* Re: [PATCH] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: Aneesh Kumar K.V @ 2014-02-28 9:04 UTC (permalink / raw)
To: liu ping fan
Cc: Peter Zijlstra, linux-mm, Paul Mackerras, Andrew Morton,
linuxppc-dev
In-Reply-To: <CAJnKYQkVziWMmCL=rTakSA4955VMvFnaFtFdmexQAKUfTuVv_Q@mail.gmail.com>
liu ping fan <qemulist@gmail.com> writes:
> On Fri, Feb 28, 2014 at 12:47 PM, Aneesh Kumar K.V
> <aneesh.kumar@linux.vnet.ibm.com> wrote:
>> Andrew Morton <akpm@linux-foundation.org> writes:
>>
> Thanks for sending V2. Since the ppc machine env is changed by
> others, I am blocking on setting up the env for re-test this patch.
> And not send out it quickly.
I sent an updated v3 also taking care of xchg
http://article.gmane.org/gmane.linux.kernel/1657613
-aneesh
^ permalink raw reply
* [PATCH V3] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: Aneesh Kumar K.V @ 2014-02-28 9:02 UTC (permalink / raw)
To: benh, akpm, Peter Zijlstra
Cc: linux-mm, Liu Ping Fan, linuxppc-dev, linux-kernel,
Aneesh Kumar K.V
From: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
When doing some numa tests on powerpc, I triggered an oops bug. I find
it is caused by using page->_last_cpupid. It should be initialized as
"-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
And finally cause an oops bug in task_numa_group(), since the online cpu is
less than possible cpu. This happen with CONFIG_SPARSE_VMEMMAP disabled
Call trace:
[ 55.978091] SMP NR_CPUS=64 NUMA PowerNV
[ 55.978118] Modules linked in:
[ 55.978145] CPU: 24 PID: 804 Comm: systemd-udevd Not tainted3.13.0-rc1+ #32
[ 55.978183] task: c000001e2746aa80 ti: c000001e32c50000 task.ti:c000001e32c50000
[ 55.978219] NIP: c0000000000f5ad0 LR: c0000000000f5ac8 CTR:c000000000913cf0
[ 55.978256] REGS: c000001e32c53510 TRAP: 0300 Not tainted(3.13.0-rc1+)
[ 55.978286] MSR: 9000000000009032 <SF,HV,EE,ME,IR,DR,RI> CR:28024424 XER: 20000000
[ 55.978380] CFAR: c000000000009324 DAR: 7265717569726857 DSISR:40000000 SOFTE: 1
GPR00: c0000000000f5ac8 c000001e32c53790 c000000001f343380000000000000021
GPR04: 0000000000000000 0000000000000031 c000000001f743380000ffffffffffff
GPR08: 0000000000000001 7265717569726573 00000000000000000000000000000000
GPR12: 0000000028024422 c00000000ffdd800 00000000296b2e640000000000000020
GPR16: 0000000000000002 0000000000000003 c000001e2f8e4658c000001e25c1c1d8
GPR20: c000001e2f8e4000 c000000001f7a858 00000000000006580000000040000392
GPR24: 00000000000000a8 c000001e33c1a400 00000000000001d8c000001e25c1c000
GPR28: c000001e33c37ff0 0007837840000392 000000000000003fc000001e32c53790
[ 55.978903] NIP [c0000000000f5ad0] .task_numa_fault+0x1470/0x2370
[ 55.978934] LR [c0000000000f5ac8] .task_numa_fault+0x1468/0x2370
[ 55.978964] Call Trace:
[ 55.978978] [c000001e32c53790] [c0000000000f5ac8].task_numa_fault+0x1468/0x2370 (unreliable)
[ 55.979036] [c000001e32c539e0] [c00000000020a820].do_numa_page+0x480/0x4a0
[ 55.979072] [c000001e32c53b10] [c00000000020bfec].handle_mm_fault+0x4ec/0xc90
[ 55.979123] [c000001e32c53c00] [c000000000e88c98].do_page_fault+0x3a8/0x890
[ 55.979161] [c000001e32c53e30] [c000000000009568]handle_page_fault+0x10/0x30
[ 55.979197] Instruction dump:
[ 55.979216] 3c82fefb 3884b138 48d9cff1 60000000 48000574 3c62fefb3863af78 3c82fefb
[ 55.979277] 3884b138 48d9cfd5 60000000 e93f0100 <812902e4> 7d2907b45529063e 7d2a07b4
[ 55.979354] ---[ end trace 15f2510da5ae07cf ]---
Signed-off-by: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
Changes from V2:
* Also updated cpupid_xchg_last to use LAST_CPUPID_MASK. We use the
that function with value -1
* Update Author information after taking to Liu
include/linux/mm.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46eade6a..86245839c9fa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -757,7 +757,7 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
{
- return xchg(&page->_last_cpupid, cpupid);
+ return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
}
static inline int page_cpupid_last(struct page *page)
@@ -766,7 +766,7 @@ static inline int page_cpupid_last(struct page *page)
}
static inline void page_cpupid_reset_last(struct page *page)
{
- page->_last_cpupid = -1;
+ page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int page_cpupid_last(struct page *page)
--
1.8.3.2
^ permalink raw reply related
* [PATCH] Corenet: Add QE platform support for Corenet
From: Zhao Qiang @ 2014-02-28 8:48 UTC (permalink / raw)
To: linuxppc-dev, B07421; +Cc: Zhao Qiang, R63061
There is QE on platform T104x, add support.
Call funcs qe_ic_init and qe_init if CONFIG_QUICC_ENGINE is defined.
Signed-off-by: Zhao Qiang <B45475@freescale.com>
---
arch/powerpc/platforms/85xx/corenet_generic.c | 32 +++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index fbd871e..f8c8e0c 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -26,6 +26,8 @@
#include <asm/udbg.h>
#include <asm/mpic.h>
#include <asm/ehv_pic.h>
+#include <asm/qe.h>
+#include <asm/qe_ic.h>
#include <linux/of_platform.h>
#include <sysdev/fsl_soc.h>
@@ -38,6 +40,10 @@ void __init corenet_gen_pic_init(void)
unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
MPIC_NO_RESET;
+#ifdef CONFIG_QUICC_ENGINE
+ struct device_node *np;
+#endif
+
if (ppc_md.get_irq == mpic_get_coreint_irq)
flags |= MPIC_ENABLE_COREINT;
@@ -45,6 +51,16 @@ void __init corenet_gen_pic_init(void)
BUG_ON(mpic == NULL);
mpic_init(mpic);
+
+#ifdef CONFIG_QUICC_ENGINE
+ np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic");
+ if (np) {
+ qe_ic_init(np, 0, qe_ic_cascade_low_mpic,
+ qe_ic_cascade_high_mpic);
+ of_node_put(np);
+ }
+#endif
+
}
/*
@@ -52,11 +68,24 @@ void __init corenet_gen_pic_init(void)
*/
void __init corenet_gen_setup_arch(void)
{
+#ifdef CONFIG_QUICC_ENGINE
+ struct device_node *np;
+#endif
mpc85xx_smp_init();
swiotlb_detect_4g();
pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
+
+#ifdef CONFIG_QUICC_ENGINE
+ np = of_find_compatible_node(NULL, NULL, "fsl,qe");
+ if (!np) {
+ pr_err("%s: Could not find Quicc Engine node\n", __func__);
+ return;
+ }
+ qe_reset();
+ of_node_put(np);
+#endif
}
static const struct of_device_id of_device_ids[] = {
@@ -81,6 +110,9 @@ static const struct of_device_id of_device_ids[] = {
{
.compatible = "fsl,qoriq-pcie-v3.0",
},
+ {
+ .compatible = "fsl,qe",
+ },
/* The following two are for the Freescale hypervisor */
{
.name = "hypervisor",
--
1.8.5
^ permalink raw reply related
* [git pull] Please pull powerpc.git merge branch
From: Benjamin Herrenschmidt @ 2014-02-28 8:45 UTC (permalink / raw)
To: Linus Torvalds; +Cc: linuxppc-dev list, Linux Kernel list
Hi Linus !
Here are a few more powerpc fixes for 3.14. Most of these are also
CC'ed to stable and fix bugs in new functionality introduced in
the last 2 or 3 versions.
The following changes since commit 66f9af83e56bfa12964d251df9d60fb571579913:
powerpc/eeh: Disable EEH on reboot (2014-02-17 11:19:39 +1100)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git merge
for you to fetch changes up to e0cf957614976896111e676e5134ac98ee227d3d:
powerpc/powernv: Fix indirect XSCOM unmangling (2014-02-28 19:15:49 +1100)
----------------------------------------------------------------
Benjamin Herrenschmidt (2):
powerpc/powernv: Fix opal_xscom_{read,write} prototype
powerpc/powernv: Fix indirect XSCOM unmangling
Gavin Shan (2):
powerpc/powernv: Dump PHB diag-data immediately
powerpc/powernv: Refactor PHB diag-data dump
Laurent Dufour (1):
powerpc/crashdump : Fix page frame number check in copy_oldmem_page
Liu Ping Fan (1):
powerpc/ftrace: bugfix for test_24bit_addr
Paul Mackerras (1):
powerpc: Increase stack redzone for 64-bit userspace to 512 bytes
Tony Breeds (1):
powerpc/le: Ensure that the 'stop-self' RTAS token is handled correctly
arch/powerpc/include/asm/compat.h | 5 +-
arch/powerpc/include/asm/opal.h | 4 +-
arch/powerpc/include/asm/ptrace.h | 16 +-
arch/powerpc/kernel/crash_dump.c | 8 +-
arch/powerpc/kernel/ftrace.c | 1 +
arch/powerpc/kernel/signal_64.c | 4 +-
arch/powerpc/platforms/powernv/eeh-ioda.c | 96 ++++++------
arch/powerpc/platforms/powernv/opal-xscom.c | 21 +--
arch/powerpc/platforms/powernv/pci.c | 220 +++++++++++++++------------
arch/powerpc/platforms/pseries/hotplug-cpu.c | 22 +--
10 files changed, 219 insertions(+), 178 deletions(-)
^ permalink raw reply
* Re: [RFC PATCH] powerpc: allow allyesconfig to build more
From: Benjamin Herrenschmidt @ 2014-02-28 7:46 UTC (permalink / raw)
To: Michael Neuling; +Cc: Stephen Rothwell, ppc-dev, paulus, Mahesh Salgaonkar
In-Reply-To: <5087.1393560369@ale.ozlabs.ibm.com>
On Fri, 2014-02-28 at 15:06 +1100, Michael Neuling wrote:
> Stephen Rothwell <sfr@canb.auug.org.au> wrote:
>
> > Fixes this build error:
> >
> > arch/powerpc/kernel/exceptions-64s.S: Assembler messages:
> > arch/powerpc/kernel/exceptions-64s.S:1312: Error: attempt to move .org backwards
> >
> > Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
>
> Builds and boots for me
>
> Acked-off-by: Michael Neuling <mikey@neuling.org>
>
And breaks at least one of my configs (the g5 one) with a relocation
problem in head_64.o (which is why I had modified the original patch to
be less aggressive iirc).
We end up moving things too far away from a conditional branch, I
think the masked_*interrupt stuff. We need to shuffle things a bit
more to get that to work.
Cheers,
Ben.
^ permalink raw reply
* Re: [PATCH] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: liu ping fan @ 2014-02-28 6:36 UTC (permalink / raw)
To: Aneesh Kumar K.V
Cc: Peter Zijlstra, linux-mm, Paul Mackerras, Andrew Morton,
linuxppc-dev
In-Reply-To: <877g8fn8qw.fsf@linux.vnet.ibm.com>
On Fri, Feb 28, 2014 at 12:47 PM, Aneesh Kumar K.V
<aneesh.kumar@linux.vnet.ibm.com> wrote:
> Andrew Morton <akpm@linux-foundation.org> writes:
>
>> On Wed, 26 Feb 2014 13:22:16 +0530 "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> wrote:
>>
>>> Andrew Morton <akpm@linux-foundation.org> writes:
>>>
>>> > On Wed, 5 Feb 2014 09:25:46 +0800 Liu Ping Fan <qemulist@gmail.com> wrote:
>>> >
>>> >> When doing some numa tests on powerpc, I triggered an oops bug. I find
>>> >> it is caused by using page->_last_cpupid. It should be initialized as
>>> >> "-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
>>> >> we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
>>> >> And finally cause an oops bug in task_numa_group(), since the online cpu is
>>> >> less than possible cpu.
