* [PATCH v8 3/4] mm: Simplify MEMORY_ISOLATION && COMPACTION || CMA into CONTIG_ALLOC
From: Alexandre Ghiti @ 2019-03-27 6:36 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190327063626.18421-1-alex@ghiti.fr>
This condition allows to define alloc_contig_range, so simplify
it into a more accurate naming.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
arch/arm64/Kconfig | 2 +-
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/s390/Kconfig | 2 +-
arch/sh/Kconfig | 2 +-
arch/sparc/Kconfig | 2 +-
arch/x86/Kconfig | 2 +-
arch/x86/mm/hugetlbpage.c | 2 +-
include/linux/gfp.h | 2 +-
mm/Kconfig | 3 +++
mm/page_alloc.c | 3 +--
10 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7e34b9eba5de..a8380629cb3f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,7 +18,7 @@ config ARM64
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_HAS_KCOV
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PTE_SPECIAL
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..eb0f592cde69 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -325,7 +325,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
depends on PPC_BOOK3S_64
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
default y
help
Enable support for the Power ISA 3.0 Radix style MMU. Currently this
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b6e3d0653002..1c8cb55b4e5d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -69,7 +69,7 @@ config S390
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_HAS_KCOV
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SET_MEMORY
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 0d9fb2468e0b..67931bdaf32f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,7 +53,7 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
select NEED_SG_DMA_LENGTH
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
help
The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ebcc9435db08..52193cfb0f32 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -91,7 +91,7 @@ config SPARC64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_PTE_SPECIAL
select PCI_DOMAINS if PCI
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
config ARCH_DEFCONFIG
string
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1f9b3cf437c..749bab313dc1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,7 +21,7 @@ config X86_64
def_bool y
depends on 64BIT
# Options that are inherently 64-bit kernel only:
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_SUPPORTS_INT128
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 92e4c4b85bba..fab095362c50 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -203,7 +203,7 @@ static __init int setup_hugepagesz(char *opt)
}
__setup("hugepagesz=", setup_hugepagesz);
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
static __init int gigantic_pages_init(void)
{
/* With compaction or CMA we can allocate gigantic pages at runtime */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index fdab7de7490d..e77ab30e9328 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -585,7 +585,7 @@ static inline bool pm_suspended_storage(void)
}
#endif /* CONFIG_PM_SLEEP */
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype, gfp_t gfp_mask);
diff --git a/mm/Kconfig b/mm/Kconfig
index 25c71eb8a7db..137eadc18732 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -258,6 +258,9 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION
config ARCH_ENABLE_THP_MIGRATION
bool
+config CONTIG_ALLOC
+ def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
+
config PHYS_ADDR_T_64BIT
def_bool 64BIT
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 03fcf73d47da..ecb115a74a9d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8109,8 +8109,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
return true;
}
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
-
+#ifdef CONFIG_CONTIG_ALLOC
static unsigned long pfn_max_align_down(unsigned long pfn)
{
return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
--
2.20.1
^ permalink raw reply related
* [PATCH v8 2/4] sparc: Advertise gigantic page support
From: Alexandre Ghiti @ 2019-03-27 6:36 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190327063626.18421-1-alex@ghiti.fr>
sparc actually supports gigantic pages and selecting
ARCH_HAS_GIGANTIC_PAGE allows it to allocate and free
gigantic pages at runtime.
sparc allows configuration such as huge pages of 16GB,
pages of 8KB and MAX_ORDER = 13 (default):
HPAGE_SHIFT (34) - PAGE_SHIFT (13) = 21 >= MAX_ORDER (13)
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: David S. Miller <davem@davemloft.net>
---
arch/sparc/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 40f8f4f73fe8..ebcc9435db08 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -91,6 +91,7 @@ config SPARC64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_PTE_SPECIAL
select PCI_DOMAINS if PCI
+ select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
config ARCH_DEFCONFIG
string
--
2.20.1
^ permalink raw reply related
* [PATCH v8 1/4] sh: Advertise gigantic page support
From: Alexandre Ghiti @ 2019-03-27 6:36 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190327063626.18421-1-alex@ghiti.fr>
sh actually supports gigantic pages and selecting
ARCH_HAS_GIGANTIC_PAGE allows it to allocate and free
gigantic pages at runtime.
At least sdk7786_defconfig exposes such a configuration with
huge pages of 64MB, pages of 4KB and MAX_ORDER = 11:
HPAGE_SHIFT (26) - PAGE_SHIFT (12) = 14 >= MAX_ORDER (11)
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
arch/sh/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index b1c91ea9a958..0d9fb2468e0b 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,6 +53,7 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
select NEED_SG_DMA_LENGTH
+ select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
help
The SuperH is a RISC processor targeted for use in embedded systems
--
2.20.1
^ permalink raw reply related
* Re: [PATCH v2] kbuild: strip whitespace in cmd_record_mcount findstring
From: Nicholas Piggin @ 2019-03-27 6:17 UTC (permalink / raw)
To: Joe Lawrence, Masahiro Yamada
Cc: Michal Marek, linuxppc-dev, Linux Kernel Mailing List,
Steven Rostedt, Linux Kbuild mailing list
In-Reply-To: <20190326173308.GA26546@redhat.com>
Joe Lawrence's on March 27, 2019 3:33 am:
> On Tue, Mar 26, 2019 at 02:29:47PM +0900, Masahiro Yamada wrote:
>> On Tue, Mar 26, 2019 at 1:05 AM Joe Lawrence <joe.lawrence@redhat.com> wrote:
>> >
>> > CC_FLAGS_FTRACE may contain trailing whitespace that interferes with
>> > findstring.
>> >
>> > For example, commit 6977f95e63b9 ("powerpc: avoid -mno-sched-epilog on
>> > GCC 4.9 and newer") introduced a change such that on my ppc64le box,
>> > CC_FLAGS_FTRACE="-pg -mprofile-kernel ". (Note the trailing space.)
>> > When cmd_record_mcount is now invoked, findstring fails as the ftrace
>> > flags were found at very end of _c_flags, without the trailing space.
>> >
>> > _c_flags=" ... -pg -mprofile-kernel"
>> > CC_FLAGS_FTRACE="-pg -mprofile-kernel "
>> > ^
>> > findstring is looking for this extra space
>> >
>> > Remove the redundant whitespaces from CC_FLAGS_FTRACE in
>> > cmd_record_mcount to avoid this problem.
>> >
>> > Fixes: 6977f95e63b9 ("powerpc: avoid -mno-sched-epilog on GCC 4.9 and newer").
>> > Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
>> > ---
>> >
>> > Standard disclaimer: I'm not a kbuild expert, but this works around the
>> > problem I reported where ftrace and livepatch self-tests were failing as
>> > specified object files were not run through the recordmcount.pl script:
>> >
>> > ppc64le: ftrace self-tests and $(CC_FLAGS_FTRACE) broken?
>> > https://lists.ozlabs.org/pipermail/linuxppc-dev/2019-March/187298.html
>> >
>> > scripts/Makefile.build | 8 ++++----
>> > 1 file changed, 4 insertions(+), 4 deletions(-)
>> >
>> > diff --git a/scripts/Makefile.build b/scripts/Makefile.build
>> > index 2554a15ecf2b..74d402b5aa3c 100644
>> > --- a/scripts/Makefile.build
>> > +++ b/scripts/Makefile.build
>> > @@ -199,10 +199,10 @@ sub_cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
>> > "$(if $(part-of-module),1,0)" "$(@)";
>> > recordmcount_source := $(srctree)/scripts/recordmcount.pl
>> > endif # BUILD_C_RECORDMCOUNT
>> > -cmd_record_mcount = \
>> > - if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \
>> > - "$(CC_FLAGS_FTRACE)" ]; then \
>> > - $(sub_cmd_record_mcount) \
>> > +cmd_record_mcount = \
>> > + if [ "$(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags))" = \
>> > + "$(strip $(CC_FLAGS_FTRACE))" ]; then \
>> > + $(sub_cmd_record_mcount) \
>> > fi
>> > endif # CC_USING_RECORD_MCOUNT
>> > endif # CONFIG_FTRACE_MCOUNT_RECORD
>> > --
>> > 2.20.1
>> >
>>
>>
>>
>> I do not see a point in using the shell command here
>> in the first place.
>>
>> Instead of adding crappy workarounds,
>> I guess the following simple code should work:
>>
>>
>> index 2554a15..5f13021 100644
>> --- a/scripts/Makefile.build
>> +++ b/scripts/Makefile.build
>> @@ -199,11 +199,8 @@ sub_cmd_record_mcount = perl
>> $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
>> "$(if $(part-of-module),1,0)" "$(@)";
>> recordmcount_source := $(srctree)/scripts/recordmcount.pl
>> endif # BUILD_C_RECORDMCOUNT
>> -cmd_record_mcount = \
>> - if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \
>> - "$(CC_FLAGS_FTRACE)" ]; then \
>> - $(sub_cmd_record_mcount) \
>> - fi
>> +cmd_record_mcount = $(if $(findstring $(CC_FLAGS_FTRACE),$(_c_flags)),\
>> + $(sub_cmd_record_mcount))
>> endif # CC_USING_RECORD_MCOUNT
>> endif # CONFIG_FTRACE_MCOUNT_RECORD
>>
>
> Hi Masahiro,
>
> Agreed on the shell command ugliness, however I still think we need to
> strip the search pattern here. With your suggestion:
>
> % rm -f kernel/trace/trace_selftest_dynamic.o
> % make kernel/trace/trace_selftest_dynamic.o
> CALL scripts/checksyscalls.sh
> CALL scripts/atomic/check-atomics.sh
> CC kernel/trace/trace_selftest_dynamic.o
>
> % eu-readelf --sections kernel/trace/trace_selftest_dynamic.o | grep mcount
> (nothing)
>
> Adding it back as, as below, restores those sections and the self tests
> work again.
Thanks for finding and fixing this, nice work!
Thanks,
Nick
>
> Regards,
>
> -- Joe
>
> -->8-- -->8-- -->8-- -->8-- -->8-- -->8-- -->8-- -->8-- -->8-- -->8--
>
> From 6a85e8ecf4179b3e80601a327ec43d8d49f0e3cd Mon Sep 17 00:00:00 2001
> From: Joe Lawrence <joe.lawrence@redhat.com>
> Date: Tue, 26 Mar 2019 10:50:28 -0400
> Subject: [PATCH v2] kbuild: strip whitespace in cmd_record_mcount findstring
>
> CC_FLAGS_FTRACE may contain trailing whitespace that interferes with
> findstring.
>
> For example, commit 6977f95e63b9 ("powerpc: avoid -mno-sched-epilog on
> GCC 4.9 and newer") introduced a change such that on my ppc64le box,
> CC_FLAGS_FTRACE="-pg -mprofile-kernel ". (Note the trailing space.)
> When cmd_record_mcount is now invoked, findstring fails as the ftrace
> flags were found at very end of _c_flags, without the trailing space.
>
> _c_flags=" ... -pg -mprofile-kernel"
> CC_FLAGS_FTRACE="-pg -mprofile-kernel "
> ^
> findstring is looking for this extra space
>
> Remove the redundant whitespaces from CC_FLAGS_FTRACE in
> cmd_record_mcount to avoid this problem.
>
> Suggested-by: Masahiro Yamada <yamada.masahiro@socionext.com> (refactoring)
> Fixes: 6977f95e63b9 ("powerpc: avoid -mno-sched-epilog on GCC 4.9 and newer").
> Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
> ---
> scripts/Makefile.build | 7 ++-----
> 1 file changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/scripts/Makefile.build b/scripts/Makefile.build
> index 2554a15ecf2b..76ca30cc4791 100644
> --- a/scripts/Makefile.build
> +++ b/scripts/Makefile.build
> @@ -199,11 +199,8 @@ sub_cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
> "$(if $(part-of-module),1,0)" "$(@)";
> recordmcount_source := $(srctree)/scripts/recordmcount.pl
> endif # BUILD_C_RECORDMCOUNT
> -cmd_record_mcount = \
> - if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \
> - "$(CC_FLAGS_FTRACE)" ]; then \
> - $(sub_cmd_record_mcount) \
> - fi
> +cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), \
> + $(sub_cmd_record_mcount))
> endif # CC_USING_RECORD_MCOUNT
> endif # CONFIG_FTRACE_MCOUNT_RECORD
>
> --
> 2.20.1
>
>
^ permalink raw reply
* Re: [PATCH v2] arch/powerpc: Rework local_paca to avoid LTO warnings
From: Nicholas Piggin @ 2019-03-27 6:02 UTC (permalink / raw)
To: Alastair D'Silva
Cc: Michal Hocko, linux-kernel, Mike, Rapoport, Paul Mackerras,
Mahesh, Salgaonkar, Andrew Morton, linuxppc-dev, Naveen N. Rao
In-Reply-To: <8d8a97e145758b92c2760012373f5217877a035c.camel@au1.ibm.com>
Alastair D'Silva's on March 27, 2019 2:37 pm:
> On Tue, 2019-03-26 at 15:58 +1000, Nicholas Piggin wrote:
>> Alastair D'Silva's on March 14, 2019 12:31 pm:
>> > From: Alastair D'Silva <alastair@d-silva.org>
>> >
>> > When building an LTO kernel, the existing code generates warnings:
>> > ./arch/powerpc/include/asm/paca.h:37:30: warning: register of
>> > ‘local_paca’ used for multiple global register variables
>> > register struct paca_struct *local_paca asm("r13");
>> > ^
>> > ./arch/powerpc/include/asm/paca.h:37:30: note: conflicts with
>> > ‘local_paca’
>>
>> Isn't this a bogus warning? It doesn't look like there's a way to
>> define it any other way.
>
> There isn't any other way to define it as a global. However, the
> warning is legitimate.
>
> The compiler sees that there are multiple global register variables,
> all pointing at the same register.
It's one variable though, so it's not a legitimate warning (unless
there is a way to declare a "reference" to it that we are not doing).
>
> The compiler can only determine this when LTO is used, as otherwise it
> only sees the one in the current compilation unit, whicd disappears by
> the time the kernel is linked.
>
>>
>> > This patch reworks local_paca into an inline getter & setter
>> > function,
>> > which addresses the warning.
>> >
>> > Changelog:
>> > V2
>> > - Address whitespace issues
>> > - keep new implementation close to where the old implementation
>> > was
>> >
>> > Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
>> > ---
>> > arch/powerpc/include/asm/paca.h | 37 +++++++++++++++++++++++++--
>> > ------
>> > arch/powerpc/kernel/paca.c | 2 +-
>> > 2 files changed, 29 insertions(+), 10 deletions(-)
>> >
>> > diff --git a/arch/powerpc/include/asm/paca.h
>> > b/arch/powerpc/include/asm/paca.h
>> > index e843bc5d1a0f..2fa0b43357c9 100644
>> > --- a/arch/powerpc/include/asm/paca.h
>> > +++ b/arch/powerpc/include/asm/paca.h
>> > @@ -34,19 +34,38 @@
>> > #include <asm/cpuidle.h>
>> > #include <asm/atomic.h>
>> >
>> > -register struct paca_struct *local_paca asm("r13");
>> > -
>> > #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
>> > extern unsigned int debug_smp_processor_id(void); /* from
>> > linux/smp.h */
>> > -/*
>> > - * Add standard checks that preemption cannot occur when using
>> > get_paca():
>> > - * otherwise the paca_struct it points to may be the wrong one
>> > just after.
>> > - */
>> > -#define get_paca() ((void) debug_smp_processor_id(), local_paca)
>> > -#else
>> > -#define get_paca() local_paca
>> > #endif
>> >
>> > +static inline struct paca_struct *get_paca_no_preempt_check(void)
>> > +{
>> > + register struct paca_struct *paca asm("r13");
>> > +
>> > + return paca;
>> > +}
>>
>> Problem is it now changes the global register variable to a local
>> register variable. The compiler would presumably be within its rights
>> to "cache" that return value or use another register for it, which
>> is not really what we want.
>>
>>
>
> I've confirmed that at least with GCC 8.2.0, the generated assembler is
> similar, but yes, the compiler may be free to take a copy into another
> register (although that would be a terrible optimisation), and then
> operate on that value.
Yep.
>
> Subsequent uses would still have to call the function (ie. fetch the
> data from r13) regardless, so I believe this scenario is safe.
>
> Can you think of a scenario where this is a problem?
It wouldn't be the subsequent use but the one use. If you're preempted
then you can't be using a stale r13 value.
Quite possibly any bug like that would already be buggy now, the cases
where it matters tend to need asm to access it. And it's something we
need to really audit and have proper accessors and preempt warnings
that Ben always harped on about.
But to just work around this warning it seems pretty dangerous to
change this and hope.
Thanks,
Nick
^ permalink raw reply
* [PATCH v4 7/7] ocxl: Provide global MMIO accessors for external drivers
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, Greg Kurz, linux-kernel,
Andrew Donnellan, Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
External drivers that communicate via OpenCAPI will need to make
MMIO calls to interact with the devices.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
---
drivers/misc/ocxl/Makefile | 2 +-
drivers/misc/ocxl/mmio.c | 234 +++++++++++++++++++++++++++++++++++++
include/misc/ocxl.h | 110 +++++++++++++++++
3 files changed, 345 insertions(+), 1 deletion(-)
create mode 100644 drivers/misc/ocxl/mmio.c
diff --git a/drivers/misc/ocxl/Makefile b/drivers/misc/ocxl/Makefile
index bc4e39bfda7b..d07d1bb8e8d4 100644
--- a/drivers/misc/ocxl/Makefile
+++ b/drivers/misc/ocxl/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0+
ccflags-$(CONFIG_PPC_WERROR) += -Werror
-ocxl-y += main.o pci.o config.o file.o pasid.o
+ocxl-y += main.o pci.o config.o file.o pasid.o mmio.o
ocxl-y += link.o context.o afu_irq.o sysfs.o trace.o
ocxl-y += core.o
obj-$(CONFIG_OCXL) += ocxl.o
diff --git a/drivers/misc/ocxl/mmio.c b/drivers/misc/ocxl/mmio.c
new file mode 100644
index 000000000000..aae713db4ebe
--- /dev/null
+++ b/drivers/misc/ocxl/mmio.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2019 IBM Corp.
