linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Ard Biesheuvel <ardb@kernel.org>
To: Mike Rapoport <rppt@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Andreas Larsson <andreas@gaisler.com>,
	 Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	Borislav Petkov <bp@alien8.de>,  Brian Cain <bcain@quicinc.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Christoph Hellwig <hch@infradead.org>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	 Dave Hansen <dave.hansen@linux.intel.com>,
	Dinh Nguyen <dinguyen@kernel.org>,
	 Geert Uytterhoeven <geert@linux-m68k.org>,
	Guo Ren <guoren@kernel.org>, Helge Deller <deller@gmx.de>,
	 Huacai Chen <chenhuacai@kernel.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Johannes Berg <johannes@sipsolutions.net>,
	 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>,
	Kent Overstreet <kent.overstreet@linux.dev>,
	 "Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Luis Chamberlain <mcgrof@kernel.org>,
	 Mark Rutland <mark.rutland@arm.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	 Matt Turner <mattst88@gmail.com>,
	Max Filippov <jcmvbkbc@gmail.com>,
	 Michael Ellerman <mpe@ellerman.id.au>,
	Michal Simek <monstr@monstr.eu>, Oleg Nesterov <oleg@redhat.com>,
	 Palmer Dabbelt <palmer@dabbelt.com>,
	Peter Zijlstra <peterz@infradead.org>,
	 Richard Weinberger <richard@nod.at>,
	Russell King <linux@armlinux.org.uk>, Song Liu <song@kernel.org>,
	 Stafford Horne <shorne@gmail.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	 Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	 Uladzislau Rezki <urezki@gmail.com>,
	Vineet Gupta <vgupta@kernel.org>, Will Deacon <will@kernel.org>,
	 bpf@vger.kernel.org, linux-alpha@vger.kernel.org,
	linux-arch@vger.kernel.org,
	 linux-arm-kernel@lists.infradead.org,
	linux-csky@vger.kernel.org,  linux-hexagon@vger.kernel.org,
	linux-kernel@vger.kernel.org,  linux-m68k@lists.linux-m68k.org,
	linux-mips@vger.kernel.org,  linux-mm@kvack.org,
	linux-modules@vger.kernel.org,  linux-openrisc@vger.kernel.org,
	linux-parisc@vger.kernel.org,  linux-riscv@lists.infradead.org,
	linux-sh@vger.kernel.org,  linux-snps-arc@lists.infradead.org,
	linux-trace-kernel@vger.kernel.org,
	 linux-um@lists.infradead.org, linuxppc-dev@lists.ozlabs.org,
	 loongarch@lists.linux.dev, sparclinux@vger.kernel.org,
	x86@kernel.org
Subject: Re: [PATCH v3 7/8] execmem: add support for cache of large ROX pages
Date: Fri, 13 Sep 2024 17:00:42 +0200	[thread overview]
Message-ID: <CAMj1kXG_Z=7B_eDAk3vhtDjfcnka3AoSKNzvFQDzpvYY2EyVfg@mail.gmail.com> (raw)
In-Reply-To: <20240909064730.3290724-8-rppt@kernel.org>

Hi Mike,

On Mon, 9 Sept 2024 at 08:51, Mike Rapoport <rppt@kernel.org> wrote:
>
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
>
> Using large pages to map text areas reduces iTLB pressure and improves
> performance.
>
> Extend execmem_alloc() with an ability to use huge pages with ROX
> permissions as a cache for smaller allocations.
>
> To populate the cache, a writable large page is allocated from vmalloc with
> VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
> ROX.
>
> Portions of that large page are handed out to execmem_alloc() callers
> without any changes to the permissions.
>
> When the memory is freed with execmem_free() it is invalidated again so
> that it won't contain stale instructions.
>
> The cache is enabled when an architecture sets EXECMEM_ROX_CACHE flag in
> definition of an execmem_range.
>
> Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
> ---
>  include/linux/execmem.h |   2 +
>  mm/execmem.c            | 289 +++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 286 insertions(+), 5 deletions(-)
>
> diff --git a/include/linux/execmem.h b/include/linux/execmem.h
> index dfdf19f8a5e8..7436aa547818 100644
> --- a/include/linux/execmem.h
> +++ b/include/linux/execmem.h
> @@ -77,12 +77,14 @@ struct execmem_range {
>
>  /**
>   * struct execmem_info - architecture parameters for code allocations
> + * @fill_trapping_insns: set memory to contain instructions that will trap
>   * @ranges: array of parameter sets defining architecture specific
>   * parameters for executable memory allocations. The ranges that are not
>   * explicitly initialized by an architecture use parameters defined for
>   * @EXECMEM_DEFAULT.
>   */
>  struct execmem_info {
> +       void (*fill_trapping_insns)(void *ptr, size_t size, bool writable);
>         struct execmem_range    ranges[EXECMEM_TYPE_MAX];
>  };
>
> diff --git a/mm/execmem.c b/mm/execmem.c
> index 0f6691e9ffe6..f547c1f3c93d 100644
> --- a/mm/execmem.c
> +++ b/mm/execmem.c
> @@ -7,28 +7,88 @@
>   */
>
>  #include <linux/mm.h>
> +#include <linux/mutex.h>
>  #include <linux/vmalloc.h>
>  #include <linux/execmem.h>
> +#include <linux/maple_tree.h>
>  #include <linux/moduleloader.h>
>  #include <linux/text-patching.h>
>
> +#include <asm/tlbflush.h>
> +
> +#include "internal.h"
> +
>  static struct execmem_info *execmem_info __ro_after_init;
>  static struct execmem_info default_execmem_info __ro_after_init;
>
> -static void *__execmem_alloc(struct execmem_range *range, size_t size)
> +#ifdef CONFIG_MMU
> +struct execmem_cache {
> +       struct mutex mutex;
> +       struct maple_tree busy_areas;
> +       struct maple_tree free_areas;
> +};
> +
> +static struct execmem_cache execmem_cache = {
> +       .mutex = __MUTEX_INITIALIZER(execmem_cache.mutex),
> +       .busy_areas = MTREE_INIT_EXT(busy_areas, MT_FLAGS_LOCK_EXTERN,
> +                                    execmem_cache.mutex),
> +       .free_areas = MTREE_INIT_EXT(free_areas, MT_FLAGS_LOCK_EXTERN,
> +                                    execmem_cache.mutex),
> +};
> +
> +static void execmem_cache_clean(struct work_struct *work)
> +{
> +       struct maple_tree *free_areas = &execmem_cache.free_areas;
> +       struct mutex *mutex = &execmem_cache.mutex;
> +       MA_STATE(mas, free_areas, 0, ULONG_MAX);
> +       void *area;
> +
> +       mutex_lock(mutex);
> +       mas_for_each(&mas, area, ULONG_MAX) {
> +               size_t size;
> +
> +               if (!xa_is_value(area))
> +                       continue;
> +
> +               size = xa_to_value(area);
> +
> +               if (IS_ALIGNED(size, PMD_SIZE) &&
> +                   IS_ALIGNED(mas.index, PMD_SIZE)) {
> +                       void *ptr = (void *)mas.index;
> +
> +                       mas_erase(&mas);
> +                       vfree(ptr);
> +               }
> +       }
> +       mutex_unlock(mutex);
> +}
> +
> +static DECLARE_WORK(execmem_cache_clean_work, execmem_cache_clean);
> +
> +static void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable)
> +{
> +       if (execmem_info->fill_trapping_insns)
> +               execmem_info->fill_trapping_insns(ptr, size, writable);
> +       else
> +               memset(ptr, 0, size);