>>> >
>>> > I grabbed this. I added this to the changelog:
>>> >
>>> > : PPC needs the LAST_CPUPID_NOT_IN_PAGE_FLAGS case because ppc needs to
>>> > : support a large physical address region, up to 2^46 but small section size
>>> > : (2^24). So when NR_CPUS grows up, it is easily to cause
>>> > : not-in-page-flags.
>>> >
>>> > to hopefully address Peter's observation.
>>> >
>>> > How should we proceed with this? I'm getting the impression that numa
>>> > balancing on ppc is a dead duck in 3.14, so perhaps this and
>>> >
>>> > powerpc-mm-add-new-set-flag-argument-to-pte-pmd-update-function.patch
>>> > mm-dirty-accountable-change-only-apply-to-non-prot-numa-case.patch
>>> > mm-use-ptep-pmdp_set_numa-for-updating-_page_numa-bit.patch
>>> >
>>>
>>> All these are already in 3.14 ?
>>
>> Yes.
>>
>>> > are 3.15-rc1 material?
>>> >
>>>
>>> We should push the first hunk to 3.14. I will wait for Liu to redo the
>>> patch. BTW this should happen only when SPARSE_VMEMMAP is not
>>> specified. Srikar had reported the issue here
>>>
>>> http://mid.gmane.org/20140219180200.GA29257@linux.vnet.ibm.com
>>>
>>> #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
>>> #define SECTIONS_WIDTH SECTIONS_SHIFT
>>> #else
>>> #define SECTIONS_WIDTH 0
>>> #endif
>>>
>>
>> I'm lost. What patch are you talking about? The first hunk of what?
>
> The patch in this thread.
>
>>
>> I assume we're talking about
>> mm-numa-bugfix-for-last_cpupid_not_in_page_flags.patch, which I had
>> queued for 3.14. I'll put it on hold until there's some clarity here.
>
> We don't need the complete patch, it is just the first hunk that we need
> to fix the crash ie. we only need
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index a7b4e31..ddc66df4 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -727,7 +727,7 @@ static inline int page_cpupid_last(struct page *page)
> }
> static inline void page_cpupid_reset_last(struct page *page)
> {
> - page->_last_cpupid = -1;
> + page->_last_cpupid = -1 & LAST_CPUPID_MASK;
> }
> #else
> static inline int page_cpupid_last(struct page *page)
>
> Also the issue will only happen when SPARSE_VMEMMAP is not enabled. I
> will send a proper patch with updated changelog. I was hoping Liu will
> get to that quickly
>
Thanks for sending V2. Since the ppc machine env is changed by
others, I am blocking on setting up the env for re-test this patch.
And not send out it quickly.
Best regards,
Fan
>
> -aneesh
>
^ permalink raw reply
* [PATCH 2/2] powerpc/perf: Add lost exception workaround
From: Michael Ellerman @ 2014-02-28 6:29 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1393568946-4136-1-git-send-email-mpe@ellerman.id.au>
Some power8 revisions have a hardware bug where we can lose a PMU
exception, this commit adds a workaround to detect the bad condition and
rectify the situation.
See the comment in the commit for a full description.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/reg.h | 2 +
arch/powerpc/perf/core-book3s.c | 100 +++++++++++++++++++++++++++++++++++++++-
arch/powerpc/perf/power8-pmu.c | 5 ++
3 files changed, 105 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 90c06ec..3003472 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -670,6 +670,7 @@
#define MMCR0_PMC1CE 0x00008000UL /* PMC1 count enable*/
#define MMCR0_PMCjCE 0x00004000UL /* PMCj count enable*/
#define MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */
+#define MMCR0_PMAO_SYNC 0x00000800UL /* PMU interrupt is synchronous */
#define MMCR0_PMAO 0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
#define MMCR0_SHRFC 0x00000040UL /* SHRre freeze conditions between threads */
#define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */
@@ -703,6 +704,7 @@
#define SPRN_EBBHR 804 /* Event based branch handler register */
#define SPRN_EBBRR 805 /* Event based branch return register */
#define SPRN_BESCR 806 /* Branch event status and control register */
+#define BESCR_GE 0x8000000000000000ULL /* Global Enable */
#define SPRN_WORT 895 /* Workload optimization register - thread */
#define SPRN_PMC1 787
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 67cf220..72cdd05 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -120,6 +120,7 @@ static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
void power_pmu_flush_branch_stack(void) {}
static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
+static void pmao_restore_workaround(bool ebb) { }
#endif /* CONFIG_PPC32 */
static bool regs_use_siar(struct pt_regs *regs)
@@ -545,10 +546,18 @@ static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
/* Enable EBB and read/write to all 6 PMCs for userspace */
mmcr0 |= MMCR0_EBE | MMCR0_PMCC_U6;
- /* Add any bits from the user reg, FC or PMAO */
+ /*
+ * Add any bits from the user MMCR0, FC or PMAO. This is compatible
+ * with pmao_restore_workaround() because we may add PMAO but we never
+ * clear it here.
+ */
mmcr0 |= current->thread.mmcr0;
- /* Be careful not to set PMXE if userspace had it cleared */
+ /*
+ * Be careful not to set PMXE if userspace had it cleared. This is also
+ * compatible with pmao_restore_workaround() because it has already
+ * cleared PMXE and we leave PMAO alone.
+ */
if (!(current->thread.mmcr0 & MMCR0_PMXE))
mmcr0 &= ~MMCR0_PMXE;
@@ -559,6 +568,91 @@ static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
out:
return mmcr0;
}
+
+static void pmao_restore_workaround(bool ebb)
+{
+ unsigned pmcs[6];
+
+ if (!cpu_has_feature(CPU_FTR_PMAO_BUG))
+ return;
+
+ /*
+ * On POWER8 there is a hardware defect which affects the PMU context
+ * switch logic, ie. power_pmu_disable/enable().
+ *
+ * When a counter overflows PMXE is cleared and FC/PMAO is set in MMCR0
+ * by the hardware. Sometime later the actual PMU exception is
+ * delivered.
+ *
+ * If we context switch, or simply disable/enable, the PMU prior to the
+ * exception arriving, the exception will be lost when we clear PMAO.
+ *
+ * When we reenable the PMU, we will write the saved MMCR0 with PMAO
+ * set, and this _should_ generate an exception. However because of the
+ * defect no exception is generated when we write PMAO, and we get
+ * stuck with no counters counting but no exception delivered.
+ *
+ * The workaround is to detect this case and tweak the hardware to
+ * create another pending PMU exception.
+ *
+ * We do that by setting up PMC6 (cycles) for an imminent overflow and
+ * enabling the PMU. That causes a new exception to be generated in the
+ * chip, but we don't take it yet because we have interrupts hard
+ * disabled. We then write back the PMU state as we want it to be seen
+ * by the exception handler. When we reenable interrupts the exception
+ * handler will be called and see the correct state.
+ *
+ * The logic is the same for EBB, except that the exception is gated by
+ * us having interrupts hard disabled as well as the fact that we are
+ * not in userspace. The exception is finally delivered when we return
+ * to userspace.
+ */
+
+ /* Only if PMAO is set and PMAO_SYNC is clear */
+ if ((current->thread.mmcr0 & (MMCR0_PMAO | MMCR0_PMAO_SYNC)) != MMCR0_PMAO)
+ return;
+
+ /* If we're doing EBB, only if BESCR[GE] is set */
+ if (ebb && !(current->thread.bescr & BESCR_GE))
+ return;
+
+ /*
+ * We are already soft-disabled in power_pmu_enable(). We need to hard
+ * enable to actually prevent the PMU exception from firing.
+ */
+ hard_irq_disable();
+
+ /*
+ * This is a bit gross, but we know we're on POWER8 and have 6 PMCs.
+ * Using read/write_pmc() in a for loop adds 12 function calls and
+ * almost doubles our code size.
+ */
+ pmcs[0] = mfspr(SPRN_PMC1);
+ pmcs[1] = mfspr(SPRN_PMC2);
+ pmcs[2] = mfspr(SPRN_PMC3);
+ pmcs[3] = mfspr(SPRN_PMC4);
+ pmcs[4] = mfspr(SPRN_PMC5);
+ pmcs[5] = mfspr(SPRN_PMC6);
+
+ /* Ensure all freeze bits are unset */
+ mtspr(SPRN_MMCR2, 0);
+
+ /* Set up PMC6 to overflow in one cycle */
+ mtspr(SPRN_PMC6, 0x7FFFFFFE);
+
+ /* Enable exceptions and unfreeze PMC6 */
+ mtspr(SPRN_MMCR0, MMCR0_PMXE | MMCR0_PMCjCE | MMCR0_PMAO);
+
+ /* Now we need to refreeze and restore the PMCs */
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMAO);
+
+ mtspr(SPRN_PMC1, pmcs[0]);
+ mtspr(SPRN_PMC2, pmcs[1]);
+ mtspr(SPRN_PMC3, pmcs[2]);
+ mtspr(SPRN_PMC4, pmcs[3]);
+ mtspr(SPRN_PMC5, pmcs[4]);
+ mtspr(SPRN_PMC6, pmcs[5]);
+}
#endif /* CONFIG_PPC64 */
static void perf_event_interrupt(struct pt_regs *regs);
@@ -1144,6 +1238,8 @@ static void power_pmu_enable(struct pmu *pmu)
cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
out_enable:
+ pmao_restore_workaround(ebb);
+
mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
mb();
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 96cee20..64f04cf 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -10,6 +10,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) "power8-pmu: " fmt
+
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <asm/firmware.h>
@@ -774,6 +776,9 @@ static int __init init_power8_pmu(void)
/* Tell userspace that EBB is supported */
cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+ if (cpu_has_feature(CPU_FTR_PMAO_BUG))
+ pr_info("PMAO restore workaround active.\n");
+
return 0;
}
early_initcall(init_power8_pmu);
--
1.8.3.2
^ permalink raw reply related
* [PATCH 1/2] powerpc: Add a cpu feature CPU_FTR_PMAO_BUG
From: Michael Ellerman @ 2014-02-28 6:29 UTC (permalink / raw)
To: linuxppc-dev
Some power8 revisions have a hardware bug where we can lose a
Performance Monitor (PMU) exception under certain circumstances.
We will be adding a workaround for this case, see the next commit for
details. The observed behaviour is that writing PMAO doesn't cause an
exception as we would expect, hence the name of the feature.