+#include <linux/sched/mm.h>
+#include "trace.h"
+#include "ocxl_internal.h"
+
+int ocxl_global_mmio_read32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 *val)
+{
+ if (offset > afu->config.global_mmio_size - 4)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ *val = readl_be((char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ *val = readl((char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_read32);
+
+int ocxl_global_mmio_read64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 *val)
+{
+ if (offset > afu->config.global_mmio_size - 8)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ *val = readq_be((char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ *val = readq((char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_read64);
+
+int ocxl_global_mmio_write32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 val)
+{
+ if (offset > afu->config.global_mmio_size - 4)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ writel_be(val, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ writel(val, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_write32);
+
+int ocxl_global_mmio_write64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 val)
+{
+ if (offset > afu->config.global_mmio_size - 8)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ writeq_be(val, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ writeq(val, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_write64);
+
+int ocxl_global_mmio_set32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 mask)
+{
+ u32 tmp;
+
+ if (offset > afu->config.global_mmio_size - 4)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ tmp = readl_be((char *)afu->global_mmio_ptr + offset);
+ tmp |= mask;
+ writel_be(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ tmp = readl((char *)afu->global_mmio_ptr + offset);
+ tmp |= mask;
+ writel(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_set32);
+
+int ocxl_global_mmio_set64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 mask)
+{
+ u64 tmp;
+
+ if (offset > afu->config.global_mmio_size - 8)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ tmp = readq_be((char *)afu->global_mmio_ptr + offset);
+ tmp |= mask;
+ writeq_be(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ tmp = readq((char *)afu->global_mmio_ptr + offset);
+ tmp |= mask;
+ writeq(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_set64);
+
+int ocxl_global_mmio_clear32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 mask)
+{
+ u32 tmp;
+
+ if (offset > afu->config.global_mmio_size - 4)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ tmp = readl_be((char *)afu->global_mmio_ptr + offset);
+ tmp &= ~mask;
+ writel_be(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ tmp = readl((char *)afu->global_mmio_ptr + offset);
+ tmp &= ~mask;
+ writel(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_clear32);
+
+int ocxl_global_mmio_clear64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 mask)
+{
+ u64 tmp;
+
+ if (offset > afu->config.global_mmio_size - 8)
+ return -EINVAL;
+
+#ifdef __BIG_ENDIAN__
+ if (endian == OCXL_HOST_ENDIAN)
+ endian = OCXL_BIG_ENDIAN;
+#endif
+
+ switch (endian) {
+ case OCXL_BIG_ENDIAN:
+ tmp = readq_be((char *)afu->global_mmio_ptr + offset);
+ tmp &= ~mask;
+ writeq_be(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+
+ default:
+ tmp = readq((char *)afu->global_mmio_ptr + offset);
+ tmp &= ~mask;
+ writeq(tmp, (char *)afu->global_mmio_ptr + offset);
+ break;
+ }
+
+ writeq(tmp, (char *)afu->global_mmio_ptr + offset);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_global_mmio_clear64);
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index dea93885a839..5c4b4916e6be 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -45,6 +45,12 @@ struct ocxl_fn_config {
s8 max_afu_index;
};
+enum ocxl_endian {
+ OCXL_BIG_ENDIAN = 0, /**< AFU data is big-endian */
+ OCXL_LITTLE_ENDIAN = 1, /**< AFU data is little-endian */
+ OCXL_HOST_ENDIAN = 2, /**< AFU data is the same endianness as the host */
+};
+
// These are opaque outside the ocxl driver
struct ocxl_afu;
struct ocxl_fn;
@@ -230,6 +236,110 @@ void ocxl_afu_set_private(struct ocxl_afu *afu, void *private);
*/
void *ocxl_afu_get_private(struct ocxl_afu *dev);
+// Global MMIO
+/**
+ * Read a 32 bit value from global MMIO
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @val: returns the value
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_read32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 *val);
+
+/**
+ * Read a 64 bit value from global MMIO
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @val: returns the value
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_read64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 *val);
+
+/**
+ * Write a 32 bit value to global MMIO
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @val: The value to write
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_write32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 val);
+
+/**
+ * Write a 64 bit value to global MMIO
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @val: The value to write
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_write64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 val);
+
+/**
+ * Set bits in a 32 bit global MMIO register
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @mask: a mask of the bits to set
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_set32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 mask);
+
+/**
+ * Set bits in a 64 bit global MMIO register
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @mask: a mask of the bits to set
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_set64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 mask);
+
+/**
+ * Set bits in a 32 bit global MMIO register
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @mask: a mask of the bits to set
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_clear32(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u32 mask);
+
+/**
+ * Set bits in a 64 bit global MMIO register
+ *
+ * @afu: The AFU
+ * @offset: The Offset from the start of MMIO
+ * @endian: the endianness that the MMIO data is in
+ * @mask: a mask of the bits to set
+ *
+ * Returns 0 for success, negative on error
+ */
+int ocxl_global_mmio_clear64(struct ocxl_afu *afu, size_t offset,
+ enum ocxl_endian endian, u64 mask);
// Functions left here are for compatibility with the cxlflash driver
--
2.20.1
^ permalink raw reply related
* [PATCH v4 6/7] ocxl: move event_fd handling to frontend
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
Event_fd is only used in the driver frontend, so it does not
need to exist in the backend code. Relocate it to the frontend
and provide an opaque mechanism for consumers instead.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/afu_irq.c | 74 ++++++++++++++++++-------------
drivers/misc/ocxl/file.c | 22 ++++++++-
drivers/misc/ocxl/ocxl_internal.h | 5 ---
include/misc/ocxl.h | 46 +++++++++++++++++++
4 files changed, 109 insertions(+), 38 deletions(-)
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index 2d410cd6f817..70f8f1c3929d 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0+
// Copyright 2017 IBM Corp.
#include <linux/interrupt.h>
-#include <linux/eventfd.h>
+#include <asm/pnv-ocxl.h>
#include "ocxl_internal.h"
#include "trace.h"
@@ -11,7 +11,9 @@ struct afu_irq {
unsigned int virq;
char *name;
u64 trigger_page;
- struct eventfd_ctx *ev_ctx;
+ irqreturn_t (*handler)(void *private);
+ void (*free_private)(void *private);
+ void *private;
};
int ocxl_irq_offset_to_id(struct ocxl_context *ctx, u64 offset)
@@ -24,14 +26,44 @@ u64 ocxl_irq_id_to_offset(struct ocxl_context *ctx, int irq_id)
return ctx->afu->irq_base_offset + (irq_id << PAGE_SHIFT);
}
+int ocxl_irq_set_handler(struct ocxl_context *ctx, int irq_id,
+ irqreturn_t (*handler)(void *private),
+ void (*free_private)(void *private),
+ void *private)
+{
+ struct afu_irq *irq;
+ int rc;
+
+ mutex_lock(&ctx->irq_lock);
+ irq = idr_find(&ctx->irq_idr, irq_id);
+ if (!irq) {
+ rc = -EINVAL;
+ goto unlock;
+ }
+
+ irq->handler = handler;
+ irq->private = private;
+ irq->free_private = free_private;
+
+ rc = 0;
+ // Fall through to unlock
+
+unlock:
+ mutex_unlock(&ctx->irq_lock);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(ocxl_irq_set_handler);
+
static irqreturn_t afu_irq_handler(int virq, void *data)
{
struct afu_irq *irq = (struct afu_irq *) data;
trace_ocxl_afu_irq_receive(virq);
- if (irq->ev_ctx)
- eventfd_signal(irq->ev_ctx, 1);
- return IRQ_HANDLED;
+
+ if (irq->handler)
+ return irq->handler(irq->private);
+
+ return IRQ_HANDLED; // Just drop it on the ground
}
static int setup_afu_irq(struct ocxl_context *ctx, struct afu_irq *irq)
@@ -117,6 +149,7 @@ int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id)
kfree(irq);
return rc;
}
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_alloc);
static void afu_irq_free(struct afu_irq *irq, struct ocxl_context *ctx)
{
@@ -126,8 +159,8 @@ static void afu_irq_free(struct afu_irq *irq, struct ocxl_context *ctx)
ocxl_irq_id_to_offset(ctx, irq->id),
1 << PAGE_SHIFT, 1);
release_afu_irq(irq);
- if (irq->ev_ctx)
- eventfd_ctx_put(irq->ev_ctx);
+ if (irq->free_private)
+ irq->free_private(irq->private);
ocxl_link_free_irq(ctx->afu->fn->link, irq->hw_irq);
kfree(irq);
}
@@ -148,6 +181,7 @@ int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id)
mutex_unlock(&ctx->irq_lock);
return 0;
}
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_free);
void ocxl_afu_irq_free_all(struct ocxl_context *ctx)
{
@@ -160,31 +194,6 @@ void ocxl_afu_irq_free_all(struct ocxl_context *ctx)
mutex_unlock(&ctx->irq_lock);
}
-int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, int irq_id, int eventfd)
-{
- struct afu_irq *irq;
- struct eventfd_ctx *ev_ctx;
- int rc = 0;
-
- mutex_lock(&ctx->irq_lock);
- irq = idr_find(&ctx->irq_idr, irq_id);
- if (!irq) {
- rc = -EINVAL;
- goto unlock;
- }
-
- ev_ctx = eventfd_ctx_fdget(eventfd);
- if (IS_ERR(ev_ctx)) {
- rc = -EINVAL;
- goto unlock;
- }
-
- irq->ev_ctx = ev_ctx;
-unlock:
- mutex_unlock(&ctx->irq_lock);
- return rc;
-}
-
u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id)
{
struct afu_irq *irq;
@@ -197,3 +206,4 @@ u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id)
mutex_unlock(&ctx->irq_lock);
return addr;
}
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_get_addr);
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index 7f5282a3af3a..8aa22893ed76 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -3,6 +3,7 @@
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/sched/signal.h>
+#include <linux/eventfd.h>
#include <linux/uaccess.h>
#include <uapi/misc/ocxl.h>
#include <asm/reg.h>
@@ -183,11 +184,27 @@ static long afu_ioctl_get_features(struct ocxl_context *ctx,
x == OCXL_IOCTL_GET_FEATURES ? "GET_FEATURES" : \
"UNKNOWN")
+static irqreturn_t irq_handler(void *private)
+{
+ struct eventfd_ctx *ev_ctx = private;
+
+ eventfd_signal(ev_ctx, 1);
+ return IRQ_HANDLED;
+}
+
+static void irq_free(void *private)
+{
+ struct eventfd_ctx *ev_ctx = private;
+
+ eventfd_ctx_put(ev_ctx);
+}
+
static long afu_ioctl(struct file *file, unsigned int cmd,
unsigned long args)
{
struct ocxl_context *ctx = file->private_data;
struct ocxl_ioctl_irq_fd irq_fd;
+ struct eventfd_ctx *ev_ctx;
int irq_id;
u64 irq_offset;
long rc;
@@ -239,7 +256,10 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
if (irq_fd.reserved)
return -EINVAL;
irq_id = ocxl_irq_offset_to_id(ctx, irq_fd.irq_offset);
- rc = ocxl_afu_irq_set_fd(ctx, irq_id, irq_fd.eventfd);
+ ev_ctx = eventfd_ctx_fdget(irq_fd.eventfd);
+ if (!ev_ctx)
+ return -EFAULT;
+ rc = ocxl_irq_set_handler(ctx, irq_id, irq_handler, irq_free, ev_ctx);
break;
case OCXL_IOCTL_GET_METADATA:
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 58969467bd5c..97415afd79f3 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -139,11 +139,6 @@ void ocxl_sysfs_unregister_afu(struct ocxl_file_info *info);
int ocxl_irq_offset_to_id(struct ocxl_context *ctx, u64 offset);
u64 ocxl_irq_id_to_offset(struct ocxl_context *ctx, int irq_id);
-int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
-int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
void ocxl_afu_irq_free_all(struct ocxl_context *ctx);
-int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, int irq_id,
- int eventfd);
-u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id);
#endif /* _OCXL_INTERNAL_H_ */
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index e4704632eac5..dea93885a839 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -155,6 +155,52 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr,
*/
int ocxl_context_detach(struct ocxl_context *ctx);
+// AFU IRQs
+
+/**
+ * Allocate an IRQ associated with an AFU context
+ * @ctx: the AFU context
+ * @irq_id: out, the IRQ ID
+ *
+ * Returns 0 on success, negative on failure
+ */
+extern int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
+
+/**
+ * Frees an IRQ associated with an AFU context
+ * @ctx: the AFU context
+ * @irq_id: the IRQ ID
+ *
+ * Returns 0 on success, negative on failure
+ */
+extern int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
+
+/**
+ * Gets the address of the trigger page for an IRQ
+ * This can then be provided to an AFU which will write to that
+ * page to trigger the IRQ.
+ * @ctx: The AFU context that the IRQ is associated with
+ * @irq_id: The IRQ ID
+ *
+ * returns the trigger page address, or 0 if the IRQ is not valid
+ */
+extern u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id);
+
+/**
+ * Provide a callback to be called when an IRQ is triggered
+ * @ctx: The AFU context that the IRQ is associated with
+ * @irq_id: The IRQ ID
+ * @handler: the callback to be called when the IRQ is triggered
+ * @free_private: the callback to be called when the IRQ is freed (may be NULL)
+ * @private: Private data to be passed to the callbacks
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ocxl_irq_set_handler(struct ocxl_context *ctx, int irq_id,
+ irqreturn_t (*handler)(void *private),
+ void (*free_private)(void *private),
+ void *private);
+
// AFU Metadata
/**
--
2.20.1
^ permalink raw reply related
* [PATCH v4 5/7] ocxl: afu_irq only deals with IRQ IDs, not offsets
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The use of offsets is required only in the frontend, so alter
the IRQ API to only work with IRQ IDs in the backend.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/afu_irq.c | 34 +++++++++++++++----------------
drivers/misc/ocxl/context.c | 7 +++++--
drivers/misc/ocxl/file.c | 13 +++++++-----
drivers/misc/ocxl/ocxl_internal.h | 10 +++++----
drivers/misc/ocxl/trace.h | 12 ++++-------
5 files changed, 39 insertions(+), 37 deletions(-)
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index 11ab996657a2..2d410cd6f817 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -14,14 +14,14 @@ struct afu_irq {
struct eventfd_ctx *ev_ctx;
};
-static int irq_offset_to_id(struct ocxl_context *ctx, u64 offset)
+int ocxl_irq_offset_to_id(struct ocxl_context *ctx, u64 offset)
{
return (offset - ctx->afu->irq_base_offset) >> PAGE_SHIFT;
}
-static u64 irq_id_to_offset(struct ocxl_context *ctx, int id)
+u64 ocxl_irq_id_to_offset(struct ocxl_context *ctx, int irq_id)
{
- return ctx->afu->irq_base_offset + (id << PAGE_SHIFT);
+ return ctx->afu->irq_base_offset + (irq_id << PAGE_SHIFT);
}
static irqreturn_t afu_irq_handler(int virq, void *data)
@@ -69,7 +69,7 @@ static void release_afu_irq(struct afu_irq *irq)
kfree(irq->name);
}
-int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset)
+int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id)
{
struct afu_irq *irq;
int rc;
@@ -101,11 +101,11 @@ int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset)
if (rc)
goto err_alloc;
- *irq_offset = irq_id_to_offset(ctx, irq->id);
-
- trace_ocxl_afu_irq_alloc(ctx->pasid, irq->id, irq->virq, irq->hw_irq,
- *irq_offset);
+ trace_ocxl_afu_irq_alloc(ctx->pasid, irq->id, irq->virq, irq->hw_irq);
mutex_unlock(&ctx->irq_lock);
+
+ *irq_id = irq->id;
+
return 0;
err_alloc:
@@ -123,7 +123,7 @@ static void afu_irq_free(struct afu_irq *irq, struct ocxl_context *ctx)
trace_ocxl_afu_irq_free(ctx->pasid, irq->id);
if (ctx->mapping)
unmap_mapping_range(ctx->mapping,
- irq_id_to_offset(ctx, irq->id),
+ ocxl_irq_id_to_offset(ctx, irq->id),
1 << PAGE_SHIFT, 1);
release_afu_irq(irq);
if (irq->ev_ctx)
@@ -132,14 +132,13 @@ static void afu_irq_free(struct afu_irq *irq, struct ocxl_context *ctx)
kfree(irq);
}
-int ocxl_afu_irq_free(struct ocxl_context *ctx, u64 irq_offset)
+int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id)
{
struct afu_irq *irq;
- int id = irq_offset_to_id(ctx, irq_offset);
mutex_lock(&ctx->irq_lock);
- irq = idr_find(&ctx->irq_idr, id);
+ irq = idr_find(&ctx->irq_idr, irq_id);
if (!irq) {
mutex_unlock(&ctx->irq_lock);
return -EINVAL;
@@ -161,14 +160,14 @@ void ocxl_afu_irq_free_all(struct ocxl_context *ctx)
mutex_unlock(&ctx->irq_lock);
}
-int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset, int eventfd)
+int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, int irq_id, int eventfd)
{
struct afu_irq *irq;
struct eventfd_ctx *ev_ctx;
- int rc = 0, id = irq_offset_to_id(ctx, irq_offset);
+ int rc = 0;
mutex_lock(&ctx->irq_lock);
- irq = idr_find(&ctx->irq_idr, id);
+ irq = idr_find(&ctx->irq_idr, irq_id);
if (!irq) {
rc = -EINVAL;
goto unlock;
@@ -186,14 +185,13 @@ int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset, int eventfd)
return rc;
}
-u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, u64 irq_offset)
+u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id)
{
struct afu_irq *irq;
- int id = irq_offset_to_id(ctx, irq_offset);
u64 addr = 0;
mutex_lock(&ctx->irq_lock);
- irq = idr_find(&ctx->irq_idr, id);
+ irq = idr_find(&ctx->irq_idr, irq_id);
if (irq)
addr = irq->trigger_page;
mutex_unlock(&ctx->irq_lock);
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index b60e674ac019..bab9c9364184 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -94,8 +94,9 @@ static vm_fault_t map_afu_irq(struct vm_area_struct *vma, unsigned long address,
u64 offset, struct ocxl_context *ctx)
{
u64 trigger_addr;
+ int irq_id = ocxl_irq_offset_to_id(ctx, offset);
- trigger_addr = ocxl_afu_irq_get_addr(ctx, offset);
+ trigger_addr = ocxl_afu_irq_get_addr(ctx, irq_id);
if (!trigger_addr)
return VM_FAULT_SIGBUS;
@@ -155,12 +156,14 @@ static const struct vm_operations_struct ocxl_vmops = {
static int check_mmap_afu_irq(struct ocxl_context *ctx,
struct vm_area_struct *vma)
{
+ int irq_id = ocxl_irq_offset_to_id(ctx, vma->vm_pgoff << PAGE_SHIFT);
+
/* only one page */
if (vma_pages(vma) != 1)
return -EINVAL;
/* check offset validty */
- if (!ocxl_afu_irq_get_addr(ctx, vma->vm_pgoff << PAGE_SHIFT))
