From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 71BA578C8A for ; Fri, 26 Apr 2024 03:58:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714103896; cv=none; b=Dg5fFIfsLTcLylF032K8I6oVa4MnG1r+BLQd6VFq+zpX759mWMsHO9nXsSBpQImi/y08Xaib/FotSUnSUKHQJRDiZdSJh++tOf266pYBCEvG9LELcfYsXUWbr+3GTVkAgEAaADXUHx3pxuENwX335dxotrgr2JNy1/qFFuCAbdg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714103896; c=relaxed/simple; bh=smwfoWIqqRVb2NYPe+cx3T6Qdo5FjttFxFijpU2ROE4=; h=Date:To:From:Subject:Message-Id; b=kM0q1aoUMBvQBvWm0RcnV232AQdqGV8EFUgIznvWwYphEETYLfDr1C+xZILSIWv8ArTHmh62KPOY9YC2fdJvoPsP5RTvAIANz2w2PSG9BIvjV0FGTwCEvn63+4UeAAqbKzoXdhcKhScuaVBGB+HqeGmlIq+c6akPlP4xhG4s4lQ= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=F/Ro/e2s; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="F/Ro/e2s" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 439D0C113CD; Fri, 26 Apr 2024 03:58:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1714103896; bh=smwfoWIqqRVb2NYPe+cx3T6Qdo5FjttFxFijpU2ROE4=; h=Date:To:From:Subject:From; b=F/Ro/e2snici11tqbjJO5ZKK7LmmsbBNE38Qzw3+14FkqKnJCHVLjb5ik2YHMzJKD 9Hgl+4CxusCjnCHbPp4aMyMSDWWCfBhGL6lTKyGslDe8k3ZvgZ3a6S4jU5OCN+NitB 8zEiLCzc8q24cgtPSBqX1fHijBDfg96Dg2jxwDNI= Date: Thu, 25 Apr 2024 20:58:15 -0700 To: mm-commits@vger.kernel.org,wedsonaf@gmail.com,viro@zeniv.linux.org.uk,vbabka@suse.cz,tj@kernel.org,peterz@infradead.org,pasha.tatashin@soleen.com,ojeda@kernel.org,kent.overstreet@linux.dev,keescook@chromium.org,gary@garyguo.net,dennis@kernel.org,cl@linux.com,boqun.feng@gmail.com,bjorn3_gh@protonmail.com,benno.lossin@proton.me,aliceryhl@google.com,alex.gaynor@gmail.com,a.hindborg@samsung.com,surenb@google.com,akpm@linux-foundation.org From: Andrew Morton Subject: [merged mm-stable] lib-introduce-early-boot-parameter-to-avoid-page_ext-memory-overhead.patch removed from -mm tree Message-Id: <20240426035816.439D0C113CD@smtp.kernel.org> Precedence: bulk X-Mailing-List: mm-commits@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: The quilt patch titled Subject: lib: introduce early boot parameter to avoid page_ext memory overhead has been removed from the -mm tree. Its filename was lib-introduce-early-boot-parameter-to-avoid-page_ext-memory-overhead.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Suren Baghdasaryan Subject: lib: introduce early boot parameter to avoid page_ext memory overhead Date: Thu, 21 Mar 2024 09:36:37 -0700 The highest memory overhead from memory allocation profiling comes from page_ext objects. This overhead exists even if the feature is disabled but compiled-in. To avoid it, introduce an early boot parameter that prevents page_ext object creation. The new boot parameter is a tri-state with possible values of 0|1|never. When it is set to "never" the memory allocation profiling support is disabled, and overhead is minimized (currently no page_ext objects are allocated, in the future more overhead might be eliminated). As a result we also lose ability to enable memory allocation profiling at runtime (because there is no space to store alloctag references). Runtime sysctrl becomes read-only if the early boot parameter was set to "never". Note that the default value of this boot parameter depends on the CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT configuration. When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n the boot parameter is set to "never", therefore eliminating any overhead. CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=y results in boot parameter being set to 1 (enabled). This allows distributions to avoid any overhead by setting CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n config and with no changes to the kernel command line. We reuse sysctl.vm.mem_profiling boot parameter name in order to avoid introducing yet another control. This change turns it into a tri-state early boot parameter. Link: https://lkml.kernel.org/r/20240321163705.3067592-16-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Kent Overstreet Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- lib/alloc_tag.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) --- a/lib/alloc_tag.c~lib-introduce-early-boot-parameter-to-avoid-page_ext-memory-overhead +++ a/lib/alloc_tag.c @@ -119,9 +119,46 @@ static bool alloc_tag_module_unload(stru return module_unused; } +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support __meminitdata = true; +#else +static bool mem_profiling_support __meminitdata; +#endif + +static int __init setup_early_mem_profiling(char *str) +{ + bool enable; + + if (!str || !str[0]) + return -EINVAL; + + if (!strncmp(str, "never", 5)) { + enable = false; + mem_profiling_support = false; + } else { + int res; + + res = kstrtobool(str, &enable); + if (res) + return res; + + mem_profiling_support = true; + } + + if (enable != static_key_enabled(&mem_alloc_profiling_key)) { + if (enable) + static_branch_enable(&mem_alloc_profiling_key); + else + static_branch_disable(&mem_alloc_profiling_key); + } + + return 0; +} +early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); + static __init bool need_page_alloc_tagging(void) { - return true; + return mem_profiling_support; } static __init void init_page_alloc_tagging(void) @@ -161,6 +198,8 @@ static int __init alloc_tag_init(void) if (IS_ERR(alloc_tag_cttype)) return PTR_ERR(alloc_tag_cttype); + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; register_sysctl_init("vm", memory_allocation_profiling_sysctls); procfs_init(); _ Patches currently in -mm which might be from surenb@google.com are userfaultfd-remove-write_once-when-setting-folio-index-during-uffdio_move.patch