This commit just adds a CPU feature bit. We set it on all power8 cpus,
and then clear it at cpu setup time if we are on a revision where the
bug is fixed.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/cputable.h | 3 ++-
arch/powerpc/kernel/cpu_setup_power.S | 15 +++++++++++++++
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 617cc76..56d3166 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -189,6 +189,7 @@ extern const char *powerpc_base_platform;
#define CPU_FTR_HAS_PPR LONG_ASM_CONST(0x0200000000000000)
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
+#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
#ifndef __ASSEMBLY__
@@ -444,7 +445,7 @@ extern const char *powerpc_base_platform;
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
- CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
+ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PMAO_BUG)
#define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 37d1bb0..cb2da74 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -179,4 +179,19 @@ __init_PMU:
mtspr SPRN_MMCR0,r5
mtspr SPRN_MMCR1,r5
mtspr SPRN_MMCR2,r5
+
+ /* Compare our PVR to POWER8 DD2 (0x4d0200) */
+ mfpvr r5
+ lis r6,0x4d
+ ori r6,r6,0x0200
+ cmplw r5,r6
+
+ /* If we are older then return */
+ bltlr
+
+ /* Otherwise clear CPU_FTR_PMAO_BUG */
+ ld r5,CPU_SPEC_FEATURES(r4)
+ LOAD_REG_IMMEDIATE(r6,CPU_FTR_PMAO_BUG)
+ xor r5,r5,r6
+ std r5,CPU_SPEC_FEATURES(r4)
blr
--
1.8.3.2
^ permalink raw reply related
* [PATCH V2] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: Aneesh Kumar K.V @ 2014-02-28 5:28 UTC (permalink / raw)
To: benh, akpm, Peter Zijlstra
Cc: Liu Ping Fan, linux-kernel, Liu Ping Fan, linux-mm,
Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <877g8fn8qw.fsf@linux.vnet.ibm.com>
From: Liu Ping Fan <qemulist@gmail.com>
When doing some numa tests on powerpc, I triggered an oops bug. I find
it is caused by using page->_last_cpupid. It should be initialized as
"-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
And finally cause an oops bug in task_numa_group(), since the online cpu is
less than possible cpu. This happen with CONFIG_SPARSE_VMEMMAP disabled
Call trace:
[ 55.978091] SMP NR_CPUS=64 NUMA PowerNV
[ 55.978118] Modules linked in:
[ 55.978145] CPU: 24 PID: 804 Comm: systemd-udevd Not tainted3.13.0-rc1+ #32
[ 55.978183] task: c000001e2746aa80 ti: c000001e32c50000 task.ti:c000001e32c50000
[ 55.978219] NIP: c0000000000f5ad0 LR: c0000000000f5ac8 CTR:c000000000913cf0
[ 55.978256] REGS: c000001e32c53510 TRAP: 0300 Not tainted(3.13.0-rc1+)
[ 55.978286] MSR: 9000000000009032 <SF,HV,EE,ME,IR,DR,RI> CR:28024424 XER: 20000000
[ 55.978380] CFAR: c000000000009324 DAR: 7265717569726857 DSISR:40000000 SOFTE: 1
GPR00: c0000000000f5ac8 c000001e32c53790 c000000001f343380000000000000021
GPR04: 0000000000000000 0000000000000031 c000000001f743380000ffffffffffff
GPR08: 0000000000000001 7265717569726573 00000000000000000000000000000000
GPR12: 0000000028024422 c00000000ffdd800 00000000296b2e640000000000000020
GPR16: 0000000000000002 0000000000000003 c000001e2f8e4658c000001e25c1c1d8
GPR20: c000001e2f8e4000 c000000001f7a858 00000000000006580000000040000392
GPR24: 00000000000000a8 c000001e33c1a400 00000000000001d8c000001e25c1c000
GPR28: c000001e33c37ff0 0007837840000392 000000000000003fc000001e32c53790
[ 55.978903] NIP [c0000000000f5ad0] .task_numa_fault+0x1470/0x2370
[ 55.978934] LR [c0000000000f5ac8] .task_numa_fault+0x1468/0x2370
[ 55.978964] Call Trace:
[ 55.978978] [c000001e32c53790] [c0000000000f5ac8].task_numa_fault+0x1468/0x2370 (unreliable)
[ 55.979036] [c000001e32c539e0] [c00000000020a820].do_numa_page+0x480/0x4a0
[ 55.979072] [c000001e32c53b10] [c00000000020bfec].handle_mm_fault+0x4ec/0xc90
[ 55.979123] [c000001e32c53c00] [c000000000e88c98].do_page_fault+0x3a8/0x890
[ 55.979161] [c000001e32c53e30] [c000000000009568]handle_page_fault+0x10/0x30
[ 55.979197] Instruction dump:
[ 55.979216] 3c82fefb 3884b138 48d9cff1 60000000 48000574 3c62fefb3863af78 3c82fefb
[ 55.979277] 3884b138 48d9cfd5 60000000 e93f0100 <812902e4> 7d2907b45529063e 7d2a07b4
[ 55.979354] ---[ end trace 15f2510da5ae07cf ]---
Signed-off-by: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
include/linux/mm.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46eade6a..1a0ea24ff972 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -766,7 +766,7 @@ static inline int page_cpupid_last(struct page *page)
}
static inline void page_cpupid_reset_last(struct page *page)
{
- page->_last_cpupid = -1;
+ page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int page_cpupid_last(struct page *page)
--
1.8.3.2
^ permalink raw reply related
* [PATCH 2/2] powerpc/powernv: Fix indirect XSCOM unmangling
From: Benjamin Herrenschmidt @ 2014-02-28 5:20 UTC (permalink / raw)
To: linuxppc-dev list
We need to unmangle the full address, not just the register
number, and we also need to support the real indirect bit
being set for in-kernel uses.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.13]
---
arch/powerpc/platforms/powernv/opal-xscom.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276..4cd2ea6 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc)
}
}
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
{
/*
* XSCOM indirect addresses have the top bit set. Additionally
- * the reset of the top 3 nibbles is always 0.
+ * the rest of the top 3 nibbles is always 0.
*
* Because the debugfs interface uses signed offsets and shifts
* the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg)
* conversion here. To leave room for further xscom address
* expansion, we only clear out the top byte
*
+ * For in-kernel use, we also support the real indirect bit, so
+ * we test for any of the top 5 bits
+ *
*/
- if (reg & (1ull << 59))
- reg = (reg & ~(0xffull << 56)) | (1ull << 63);
- return reg;
+ if (addr & (0x1full << 59))
+ addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+ return addr;
}
static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
int64_t rc;
__be64 v;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
*value = be64_to_cpu(v);
return opal_xscom_err_xlate(rc);
}
@@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
struct opal_scom_map *m = map;
int64_t rc;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_write(m->chip, m->addr + reg, value);
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_write(m->chip, reg, value);
return opal_xscom_err_xlate(rc);
}
^ permalink raw reply related
* [PATCH 1/2] powerpc/powernv: Fix opal_xscom_{read,write} prototype
From: Benjamin Herrenschmidt @ 2014-02-28 5:20 UTC (permalink / raw)
To: linuxppc-dev list
The OPAL firmware functions opal_xscom_read and opal_xscom_write
take a 64-bit argument for the XSCOM (PCB) address in order to
support the indirect mode on P8.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.13]
---
arch/powerpc/include/asm/opal.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..ed82142 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
int64_t opal_pci_poll(uint64_t phb_id);
int64_t opal_return_cpu(void);
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, uint32_t data, uint32_t sz);
^ permalink raw reply related
* Re: [PATCH] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: Aneesh Kumar K.V @ 2014-02-28 4:47 UTC (permalink / raw)
To: Andrew Morton
Cc: Peter Zijlstra, Liu Ping Fan, linux-mm, Paul Mackerras,
linuxppc-dev
In-Reply-To: <20140227154104.4e3572f1d9e2692d431d1a4e@linux-foundation.org>
Andrew Morton <akpm@linux-foundation.org> writes:
> On Wed, 26 Feb 2014 13:22:16 +0530 "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> wrote:
>
>> Andrew Morton <akpm@linux-foundation.org> writes:
>>
>> > On Wed, 5 Feb 2014 09:25:46 +0800 Liu Ping Fan <qemulist@gmail.com> wrote:
>> >
>> >> When doing some numa tests on powerpc, I triggered an oops bug. I find
>> >> it is caused by using page->_last_cpupid. It should be initialized as
>> >> "-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
>> >> we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
>> >> And finally cause an oops bug in task_numa_group(), since the online cpu is
>> >> less than possible cpu.
>> >
>> > I grabbed this. I added this to the changelog:
>> >
>> > : PPC needs the LAST_CPUPID_NOT_IN_PAGE_FLAGS case because ppc needs to
>> > : support a large physical address region, up to 2^46 but small section size
>> > : (2^24). So when NR_CPUS grows up, it is easily to cause
>> > : not-in-page-flags.
>> >
>> > to hopefully address Peter's observation.
>> >
>> > How should we proceed with this? I'm getting the impression that numa
>> > balancing on ppc is a dead duck in 3.14, so perhaps this and
>> >
>> > powerpc-mm-add-new-set-flag-argument-to-pte-pmd-update-function.patch
>> > mm-dirty-accountable-change-only-apply-to-non-prot-numa-case.patch
>> > mm-use-ptep-pmdp_set_numa-for-updating-_page_numa-bit.patch
>> >
>>
>> All these are already in 3.14 ?
>
> Yes.
>
>> > are 3.15-rc1 material?
>> >
>>
>> We should push the first hunk to 3.14. I will wait for Liu to redo the
>> patch. BTW this should happen only when SPARSE_VMEMMAP is not
>> specified. Srikar had reported the issue here
>>
>> http://mid.gmane.org/20140219180200.GA29257@linux.vnet.ibm.com
>>
>> #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
>> #define SECTIONS_WIDTH SECTIONS_SHIFT
>> #else
>> #define SECTIONS_WIDTH 0
>> #endif
>>
>
> I'm lost. What patch are you talking about? The first hunk of what?
The patch in this thread.
>
> I assume we're talking about
> mm-numa-bugfix-for-last_cpupid_not_in_page_flags.patch, which I had
> queued for 3.14. I'll put it on hold until there's some clarity here.
We don't need the complete patch, it is just the first hunk that we need
to fix the crash ie. we only need
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a7b4e31..ddc66df4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -727,7 +727,7 @@ static inline int page_cpupid_last(struct page *page)
}
static inline void page_cpupid_reset_last(struct page *page)
{
- page->_last_cpupid = -1;
+ page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int page_cpupid_last(struct page *page)
Also the issue will only happen when SPARSE_VMEMMAP is not enabled. I
will send a proper patch with updated changelog. I was hoping Liu will
get to that quickly
-aneesh
^ permalink raw reply related
* Re: [RFC PATCH] powerpc: allow allyesconfig to build more
From: Michael Neuling @ 2014-02-28 4:06 UTC (permalink / raw)
To: Stephen Rothwell; +Cc: ppc-dev, paulus, Mahesh Salgaonkar
In-Reply-To: <20140227171719.01d7de4be01559dd02968f7c@canb.auug.org.au>
Stephen Rothwell <sfr@canb.auug.org.au> wrote:
> Fixes this build error:
>
> arch/powerpc/kernel/exceptions-64s.S: Assembler messages:
> arch/powerpc/kernel/exceptions-64s.S:1312: Error: attempt to move .org backwards
>
> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Builds and boots for me
Acked-off-by: Michael Neuling <mikey@neuling.org>
> ---
> arch/powerpc/kernel/exceptions-64s.S | 20 ++++++++++----------
> 1 file changed, 10 insertions(+), 10 deletions(-)
>
> This builds allyesconfig better (we still have RELOC failures in the
> link) and hopefully fixes the allmodconfig build, but I don't know if
> it is semantically OK.
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 38d507306a11..b87859ffc8e7 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -1294,16 +1294,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
> .globl __end_handlers
> __end_handlers:
>
> - /* Equivalents to the above handlers for relocation-on interrupt vectors */
> - STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
> - MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
> -
> - STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
> - STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
> - STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
> - STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
> - STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
> -
> #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
> /*
> * Data area reserved for FWNMI option.
> @@ -1325,6 +1315,16 @@ fwnmi_data_area:
> initial_stab:
> .space 4096
>
> + /* Equivalents to the above handlers for relocation-on interrupt vectors */
> + STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
> + MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
> +
> + STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
> + STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
> + STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
> + STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
> + STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
> +
> #ifdef CONFIG_PPC_POWERNV
> _GLOBAL(opal_mc_secondary_handler)
> HMT_MEDIUM_PPR_DISCARD
> --
> 1.9.0
>
> --
> Cheers,
> Stephen Rothwell sfr@canb.auug.org.au
^ permalink raw reply
* Re: [PATCH] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: liu ping fan @ 2014-02-28 2:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Peter Zijlstra, linux-mm, Paul Mackerras, Aneesh Kumar K.V,
linuxppc-dev
In-Reply-To: <20140227154104.4e3572f1d9e2692d431d1a4e@linux-foundation.org>
On Fri, Feb 28, 2014 at 7:41 AM, Andrew Morton
<akpm@linux-foundation.org> wrote:
> On Wed, 26 Feb 2014 13:22:16 +0530 "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> wrote:
>
>> Andrew Morton <akpm@linux-foundation.org> writes:
>>
>> > On Wed, 5 Feb 2014 09:25:46 +0800 Liu Ping Fan <qemulist@gmail.com> wrote:
>> >
>> >> When doing some numa tests on powerpc, I triggered an oops bug. I find
>> >> it is caused by using page->_last_cpupid. It should be initialized as
>> >> "-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
>> >> we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
>> >> And finally cause an oops bug in task_numa_group(), since the online cpu is
>> >> less than possible cpu.
>> >
>> > I grabbed this. I added this to the changelog:
>> >
>> > : PPC needs the LAST_CPUPID_NOT_IN_PAGE_FLAGS case because ppc needs to
>> > : support a large physical address region, up to 2^46 but small section size
>> > : (2^24). So when NR_CPUS grows up, it is easily to cause
>> > : not-in-page-flags.
>> >
>> > to hopefully address Peter's observation.
>> >
>> > How should we proceed with this? I'm getting the impression that numa
>> > balancing on ppc is a dead duck in 3.14, so perhaps this and
>> >
>> > powerpc-mm-add-new-set-flag-argument-to-pte-pmd-update-function.patch
>> > mm-dirty-accountable-change-only-apply-to-non-prot-numa-case.patch
>> > mm-use-ptep-pmdp_set_numa-for-updating-_page_numa-bit.patch
>> >
>>
>> All these are already in 3.14 ?