+ if (!ocxl_afu_irq_get_addr(ctx, irq_id))
return -EINVAL;
/*
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index 8225892a5d77..7f5282a3af3a 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -188,6 +188,7 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
{
struct ocxl_context *ctx = file->private_data;
struct ocxl_ioctl_irq_fd irq_fd;
+ int irq_id;
u64 irq_offset;
long rc;
bool closed;
@@ -209,12 +210,13 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
break;
case OCXL_IOCTL_IRQ_ALLOC:
- rc = ocxl_afu_irq_alloc(ctx, &irq_offset);
+ rc = ocxl_afu_irq_alloc(ctx, &irq_id);
if (!rc) {
+ irq_offset = ocxl_irq_id_to_offset(ctx, irq_id);
rc = copy_to_user((u64 __user *) args, &irq_offset,
sizeof(irq_offset));
if (rc) {
- ocxl_afu_irq_free(ctx, irq_offset);
+ ocxl_afu_irq_free(ctx, irq_id);
return -EFAULT;
}
}
@@ -225,7 +227,8 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
sizeof(irq_offset));
if (rc)
return -EFAULT;
- rc = ocxl_afu_irq_free(ctx, irq_offset);
+ irq_id = ocxl_irq_offset_to_id(ctx, irq_offset);
+ rc = ocxl_afu_irq_free(ctx, irq_id);
break;
case OCXL_IOCTL_IRQ_SET_FD:
@@ -235,8 +238,8 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
return -EFAULT;
if (irq_fd.reserved)
return -EINVAL;
- rc = ocxl_afu_irq_set_fd(ctx, irq_fd.irq_offset,
- irq_fd.eventfd);
+ irq_id = ocxl_irq_offset_to_id(ctx, irq_fd.irq_offset);
+ rc = ocxl_afu_irq_set_fd(ctx, irq_id, irq_fd.eventfd);
break;
case OCXL_IOCTL_GET_METADATA:
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index de6c16237742..58969467bd5c 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -137,11 +137,13 @@ void ocxl_context_detach_all(struct ocxl_afu *afu);
int ocxl_sysfs_register_afu(struct ocxl_file_info *info);
void ocxl_sysfs_unregister_afu(struct ocxl_file_info *info);
-int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset);
-int ocxl_afu_irq_free(struct ocxl_context *ctx, u64 irq_offset);
+int ocxl_irq_offset_to_id(struct ocxl_context *ctx, u64 offset);
+u64 ocxl_irq_id_to_offset(struct ocxl_context *ctx, int irq_id);
+int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
+int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
void ocxl_afu_irq_free_all(struct ocxl_context *ctx);
-int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset,
+int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, int irq_id,
int eventfd);
-u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, u64 irq_offset);
+u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id);
#endif /* _OCXL_INTERNAL_H_ */
diff --git a/drivers/misc/ocxl/trace.h b/drivers/misc/ocxl/trace.h
index bcb7ff330c1e..024f417e7e01 100644
--- a/drivers/misc/ocxl/trace.h
+++ b/drivers/misc/ocxl/trace.h
@@ -107,16 +107,14 @@ DEFINE_EVENT(ocxl_fault_handler, ocxl_fault_ack,
);
TRACE_EVENT(ocxl_afu_irq_alloc,
- TP_PROTO(int pasid, int irq_id, unsigned int virq, int hw_irq,
- u64 irq_offset),
- TP_ARGS(pasid, irq_id, virq, hw_irq, irq_offset),
+ TP_PROTO(int pasid, int irq_id, unsigned int virq, int hw_irq),
+ TP_ARGS(pasid, irq_id, virq, hw_irq),
TP_STRUCT__entry(
__field(int, pasid)
__field(int, irq_id)
__field(unsigned int, virq)
__field(int, hw_irq)
- __field(u64, irq_offset)
),
TP_fast_assign(
@@ -124,15 +122,13 @@ TRACE_EVENT(ocxl_afu_irq_alloc,
__entry->irq_id = irq_id;
__entry->virq = virq;
__entry->hw_irq = hw_irq;
- __entry->irq_offset = irq_offset;
),
- TP_printk("pasid=0x%x irq_id=%d virq=%u hw_irq=%d irq_offset=0x%llx",
+ TP_printk("pasid=0x%x irq_id=%d virq=%u hw_irq=%d",
__entry->pasid,
__entry->irq_id,
__entry->virq,
- __entry->hw_irq,
- __entry->irq_offset
+ __entry->hw_irq
)
);
--
2.20.1
^ permalink raw reply related
* [PATCH v4 4/7] ocxl: Allow external drivers to use OpenCAPI contexts
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, Greg Kurz, linux-kernel,
Andrew Donnellan, Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
Most OpenCAPI operations require a valid context, so
exposing these functions to external drivers is necessary.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
---
drivers/misc/ocxl/context.c | 22 ++++++++++-------
drivers/misc/ocxl/file.c | 8 ++-----
drivers/misc/ocxl/ocxl_internal.h | 6 -----
include/misc/ocxl.h | 39 +++++++++++++++++++++++++++++++
4 files changed, 55 insertions(+), 20 deletions(-)
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index c73a859d2224..b60e674ac019 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -4,15 +4,17 @@
#include "trace.h"
#include "ocxl_internal.h"
-struct ocxl_context *ocxl_context_alloc(void)
-{
- return kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
-}
-
-int ocxl_context_init(struct ocxl_context *ctx, struct ocxl_afu *afu,
+int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
struct address_space *mapping)
{
int pasid;
+ struct ocxl_context *ctx;
+
+ *context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
+ if (!*context)
+ return -ENOMEM;
+
+ ctx = *context;
ctx->afu = afu;
mutex_lock(&afu->contexts_lock);
@@ -43,6 +45,7 @@ int ocxl_context_init(struct ocxl_context *ctx, struct ocxl_afu *afu,
ocxl_afu_get(afu);
return 0;
}
+EXPORT_SYMBOL_GPL(ocxl_context_alloc);
/*
* Callback for when a translation fault triggers an error
@@ -63,7 +66,7 @@ static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
wake_up_all(&ctx->events_wq);
}
-int ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
+int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
{
int rc;
@@ -75,7 +78,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
}
rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
- current->mm->context.id, ctx->tidr, amr, current->mm,
+ mm->context.id, ctx->tidr, amr, mm,
xsl_fault_error, ctx);
if (rc)
goto out;
@@ -85,6 +88,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
mutex_unlock(&ctx->status_mutex);
return rc;
}
+EXPORT_SYMBOL_GPL(ocxl_context_attach);
static vm_fault_t map_afu_irq(struct vm_area_struct *vma, unsigned long address,
u64 offset, struct ocxl_context *ctx)
@@ -243,6 +247,7 @@ int ocxl_context_detach(struct ocxl_context *ctx)
}
return 0;
}
+EXPORT_SYMBOL_GPL(ocxl_context_detach);
void ocxl_context_detach_all(struct ocxl_afu *afu)
{
@@ -280,3 +285,4 @@ void ocxl_context_free(struct ocxl_context *ctx)
ocxl_afu_put(ctx->afu);
kfree(ctx);
}
+EXPORT_SYMBOL_GPL(ocxl_context_free);
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index 7a38ea5af9db..8225892a5d77 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -61,11 +61,7 @@ static int afu_open(struct inode *inode, struct file *file)
if (!info)
return -ENODEV;
- ctx = ocxl_context_alloc();
- if (!ctx)
- return -ENOMEM;
-
- rc = ocxl_context_init(ctx, info->afu, inode->i_mapping);
+ rc = ocxl_context_alloc(&ctx, info->afu, inode->i_mapping);
if (rc)
return rc;
@@ -90,7 +86,7 @@ static long afu_ioctl_attach(struct ocxl_context *ctx,
return -EINVAL;
amr = arg.amr & mfspr(SPRN_UAMOR);
- rc = ocxl_context_attach(ctx, amr);
+ rc = ocxl_context_attach(ctx, amr, current->mm);
return rc;
}
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 53b6c64a1bf0..de6c16237742 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -130,15 +130,9 @@ int ocxl_config_check_afu_index(struct pci_dev *dev,
*/
int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid);
-struct ocxl_context *ocxl_context_alloc(void);
-int ocxl_context_init(struct ocxl_context *ctx, struct ocxl_afu *afu,
- struct address_space *mapping);
-int ocxl_context_attach(struct ocxl_context *ctx, u64 amr);
int ocxl_context_mmap(struct ocxl_context *ctx,
struct vm_area_struct *vma);
-int ocxl_context_detach(struct ocxl_context *ctx);
void ocxl_context_detach_all(struct ocxl_afu *afu);
-void ocxl_context_free(struct ocxl_context *ctx);
int ocxl_sysfs_register_afu(struct ocxl_file_info *info);
void ocxl_sysfs_unregister_afu(struct ocxl_file_info *info);
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index 8bafd748e380..e4704632eac5 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -48,6 +48,7 @@ struct ocxl_fn_config {
// These are opaque outside the ocxl driver
struct ocxl_afu;
struct ocxl_fn;
+struct ocxl_context;
// Device detection & initialisation
@@ -116,6 +117,44 @@ const struct ocxl_fn_config *ocxl_function_config(struct ocxl_fn *fn);
*/
void ocxl_function_close(struct ocxl_fn *fn);
+// Context allocation
+
+/**
+ * Allocate an OpenCAPI context
+ *
+ * @context: The OpenCAPI context to allocate, must be freed with ocxl_context_free
+ * @afu: The AFU the context belongs to
+ * @mapping: The mapping to unmap when the context is closed (may be NULL)
+ */
+int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
+ struct address_space *mapping);
+
+/**
+ * Free an OpenCAPI context
+ *
+ * @ctx: The OpenCAPI context to free
+ */
+void ocxl_context_free(struct ocxl_context *ctx);
+
+/**
+ * Grant access to an MM to an OpenCAPI context
+ * @ctx: The OpenCAPI context to attach
+ * @amr: The value of the AMR register to restrict access
+ * @mm: The mm to attach to the context
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ocxl_context_attach(struct ocxl_context *ctx, u64 amr,
+ struct mm_struct *mm);
+
+/**
+ * Detach an MM from an OpenCAPI context
+ * @ctx: The OpenCAPI context to attach
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ocxl_context_detach(struct ocxl_context *ctx);
+
// AFU Metadata
/**
--
2.20.1
^ permalink raw reply related
* [PATCH v4 3/7] ocxl: Create a clear delineation between ocxl backend & frontend
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The OCXL driver contains both frontend code for interacting with userspace,
as well as backend code for interacting with the hardware.
This patch separates the backend code from the frontend so that it can be
used by other device drivers that communicate via OpenCAPI.
Relocate dev, cdev & sysfs files to the frontend code to allow external
drivers to maintain their own devices.
Reference counting on the device in the backend is replaced with kref
counting.
Move file & sysfs layer initialisation from core.c (backend) to
pci.c (frontend).
Create an ocxl_function oriented interface for initing devices &
enumerating AFUs.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/context.c | 2 +-
drivers/misc/ocxl/core.c | 201 +++++++++++++++++++-----------
drivers/misc/ocxl/file.c | 142 ++++++++++++++-------
drivers/misc/ocxl/ocxl_internal.h | 31 ++---
drivers/misc/ocxl/pci.c | 56 ++++-----
drivers/misc/ocxl/sysfs.c | 54 ++++----
include/misc/ocxl.h | 119 ++++++++++++++++--
7 files changed, 409 insertions(+), 196 deletions(-)
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index c10a940e3b38..c73a859d2224 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -238,7 +238,7 @@ int ocxl_context_detach(struct ocxl_context *ctx)
}
rc = ocxl_link_remove_pe(ctx->afu->fn->link, ctx->pasid);
if (rc) {
- dev_warn(&ctx->afu->dev,
+ dev_warn(&dev->dev,
"Couldn't remove PE entry cleanly: %d\n", rc);
}
return 0;
diff --git a/drivers/misc/ocxl/core.c b/drivers/misc/ocxl/core.c
index 2f2fe12eac1e..b7a09b21ab36 100644
--- a/drivers/misc/ocxl/core.c
+++ b/drivers/misc/ocxl/core.c
@@ -13,16 +13,6 @@ static void ocxl_fn_put(struct ocxl_fn *fn)
put_device(&fn->dev);
}
-struct ocxl_afu *ocxl_afu_get(struct ocxl_afu *afu)
-{
- return (get_device(&afu->dev) == NULL) ? NULL : afu;
-}
-
-void ocxl_afu_put(struct ocxl_afu *afu)
-{
- put_device(&afu->dev);
-}
-
static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
{
struct ocxl_afu *afu;
@@ -31,6 +21,7 @@ static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
if (!afu)
return NULL;
+ kref_init(&afu->kref);
mutex_init(&afu->contexts_lock);
mutex_init(&afu->afu_control_lock);
idr_init(&afu->contexts_idr);
@@ -39,32 +30,26 @@ static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
return afu;
}
-static void free_afu(struct ocxl_afu *afu)
+static void free_afu(struct kref *kref)
{
+ struct ocxl_afu *afu = container_of(kref, struct ocxl_afu, kref);
+
idr_destroy(&afu->contexts_idr);
ocxl_fn_put(afu->fn);
kfree(afu);
}
-static void free_afu_dev(struct device *dev)
+void ocxl_afu_get(struct ocxl_afu *afu)
{
- struct ocxl_afu *afu = to_ocxl_afu(dev);
-
- ocxl_unregister_afu(afu);
- free_afu(afu);
+ kref_get(&afu->kref);
}
+EXPORT_SYMBOL_GPL(ocxl_afu_get);
-static int set_afu_device(struct ocxl_afu *afu, const char *location)
+void ocxl_afu_put(struct ocxl_afu *afu)
{
- struct ocxl_fn *fn = afu->fn;
- int rc;
-
- afu->dev.parent = &fn->dev;
- afu->dev.release = free_afu_dev;
- rc = dev_set_name(&afu->dev, "%s.%s.%hhu", afu->config.name, location,
- afu->config.idx);
- return rc;
+ kref_put(&afu->kref, free_afu);
}
+EXPORT_SYMBOL_GPL(ocxl_afu_put);
static int assign_afu_actag(struct ocxl_afu *afu)
{
@@ -233,27 +218,25 @@ static int configure_afu(struct ocxl_afu *afu, u8 afu_idx, struct pci_dev *dev)
if (rc)
return rc;
- rc = set_afu_device(afu, dev_name(&dev->dev));
- if (rc)
- return rc;
-
rc = assign_afu_actag(afu);
if (rc)
return rc;
rc = assign_afu_pasid(afu);
- if (rc) {
- reclaim_afu_actag(afu);
- return rc;
- }
+ if (rc)
+ goto err_free_actag;
rc = map_mmio_areas(afu);
- if (rc) {
- reclaim_afu_pasid(afu);
- reclaim_afu_actag(afu);
- return rc;
- }
+ if (rc)
+ goto err_free_pasid;
+
return 0;
+
+err_free_pasid:
+ reclaim_afu_pasid(afu);
+err_free_actag:
+ reclaim_afu_actag(afu);
+ return rc;
}
static void deconfigure_afu(struct ocxl_afu *afu)
@@ -265,16 +248,8 @@ static void deconfigure_afu(struct ocxl_afu *afu)
static int activate_afu(struct pci_dev *dev, struct ocxl_afu *afu)
{
- int rc;
-
ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 1);
- /*
- * Char device creation is the last step, as processes can
- * call our driver immediately, so all our inits must be finished.
- */
- rc = ocxl_create_cdev(afu);
- if (rc)
- return rc;
+
return 0;
}
@@ -282,11 +257,10 @@ static void deactivate_afu(struct ocxl_afu *afu)
{
struct pci_dev *dev = to_pci_dev(afu->fn->dev.parent);
- ocxl_destroy_cdev(afu);
ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 0);
}
-int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
+static int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
{
int rc;
struct ocxl_afu *afu;
@@ -297,41 +271,29 @@ int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
rc = configure_afu(afu, afu_idx, dev);
if (rc) {
- free_afu(afu);
+ ocxl_afu_put(afu);
return rc;
}
- rc = ocxl_register_afu(afu);
- if (rc)
- goto err;
-
- rc = ocxl_sysfs_add_afu(afu);
- if (rc)
- goto err;
-
rc = activate_afu(dev, afu);
- if (rc)
- goto err_sys;
+ if (rc) {
+ deconfigure_afu(afu);
+ ocxl_afu_put(afu);
+ return rc;
+ }
list_add_tail(&afu->list, &fn->afu_list);
- return 0;
-err_sys:
- ocxl_sysfs_remove_afu(afu);
-err:
- deconfigure_afu(afu);
- device_unregister(&afu->dev);
- return rc;
+ return 0;
}
-void remove_afu(struct ocxl_afu *afu)
+static void remove_afu(struct ocxl_afu *afu)
{
list_del(&afu->list);
ocxl_context_detach_all(afu);
deactivate_afu(afu);
- ocxl_sysfs_remove_afu(afu);
deconfigure_afu(afu);
- device_unregister(&afu->dev);
+ ocxl_afu_put(afu); // matches the implicit get in alloc_afu
}
static struct ocxl_fn *alloc_function(void)
@@ -358,7 +320,7 @@ static void free_function(struct ocxl_fn *fn)
static void free_function_dev(struct device *dev)
{
- struct ocxl_fn *fn = to_ocxl_function(dev);
+ struct ocxl_fn *fn = container_of(dev, struct ocxl_fn, dev);
free_function(fn);
}
@@ -372,7 +334,6 @@ static int set_function_device(struct ocxl_fn *fn, struct pci_dev *dev)
rc = dev_set_name(&fn->dev, "ocxlfn.%s", dev_name(&dev->dev));
if (rc)
return rc;
- pci_set_drvdata(dev, fn);
return 0;
}
@@ -490,7 +451,7 @@ static void deconfigure_function(struct ocxl_fn *fn)
pci_disable_device(dev);
}
-struct ocxl_fn *init_function(struct pci_dev *dev)
+static struct ocxl_fn *init_function(struct pci_dev *dev)
{
struct ocxl_fn *fn;
int rc;
@@ -514,8 +475,100 @@ struct ocxl_fn *init_function(struct pci_dev *dev)
return fn;
}
-void remove_function(struct ocxl_fn *fn)
+// Device detection & initialisation
+
+struct ocxl_fn *ocxl_function_open(struct pci_dev *dev)
+{
+ int rc, afu_count = 0;
+ u8 afu;
+ struct ocxl_fn *fn;
+
+ if (!radix_enabled()) {
+ dev_err(&dev->dev, "Unsupported memory model (hash)\n");
+ return ERR_PTR(-ENODEV);
+ }
+
+ fn = init_function(dev);
+ if (IS_ERR(fn)) {
+ dev_err(&dev->dev, "function init failed: %li\n",
+ PTR_ERR(fn));
+ return fn;
+ }
+
+ for (afu = 0; afu <= fn->config.max_afu_index; afu++) {
+ rc = ocxl_config_check_afu_index(dev, &fn->config, afu);
+ if (rc > 0) {
+ rc = init_afu(dev, fn, afu);
+ if (rc) {
+ dev_err(&dev->dev,
+ "Can't initialize AFU index %d\n", afu);
+ continue;
+ }
+ afu_count++;
+ }
+ }
+ dev_info(&dev->dev, "%d AFU(s) configured\n", afu_count);
+ return fn;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_open);
+
+struct list_head *ocxl_function_afu_list(struct ocxl_fn *fn)
+{
+ return &fn->afu_list;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_afu_list);
+
+struct ocxl_afu *ocxl_function_fetch_afu(struct ocxl_fn *fn, u8 afu_idx)
+{
+ struct ocxl_afu *afu;
+
+ list_for_each_entry(afu, &fn->afu_list, list) {
+ if (afu->config.idx == afu_idx)
+ return afu;
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_fetch_afu);
+
+const struct ocxl_fn_config *ocxl_function_config(struct ocxl_fn *fn)
{
+ return &fn->config;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_config);
+
+void ocxl_function_close(struct ocxl_fn *fn)
+{
+ struct ocxl_afu *afu, *tmp;
+
+ list_for_each_entry_safe(afu, tmp, &fn->afu_list, list) {
+ remove_afu(afu);
+ }
+
deconfigure_function(fn);
device_unregister(&fn->dev);
}
+EXPORT_SYMBOL_GPL(ocxl_function_close);
+
+// AFU Metadata
+
+struct ocxl_afu_config *ocxl_afu_config(struct ocxl_afu *afu)
+{
+ return &afu->config;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_config);
+
+void ocxl_afu_set_private(struct ocxl_afu *afu, void *private)
+{
+ afu->private = private;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_set_private);
+
+void *ocxl_afu_get_private(struct ocxl_afu *afu)
+{
+ if (afu)
+ return afu->private;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_get_private);
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index 009e09b7ded5..7a38ea5af9db 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -17,70 +17,60 @@ static struct class *ocxl_class;
static struct mutex minors_idr_lock;
static struct idr minors_idr;
-static struct ocxl_afu *find_and_get_afu(dev_t devno)
+static struct ocxl_file_info *find_file_info(dev_t devno)
{
- struct ocxl_afu *afu;
- int afu_minor;
+ struct ocxl_file_info *info;
- afu_minor = MINOR(devno);
/*
* We don't declare an RCU critical section here, as our AFU
* is protected by a reference counter on the device. By the time the
- * minor number of a device is removed from the idr, the ref count of
+ * info reference is removed from the idr, the ref count of
* the device is already at 0, so no user API will access that AFU and
* this function can't return it.