Does this really have to be a function pointer with a runtime check?

This could just be a __weak definition, with the arch providing an
override if the memset() is not appropriate.


  reply	other threads:[~2024-09-13 15:01 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-09  6:47 [PATCH v3 0/8] x86/module: use large ROX pages for text allocations Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 1/8] mm: vmalloc: group declarations depending on CONFIG_MMU together Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 2/8] mm: vmalloc: don't account for number of nodes for HUGE_VMAP allocations Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 3/8] asm-generic: introduce text-patching.h Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 4/8] module: prepare to handle ROX allocations for text Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 5/8] ftrace: Add swap_func to ftrace_process_locs() Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 6/8] x86/module: perpare module loading for ROX allocations of text Mike Rapoport
2024-09-09  9:29   ` Peter Zijlstra
2024-09-09 14:34     ` Mike Rapoport
2024-09-09 14:49       ` Steven Rostedt
2024-09-11 10:19         ` Mike Rapoport
2024-09-09  6:47 ` [PATCH v3 7/8] execmem: add support for cache of large ROX pages Mike Rapoport
2024-09-13 15:00   ` Ard Biesheuvel [this message]
2024-09-15 13:48     ` Mike Rapoport
2024-09-19 11:18   ` Liam R. Howlett
2024-09-09  6:47 ` [PATCH v3 8/8] x86/module: enable ROX caches for module text Mike Rapoport

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='CAMj1kXG_Z=7B_eDAk3vhtDjfcnka3AoSKNzvFQDzpvYY2EyVfg@mail.gmail.com' \
    --to=ardb@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=andreas@gaisler.com \
    --cc=arnd@arndb.de \
    --cc=bcain@quicinc.com \
    --cc=bp@alien8.de \
    --cc=bpf@vger.kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=chenhuacai@kernel.org \
    --cc=christophe.leroy@csgroup.eu \
    --cc=dave.hansen@linux.intel.com \
    --cc=deller@gmx.de \
    --cc=dinguyen@kernel.org \
    --cc=geert@linux-m68k.org \
    --cc=glaubitz@physik.fu-berlin.de \
    --cc=guoren@kernel.org \
    --cc=hch@infradead.org \
    --cc=jcmvbkbc@gmail.com \
    --cc=johannes@sipsolutions.net \
    --cc=kent.overstreet@linux.dev \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-csky@vger.kernel.org \
    --cc=linux-hexagon@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-m68k@lists.linux-m68k.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-modules@vger.kernel.org \
    --cc=linux-openrisc@vger.kernel.org \
    --cc=linux-parisc@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=linux-sh@vger.kernel.org \
    --cc=linux-snps-arc@lists.infradead.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=linux-um@lists.infradead.org \
    --cc=linux@armlinux.org.uk \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=loongarch@lists.linux.dev \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mattst88@gmail.com \
    --cc=mcgrof@kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=monstr@monstr.eu \
    --cc=mpe@ellerman.id.au \
    --cc=oleg@redhat.com \
    --cc=palmer@dabbelt.com \
    --cc=peterz@infradead.org \
    --cc=richard@nod.at \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=shorne@gmail.com \
    --cc=song@kernel.org \
    --cc=sparclinux@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=tsbogend@alpha.franken.de \
    --cc=urezki@gmail.com \
    --cc=vgupta@kernel.org \
    --cc=will@kernel.org \
    --cc=x86@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).