>
> Yes.
>
>> > are 3.15-rc1 material?
>> >
>>
>> We should push the first hunk to 3.14. I will wait for Liu to redo the
>> patch. BTW this should happen only when SPARSE_VMEMMAP is not
>> specified. Srikar had reported the issue here
>>
>> http://mid.gmane.org/20140219180200.GA29257@linux.vnet.ibm.com
>>
>> #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
>> #define SECTIONS_WIDTH SECTIONS_SHIFT
>> #else
>> #define SECTIONS_WIDTH 0
>> #endif
>>
>
> I'm lost. What patch are you talking about? The first hunk of what?
>
I think Aneesh was talking about the chunk of patch, which modified
the file "page-flags-layout.h".
I tried to collapse and simplify the logic, but it will incur that
LAST_CPUPID_WIDTH depends on CONFIG_NUMA_BALANCING.
It is an error since we need LAST_CPUPID_WIDTH even without
CONFIG_NUMA_BALANCING. (Sorry, I compiled and run kernel, but not find
this).
Thanks and best regards,
Fan
> I assume we're talking about
> mm-numa-bugfix-for-last_cpupid_not_in_page_flags.patch, which I had
> queued for 3.14. I'll put it on hold until there's some clarity here.
>
^ permalink raw reply
* [PATCH] powerpc/powernv: Read OPAL error log and export it through sysfs
From: Stewart Smith @ 2014-02-28 0:58 UTC (permalink / raw)
To: Mahesh J Salgaonkar, benh, linuxppc-dev; +Cc: Stewart Smith
In-Reply-To: <87k3cin5kd.fsf@river.au.ibm.com>
Based on a patch by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch adds support to read error logs from OPAL and export
them to userspace through a sysfs interface.
We export each log entry as a directory in /sys/firmware/opal/elog/
Currently, OPAL will buffer up to 128 error log records, we don't
need to have any knowledge of this limit on the Linux side as that
is actually largely transparent to us.
Each error log entry has the following files: id, type, acknowledge, raw.
Currently we just export the raw binary error log in the 'raw' attribute.
In a future patch, we may parse more of the error log to make it a bit
easier for userspace (e.g. to be able to display a brief summary in
petitboot without having to have a full parser).
If we have >128 logs from OPAL, we'll only be notified of 128 until
userspace starts acknowledging them. This limitation may be lifted in
the future and with this patch, that should "just work" from the linux side.
A userspace daemon should:
- wait for error log entries using normal mechanisms (we announce creation)
- read error log entry
- save error log entry safely to disk
- acknowledge the error log entry
- rinse, repeat.
On the Linux side, we read the error log when we're notified of it. This
possibly isn't ideal as it would be better to only read them on-demand.
However, this doesn't really work with current OPAL interface, so we
read the error log immediately when notified at the moment.
I've tested this pretty extensively and am rather confident that the
linux side of things works rather well. There is currently an issue with
the service processor side of things for >128 error logs though.
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
---
Documentation/ABI/stable/sysfs-firmware-opal-elog | 60 ++++
arch/powerpc/include/asm/opal.h | 13 +
arch/powerpc/platforms/powernv/Makefile | 2 +-
arch/powerpc/platforms/powernv/opal-elog.c | 312 +++++++++++++++++++++
arch/powerpc/platforms/powernv/opal-wrappers.S | 5 +
arch/powerpc/platforms/powernv/opal.c | 2 +
6 files changed, 393 insertions(+), 1 deletion(-)
create mode 100644 Documentation/ABI/stable/sysfs-firmware-opal-elog
create mode 100644 arch/powerpc/platforms/powernv/opal-elog.c
diff --git a/Documentation/ABI/stable/sysfs-firmware-opal-elog b/Documentation/ABI/stable/sysfs-firmware-opal-elog
new file mode 100644
index 0000000..e1f3058
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-firmware-opal-elog
@@ -0,0 +1,60 @@
+What: /sys/firmware/opal/elog
+Date: Feb 2014
+Contact: Stewart Smith <stewart@linux.vnet.ibm.com>
+Description:
+ This directory exposes error log entries retrieved
+ through the OPAL firmware interface.
+
+ Each error log is identified by a unique ID and will
+ exist until explicitly acknowledged to firmware.
+
+ Each log entry has a directory in /sys/firmware/opal/elog.
+
+ Log entries may be purged by the service processor
+ before retrieved by firmware or retrieved/acknowledged by
+ Linux if there is no room for more log entries.
+
+ In the event that Linux has retrieved the log entries
+ but not explicitly acknowledged them to firmware and
+ the service processor needs more room for log entries,
+ the only remaining copy of a log message may be in
+ Linux.
+
+ Typically, a user space daemon will monitor for new
+ entries, read them out and acknowledge them.
+
+ The service processor may be able to store more log
+ entries than firmware can, so after you acknowledge
+ an event from Linux you may instantly get another one
+ from the queue that was generated some time in the past.
+
+ The raw log format is a binary format. We currently
+ do not parse this at all in kernel, leaving it up to
+ user space to solve the problem. In future, we may
+ do more parsing in kernel and add more files to make
+ it easier for simple user space processes to extract
+ more information.
+
+ For each log entry (directory), there are the following
+ files:
+
+ id: An ASCII representation of the ID of the
+ error log, in hex - e.g. "0x01".
+
+ type: An ASCII representation of the type id and
+ description of the type of error log.
+ Currently just "0x00 PEL" - platform error log.
+ In the future there may be additional types.
+
+ raw: A read-only binary file that can be read
+ to get the raw log entry. These are
+ <16kb, often just hundreds of bytes and
+ "average" 2kb.
+
+ acknowledge: Writing 'ack' to this file will acknowledge
+ the error log to firmware (and in turn
+ the service processor, if applicable).
+ Shortly after acknowledging it, the log
+ entry will be removed from sysfs.
+ Reading this file will list the supported
+ operations (curently just acknowledge).
\ No newline at end of file
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..b404545 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -151,6 +151,11 @@ extern int opal_enter_rtas(struct rtas_args *args,
#define OPAL_LPC_READ 67
#define OPAL_LPC_WRITE 68
#define OPAL_RETURN_CPU 69
+#define OPAL_ELOG_READ 71
+#define OPAL_ELOG_WRITE 72
+#define OPAL_ELOG_ACK 73
+#define OPAL_ELOG_RESEND 74
+#define OPAL_ELOG_SIZE 75
#define OPAL_FLASH_VALIDATE 76
#define OPAL_FLASH_MANAGE 77
#define OPAL_FLASH_UPDATE 78
@@ -823,6 +828,13 @@ int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, uint32_t data, uint32_t sz);
int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, __be32 *data, uint32_t sz);
+
+int64_t opal_read_elog(uint64_t buffer, size_t size, uint64_t log_id);
+int64_t opal_get_elog_size(uint64_t *log_id, size_t *size, uint64_t *elog_type);
+int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset);
+int64_t opal_send_ack_elog(uint64_t log_id);
+void opal_resend_pending_logs(void);
+
int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
int64_t opal_manage_flash(uint8_t op);
int64_t opal_update_flash(uint64_t blk_list);
@@ -861,6 +873,7 @@ extern void opal_get_rtc_time(struct rtc_time *tm);
extern unsigned long opal_get_boot_time(void);
extern void opal_nvram_init(void);
extern void opal_flash_init(void);
+extern int opal_elog_init(void);
extern int opal_machine_check(struct pt_regs *regs);
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 8d767fd..189fd45 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,6 +1,6 @@
obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o
obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
-obj-y += rng.o
+obj-y += rng.o opal-elog.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
new file mode 100644
index 0000000..61e2ef3
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -0,0 +1,312 @@
+/*
+ * Error log support on PowerNV.
+ *
+ * Copyright 2013,2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/fs.h>
+#include <linux/vmalloc.h>
+#include <linux/fcntl.h>
+#include <asm/uaccess.h>
+#include <asm/opal.h>
+
+struct elog_obj {
+ struct kobject kobj;
+ struct bin_attribute raw_attr;
+ uint64_t id;
+ uint64_t type;
+ size_t size;
+ char *buffer;
+};
+#define to_elog_obj(x) container_of(x, struct elog_obj, kobj)
+
+struct elog_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct elog_obj *elog, struct elog_attribute *attr,
+ char *buf);
+ ssize_t (*store)(struct elog_obj *elog, struct elog_attribute *attr,
+ const char *buf, size_t count);
+};
+#define to_elog_attr(x) container_of(x, struct elog_attribute, attr)
+
+static ssize_t elog_id_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0x%llx\n", elog_obj->id);
+}
+
+static const char *elog_type_to_string(uint64_t type)
+{
+ switch (type) {
+ case 0: return "PEL";
+ default: return "unknown";
+ }
+}
+
+static ssize_t elog_type_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0x%llx %s\n",
+ elog_obj->type,
+ elog_type_to_string(elog_obj->type));
+}
+
+static ssize_t elog_ack_show(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "ack - acknowledge log message\n");
+}
+
+static void delay_release_kobj(void *kobj)
+{
+ kobject_put((struct kobject *)kobj);
+}
+
+static ssize_t elog_ack_store(struct elog_obj *elog_obj,
+ struct elog_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ opal_send_ack_elog(elog_obj->id);
+ sysfs_schedule_callback(&elog_obj->kobj, delay_release_kobj,
+ &elog_obj->kobj, THIS_MODULE);
+ return count;
+}
+
+static struct elog_attribute id_attribute =
+ __ATTR(id, 0666, elog_id_show, NULL);
+static struct elog_attribute type_attribute =
+ __ATTR(type, 0666, elog_type_show, NULL);
+static struct elog_attribute ack_attribute =
+ __ATTR(acknowledge, 0660, elog_ack_show, elog_ack_store);
+
+static struct kset *elog_kset;
+
+static ssize_t elog_attr_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct elog_attribute *attribute;
+ struct elog_obj *elog;
+
+ attribute = to_elog_attr(attr);
+ elog = to_elog_obj(kobj);
+
+ if (!attribute->show)
+ return -EIO;
+
+ return attribute->show(elog, attribute, buf);
+}
+
+static ssize_t elog_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct elog_attribute *attribute;
+ struct elog_obj *elog;
+
+ attribute = to_elog_attr(attr);
+ elog = to_elog_obj(kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(elog, attribute, buf, len);
+}
+
+static const struct sysfs_ops elog_sysfs_ops = {
+ .show = elog_attr_show,
+ .store = elog_attr_store,
+};
+
+static void elog_release(struct kobject *kobj)
+{
+ struct elog_obj *elog;
+
+ elog = to_elog_obj(kobj);
+ kfree(elog->buffer);
+ kfree(elog);
+}
+
+static struct attribute *elog_default_attrs[] = {
+ &id_attribute.attr,
+ &type_attribute.attr,
+ &ack_attribute.attr,
+ NULL,
+};
+
+static struct kobj_type elog_ktype = {
+ .sysfs_ops = &elog_sysfs_ops,
+ .release = &elog_release,
+ .default_attrs = elog_default_attrs,
+};
+
+/* Maximum size of a single log on FSP is 16KB */
+#define OPAL_MAX_ERRLOG_SIZE 16384
+
+static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buffer, loff_t pos, size_t count)
+{
+ int opal_rc;
+
+ struct elog_obj *elog = to_elog_obj(kobj);
+
+ /* We may have had an error reading before, so let's retry */
+ if (!elog->buffer) {
+ elog->buffer = kzalloc(elog->size, GFP_KERNEL);
+ if (!elog->buffer)
+ return -EIO;
+
+ opal_rc = opal_read_elog(__pa(elog->buffer),
+ elog->size, elog->id);
+ if (opal_rc != OPAL_SUCCESS) {
+ pr_err("ELOG: log read failed for log-id=%llx\n",
+ elog->id);
+ kfree(elog->buffer);
+ elog->buffer = NULL;
+ return -EIO;
+ }
+ }
+
+ memcpy(buffer, elog->buffer + pos, count);
+
+ return count;
+}
+
+static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type)
+{
+ struct elog_obj *elog;
+ int rc;
+
+ elog = kzalloc(sizeof(*elog), GFP_KERNEL);
+ if (!elog)
+ return NULL;
+
+ elog->kobj.kset = elog_kset;
+
+ kobject_init(&elog->kobj, &elog_ktype);
+
+ sysfs_bin_attr_init(&elog->raw_attr);
+
+ elog->raw_attr.attr.name = "raw";
+ elog->raw_attr.attr.mode = 0400;
+ elog->raw_attr.size = size;
+ elog->raw_attr.read = raw_attr_read;
+
+ elog->id = id;
+ elog->size = size;
+ elog->type = type;
+
+ elog->buffer = kzalloc(elog->size, GFP_KERNEL);
+
+ if (elog->buffer) {
+ rc = opal_read_elog(__pa(elog->buffer),
+ elog->size, elog->id);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("ELOG: log read failed for log-id=%llx\n",
+ elog->id);
+ kfree(elog->buffer);
+ elog->buffer = NULL;
+ }
+ }
+
+ rc = kobject_add(&elog->kobj, NULL, "0x%llx", id);
+ if (rc) {
+ kobject_put(&elog->kobj);
+ return NULL;
+ }
+
+ rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr);
+ if (rc) {
+ kobject_put(&elog->kobj);
+ return NULL;
+ }
+
+ kobject_uevent(&elog->kobj, KOBJ_ADD);
+
+ return elog;
+}
+
+static void elog_work_fn(struct work_struct *work)
+{
+ size_t elog_size;
+ uint64_t log_id;
+ uint64_t elog_type;
+ int rc;
+ char name[2+16+1];
+
+ rc = opal_get_elog_size(&log_id, &elog_size, &elog_type);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("ELOG: Opal log read failed\n");
+ return;
+ }
+
+ BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
+
+ if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
+ elog_size = OPAL_MAX_ERRLOG_SIZE;
+
+ sprintf(name, "0x%llx", log_id);
+
+ /* we may get notified twice, let's handle
+ * that gracefully and not create two conflicting
+ * entries.