*/
- afu = idr_find(&minors_idr, afu_minor);
- if (afu)
- ocxl_afu_get(afu);
- return afu;
+ info = idr_find(&minors_idr, MINOR(devno));
+ return info;
}
-static int allocate_afu_minor(struct ocxl_afu *afu)
+static int allocate_minor(struct ocxl_file_info *info)
{
int minor;
mutex_lock(&minors_idr_lock);
- minor = idr_alloc(&minors_idr, afu, 0, OCXL_NUM_MINORS, GFP_KERNEL);
+ minor = idr_alloc(&minors_idr, info, 0, OCXL_NUM_MINORS, GFP_KERNEL);
mutex_unlock(&minors_idr_lock);
return minor;
}
-static void free_afu_minor(struct ocxl_afu *afu)
+static void free_minor(struct ocxl_file_info *info)
{
mutex_lock(&minors_idr_lock);
- idr_remove(&minors_idr, MINOR(afu->dev.devt));
+ idr_remove(&minors_idr, MINOR(info->dev.devt));
mutex_unlock(&minors_idr_lock);
}
static int afu_open(struct inode *inode, struct file *file)
{
- struct ocxl_afu *afu;
+ struct ocxl_file_info *info;
struct ocxl_context *ctx;
int rc;
pr_debug("%s for device %x\n", __func__, inode->i_rdev);
- afu = find_and_get_afu(inode->i_rdev);
- if (!afu)
+ info = find_file_info(inode->i_rdev);
+ if (!info)
return -ENODEV;
ctx = ocxl_context_alloc();
- if (!ctx) {
- rc = -ENOMEM;
- goto put_afu;
- }
+ if (!ctx)
+ return -ENOMEM;
- rc = ocxl_context_init(ctx, afu, inode->i_mapping);
+ rc = ocxl_context_init(ctx, info->afu, inode->i_mapping);
if (rc)
- goto put_afu;
+ return rc;
+
file->private_data = ctx;
- ocxl_afu_put(afu);
return 0;
-
-put_afu:
- ocxl_afu_put(afu);
- return rc;
}
static long afu_ioctl_attach(struct ocxl_context *ctx,
@@ -204,11 +194,16 @@ static long afu_ioctl(struct file *file, unsigned int cmd,
struct ocxl_ioctl_irq_fd irq_fd;
u64 irq_offset;
long rc;
+ bool closed;
pr_debug("%s for context %d, command %s\n", __func__, ctx->pasid,
CMD_STR(cmd));
- if (ctx->status == CLOSED)
+ mutex_lock(&ctx->status_mutex);
+ closed = (ctx->status == CLOSED);
+ mutex_unlock(&ctx->status_mutex);
+
+ if (closed)
return -EIO;
switch (cmd) {
@@ -468,39 +463,102 @@ static const struct file_operations ocxl_afu_fops = {
.release = afu_release,
};
-int ocxl_create_cdev(struct ocxl_afu *afu)
+// Free the info struct
+static void info_release(struct device *dev)
+{
+ struct ocxl_file_info *info = container_of(dev, struct ocxl_file_info, dev);
+
+ free_minor(info);
+ ocxl_afu_put(info->afu);
+ kfree(info);
+}
+
+static int ocxl_file_make_visible(struct ocxl_file_info *info)
{
int rc;
- cdev_init(&afu->cdev, &ocxl_afu_fops);
- rc = cdev_add(&afu->cdev, afu->dev.devt, 1);
+ cdev_init(&info->cdev, &ocxl_afu_fops);
+ rc = cdev_add(&info->cdev, info->dev.devt, 1);
if (rc) {
- dev_err(&afu->dev, "Unable to add afu char device: %d\n", rc);
+ dev_err(&info->dev, "Unable to add afu char device: %d\n", rc);
return rc;
}
+
return 0;
}
-void ocxl_destroy_cdev(struct ocxl_afu *afu)
+static void ocxl_file_make_invisible(struct ocxl_file_info *info)
{
- cdev_del(&afu->cdev);
+ cdev_del(&info->cdev);
}
-int ocxl_register_afu(struct ocxl_afu *afu)
+int ocxl_file_register_afu(struct ocxl_afu *afu)
{
int minor;
+ int rc;
+ struct ocxl_file_info *info;
+ struct ocxl_fn *fn = afu->fn;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (info == NULL)
+ return -ENOMEM;
- minor = allocate_afu_minor(afu);
- if (minor < 0)
+ minor = allocate_minor(info);
+ if (minor < 0) {
+ kfree(info);
return minor;
- afu->dev.devt = MKDEV(MAJOR(ocxl_dev), minor);
- afu->dev.class = ocxl_class;
- return device_register(&afu->dev);
+ }
+
+ info->dev.parent = &fn->dev;
+ info->dev.devt = MKDEV(MAJOR(ocxl_dev), minor);
+ info->dev.class = ocxl_class;
+ info->dev.release = info_release;
+
+ info->afu = afu;
+ ocxl_afu_get(afu);
+
+ rc = dev_set_name(&info->dev, "%s.%s.%hhu",
+ afu->config.name, dev_name(&pci_dev->dev), afu->config.idx);
+ if (rc)
+ goto err_put;
+
+ rc = device_register(&info->dev);
+ if (rc)
+ goto err_put;
+
+ rc = ocxl_sysfs_register_afu(info);
+ if (rc)
+ goto err_unregister;
+
+ rc = ocxl_file_make_visible(info);
+ if (rc)
+ goto err_unregister;
+
+ ocxl_afu_set_private(afu, info);
+
+ return 0;
+
+err_unregister:
+ ocxl_sysfs_unregister_afu(info); // safe to call even if register failed
+ device_unregister(&info->dev);
+err_put:
+ ocxl_afu_put(afu);
+ free_minor(info);
+ kfree(info);
+ return rc;
}
-void ocxl_unregister_afu(struct ocxl_afu *afu)
+void ocxl_file_unregister_afu(struct ocxl_afu *afu)
{
- free_afu_minor(afu);
+ struct ocxl_file_info *info = ocxl_afu_get_private(afu);
+
+ if (!info)
+ return;
+
+ ocxl_file_make_invisible(info);
+ ocxl_sysfs_unregister_afu(info);
+ device_unregister(&info->dev);
}
static char *ocxl_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 81086534dab5..53b6c64a1bf0 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -11,9 +11,6 @@
#define MAX_IRQ_PER_LINK 2000
#define MAX_IRQ_PER_CONTEXT MAX_IRQ_PER_LINK
-#define to_ocxl_function(d) container_of(d, struct ocxl_fn, dev)
-#define to_ocxl_afu(d) container_of(d, struct ocxl_afu, dev)
-
extern struct pci_driver ocxl_pci_driver;
struct ocxl_fn {
@@ -30,11 +27,17 @@ struct ocxl_fn {
void *link;
};
+struct ocxl_file_info {
+ struct ocxl_afu *afu;
+ struct device dev;
+ struct cdev cdev;
+ struct bin_attribute attr_global_mmio;
+};
+
struct ocxl_afu {
+ struct kref kref;
struct ocxl_fn *fn;
struct list_head list;
- struct device dev;
- struct cdev cdev;
struct ocxl_afu_config config;
int pasid_base;
int pasid_count; /* opened contexts */
@@ -48,7 +51,7 @@ struct ocxl_afu {
u64 irq_base_offset;
void __iomem *global_mmio_ptr;
u64 pp_mmio_start;
- struct bin_attribute attr_global_mmio;
+ void *private;
};
enum ocxl_context_status {
@@ -91,13 +94,10 @@ struct ocxl_process_element {
__be32 software_state;
};
-struct ocxl_afu *ocxl_afu_get(struct ocxl_afu *afu);
-void ocxl_afu_put(struct ocxl_afu *afu);
-
int ocxl_create_cdev(struct ocxl_afu *afu);
void ocxl_destroy_cdev(struct ocxl_afu *afu);
-int ocxl_register_afu(struct ocxl_afu *afu);
-void ocxl_unregister_afu(struct ocxl_afu *afu);
+int ocxl_file_register_afu(struct ocxl_afu *afu);
+void ocxl_file_unregister_afu(struct ocxl_afu *afu);
int ocxl_file_init(void);
void ocxl_file_exit(void);
@@ -140,8 +140,8 @@ int ocxl_context_detach(struct ocxl_context *ctx);
void ocxl_context_detach_all(struct ocxl_afu *afu);
void ocxl_context_free(struct ocxl_context *ctx);
-int ocxl_sysfs_add_afu(struct ocxl_afu *afu);
-void ocxl_sysfs_remove_afu(struct ocxl_afu *afu);
+int ocxl_sysfs_register_afu(struct ocxl_file_info *info);
+void ocxl_sysfs_unregister_afu(struct ocxl_file_info *info);
int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset);
int ocxl_afu_irq_free(struct ocxl_context *ctx, u64 irq_offset);
@@ -150,9 +150,4 @@ int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset,
int eventfd);
u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, u64 irq_offset);
-struct ocxl_fn *init_function(struct pci_dev *dev);
-void remove_function(struct ocxl_fn *fn);
-int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx);
-void remove_afu(struct ocxl_afu *afu);
-
#endif /* _OCXL_INTERNAL_H_ */
diff --git a/drivers/misc/ocxl/pci.c b/drivers/misc/ocxl/pci.c
index 4ed7cb1a667f..f2a3ef4b9bdd 100644
--- a/drivers/misc/ocxl/pci.c
+++ b/drivers/misc/ocxl/pci.c
@@ -16,47 +16,45 @@ MODULE_DEVICE_TABLE(pci, ocxl_pci_tbl);
static int ocxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
- int rc, afu_count = 0;
- u8 afu;
+ int rc;
+ struct ocxl_afu *afu, *tmp;
struct ocxl_fn *fn;
+ struct list_head *afu_list;
- if (!radix_enabled()) {
- dev_err(&dev->dev, "Unsupported memory model (hash)\n");
- return -ENODEV;
- }
-
- fn = init_function(dev);
- if (IS_ERR(fn)) {
- dev_err(&dev->dev, "function init failed: %li\n",
- PTR_ERR(fn));
+ fn = ocxl_function_open(dev);
+ if (IS_ERR(fn))
return PTR_ERR(fn);
- }
- for (afu = 0; afu <= fn->config.max_afu_index; afu++) {
- rc = ocxl_config_check_afu_index(dev, &fn->config, afu);
- if (rc > 0) {
- rc = init_afu(dev, fn, afu);
- if (rc) {
- dev_err(&dev->dev,
- "Can't initialize AFU index %d\n", afu);
- continue;
- }
- afu_count++;
+ pci_set_drvdata(dev, fn);
+
+ afu_list = ocxl_function_afu_list(fn);
+
+ list_for_each_entry_safe(afu, tmp, afu_list, list) {
+ // Cleanup handled within ocxl_file_register_afu()
+ rc = ocxl_file_register_afu(afu);
+ if (rc) {
+ dev_err(&dev->dev, "Failed to register AFU '%s' index %d",
+ afu->config.name, afu->config.idx);
}
}
- dev_info(&dev->dev, "%d AFU(s) configured\n", afu_count);
+
return 0;
}
-static void ocxl_remove(struct pci_dev *dev)
+void ocxl_remove(struct pci_dev *dev)
{
- struct ocxl_afu *afu, *tmp;
- struct ocxl_fn *fn = pci_get_drvdata(dev);
+ struct ocxl_fn *fn;
+ struct ocxl_afu *afu;
+ struct list_head *afu_list;
- list_for_each_entry_safe(afu, tmp, &fn->afu_list, list) {
- remove_afu(afu);
+ fn = pci_get_drvdata(dev);
+ afu_list = ocxl_function_afu_list(fn);
+
+ list_for_each_entry(afu, afu_list, list) {
+ ocxl_file_unregister_afu(afu);
}
- remove_function(fn);
+
+ ocxl_function_close(fn);
}
struct pci_driver ocxl_pci_driver = {
diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c
index 0ab1fd1b2682..58f1ba264206 100644
--- a/drivers/misc/ocxl/sysfs.c
+++ b/drivers/misc/ocxl/sysfs.c
@@ -3,11 +3,18 @@
#include <linux/sysfs.h>
#include "ocxl_internal.h"
+static inline struct ocxl_afu *to_afu(struct device *device)
+{
+ struct ocxl_file_info *info = container_of(device, struct ocxl_file_info, dev);
+
+ return info->afu;
+}
+
static ssize_t global_mmio_size_show(struct device *device,
struct device_attribute *attr,
char *buf)
{
- struct ocxl_afu *afu = to_ocxl_afu(device);
+ struct ocxl_afu *afu = to_afu(device);
return scnprintf(buf, PAGE_SIZE, "%d\n",
afu->config.global_mmio_size);
@@ -17,7 +24,7 @@ static ssize_t pp_mmio_size_show(struct device *device,
struct device_attribute *attr,
char *buf)
{
- struct ocxl_afu *afu = to_ocxl_afu(device);
+ struct ocxl_afu *afu = to_afu(device);
return scnprintf(buf, PAGE_SIZE, "%d\n",
afu->config.pp_mmio_stride);
@@ -27,7 +34,7 @@ static ssize_t afu_version_show(struct device *device,
struct device_attribute *attr,
char *buf)
{
- struct ocxl_afu *afu = to_ocxl_afu(device);
+ struct ocxl_afu *afu = to_afu(device);
return scnprintf(buf, PAGE_SIZE, "%hhu:%hhu\n",
afu->config.version_major,
@@ -38,7 +45,7 @@ static ssize_t contexts_show(struct device *device,
struct device_attribute *attr,
char *buf)
{
- struct ocxl_afu *afu = to_ocxl_afu(device);
+ struct ocxl_afu *afu = to_afu(device);
return scnprintf(buf, PAGE_SIZE, "%d/%d\n",
afu->pasid_count, afu->pasid_max);
@@ -55,7 +62,7 @@ static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr, char *buf,
loff_t off, size_t count)
{
- struct ocxl_afu *afu = to_ocxl_afu(kobj_to_dev(kobj));
+ struct ocxl_afu *afu = to_afu(kobj_to_dev(kobj));
if (count == 0 || off < 0 ||
off >= afu->config.global_mmio_size)
@@ -86,7 +93,7 @@ static int global_mmio_mmap(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr,
struct vm_area_struct *vma)
{
- struct ocxl_afu *afu = to_ocxl_afu(kobj_to_dev(kobj));
+ struct ocxl_afu *afu = to_afu(kobj_to_dev(kobj));
if ((vma_pages(vma) + vma->vm_pgoff) >
(afu->config.global_mmio_size >> PAGE_SHIFT))
@@ -99,27 +106,25 @@ static int global_mmio_mmap(struct file *filp, struct kobject *kobj,
return 0;
}
-int ocxl_sysfs_add_afu(struct ocxl_afu *afu)
+int ocxl_sysfs_register_afu(struct ocxl_file_info *info)
{
int i, rc;
for (i = 0; i < ARRAY_SIZE(afu_attrs); i++) {
- rc = device_create_file(&afu->dev, &afu_attrs[i]);
+ rc = device_create_file(&info->dev, &afu_attrs[i]);
if (rc)
goto err;
}
- sysfs_attr_init(&afu->attr_global_mmio.attr);
- afu->attr_global_mmio.attr.name = "global_mmio_area";
- afu->attr_global_mmio.attr.mode = 0600;
- afu->attr_global_mmio.size = afu->config.global_mmio_size;
- afu->attr_global_mmio.read = global_mmio_read;
- afu->attr_global_mmio.mmap = global_mmio_mmap;
- rc = device_create_bin_file(&afu->dev, &afu->attr_global_mmio);
+ sysfs_attr_init(&info->attr_global_mmio.attr);
+ info->attr_global_mmio.attr.name = "global_mmio_area";
+ info->attr_global_mmio.attr.mode = 0600;
+ info->attr_global_mmio.size = info->afu->config.global_mmio_size;
+ info->attr_global_mmio.read = global_mmio_read;
+ info->attr_global_mmio.mmap = global_mmio_mmap;
+ rc = device_create_bin_file(&info->dev, &info->attr_global_mmio);
if (rc) {
- dev_err(&afu->dev,
- "Unable to create global mmio attr for afu: %d\n",
- rc);
+ dev_err(&info->dev, "Unable to create global mmio attr for afu: %d\n", rc);
goto err;
}
@@ -127,15 +132,20 @@ int ocxl_sysfs_add_afu(struct ocxl_afu *afu)
err:
for (i--; i >= 0; i--)
- device_remove_file(&afu->dev, &afu_attrs[i]);
+ device_remove_file(&info->dev, &afu_attrs[i]);
+
return rc;
}
-void ocxl_sysfs_remove_afu(struct ocxl_afu *afu)
+void ocxl_sysfs_unregister_afu(struct ocxl_file_info *info)
{
int i;
+ /*
+ * device_remove_bin_file is safe to call if the file is not added as
+ * the files are removed by name, and early exit if not found
+ */
for (i = 0; i < ARRAY_SIZE(afu_attrs); i++)
- device_remove_file(&afu->dev, &afu_attrs[i]);
- device_remove_bin_file(&afu->dev, &afu->attr_global_mmio);
+ device_remove_file(&info->dev, &afu_attrs[i]);
+ device_remove_bin_file(&info->dev, &info->attr_global_mmio);
}
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index 9530d3be1b30..8bafd748e380 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -16,11 +16,7 @@
#define OCXL_AFU_NAME_SZ (24+1) /* add 1 for NULL termination */
-/*
- * The following 2 structures are a fairly generic way of representing
- * the configuration data for a function and AFU, as read from the
- * configuration space.
