lib: introduce early boot parameter to avoid page_ext memory overhead

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 <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 59bb71036837b4e827c4214c6bd5fbfbdbd375f3..6bd8e85beaf72ec37a798467da40f47a65ee6f61 100644 (file)
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -119,9 +119,46 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype,
        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();