+ */
+ if (kset_find_obj(elog_kset, name))
+ return;
+
+ create_elog_obj(log_id, elog_size, elog_type);
+}
+
+static DECLARE_WORK(elog_work, elog_work_fn);
+
+static int elog_event(struct notifier_block *nb,
+ unsigned long events, void *change)
+{
+ /* check for error log event */
+ if (events & OPAL_EVENT_ERROR_LOG_AVAIL)
+ schedule_work(&elog_work);
+ return 0;
+}
+
+static struct notifier_block elog_nb = {
+ .notifier_call = elog_event,
+ .next = NULL,
+ .priority = 0
+};
+
+int __init opal_elog_init(void)
+{
+ int rc = 0;
+
+ elog_kset = kset_create_and_add("elog", NULL, opal_kobj);
+ if (!elog_kset) {
+ pr_warn("%s: failed to create elog kset\n", __func__);
+ return -1;
+ }
+
+ rc = opal_notifier_register(&elog_nb);
+ if (rc) {
+ pr_err("%s: Can't register OPAL event notifier (%d)\n",
+ __func__, rc);
+ return rc;
+ }
+
+ /* We are now ready to pull error logs from opal. */
+ opal_resend_pending_logs();
+
+ return 0;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 3e8829c..5fcbf25 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -123,6 +123,11 @@ OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE);
OPAL_CALL(opal_lpc_read, OPAL_LPC_READ);
OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE);
OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU);
+OPAL_CALL(opal_read_elog, OPAL_ELOG_READ);
+OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK);
+OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE);
+OPAL_CALL(opal_resend_pending_logs, OPAL_ELOG_RESEND);
+OPAL_CALL(opal_write_elog, OPAL_ELOG_WRITE);
OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE);
OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE);
OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 65499ad..fb77302 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -472,6 +472,8 @@ static int __init opal_init(void)
/* Create "opal" kobject under /sys/firmware */
rc = opal_sysfs_init();
if (rc == 0) {
+ /* Setup error log interface */
+ rc = opal_elog_init();
/* Setup code update interface */
opal_flash_init();
}
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH] mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS
From: Andrew Morton @ 2014-02-27 23:41 UTC (permalink / raw)
To: Aneesh Kumar K.V
Cc: Peter Zijlstra, Liu Ping Fan, linux-mm, Paul Mackerras,
linuxppc-dev
In-Reply-To: <87k3cifgzz.fsf@linux.vnet.ibm.com>
On Wed, 26 Feb 2014 13:22:16 +0530 "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> wrote:
> Andrew Morton <akpm@linux-foundation.org> writes:
>
> > On Wed, 5 Feb 2014 09:25:46 +0800 Liu Ping Fan <qemulist@gmail.com> wrote:
> >
> >> When doing some numa tests on powerpc, I triggered an oops bug. I find
> >> it is caused by using page->_last_cpupid. It should be initialized as
> >> "-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(),
> >> we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)).
> >> And finally cause an oops bug in task_numa_group(), since the online cpu is
> >> less than possible cpu.
> >
> > I grabbed this. I added this to the changelog:
> >
> > : PPC needs the LAST_CPUPID_NOT_IN_PAGE_FLAGS case because ppc needs to
> > : support a large physical address region, up to 2^46 but small section size
> > : (2^24). So when NR_CPUS grows up, it is easily to cause
> > : not-in-page-flags.
> >
> > to hopefully address Peter's observation.
> >
> > How should we proceed with this? I'm getting the impression that numa
> > balancing on ppc is a dead duck in 3.14, so perhaps this and
> >
> > powerpc-mm-add-new-set-flag-argument-to-pte-pmd-update-function.patch
> > mm-dirty-accountable-change-only-apply-to-non-prot-numa-case.patch
> > mm-use-ptep-pmdp_set_numa-for-updating-_page_numa-bit.patch
> >
>
> All these are already in 3.14 ?
Yes.
> > are 3.15-rc1 material?
> >
>
> We should push the first hunk to 3.14. I will wait for Liu to redo the
> patch. BTW this should happen only when SPARSE_VMEMMAP is not
> specified. Srikar had reported the issue here
>
> http://mid.gmane.org/20140219180200.GA29257@linux.vnet.ibm.com
>
> #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
> #define SECTIONS_WIDTH SECTIONS_SHIFT
> #else
> #define SECTIONS_WIDTH 0
> #endif
>
I'm lost. What patch are you talking about? The first hunk of what?
I assume we're talking about
mm-numa-bugfix-for-last_cpupid_not_in_page_flags.patch, which I had
queued for 3.14. I'll put it on hold until there's some clarity here.
^ permalink raw reply
* [PATCH v3 11/11] powerpc/perf/hv_{gpci, 24x7}: add documentation of device attributes
From: Cody P Schafer @ 2014-02-27 21:05 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Rob Landley, linux-doc, Peter Zijlstra, LKML, Michael Ellerman,
Ingo Molnar, Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
gpci and 24x7 expose some device specific attributes. Add some
documentation for them.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
.../testing/sysfs-bus-event_source-devices-hv_24x7 | 23 ++++++++++++
.../testing/sysfs-bus-event_source-devices-hv_gpci | 43 ++++++++++++++++++++++
2 files changed, 66 insertions(+)
create mode 100644 Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
create mode 100644 Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
new file mode 100644
index 0000000..e78ee79
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -0,0 +1,23 @@
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Provides access to the binary "24x7 catalog" provided by the
+ hypervisor on POWER7 and 8 systems. This catalog lists events
+ avaliable from the powerpc "hv_24x7" pmu. Its format is
+ documented here:
+ https://raw.githubusercontent.com/jmesmon/catalog-24x7/master/hv-24x7-catalog.h
+
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog_length
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number equal to the length in bytes of the catalog. This is
+ also extractable from the provided binary "catalog" sysfs entry.
+
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog_version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Exposes the "version" field of the 24x7 catalog. This is also
+ extractable from the provided binary "catalog" sysfs entry.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
new file mode 100644
index 0000000..3fa58c2
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
@@ -0,0 +1,43 @@
+What: /sys/bus/event_source/devices/hv_gpci/interface/collect_privileged
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ '0' if the hypervisor is configured to forbid access to event
+ counters being accumulated by other guests and to physical
+ domain event counters.
+ '1' if that access is allowed.
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/ga
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "GA" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/expanded
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "EXPANDED" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/lab
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "LAB" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number indicating the version of the gpci interface that the
+ hypervisor reports supporting.
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/kernel_version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number indicating the latest version of the gpci interface
+ that the kernel is aware of.
--
1.9.0
^ permalink raw reply related
* [PATCH v3 10/11] powerpc/perf: add kconfig option for hypervisor provided counters
From: Cody P Schafer @ 2014-02-27 21:05 UTC (permalink / raw)
To: Linux PPC, Anshuman Khandual, Benjamin Herrenschmidt,
Cody P Schafer, Deepthi Dharwar, Gavin Shan, Lijun Pan, Li Zhong,
Michael Ellerman, Paul Bolle, Priyanka Jain, Srivatsa S. Bhat
Cc: Peter Zijlstra, LKML, Ingo Molnar, Paul Mackerras,
Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/Makefile | 2 ++
arch/powerpc/platforms/pseries/Kconfig | 12 ++++++++++++
2 files changed, 14 insertions(+)
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 60d71ee..f9c083a 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -11,5 +11,7 @@ obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
+obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 80b1d57..2cb8b77 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -111,6 +111,18 @@ config CMM
will be reused for other LPARs. The interface allows firmware to
balance memory across many LPARs.
+config HV_PERF_CTRS
+ bool "Hypervisor supplied PMU events (24x7 & GPCI)"
+ default y
+ depends on PERF_EVENTS && PPC_PSERIES
+ help
+ Enable access to hypervisor supplied counters in perf. Currently,
+ this enables code that uses the hcall GetPerfCounterInfo and 24x7
+ interfaces to retrieve counters. GPCI exists on Power 6 and later
+ systems. 24x7 is available on Power 8 systems.
+
+ If unsure, select Y.
+
config DTL
bool "Dispatch Trace Log"
depends on PPC_SPLPAR && DEBUG_FS
--
1.9.0
^ permalink raw reply related
* [PATCH v3 09/11] powerpc/perf: add support for the hv 24x7 interface
From: Cody P Schafer @ 2014-02-27 21:05 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Peter Zijlstra, LKML, Michael Ellerman, Ingo Molnar,
Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
This provides a basic interface between hv_24x7 and perf. Similar to
the one provided for gpci, it lacks transaction support and does not
list any events.
Example usage via perf tool:
perf stat -e 'hv_24x7/domain=2,offset=8,starting_index=0,lpar=0xffffffff/' -r 0 -C 0 -x ' ' sleep 0.1
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-24x7.c | 492 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 492 insertions(+)
create mode 100644 arch/powerpc/perf/hv-24x7.c
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
new file mode 100644
index 0000000..c1847a3
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -0,0 +1,492 @@
+/*
+ * Hypervisor supplied "24x7" performance counter support
+ *
+ * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
+ * Copyright 2014 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "hv-24x7: " fmt
+
+#include <linux/perf_event.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/io.h>
+
+#include "hv-24x7.h"
+#include "hv-24x7-catalog.h"
+#include "hv-common.h"
+
+/*
+ * TODO: Merging events:
+ * - Think of the hcall as an interface to a 4d array of counters:
+ * - x = domains
+ * - y = indexes in the domain (core, chip, vcpu, node, etc)
+ * - z = offset into the counter space
+ * - w = lpars (guest vms, "logical partitions")
+ * - A single request is: x,y,y_last,z,z_last,w,w_last
+ * - this means we can retrieve a rectangle of counters in y,z for a single x.
+ *
+ * - Things to consider (ignoring w):
+ * - input cost_per_request = 16
+ * - output cost_per_result(ys,zs) = 8 + 8 * ys + ys * zs
+ * - limited number of requests per hcall (must fit into 4K bytes)
+ * - 4k = 16 [buffer header] - 16 [request size] * request_count
+ * - 255 requests per hcall
+ * - sometimes it will be more efficient to read extra data and discard
+ */
+
+PMU_FORMAT_RANGE(domain, config, 0, 3); /* u3 0-6, one of HV_24X7_PERF_DOMAIN */
+PMU_FORMAT_RANGE(starting_index, config, 16, 31); /* u16 */
+PMU_FORMAT_RANGE(offset, config, 32, 63); /* u32, see "data_offset" */
+PMU_FORMAT_RANGE(lpar, config1, 0, 15); /* u16 */
+
+PMU_FORMAT_RANGE_RESERVED(reserved1, config, 4, 15);
+PMU_FORMAT_RANGE_RESERVED(reserved2, config1, 16, 63);
+PMU_FORMAT_RANGE_RESERVED(reserved3, config2, 0, 63);
+
+static struct attribute *format_attrs[] = {
+ &format_attr_domain.attr,
+ &format_attr_offset.attr,
+ &format_attr_starting_index.attr,
+ &format_attr_lpar.attr,
+ NULL,
+};
+
+static struct attribute_group format_group = {
+ .name = "format",
+ .attrs = format_attrs,
+};
+
+/*
+ * read_offset_data - copy data from one buffer to another while treating the
+ * source buffer as a small view on the total avaliable
+ * source data.
