All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: Nikolay Borisov <nik.borisov@suse.com>
Cc: linux-kernel@vger.kernel.org, Juergen Gross <jgross@suse.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 37/49] x86/alternatives: Move text_poke_array completion from smp_text_poke_batch_finish() and smp_text_poke_batch_flush() to smp_text_poke_batch_process()
Date: Fri, 4 Apr 2025 09:48:31 +0200	[thread overview]
Message-ID: <Z--Oz3oz6_xcp4M7@gmail.com> (raw)
In-Reply-To: <b7c3882f-9691-47fc-9e50-267fef9cfc06@suse.com>


* Nikolay Borisov <nik.borisov@suse.com> wrote:

> > Yeah, it doesn't change semantics, but it's a very small
> > deoptimization.
> > > Mind sending a patch? It does simplify the facility some more and that
> > single branch will wash away against costs like the CR3 flushes done
> 
> Given that poke_batch_finish does a cond_resched and sync_each_cpu 
> which is an IPI can it even be considered a performance critical path 
> ?

Probably not, but even if it was, I think your change would still be an 
overall win, so please send a changelogged patch against 
WIP.x86/alternatives.

Thanks,

	Ingo

  reply	other threads:[~2025-04-04  7:48 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-28 13:26 [PATCH -v2 00/49] Simplify, reorganize and clean up the x86 text-patching code (alternative.c) Ingo Molnar
2025-03-28 13:26 ` [PATCH 01/49] x86/alternatives: Rename 'struct bp_patching_desc' to 'struct int3_patching_desc' Ingo Molnar
2025-03-28 13:26 ` [PATCH 02/49] x86/alternatives: Rename 'bp_refs' to 'int3_refs' Ingo Molnar
2025-03-28 13:26 ` [PATCH 03/49] x86/alternatives: Rename 'text_poke_bp_batch()' to 'smp_text_poke_batch_process()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 04/49] x86/alternatives: Rename 'text_poke_bp()' to 'smp_text_poke_single()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 05/49] x86/alternatives: Rename 'poke_int3_handler()' to 'smp_text_poke_int3_trap_handler()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 06/49] x86/alternatives: Rename 'poking_mm' to 'text_poke_mm' Ingo Molnar
2025-03-28 13:26 ` [PATCH 07/49] x86/alternatives: Rename 'poking_addr' to 'text_poke_mm_addr' Ingo Molnar
2025-03-28 13:26 ` [PATCH 08/49] x86/alternatives: Rename 'bp_desc' to 'int3_desc' Ingo Molnar
2025-03-28 13:26 ` [PATCH 09/49] x86/alternatives: Remove duplicate 'text_poke_early()' prototype Ingo Molnar
2025-03-28 13:26 ` [PATCH 10/49] x86/alternatives: Update comments in int3_emulate_push() Ingo Molnar
2025-03-28 13:26 ` [PATCH 11/49] x86/alternatives: Remove the confusing, inaccurate & unnecessary 'temp_mm_state_t' abstraction Ingo Molnar
2025-04-01 14:36   ` Peter Zijlstra
2025-04-01 19:06     ` Ingo Molnar
2025-04-02  4:07       ` Ingo Molnar
2025-04-02  7:54         ` Peter Zijlstra
2025-03-28 13:26 ` [PATCH 12/49] x86/alternatives: Rename 'text_poke_flush()' to 'smp_text_poke_batch_flush()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 13/49] x86/alternatives: Rename 'text_poke_finish()' to 'smp_text_poke_batch_finish()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 14/49] x86/alternatives: Rename 'text_poke_queue()' to 'smp_text_poke_batch_add()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 15/49] x86/alternatives: Rename 'text_poke_loc_init()' to 'text_poke_int3_loc_init()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 16/49] x86/alternatives: Rename 'struct text_poke_loc' to 'struct smp_text_poke_loc' Ingo Molnar
2025-03-28 13:26 ` [PATCH 17/49] x86/alternatives: Rename 'struct int3_patching_desc' to 'struct text_poke_int3_vec' Ingo Molnar
2025-03-28 13:26 ` [PATCH 18/49] x86/alternatives: Rename 'int3_desc' to 'int3_vec' Ingo Molnar
2025-03-28 13:26 ` [PATCH 19/49] x86/alternatives: Add text_mutex) assert to smp_text_poke_batch_flush() Ingo Molnar
2025-03-28 13:26 ` [PATCH 20/49] x86/alternatives: Assert that smp_text_poke_int3_trap_handler() can only ever handle 'tp_vec[]' based requests Ingo Molnar
2025-03-28 13:26 ` [PATCH 21/49] x86/alternatives: Use non-inverted logic instead of 'tp_order_fail()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 22/49] x86/alternatives: Remove the 'addr == NULL means forced-flush' hack from smp_text_poke_batch_finish()/smp_text_poke_batch_flush()/text_poke_addr_ordered() Ingo Molnar