- */
+
struct ocxl_afu_config {
u8 idx;
int dvsec_afu_control_pos; /* offset of AFU control DVSEC */
@@ -49,12 +45,108 @@ struct ocxl_fn_config {
s8 max_afu_index;
};
-/*
- * Read the configuration space of a function and fill in a
- * ocxl_fn_config structure with all the function details
+// These are opaque outside the ocxl driver
+struct ocxl_afu;
+struct ocxl_fn;
+
+// Device detection & initialisation
+
+/**
+ * Open an OpenCAPI function on an OpenCAPI device
+ *
+ * @dev: The PCI device that contains the function
+ *
+ * Returns an opaque pointer to the function, or an error pointer (check with IS_ERR)
*/
-int ocxl_config_read_function(struct pci_dev *dev,
- struct ocxl_fn_config *fn);
+struct ocxl_fn *ocxl_function_open(struct pci_dev *dev);
+
+/**
+ * Get the list of AFUs associated with a PCI function device
+ *
+ * Returns a list of struct ocxl_afu *
+ *
+ * @fn: The OpenCAPI function containing the AFUs
+ */
+struct list_head *ocxl_function_afu_list(struct ocxl_fn *fn);
+
+/**
+ * Fetch an AFU instance from an OpenCAPI function
+ *
+ * @fn: The OpenCAPI function to get the AFU from
+ * @afu_idx: The index of the AFU to get
+ *
+ * If successful, the AFU should be released with ocxl_afu_put()
+ *
+ * Returns a pointer to the AFU, or NULL on error
+ */
+struct ocxl_afu *ocxl_function_fetch_afu(struct ocxl_fn *fn, u8 afu_idx);
+
+/**
+ * Take a reference to an AFU
+ *
+ * @afu: The AFU to increment the reference count on
+ */
+void ocxl_afu_get(struct ocxl_afu *afu);
+
+/**
+ * Release a reference to an AFU
+ *
+ * @afu: The AFU to decrement the reference count on
+ */
+void ocxl_afu_put(struct ocxl_afu *afu);
+
+
+/**
+ * Get the configuration information for an OpenCAPI function
+ *
+ * @fn: The OpenCAPI function to get the config for
+ *
+ * Returns the function config, or NULL on error
+ */
+const struct ocxl_fn_config *ocxl_function_config(struct ocxl_fn *fn);
+
+/**
+ * Close an OpenCAPI function
+ *
+ * This will free any AFUs previously retrieved from the function, and
+ * detach and associated contexts. The contexts must by freed by the caller.
+ *
+ * @fn: The OpenCAPI function to close
+ *
+ */
+void ocxl_function_close(struct ocxl_fn *fn);
+
+// AFU Metadata
+
+/**
+ * Get a pointer to the config for an AFU
+ *
+ * @afu: a pointer to the AFU to get the config for
+ *
+ * Returns a pointer to the AFU config
+ */
+struct ocxl_afu_config *ocxl_afu_config(struct ocxl_afu *afu);
+
+/**
+ * Assign opaque hardware specific information to an OpenCAPI AFU.
+ *
+ * @dev: The PCI device associated with the OpenCAPI device
+ * @private: the opaque hardware specific information to assign to the driver
+ */
+void ocxl_afu_set_private(struct ocxl_afu *afu, void *private);
+
+/**
+ * Fetch the hardware specific information associated with an external OpenCAPI
+ * AFU. This may be consumed by an external OpenCAPI driver.
+ *
+ * @afu: The AFU
+ *
+ * Returns the opaque pointer associated with the device, or NULL if not set
+ */
+void *ocxl_afu_get_private(struct ocxl_afu *dev);
+
+
+// Functions left here are for compatibility with the cxlflash driver
/*
* Read the configuration space of a function for the AFU specified by
@@ -141,6 +233,13 @@ int ocxl_config_set_TL(struct pci_dev *dev, int tl_dvsec);
int ocxl_config_terminate_pasid(struct pci_dev *dev,
int afu_control_offset, int pasid);
+/*
+ * Read the configuration space of a function and fill in a
+ * ocxl_fn_config structure with all the function details
+ */
+int ocxl_config_read_function(struct pci_dev *dev,
+ struct ocxl_fn_config *fn);
+
/*
* Set up the opencapi link for the function.
*
--
2.20.1
^ permalink raw reply related
* [PATCH v4 2/7] ocxl: Don't pass pci_dev around
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This data is already available in a struct
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/core.c | 38 +++++++++++++++++++++-----------------
1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/drivers/misc/ocxl/core.c b/drivers/misc/ocxl/core.c
index 1a4411b72d35..2f2fe12eac1e 100644
--- a/drivers/misc/ocxl/core.c
+++ b/drivers/misc/ocxl/core.c
@@ -66,10 +66,11 @@ static int set_afu_device(struct ocxl_afu *afu, const char *location)
return rc;
}
-static int assign_afu_actag(struct ocxl_afu *afu, struct pci_dev *dev)
+static int assign_afu_actag(struct ocxl_afu *afu)
{
struct ocxl_fn *fn = afu->fn;
int actag_count, actag_offset;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
/*
* if there were not enough actags for the function, each afu
@@ -79,16 +80,16 @@ static int assign_afu_actag(struct ocxl_afu *afu, struct pci_dev *dev)
fn->actag_enabled / fn->actag_supported;
actag_offset = ocxl_actag_afu_alloc(fn, actag_count);
if (actag_offset < 0) {
- dev_err(&afu->dev, "Can't allocate %d actags for AFU: %d\n",
+ dev_err(&pci_dev->dev, "Can't allocate %d actags for AFU: %d\n",
actag_count, actag_offset);
return actag_offset;
}
afu->actag_base = fn->actag_base + actag_offset;
afu->actag_enabled = actag_count;
- ocxl_config_set_afu_actag(dev, afu->config.dvsec_afu_control_pos,
+ ocxl_config_set_afu_actag(pci_dev, afu->config.dvsec_afu_control_pos,
afu->actag_base, afu->actag_enabled);
- dev_dbg(&afu->dev, "actag base=%d enabled=%d\n",
+ dev_dbg(&pci_dev->dev, "actag base=%d enabled=%d\n",
afu->actag_base, afu->actag_enabled);
return 0;
}
@@ -103,10 +104,11 @@ static void reclaim_afu_actag(struct ocxl_afu *afu)
ocxl_actag_afu_free(afu->fn, start_offset, size);
}
-static int assign_afu_pasid(struct ocxl_afu *afu, struct pci_dev *dev)
+static int assign_afu_pasid(struct ocxl_afu *afu)
{
struct ocxl_fn *fn = afu->fn;
int pasid_count, pasid_offset;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
/*
* We only support the case where the function configuration
@@ -115,7 +117,7 @@ static int assign_afu_pasid(struct ocxl_afu *afu, struct pci_dev *dev)
pasid_count = 1 << afu->config.pasid_supported_log;
pasid_offset = ocxl_pasid_afu_alloc(fn, pasid_count);
if (pasid_offset < 0) {
- dev_err(&afu->dev, "Can't allocate %d PASIDs for AFU: %d\n",
+ dev_err(&pci_dev->dev, "Can't allocate %d PASIDs for AFU: %d\n",
pasid_count, pasid_offset);
return pasid_offset;
}
@@ -123,10 +125,10 @@ static int assign_afu_pasid(struct ocxl_afu *afu, struct pci_dev *dev)
afu->pasid_count = 0;
afu->pasid_max = pasid_count;
- ocxl_config_set_afu_pasid(dev, afu->config.dvsec_afu_control_pos,
+ ocxl_config_set_afu_pasid(pci_dev, afu->config.dvsec_afu_control_pos,
afu->pasid_base,
afu->config.pasid_supported_log);
- dev_dbg(&afu->dev, "PASID base=%d, enabled=%d\n",
+ dev_dbg(&pci_dev->dev, "PASID base=%d, enabled=%d\n",
afu->pasid_base, pasid_count);
return 0;
}
@@ -172,9 +174,10 @@ static void release_fn_bar(struct ocxl_fn *fn, int bar)
WARN_ON(fn->bar_used[idx] < 0);
}
-static int map_mmio_areas(struct ocxl_afu *afu, struct pci_dev *dev)
+static int map_mmio_areas(struct ocxl_afu *afu)
{
int rc;
+ struct pci_dev *pci_dev = to_pci_dev(afu->fn->dev.parent);
rc = reserve_fn_bar(afu->fn, afu->config.global_mmio_bar);
if (rc)
@@ -187,10 +190,10 @@ static int map_mmio_areas(struct ocxl_afu *afu, struct pci_dev *dev)
}
afu->global_mmio_start =
- pci_resource_start(dev, afu->config.global_mmio_bar) +
+ pci_resource_start(pci_dev, afu->config.global_mmio_bar) +
afu->config.global_mmio_offset;
afu->pp_mmio_start =
- pci_resource_start(dev, afu->config.pp_mmio_bar) +
+ pci_resource_start(pci_dev, afu->config.pp_mmio_bar) +
afu->config.pp_mmio_offset;
afu->global_mmio_ptr = ioremap(afu->global_mmio_start,
@@ -198,7 +201,7 @@ static int map_mmio_areas(struct ocxl_afu *afu, struct pci_dev *dev)
if (!afu->global_mmio_ptr) {
release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
release_fn_bar(afu->fn, afu->config.global_mmio_bar);
- dev_err(&dev->dev, "Error mapping global mmio area\n");
+ dev_err(&pci_dev->dev, "Error mapping global mmio area\n");
return -ENOMEM;
}
@@ -234,17 +237,17 @@ static int configure_afu(struct ocxl_afu *afu, u8 afu_idx, struct pci_dev *dev)
if (rc)
return rc;
- rc = assign_afu_actag(afu, dev);
+ rc = assign_afu_actag(afu);
if (rc)
return rc;
- rc = assign_afu_pasid(afu, dev);
+ rc = assign_afu_pasid(afu);
if (rc) {
reclaim_afu_actag(afu);
return rc;
}
- rc = map_mmio_areas(afu, dev);
+ rc = map_mmio_areas(afu);
if (rc) {
reclaim_afu_pasid(afu);
reclaim_afu_actag(afu);
@@ -331,7 +334,7 @@ void remove_afu(struct ocxl_afu *afu)
device_unregister(&afu->dev);
}
-static struct ocxl_fn *alloc_function(struct pci_dev *dev)
+static struct ocxl_fn *alloc_function(void)
{
struct ocxl_fn *fn;
@@ -342,6 +345,7 @@ static struct ocxl_fn *alloc_function(struct pci_dev *dev)
INIT_LIST_HEAD(&fn->afu_list);
INIT_LIST_HEAD(&fn->pasid_list);
INIT_LIST_HEAD(&fn->actag_list);
+
return fn;
}
@@ -491,7 +495,7 @@ struct ocxl_fn *init_function(struct pci_dev *dev)
struct ocxl_fn *fn;
int rc;
- fn = alloc_function(dev);
+ fn = alloc_function();
if (!fn)
return ERR_PTR(-ENOMEM);
--
2.20.1
^ permalink raw reply related
* [PATCH v4 1/7] ocxl: Split pci.c
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190327053137.15173-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
In preparation for making core code available for external drivers,
move the core code out of pci.c and into core.c
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/Makefile | 1 +
drivers/misc/ocxl/core.c | 517 +++++++++++++++++++++++++++++
drivers/misc/ocxl/ocxl_internal.h | 5 +
drivers/misc/ocxl/pci.c | 519 +-----------------------------
4 files changed, 524 insertions(+), 518 deletions(-)
create mode 100644 drivers/misc/ocxl/core.c
diff --git a/drivers/misc/ocxl/Makefile b/drivers/misc/ocxl/Makefile
index 5229dcda8297..bc4e39bfda7b 100644
--- a/drivers/misc/ocxl/Makefile
+++ b/drivers/misc/ocxl/Makefile
@@ -3,6 +3,7 @@ ccflags-$(CONFIG_PPC_WERROR) += -Werror
ocxl-y += main.o pci.o config.o file.o pasid.o
ocxl-y += link.o context.o afu_irq.o sysfs.o trace.o
+ocxl-y += core.o
obj-$(CONFIG_OCXL) += ocxl.o
# For tracepoints to include our trace.h from tracepoint infrastructure:
diff --git a/drivers/misc/ocxl/core.c b/drivers/misc/ocxl/core.c
new file mode 100644
index 000000000000..1a4411b72d35
--- /dev/null
+++ b/drivers/misc/ocxl/core.c
@@ -0,0 +1,517 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2019 IBM Corp.
+#include <linux/idr.h>
+#include "ocxl_internal.h"
+
+static struct ocxl_fn *ocxl_fn_get(struct ocxl_fn *fn)
+{
+ return (get_device(&fn->dev) == NULL) ? NULL : fn;
+}
+
+static void ocxl_fn_put(struct ocxl_fn *fn)
+{
+ put_device(&fn->dev);
+}
+
+struct ocxl_afu *ocxl_afu_get(struct ocxl_afu *afu)
+{
+ return (get_device(&afu->dev) == NULL) ? NULL : afu;
+}
+
+void ocxl_afu_put(struct ocxl_afu *afu)
+{
+ put_device(&afu->dev);
+}
+
+static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
+{
+ struct ocxl_afu *afu;
+
+ afu = kzalloc(sizeof(struct ocxl_afu), GFP_KERNEL);
+ if (!afu)
+ return NULL;
+
+ mutex_init(&afu->contexts_lock);
+ mutex_init(&afu->afu_control_lock);
+ idr_init(&afu->contexts_idr);
+ afu->fn = fn;
+ ocxl_fn_get(fn);
+ return afu;
+}
+
+static void free_afu(struct ocxl_afu *afu)
+{
+ idr_destroy(&afu->contexts_idr);
+ ocxl_fn_put(afu->fn);
+ kfree(afu);
+}
+
+static void free_afu_dev(struct device *dev)
+{
+ struct ocxl_afu *afu = to_ocxl_afu(dev);
+
+ ocxl_unregister_afu(afu);
+ free_afu(afu);
+}
+
+static int set_afu_device(struct ocxl_afu *afu, const char *location)
+{
+ struct ocxl_fn *fn = afu->fn;
+ int rc;
+
+ afu->dev.parent = &fn->dev;
+ afu->dev.release = free_afu_dev;
+ rc = dev_set_name(&afu->dev, "%s.%s.%hhu", afu->config.name, location,
+ afu->config.idx);
+ return rc;
+}
+
+static int assign_afu_actag(struct ocxl_afu *afu, struct pci_dev *dev)
+{
+ struct ocxl_fn *fn = afu->fn;
+ int actag_count, actag_offset;
+
+ /*
+ * if there were not enough actags for the function, each afu
+ * reduces its count as well
+ */
+ actag_count = afu->config.actag_supported *
+ fn->actag_enabled / fn->actag_supported;
+ actag_offset = ocxl_actag_afu_alloc(fn, actag_count);
+ if (actag_offset < 0) {
+ dev_err(&afu->dev, "Can't allocate %d actags for AFU: %d\n",
+ actag_count, actag_offset);
+ return actag_offset;
+ }
+ afu->actag_base = fn->actag_base + actag_offset;
+ afu->actag_enabled = actag_count;
+
+ ocxl_config_set_afu_actag(dev, afu->config.dvsec_afu_control_pos,
+ afu->actag_base, afu->actag_enabled);
+ dev_dbg(&afu->dev, "actag base=%d enabled=%d\n",
+ afu->actag_base, afu->actag_enabled);
+ return 0;
+}
+
+static void reclaim_afu_actag(struct ocxl_afu *afu)
+{
+ struct ocxl_fn *fn = afu->fn;
+ int start_offset, size;
+
+ start_offset = afu->actag_base - fn->actag_base;
+ size = afu->actag_enabled;
+ ocxl_actag_afu_free(afu->fn, start_offset, size);
+}
+
+static int assign_afu_pasid(struct ocxl_afu *afu, struct pci_dev *dev)
+{
+ struct ocxl_fn *fn = afu->fn;
+ int pasid_count, pasid_offset;
+
+ /*
+ * We only support the case where the function configuration
+ * requested enough PASIDs to cover all AFUs.