+ *
+ * @dest: buffer to copy into
+ * @dest_len: length of @dest in bytes
+ * @requested_offset: the offset within the source data we want. Must be > 0
+ * @src: buffer to copy data from
+ * @src_len: length of @src in bytes
+ * @source_offset: the offset in the sorce data that (src,src_len) refers to.
+ * Must be > 0
+ *
+ * returns the number of bytes copied.
+ *
+ * The following ascii art shows the various buffer possitioning we need to
+ * handle, assigns some arbitrary varibles to points on the buffer, and then
+ * shows how we fiddle with those values to get things we care about (copy
+ * start in src and copy len)
+ *
+ * s = @src buffer
+ * d = @dest buffer
+ * '.' areas in d are written to.
+ *
+ * u
+ * x w v z
+ * d |.........|
+ * s |----------------------|
+ *
+ * u
+ * x w z v
+ * d |........------|
+ * s |------------------|
+ *
+ * x w u,z,v
+ * d |........|
+ * s |------------------|
+ *
+ * x,w u,v,z
+ * d |..................|
+ * s |------------------|
+ *
+ * x u
+ * w v z
+ * d |........|
+ * s |------------------|
+ *
+ * x z w v
+ * d |------|
+ * s |------|
+ *
+ * x = source_offset
+ * w = requested_offset
+ * z = source_offset + src_len
+ * v = requested_offset + dest_len
+ *
+ * w_offset_in_s = w - x = requested_offset - source_offset
+ * z_offset_in_s = z - x = src_len
+ * v_offset_in_s = v - x = request_offset + dest_len - src_len
+ */
+static ssize_t read_offset_data(void *dest, size_t dest_len,
+ loff_t requested_offset, void *src,
+ size_t src_len, loff_t source_offset)
+{
+ size_t w_offset_in_s = requested_offset - source_offset;
+ size_t z_offset_in_s = src_len;
+ size_t v_offset_in_s = requested_offset + dest_len - src_len;
+ size_t u_offset_in_s = min(z_offset_in_s, v_offset_in_s);
+ size_t copy_len = u_offset_in_s - w_offset_in_s;
+
+ if (requested_offset < 0 || source_offset < 0)
+ return -EINVAL;
+
+ if (z_offset_in_s <= w_offset_in_s)
+ return 0;
+
+ memcpy(dest, src + w_offset_in_s, copy_len);
+ return copy_len;
+}
+
+static unsigned long h_get_24x7_catalog_page(char page[static 4096],
+ u32 version, u32 index)
+{
+ WARN_ON(!IS_ALIGNED((unsigned long)page, 4096));
+ return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE,
+ virt_to_phys(page),
+ version,
+ index);
+}
+
+static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf,
+ loff_t offset, size_t count)
+{
+ unsigned long hret;
+ ssize_t ret = 0;
+ size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
+ loff_t page_offset = 0;
+ uint32_t catalog_version_num = 0;
+ void *page = kmalloc(4096, GFP_USER);
+ struct hv_24x7_catalog_page_0 *page_0 = page;
+ if (!page)
+ return -ENOMEM;
+
+
+ hret = h_get_24x7_catalog_page(page, 0, 0);
+ if (hret) {
+ ret = -EIO;
+ goto e_free;
+ }
+
+ catalog_version_num = be32_to_cpu(page_0->version);
+ catalog_page_len = be32_to_cpu(page_0->length);
+ catalog_len = catalog_page_len * 4096;
+
+ page_offset = offset / 4096;
+ page_count = count / 4096;
+
+ if (page_offset >= catalog_page_len)
+ goto e_free;
+
+ if (page_offset != 0) {
+ hret = h_get_24x7_catalog_page(page, catalog_version_num,
+ page_offset);
+ if (hret) {
+ ret = -EIO;
+ goto e_free;
+ }
+ }
+
+ ret = read_offset_data(buf, count, offset,
+ page, 4096, page_offset * 4096);
+e_free:
+ if (hret)
+ pr_err("h_get_24x7_catalog_page(ver=%d, page=%lld) failed: rc=%ld\n",
+ catalog_version_num, page_offset, hret);
+ kfree(page);
+
+ pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n",
+ offset, page_offset, count, page_count, catalog_len,
+ catalog_page_len, ret);
+
+ return ret;
+}
+
+#define PAGE_0_ATTR(_name, _fmt, _expr) \
+static ssize_t _name##_show(struct device *dev, \
+ struct device_attribute *dev_attr, \
+ char *buf) \
+{ \
+ unsigned long hret; \
+ ssize_t ret = 0; \
+ void *page = kmalloc(4096, GFP_USER); \
+ struct hv_24x7_catalog_page_0 *page_0 = page; \
+ if (!page) \
+ return -ENOMEM; \
+ hret = h_get_24x7_catalog_page(page, 0, 0); \
+ if (hret) { \
+ ret = -EIO; \
+ goto e_free; \
+ } \
+ ret = sprintf(buf, _fmt, _expr); \
+e_free: \
+ kfree(page); \
+ return ret; \
+} \
+static DEVICE_ATTR_RO(_name)
+
+PAGE_0_ATTR(catalog_version, "%lld\n",
+ (unsigned long long)be32_to_cpu(page_0->version));
+PAGE_0_ATTR(catalog_len, "%lld\n",
+ (unsigned long long)be32_to_cpu(page_0->length) * 4096);
+static BIN_ATTR_RO(catalog, 0/* real length varies */);
+
+static struct bin_attribute *if_bin_attrs[] = {
+ &bin_attr_catalog,
+ NULL,
+};
+
+static struct attribute *if_attrs[] = {
+ &dev_attr_catalog_len.attr,
+ &dev_attr_catalog_version.attr,
+ NULL,
+};
+
+static struct attribute_group if_group = {
+ .name = "interface",
+ .bin_attrs = if_bin_attrs,
+ .attrs = if_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+ &format_group,
+ &if_group,
+ NULL,
+};
+
+static bool is_physical_domain(int domain)
+{
+ return domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP ||
+ domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
+}
+
+static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
+ u16 lpar, u64 *res,
+ bool success_expected)
+{
+ unsigned long ret;
+
+ /*
+ * request_buffer and result_buffer are not required to be 4k aligned,
+ * but are not allowed to cross any 4k boundary. Aligning them to 4k is
+ * the simplest way to ensure that.
+ */
+ struct reqb {
+ struct hv_24x7_request_buffer buf;
+ struct hv_24x7_request req;
+ } __packed __aligned(4096) request_buffer = {
+ .buf = {
+ .interface_version = HV_24X7_IF_VERSION_CURRENT,
+ .num_requests = 1,
+ },
+ .req = {
+ .performance_domain = domain,
+ .data_size = cpu_to_be16(8),
+ .data_offset = cpu_to_be32(offset),
+ .starting_lpar_ix = cpu_to_be16(lpar),
+ .max_num_lpars = cpu_to_be16(1),
+ .starting_ix = cpu_to_be16(ix),
+ .max_ix = cpu_to_be16(1),
+ }
+ };
+
+ struct resb {
+ struct hv_24x7_data_result_buffer buf;
+ struct hv_24x7_result res;
+ struct hv_24x7_result_element elem;
+ __be64 result;
+ } __packed __aligned(4096) result_buffer = {};
+
+ ret = plpar_hcall_norets(H_GET_24X7_DATA,
+ virt_to_phys(&request_buffer), sizeof(request_buffer),
+ virt_to_phys(&result_buffer), sizeof(result_buffer));
+
+ if (ret) {
+ if (success_expected)
+ pr_err_ratelimited("hcall failed: %d %#x %#x %d => 0x%lx (%ld) detail=0x%x failing ix=%x\n",
+ domain, offset, ix, lpar,
+ ret, ret,
+ result_buffer.buf.detailed_rc,
+ result_buffer.buf.failing_request_ix);
+ return ret;
+ }
+
+ *res = be64_to_cpu(result_buffer.result);
+ return ret;
+}
+
+static unsigned long event_24x7_request(struct perf_event *event, u64 *res,
+ bool success_expected)
+{
+ return single_24x7_request(event_get_domain(event),
+ event_get_offset(event),
+ event_get_starting_index(event),
+ event_get_lpar(event),
+ res,
+ success_expected);
+}
+
+static int h_24x7_event_init(struct perf_event *event)
+{
+ struct hv_perf_caps caps;
+ unsigned domain;
+ unsigned long hret;
+ u64 ct;
+
+ /* Not our event */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* Unused areas must be 0 */
+ if (event_get_reserved1(event) ||
+ event_get_reserved2(event) ||
+ event_get_reserved3(event)) {
+ pr_devel("reserved set when forbidden 0x%llx(0x%llx) 0x%llx(0x%llx) 0x%llx(0x%llx)\n",
+ event->attr.config,
+ event_get_reserved1(event),
+ event->attr.config1,
+ event_get_reserved2(event),
+ event->attr.config2,
+ event_get_reserved3(event));
+ return -EINVAL;
+ }
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ is_sampling_event(event)) /* no sampling */
+ return -EINVAL;
+
+ /* no branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ /* offset must be 8 byte aligned */
+ if (event_get_offset(event) % 8) {
+ pr_devel("bad alignment\n");
+ return -EINVAL;
+ }
+
+ /* Domains above 6 are invalid */
+ domain = event_get_domain(event);
+ if (domain > 6) {
+ pr_devel("invalid domain %d\n", domain);
+ return -EINVAL;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_devel("could not get capabilities: rc=%ld\n", hret);
+ return -EIO;
+ }
+
+ /* PHYSICAL domains & other lpars require extra capabilities */
+ if (!caps.collect_privileged && (is_physical_domain(domain) ||
+ (event_get_lpar(event) != event_get_lpar_max()))) {
+ pr_devel("hv permisions disallow: is_physical_domain:%d, lpar=0x%llx\n",
+ is_physical_domain(domain),
+ event_get_lpar(event));
+ return -EACCES;
+ }
+
+ /* see if the event complains */
+ if (event_24x7_request(event, &ct, false)) {
+ pr_devel("test hcall failed\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static u64 h_24x7_get_value(struct perf_event *event)
+{
+ unsigned long ret;
+ u64 ct;
+ ret = event_24x7_request(event, &ct, true);
+ if (ret)
+ /* We checked this in event init, shouldn't fail here... */
+ return 0;
+
+ return ct;
+}
+
+static void h_24x7_event_update(struct perf_event *event)
+{
+ s64 prev;
+ u64 now;
+ now = h_24x7_get_value(event);
+ prev = local64_xchg(&event->hw.prev_count, now);
+ local64_add(now - prev, &event->count);
+}
+
+static void h_24x7_event_start(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_RELOAD)
+ local64_set(&event->hw.prev_count, h_24x7_get_value(event));
+}
+
+static void h_24x7_event_stop(struct perf_event *event, int flags)
+{
+ h_24x7_event_update(event);
+}
+
+static int h_24x7_event_add(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_START)
+ h_24x7_event_start(event, flags);
+
+ return 0;
+}
+
+static struct pmu h_24x7_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+
+ .name = "hv_24x7",
+ .attr_groups = attr_groups,
+ .event_init = h_24x7_event_init,
+ .add = h_24x7_event_add,
+ .del = h_24x7_event_stop,
+ .start = h_24x7_event_start,
+ .stop = h_24x7_event_stop,
+ .read = h_24x7_event_update,
+
+ .event_idx = perf_event_nop_0,
+};
+
+static int hv_24x7_init(void)
+{
+ int r;
+ unsigned long hret;
+ struct hv_perf_caps caps;
+
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ pr_info("not a virtualized system, not enabling\n");
+ return -ENODEV;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+ hret);
+ return -ENODEV;
+ }
+
+ r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+device_initcall(hv_24x7_init);
--
1.9.0
^ permalink raw reply related
* [PATCH v3 08/11] powerpc/perf: add support for the hv gpci (get performance counter info) interface
From: Cody P Schafer @ 2014-02-27 21:05 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Peter Zijlstra, LKML, Michael Ellerman, Ingo Molnar,
Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
This provides a basic link between perf and hv_gpci. Notably, it does
not yet support transactions and does not list any events (they can
still be manually composed).
