From: Dan Williams <dan.j.williams@intel.com> To: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>, Stable <stable@vger.kernel.org>, Len Brown <lenb@kernel.org>, Borislav Petkov <bp@alien8.de>, James Morse <james.morse@arm.com>, Erik Kaneda <erik.kaneda@intel.com>, Myron Stowe <myron.stowe@redhat.com>, "Rafael J. Wysocki" <rjw@rjwysocki.net>, Andy Shevchenko <andriy.shevchenko@linux.intel.com>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org>, linux-nvdimm <linux-nvdimm@lists.01.org> Subject: Re: [PATCH] ACPI: Drop rcu usage for MMIO mappings Date: Thu, 7 May 2020 16:12:57 -0700 [thread overview] Message-ID: <CAPcyv4gOxrOZUKfA4cObKUaZRkkjRyQFkS+=Q9FXziK00CE8yA@mail.gmail.com> (raw) In-Reply-To: <CAHp75Vf0zBnwHubK+C265M9nh3Y5K2K=8ck61HQtnW+021bgwQ@mail.gmail.com> On Thu, May 7, 2020 at 2:25 AM Andy Shevchenko <andy.shevchenko@gmail.com> wrote: > > On Thu, May 7, 2020 at 3:21 AM Dan Williams <dan.j.williams@intel.com> wrote: > > > > Recently a performance problem was reported for a process invoking a > > non-trival ASL program. The method call in this case ends up > > repetitively triggering a call path like: > > > > acpi_ex_store > > acpi_ex_store_object_to_node > > acpi_ex_write_data_to_field > > acpi_ex_insert_into_field > > acpi_ex_write_with_update_rule > > acpi_ex_field_datum_io > > acpi_ex_access_region > > acpi_ev_address_space_dispatch > > acpi_ex_system_memory_space_handler > > acpi_os_map_cleanup.part.14 > > _synchronize_rcu_expedited.constprop.89 > > schedule > > > > The end result of frequent synchronize_rcu_expedited() invocation is > > tiny sub-millisecond spurts of execution where the scheduler freely > > migrates this apparently sleepy task. The overhead of frequent scheduler > > invocation multiplies the execution time by a factor of 2-3X. > > > > For example, performance improves from 16 minutes to 7 minutes for a > > firmware update procedure across 24 devices. > > > > Perhaps the rcu usage was intended to allow for not taking a sleeping > > lock in the acpi_os_{read,write}_memory() path which ostensibly could be > > called from an APEI NMI error interrupt? Neither rcu_read_lock() nor > > ioremap() are interrupt safe, so add a WARN_ONCE() to validate that rcu > > was not serving as a mechanism to avoid direct calls to ioremap(). Even > > the original implementation had a spin_lock_irqsave(), but that is not > > NMI safe. > > > > APEI itself already has some concept of avoiding ioremap() from > > interrupt context (see erst_exec_move_data()), if the new warning > > triggers it means that APEI either needs more instrumentation like that > > to pre-emptively fail, or more infrastructure to arrange for pre-mapping > > the resources it needs in NMI context. > > ... > > > +static void __iomem *acpi_os_rw_map(acpi_physical_address phys_addr, > > + unsigned int size, bool *did_fallback) > > +{ > > + void __iomem *virt_addr = NULL; > > Assignment is not needed as far as I can see. True, holdover from a previous version, will drop. > > > + if (WARN_ONCE(in_interrupt(), "ioremap in interrupt context\n")) > > + return NULL; > > + > > + /* Try to use a cached mapping and fallback otherwise */ > > + *did_fallback = false; > > + mutex_lock(&acpi_ioremap_lock); > > + virt_addr = acpi_map_vaddr_lookup(phys_addr, size); > > + if (virt_addr) > > + return virt_addr; > > + mutex_unlock(&acpi_ioremap_lock); > > + > > + virt_addr = acpi_os_ioremap(phys_addr, size); > > + *did_fallback = true; > > + > > + return virt_addr; > > +} > > I'm wondering if Sparse is okay with this... Seems like it is: $ sparse --version v0.6.1-191-gc51a0382202e $ cat out | grep osl\.c CHECK drivers/acpi/osl.c drivers/acpi/osl.c:373:17: warning: cast removes address space '<asn:2>' of expression ...was the only warning I got. _______________________________________________ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-leave@lists.01.org
WARNING: multiple messages have this Message-ID (diff)
From: Dan Williams <dan.j.williams@intel.com> To: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>, Stable <stable@vger.kernel.org>, Len Brown <lenb@kernel.org>, Borislav Petkov <bp@alien8.de>, Ira Weiny <ira.weiny@intel.com>, James Morse <james.morse@arm.com>, Erik Kaneda <erik.kaneda@intel.com>, Myron Stowe <myron.stowe@redhat.com>, "Rafael J. Wysocki" <rjw@rjwysocki.net>, Andy Shevchenko <andriy.shevchenko@linux.intel.com>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org>, linux-nvdimm <linux-nvdimm@lists.01.org> Subject: Re: [PATCH] ACPI: Drop rcu usage for MMIO mappings Date: Thu, 7 May 2020 16:12:57 -0700 [thread overview] Message-ID: <CAPcyv4gOxrOZUKfA4cObKUaZRkkjRyQFkS+=Q9FXziK00CE8yA@mail.gmail.com> (raw) In-Reply-To: <CAHp75Vf0zBnwHubK+C265M9nh3Y5K2K=8ck61HQtnW+021bgwQ@mail.gmail.com> On Thu, May 7, 2020 at 2:25 AM Andy Shevchenko <andy.shevchenko@gmail.com> wrote: > > On Thu, May 7, 2020 at 3:21 AM Dan Williams <dan.j.williams@intel.com> wrote: > > > > Recently a performance problem was reported for a process invoking a > > non-trival ASL program. The method call in this case ends up > > repetitively triggering a call path like: > > > > acpi_ex_store > > acpi_ex_store_object_to_node > > acpi_ex_write_data_to_field > > acpi_ex_insert_into_field > > acpi_ex_write_with_update_rule > > acpi_ex_field_datum_io > > acpi_ex_access_region > > acpi_ev_address_space_dispatch > > acpi_ex_system_memory_space_handler > > acpi_os_map_cleanup.part.14 > > _synchronize_rcu_expedited.constprop.89 > > schedule > > > > The end result of frequent synchronize_rcu_expedited() invocation is > > tiny sub-millisecond spurts of execution where the scheduler freely > > migrates this apparently sleepy task. The overhead of frequent scheduler > > invocation multiplies the execution time by a factor of 2-3X. > > > > For example, performance improves from 16 minutes to 7 minutes for a > > firmware update procedure across 24 devices. > > > > Perhaps the rcu usage was intended to allow for not taking a sleeping > > lock in the acpi_os_{read,write}_memory() path which ostensibly could be > > called from an APEI NMI error interrupt? Neither rcu_read_lock() nor > > ioremap() are interrupt safe, so add a WARN_ONCE() to validate that rcu > > was not serving as a mechanism to avoid direct calls to ioremap(). Even > > the original implementation had a spin_lock_irqsave(), but that is not > > NMI safe. > > > > APEI itself already has some concept of avoiding ioremap() from > > interrupt context (see erst_exec_move_data()), if the new warning > > triggers it means that APEI either needs more instrumentation like that > > to pre-emptively fail, or more infrastructure to arrange for pre-mapping > > the resources it needs in NMI context. > > ... > > > +static void __iomem *acpi_os_rw_map(acpi_physical_address phys_addr, > > + unsigned int size, bool *did_fallback) > > +{ > > + void __iomem *virt_addr = NULL; > > Assignment is not needed as far as I can see. True, holdover from a previous version, will drop. > > > + if (WARN_ONCE(in_interrupt(), "ioremap in interrupt context\n")) > > + return NULL; > > + > > + /* Try to use a cached mapping and fallback otherwise */ > > + *did_fallback = false; > > + mutex_lock(&acpi_ioremap_lock); > > + virt_addr = acpi_map_vaddr_lookup(phys_addr, size); > > + if (virt_addr) > > + return virt_addr; > > + mutex_unlock(&acpi_ioremap_lock); > > + > > + virt_addr = acpi_os_ioremap(phys_addr, size); > > + *did_fallback = true; > > + > > + return virt_addr; > > +} > > I'm wondering if Sparse is okay with this... Seems like it is: $ sparse --version v0.6.1-191-gc51a0382202e $ cat out | grep osl\.c CHECK drivers/acpi/osl.c drivers/acpi/osl.c:373:17: warning: cast removes address space '<asn:2>' of expression ...was the only warning I got.
next prev parent reply other threads:[~2020-05-07 23:13 UTC|newest] Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-05-06 23:39 [PATCH] ACPI: Drop rcu usage for MMIO mappings Dan Williams 2020-05-06 23:39 ` Dan Williams 2020-05-07 9:24 ` Andy Shevchenko 2020-05-07 9:24 ` Andy Shevchenko 2020-05-07 23:12 ` Dan Williams [this message] 2020-05-07 23:12 ` Dan Williams 2020-05-07 16:43 ` Rafael J. Wysocki 2020-05-07 16:43 ` Rafael J. Wysocki 2020-05-07 21:20 ` Dan Williams 2020-05-07 21:20 ` Dan Williams 2020-05-11 9:00 ` [ACPI] b13663bdf9: BUG:sleeping_function_called_from_invalid_context_at_kernel/locking/mutex.c kernel test robot 2020-05-11 9:00 ` kernel test robot 2020-05-11 9:00 ` kernel test robot 2020-05-12 16:28 ` Rafael J. Wysocki 2020-05-12 16:28 ` Rafael J. Wysocki 2020-05-12 16:28 ` Rafael J. Wysocki 2020-05-12 18:05 ` Dan Williams 2020-05-12 18:05 ` Dan Williams 2020-05-12 18:05 ` Dan Williams 2020-05-18 18:08 ` James Morse 2020-05-18 18:08 ` James Morse 2020-05-18 18:08 ` James Morse 2020-05-18 19:44 ` Dan Williams 2020-05-18 19:44 ` Dan Williams 2020-05-18 19:44 ` Dan Williams
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='CAPcyv4gOxrOZUKfA4cObKUaZRkkjRyQFkS+=Q9FXziK00CE8yA@mail.gmail.com' \ --to=dan.j.williams@intel.com \ --cc=andriy.shevchenko@linux.intel.com \ --cc=andy.shevchenko@gmail.com \ --cc=bp@alien8.de \ --cc=erik.kaneda@intel.com \ --cc=james.morse@arm.com \ --cc=lenb@kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-nvdimm@lists.01.org \ --cc=myron.stowe@redhat.com \ --cc=rafael.j.wysocki@intel.com \ --cc=rjw@rjwysocki.net \ --cc=stable@vger.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: linkBe 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.