+ */
+ pasid_count = 1 << afu->config.pasid_supported_log;
+ pasid_offset = ocxl_pasid_afu_alloc(fn, pasid_count);
+ if (pasid_offset < 0) {
+ dev_err(&afu->dev, "Can't allocate %d PASIDs for AFU: %d\n",
+ pasid_count, pasid_offset);
+ return pasid_offset;
+ }
+ afu->pasid_base = fn->pasid_base + pasid_offset;
+ afu->pasid_count = 0;
+ afu->pasid_max = pasid_count;
+
+ ocxl_config_set_afu_pasid(dev, afu->config.dvsec_afu_control_pos,
+ afu->pasid_base,
+ afu->config.pasid_supported_log);
+ dev_dbg(&afu->dev, "PASID base=%d, enabled=%d\n",
+ afu->pasid_base, pasid_count);
+ return 0;
+}
+
+static void reclaim_afu_pasid(struct ocxl_afu *afu)
+{
+ struct ocxl_fn *fn = afu->fn;
+ int start_offset, size;
+
+ start_offset = afu->pasid_base - fn->pasid_base;
+ size = 1 << afu->config.pasid_supported_log;
+ ocxl_pasid_afu_free(afu->fn, start_offset, size);
+}
+
+static int reserve_fn_bar(struct ocxl_fn *fn, int bar)
+{
+ struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+ int rc, idx;
+
+ if (bar != 0 && bar != 2 && bar != 4)
+ return -EINVAL;
+
+ idx = bar >> 1;
+ if (fn->bar_used[idx]++ == 0) {
+ rc = pci_request_region(dev, bar, "ocxl");
+ if (rc)
+ return rc;
+ }
+ return 0;
+}
+
+static void release_fn_bar(struct ocxl_fn *fn, int bar)
+{
+ struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+ int idx;
+
+ if (bar != 0 && bar != 2 && bar != 4)
+ return;
+
+ idx = bar >> 1;
+ if (--fn->bar_used[idx] == 0)
+ pci_release_region(dev, bar);
+ WARN_ON(fn->bar_used[idx] < 0);
+}
+
+static int map_mmio_areas(struct ocxl_afu *afu, struct pci_dev *dev)
+{
+ int rc;
+
+ rc = reserve_fn_bar(afu->fn, afu->config.global_mmio_bar);
+ if (rc)
+ return rc;
+
+ rc = reserve_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+ if (rc) {
+ release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+ return rc;
+ }
+
+ afu->global_mmio_start =
+ pci_resource_start(dev, afu->config.global_mmio_bar) +
+ afu->config.global_mmio_offset;
+ afu->pp_mmio_start =
+ pci_resource_start(dev, afu->config.pp_mmio_bar) +
+ afu->config.pp_mmio_offset;
+
+ afu->global_mmio_ptr = ioremap(afu->global_mmio_start,
+ afu->config.global_mmio_size);
+ if (!afu->global_mmio_ptr) {
+ release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+ release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+ dev_err(&dev->dev, "Error mapping global mmio area\n");
+ return -ENOMEM;
+ }
+
+ /*
+ * Leave an empty page between the per-process mmio area and
+ * the AFU interrupt mappings
+ */
+ afu->irq_base_offset = afu->config.pp_mmio_stride + PAGE_SIZE;
+ return 0;
+}
+
+static void unmap_mmio_areas(struct ocxl_afu *afu)
+{
+ if (afu->global_mmio_ptr) {
+ iounmap(afu->global_mmio_ptr);
+ afu->global_mmio_ptr = NULL;
+ }
+ afu->global_mmio_start = 0;
+ afu->pp_mmio_start = 0;
+ release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+ release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+}
+
+static int configure_afu(struct ocxl_afu *afu, u8 afu_idx, struct pci_dev *dev)
+{
+ int rc;
+
+ rc = ocxl_config_read_afu(dev, &afu->fn->config, &afu->config, afu_idx);
+ if (rc)
+ return rc;
+
+ rc = set_afu_device(afu, dev_name(&dev->dev));
+ if (rc)
+ return rc;
+
+ rc = assign_afu_actag(afu, dev);
+ if (rc)
+ return rc;
+
+ rc = assign_afu_pasid(afu, dev);
+ if (rc) {
+ reclaim_afu_actag(afu);
+ return rc;
+ }
+
+ rc = map_mmio_areas(afu, dev);
+ if (rc) {
+ reclaim_afu_pasid(afu);
+ reclaim_afu_actag(afu);
+ return rc;
+ }
+ return 0;
+}
+
+static void deconfigure_afu(struct ocxl_afu *afu)
+{
+ unmap_mmio_areas(afu);
+ reclaim_afu_pasid(afu);
+ reclaim_afu_actag(afu);
+}
+
+static int activate_afu(struct pci_dev *dev, struct ocxl_afu *afu)
+{
+ int rc;
+
+ ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 1);
+ /*
+ * Char device creation is the last step, as processes can
+ * call our driver immediately, so all our inits must be finished.
+ */
+ rc = ocxl_create_cdev(afu);
+ if (rc)
+ return rc;
+ return 0;
+}
+
+static void deactivate_afu(struct ocxl_afu *afu)
+{
+ struct pci_dev *dev = to_pci_dev(afu->fn->dev.parent);
+
+ ocxl_destroy_cdev(afu);
+ ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 0);
+}
+
+int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
+{
+ int rc;
+ struct ocxl_afu *afu;
+
+ afu = alloc_afu(fn);
+ if (!afu)
+ return -ENOMEM;
+
+ rc = configure_afu(afu, afu_idx, dev);
+ if (rc) {
+ free_afu(afu);
+ return rc;
+ }
+
+ rc = ocxl_register_afu(afu);
+ if (rc)
+ goto err;
+
+ rc = ocxl_sysfs_add_afu(afu);
+ if (rc)
+ goto err;
+
+ rc = activate_afu(dev, afu);
+ if (rc)
+ goto err_sys;
+
+ list_add_tail(&afu->list, &fn->afu_list);
+ return 0;
+
+err_sys:
+ ocxl_sysfs_remove_afu(afu);
+err:
+ deconfigure_afu(afu);
+ device_unregister(&afu->dev);
+ return rc;
+}
+
+void remove_afu(struct ocxl_afu *afu)
+{
+ list_del(&afu->list);
+ ocxl_context_detach_all(afu);
+ deactivate_afu(afu);
+ ocxl_sysfs_remove_afu(afu);
+ deconfigure_afu(afu);
+ device_unregister(&afu->dev);
+}
+
+static struct ocxl_fn *alloc_function(struct pci_dev *dev)
+{
+ struct ocxl_fn *fn;
+
+ fn = kzalloc(sizeof(struct ocxl_fn), GFP_KERNEL);
+ if (!fn)
+ return NULL;
+
+ INIT_LIST_HEAD(&fn->afu_list);
+ INIT_LIST_HEAD(&fn->pasid_list);
+ INIT_LIST_HEAD(&fn->actag_list);
+ return fn;
+}
+
+static void free_function(struct ocxl_fn *fn)
+{
+ WARN_ON(!list_empty(&fn->afu_list));
+ WARN_ON(!list_empty(&fn->pasid_list));
+ kfree(fn);
+}
+
+static void free_function_dev(struct device *dev)
+{
+ struct ocxl_fn *fn = to_ocxl_function(dev);
+
+ free_function(fn);
+}
+
+static int set_function_device(struct ocxl_fn *fn, struct pci_dev *dev)
+{
+ int rc;
+
+ fn->dev.parent = &dev->dev;
+ fn->dev.release = free_function_dev;
+ rc = dev_set_name(&fn->dev, "ocxlfn.%s", dev_name(&dev->dev));
+ if (rc)
+ return rc;
+ pci_set_drvdata(dev, fn);
+ return 0;
+}
+
+static int assign_function_actag(struct ocxl_fn *fn)
+{
+ struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+ u16 base, enabled, supported;
+ int rc;
+
+ rc = ocxl_config_get_actag_info(dev, &base, &enabled, &supported);
+ if (rc)
+ return rc;
+
+ fn->actag_base = base;
+ fn->actag_enabled = enabled;
+ fn->actag_supported = supported;
+
+ ocxl_config_set_actag(dev, fn->config.dvsec_function_pos,
+ fn->actag_base, fn->actag_enabled);
+ dev_dbg(&fn->dev, "actag range starting at %d, enabled %d\n",
+ fn->actag_base, fn->actag_enabled);
+ return 0;
+}
+
+static int set_function_pasid(struct ocxl_fn *fn)
+{
+ struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+ int rc, desired_count, max_count;
+
+ /* A function may not require any PASID */
+ if (fn->config.max_pasid_log < 0)
+ return 0;
+
+ rc = ocxl_config_get_pasid_info(dev, &max_count);
+ if (rc)
+ return rc;
+
+ desired_count = 1 << fn->config.max_pasid_log;
+
+ if (desired_count > max_count) {
+ dev_err(&fn->dev,
+ "Function requires more PASIDs than is available (%d vs. %d)\n",
+ desired_count, max_count);
+ return -ENOSPC;
+ }
+
+ fn->pasid_base = 0;
+ return 0;
+}
+
+static int configure_function(struct ocxl_fn *fn, struct pci_dev *dev)
+{
+ int rc;
+
+ rc = pci_enable_device(dev);
+ if (rc) {
+ dev_err(&dev->dev, "pci_enable_device failed: %d\n", rc);
+ return rc;
+ }
+
+ /*
+ * Once it has been confirmed to work on our hardware, we
+ * should reset the function, to force the adapter to restart
+ * from scratch.
+ * A function reset would also reset all its AFUs.
+ *
+ * Some hints for implementation:
+ *
+ * - there's not status bit to know when the reset is done. We
+ * should try reading the config space to know when it's
+ * done.
+ * - probably something like:
+ * Reset
+ * wait 100ms
+ * issue config read
+ * allow device up to 1 sec to return success on config
+ * read before declaring it broken
+ *
+ * Some shared logic on the card (CFG, TLX) won't be reset, so
+ * there's no guarantee that it will be enough.
+ */
+ rc = ocxl_config_read_function(dev, &fn->config);
+ if (rc)
+ return rc;
+
+ rc = set_function_device(fn, dev);
+ if (rc)
+ return rc;
+
+ rc = assign_function_actag(fn);
+ if (rc)
+ return rc;
+
+ rc = set_function_pasid(fn);
+ if (rc)
+ return rc;
+
+ rc = ocxl_link_setup(dev, 0, &fn->link);
+ if (rc)
+ return rc;
+
+ rc = ocxl_config_set_TL(dev, fn->config.dvsec_tl_pos);
+ if (rc) {
+ ocxl_link_release(dev, fn->link);
+ return rc;
+ }
+ return 0;
+}
+
+static void deconfigure_function(struct ocxl_fn *fn)
+{
+ struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+
+ ocxl_link_release(dev, fn->link);
+ pci_disable_device(dev);
+}
+
+struct ocxl_fn *init_function(struct pci_dev *dev)
+{
+ struct ocxl_fn *fn;
+ int rc;
+
+ fn = alloc_function(dev);
+ if (!fn)
+ return ERR_PTR(-ENOMEM);
+
+ rc = configure_function(fn, dev);
+ if (rc) {
+ free_function(fn);
+ return ERR_PTR(rc);
+ }
+
+ rc = device_register(&fn->dev);
+ if (rc) {
+ deconfigure_function(fn);
+ put_device(&fn->dev);
+ return ERR_PTR(rc);
+ }
+ return fn;
+}
+
+void remove_function(struct ocxl_fn *fn)
+{
+ deconfigure_function(fn);
+ device_unregister(&fn->dev);
+}
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 06fd98c989c8..81086534dab5 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -150,4 +150,9 @@ int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset,
int eventfd);
u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, u64 irq_offset);
+struct ocxl_fn *init_function(struct pci_dev *dev);
+void remove_function(struct ocxl_fn *fn);
+int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx);
+void remove_afu(struct ocxl_afu *afu);
+
#endif /* _OCXL_INTERNAL_H_ */
diff --git a/drivers/misc/ocxl/pci.c b/drivers/misc/ocxl/pci.c
index 21f425472a82..4ed7cb1a667f 100644
--- a/drivers/misc/ocxl/pci.c
+++ b/drivers/misc/ocxl/pci.c
@@ -1,9 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
-// Copyright 2017 IBM Corp.
+// Copyright 2019 IBM Corp.
#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/idr.h>
-#include <asm/pnv-ocxl.h>
#include "ocxl_internal.h"
/*
@@ -17,520 +14,6 @@ static const struct pci_device_id ocxl_pci_tbl[] = {
};
MODULE_DEVICE_TABLE(pci, ocxl_pci_tbl);
-
-static struct ocxl_fn *ocxl_fn_get(struct ocxl_fn *fn)
-{
- return (get_device(&fn->dev) == NULL) ? NULL : fn;
-}
-
-static void ocxl_fn_put(struct ocxl_fn *fn)
-{
- put_device(&fn->dev);
-}
-
-struct ocxl_afu *ocxl_afu_get(struct ocxl_afu *afu)
-{
- return (get_device(&afu->dev) == NULL) ? NULL : afu;
-}
-
-void ocxl_afu_put(struct ocxl_afu *afu)
-{
- put_device(&afu->dev);
-}
-
-static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
-{
- struct ocxl_afu *afu;
-
- afu = kzalloc(sizeof(struct ocxl_afu), GFP_KERNEL);
- if (!afu)
- return NULL;
-
- mutex_init(&afu->contexts_lock);
- mutex_init(&afu->afu_control_lock);
- idr_init(&afu->contexts_idr);
- afu->fn = fn;
- ocxl_fn_get(fn);
- return afu;
-}
-
-static void free_afu(struct ocxl_afu *afu)
-{
- idr_destroy(&afu->contexts_idr);
- ocxl_fn_put(afu->fn);
- kfree(afu);
-}
-
-static void free_afu_dev(struct device *dev)
-{
- struct ocxl_afu *afu = to_ocxl_afu(dev);
-
- ocxl_unregister_afu(afu);
- free_afu(afu);
-}
-
-static int set_afu_device(struct ocxl_afu *afu, const char *location)
-{
- struct ocxl_fn *fn = afu->fn;
- int rc;
-
- afu->dev.parent = &fn->dev;
- afu->dev.release = free_afu_dev;
- rc = dev_set_name(&afu->dev, "%s.%s.%hhu", afu->config.name, location,
- afu->config.idx);
- return rc;
-}
-
-static int assign_afu_actag(struct ocxl_afu *afu, struct pci_dev *dev)
-{
- struct ocxl_fn *fn = afu->fn;
- int actag_count, actag_offset;
-
- /*
- * if there were not enough actags for the function, each afu
- * reduces its count as well
- */
- actag_count = afu->config.actag_supported *
- fn->actag_enabled / fn->actag_supported;
- actag_offset = ocxl_actag_afu_alloc(fn, actag_count);
- if (actag_offset < 0) {
- dev_err(&afu->dev, "Can't allocate %d actags for AFU: %d\n",
- actag_count, actag_offset);
- return actag_offset;
- }
- afu->actag_base = fn->actag_base + actag_offset;
- afu->actag_enabled = actag_count;
-
- ocxl_config_set_afu_actag(dev, afu->config.dvsec_afu_control_pos,
- afu->actag_base, afu->actag_enabled);
- dev_dbg(&afu->dev, "actag base=%d enabled=%d\n",
- afu->actag_base, afu->actag_enabled);
- return 0;
-}
-
-static void reclaim_afu_actag(struct ocxl_afu *afu)
-{
- struct ocxl_fn *fn = afu->fn;
- int start_offset, size;
-
- start_offset = afu->actag_base - fn->actag_base;
- size = afu->actag_enabled;
- ocxl_actag_afu_free(afu->fn, start_offset, size);
-}
-
-static int assign_afu_pasid(struct ocxl_afu *afu, struct pci_dev *dev)
-{
- struct ocxl_fn *fn = afu->fn;
- int pasid_count, pasid_offset;
-
- /*
- * We only support the case where the function configuration
- * requested enough PASIDs to cover all AFUs.
- */
- pasid_count = 1 << afu->config.pasid_supported_log;
- pasid_offset = ocxl_pasid_afu_alloc(fn, pasid_count);
- if (pasid_offset < 0) {
- dev_err(&afu->dev, "Can't allocate %d PASIDs for AFU: %d\n",
- pasid_count, pasid_offset);
- return pasid_offset;
- }
- afu->pasid_base = fn->pasid_base + pasid_offset;
- afu->pasid_count = 0;
- afu->pasid_max = pasid_count;
-
- ocxl_config_set_afu_pasid(dev, afu->config.dvsec_afu_control_pos,
- afu->pasid_base,
- afu->config.pasid_supported_log);
- dev_dbg(&afu->dev, "PASID base=%d, enabled=%d\n",
- afu->pasid_base, pasid_count);
- return 0;
-}
-
-static void reclaim_afu_pasid(struct ocxl_afu *afu)
-{
- struct ocxl_fn *fn = afu->fn;
- int start_offset, size;
-
- start_offset = afu->pasid_base - fn->pasid_base;
- size = 1 << afu->config.pasid_supported_log;
- ocxl_pasid_afu_free(afu->fn, start_offset, size);
-}
-
-static int reserve_fn_bar(struct ocxl_fn *fn, int bar)
-{
- struct pci_dev *dev = to_pci_dev(fn->dev.parent);
- int rc, idx;
-
- if (bar != 0 && bar != 2 && bar != 4)
- return -EINVAL;
-
- idx = bar >> 1;
- if (fn->bar_used[idx]++ == 0) {
- rc = pci_request_region(dev, bar, "ocxl");
- if (rc)
- return rc;
- }
- return 0;
-}
-
-static void release_fn_bar(struct ocxl_fn *fn, int bar)
-{
- struct pci_dev *dev = to_pci_dev(fn->dev.parent);
- int idx;
-
- if (bar != 0 && bar != 2 && bar != 4)
- return;
-
- idx = bar >> 1;
- if (--fn->bar_used[idx] == 0)
- pci_release_region(dev, bar);
- WARN_ON(fn->bar_used[idx] < 0);
-}
-
-static int map_mmio_areas(struct ocxl_afu *afu, struct pci_dev *dev)
-{
- int rc;
-
- rc = reserve_fn_bar(afu->fn, afu->config.global_mmio_bar);
- if (rc)
- return rc;
-
- rc = reserve_fn_bar(afu->fn, afu->config.pp_mmio_bar);
- if (rc) {
- release_fn_bar(afu->fn, afu->config.global_mmio_bar);
- return rc;
- }
-
- afu->global_mmio_start =
- pci_resource_start(dev, afu->config.global_mmio_bar) +
- afu->config.global_mmio_offset;
- afu->pp_mmio_start =
- pci_resource_start(dev, afu->config.pp_mmio_bar) +
- afu->config.pp_mmio_offset;
-
- afu->global_mmio_ptr = ioremap(afu->global_mmio_start,
- afu->config.global_mmio_size);
- if (!afu->global_mmio_ptr) {
- release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
- release_fn_bar(afu->fn, afu->config.global_mmio_bar);
- dev_err(&dev->dev, "Error mapping global mmio area\n");
- return -ENOMEM;
- }
-
- /*
- * Leave an empty page between the per-process mmio area and
- * the AFU interrupt mappings
- */
- afu->irq_base_offset = afu->config.pp_mmio_stride + PAGE_SIZE;
- return 0;
-}
-
-static void unmap_mmio_areas(struct ocxl_afu *afu)
-{
- if (afu->global_mmio_ptr) {
- iounmap(afu->global_mmio_ptr);
- afu->global_mmio_ptr = NULL;
- }
- afu->global_mmio_start = 0;
- afu->pp_mmio_start = 0;
- release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
- release_fn_bar(afu->fn, afu->config.global_mmio_bar);
-}
-
-static int configure_afu(struct ocxl_afu *afu, u8 afu_idx, struct pci_dev *dev)
-{
- int rc;
-
- rc = ocxl_config_read_afu(dev, &afu->fn->config, &afu->config, afu_idx);
- if (rc)
- return rc;
-
- rc = set_afu_device(afu, dev_name(&dev->dev));
- if (rc)
- return rc;
-
- rc = assign_afu_actag(afu, dev);
- if (rc)
- return rc;
-
- rc = assign_afu_pasid(afu, dev);
- if (rc) {
- reclaim_afu_actag(afu);
- return rc;
- }
-
- rc = map_mmio_areas(afu, dev);
- if (rc) {
- reclaim_afu_pasid(afu);
- reclaim_afu_actag(afu);
- return rc;
- }
- return 0;
-}
-
-static void deconfigure_afu(struct ocxl_afu *afu)
-{
- unmap_mmio_areas(afu);
- reclaim_afu_pasid(afu);
- reclaim_afu_actag(afu);
-}
-
-static int activate_afu(struct pci_dev *dev, struct ocxl_afu *afu)
-{
- int rc;
-
- ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 1);
- /*
- * Char device creation is the last step, as processes can
- * call our driver immediately, so all our inits must be finished.
