patched from text_poke_bp_batch() and we see a huge loss of performance due to false sharing on bp_desc.refs lasting up to three seconds. 51.30% server_bin [kernel.kallsyms] [k] poke_int3_handler | |--46.45%--poke_int3_handler | exc_int3 | asm_exc_int3 | | | |--24.26%--cls_bpf_classify | | tcf_classify | | __dev_queue_xmit | | ip6_finish_output2 | | ip6_output | | ip6_xmit | | inet6_csk_xmit | | __tcp_transmit_skb Fix this by replacing bp_desc.refs with a per-cpu bp_refs. Before the patch, on a host with 240 cores (480 threads): $ sysctl -wq kernel.bpf_stats_enabled=0 text_poke_bp_batch(nr_entries=164) : Took 2655300 usec $ bpftool prog | grep run_time_ns ... 105: sched_cls name hn_egress tag 699fc5eea64144e3 gpl run_time_ns 3009063719 run_cnt 82757845 : average cost is 36 nsec per call After this patch: $ sysctl -wq kernel.bpf_stats_enabled=0 text_poke_bp_batch(nr_entries=164) : Took 702 usec $ bpftool prog | grep run_time_ns ... 105: sched_cls name hn_egress tag 699fc5eea64144e3 gpl run_time_ns 1928223019 run_cnt 67682728 : average cost is 28 nsec per call Ie. text-patching performance improved 3700x: from 2.65 seconds to 0.0007 seconds. Since the atomic_cond_read_acquire(refs, !VAL) spin-loop was not triggered even once in my tests, add an unlikely() annotation, because this appears to be the common case. [ mingo: Improved the changelog some more. ] Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Juergen Gross <jgross@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Brian Gerst <brgerst@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/r/20250411054105.2341982-2-mingo@kernel.org
2025-04-11x86/i8253: Call clockevent_i8253_disable() with interrupts disabledFernando Fernandez Mancera
There's a lockdep false positive warning related to i8253_lock: WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected ... systemd-sleep/3324 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: ffffffffb2c23398 (i8253_lock){+.+.}-{2:2}, at: pcspkr_event+0x3f/0xe0 [pcspkr] ... ... which became HARDIRQ-irq-unsafe at: ... lock_acquire+0xd0/0x2f0 _raw_spin_lock+0x30/0x40 clockevent_i8253_disable+0x1c/0x60 pit_timer_init+0x25/0x50 hpet_time_init+0x46/0x50 x86_late_time_init+0x1b/0x40 start_kernel+0x962/0xa00 x86_64_start_reservations+0x24/0x30 x86_64_start_kernel+0xed/0xf0 common_startup_64+0x13e/0x141 ... Lockdep complains due pit_timer_init() using the lock in an IRQ-unsafe fashion, but it's a false positive, because there is no deadlock possible at that point due to init ordering: at the point where pit_timer_init() is called there is no other possible usage of i8253_lock because the system is still in the very early boot stage with no interrupts. But in any case, pit_timer_init() should disable interrupts before calling clockevent_i8253_disable() out of general principle, and to keep lockdep working even in this scenario. Use scoped_guard() for that, as suggested by Thomas Gleixner. [ mingo: Cleaned up the changelog. ] Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/Z-uwd4Bnn7FcCShX@gmail.com
2025-04-10x86/kexec: Invalidate GDT/IDT from relocate_kernel() instead of earlierDavid Woodhouse
Reduce the window during which exceptions are unhandled, by leaving the GDT/IDT in place all the way into the relocate_kernel() function, until the moment that %cr3 gets replaced. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Brian Gerst <brgerst@gmail.com> Cc: Juergen Gross <jgross@suse.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20250326142404.256980-4-dwmw2@infradead.org
2025-04-10x86/kexec: Add 8250 MMIO serial port outputDavid Woodhouse
This supports the same 32-bit MMIO-mapped 8250 as the early_printk code. It's not clear why the early_printk code supports this form and only this form; the actual runtime 8250_pci doesn't seem to support it. But having hacked up QEMU to expose such a device, early_printk does work with it, and now so does the kexec debug code. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Brian Gerst <brgerst@gmail.com> Cc: Juergen Gross <jgross@suse.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20250326142404.256980-3-dwmw2@infradead.org
2025-04-10x86/kexec: Add 8250 serial port outputDavid Woodhouse
If a serial port was configured for early_printk, use it for debug output from the relocate_kernel exception handler too. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Brian Gerst <brgerst@gmail.com> Cc: Juergen Gross <jgross@suse.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20250326142404.256980-2-dwmw2@infradead.org
2025-04-10x86/msr: Rename 'wrmsrl_cstar()' to 'wrmsrq_cstar()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'native_wrmsrl()' to 'native_wrmsrq()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'wrmsrl_amd_safe()' to 'wrmsrq_amd_safe()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'rdmsrl_amd_safe()' to 'rdmsrq_amd_safe()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'mce_wrmsrl()' to 'mce_wrmsrq()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'mce_rdmsrl()' to 'mce_rdmsrq()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'wrmsrl_on_cpu()' to 'wrmsrq_on_cpu()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
2025-04-10x86/msr: Rename 'rdmsrl_on_cpu()' to 'rdmsrq_on_cpu()'Ingo Molnar
Suggested-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Juergen Gross <jgross@suse.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Xin Li <xin@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org>
generated by cgit (git 2.34.1) at 2025-07-15 21:25:31 +0000