2025-03-28 13:26 ` [PATCH 23/49] x86/alternatives: Simplify smp_text_poke_single() by using tp_vec and existing APIs Ingo Molnar
2025-04-01 14:40   ` Peter Zijlstra
2025-04-01 18:49     ` Ingo Molnar
2025-03-28 13:26 ` [PATCH 24/49] x86/alternatives: Assert input parameters in smp_text_poke_batch_process() Ingo Molnar
2025-03-28 13:26 ` [PATCH 25/49] x86/alternatives: Introduce 'struct smp_text_poke_array' and move tp_vec and tp_vec_nr to it Ingo Molnar
2025-03-28 13:26 ` [PATCH 26/49] x86/alternatives: Remove the tp_vec indirection Ingo Molnar
2025-03-28 13:26 ` [PATCH 27/49] x86/alternatives: Rename 'try_get_desc()' to 'try_get_text_poke_array()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 28/49] x86/alternatives: Rename 'put_desc()' to 'put_text_poke_array()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 29/49] x86/alternatives: Simplify try_get_text_poke_array() Ingo Molnar
2025-03-28 13:26 ` [PATCH 30/49] x86/alternatives: Simplify smp_text_poke_int3_trap_handler() Ingo Molnar
2025-03-28 13:26 ` [PATCH 31/49] x86/alternatives: Simplify smp_text_poke_batch_process() Ingo Molnar
2025-03-28 13:26 ` [PATCH 32/49] x86/alternatives: Rename 'int3_refs' to 'text_poke_array_refs' Ingo Molnar
2025-03-28 13:26 ` [PATCH 33/49] x86/alternatives: Move the text_poke_array manipulation into text_poke_int3_loc_init() and rename it to __smp_text_poke_batch_add() Ingo Molnar
2025-03-28 13:26 ` [PATCH 34/49] x86/alternatives: Remove the mixed-patching restriction on smp_text_poke_single() Ingo Molnar
2025-03-28 13:26 ` [PATCH 35/49] x86/alternatives: Document 'smp_text_poke_single()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 36/49] x86/alternatives: Add documentation for smp_text_poke_batch_add() Ingo Molnar
2025-03-28 13:26 ` [PATCH 37/49] x86/alternatives: Move text_poke_array completion from smp_text_poke_batch_finish() and smp_text_poke_batch_flush() to smp_text_poke_batch_process() Ingo Molnar
2025-04-03 13:08   ` Nikolay Borisov
2025-04-03 13:38     ` Ingo Molnar
2025-04-03 13:41       ` Nikolay Borisov
2025-04-03 14:13         ` Ingo Molnar
2025-04-03 14:39           ` Nikolay Borisov
2025-04-03 15:29             ` Ingo Molnar
2025-04-03 15:34               ` Nikolay Borisov
2025-04-04  7:48                 ` Ingo Molnar [this message]
2025-03-28 13:26 ` [PATCH 38/49] x86/alternatives: Rename 'text_poke_sync()' to 'smp_text_poke_sync_each_cpu()' Ingo Molnar
2025-03-28 13:26 ` [PATCH 39/49] x86/alternatives: Simplify text_poke_addr_ordered() Ingo Molnar
2025-03-28 13:26 ` [PATCH 40/49] x86/alternatives: Constify text_poke_addr() Ingo Molnar
2025-03-28 13:26 ` [PATCH 41/49] x86/alternatives: Simplify and clean up patch_cmp() Ingo Molnar
2025-03-28 13:26 ` [PATCH 42/49] x86/alternatives: Standardize on 'tpl' local variable names for 'struct smp_text_poke_loc *' Ingo Molnar
2025-03-28 13:26 ` [PATCH 43/49] x86/alternatives: Rename 'TP_ARRAY_NR_ENTRIES_MAX' to 'TEXT_POKE_ARRAY_MAX' Ingo Molnar
2025-03-28 13:26 ` [PATCH 44/49] x86/alternatives: Rename 'POKE_MAX_OPCODE_SIZE' to 'TEXT_POKE_MAX_OPCODE_SIZE' Ingo Molnar
2025-03-28 13:27 ` [PATCH 45/49] x86/alternatives: Simplify the #include section Ingo Molnar
2025-03-28 13:27 ` [PATCH 46/49] x86/alternatives: Move declarations of vmlinux.lds.S defined section symbols to <asm/alternative.h> Ingo Molnar
2025-03-28 13:27 ` [PATCH 47/49] x86/alternatives: Remove 'smp_text_poke_batch_flush()' Ingo Molnar
2025-03-28 13:27 ` [PATCH 48/49] x86/alternatives: Update the comments in smp_text_poke_batch_process() Ingo Molnar
2025-03-28 13:27 ` [PATCH 49/49] x86/alternatives: Rename 'apply_relocation()' to 'text_poke_apply_relocation()' Ingo Molnar
2025-04-01 14:31 ` [PATCH -v2 00/49] Simplify, reorganize and clean up the x86 text-patching code (alternative.c) Peter Zijlstra
2025-04-09 20:51   ` Ingo Molnar
2025-04-10 12:57     ` Peter Zijlstra
2025-04-01 14:31 ` Peter Zijlstra
2025-04-02  3:47   ` Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Z--Oz3oz6_xcp4M7@gmail.com \
    --to=mingo@kernel.org \
    --cc=bp@alien8.de \
    --cc=hpa@zytor.com \
    --cc=jgross@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nik.borisov@suse.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.