- */
- rc = ocxl_create_cdev(afu);
- if (rc)
- return rc;
- return 0;
-}
-
-static void deactivate_afu(struct ocxl_afu *afu)
-{
- struct pci_dev *dev = to_pci_dev(afu->fn->dev.parent);
-
- ocxl_destroy_cdev(afu);
- ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 0);
-}
-
-static int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
-{
- int rc;
- struct ocxl_afu *afu;
-
- afu = alloc_afu(fn);
- if (!afu)
- return -ENOMEM;
-
- rc = configure_afu(afu, afu_idx, dev);
- if (rc) {
- free_afu(afu);
- return rc;
- }
-
- rc = ocxl_register_afu(afu);
- if (rc)
- goto err;
-
- rc = ocxl_sysfs_add_afu(afu);
- if (rc)
- goto err;
-
- rc = activate_afu(dev, afu);
- if (rc)
- goto err_sys;
-
- list_add_tail(&afu->list, &fn->afu_list);
- return 0;
-
-err_sys:
- ocxl_sysfs_remove_afu(afu);
-err:
- deconfigure_afu(afu);
- device_unregister(&afu->dev);
- return rc;
-}
-
-static void remove_afu(struct ocxl_afu *afu)
-{
- list_del(&afu->list);
- ocxl_context_detach_all(afu);
- deactivate_afu(afu);
- ocxl_sysfs_remove_afu(afu);
- deconfigure_afu(afu);
- device_unregister(&afu->dev);
-}
-
-static struct ocxl_fn *alloc_function(struct pci_dev *dev)
-{
- struct ocxl_fn *fn;
-
- fn = kzalloc(sizeof(struct ocxl_fn), GFP_KERNEL);
- if (!fn)
- return NULL;
-
- INIT_LIST_HEAD(&fn->afu_list);
- INIT_LIST_HEAD(&fn->pasid_list);
- INIT_LIST_HEAD(&fn->actag_list);
- return fn;
-}
-
-static void free_function(struct ocxl_fn *fn)
-{
- WARN_ON(!list_empty(&fn->afu_list));
- WARN_ON(!list_empty(&fn->pasid_list));
- kfree(fn);
-}
-
-static void free_function_dev(struct device *dev)
-{
- struct ocxl_fn *fn = to_ocxl_function(dev);
-
- free_function(fn);
-}
-
-static int set_function_device(struct ocxl_fn *fn, struct pci_dev *dev)
-{
- int rc;
-
- fn->dev.parent = &dev->dev;
- fn->dev.release = free_function_dev;
- rc = dev_set_name(&fn->dev, "ocxlfn.%s", dev_name(&dev->dev));
- if (rc)
- return rc;
- pci_set_drvdata(dev, fn);
- return 0;
-}
-
-static int assign_function_actag(struct ocxl_fn *fn)
-{
- struct pci_dev *dev = to_pci_dev(fn->dev.parent);
- u16 base, enabled, supported;
- int rc;
-
- rc = ocxl_config_get_actag_info(dev, &base, &enabled, &supported);
- if (rc)
- return rc;
-
- fn->actag_base = base;
- fn->actag_enabled = enabled;
- fn->actag_supported = supported;
-
- ocxl_config_set_actag(dev, fn->config.dvsec_function_pos,
- fn->actag_base, fn->actag_enabled);
- dev_dbg(&fn->dev, "actag range starting at %d, enabled %d\n",
- fn->actag_base, fn->actag_enabled);
- return 0;
-}
-
-static int set_function_pasid(struct ocxl_fn *fn)
-{
- struct pci_dev *dev = to_pci_dev(fn->dev.parent);
- int rc, desired_count, max_count;
-
- /* A function may not require any PASID */
- if (fn->config.max_pasid_log < 0)
- return 0;
-
- rc = ocxl_config_get_pasid_info(dev, &max_count);
- if (rc)
- return rc;
-
- desired_count = 1 << fn->config.max_pasid_log;
-
- if (desired_count > max_count) {
- dev_err(&fn->dev,
- "Function requires more PASIDs than is available (%d vs. %d)\n",
- desired_count, max_count);
- return -ENOSPC;
- }
-
- fn->pasid_base = 0;
- return 0;
-}
-
-static int configure_function(struct ocxl_fn *fn, struct pci_dev *dev)
-{
- int rc;
-
- rc = pci_enable_device(dev);
- if (rc) {
- dev_err(&dev->dev, "pci_enable_device failed: %d\n", rc);
- return rc;
- }
-
- /*
- * Once it has been confirmed to work on our hardware, we
- * should reset the function, to force the adapter to restart
- * from scratch.
- * A function reset would also reset all its AFUs.
- *
- * Some hints for implementation:
- *
- * - there's not status bit to know when the reset is done. We
- * should try reading the config space to know when it's
- * done.
- * - probably something like:
- * Reset
- * wait 100ms
- * issue config read
- * allow device up to 1 sec to return success on config
- * read before declaring it broken
- *
- * Some shared logic on the card (CFG, TLX) won't be reset, so
- * there's no guarantee that it will be enough.
- */
- rc = ocxl_config_read_function(dev, &fn->config);
- if (rc)
- return rc;
-
- rc = set_function_device(fn, dev);
- if (rc)
- return rc;
-
- rc = assign_function_actag(fn);
- if (rc)
- return rc;
-
- rc = set_function_pasid(fn);
- if (rc)
- return rc;
-
- rc = ocxl_link_setup(dev, 0, &fn->link);
- if (rc)
- return rc;
-
- rc = ocxl_config_set_TL(dev, fn->config.dvsec_tl_pos);
- if (rc) {
- ocxl_link_release(dev, fn->link);
- return rc;
- }
- return 0;
-}
-
-static void deconfigure_function(struct ocxl_fn *fn)
-{
- struct pci_dev *dev = to_pci_dev(fn->dev.parent);
-
- ocxl_link_release(dev, fn->link);
- pci_disable_device(dev);
-}
-
-static struct ocxl_fn *init_function(struct pci_dev *dev)
-{
- struct ocxl_fn *fn;
- int rc;
-
- fn = alloc_function(dev);
- if (!fn)
- return ERR_PTR(-ENOMEM);
-
- rc = configure_function(fn, dev);
- if (rc) {
- free_function(fn);
- return ERR_PTR(rc);
- }
-
- rc = device_register(&fn->dev);
- if (rc) {
- deconfigure_function(fn);
- put_device(&fn->dev);
- return ERR_PTR(rc);
- }
- return fn;
-}
-
-static void remove_function(struct ocxl_fn *fn)
-{
- deconfigure_function(fn);
- device_unregister(&fn->dev);
-}
-
static int ocxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
int rc, afu_count = 0;
--
2.20.1
^ permalink raw reply related
* [PATCH v4 0/7] Refactor OCXL driver to allow external drivers to use it
From: Alastair D'Silva @ 2019-03-27 5:31 UTC (permalink / raw)
To: alastair
Cc: Arnd Bergmann, Greg Kroah-Hartman, linux-kernel, Andrew Donnellan,
Frederic Barrat, linuxppc-dev
From: Alastair D'Silva <alastair@d-silva.org>
This series reworks the OpenCAPI driver to split frontend
(driver interactions) from backend (hardware interactions).
This allows external drivers to utilise the core of the
generic OpenCAPI driver to communicate with specific
OpenCAPI hardware.
This series is bisectable.
Changelog:
V4:
- For: 'ocxl: Create a clear delineation between ocxl backend & frontend'
- Reword non-RCU comment to reflect info struct
- Inline returns from err label in afu_open()
- ocxl_file_make_(in)visibile & ocxl_sysfs_(un)register use info
directly, rather than fetching in from the AFU. This, together with
a delayed ocxl_afu_set_private(), make it clearer that
ocxl_file_register() must succeed for cleanup code to be called
- Remove stray ocxl_free_afu() prototype from header
- For: 'ocxl: Allow external drivers to use OpenCAPI contexts'
- Merge ocxl_context_init & ocxl_context_alloc
- Add missing opaque struct ocxl_context
- For: 'ocxl: move event_fd handling to frontend'
- Set missed free_private value in irq struct
- Change goto unlock to fall-through comment
- Clean stray whitespace
- Mention that free_private can be NULL in ocxl_irq_set_handler docs
V3:
- For: 'ocxl: Create a clear delineation between ocxl backend & frontend'
- Integrate Frederick Barrat's suggestions
- Further cleanup on error paths
- Remove release handler for AFU private data
- Make ocxl_file_make_(in)visibile static & call from ocxl_file_(un)register
V2:
- Reorder patches as some required structs that were only available later
- Add dev.release implementation for ocxl_file_info to address warning on
driver unload (ocxl: Create a clear delineation...)
- Set output var irq_id in ocxl_afu_irq_alloc (ocxl: afu_irq only deals...)
- Bump copyright year (ocxl: Provide global MMIO accessors...,
ocxl: Split pci.c)
Alastair D'Silva (7):
ocxl: Split pci.c
ocxl: Don't pass pci_dev around
ocxl: Create a clear delineation between ocxl backend & frontend
ocxl: Allow external drivers to use OpenCAPI contexts
ocxl: afu_irq only deals with IRQ IDs, not offsets
ocxl: move event_fd handling to frontend
ocxl: Provide global MMIO accessors for external drivers
drivers/misc/ocxl/Makefile | 3 +-
drivers/misc/ocxl/afu_irq.c | 102 +++---
drivers/misc/ocxl/context.c | 31 +-
drivers/misc/ocxl/core.c | 574 ++++++++++++++++++++++++++++++
drivers/misc/ocxl/file.c | 177 ++++++---
drivers/misc/ocxl/mmio.c | 234 ++++++++++++
drivers/misc/ocxl/ocxl_internal.h | 39 +-
drivers/misc/ocxl/pci.c | 565 ++---------------------------
drivers/misc/ocxl/sysfs.c | 54 +--
drivers/misc/ocxl/trace.h | 12 +-
include/misc/ocxl.h | 314 +++++++++++++++-
11 files changed, 1390 insertions(+), 715 deletions(-)
create mode 100644 drivers/misc/ocxl/core.c
create mode 100644 drivers/misc/ocxl/mmio.c
--
2.20.1
^ permalink raw reply
* Re: [PATCH v2] arch/powerpc: Rework local_paca to avoid LTO warnings
From: Alastair D'Silva @ 2019-03-27 4:37 UTC (permalink / raw)
To: Nicholas Piggin
Cc: Michal Hocko, linux-kernel, Mike Rapoport, Paul Mackerras,
Mahesh Salgaonkar, Andrew Morton, linuxppc-dev, Naveen N. Rao
In-Reply-To: <1553579424.0r39b9otz6.astroid@bobo.none>
On Tue, 2019-03-26 at 15:58 +1000, Nicholas Piggin wrote:
> Alastair D'Silva's on March 14, 2019 12:31 pm:
> > From: Alastair D'Silva <alastair@d-silva.org>
> >
> > When building an LTO kernel, the existing code generates warnings:
> > ./arch/powerpc/include/asm/paca.h:37:30: warning: register of
> > ‘local_paca’ used for multiple global register variables
> > register struct paca_struct *local_paca asm("r13");
> > ^
> > ./arch/powerpc/include/asm/paca.h:37:30: note: conflicts with
> > ‘local_paca’
>
> Isn't this a bogus warning? It doesn't look like there's a way to
> define it any other way.
There isn't any other way to define it as a global. However, the
warning is legitimate.
The compiler sees that there are multiple global register variables,
all pointing at the same register.
The compiler can only determine this when LTO is used, as otherwise it
only sees the one in the current compilation unit, whicd disappears by
the time the kernel is linked.
>
> > This patch reworks local_paca into an inline getter & setter
> > function,
> > which addresses the warning.
> >
> > Changelog:
> > V2
> > - Address whitespace issues
> > - keep new implementation close to where the old implementation
> > was
> >
> > Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
> > ---
> > arch/powerpc/include/asm/paca.h | 37 +++++++++++++++++++++++++--
> > ------
> > arch/powerpc/kernel/paca.c | 2 +-
> > 2 files changed, 29 insertions(+), 10 deletions(-)
> >
> > diff --git a/arch/powerpc/include/asm/paca.h
> > b/arch/powerpc/include/asm/paca.h
> > index e843bc5d1a0f..2fa0b43357c9 100644
> > --- a/arch/powerpc/include/asm/paca.h
> > +++ b/arch/powerpc/include/asm/paca.h
> > @@ -34,19 +34,38 @@
> > #include <asm/cpuidle.h>
> > #include <asm/atomic.h>
> >
> > -register struct paca_struct *local_paca asm("r13");
> > -
> > #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
> > extern unsigned int debug_smp_processor_id(void); /* from
> > linux/smp.h */
> > -/*
> > - * Add standard checks that preemption cannot occur when using
> > get_paca():
> > - * otherwise the paca_struct it points to may be the wrong one
> > just after.
> > - */
> > -#define get_paca() ((void) debug_smp_processor_id(), local_paca)
> > -#else
> > -#define get_paca() local_paca
> > #endif
> >
> > +static inline struct paca_struct *get_paca_no_preempt_check(void)
> > +{
> > + register struct paca_struct *paca asm("r13");
> > +
> > + return paca;
> > +}
>
> Problem is it now changes the global register variable to a local
> register variable. The compiler would presumably be within its rights
> to "cache" that return value or use another register for it, which
> is not really what we want.
>
>
I've confirmed that at least with GCC 8.2.0, the generated assembler is
similar, but yes, the compiler may be free to take a copy into another
register (although that would be a terrible optimisation), and then
operate on that value.
Subsequent uses would still have to call the function (ie. fetch the
data from r13) regardless, so I believe this scenario is safe.
Can you think of a scenario where this is a problem?
--
Alastair D'Silva
Open Source Developer
Linux Technology Centre, IBM Australia
mob: 0423 762 819
^ permalink raw reply
* Re: linux-next: build failure after merge of the sound-asoc tree
From: Michael Ellerman @ 2019-03-27 4:29 UTC (permalink / raw)
To: Mark Brown, Stephen Rothwell
Cc: Liam Girdwood, Annaliese McDermond, Linux Kernel Mailing List,
linuxppc-dev, Linux Next Mailing List, Paul Mackerras
In-Reply-To: <20190326131550.GB10898@sirena.org.uk>
Mark Brown <broonie@kernel.org> writes:
> On Tue, Mar 26, 2019 at 01:33:49PM +1100, Stephen Rothwell wrote:
>
>> After merging the sound-asoc tree, today's linux-next build (powerpc
>> allyesconfig) failed like this:
>
>> sound/soc/codecs/tlv320aic32x4-clk.c: In function 'clk_aic32x4_pll_prepare':
>> include/linux/kernel.h:979:32: error: dereferencing pointer to incomplete type 'struct clk_hw'
>> BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \
>> ^~~~~~
>
> Hrm, seems PowerPC is still not using the common clock API - is there
> any plan for that? There are some ASoC PowerPC uses so it's going to be
> a bit of an issue as we expand our use of the clock API.
I don't know anything about the common clock API. What would it involve
for powerpc to use it?
cheers
^ permalink raw reply
* [PATCH] powerpc/64: Fix booting large kernels with STRICT_KERNEL_RWX
From: Russell Currey @ 2019-03-27 3:35 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Russell Currey
With STRICT_KERNEL_RWX enabled anything marked __init is placed at a 16M
boundary. This is necessary so that it can be repurposed later with
different permissions. However, in kernels with text larger than 16M,
this pushes early_setup past 32M, incapable of being reached by the
branch instruction.
Fix this by setting the CTR and branching there instead.
Fixes: 1e0fc9d1eb2b ("powerpc/Kconfig: Enable STRICT_KERNEL_RWX for some configs")
Signed-off-by: Russell Currey <ruscur@russell.cc>
---
arch/powerpc/kernel/head_64.S | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 3fad8d499767..c2b53febadd9 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -968,7 +968,9 @@ start_here_multiplatform:
/* Restore parameters passed from prom_init/kexec */
mr r3,r31
- bl early_setup /* also sets r13 and SPRG_PACA */
+ LOAD_REG_ADDR(r12, early_setup)
+ mtctr r12
+ bctrl /* also sets r13 and SPRG_PACA */
LOAD_REG_ADDR(r3, start_here_common)
ld r4,PACAKMSR(r13)
--
2.21.0
^ permalink raw reply related
* Re: [PATCH] powerpc: vmlinux.lds: Drop Binutils 2.18 workarounds
From: Segher Boessenkool @ 2019-03-26 22:59 UTC (permalink / raw)
To: Christophe Leroy; +Cc: linuxppc-dev, Joel Stanley
In-Reply-To: <20190326222941.GW3969@gate.crashing.org>
On Tue, Mar 26, 2019 at 05:29:43PM -0500, Segher Boessenkool wrote:
> On Tue, Mar 26, 2019 at 03:12:31PM -0500, Segher Boessenkool wrote:
> > On Tue, Mar 26, 2019 at 08:28:58PM +0100, Christophe Leroy wrote:
> > >
> > >
> > > Le 26/03/2019 à 19:19, Segher Boessenkool a écrit :
> > > >On Tue, Mar 26, 2019 at 07:55:33AM +0000, Christophe Leroy wrote:
> > > >> STACK off 0x00000000 vaddr 0x00000000 paddr 0x00000000 align 2**4
> > > >> filesz 0x00000000 memsz 0x00000000 flags rwx
> > > >
> > > >You need to prevent this one somehow. What object file forces this?