Example usage via perf tool:
perf stat -e 'hv_gpci/counter_info_version=3,offset=0,length=8,secondary_index=0,starting_index=0xffffffff,request=0x10/' -r 0 -C 0 -x ' ' sleep 0.1
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-gpci.c | 277 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 277 insertions(+)
create mode 100644 arch/powerpc/perf/hv-gpci.c
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
new file mode 100644
index 0000000..2f64732
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -0,0 +1,277 @@
+/*
+ * Hypervisor supplied "gpci" ("get performance counter info") performance
+ * counter support
+ *
+ * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
+ * Copyright 2014 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#define pr_fmt(fmt) "hv-gpci: " fmt
+
+#include <linux/init.h>
+#include <linux/perf_event.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/io.h>
+
+#include "hv-gpci.h"
+#include "hv-common.h"
+
+PMU_FORMAT_RANGE(request, config, 0, 31); /* u32 */
+PMU_FORMAT_RANGE(starting_index, config, 32, 63); /* u32 */
+PMU_FORMAT_RANGE(secondary_index, config1, 0, 15); /* u16 */
+PMU_FORMAT_RANGE(counter_info_version, config1, 16, 23); /* u8 */
+PMU_FORMAT_RANGE(length, config1, 24, 31); /* u8, bytes of data (1-8) */
+PMU_FORMAT_RANGE(offset, config1, 32, 63); /* u32, byte offset */
+
+static struct attribute *format_attrs[] = {
+ &format_attr_request.attr,
+ &format_attr_starting_index.attr,
+ &format_attr_secondary_index.attr,
+ &format_attr_counter_info_version.attr,
+
+ &format_attr_offset.attr,
+ &format_attr_length.attr,
+ NULL,
+};
+
+static struct attribute_group format_group = {
+ .name = "format",
+ .attrs = format_attrs,
+};
+
+#define HV_CAPS_ATTR(_name, _format) \
+static ssize_t _name##_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *page) \
+{ \
+ struct hv_perf_caps caps; \
+ unsigned long hret = hv_perf_caps_get(&caps); \
+ if (hret) \
+ return -EIO; \
+ \
+ return sprintf(page, _format, caps._name); \
+} \
+static struct device_attribute hv_caps_attr_##_name = __ATTR_RO(_name)
+
+static ssize_t kernel_version_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
+}
+
+DEVICE_ATTR_RO(kernel_version);
+HV_CAPS_ATTR(version, "0x%x\n");
+HV_CAPS_ATTR(ga, "%d\n");
+HV_CAPS_ATTR(expanded, "%d\n");
+HV_CAPS_ATTR(lab, "%d\n");
+HV_CAPS_ATTR(collect_privileged, "%d\n");
+
+static struct attribute *interface_attrs[] = {
+ &dev_attr_kernel_version.attr,
+ &hv_caps_attr_version.attr,
+ &hv_caps_attr_ga.attr,
+ &hv_caps_attr_expanded.attr,
+ &hv_caps_attr_lab.attr,
+ &hv_caps_attr_collect_privileged.attr,
+ NULL,
+};
+
+static struct attribute_group interface_group = {
+ .name = "interface",
+ .attrs = interface_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+ &format_group,
+ &interface_group,
+ NULL,
+};
+
+#define GPCI_MAX_DATA_BYTES \
+ (1024 - sizeof(struct hv_get_perf_counter_info_params))
+
+static unsigned long single_gpci_request(u32 req, u32 starting_index,
+ u16 secondary_index, u8 version_in, u32 offset, u8 length,
+ u64 *value)
+{
+ unsigned long ret;
+ size_t i;
+ u64 count;
+
+ struct {
+ struct hv_get_perf_counter_info_params params;
+ uint8_t bytes[GPCI_MAX_DATA_BYTES];
+ } __packed __aligned(sizeof(uint64_t)) arg = {
+ .params = {
+ .counter_request = cpu_to_be32(req),
+ .starting_index = cpu_to_be32(starting_index),
+ .secondary_index = cpu_to_be16(secondary_index),
+ .counter_info_version_in = version_in,
+ }
+ };
+
+ ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+ virt_to_phys(&arg), sizeof(arg));
+ if (ret) {
+ pr_devel("hcall failed: 0x%lx\n", ret);
+ return ret;
+ }
+
+ /*
+ * we verify offset and length are within the zeroed buffer at event
+ * init.
+ */
+ count = 0;
+ for (i = offset; i < offset + length; i++)
+ count |= arg.bytes[i] << (i - offset);
+
+ *value = count;
+ return ret;
+}
+
+static u64 h_gpci_get_value(struct perf_event *event)
+{
+ u64 count;
+ unsigned long ret = single_gpci_request(event_get_request(event),
+ event_get_starting_index(event),
+ event_get_secondary_index(event),
+ event_get_counter_info_version(event),
+ event_get_offset(event),
+ event_get_length(event),
+ &count);
+ if (ret)
+ return 0;
+ return count;
+}
+
+static void h_gpci_event_update(struct perf_event *event)
+{
+ s64 prev;
+ u64 now = h_gpci_get_value(event);
+ prev = local64_xchg(&event->hw.prev_count, now);
+ local64_add(now - prev, &event->count);
+}
+
+static void h_gpci_event_start(struct perf_event *event, int flags)
+{
+ local64_set(&event->hw.prev_count, h_gpci_get_value(event));
+}
+
+static void h_gpci_event_stop(struct perf_event *event, int flags)
+{
+ h_gpci_event_update(event);
+}
+
+static int h_gpci_event_add(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_START)
+ h_gpci_event_start(event, flags);
+
+ return 0;
+}
+
+static int h_gpci_event_init(struct perf_event *event)
+{
+ u64 count;
+ u8 length;
+
+ /* Not our event */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* config2 is unused */
+ if (event->attr.config2) {
+ pr_devel("config2 set when reserved\n");
+ return -EINVAL;
+ }
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ is_sampling_event(event)) /* no sampling */
+ return -EINVAL;
+
+ /* no branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ length = event_get_length(event);
+ if (length < 1 || length > 8) {
+ pr_devel("length invalid\n");
+ return -EINVAL;
+ }
+
+ /* last byte within the buffer? */
+ if ((event_get_offset(event) + length) > GPCI_MAX_DATA_BYTES) {
+ pr_devel("request outside of buffer: %zu > %zu\n",
+ (size_t)event_get_offset(event) + length,
+ GPCI_MAX_DATA_BYTES);
+ return -EINVAL;
+ }
+
+ /* check if the request works... */
+ if (single_gpci_request(event_get_request(event),
+ event_get_starting_index(event),
+ event_get_secondary_index(event),
+ event_get_counter_info_version(event),
+ event_get_offset(event),
+ length,
+ &count)) {
+ pr_devel("gpci hcall failed\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct pmu h_gpci_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+
+ .name = "hv_gpci",
+ .attr_groups = attr_groups,
+ .event_init = h_gpci_event_init,
+ .add = h_gpci_event_add,
+ .del = h_gpci_event_stop,
+ .start = h_gpci_event_start,
+ .stop = h_gpci_event_stop,
+ .read = h_gpci_event_update,
+
+ .event_idx = perf_event_nop_0,
+};
+
+static int hv_gpci_init(void)
+{
+ int r;
+ unsigned long hret;
+ struct hv_perf_caps caps;
+
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ pr_info("not a virtualized system, not enabling\n");
+ return -ENODEV;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+ hret);
+ return -ENODEV;
+ }
+
+ r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+device_initcall(hv_gpci_init);
--
1.9.0
^ permalink raw reply related
* [PATCH v3 07/11] powerpc/perf: add a shared interface to get gpci version and capabilities
From: Cody P Schafer @ 2014-02-27 21:05 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Peter Zijlstra, LKML, Michael Ellerman, Ingo Molnar,
Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
This exposes a simple way to grab the firmware provided
collect_priveliged, ga, expanded, and lab capability bits. All of these
bits come in from the same gpci request, so we've exposed all of them.
Only the collect_priveliged bit is really used by the hv-gpci/hv-24x7
code, the other bits are simply exposed in sysfs to inform the user.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-common.c | 39 +++++++++++++++++++++++++++++++++++++++
arch/powerpc/perf/hv-common.h | 17 +++++++++++++++++
2 files changed, 56 insertions(+)
create mode 100644 arch/powerpc/perf/hv-common.c
create mode 100644 arch/powerpc/perf/hv-common.h
diff --git a/arch/powerpc/perf/hv-common.c b/arch/powerpc/perf/hv-common.c
new file mode 100644
index 0000000..47e02b3
--- /dev/null
+++ b/arch/powerpc/perf/hv-common.c
@@ -0,0 +1,39 @@
+#include <asm/io.h>
+#include <asm/hvcall.h>
+
+#include "hv-gpci.h"
+#include "hv-common.h"
+
+unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
+{
+ unsigned long r;
+ struct p {
+ struct hv_get_perf_counter_info_params params;
+ struct cv_system_performance_capabilities caps;
+ } __packed __aligned(sizeof(uint64_t));
+
+ struct p arg = {
+ .params = {
+ .counter_request = cpu_to_be32(
+ CIR_SYSTEM_PERFORMANCE_CAPABILITIES),
+ .starting_index = cpu_to_be32(-1),
+ .counter_info_version_in = 0,
+ }
+ };
+
+ r = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+ virt_to_phys(&arg), sizeof(arg));
+
+ if (r)
+ return r;
+
+ pr_devel("capability_mask: 0x%x\n", arg.caps.capability_mask);
+
+ caps->version = arg.params.counter_info_version_out;
+ caps->collect_privileged = !!arg.caps.perf_collect_privileged;
+ caps->ga = !!(arg.caps.capability_mask & CV_CM_GA);
+ caps->expanded = !!(arg.caps.capability_mask & CV_CM_EXPANDED);
+ caps->lab = !!(arg.caps.capability_mask & CV_CM_LAB);
+
+ return r;
+}
diff --git a/arch/powerpc/perf/hv-common.h b/arch/powerpc/perf/hv-common.h
new file mode 100644
index 0000000..7e615bd
--- /dev/null
+++ b/arch/powerpc/perf/hv-common.h
@@ -0,0 +1,17 @@
+#ifndef LINUX_POWERPC_PERF_HV_COMMON_H_
+#define LINUX_POWERPC_PERF_HV_COMMON_H_
+
+#include <linux/types.h>
+
+struct hv_perf_caps {
+ u16 version;
+ u16 collect_privileged:1,
+ ga:1,
+ expanded:1,
+ lab:1,
+ unused:12;
+};
+
+unsigned long hv_perf_caps_get(struct hv_perf_caps *caps);
+
+#endif
--
1.9.0
^ permalink raw reply related
* [PATCH v3 06/11] powerpc/perf: add 24x7 interface headers
From: Cody P Schafer @ 2014-02-27 21:04 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Peter Zijlstra, LKML, Michael Ellerman, Ingo Molnar,
Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
24x7 (also called hv_24x7 or H_24X7) is an interface to obtain
performance counters from the hypervisor. These counters do not have a
fixed format/possition and are instead documented in a "24x7 Catalog",
which is provided by the hypervisor (that interface is also documented
paritialy in the included hv-24x7-catalog.h and fully in at
https://raw.githubusercontent.com/jmesmon/catalog-24x7/master/hv-24x7-catalog.h ).
The 24x7 data access is simply a copy operation into a 4 dimentional
array of 64bit counters (from hypervisor to kernel memory). There is no
interupt triggered on overflow, these are completely disjoint from the
typical power pmu.
This method of obtaining performance counters from the hypervisor is
intended to paritialy replace the gpci interface.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-24x7-catalog.h | 33 +++++++++++
arch/powerpc/perf/hv-24x7.h | 109 ++++++++++++++++++++++++++++++++++++
2 files changed, 142 insertions(+)
create mode 100644 arch/powerpc/perf/hv-24x7-catalog.h
create mode 100644 arch/powerpc/perf/hv-24x7.h
diff --git a/arch/powerpc/perf/hv-24x7-catalog.h b/arch/powerpc/perf/hv-24x7-catalog.h
new file mode 100644
index 0000000..21b19dd
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7-catalog.h
@@ -0,0 +1,33 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+#define LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+
+#include <linux/types.h>
+
+/* From document "24x7 Event and Group Catalog Formats Proposal" v0.15 */
+
+struct hv_24x7_catalog_page_0 {
+#define HV_24X7_CATALOG_MAGIC 0x32347837 /* "24x7" in ASCII */
+ __be32 magic;
+ __be32 length; /* In 4096 byte pages */
+ __be64 version; /* XXX: arbitrary? what's the meaning/useage/purpose? */
+ __u8 build_time_stamp[16]; /* "YYYYMMDDHHMMSS\0\0" */
+ __u8 reserved2[32];
+ __be16 schema_data_offs; /* in 4096 byte pages */
+ __be16 schema_data_len; /* in 4096 byte pages */
+ __be16 schema_entry_count;
+ __u8 reserved3[2];
+ __be16 event_data_offs;
+ __be16 event_data_len;
+ __be16 event_entry_count;
+ __u8 reserved4[2];
+ __be16 group_data_offs; /* in 4096 byte pages */
+ __be16 group_data_len; /* in 4096 byte pages */
+ __be16 group_entry_count;
+ __u8 reserved5[2];
+ __be16 formula_data_offs; /* in 4096 byte pages */
+ __be16 formula_data_len; /* in 4096 byte pages */
+ __be16 formula_entry_count;
+ __u8 reserved6[2];
+} __packed;
+
+#endif
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
new file mode 100644
index 0000000..720ebce
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -0,0 +1,109 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_H_
+#define LINUX_POWERPC_PERF_HV_24X7_H_
+
+#include <linux/types.h>
+
+struct hv_24x7_request {
+ /* PHYSICAL domains require enabling via phyp/hmc. */
+#define HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP 0x01
+#define HV_24X7_PERF_DOMAIN_PHYSICAL_CORE 0x02
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CORE 0x03
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CHIP 0x04
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_NODE 0x05
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_REMOTE_NODE 0x06
+ __u8 performance_domain;
+ __u8 reserved[0x1];
+
+ /* bytes to read starting at @data_offset. must be a multiple of 8 */
+ __be16 data_size;
+
+ /*
+ * byte offset within the perf domain to read from. must be 8 byte
+ * aligned
+ */
+ __be32 data_offset;
+
+ /*
+ * only valid for VIRTUAL_PROCESSOR domains, ignored for others.
+ * -1 means "current partition only"
+ * Enabling via phyp/hmc required for non-"-1" values. 0 forbidden
+ * unless requestor is 0.
+ */
+ __be16 starting_lpar_ix;
+
+ /*
+ * Ignored when @starting_lpar_ix == -1
+ * Ignored when @performance_domain is not VIRTUAL_PROCESSOR_*
+ * -1 means "infinite" or all
+ */
+ __be16 max_num_lpars;
+
+ /* chip, core, or virtual processor based on @performance_domain */
+ __be16 starting_ix;
+ __be16 max_ix;
+} __packed;
+
+struct hv_24x7_request_buffer {
+ /* 0 - ? */
+ /* 1 - ? */
+#define HV_24X7_IF_VERSION_CURRENT 0x01
+ __u8 interface_version;
+ __u8 num_requests;
+ __u8 reserved[0xE];
+ struct hv_24x7_request requests[];
+} __packed;
+
+struct hv_24x7_result_element {
+ __be16 lpar_ix;
+
+ /*
+ * represents the core, chip, or virtual processor based on the
+ * request's @performance_domain
+ */
+ __be16 domain_ix;
+
+ /* -1 if @performance_domain does not refer to a virtual processor */
+ __be32 lpar_cfg_instance_id;
+
+ /* size = @result_element_data_size of cointaining result. */
+ __u8 element_data[];
+} __packed;
+
+struct hv_24x7_result {
+ __u8 result_ix;
+
+ /*
+ * 0 = not all result elements fit into the buffer, additional requests
+ * required
+ * 1 = all result elements were returned
+ */
+ __u8 results_complete;
+ __be16 num_elements_returned;
+
+ /* This is a copy of @data_size from the coresponding hv_24x7_request */
+ __be16 result_element_data_size;
+ __u8 reserved[0x2];
+
+ /* WARNING: only valid for first result element due to variable sizes
+ * of result elements */
+ /* struct hv_24x7_result_element[@num_elements_returned] */
+ struct hv_24x7_result_element elements[];
+} __packed;
+
+struct hv_24x7_data_result_buffer {
+ /* See versioning for request buffer */
+ __u8 interface_version;
+
+ __u8 num_results;
+ __u8 reserved[0x1];
+ __u8 failing_request_ix;
+ __be32 detailed_rc;
+ __be64 cec_cfg_instance_id;
+ __be64 catalog_version_num;
+ __u8 reserved2[0x8];
+ /* WARNING: only valid for the first result due to variable sizes of
+ * results */
+ struct hv_24x7_result results[]; /* [@num_results] */
+} __packed;
+
+#endif
--
1.9.0
^ permalink raw reply related
* [PATCH v3 05/11] powerpc/perf: add hv_gpci interface header
From: Cody P Schafer @ 2014-02-27 21:04 UTC (permalink / raw)
To: Linux PPC, Cody P Schafer
Cc: Peter Zijlstra, LKML, Michael Ellerman, Ingo Molnar,
Paul Mackerras, Arnaldo Carvalho de Melo, scottwood
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
"H_GetPerformanceCounterInfo" (refered to as hv_gpci or just gpci from
here on) is an interface to retrieve specific performance counters and
other data from the hypervisor. All outputs have a fixed format. This
header only describes the portions of the interface that we plan on
using in linux at this time.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-gpci.h | 73 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 73 insertions(+)
create mode 100644 arch/powerpc/perf/hv-gpci.h
diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h
new file mode 100644
index 0000000..b25f460
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci.h
@@ -0,0 +1,73 @@
+#ifndef LINUX_POWERPC_PERF_HV_GPCI_H_
+#define LINUX_POWERPC_PERF_HV_GPCI_H_
+
+#include <linux/types.h>
+
+/* From the document "H_GetPerformanceCounterInfo Interface" v1.07 */
+
+/* H_GET_PERF_COUNTER_INFO argument */
+struct hv_get_perf_counter_info_params {
+ __be32 counter_request; /* I */
+ __be32 starting_index; /* IO */
+ __be16 secondary_index; /* IO */
+ __be16 returned_values; /* O */
+ __be32 detail_rc; /* O, only needed when called via *_norets() */
+
+ /*
+ * O, size each of counter_value element in bytes, only set for version
+ * >= 0x3
+ */
+ __be16 cv_element_size;
+
+ /* I, 0 (zero) for versions < 0x3 */
+ __u8 counter_info_version_in;
+
+ /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */
+ __u8 counter_info_version_out;
+ __u8 reserved[0xC];
+ __u8 counter_value[];
+} __packed;
+
+/*
+ * counter info version => fw version/reference (spec version)
+ *
+ * 8 => power8 (1.07)
+ * [7 is skipped by spec 1.07]
+ * 6 => TLBIE (1.07)
+ * 5 => v7r7m0.phyp (1.05)
+ * [4 skipped]
+ * 3 => v7r6m0.phyp (?)
+ * [1,2 skipped]
+ * 0 => v7r{2,3,4}m0.phyp (?)
+ */
+#define COUNTER_INFO_VERSION_CURRENT 0x8
+
+/*
+ * These determine the counter_value[] layout and the meaning of starting_index
+ * and secondary_index.
+ *
+ * Unless otherwise noted, @secondary_index is unused and ignored.
+ */
+enum counter_info_requests {
+
+ /* GENERAL */
+
+ /* @starting_index: must be -1 (to refer to the current partition)
+ */
+ CIR_SYSTEM_PERFORMANCE_CAPABILITIES = 0X40,
+};
+
+struct cv_system_performance_capabilities {
+ /* If != 0, allowed to collect data from other partitions */
+ __u8 perf_collect_privileged;
+
+ /* These following are only valid if counter_info_version >= 0x3 */
+#define CV_CM_GA (1 << 7)
+#define CV_CM_EXPANDED (1 << 6)
+#define CV_CM_LAB (1 << 5)
+ /* remaining bits are reserved */
+ __u8 capability_mask;
+ __u8 reserved[0xE];
+} __packed;
+
+#endif
--
1.9.0
^ permalink raw reply related
* [PATCH v3 02/11] perf: add PMU_FORMAT_RANGE() helper for use by sw-like pmus
From: Cody P Schafer @ 2014-02-27 21:04 UTC (permalink / raw)
To: Linux PPC, Arnaldo Carvalho de Melo, Ingo Molnar, Paul Mackerras,
Peter Zijlstra
Cc: Peter Zijlstra, LKML, Michael Ellerman, scottwood, Cody P Schafer
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
Add PMU_FORMAT_RANGE() and PMU_FORMAT_RANGE_RESERVED() (for reserved
areas) which generate functions to extract the relevent bits from
event->attr.config{,1,2} for use by sw-like pmus where the
'config{,1,2}' values don't map directly to hardware registers.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
include/linux/perf_event.h | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e56b07f..3da5081 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -871,4 +871,21 @@ _name##_show(struct device *dev, \
\
static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
+#define PMU_FORMAT_RANGE(name, attr_var, bit_start, bit_end) \
+PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end); \
+PMU_FORMAT_RANGE_RESERVED(name, attr_var, bit_start, bit_end)
+
+#define PMU_FORMAT_RANGE_RESERVED(name, attr_var, bit_start, bit_end) \
+static u64 event_get_##name##_max(void) \
+{ \
+ int bits = (bit_end) - (bit_start) + 1; \
+ return ((0x1ULL << (bits - 1ULL)) - 1ULL) | \
+ (0xFULL << (bits - 4ULL)); \
+} \
+static u64 event_get_##name(struct perf_event *event) \
+{ \
+ return (event->attr.attr_var >> (bit_start)) & \
+ event_get_##name##_max(); \
+}
+
#endif /* _LINUX_PERF_EVENT_H */
--
1.9.0
^ permalink raw reply related
* [PATCH v3 03/11] perf: provide a common perf_event_nop_0() for use with .event_idx
From: Cody P Schafer @ 2014-02-27 21:04 UTC (permalink / raw)
To: Linux PPC, Arnaldo Carvalho de Melo, Ingo Molnar, Paul Mackerras,
Peter Zijlstra
Cc: Peter Zijlstra, LKML, Michael Ellerman, scottwood, Cody P Schafer
In-Reply-To: <1393535105-7528-1-git-send-email-cody@linux.vnet.ibm.com>
Rather an having every pmu that needs a function that just returns 0 for
.event_idx define their own copy, reuse the one in kernel/events/core.c.
Rename from perf_swevent_event_idx() because we're no longer using it
for just software events. Naming is based on the perf_pmu_nop_*()
functions.
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
include/linux/perf_event.h | 1 +
kernel/events/core.c | 10 +++++-----
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3da5081..24a7b45 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -560,6 +560,7 @@ extern void perf_pmu_migrate_context(struct pmu *pmu,
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
+extern int perf_event_nop_0(struct perf_event *event);
struct perf_sample_data {
u64 type;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..2938a77 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5816,7 +5816,7 @@ static int perf_swevent_init(struct perf_event *event)
return 0;
}
-static int perf_swevent_event_idx(struct perf_event *event)
+int perf_event_nop_0(struct perf_event *event)
{
return 0;
}
@@ -5831,7 +5831,7 @@ static struct pmu perf_swevent = {
.stop = perf_swevent_stop,
.read = perf_swevent_read,
- .event_idx = perf_swevent_event_idx,
+ .event_idx = perf_event_nop_0,
};
#ifdef CONFIG_EVENT_TRACING
@@ -5950,7 +5950,7 @@ static struct pmu perf_tracepoint = {
.stop = perf_swevent_stop,
.read = perf_swevent_read,
- .event_idx = perf_swevent_event_idx,
+ .event_idx = perf_event_nop_0,
};
static inline void perf_tp_register(void)
@@ -6177,7 +6177,7 @@ static struct pmu perf_cpu_clock = {
.stop = cpu_clock_event_stop,
.read = cpu_clock_event_read,
- .event_idx = perf_swevent_event_idx,
+ .event_idx = perf_event_nop_0,
};
/*
@@ -6257,7 +6257,7 @@ static struct pmu perf_task_clock = {
.stop = task_clock_event_stop,
.read = task_clock_event_read,
- .event_idx = perf_swevent_event_idx,
+ .event_idx = perf_event_nop_0,
};
static void perf_pmu_nop_void(struct pmu *pmu)
--
1.9.0
^ permalink raw reply related
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