> > >
> > > mpc885_ads_defconfig
> >
> > No, which object file, ".o file". Not defconfig :-)
>
> I tried to reproduce this. It does not fail with a ppc6xx_defconfig
> build, and mpc885_ads_defconfig fails with
>
> INFO: Uncompressed kernel (size 0x435178) overlaps the address of the wrapper(0x400000)
> INFO: Fixing the link_address of wrapper to (0x500000)
> ln: failed to access 'arch/powerpc/boot/cuImage.mpc885ads': No such file or directory
(Fixed this by getting a working mkimage)
> What is your GCC?
That question remains -- all my powerpc kernel builds work just fine with
that patch applied (recent GCC, recent binutils).
Segher
^ permalink raw reply
* Re: [PATCH] powerpc: vmlinux.lds: Drop Binutils 2.18 workarounds
From: Segher Boessenkool @ 2019-03-26 22:29 UTC (permalink / raw)
To: Christophe Leroy; +Cc: linuxppc-dev, Joel Stanley
In-Reply-To: <20190326201231.GV3969@gate.crashing.org>
On Tue, Mar 26, 2019 at 03:12:31PM -0500, Segher Boessenkool wrote:
> On Tue, Mar 26, 2019 at 08:28:58PM +0100, Christophe Leroy wrote:
> >
> >
> > Le 26/03/2019 à 19:19, Segher Boessenkool a écrit :
> > >On Tue, Mar 26, 2019 at 07:55:33AM +0000, Christophe Leroy wrote:
> > >> STACK off 0x00000000 vaddr 0x00000000 paddr 0x00000000 align 2**4
> > >> filesz 0x00000000 memsz 0x00000000 flags rwx
> > >
> > >You need to prevent this one somehow. What object file forces this?
> >
> > mpc885_ads_defconfig
>
> No, which object file, ".o file". Not defconfig :-)
I tried to reproduce this. It does not fail with a ppc6xx_defconfig
build, and mpc885_ads_defconfig fails with
INFO: Uncompressed kernel (size 0x435178) overlaps the address of the wrapper(0x400000)
INFO: Fixing the link_address of wrapper to (0x500000)
ln: failed to access 'arch/powerpc/boot/cuImage.mpc885ads': No such file or directory
What is your GCC?
Segher
^ permalink raw reply
* Re: [RFC PATCH v2 10/14] kernel/watchdog: Add a function to obtain the watchdog_allowed_mask
From: Thomas Gleixner @ 2019-03-26 21:22 UTC (permalink / raw)
To: Ricardo Neri
Cc: Rafael J. Wysocki, Peter Zijlstra, Alexei Starovoitov,
Kai-Heng Feng, Paul Mackerras, H. Peter Anvin, sparclinux,
Ingo Molnar, Christoffer Dall, Davidlohr Bueso, Ashok Raj, x86,
David Rientjes, Andi Kleen, Waiman Long, Borislav Petkov,
Don Zickus, Ravi V. Shankar, Konrad Rzeszutek Wilk, Marc Zyngier,
Frederic Weisbecker, Nicholas Piggin, Ricardo Neri,
Byungchul Park, Mathieu Desnoyers, Josh Poimboeuf,
Paul E. McKenney, Tony Luck, Babu Moger, Randy Dunlap,
linux-kernel, Luis R. Rodriguez, Masami Hiramatsu,
Philippe Ombredanne, Colin Ian King, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <1551283518-18922-11-git-send-email-ricardo.neri-calderon@linux.intel.com>
On Wed, 27 Feb 2019, Ricardo Neri wrote:
>
> -struct cpumask watchdog_allowed_mask __read_mostly;
> +static struct cpumask watchdog_allowed_mask __read_mostly;
That hunk is correct.
> struct cpumask watchdog_cpumask __read_mostly;
> unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
> @@ -92,6 +92,11 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str)
> }
> __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
> # endif /* CONFIG_SMP */
> +
> +struct cpumask *watchdog_get_allowed_cpumask(void)
> +{
> + return &watchdog_allowed_mask;
> +}
That part is pointless as I showed you in the other reply. You don't need
that mask in your code at all.
Thanks,
tglx
^ permalink raw reply
* Re: [RFC PATCH v2 09/14] watchdog/hardlockup: Make arch_touch_nmi_watchdog() to hpet-based implementation
From: Thomas Gleixner @ 2019-03-26 21:20 UTC (permalink / raw)
To: Ricardo Neri
Cc: Rafael J. Wysocki, Peter Zijlstra, Alexei Starovoitov,
Kai-Heng Feng, Paul Mackerras, H. Peter Anvin, sparclinux,
Paul E. McKenney, Ingo Molnar, Christoffer Dall, Davidlohr Bueso,
Ashok Raj, x86, David Rientjes, Andi Kleen, Waiman Long,
Borislav Petkov, Don Zickus, Ravi V. Shankar,
Konrad Rzeszutek Wilk, Marc Zyngier, Frederic Weisbecker,
Nicholas Piggin, Ricardo Neri, Byungchul Park, Mathieu Desnoyers,
Josh Poimboeuf, Tony Luck, Babu Moger, Randy Dunlap, linux-kernel,
Luis R. Rodriguez, Masami Hiramatsu, Philippe Ombredanne,
Colin Ian King, Andrew Morton, linuxppc-dev, David S. Miller
In-Reply-To: <20190301011713.GA8058@ranerica-svr.sc.intel.com>
On Thu, 28 Feb 2019, Ricardo Neri wrote:
> > >
> > > -#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
> > > +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) || \
> > > + defined(CONFIG_X86_HARDLOCKUP_DETECTOR_HPET)
> >
> > Why not instead make CONFIG_X86_HARDLOCKUP_DETECTOR_HPET select
> > CONFIG_HARDLOCKUP_DETECTOR_PERF? Keep the arch-specific details
> > in the arch-specific files and all that.
>
> Thanks for your feedback, Paul! The HPET implementation does not use
> perf. Thus, in my opinion is not correct for the HPET HLD to select
> the perf implementation. Patch 8 of this series splits the perf-specific
> code and the generic hardlockup detector code. Does this make sense?
That's what intermediate config symbols are for.
config HARDLOCKUP_DETECTOR_CORE
bool
And make both PERF and HPET select it.
Thanks,
tglx
^ permalink raw reply
* Re: [RFC PATCH v2 08/14] watchdog/hardlockup: Decouple the hardlockup detector from perf
From: Thomas Gleixner @ 2019-03-26 21:18 UTC (permalink / raw)
To: Ricardo Neri
Cc: Peter Zijlstra, Ricardo Neri, Paul Mackerras, H. Peter Anvin,
sparclinux, Ingo Molnar, Ashok Raj, x86, Andi Kleen,
Borislav Petkov, Don Zickus, Ravi V. Shankar, Frederic Weisbecker,
Nicholas Piggin, Mathieu Desnoyers, Tony Luck, Babu Moger,
linux-kernel, Luis R. Rodriguez, Masami Hiramatsu,
Philippe Ombredanne, Colin Ian King, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <1551283518-18922-9-git-send-email-ricardo.neri-calderon@linux.intel.com>
On Wed, 27 Feb 2019, Ricardo Neri wrote:
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Detect hard lockups on a system
> + *
> + * Copyright (C) Intel Corporation 2019
> + *
> + * Note: All of this code comes from the original perf-specific hardlockup
> + * detector.
And because you copied it from there without modification this becomes
automatically Copyrighted by Intel?
May I recommend that you talk to your legal departement about this.
Aside of that there is really no value in creating yet another file. The
code in question can simply wrapped into a large #ifdef PERF in the old
file.
Thanks,
tglx
^ permalink raw reply
* Re: [PATCH RFC v4 20/21] PCI: pciehp: Add support for the movable BARs feature
From: Bjorn Helgaas @ 2019-03-26 21:11 UTC (permalink / raw)
To: Sergey Miroshnichenko; +Cc: linux-pci, linuxppc-dev, linux
In-Reply-To: <20190311133122.11417-21-s.miroshnichenko@yadro.com>
On Mon, Mar 11, 2019 at 04:31:21PM +0300, Sergey Miroshnichenko wrote:
> With movable BARs, adding a hotplugged device may affect all the PCIe
> domain starting from the root, so use a pci_rescan_bus() function which
> handles the rearrangement of existing BARs and bridge windows.
>
> Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
> ---
> drivers/pci/hotplug/pciehp_pci.c | 14 +++++++++-----
> 1 file changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
> index b9c1396db6fe..7c0871db5bae 100644
> --- a/drivers/pci/hotplug/pciehp_pci.c
> +++ b/drivers/pci/hotplug/pciehp_pci.c
> @@ -56,12 +56,16 @@ int pciehp_configure_device(struct controller *ctrl)
> goto out;
> }
>
> - for_each_pci_bridge(dev, parent)
> - pci_hp_add_bridge(dev);
> + if (pci_movable_bars_enabled()) {
> + pci_rescan_bus(parent);
> + } else {
> + for_each_pci_bridge(dev, parent)
> + pci_hp_add_bridge(dev);
>
> - pci_assign_unassigned_bridge_resources(bridge);
> - pcie_bus_configure_settings(parent);
> - pci_bus_add_devices(parent);
> + pci_assign_unassigned_bridge_resources(bridge);
> + pcie_bus_configure_settings(parent);
> + pci_bus_add_devices(parent);
> + }
The addition of a second path at this level, i.e., different paths
depending on whether movable BARs are enabled, seems a little
problematic because it's hard to determine whether they're equivalent
except for the movable BAR aspect. For example, you don't call
pci_hp_add_bridge() when movable BARs are enabled, and I can't tell
whether that's intentional or whether it's a problem.
This looks like the sort of change that should be made in other
hotplug paths, e.g., enable_slot() for acpiphp,
pcibios_finish_adding_to_bus() for powerpc (maybe? I can't really
tell), cpci_configure_slot() shpchp_configure_device()?
If we have or could invent some top-level interface that all these
places could use, and somewhere inside that we could do the movable
BAR magic, I think that would make it more maintainable.
> out:
> pci_unlock_rescan_remove();
> --
> 2.20.1
>
^ permalink raw reply
* Re: [PATCH] powerpc: vmlinux.lds: Drop Binutils 2.18 workarounds
From: Segher Boessenkool @ 2019-03-26 20:12 UTC (permalink / raw)
To: Christophe Leroy; +Cc: linuxppc-dev, Joel Stanley
In-Reply-To: <5f4aa4b2-1c44-70b9-c383-5d40aecd695c@c-s.fr>
On Tue, Mar 26, 2019 at 08:28:58PM +0100, Christophe Leroy wrote:
>
>
> Le 26/03/2019 à 19:19, Segher Boessenkool a écrit :
> >On Tue, Mar 26, 2019 at 07:55:33AM +0000, Christophe Leroy wrote:
> >> STACK off 0x00000000 vaddr 0x00000000 paddr 0x00000000 align 2**4
> >> filesz 0x00000000 memsz 0x00000000 flags rwx
> >
> >You need to prevent this one somehow. What object file forces this?
>
> mpc885_ads_defconfig
No, which object file, ".o file". Not defconfig :-)
Segher
^ permalink raw reply
* Re: [PATCH RFC v4 17/21] PCI: Calculate boundaries for bridge windows
From: Bjorn Helgaas @ 2019-03-26 21:01 UTC (permalink / raw)
To: Sergey Miroshnichenko; +Cc: linux-pci, linuxppc-dev, linux
In-Reply-To: <20190311133122.11417-18-s.miroshnichenko@yadro.com>
On Mon, Mar 11, 2019 at 04:31:18PM +0300, Sergey Miroshnichenko wrote:
> If a bridge window contains fixed areas (there are PCIe devices with
> immovable BARs located on this bus),
I think what you mean by "immovable BARs" is "drivers that don't
support moving BARs". I want to keep the concept of legacy and EA
resources separate because those are immovable in principle, but
drivers can always be improved.
> this window must be allocated
> within the bound memory area, limited by windows size and by address
> range of fixed resources, calculated as follows:
>
> | <-- bus's fixed_range_hard --> |
> | <-- fixed_range_hard.end - window size --> |
> | <-- fixed_range_hard.start + window size --> |
> | <-- bus's fixed_range_soft --> |
>
> Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
> ---
> drivers/pci/setup-bus.c | 56 +++++++++++++++++++++++++++++++++++++++++
> include/linux/pci.h | 4 ++-
> 2 files changed, 59 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
> index a1fd7f3c5ea8..f4737339d5ec 100644
> --- a/drivers/pci/setup-bus.c
> +++ b/drivers/pci/setup-bus.c
> @@ -1809,6 +1809,61 @@ static enum enable_type pci_realloc_detect(struct pci_bus *bus,
> }
> #endif
>
> +static void pci_bus_update_fixed_range_soft(struct pci_bus *bus)
> +{
> + struct pci_dev *dev;
> + struct pci_bus *parent = bus->parent;
> + int idx;
> +
> + list_for_each_entry(dev, &bus->devices, bus_list)
> + if (dev->subordinate)
> + pci_bus_update_fixed_range_soft(dev->subordinate);
> +
> + if (!parent || !bus->self)
> + return;
> +
> + for (idx = 0; idx < ARRAY_SIZE(bus->fixed_range_hard); ++idx) {
> + struct resource *r;
> + resource_size_t soft_start, soft_end;
> + resource_size_t hard_start = bus->fixed_range_hard[idx].start;
> + resource_size_t hard_end = bus->fixed_range_hard[idx].end;
> +
> + if (hard_start > hard_end)
> + continue;
> +
> + r = bus->resource[idx];
> +
> + soft_start = hard_end - resource_size(r) + 1;
> + soft_end = hard_start + resource_size(r) - 1;
> +
> + if (soft_start > hard_start)
> + soft_start = hard_start;
> +
> + if (soft_end < hard_end)
> + soft_end = hard_end;
> +
> + list_for_each_entry(dev, &parent->devices, bus_list) {
> + struct pci_bus *sibling = dev->subordinate;
> + resource_size_t s_start, s_end;
> +
> + if (!sibling || sibling == bus)
> + continue;
> +
> + s_start = sibling->fixed_range_hard[idx].start;
> + s_end = sibling->fixed_range_hard[idx].end;
> +
> + if (s_start > s_end)
> + continue;
> +
> + if (s_end < hard_start && s_end > soft_start)
> + soft_start = s_end;
> + }
> +
> + bus->fixed_range_soft[idx].start = soft_start;
> + bus->fixed_range_soft[idx].end = soft_end;
> + }
> +}
> +
> /*
> * first try will not touch pci bridge res
> * second and later try will clear small leaf bridge res
> @@ -1847,6 +1902,7 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
> /* Depth first, calculate sizes and alignments of all
> subordinate buses. */
> __pci_bus_size_bridges(bus, add_list);
> + pci_bus_update_fixed_range_soft(bus);
>
> /* Depth last, allocate resources and update the hardware. */
> __pci_bus_assign_resources(bus, add_list, &fail_head);
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 7a4d62d84bc1..75a56db73ad4 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -574,9 +574,11 @@ struct pci_bus {
>
> /*
> * If there are fixed resources in the bridge window, the hard range
> - * contains the lowest and the highest addresses of them.
> + * contains the lowest and the highest addresses of them, and this
> + * bridge window must reside within the soft range.
> */
> struct resource fixed_range_hard[PCI_BRIDGE_RESOURCE_NUM];
> + struct resource fixed_range_soft[PCI_BRIDGE_RESOURCE_NUM];
>
> struct pci_ops *ops; /* Configuration access functions */
> struct msi_controller *msi; /* MSI controller */
> --
> 2.20.1
>
^ permalink raw reply
* Re: [PATCH RFC v4 15/21] PCI: Allow the failed resources to be reassigned later
From: Bjorn Helgaas @ 2019-03-26 20:58 UTC (permalink / raw)
To: Sergey Miroshnichenko; +Cc: linux-pci, linuxppc-dev, linux
In-Reply-To: <20190311133122.11417-16-s.miroshnichenko@yadro.com>
On Mon, Mar 11, 2019 at 04:31:16PM +0300, Sergey Miroshnichenko wrote:
> Don't lose the size of the requested EP's BAR if it can't be fit
> in a current trial, so this can be retried.
s/EP/device/, since this applies equally to conventional PCI.
> But a failed bridge window must be dropped and recalculated in the
> next trial.
>
> Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
> ---
> drivers/pci/setup-bus.c | 3 ++-
> drivers/pci/setup-res.c | 12 ++++++++++++
> 2 files changed, 14 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
> index f9d605cd1725..c1559a4a8564 100644
> --- a/drivers/pci/setup-bus.c
> +++ b/drivers/pci/setup-bus.c
> @@ -309,7 +309,8 @@ static void assign_requested_resources_sorted(struct list_head *head,
> 0 /* don't care */,
> 0 /* don't care */);
> }
> - reset_resource(res);
> + if (!pci_movable_bars_enabled())
> + reset_resource(res);
> }
> }
> }
> diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
> index d8ca40a97693..732d18f60f1b 100644
> --- a/drivers/pci/setup-res.c
> +++ b/drivers/pci/setup-res.c
> @@ -298,6 +298,18 @@ static int _pci_assign_resource(struct pci_dev *dev, int resno,
>
> bus = dev->bus;
> while ((ret = __pci_assign_resource(bus, dev, resno, size, min_align))) {
> + if (pci_movable_bars_enabled()) {
> + if (resno >= PCI_BRIDGE_RESOURCES &&
> + resno <= PCI_BRIDGE_RESOURCE_END) {
> + struct resource *res = dev->resource + resno;
> +
> + res->start = 0;
> + res->end = 0;
> + res->flags = 0;
> + }
> + break;
> + }
> +
> if (!bus->parent || !bus->self->transparent)
> break;
> bus = bus->parent;
> --
> 2.20.1
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox