* [PATCH 3/3] rheap: move rheap.c from arch/powerpc/lib/ to lib/
From: Zhao Qiang @ 2014-09-25 2:47 UTC (permalink / raw)
To: linuxppc-dev, linux-kernel, B07421; +Cc: Zhao Qiang, R63061
In-Reply-To: <1411613237-2271-1-git-send-email-B45475@freescale.com>
qe need to use the rheap, so move it to public directory.
Signed-off-by: Zhao Qiang <B45475@freescale.com>
---
arch/powerpc/Kconfig | 3 ---
arch/powerpc/include/asm/fsl_85xx_cache_sram.h | 2 +-
arch/powerpc/lib/Makefile | 2 --
arch/powerpc/platforms/44x/Kconfig | 2 +-
arch/powerpc/platforms/85xx/Kconfig | 2 +-
arch/powerpc/platforms/Kconfig | 2 +-
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/powerpc/sysdev/cpm1.c | 2 +-
arch/powerpc/sysdev/cpm2.c | 2 +-
arch/powerpc/sysdev/cpm_common.c | 2 +-
arch/powerpc/sysdev/ppc4xx_ocm.c | 2 +-
drivers/dma/bestcomm/Kconfig | 2 +-
drivers/soc/qe/Kconfig | 2 +-
drivers/soc/qe/qe.c | 2 +-
drivers/soc/qe/qe_common.c | 2 +-
drivers/video/Kconfig | 2 +-
include/linux/fsl/bestcomm/sram.h | 2 +-
{arch/powerpc/include/asm => include/linux/fsl}/rheap.h | 0
lib/Kconfig | 3 +++
lib/Makefile | 2 ++
{arch/powerpc/lib => lib}/rheap.c | 2 +-
21 files changed, 21 insertions(+), 21 deletions(-)
rename {arch/powerpc/include/asm => include/linux/fsl}/rheap.h (100%)
rename {arch/powerpc/lib => lib}/rheap.c (99%)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d20dc2b..18b658e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1046,7 +1046,4 @@ config PPC_CLOCK
default n
select HAVE_CLK
-config PPC_LIB_RHEAP
- bool
-
source "arch/powerpc/kvm/Kconfig"
diff --git a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
index 2af2bdc..e57888a 100644
--- a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
+++ b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
@@ -26,7 +26,7 @@
#ifndef __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__
#define __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <linux/spinlock.h>
/*
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 4504332..c7b4e2f 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -26,8 +26,6 @@ obj-$(CONFIG_SMP) += locks.o
obj-$(CONFIG_ALTIVEC) += vmx-helper.o
endif
-obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
-
obj-y += code-patching.o
obj-y += feature-fixups.o
obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index d6c7506..0ea1aee 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -254,7 +254,7 @@ config PPC4xx_GPIO
config PPC4xx_OCM
bool "PPC4xx On Chip Memory (OCM) support"
depends on 4xx
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
help
Enable OCM support for PowerPC 4xx platforms with on chip memory,
OCM provides the fast place for memory access to improve performance.
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index ae9fdb51..ab4777a 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -19,7 +19,7 @@ if PPC32
config FSL_85XX_CACHE_SRAM
bool "Freescale l2cache sram support"
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
help
When selected, this option enables cache-sram support
for memory allocation on P1/P2 QorIQ platforms.
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index d09ae32f..9c38a8d 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -282,7 +282,7 @@ config CPM2
bool "Enable support for the CPM2 (Communications Processor Module)"
depends on (FSL_SOC_BOOKE && PPC32) || 8260
select CPM
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
select PPC_PCI_CHOICE
select ARCH_REQUIRE_GPIOLIB
help
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index c9ef8a5..d68d19e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -33,7 +33,7 @@ config PPC_8xx
bool "Freescale 8xx"
select FSL_SOC
select 8xx
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
config 40x
bool "AMCC 40x"
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 5e6ff38..c6f5762 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -38,7 +38,7 @@
#include <asm/cpm1.h>
#include <asm/io.h>
#include <asm/tlbflush.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <asm/prom.h>
#include <asm/cpm.h>
diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c
index 8dc1e24..5a63d35 100644
--- a/arch/powerpc/sysdev/cpm2.c
+++ b/arch/powerpc/sysdev/cpm2.c
@@ -41,7 +41,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/cpm2.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <asm/fs_pd.h>
#include <sysdev/fsl_soc.h>
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 4dd5341..98cac81 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -26,7 +26,7 @@
#include <asm/udbg.h>
#include <asm/io.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <asm/cpm.h>
#include <mm/mmu_decl.h>
diff --git a/arch/powerpc/sysdev/ppc4xx_ocm.c b/arch/powerpc/sysdev/ppc4xx_ocm.c
index 1b15f93..c6a1561 100644
--- a/arch/powerpc/sysdev/ppc4xx_ocm.c
+++ b/arch/powerpc/sysdev/ppc4xx_ocm.c
@@ -26,7 +26,7 @@
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
#include <linux/of.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <asm/ppc4xx_ocm.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
diff --git a/drivers/dma/bestcomm/Kconfig b/drivers/dma/bestcomm/Kconfig
index 29e4270..9bb1bf8 100644
--- a/drivers/dma/bestcomm/Kconfig
+++ b/drivers/dma/bestcomm/Kconfig
@@ -6,7 +6,7 @@ config PPC_BESTCOMM
tristate "Bestcomm DMA engine support"
depends on PPC_MPC52xx
default n
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
help
BestComm is the name of the communication coprocessor found
on the Freescale MPC5200 family of processor. Its usage is
diff --git a/drivers/soc/qe/Kconfig b/drivers/soc/qe/Kconfig
index 5c2b9d8..49118e1 100644
--- a/drivers/soc/qe/Kconfig
+++ b/drivers/soc/qe/Kconfig
@@ -5,7 +5,7 @@
config QUICC_ENGINE
bool "Freescale QUICC Engine (QE) Support"
depends on FSL_SOC && (PPC32 || PPC64)
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
select CRC32
---help---
The QUICC Engine (QE) is a new generation of communications
diff --git a/drivers/soc/qe/qe.c b/drivers/soc/qe/qe.c
index 55a9c6d..a5e4780 100644
--- a/drivers/soc/qe/qe.c
+++ b/drivers/soc/qe/qe.c
@@ -36,7 +36,7 @@
#include <linux/fsl/immap_qe.h>
#include <linux/fsl/qe.h>
#include <asm/prom.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
static void qe_snums_init(void);
static int qe_sdma_init(void);
diff --git a/drivers/soc/qe/qe_common.c b/drivers/soc/qe/qe_common.c
index ee02ae8..c047fde 100644
--- a/drivers/soc/qe/qe_common.c
+++ b/drivers/soc/qe/qe_common.c
@@ -26,7 +26,7 @@
#include <linux/slab.h>
#include <asm/io.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <linux/fsl/qe.h>
static spinlock_t qe_muram_lock;
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 2a46153..4ce7204 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -1972,7 +1972,7 @@ config FB_FSL_DIU
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
- select PPC_LIB_RHEAP
+ select LIB_RHEAP
---help---
Framebuffer driver for the Freescale SoC DIU
diff --git a/include/linux/fsl/bestcomm/sram.h b/include/linux/fsl/bestcomm/sram.h
index b6d6689..117eaa1 100644
--- a/include/linux/fsl/bestcomm/sram.h
+++ b/include/linux/fsl/bestcomm/sram.h
@@ -12,7 +12,7 @@
#ifndef __BESTCOMM_SRAM_H__
#define __BESTCOMM_SRAM_H__
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
#include <asm/mmu.h>
#include <linux/spinlock.h>
diff --git a/arch/powerpc/include/asm/rheap.h b/include/linux/fsl/rheap.h
similarity index 100%
rename from arch/powerpc/include/asm/rheap.h
rename to include/linux/fsl/rheap.h
diff --git a/lib/Kconfig b/lib/Kconfig
index 4490089..4ffcc86 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -365,6 +365,9 @@ config CPU_RMAP
bool
depends on SMP
+config LIB_RHEAP
+ bool
+
config DQL
bool
diff --git a/lib/Makefile b/lib/Makefile
index 6e23a0f..8523e9d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -194,3 +194,5 @@ quiet_cmd_build_OID_registry = GEN $@
clean-files += oid_registry_data.c
obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
+
+obj-$(CONFIG_LIB_RHEAP) += rheap.o
diff --git a/arch/powerpc/lib/rheap.c b/lib/rheap.c
similarity index 99%
rename from arch/powerpc/lib/rheap.c
rename to lib/rheap.c
index a1060a8..af180fd 100644
--- a/arch/powerpc/lib/rheap.c
+++ b/lib/rheap.c
@@ -20,7 +20,7 @@
#include <linux/err.h>
#include <linux/slab.h>
-#include <asm/rheap.h>
+#include <linux/fsl/rheap.h>
/*
* Fixup a list_head, needed when copying lists. If the pointers fall
--
2.1.0.27.g96db324
^ permalink raw reply related
* [PATCH 2/3] qe_common: add qe common functions to qe_common.c
From: Zhao Qiang @ 2014-09-25 2:47 UTC (permalink / raw)
To: linuxppc-dev, linux-kernel, B07421; +Cc: Zhao Qiang, R63061
qe need to call some common functions, move them into
public directory, add a new file drivers/soc/qe/qe_common.c
for them.
Signed-off-by: Zhao Qiang <B45475@freescale.com>
---
drivers/soc/qe/Makefile | 2 +-
drivers/soc/qe/qe_common.c | 185 +++++++++++++++++++++++++++++++++++++++++++++
include/linux/fsl/qe.h | 52 +++++++++++--
3 files changed, 230 insertions(+), 9 deletions(-)
create mode 100644 drivers/soc/qe/qe_common.c
diff --git a/drivers/soc/qe/Makefile b/drivers/soc/qe/Makefile
index f1855c1..77f6fd9 100644
--- a/drivers/soc/qe/Makefile
+++ b/drivers/soc/qe/Makefile
@@ -1,7 +1,7 @@
#
# Makefile for the linux ppc-specific parts of QE
#
-obj-$(CONFIG_QUICC_ENGINE)+= qe.o qe_ic.o qe_io.o
+obj-$(CONFIG_QUICC_ENGINE)+= qe.o qe_ic.o qe_io.o qe_common.o
obj-$(CONFIG_UCC) += ucc.o
obj-$(CONFIG_UCC_SLOW) += ucc_slow.o
diff --git a/drivers/soc/qe/qe_common.c b/drivers/soc/qe/qe_common.c
new file mode 100644
index 0000000..ee02ae8
--- /dev/null
+++ b/drivers/soc/qe/qe_common.c
@@ -0,0 +1,185 @@
+/*
+ * Common QE code
+ *
+ * Author: Scott Wood <scottwood@freescale.com>
+ *
+ * Copyright 2007-2008,2010 Freescale Semiconductor, Inc.
+ *
+ * Some parts derived from commproc.c/cpm2_common.c, which is:
+ * Copyright (c) 1997 Dan error_act (dmalek@jlc.net)
+ * Copyright (c) 1999-2001 Dan Malek <dan@embeddedalley.com>
+ * Copyright (c) 2000 MontaVista Software, Inc (source@mvista.com)
+ * 2006 (c) MontaVista Software, Inc.
+ * Vitaly Bordug <vbordug@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+#include <asm/io.h>
+#include <asm/rheap.h>
+#include <linux/fsl/qe.h>
+
+static spinlock_t qe_muram_lock;
+static rh_block_t qe_boot_muram_rh_block[16];
+static rh_info_t qe_muram_info;
+static u8 __iomem *muram_vbase;
+static phys_addr_t muram_pbase;
+
+/* Max address size we deal with */
+#define OF_MAX_ADDR_CELLS 4
+
+int qe_muram_init(void)
+{
+ struct device_node *np;
+ struct resource r;
+ u32 zero[OF_MAX_ADDR_CELLS] = {};
+ resource_size_t max = 0;
+ int i = 0;
+ int ret = 0;
+
+ if (muram_pbase)
+ return 0;
+
+ spin_lock_init(&qe_muram_lock);
+ /* initialize the info header */
+ rh_init(&qe_muram_info, 1,
+ sizeof(qe_boot_muram_rh_block) /
+ sizeof(qe_boot_muram_rh_block[0]),
+ qe_boot_muram_rh_block);
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,qe-muram-data");
+ if (!np) {
+ /* try legacy bindings */
+ np = of_find_node_by_name(NULL, "data-only");
+ if (!np) {
+ printk(KERN_ERR "Cannot find CPM muram data node");
+ ret = -ENODEV;
+ goto out;
+ }
+ }
+
+ muram_pbase = of_translate_address(np, zero);
+ if (muram_pbase == (phys_addr_t)OF_BAD_ADDR) {
+ printk(KERN_ERR "Cannot translate zero through CPM muram node");
+ ret = -ENODEV;
+ goto out;
+ }
+
+ while (of_address_to_resource(np, i++, &r) == 0) {
+ if (r.end > max)
+ max = r.end;
+
+ rh_attach_region(&qe_muram_info, r.start - muram_pbase,
+ resource_size(&r));
+ }
+
+ muram_vbase = ioremap(muram_pbase, max - muram_pbase + 1);
+ if (!muram_vbase) {
+ printk(KERN_ERR "Cannot map CPM muram");
+ ret = -ENOMEM;
+ }
+
+out:
+ of_node_put(np);
+ return ret;
+}
+
+/**
+ * qe_muram_alloc - allocate the requested size worth of multi-user ram
+ * @size: number of bytes to allocate
+ * @align: requested alignment, in bytes
+ *
+ * This function returns an offset into the muram area.
+ * Use qe_dpram_addr() to get the virtual address of the area.
+ * Use qe_muram_free() to free the allocation.
+ */
+unsigned long qe_muram_alloc(unsigned long size, unsigned long align)
+{
+ unsigned long start;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qe_muram_lock, flags);
+ qe_muram_info.alignment = align;
+ start = rh_alloc(&qe_muram_info, size, "commproc");
+ memset(qe_muram_addr(start), 0, size);
+ spin_unlock_irqrestore(&qe_muram_lock, flags);
+
+ return start;
+}
+EXPORT_SYMBOL(qe_muram_alloc);
+
+/**
+ * qe_muram_free - free a chunk of multi-user ram
+ * @offset: The beginning of the chunk as returned by qe_muram_alloc().
+ */
+int qe_muram_free(unsigned long offset)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qe_muram_lock, flags);
+ ret = rh_free(&qe_muram_info, offset);
+ spin_unlock_irqrestore(&qe_muram_lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(qe_muram_free);
+
+/**
+ * qe_muram_alloc_fixed - reserve a specific region of multi-user ram
+ * @offset: the offset into the muram area to reserve
+ * @size: the number of bytes to reserve
+ *
+ * This function returns "start" on success, -ENOMEM on failure.
+ * Use qe_dpram_addr() to get the virtual address of the area.
+ * Use qe_muram_free() to free the allocation.
+ */
+unsigned long qe_muram_alloc_fixed(unsigned long offset, unsigned long size)
+{
+ unsigned long start;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qe_muram_lock, flags);
+ qe_muram_info.alignment = 1;
+ start = rh_alloc_fixed(&qe_muram_info, offset, size, "commproc");
+ spin_unlock_irqrestore(&qe_muram_lock, flags);
+
+ return start;
+}
+EXPORT_SYMBOL(qe_muram_alloc_fixed);
+
+/**
+ * qe_muram_addr - turn a muram offset into a virtual address
+ * @offset: muram offset to convert
+ */
+void __iomem *qe_muram_addr(unsigned long offset)
+{
+ return muram_vbase + offset;
+}
+EXPORT_SYMBOL(qe_muram_addr);
+
+unsigned long qe_muram_offset(void __iomem *addr)
+{
+ return addr - (void __iomem *)muram_vbase;
+}
+EXPORT_SYMBOL(qe_muram_offset);
+
+/**
+ * qe_muram_dma - turn a muram virtual address into a DMA address
+ * @offset: virtual address from qe_muram_addr() to convert
+ */
+dma_addr_t qe_muram_dma(void __iomem *addr)
+{
+ return muram_pbase + ((u8 __iomem *)addr - muram_vbase);
+}
+EXPORT_SYMBOL(qe_muram_dma);
diff --git a/include/linux/fsl/qe.h b/include/linux/fsl/qe.h
index d56b8e0..fab0398 100644
--- a/include/linux/fsl/qe.h
+++ b/include/linux/fsl/qe.h
@@ -19,7 +19,8 @@
#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/err.h>
-#include <asm/cpm.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/fsl/immap_qe.h>
#define QE_NUM_OF_SNUM 256 /* There are 256 serial number in QE */
@@ -188,13 +189,48 @@ static inline int qe_alive_during_sleep(void)
#endif
}
-/* we actually use cpm_muram implementation, define this for convenience */
-#define qe_muram_init cpm_muram_init
-#define qe_muram_alloc cpm_muram_alloc
-#define qe_muram_alloc_fixed cpm_muram_alloc_fixed
-#define qe_muram_free cpm_muram_free
-#define qe_muram_addr cpm_muram_addr
-#define qe_muram_offset cpm_muram_offset
+int qe_muram_init(void);
+
+#if defined(CONFIG_QUICC_ENGINE)
+unsigned long qe_muram_alloc(unsigned long size, unsigned long align);
+int qe_muram_free(unsigned long offset);
+unsigned long qe_muram_alloc_fixed(unsigned long offset, unsigned long size);
+void __iomem *qe_muram_addr(unsigned long offset);
+unsigned long qe_muram_offset(void __iomem *addr);
+dma_addr_t qe_muram_dma(void __iomem *addr);
+#else
+static inline unsigned long qe_muram_alloc(unsigned long size,
+ unsigned long align)
+{
+ return -ENOSYS;
+}
+
+static inline int qe_muram_free(unsigned long offset)
+{
+ return -ENOSYS;
+}
+
+static inline unsigned long qe_muram_alloc_fixed(unsigned long offset,
+ unsigned long size)
+{
+ return -ENOSYS;
+}
+
+static inline void __iomem *qe_muram_addr(unsigned long offset)
+{
+ return NULL;
+}
+
+static inline unsigned long qe_muram_offset(void __iomem *addr)
+{
+ return -ENOSYS;
+}
+
+static inline dma_addr_t qe_muram_dma(void __iomem *addr)
+{
+ return 0;
+}
+#endif /* defined(CONFIG_QUICC_ENGINE) */
/* Structure that defines QE firmware binary files.
*
--
2.1.0.27.g96db324
^ permalink raw reply related
* Re: fadump: fix endianess issues in firmware assisted dump handling
From: Michael Ellerman @ 2014-09-25 1:40 UTC (permalink / raw)
To: Hari Bathini, linuxppc-dev; +Cc: Mahesh J Salgaonkar
In-Reply-To: <20140903122948.28708.22188.stgit@localhost.localdomain>
On Wed, 2014-03-09 at 12:29:48 UTC, Hari Bathini wrote:
> Firmware-assisted dump (fadump) kernel code is not LE compliant. The
> below patch tries to fix this issue. Tested this patch with upstream
> kernel. Did some sanity testing for the LE fadump vmcore generated.
> Below output shows crash tool successfully opening LE fadump vmcore.
>
> Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
> Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
In general I really dislike this kind of endian conversion, ie. where we just
litter the code with endian conversions at every usage site.
But in this case it's probably OK, because we can't really do much better.
> diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
> index 742694c..7d73b2d 100644
> --- a/arch/powerpc/kernel/fadump.c
> +++ b/arch/powerpc/kernel/fadump.c
> @@ -72,7 +72,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
> return 1;
>
> fw_dump.fadump_supported = 1;
> - fw_dump.ibm_configure_kernel_dump = *token;
> + fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
I'm getting a sparse warning here:
arch/powerpc/kernel/fadump.c:75:45: warning: cast to restricted __be32
I think token should be a __be32 *.
> pr_debug("--------CPU State Data------------\n");
> - pr_debug("Magic Number: %llx\n", reg_header->magic_number);
> - pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
> + pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
> + pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
>
> - vaddr += reg_header->num_cpu_offset;
> - num_cpus = *((u32 *)(vaddr));
> + vaddr += be32_to_cpu(reg_header->num_cpu_offset);
> + num_cpus = be32_to_cpu(*((u32 *)(vaddr)));
And here too:
arch/powerpc/kernel/fadump.c:619:20: warning: cast to restricted __be32
I guess the cast is OK there because you are calculating the offset, but the
cast should be to __be32.
> diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
> index 34e6423..587887e 100644
> --- a/arch/powerpc/platforms/pseries/lpar.c
> +++ b/arch/powerpc/platforms/pseries/lpar.c
> @@ -43,6 +43,7 @@
> #include <asm/trace.h>
> #include <asm/firmware.h>
> #include <asm/plpar_wrappers.h>
> +#include <asm/fadump.h>
>
> #include "pseries.h"
>
> @@ -249,8 +250,12 @@ static void pSeries_lpar_hptab_clear(void)
> }
>
> #ifdef __LITTLE_ENDIAN__
> - /* Reset exceptions to big endian */
> - if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
> + /*
> + * Reset exceptions to big endian
> + * During fadump kernel boot, we dont need to reset exception to big endian
> + * as we have already booted into LE kernel.
> + */
> + if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active()) {
> long rc;
>
> rc = pseries_big_endian_exceptions();
It's really unfortunate that we need to inject this knowledge of fadump into
the setup code.
It sounds like we have to do it though, Mahesh said on irc that without it the
system won't boot. Please elaborate on *why* the system won't boot.
And please make the comment much clearer, ie. it's not that we don't need to
reset exceptions to big endian, it's that we *must not* reset them to big
endian.
cheers
^ permalink raw reply
* Re: powerpc: Fix build failure when MEMORY_HOTPLUG=y
From: Michael Ellerman @ 2014-09-25 1:14 UTC (permalink / raw)
To: Pranith Kumar, Benjamin Herrenschmidt, Paul Mackerras,
linuxppc-dev, linux-kernel
Cc: Andew Morton
In-Reply-To: <1408482065-18457-1-git-send-email-bobby.prani@gmail.com>
On Tue, 2014-19-08 at 21:01:05 UTC, Pranith Kumar wrote:
> ARCH_ENABLE_MEMORY_HOTPLUG is enabled by default for powerpc. This causes build
> failures when SPARSEMEM=n as memory hotplug needs definition which are defined
> only when SPARSEMEM=y. The error is as follows:
> arch/powerpc/platforms/pseries/hotplug-memory.c:27:31: error: 'SECTION_SIZE_BITS' undeclared (first use in this function)
> arch/powerpc/platforms/pseries/hotplug-memory.c:27:31: note: each undeclared identifier is reported only once for each function it appears in
I don't see how you can even build pseries without SPARSEMEM=y ?
The three options are:
default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
default FLATMEM_MANUAL
We don't have DISCONTIGMEM.
FLATMEM_MANUAL depends on !ARCH_SPARSEMEM_ENABLE.
We turn on ARCH_SPARSEMEM_ENABLE, and it's not user editable.
cheers
^ permalink raw reply
* Re: [4/5] pseries: Implement memory hotplug add in the kernel
From: Nathan Fontenot @ 2014-09-24 20:57 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <1410937639.27681.12.camel@concordia>
On 09/17/2014 02:07 AM, Michael Ellerman wrote:
>
> On Mon, 2014-09-15 at 15:32 -0500, Nathan Fontenot wrote:
>> This patch adds the ability to do memory hotplug adding in the kernel.
>>
>> Currently the hotplug add/remove of memory is handled by the drmgr
>> command. The drmgr command performs the add/remove by performing
>> some work in user-space and making requests to the kernel to handle
>> other pieces. By moving all of the work to the kernel we can do the
>> add and remove faster, and provide a common place to do memory hotplug
>> for both the PowerVM and PowerKVM environments.
>>
>> Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
>> ---
>> + for (i = 0; i < entries; i++, lmb++) {
>> + u32 drc_index = be32_to_cpu(lmb->drc_index);
>> +
>> + if (lmbs_to_add == lmbs_added)
>> + break;
>> +
>> + if (be32_to_cpu(lmb->flags) & DRCONF_MEM_ASSIGNED)
>> + continue;
>> +
>> + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX
>> + && lmb->drc_index != hp_elog->_drc_u.drc_index)
>> + continue;
>> +
>> + rc = dlpar_acquire_drc(drc_index);
>> + if (rc)
>> + continue;
>> +
>> + rc = dlpar_add_one_lmb(lmb);
>> + if (rc) {
>> + dlpar_release_drc(drc_index);
>> + continue;
>> + }
>
> In both the above error cases you just move along. That means we potentially
> hotplugged some memory but not everything that we were asked to. That seems
> like a bad idea, we should either do everything or nothing.
>
Michael, how set are you on the all or nothing approach?
Note that I think the all or nothing approach is best but I think it will
present some problems. We do memory add (and remove) on a LMB basis, so it
is possible to hit a scenario in which we cannot revert back to the original
state. For example, a request to add 5 LMBs only succeeds in adding 4 LMBs.
There is no guarantee that we then remove the 4 MLBs that were added. That
memory could be in use somewhere that it cannot be moved.
I would suggest we continue with the current approach in that we try to
satisfy the request but not try to roll-back the changes if the entire
request cannot be satisfied.
-Nathan
^ permalink raw reply
* Re: [PATCH v3 3/3] pseries: Fix endian issues in cpu hot-removal
From: Nathan Fontenot @ 2014-09-24 20:16 UTC (permalink / raw)
To: Thomas Falcon, linuxppc-dev; +Cc: bharata
In-Reply-To: <1410898547-12296-4-git-send-email-tlfalcon@linux.vnet.ibm.com>
On 09/16/2014 03:15 PM, Thomas Falcon wrote:
> When removing a cpu, this patch makes sure that values
> gotten from or passed to firmware are in the correct
> endian format.
>
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Acked-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
> ---
> Changes in v3:
>
> drc_index in dlpar_cpu_release is no longer const to
> fix compilation error found by Bharata Rao
> ---
> arch/powerpc/platforms/pseries/dlpar.c | 20 +++++++++++---------
> arch/powerpc/platforms/pseries/hotplug-cpu.c | 10 ++++++----
> 2 files changed, 17 insertions(+), 13 deletions(-)
>
> diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
> index 187e4eb..0fad5b6 100644
> --- a/arch/powerpc/platforms/pseries/dlpar.c
> +++ b/arch/powerpc/platforms/pseries/dlpar.c
> @@ -444,7 +444,8 @@ static int dlpar_offline_cpu(struct device_node *dn)
> int rc = 0;
> unsigned int cpu;
> int len, nthreads, i;
> - const u32 *intserv;
> + const __be32 *intserv;
> + u32 thread;
>
> intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
> if (!intserv)
> @@ -454,8 +455,9 @@ static int dlpar_offline_cpu(struct device_node *dn)
>
> cpu_maps_update_begin();
> for (i = 0; i < nthreads; i++) {
> + thread = be32_to_cpu(intserv[i]);
> for_each_present_cpu(cpu) {
> - if (get_hard_smp_processor_id(cpu) != intserv[i])
> + if (get_hard_smp_processor_id(cpu) != thread)
> continue;
>
> if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
> @@ -477,14 +479,14 @@ static int dlpar_offline_cpu(struct device_node *dn)
> * Upgrade it's state to CPU_STATE_OFFLINE.
> */
> set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
> - BUG_ON(plpar_hcall_norets(H_PROD, intserv[i])
> + BUG_ON(plpar_hcall_norets(H_PROD, thread)
> != H_SUCCESS);
> __cpu_die(cpu);
> break;
> }
> if (cpu == num_possible_cpus())
> printk(KERN_WARNING "Could not find cpu to offline "
> - "with physical id 0x%x\n", intserv[i]);
> + "with physical id 0x%x\n", thread);
> }
> cpu_maps_update_done();
>
> @@ -496,15 +498,15 @@ out:
> static ssize_t dlpar_cpu_release(const char *buf, size_t count)
> {
> struct device_node *dn;
> - const u32 *drc_index;
> + u32 drc_index;
> int rc;
>
> dn = of_find_node_by_path(buf);
> if (!dn)
> return -EINVAL;
>
> - drc_index = of_get_property(dn, "ibm,my-drc-index", NULL);
> - if (!drc_index) {
> + rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
> + if (rc) {
> of_node_put(dn);
> return -EINVAL;
> }
> @@ -515,7 +517,7 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
> return -EINVAL;
> }
>
> - rc = dlpar_release_drc(*drc_index);
> + rc = dlpar_release_drc(drc_index);
> if (rc) {
> of_node_put(dn);
> return rc;
> @@ -523,7 +525,7 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
>
> rc = dlpar_detach_node(dn);
> if (rc) {
> - dlpar_acquire_drc(*drc_index);
> + dlpar_acquire_drc(drc_index);
> return rc;
> }
>
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 447f8c6..5c375f9 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -90,7 +90,7 @@ static void rtas_stop_self(void)
> {
> static struct rtas_args args = {
> .nargs = 0,
> - .nret = 1,
> + .nret = cpu_to_be32(1),
> .rets = &args.args[0],
> };
>
> @@ -312,7 +312,8 @@ static void pseries_remove_processor(struct device_node *np)
> {
> unsigned int cpu;
> int len, nthreads, i;
> - const u32 *intserv;
> + const __be32 *intserv;
> + u32 thread;
>
> intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len);
> if (!intserv)
> @@ -322,8 +323,9 @@ static void pseries_remove_processor(struct device_node *np)
>
> cpu_maps_update_begin();
> for (i = 0; i < nthreads; i++) {
> + thread = be32_to_cpu(intserv[i]);
> for_each_present_cpu(cpu) {
> - if (get_hard_smp_processor_id(cpu) != intserv[i])
> + if (get_hard_smp_processor_id(cpu) != thread)
> continue;
> BUG_ON(cpu_online(cpu));
> set_cpu_present(cpu, false);
> @@ -332,7 +334,7 @@ static void pseries_remove_processor(struct device_node *np)
> }
> if (cpu >= nr_cpu_ids)
> printk(KERN_WARNING "Could not find cpu to remove "
> - "with physical id 0x%x\n", intserv[i]);
> + "with physical id 0x%x\n", thread);
> }
> cpu_maps_update_done();
> }
>
^ permalink raw reply
* Re: [PATCH v2 2/3] pseries: Fix endian issues in onlining cpu threads
From: Nathan Fontenot @ 2014-09-24 20:15 UTC (permalink / raw)
To: Thomas Falcon, linuxppc-dev; +Cc: bharata
In-Reply-To: <1410898547-12296-3-git-send-email-tlfalcon@linux.vnet.ibm.com>
On 09/16/2014 03:15 PM, Thomas Falcon wrote:
> The ibm,ppc-interrupt-server#s property is in big endian format.
> These values need to be converted when used by little endian
> architectures.
>
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Acked-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
> ---
> Changes in v2:
>
> Followed suggestions from Michael Ellerman
> conversion of intserv values occur once
> ---
> arch/powerpc/platforms/pseries/dlpar.c | 8 +++++---
> 1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
> index 5acbe59..187e4eb 100644
> --- a/arch/powerpc/platforms/pseries/dlpar.c
> +++ b/arch/powerpc/platforms/pseries/dlpar.c
> @@ -363,7 +363,8 @@ static int dlpar_online_cpu(struct device_node *dn)
> int rc = 0;
> unsigned int cpu;
> int len, nthreads, i;
> - const u32 *intserv;
> + const __be32 *intserv;
> + u32 thread;
>
> intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
> if (!intserv)
> @@ -373,8 +374,9 @@ static int dlpar_online_cpu(struct device_node *dn)
>
> cpu_maps_update_begin();
> for (i = 0; i < nthreads; i++) {
> + thread = be32_to_cpu(intserv[i]);
> for_each_present_cpu(cpu) {
> - if (get_hard_smp_processor_id(cpu) != intserv[i])
> + if (get_hard_smp_processor_id(cpu) != thread)
> continue;
> BUG_ON(get_cpu_current_state(cpu)
> != CPU_STATE_OFFLINE);
> @@ -388,7 +390,7 @@ static int dlpar_online_cpu(struct device_node *dn)
> }
> if (cpu == num_possible_cpus())
> printk(KERN_WARNING "Could not find cpu to online "
> - "with physical id 0x%x\n", intserv[i]);
> + "with physical id 0x%x\n", thread);
> }
> cpu_maps_update_done();
>
>
^ permalink raw reply
* Re: [PATCH v2 1/3] pseries: Make CPU hotplug path endian safe
From: Nathan Fontenot @ 2014-09-24 20:15 UTC (permalink / raw)
To: Thomas Falcon, linuxppc-dev; +Cc: bharata
In-Reply-To: <1410898547-12296-2-git-send-email-tlfalcon@linux.vnet.ibm.com>
On 09/16/2014 03:15 PM, Thomas Falcon wrote:
> From: Bharata B Rao <bharata@linux.vnet.ibm.com>
>
> - ibm,rtas-configure-connector should treat the RTAS data as big endian.
> - Treat ibm,ppc-interrupt-server#s as big-endian when setting
> smp_processor_id during hotplug.
>
> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Acked-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
> ---
>
> Changes in v2:
> - Don't convert drc_index to BE in dlpar_configure_connector() but instead
> convert in the caller dlpar_cpu_probe() so that migration path isn't
> affected.
> - Mark members of cc_workarea struct as __be32 instead of u32 (Thomas)
> - Based on top of Thomas Falcon's two patches.
> (http://patchwork.ozlabs.org/patch/388767/)
>
> v1: http://patchwork.ozlabs.org/patch/386216/
>
> arch/powerpc/platforms/pseries/dlpar.c | 22 +++++++++++-----------
> arch/powerpc/platforms/pseries/hotplug-cpu.c | 4 ++--
> arch/powerpc/platforms/pseries/pseries.h | 3 ++-
> 3 files changed, 15 insertions(+), 14 deletions(-)
>
> diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
> index a2450b8..5acbe59 100644
> --- a/arch/powerpc/platforms/pseries/dlpar.c
> +++ b/arch/powerpc/platforms/pseries/dlpar.c
> @@ -24,11 +24,11 @@
> #include <asm/rtas.h>
>
> struct cc_workarea {
> - u32 drc_index;
> - u32 zero;
> - u32 name_offset;
> - u32 prop_length;
> - u32 prop_offset;
> + __be32 drc_index;
> + __be32 zero;
> + __be32 name_offset;
> + __be32 prop_length;
> + __be32 prop_offset;
> };
>
> void dlpar_free_cc_property(struct property *prop)
> @@ -48,11 +48,11 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa)
> if (!prop)
> return NULL;
>
> - name = (char *)ccwa + ccwa->name_offset;
> + name = (char *)ccwa + be32_to_cpu(ccwa->name_offset);
> prop->name = kstrdup(name, GFP_KERNEL);
>
> - prop->length = ccwa->prop_length;
> - value = (char *)ccwa + ccwa->prop_offset;
> + prop->length = be32_to_cpu(ccwa->prop_length);
> + value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset);
> prop->value = kmemdup(value, prop->length, GFP_KERNEL);
> if (!prop->value) {
> dlpar_free_cc_property(prop);
> @@ -78,7 +78,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
> if (!dn)
> return NULL;
>
> - name = (char *)ccwa + ccwa->name_offset;
> + name = (char *)ccwa + be32_to_cpu(ccwa->name_offset);
> dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name);
> if (!dn->full_name) {
> kfree(dn);
> @@ -125,7 +125,7 @@ void dlpar_free_cc_nodes(struct device_node *dn)
> #define CALL_AGAIN -2
> #define ERR_CFG_USE -9003
>
> -struct device_node *dlpar_configure_connector(u32 drc_index,
> +struct device_node *dlpar_configure_connector(__be32 drc_index,
> struct device_node *parent)
> {
> struct device_node *dn;
> @@ -411,7 +411,7 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
> if (!parent)
> return -ENODEV;
>
> - dn = dlpar_configure_connector(drc_index, parent);
> + dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
> if (!dn)
> return -EINVAL;
>
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 20d6297..447f8c6 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -247,7 +247,7 @@ static int pseries_add_processor(struct device_node *np)
> unsigned int cpu;
> cpumask_var_t candidate_mask, tmp;
> int err = -ENOSPC, len, nthreads, i;
> - const u32 *intserv;
> + const __be32 *intserv;
>
> intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len);
> if (!intserv)
> @@ -293,7 +293,7 @@ static int pseries_add_processor(struct device_node *np)
> for_each_cpu(cpu, tmp) {
> BUG_ON(cpu_present(cpu));
> set_cpu_present(cpu, true);
> - set_hard_smp_processor_id(cpu, *intserv++);
> + set_hard_smp_processor_id(cpu, be32_to_cpu(*intserv++));
> }
> err = 0;
> out_unlock:
> diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
> index 361add6..1796c54 100644
> --- a/arch/powerpc/platforms/pseries/pseries.h
> +++ b/arch/powerpc/platforms/pseries/pseries.h
> @@ -56,7 +56,8 @@ extern void hvc_vio_init_early(void);
> /* Dynamic logical Partitioning/Mobility */
> extern void dlpar_free_cc_nodes(struct device_node *);
> extern void dlpar_free_cc_property(struct property *);
> -extern struct device_node *dlpar_configure_connector(u32, struct device_node *);
> +extern struct device_node *dlpar_configure_connector(__be32,
> + struct device_node *);
> extern int dlpar_attach_node(struct device_node *);
> extern int dlpar_detach_node(struct device_node *);
>
>
^ permalink raw reply
* [PATCH v4 10/10] powerpc/perf/hv-24x7: Document sysfs event description entries
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
.../testing/sysfs-bus-event_source-devices-hv_24x7 | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index e78ee79..5b501d7 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -21,3 +21,25 @@ 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.
+
+What: /sys/bus/event_source/devices/hv_24x7/event_descs/<event-name>
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Provides the description of a particular event as provided by
+ the firmware. If firmware does not provide a description, no
+ file will be created.
+
+ Note that the event-name lacks the domain suffix appended for
+ events in the events/ dir.
+
+What: /sys/bus/event_source/devices/hv_24x7/event_long_descs/<event-name>
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Provides the "long" description of a particular event as
+ provided by the firmware. If firmware does not provide a
+ description, no file will be created.
+
+ Note that the event-name lacks the domain suffix appended for
+ events in the events/ dir.
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 08/10] perf Documentation: add event parameters
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Event parameters are a basic way for partial events to be specified in
sysfs with per-event names given to the fields that need to be filled in
when using a particular event.
It is intended for supporting cases where the single 'cpu' parameter is
insufficient. For example, POWER 8 has events for physical
sockets/cores/cpus that are accessible from with virtual machines. To
keep using the single 'cpu' parameter we'd need to perform a mapping
between Linux's cpus and the physical machine's cpus (in this case
Linux is running under a hypervisor). This isn't possible because
bindings between our cpus and physical cpus may not be fixed, and we
probably won't have a "cpu" on each physical cpu.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
Documentation/ABI/testing/sysfs-bus-event_source-devices-events | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 20979f8..c1f9850 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -52,12 +52,18 @@ Description: Per-pmu performance monitoring events specific to the running syste
event=0x2abc
event=0x423,inv,cmask=0x3
domain=0x1,offset=0x8,starting_index=0xffff
+ domain=0x1,offset=0x8,starting_index=phys_cpu
Each of the assignments indicates a value to be assigned to a
particular set of bits (as defined by the format file
corresponding to the <term>) in the perf_event structure passed
to the perf_open syscall.
+ In the case of the last example, a value replacing "phys_cpu"
+ would need to be provided by the user selecting the particular
+ event. This is refered to as "event parameterization". All
+ non-numerical values indicate an event parameter.
+
What: /sys/bus/event_source/devices/<pmu>/events/<event>.unit
Date: 2014/02/24
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 09/10] tools/perf: Document parameterized and symbolic events
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Changelog[v6]:
- [Sukadev Bhattiprolu]: Update documentation of perf-list and
perf-record; Added documentation for perf-stat.
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
tools/perf/Documentation/perf-list.txt | 13 +++++++++++++
tools/perf/Documentation/perf-record.txt | 12 ++++++++++++
tools/perf/Documentation/perf-stat.txt | 20 ++++++++++++++++----
3 files changed, 41 insertions(+), 4 deletions(-)
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 6fce6a6..c405da24 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -89,6 +89,19 @@ raw encoding of 0x1A8 can be used:
You should refer to the processor specific documentation for getting these
details. Some of them are referenced in the SEE ALSO section below.
+PARAMETERIZED EVENTS
+--------------------
+
+Some pmu events listed by 'perf-list' will be displayed with '?' in them. For
+example:
+
+ hv_gpci/dtbp_ptitc,starting_index=?/
+
+This means that when provided as an event, a value for 'starting_index' must
+also be supplied. For example:
+
+ perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,starting_index=0x2/' ...
+
OPTIONS
-------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d460049..a6a2f9c 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,6 +33,18 @@ OPTIONS
- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
hexadecimal event descriptor.
+ - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
+ 'param1', 'param2', etc are defined as formats for the PMU in
+ /sys/bus/event_sources/devices/<pmu>/format/*.
+
+ - a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
+
+ where M, N, K are numbers (in decimal, hex, octal format). Acceptable
+ values for each of 'config', 'config1' and 'config2' are defined by
+ corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/*
+ param1 and param2 are defined as formats for the PMU in:
+ /sys/bus/event_sources/devices/<pmu>/format/*
+
- a hardware breakpoint event in the form of '\mem:addr[:access]'
where addr is the address in memory you want to break in.
Access is the memory access type (read, write, execute) it can
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 29ee857..04e150d 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -25,10 +25,22 @@ OPTIONS
-e::
--event=::
- Select the PMU event. Selection can be a symbolic event name
- (use 'perf list' to list all events) or a raw PMU
- event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ Select the PMU event. Selection can be:
+
+ - a symbolic event name (use 'perf list' to list all events)
+
+ - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
+ hexadecimal event descriptor.
+
+ - a symbolically formed event like 'pmu/param1=0x3,param2/' where
+ param1 and param2 are defined as formats for the PMU in
+ /sys/bus/event_sources/devices/<pmu>/format/*
+
+ - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
+ where M, N, K are numbers (in decimal, hex, octal format).
+ Acceptable values for each of 'config', 'config1' and 'config2'
+ parameters are defined by corresponding entries in
+ /sys/bus/event_sources/devices/<pmu>/format/*
-i::
--no-inherit::
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 07/10] powerpc/perf/hv-gpci: add the remaining gpci requests
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Add the remaining gpci requests that contain counters suitable for use
by perf. Omit those that don't contain any counters (but note their
ommision).
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-gpci-requests.h | 183 +++++++++++++++++++++++++++++++++++
1 file changed, 183 insertions(+)
diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h
index 0dfc4d9..a908b08 100644
--- a/arch/powerpc/perf/hv-gpci-requests.h
+++ b/arch/powerpc/perf/hv-gpci-requests.h
@@ -65,6 +65,33 @@ REQUEST(__count(0, 8, processor_time_in_timebase_cycles)
)
#include I(REQUEST_END)
+#define REQUEST_NAME entitled_capped_uncapped_donated_idle_timebase_by_partition
+#define REQUEST_NUM 0x20
+#define REQUEST_IDX_KIND sibling_part_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 8, partition_id)
+ __count(0x8, 8, entitled_cycles)
+ __count(0x10, 8, consumed_capped_cycles)
+ __count(0x18, 8, consumed_uncapped_cycles)
+ __count(0x20, 8, cycles_donated)
+ __count(0x28, 8, purr_idle_cycles)
+)
+#include I(REQUEST_END)
+
+/*
+ * Not avaliable for counter_info_version >= 0x8, use
+ * run_instruction_cycles_by_partition(0x100) instead.
+ */
+#define REQUEST_NAME run_instructions_run_cycles_by_partition
+#define REQUEST_NUM 0x30
+#define REQUEST_IDX_KIND sibling_part_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 8, partition_id)
+ __count(0x8, 8, instructions_completed)
+ __count(0x10, 8, cycles)
+)
+#include I(REQUEST_END)
+
#define REQUEST_NAME system_performance_capabilities
#define REQUEST_NUM 0x40
#define REQUEST_IDX_KIND M1
@@ -75,5 +102,161 @@ REQUEST(__field(0, 1, perf_collect_privileged)
)
#include I(REQUEST_END)
+#define REQUEST_NAME processor_bus_utilization_abc_links
+#define REQUEST_NUM 0x50
+#define REQUEST_IDX_KIND hw_chip_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, total_link_cycles)
+ __count(0x18, 8, idle_cycles_for_a_link)
+ __count(0x20, 8, idle_cycles_for_b_link)
+ __count(0x28, 8, idle_cycles_for_c_link)
+ __array(0x30, 0x20, reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_wxyz_links
+#define REQUEST_NUM 0x60
+#define REQUEST_IDX_KIND hw_chip_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, total_link_cycles)
+ __count(0x18, 8, idle_cycles_for_w_link)
+ __count(0x20, 8, idle_cycles_for_x_link)
+ __count(0x28, 8, idle_cycles_for_y_link)
+ __count(0x30, 8, idle_cycles_for_z_link)
+ __array(0x38, 0x28, reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_gx_links
+#define REQUEST_NUM 0x70
+#define REQUEST_IDX_KIND hw_chip_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, gx0_in_address_cycles)
+ __count(0x18, 8, gx0_in_data_cycles)
+ __count(0x20, 8, gx0_in_retries)
+ __count(0x28, 8, gx0_in_bus_cycles)
+ __count(0x30, 8, gx0_in_cycles_total)
+ __count(0x38, 8, gx0_out_address_cycles)
+ __count(0x40, 8, gx0_out_data_cycles)
+ __count(0x48, 8, gx0_out_retries)
+ __count(0x50, 8, gx0_out_bus_cycles)
+ __count(0x58, 8, gx0_out_cycles_total)
+ __count(0x60, 8, gx1_in_address_cycles)
+ __count(0x68, 8, gx1_in_data_cycles)
+ __count(0x70, 8, gx1_in_retries)
+ __count(0x78, 8, gx1_in_bus_cycles)
+ __count(0x80, 8, gx1_in_cycles_total)
+ __count(0x88, 8, gx1_out_address_cycles)
+ __count(0x90, 8, gx1_out_data_cycles)
+ __count(0x98, 8, gx1_out_retries)
+ __count(0xA0, 8, gx1_out_bus_cycles)
+ __count(0xA8, 8, gx1_out_cycles_total)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_mc_links
+#define REQUEST_NUM 0x80
+#define REQUEST_IDX_KIND hw_chip_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, mc0_frames)
+ __count(0x18, 8, mc0_reads)
+ __count(0x20, 8, mc0_write)
+ __count(0x28, 8, mc0_total_cycles)
+ __count(0x30, 8, mc1_frames)
+ __count(0x38, 8, mc1_reads)
+ __count(0x40, 8, mc1_writes)
+ __count(0x48, 8, mc1_total_cycles)
+)
+#include I(REQUEST_END)
+
+/* Processor_config (0x90) skipped, no counters */
+/* Current_processor_frequency (0x91) skipped, no counters */
+
+#define REQUEST_NAME processor_core_utilization
+#define REQUEST_NUM 0x94
+#define REQUEST_IDX_KIND phys_processor_idx
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, phys_processor_idx)
+ __field(0x4, 4, hw_processor_id)
+ __count(0x8, 8, cycles_across_any_thread)
+ __count(0x10, 8, timebase_at_collection)
+ __count(0x18, 8, purr_cycles)
+ __count(0x20, 8, sum_of_cycles_across_all_threads)
+ __count(0x28, 8, instructions_completed)
+)
+#include I(REQUEST_END)
+
+/* Processor_core_power_mode (0x95) skipped, no counters */
+/* Affinity_domain_information_by_virtual_processor (0xA0) skipped,
+ * no counters */
+/* Affinity_domain_information_by_domain (0xB0) skipped, no counters */
+/* Affinity_domain_information_by_partition (0xB1) skipped, no counters */
+/* Physical_memory_info (0xC0) skipped, no counters */
+/* Processor_bus_topology (0xD0) skipped, no counters */
+
+#define REQUEST_NAME partition_hypervisor_queuing_times
+#define REQUEST_NUM 0xE0
+#define REQUEST_IDX_KIND partition_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 2, partition_id)
+ __array(0x2, 6, reserved1)
+ __count(0x8, 8, time_waiting_for_entitlement)
+ __count(0x10, 8, times_waited_for_entitlement)
+ __count(0x18, 8, time_waiting_for_phys_processor)
+ __count(0x20, 8, times_waited_for_phys_processor)
+ __count(0x28, 8, dispatches_on_home_core)
+ __count(0x30, 8, dispatches_on_home_primary_affinity_domain)
+ __count(0x38, 8, dispatches_on_home_secondary_affinity_domain)
+ __count(0x40, 8, dispatches_off_home_secondary_affinity_domain)
+ __count(0x48, 8, dispatches_on_dedicated_processor_donating_cycles)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_hypervisor_times
+#define REQUEST_NUM 0xF0
+#define REQUEST_IDX_KIND M1
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors)
+ __count(0x8, 8, time_spent_processing_virtual_processor_timers)
+ __count(0x10, 8, time_spent_managing_partitions_over_entitlement)
+ __count(0x18, 8, time_spent_on_system_managment)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_tlbie_count_and_time
+#define REQUEST_NUM 0xF4
+#define REQUEST_IDX_KIND M1
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, tlbie_instructions_issued)
+ /*
+ * FIXME: The spec says the offset here is 0x10, which I suspect
+ * is wrong.
+ */
+ __count(0x8, 8, time_spent_issuing_tlbies)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME partition_instruction_count_and_time
+#define REQUEST_NUM 0x100
+#define REQUEST_IDX_KIND partition_id
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 2, partition_id)
+ __array(0x2, 0x6, reserved1)
+ __count(0x8, 8, instructions_performed)
+ __count(0x10, 8, time_collected)
+)
+#include I(REQUEST_END)
+
+/* set_mmcrh (0x80001000) skipped, no counters */
+/* retrieve_hpmcx (0x80002000) skipped, no counters */
+
#undef M1
#include "req-gen/_end.h"
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 06/10] powerpc/perf/{hv-gpci, hv-common}: generate requests with counters annotated
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
This adds (in req-gen/) a framework for defining gpci counter requests.
It uses macro magic similar to ftrace.
Also convert the existing hv-gpci request structures and enum values to
use the new framework (and adjust old users of the structs and enum
values to cope with changes in naming).
In exchange for this macro disaster, we get autogenerated event listing
for GPCI in sysfs, build time field offset checking, and zero
duplication of information about GPCI requests.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-common.c | 10 +-
arch/powerpc/perf/hv-gpci-requests.h | 79 +++++++++++++++
arch/powerpc/perf/hv-gpci.c | 8 ++
arch/powerpc/perf/hv-gpci.h | 37 +++----
arch/powerpc/perf/req-gen/_begin.h | 13 +++
arch/powerpc/perf/req-gen/_clear.h | 5 +
arch/powerpc/perf/req-gen/_end.h | 4 +
arch/powerpc/perf/req-gen/_request-begin.h | 15 +++
arch/powerpc/perf/req-gen/_request-end.h | 8 ++
arch/powerpc/perf/req-gen/perf.h | 155 +++++++++++++++++++++++++++++
10 files changed, 304 insertions(+), 30 deletions(-)
create mode 100644 arch/powerpc/perf/hv-gpci-requests.h
create mode 100644 arch/powerpc/perf/req-gen/_begin.h
create mode 100644 arch/powerpc/perf/req-gen/_clear.h
create mode 100644 arch/powerpc/perf/req-gen/_end.h
create mode 100644 arch/powerpc/perf/req-gen/_request-begin.h
create mode 100644 arch/powerpc/perf/req-gen/_request-end.h
create mode 100644 arch/powerpc/perf/req-gen/perf.h
diff --git a/arch/powerpc/perf/hv-common.c b/arch/powerpc/perf/hv-common.c
index 47e02b3..7dce8f10 100644
--- a/arch/powerpc/perf/hv-common.c
+++ b/arch/powerpc/perf/hv-common.c
@@ -9,13 +9,13 @@ 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;
+ struct hv_gpci_system_performance_capabilities caps;
} __packed __aligned(sizeof(uint64_t));
struct p arg = {
.params = {
.counter_request = cpu_to_be32(
- CIR_SYSTEM_PERFORMANCE_CAPABILITIES),
+ HV_GPCI_system_performance_capabilities),
.starting_index = cpu_to_be32(-1),
.counter_info_version_in = 0,
}
@@ -31,9 +31,9 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
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);
+ caps->ga = !!(arg.caps.capability_mask & HV_GPCI_CM_GA);
+ caps->expanded = !!(arg.caps.capability_mask & HV_GPCI_CM_EXPANDED);
+ caps->lab = !!(arg.caps.capability_mask & HV_GPCI_CM_LAB);
return r;
}
diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h
new file mode 100644
index 0000000..0dfc4d9
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci-requests.h
@@ -0,0 +1,79 @@
+
+#include "req-gen/_begin.h"
+
+/*
+ * Based on the document "getPerfCountInfo v1.07"
+ */
+
+/* this needs to be -1 encoded in hex suitable for parsing by tools/perf. */
+#define M1 0xffffffffffffffff
+
+/*
+ * #define REQUEST_NAME counter_request_name
+ * #define REQUEST_NUM r_num
+ * #define REQUEST_IDX_KIND starting_index_kind
+ * #include I(REQUEST_BEGIN)
+ * REQUEST(
+ * __field(...)
+ * __field(...)
+ * __array(...)
+ * __count(...)
+ * )
+ * #include I(REQUEST_END)
+ *
+ * - starting_index_kind is one of:
+ * M1: must be -1
+ * chip_id: hardware chip id or -1 for current hw chip
+ * phys_processor_idx:
+ *
+ * __count(offset, bytes, name):
+ * a counter that should be exposed via perf
+ * __field(offset, bytes, name)
+ * a normal field
+ * __array(offset, bytes, name)
+ * an array of bytes
+ *
+ *
+ * @bytes for __count, and __field _must_ be a numeral token
+ * in decimal, not an expression and not in hex.
+ *
+ *
+ * TODO:
+ * - expose secondary index (if any counter ever uses it, only 0xA0
+ * appears to use it right now, and it doesn't have any counters)
+ * - embed versioning info
+ * - include counter descriptions
+ */
+#define REQUEST_NAME dispatch_timebase_by_processor
+#define REQUEST_NUM 0x10
+#define REQUEST_IDX_KIND phys_processor_idx
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, processor_time_in_timebase_cycles)
+ __field(0x8, 4, hw_processor_id)
+ __field(0xC, 2, owning_part_id)
+ __field(0xE, 1, processor_state)
+ __field(0xF, 1, version)
+ __field(0x10, 4, hw_chip_id)
+ __field(0x14, 4, phys_module_id)
+ __field(0x18, 4, primary_affinity_domain_idx)
+ __field(0x1C, 4, secondary_affinity_domain_idx)
+ __field(0x20, 4, processor_version)
+ __field(0x24, 2, logical_processor_idx)
+ __field(0x26, 2, reserved)
+ __field(0x28, 4, processor_id_register)
+ __field(0x2C, 4, phys_processor_idx)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_performance_capabilities
+#define REQUEST_NUM 0x40
+#define REQUEST_IDX_KIND M1
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 1, perf_collect_privileged)
+ __field(0x1, 1 , capability_mask)
+ __array(0x2, 0xE, reserved)
+)
+#include I(REQUEST_END)
+
+#undef M1
+#include "req-gen/_end.h"
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 15fc76c..0c8e1c3 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -57,6 +57,11 @@ static struct attribute_group format_group = {
.attrs = format_attrs,
};
+static struct attribute_group event_group = {
+ .name = "events",
+ .attrs = hv_gpci_event_attrs,
+};
+
#define HV_CAPS_ATTR(_name, _format) \
static ssize_t _name##_show(struct device *dev, \
struct device_attribute *attr, \
@@ -102,6 +107,7 @@ static struct attribute_group interface_group = {
static const struct attribute_group *attr_groups[] = {
&format_group,
+ &event_group,
&interface_group,
NULL,
};
@@ -271,6 +277,8 @@ static int hv_gpci_init(void)
unsigned long hret;
struct hv_perf_caps caps;
+ hv_gpci_assert_offsets_correct();
+
if (!firmware_has_feature(FW_FEATURE_LPAR)) {
pr_debug("not a virtualized system, not enabling\n");
return -ENODEV;
diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h
index b25f460..86ede82 100644
--- a/arch/powerpc/perf/hv-gpci.h
+++ b/arch/powerpc/perf/hv-gpci.h
@@ -42,32 +42,19 @@ struct hv_get_perf_counter_info_params {
*/
#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,
+/* capability mask masks. */
+enum {
+ HV_GPCI_CM_GA = (1 << 7),
+ HV_GPCI_CM_EXPANDED = (1 << 6),
+ HV_GPCI_CM_LAB = (1 << 5)
};
-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;
+#define REQUEST_FILE "../hv-gpci-requests.h"
+#define NAME_LOWER hv_gpci
+#define NAME_UPPER HV_GPCI
+#include "req-gen/perf.h"
+#undef REQUEST_FILE
+#undef NAME_LOWER
+#undef NAME_UPPER
#endif
diff --git a/arch/powerpc/perf/req-gen/_begin.h b/arch/powerpc/perf/req-gen/_begin.h
new file mode 100644
index 0000000..acfb17a
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_begin.h
@@ -0,0 +1,13 @@
+/* Include paths to be used in interface defining headers */
+#ifndef POWERPC_PERF_REQ_GEN_H_
+#define POWERPC_PERF_REQ_GEN_H_
+
+#define CAT2_STR_(t, s) __stringify(t/s)
+#define CAT2_STR(t, s) CAT2_STR_(t, s)
+#define I(...) __VA_ARGS__
+
+#endif
+
+#define REQ_GEN_PREFIX req-gen
+#define REQUEST_BEGIN CAT2_STR(REQ_GEN_PREFIX, _request-begin.h)
+#define REQUEST_END CAT2_STR(REQ_GEN_PREFIX, _request-end.h)
diff --git a/arch/powerpc/perf/req-gen/_clear.h b/arch/powerpc/perf/req-gen/_clear.h
new file mode 100644
index 0000000..422974f
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_clear.h
@@ -0,0 +1,5 @@
+
+#undef __field_
+#undef __count_
+#undef __array_
+#undef REQUEST_
diff --git a/arch/powerpc/perf/req-gen/_end.h b/arch/powerpc/perf/req-gen/_end.h
new file mode 100644
index 0000000..8a40698
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_end.h
@@ -0,0 +1,4 @@
+
+#undef REQ_GEN_PREFIX
+#undef REQUEST_BEGIN
+#undef REQUEST_END
diff --git a/arch/powerpc/perf/req-gen/_request-begin.h b/arch/powerpc/perf/req-gen/_request-begin.h
new file mode 100644
index 0000000..f6d9864
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_request-begin.h
@@ -0,0 +1,15 @@
+
+#define REQUEST(r_contents) \
+ REQUEST_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, I(r_contents))
+
+#define __field(f_offset, f_bytes, f_name) \
+ __field_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
+
+#define __array(f_offset, f_bytes, f_name) \
+ __array_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
+
+#define __count(f_offset, f_bytes, f_name) \
+ __count_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
diff --git a/arch/powerpc/perf/req-gen/_request-end.h b/arch/powerpc/perf/req-gen/_request-end.h
new file mode 100644
index 0000000..5573be6
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_request-end.h
@@ -0,0 +1,8 @@
+#undef REQUEST
+#undef __field
+#undef __array
+#undef __count
+
+#undef REQUEST_NAME
+#undef REQUEST_NUM
+#undef REQUEST_IDX_KIND
diff --git a/arch/powerpc/perf/req-gen/perf.h b/arch/powerpc/perf/req-gen/perf.h
new file mode 100644
index 0000000..591d663
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/perf.h
@@ -0,0 +1,155 @@
+#ifndef LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+#define LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+
+#include <linux/perf_event.h>
+
+#ifndef REQUEST_FILE
+#error "REQUEST_FILE must be defined before including"
+#endif
+
+#ifndef NAME_LOWER
+#error "NAME_LOWER must be defined before including"
+#endif
+
+#ifndef NAME_UPPER
+#error "NAME_UPPER must be defined before including"
+#endif
+
+#define BE_TYPE_b1 __u8
+#define BE_TYPE_b2 __be16
+#define BE_TYPE_b4 __be32
+#define BE_TYPE_b8 __be64
+
+#define BYTES_TO_BE_TYPE(bytes) \
+ BE_TYPE_b##bytes
+
+#define CAT2_(a, b) a ## b
+#define CAT2(a, b) CAT2_(a, b)
+#define CAT3_(a, b, c) a ## b ## c
+#define CAT3(a, b, c) CAT3_(a, b, c)
+
+/*
+ * enumerate the request values as
+ * <NAME_UPPER>_<request name> = <request value>
+ */
+#define REQUEST_VALUE__(name_upper, r_name) name_upper ## _ ## r_name
+#define REQUEST_VALUE_(name_upper, r_name) REQUEST_VALUE__(name_upper, r_name)
+#define REQUEST_VALUE(r_name) REQUEST_VALUE_(NAME_UPPER, r_name)
+
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ REQUEST_VALUE(r_name) = r_value,
+enum CAT2(NAME_LOWER, _requests) {
+#include REQUEST_FILE
+};
+
+/*
+ * For each request:
+ * struct <NAME_LOWER>_<request name> {
+ * r_fields
+ * };
+ */
+#include "_clear.h"
+#define STRUCT_NAME__(name_lower, r_name) name_lower ## _ ## r_name
+#define STRUCT_NAME_(name_lower, r_name) STRUCT_NAME__(name_lower, r_name)
+#define STRUCT_NAME(r_name) STRUCT_NAME_(NAME_LOWER, r_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+struct STRUCT_NAME(r_name) { \
+ r_fields \
+};
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+ BYTES_TO_BE_TYPE(f_bytes) f_name;
+#define __count_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+ __field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_bytes, a_name) \
+ __u8 a_name[a_bytes];
+
+#include REQUEST_FILE
+
+/*
+ * Generate a check of the field offsets
+ * <NAME_LOWER>_assert_offsets_correct()
+ */
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, index, r_fields) \
+r_fields
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name) \
+ BUILD_BUG_ON(offsetof(struct STRUCT_NAME(r_name), f_name) != f_offset);
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+ __field_(r_name, r_value, r_idx_1, c_offset, c_size, c_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name) \
+ __field_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+
+static inline void CAT2(NAME_LOWER, _assert_offsets_correct)(void)
+{
+#include REQUEST_FILE
+}
+
+/*
+ * Generate event attributes:
+ * PMU_EVENT_ATTR_STRING(<request name>_<field name>,
+ * <NAME_LOWER>_event_attr_<request name>_<field name>,
+ * "request=<request value>"
+ * "starting_index=<starting index type>"
+ * "counter_info_version=CURRENT_COUNTER_INFO_VERSION"
+ * "length=<f_size>"
+ * "offset=<f_offset>")
+ *
+ * TODO: counter_info_version may need to vary, we should interperate the
+ * value to some extent
+ */
+#define EVENT_ATTR_NAME__(name, r_name, c_name) \
+ name ## _event_attr_ ## r_name ## _ ## c_name
+#define EVENT_ATTR_NAME_(name, r_name, c_name) \
+ EVENT_ATTR_NAME__(name, r_name, c_name)
+#define EVENT_ATTR_NAME(r_name, c_name) \
+ EVENT_ATTR_NAME_(NAME_LOWER, r_name, c_name)
+
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+PMU_EVENT_ATTR_STRING( \
+ CAT3(r_name, _, c_name), \
+ EVENT_ATTR_NAME(r_name, c_name), \
+ "request=" __stringify(r_value) "," \
+ "starting_index=" __stringify(r_idx_1) "," \
+ "counter_info_version=" \
+ __stringify(COUNTER_INFO_VERSION_CURRENT) "," \
+ "length=" #c_size "," \
+ "offset=" #c_offset)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ r_fields
+
+#include REQUEST_FILE
+
+/*
+ * Define event attribute array
+ * static struct attribute *hv_gpci_event_attrs[] = {
+ * &<NAME_LOWER>_event_attr_<request name>_<field name>.attr,
+ * };
+ */
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+ &EVENT_ATTR_NAME(r_name, c_name).attr.attr,
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ r_fields
+
+static __maybe_unused struct attribute *hv_gpci_event_attrs[] = {
+#include REQUEST_FILE
+ NULL
+};
+
+/* cleanup */
+#include "_clear.h"
+#undef EVENT_ATTR_NAME
+#undef EVENT_ATTR_NAME_
+#undef BIT_NAME
+#undef BIT_NAME_
+#undef STRUCT_NAME
+#undef REQUEST_VALUE
+#undef REQUEST_VALUE_
+
+#endif
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 05/10] perf: add PMU_EVENT_ATTR_STRING() helper
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Helper for constructing static struct perf_pmu_events_attr s.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
include/linux/perf_event.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index da442a0..4840c7f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -903,6 +903,13 @@ static struct perf_pmu_events_attr _var = { \
.id = _id, \
};
+#define PMU_EVENT_ATTR_STRING(_name, _var, _value) \
+static struct perf_pmu_events_attr _var = { \
+ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
+ .event_str = _value, \
+};
+
+
#define PMU_FORMAT_ATTR(_name, _format) \
static ssize_t \
_name##_show(struct device *dev, \
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 03/10] perf: provide sysfs_show for struct perf_pmu_events_attr
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
(struct perf_pmu_events_attr) is defined in include/linux/perf_event.h,
but the only "show" for it is in x86 and contains x86 specific stuff.
Make a generic one for those of us who are just using the event_str.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
include/linux/perf_event.h | 3 +++
kernel/events/core.c | 8 ++++++++
2 files changed, 11 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d0..da442a0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -894,6 +894,9 @@ struct perf_pmu_events_attr {
const char *event_str;
};
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page);
+
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, _show, NULL), \
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 733c616..9ef60e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8210,6 +8210,14 @@ void __init perf_event_init(void)
!= 1024);
}
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr =
+ container_of(attr, struct perf_pmu_events_attr, attr);
+ return sprintf(page, "%s\n", pmu_attr->event_str);
+}
+
static int __init perf_event_sysfs_init(void)
{
struct pmu *pmu;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 04/10] powerpc/perf/hv-24x7: parse catalog and populate sysfs with events
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Retrieves and parses the 24x7 catalog on POWER systems that supply it
(right now, only POWER 8). Events are exposed via sysfs in the standard
fashion, and are all parameterized.
Catalog is (at the moment) only parsed on boot. It needs re-parsing
when a some hypervisor events occur. At that point we'll also need to
prevent old events from continuing to function (counter that is passed
in via spare space in the config values?).
Changelog[v6]
[Sukadev Bhattiprolu] Use PHYS and VCPU in place of PHYSICAL and
VIRTUAL_PROCESSOR to shorten the names of the domains and hence,
events;
Changelog[v2]
[Joe Perches, David Laight] Use beNN_to_cpu() instead of guessing
the size from type.
Use kmem_cache_free() to free page allocated with kmem_cache_alloc().
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-24x7-catalog.h | 25 ++
arch/powerpc/perf/hv-24x7-domains.h | 28 ++
arch/powerpc/perf/hv-24x7.c | 787 +++++++++++++++++++++++++++++++++++-
arch/powerpc/perf/hv-24x7.h | 12 +-
4 files changed, 838 insertions(+), 14 deletions(-)
create mode 100644 arch/powerpc/perf/hv-24x7-domains.h
diff --git a/arch/powerpc/perf/hv-24x7-catalog.h b/arch/powerpc/perf/hv-24x7-catalog.h
index 21b19dd..69e2e1f 100644
--- a/arch/powerpc/perf/hv-24x7-catalog.h
+++ b/arch/powerpc/perf/hv-24x7-catalog.h
@@ -30,4 +30,29 @@ struct hv_24x7_catalog_page_0 {
__u8 reserved6[2];
} __packed;
+struct hv_24x7_event_data {
+ __be16 length; /* in bytes, must be a multiple of 16 */
+ __u8 reserved1[2];
+ __u8 domain; /* Chip = 1, Core = 2 */
+ __u8 reserved2[1];
+ __be16 event_group_record_offs; /* in bytes, must be 8 byte aligned */
+ __be16 event_group_record_len; /* in bytes */
+
+ /* in bytes, offset from event_group_record */
+ __be16 event_counter_offs;
+
+ /* verified_state, unverified_state, caveat_state, broken_state, ... */
+ __be32 flags;
+
+ __be16 primary_group_ix;
+ __be16 group_count;
+ __be16 event_name_len;
+ __u8 remainder[];
+ /* __u8 event_name[event_name_len - 2]; */
+ /* __be16 event_description_len; */
+ /* __u8 event_desc[event_description_len - 2]; */
+ /* __be16 detailed_desc_len; */
+ /* __u8 detailed_desc[detailed_desc_len - 2]; */
+} __packed;
+
#endif
diff --git a/arch/powerpc/perf/hv-24x7-domains.h b/arch/powerpc/perf/hv-24x7-domains.h
new file mode 100644
index 0000000..49c1efd
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7-domains.h
@@ -0,0 +1,28 @@
+
+/*
+ * DOMAIN(name, num, index_kind, is_physical)
+ *
+ * @name: An all caps token, suitable for use in generating an enum
+ * member and appending to an event name in sysfs.
+ *
+ * @num: The number corresponding to the domain as given in
+ * documentation. We assume the catalog domain and the hcall
+ * domain have the same numbering (so far they do), but this
+ * may need to be changed in the future.
+ *
+ * @index_kind: A stringifiable token describing the meaning of the index
+ * within the given domain. Must fit the parsing rules of the
+ * perf sysfs api.
+ *
+ * @is_physical: True if the domain is physical, false otherwise (if virtual).
+ *
+ * Note: The terms PHYS_CHIP, PHYS_CORE, VCPU correspond to physical chip,
+ * physical core and virtual processor in 24x7 Counters specifications.
+ */
+
+DOMAIN(PHYS_CHIP, 0x01, chip, true)
+DOMAIN(PHYS_CORE, 0x02, core, true)
+DOMAIN(VCPU_HOME_CORE, 0x03, vcpu, false)
+DOMAIN(VCPU_HOME_CHIP, 0x04, vcpu, false)
+DOMAIN(VCPU_HOME_NODE, 0x05, vcpu, false)
+DOMAIN(VCPU_REMOTE_NODE, 0x06, vcpu, false)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 9427ef7..f13e2ea 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -13,16 +13,80 @@
#define pr_fmt(fmt) "hv-24x7: " fmt
#include <linux/perf_event.h>
+#include <linux/rbtree.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
#include <asm/firmware.h>
#include <asm/hvcall.h>
#include <asm/io.h>
+#include <linux/byteorder/generic.h>
#include "hv-24x7.h"
#include "hv-24x7-catalog.h"
#include "hv-common.h"
+static const char *domain_to_index_string(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ return #x;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ default:
+ WARN(1, "unknown domain %d\n", domain);
+ return "UNKNOWN_DOMAIN_INDEX_STRING";
+ }
+}
+
+static const char *event_domain_suffix(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ return "__" #n;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ default:
+ WARN(1, "unknown domain %d\n", domain);
+ return "__UNKNOWN_DOMAIN_SUFFIX";
+ }
+}
+
+static bool domain_is_valid(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ /* fall through */
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool is_physical_domain(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ return c;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ default:
+ return false;
+ }
+}
+
+static bool catalog_entry_domain_is_valid(unsigned domain)
+{
+ return is_physical_domain(domain);
+}
+
/*
* TODO: Merging events:
* - Think of the hcall as an interface to a 4d array of counters:
@@ -73,8 +137,115 @@ static struct attribute_group format_group = {
.attrs = format_attrs,
};
+static struct attribute_group event_group = {
+ .name = "events",
+ /* .attrs is set in init */
+};
+
+static struct attribute_group event_desc_group = {
+ .name = "event_descs",
+ /* .attrs is set in init */
+};
+
+static struct attribute_group event_long_desc_group = {
+ .name = "event_long_descs",
+ /* .attrs is set in init */
+};
+
static struct kmem_cache *hv_page_cache;
+static char *event_name(struct hv_24x7_event_data *ev, int *len)
+{
+ *len = be16_to_cpu(ev->event_name_len) - 2;
+ return (char *)ev->remainder;
+}
+
+static char *event_desc(struct hv_24x7_event_data *ev, int *len)
+{
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+ __be16 *desc_len = (__be16 *)(ev->remainder + nl - 2);
+ *len = be16_to_cpu(*desc_len) - 2;
+ return (char *)ev->remainder + nl;
+}
+
+static char *event_long_desc(struct hv_24x7_event_data *ev, int *len)
+{
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+ __be16 *desc_len_ = (__be16 *)(ev->remainder + nl - 2);
+ unsigned desc_len = be16_to_cpu(*desc_len_);
+ __be16 *long_desc_len = (__be16 *)(ev->remainder + nl + desc_len - 2);
+ *len = be16_to_cpu(*long_desc_len) - 2;
+ return (char *)ev->remainder + nl + desc_len;
+}
+
+static bool event_fixed_portion_is_within(struct hv_24x7_event_data *ev,
+ void *end)
+{
+ void *start = ev;
+
+ return (start + offsetof(struct hv_24x7_event_data, remainder)) < end;
+}
+
+/*
+ * Things we don't check:
+ * - padding for desc, name, and long/detailed desc is required to be '\0'
+ * bytes.
+ *
+ * Return NULL if we pass end,
+ * Otherwise return the address of the byte just following the event.
+ */
+static void *event_end(struct hv_24x7_event_data *ev, void *end)
+{
+ void *start = ev;
+ __be16 *dl_, *ldl_;
+ unsigned dl, ldl;
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+
+ if (nl < 2) {
+ pr_debug("%s: name length too short: %d", __func__, nl);
+ return NULL;
+ }
+
+ if (start + nl > end) {
+ pr_debug("%s: start=%p + nl=%u > end=%p",
+ __func__, start, nl, end);
+ return NULL;
+ }
+
+ dl_ = (__be16 *)(ev->remainder + nl - 2);
+ if (!IS_ALIGNED((uintptr_t)dl_, 2))
+ pr_warn("desc len not aligned %p", dl_);
+ dl = be16_to_cpu(*dl_);
+ if (dl < 2) {
+ pr_debug("%s: desc len too short: %d", __func__, dl);
+ return NULL;
+ }
+
+ if (start + nl + dl > end) {
+ pr_debug("%s: (start=%p + nl=%u + dl=%u)=%p > end=%p",
+ __func__, start, nl, dl, start + nl + dl, end);
+ return NULL;
+ }
+
+ ldl_ = (__be16 *)(ev->remainder + nl + dl - 2);
+ if (!IS_ALIGNED((uintptr_t)ldl_, 2))
+ pr_warn("long desc len not aligned %p", ldl_);
+ ldl = be16_to_cpu(*ldl_);
+ if (ldl < 2) {
+ pr_debug("%s: long desc len too short (ldl=%u)",
+ __func__, ldl);
+ return NULL;
+ }
+
+ if (start + nl + dl + ldl > end) {
+ pr_debug("%s: start=%p + nl=%u + dl=%u + ldl=%u > end=%p",
+ __func__, start, nl, dl, ldl, end);
+ return NULL;
+ }
+
+ return start + nl + dl + ldl;
+}
+
static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
unsigned long version,
unsigned long index)
@@ -97,6 +268,605 @@ static unsigned long h_get_24x7_catalog_page(char page[],
version, index);
}
+static unsigned core_domains[] = {
+ HV_PERF_DOMAIN_PHYS_CORE,
+ HV_PERF_DOMAIN_VCPU_HOME_CORE,
+ HV_PERF_DOMAIN_VCPU_HOME_CHIP,
+ HV_PERF_DOMAIN_VCPU_HOME_NODE,
+ HV_PERF_DOMAIN_VCPU_REMOTE_NODE,
+};
+/* chip event data always yeilds a single event, core yeilds multiple */
+#define MAX_EVENTS_PER_EVENT_DATA ARRAY_SIZE(core_domains)
+
+static char *event_fmt(struct hv_24x7_event_data *event, unsigned domain)
+{
+ const char *lpar;
+
+ if (is_physical_domain(domain))
+ lpar = "0x0";
+ else
+ lpar = "sibling_guest_id";
+
+ return kasprintf(GFP_KERNEL,
+ "domain=0x%x,offset=0x%x,starting_index=%s,lpar=%s",
+ domain,
+ be16_to_cpu(event->event_counter_offs) +
+ be16_to_cpu(event->event_group_record_offs),
+ domain_to_index_string(domain),
+ lpar);
+}
+
+/* Avoid trusting fw to NUL terminate strings */
+static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
+{
+ return kasprintf(gfp, "%.*s", max_len, maybe_str);
+}
+
+static ssize_t device_show_string(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dev_ext_attribute *d;
+
+ d = container_of(attr, struct dev_ext_attribute, attr);
+ return sprintf(buf, "%s\n", (char *)d->var);
+}
+
+static struct attribute *device_str_attr_create_(char *name, char *str)
+{
+ struct dev_ext_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+
+ if (!attr)
+ return NULL;
+
+ attr->var = str;
+ attr->attr.attr.name = name;
+ attr->attr.attr.mode = 0444;
+ attr->attr.show = device_show_string;
+ return &attr->attr.attr;
+}
+
+static struct attribute *device_str_attr_create(char *name, int name_max,
+ int name_nonce,
+ char *str, size_t str_max)
+{
+ char *n;
+ char *s = memdup_to_str(str, str_max, GFP_KERNEL);
+ struct attribute *a;
+
+ if (!s)
+ return NULL;
+
+ if (!name_nonce)
+ n = kasprintf(GFP_KERNEL, "%.*s", name_max, name);
+ else
+ n = kasprintf(GFP_KERNEL, "%.*s__%d", name_max, name,
+ name_nonce);
+ if (!n)
+ goto out_s;
+
+ a = device_str_attr_create_(n, s);
+ if (!a)
+ goto out_n;
+
+ return a;
+out_n:
+ kfree(n);
+out_s:
+ kfree(s);
+ return NULL;
+}
+
+static void device_str_attr_destroy(struct attribute *attr)
+{
+ struct dev_ext_attribute *d;
+
+ d = container_of(attr, struct dev_ext_attribute, attr.attr);
+ kfree(d->var);
+ kfree(d->attr.attr.name);
+ kfree(d);
+}
+
+static struct attribute *event_to_attr(unsigned ix,
+ struct hv_24x7_event_data *event,
+ unsigned domain,
+ int nonce)
+{
+ int event_name_len;
+ char *ev_name, *a_ev_name, *val;
+ const char *ev_suffix;
+ struct attribute *attr;
+
+ if (!domain_is_valid(domain)) {
+ pr_warn("catalog event %u has invalid domain %u\n",
+ ix, domain);
+ return NULL;
+ }
+
+ val = event_fmt(event, domain);
+ if (!val)
+ return NULL;
+
+ ev_suffix = event_domain_suffix(domain);
+ ev_name = event_name(event, &event_name_len);
+ if (!nonce)
+ a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s",
+ (int)event_name_len, ev_name, ev_suffix);
+ else
+ a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s__%d",
+ (int)event_name_len, ev_name, ev_suffix, nonce);
+
+
+ if (!a_ev_name)
+ goto out_val;
+
+ attr = device_str_attr_create_(a_ev_name, val);
+ if (!attr)
+ goto out_name;
+
+ return attr;
+out_name:
+ kfree(a_ev_name);
+out_val:
+ kfree(val);
+ return NULL;
+}
+
+static struct attribute *event_to_desc_attr(struct hv_24x7_event_data *event,
+ int nonce)
+{
+ int nl, dl;
+ char *name = event_name(event, &nl);
+ char *desc = event_desc(event, &dl);
+
+ /* If there isn't a description, don't create the sysfs file */
+ if (!dl)
+ return NULL;
+
+ return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static struct attribute *
+event_to_long_desc_attr(struct hv_24x7_event_data *event, int nonce)
+{
+ int nl, dl;
+ char *name = event_name(event, &nl);
+ char *desc = event_long_desc(event, &dl);
+
+ /* If there isn't a description, don't create the sysfs file */
+ if (!dl)
+ return NULL;
+
+ return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static ssize_t event_data_to_attrs(unsigned ix, struct attribute **attrs,
+ struct hv_24x7_event_data *event, int nonce)
+{
+ unsigned i;
+
+ switch (event->domain) {
+ case HV_PERF_DOMAIN_PHYS_CHIP:
+ *attrs = event_to_attr(ix, event, event->domain, nonce);
+ return 1;
+ case HV_PERF_DOMAIN_PHYS_CORE:
+ for (i = 0; i < ARRAY_SIZE(core_domains); i++) {
+ attrs[i] = event_to_attr(ix, event, core_domains[i],
+ nonce);
+ if (!attrs[i]) {
+ pr_warn("catalog event %u: individual attr %u "
+ "creation failure\n", ix, i);
+ for (; i; i--)
+ device_str_attr_destroy(attrs[i - 1]);
+ return -1;
+ }
+ }
+ return i;
+ default:
+ pr_warn("catalog event %u: domain %u is not allowed in the "
+ "catalog\n", ix, event->domain);
+ return -1;
+ }
+}
+
+static size_t event_to_attr_ct(struct hv_24x7_event_data *event)
+{
+ switch (event->domain) {
+ case HV_PERF_DOMAIN_PHYS_CHIP:
+ return 1;
+ case HV_PERF_DOMAIN_PHYS_CORE:
+ return ARRAY_SIZE(core_domains);
+ default:
+ return 0;
+ }
+}
+
+static unsigned long vmalloc_to_phys(void *v)
+{
+ struct page *p = vmalloc_to_page(v);
+
+ BUG_ON(!p);
+ return page_to_phys(p) + offset_in_page(v);
+}
+
+/* */
+struct event_uniq {
+ struct rb_node node;
+ const char *name;
+ int nl;
+ unsigned ct;
+ unsigned domain;
+};
+
+static int memord(const void *d1, size_t s1, const void *d2, size_t s2)
+{
+ if (s1 < s2)
+ return 1;
+ if (s2 > s1)
+ return -1;
+
+ return memcmp(d1, d2, s1);
+}
+
+static int ev_uniq_ord(const void *v1, size_t s1, unsigned d1, const void *v2,
+ size_t s2, unsigned d2)
+{
+ int r = memord(v1, s1, v2, s2);
+
+ if (r)
+ return r;
+ if (d1 > d2)
+ return 1;
+ if (d2 > d1)
+ return -1;
+ return 0;
+}
+
+static int event_uniq_add(struct rb_root *root, const char *name, int nl,
+ unsigned domain)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct event_uniq *data;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct event_uniq *it;
+ int result;
+
+ it = container_of(*new, struct event_uniq, node);
+ result = ev_uniq_ord(name, nl, domain, it->name, it->nl,
+ it->domain);
+
+ parent = *new;
+ if (result < 0)
+ new = &((*new)->rb_left);
+ else if (result > 0)
+ new = &((*new)->rb_right);
+ else {
+ it->ct++;
+ pr_info("found a duplicate event %.*s, ct=%u\n", nl,
+ name, it->ct);
+ return it->ct;
+ }
+ }
+
+ data = kmalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ *data = (struct event_uniq) {
+ .name = name,
+ .nl = nl,
+ .ct = 0,
+ .domain = domain,
+ };
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+
+ /* data->ct */
+ return 0;
+}
+
+static void event_uniq_destroy(struct rb_root *root)
+{
+ /*
+ * the strings we point to are in the giant block of memory filled by
+ * the catalog, and are freed seperately.
+ */
+ struct event_uniq *pos, *n;
+
+ rbtree_postorder_for_each_entry_safe(pos, n, root, node)
+ kfree(pos);
+}
+
+
+/*
+ * ensure the event structure's sizes are self consistent and don't cause us to
+ * read outside of the event
+ *
+ * On success, return the event length in bytes.
+ * Otherwise, return -1 (and print as appropriate).
+ */
+static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
+ size_t event_idx,
+ size_t event_data_bytes,
+ size_t event_entry_count,
+ size_t offset, void *end)
+{
+ ssize_t ev_len;
+ void *ev_end, *calc_ev_end;
+
+ if (offset >= event_data_bytes)
+ return -1;
+
+ if (event_idx >= event_entry_count) {
+ pr_devel("catalog event data has %zu bytes of padding after last event\n",
+ event_data_bytes - offset);
+ return -1;
+ }
+
+ if (!event_fixed_portion_is_within(event, end)) {
+ pr_warn("event %zu fixed portion is not within range\n",
+ event_idx);
+ return -1;
+ }
+
+ ev_len = be16_to_cpu(event->length);
+
+ if (ev_len % 16)
+ pr_info("event %zu has length %zu not divisible by 16: event=%pK\n",
+ event_idx, ev_len, event);
+
+ ev_end = (__u8 *)event + ev_len;
+ if (ev_end > end) {
+ pr_warn("event %zu has .length=%zu, ends after buffer end: ev_end=%pK > end=%pK, offset=%zu\n",
+ event_idx, ev_len, ev_end, end,
+ offset);
+ return -1;
+ }
+
+ calc_ev_end = event_end(event, end);
+ if (!calc_ev_end) {
+ pr_warn("event %zu has a calculated length which exceeds buffer length %zu: event=%pK end=%pK, offset=%zu\n",
+ event_idx, event_data_bytes, event, end,
+ offset);
+ return -1;
+ }
+
+ if (calc_ev_end > ev_end) {
+ pr_warn("event %zu exceeds it's own length: event=%pK, end=%pK, offset=%zu, calc_ev_end=%pK\n",
+ event_idx, event, ev_end, offset, calc_ev_end);
+ return -1;
+ }
+
+ return ev_len;
+}
+
+#define MAX_4K (SIZE_MAX / 4096)
+
+static void create_events_from_catalog(struct attribute ***events_,
+ struct attribute ***event_descs_,
+ struct attribute ***event_long_descs_)
+{
+ unsigned long hret;
+ size_t catalog_len, catalog_page_len, event_entry_count,
+ event_data_len, event_data_offs,
+ event_data_bytes, junk_events, event_idx, event_attr_ct, i,
+ attr_max, event_idx_last, desc_ct, long_desc_ct;
+ ssize_t ct, ev_len;
+ uint32_t catalog_version_num;
+ struct attribute **events, **event_descs, **event_long_descs;
+ struct hv_24x7_catalog_page_0 *page_0 =
+ kmem_cache_alloc(hv_page_cache, GFP_KERNEL);
+ void *page = page_0;
+ void *event_data, *end;
+ struct hv_24x7_event_data *event;
+ struct rb_root ev_uniq = RB_ROOT;
+
+ if (!page)
+ goto e_out;
+
+ hret = h_get_24x7_catalog_page(page, 0, 0);
+ if (hret)
+ goto e_free;
+
+ catalog_version_num = be64_to_cpu(page_0->version);
+ catalog_page_len = be32_to_cpu(page_0->length);
+
+ if (MAX_4K < catalog_page_len) {
+ pr_err("invalid page count: %zu\n", catalog_page_len);
+ goto e_free;
+ }
+
+ catalog_len = catalog_page_len * 4096;
+
+ event_entry_count = be16_to_cpu(page_0->event_entry_count);
+ event_data_offs = be16_to_cpu(page_0->event_data_offs);
+ event_data_len = be16_to_cpu(page_0->event_data_len);
+
+ pr_devel("cv %zu cl %zu eec %zu edo %zu edl %zu\n",
+ (size_t)catalog_version_num, catalog_len,
+ event_entry_count, event_data_offs, event_data_len);
+
+ if ((MAX_4K < event_data_len)
+ || (MAX_4K < event_data_offs)
+ || (MAX_4K - event_data_offs < event_data_len)) {
+ pr_err("invalid event data offs %zu and/or len %zu\n",
+ event_data_offs, event_data_len);
+ goto e_free;
+ }
+
+ if ((event_data_offs + event_data_len) > catalog_page_len) {
+ pr_err("event data %zu-%zu does not fit inside catalog 0-%zu\n",
+ event_data_offs,
+ event_data_offs + event_data_len,
+ catalog_page_len);
+ goto e_free;
+ }
+
+ if (SIZE_MAX / MAX_EVENTS_PER_EVENT_DATA - 1 < event_entry_count) {
+ pr_err("event_entry_count %zu is invalid\n",
+ event_entry_count);
+ goto e_free;
+ }
+
+ event_data_bytes = event_data_len * 4096;
+
+ /*
+ * event data can span several pages, events can cross between these
+ * pages. Use vmalloc to make this easier.
+ */
+ event_data = vmalloc(event_data_bytes);
+ if (!event_data) {
+ pr_err("could not allocate event data\n");
+ goto e_free;
+ }
+
+ end = event_data + event_data_bytes;
+
+ /*
+ * using vmalloc_to_phys() like this only works if PAGE_SIZE is
+ * divisible by 4096
+ */
+ BUILD_BUG_ON(PAGE_SIZE % 4096);
+
+ for (i = 0; i < event_data_len; i++) {
+ hret = h_get_24x7_catalog_page_(
+ vmalloc_to_phys(event_data + i * 4096),
+ catalog_version_num,
+ i + event_data_offs);
+ if (hret) {
+ pr_err("failed to get event data in page %zu\n",
+ i + event_data_offs);
+ goto e_event_data;
+ }
+ }
+
+ /*
+ * scan the catalog to determine the number of attributes we need, and
+ * verify it at the same time.
+ */
+ for (junk_events = 0, event = event_data, event_idx = 0, attr_max = 0;
+ ;
+ event_idx++, event = (void *)event + ev_len) {
+ size_t offset = (void *)event - (void *)event_data;
+ char *name;
+ int nl;
+
+ ev_len = catalog_event_len_validate(event, event_idx,
+ event_data_bytes,
+ event_entry_count,
+ offset, end);
+ if (ev_len < 0)
+ break;
+
+ name = event_name(event, &nl);
+
+ if (event->event_group_record_len == 0) {
+ pr_devel("invalid event %zu (%.*s): group_record_len == 0, skipping\n",
+ event_idx, nl, name);
+ junk_events++;
+ continue;
+ }
+
+ if (!catalog_entry_domain_is_valid(event->domain)) {
+ pr_info("event %zu (%.*s) has invalid domain %d\n",
+ event_idx, nl, name, event->domain);
+ junk_events++;
+ continue;
+ }
+
+ attr_max += event_to_attr_ct(event);
+ }
+
+ event_idx_last = event_idx;
+ if (event_idx_last != event_entry_count)
+ pr_warn("event buffer ended before listed # of events were parsed (got %zu, wanted %zu, junk %zu)\n",
+ event_idx_last, event_entry_count, junk_events);
+
+ events = kmalloc_array(attr_max + 1, sizeof(*events), GFP_KERNEL);
+ if (!events)
+ goto e_event_data;
+
+ event_descs = kmalloc_array(event_idx + 1, sizeof(*event_descs),
+ GFP_KERNEL);
+ if (!event_descs)
+ goto e_event_attrs;
+
+ event_long_descs = kmalloc_array(event_idx + 1,
+ sizeof(*event_long_descs), GFP_KERNEL);
+ if (!event_long_descs)
+ goto e_event_descs;
+
+ /* Iterate over the catalog filling in the attribute vector */
+ for (junk_events = 0, event_attr_ct = 0, desc_ct = 0, long_desc_ct = 0,
+ event = event_data, event_idx = 0;
+ event_idx < event_idx_last;
+ event_idx++, ev_len = be16_to_cpu(event->length),
+ event = (void *)event + ev_len) {
+ char *name;
+ int nl;
+ int nonce;
+ /*
+ * these are the only "bad" events that are intermixed and that
+ * we can ignore without issue. make sure to skip them here
+ */
+ if (event->event_group_record_len == 0)
+ continue;
+ if (!catalog_entry_domain_is_valid(event->domain))
+ continue;
+
+ name = event_name(event, &nl);
+ nonce = event_uniq_add(&ev_uniq, name, nl, event->domain);
+ ct = event_data_to_attrs(event_idx, events + event_attr_ct,
+ event, nonce);
+ if (ct <= 0) {
+ pr_warn("event %zu (%.*s) creation failure, skipping\n",
+ event_idx, nl, name);
+ junk_events++;
+ } else {
+ event_attr_ct += ct;
+ event_descs[desc_ct] = event_to_desc_attr(event, nonce);
+ if (event_descs[desc_ct])
+ desc_ct++;
+ event_long_descs[long_desc_ct] =
+ event_to_long_desc_attr(event, nonce);
+ if (event_long_descs[long_desc_ct])
+ long_desc_ct++;
+ }
+ }
+
+ pr_info("read %zu catalog entries, created %zu event attrs (%zu failures), %zu descs\n",
+ event_idx, event_attr_ct, junk_events, desc_ct);
+
+ events[event_attr_ct] = NULL;
+ event_descs[desc_ct] = NULL;
+ event_long_descs[long_desc_ct] = NULL;
+
+ event_uniq_destroy(&ev_uniq);
+ vfree(event_data);
+ kmem_cache_free(hv_page_cache, page);
+
+ *events_ = events;
+ *event_descs_ = event_descs;
+ *event_long_descs_ = event_long_descs;
+ return;
+
+e_event_descs:
+ kfree(event_descs);
+e_event_attrs:
+ kfree(events);
+e_event_data:
+ vfree(event_data);
+e_free:
+ kmem_cache_free(hv_page_cache, page);
+e_out:
+ *events_ = NULL;
+ *event_descs_ = NULL;
+ *event_long_descs_ = NULL;
+}
+
static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr, char *buf,
loff_t offset, size_t count)
@@ -178,7 +948,7 @@ static ssize_t _name##_show(struct device *dev, \
} \
ret = sprintf(buf, _fmt, _expr); \
e_free: \
- kfree(page); \
+ kmem_cache_free(hv_page_cache, page); \
return ret; \
} \
static DEVICE_ATTR_RO(_name)
@@ -208,16 +978,13 @@ static struct attribute_group if_group = {
static const struct attribute_group *attr_groups[] = {
&format_group,
+ &event_group,
+ &event_desc_group,
+ &event_long_desc_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)
@@ -363,7 +1130,7 @@ static int h_24x7_event_init(struct perf_event *event)
return -EIO;
}
- /* PHYSICAL domains & other lpars require extra capabilities */
+ /* 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",
@@ -465,6 +1232,10 @@ static int hv_24x7_init(void)
/* sampling not supported */
h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+ create_events_from_catalog(&event_group.attrs,
+ &event_desc_group.attrs,
+ &event_long_desc_group.attrs);
+
r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
if (r)
return r;
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
index 720ebce..69cd4e6 100644
--- a/arch/powerpc/perf/hv-24x7.h
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -3,14 +3,14 @@
#include <linux/types.h>
+enum hv_perf_domains {
+#define DOMAIN(n, v, x, c) HV_PERF_DOMAIN_##n = v,
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+};
+
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];
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 02/10] tools/perf: extend format_alias() to include event parameters
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
This causes `perf list pmu` to show parameters for parameterized events
like follows:
pmu/event_name,param1=?,param2=?/ [Kernel PMU event]
An example:
hv_gpci/dispatch_timebase_by_processor_processor_time_in_timebase_cycles,phys_processor_idx=?/ [Kernel PMU event]
Changelog[v6]
[Jir Olsa] If the parameter for an event in sysfs is 'param=val',
have perf-list show the event as 'param=?' rather than 'val=?'.
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
tools/perf/util/pmu.c | 26 +++++++++++++++++++++++++-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 67e59b9..a05dd9d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -760,10 +760,33 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
set_bit(b, bits);
}
+static int sub_non_neg(int a, int b)
+{
+ if (b > a)
+ return 0;
+ return a - b;
+}
+
static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
struct perf_pmu_alias *alias)
{
- snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+ struct parse_events_term *term;
+ int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
+
+ list_for_each_entry(term, &alias->terms, list)
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+ used += snprintf(buf + used, sub_non_neg(len, used),
+ ",%s=?", term->config);
+
+ if (sub_non_neg(len, used) > 0) {
+ buf[used] = '/';
+ used++;
+ }
+ if (sub_non_neg(len, used) > 0) {
+ buf[used] = '\0';
+ used++;
+ } else
+ buf[len - 1] = '\0';
return buf;
}
@@ -814,6 +837,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
if (is_cpu && !name_only)
aliases[j] = format_alias_or(buf, sizeof(buf),
pmu, alias);
+
aliases[j] = strdup(aliases[j]);
j++;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 01/10] tools/perf: support parsing parameterized events
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586844-21381-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Enable event specification like:
pmu/event_name,param1=0x1,param2=0x4/
Assuming that
/sys/bus/event_source/devices/pmu/events/event_name
Contains something like
param2=foo,bar=1,param1=baz
Changelog[v4]:
[Jiri Olsa] Merge to recent perf-core and fix a small conflict.
Changelog[v3]:
[Jiri Olsa] If the sysfs event file specifies 'param=val', make the
usage 'hv_24x7/event,param=123/' rather than 'hv_24x7/event,val=123/'.
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Conflicts:
tools/perf/util/pmu.c
---
tools/perf/util/parse-events.h | 1 +
tools/perf/util/pmu.c | 65 +++++++++++++++++++++++++++++++++++-------
2 files changed, 55 insertions(+), 11 deletions(-)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index df094b4..9d7d2d5 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -59,6 +59,7 @@ struct parse_events_term {
int type_val;
int type_term;
struct list_head list;
+ bool used;
};
struct parse_events_evlist {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 22a4ad5..67e59b9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -511,31 +511,68 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
}
/*
+ * Term is a string term, and might be a param-term. Try to look up it's value
+ * in the remaining terms.
+ * - We have a term like "base-or-format-term=param-term",
+ * - We need to find the value supplied for "param-term" (with param-term named
+ * in a config string) later on in the term list.
+ */
+static int pmu_resolve_param_term(struct parse_events_term *term,
+ struct list_head *head_terms,
+ __u64 *value)
+{
+ struct parse_events_term *t;
+
+ list_for_each_entry(t, head_terms, list) {
+ if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+ if (!strcmp(t->config, term->config)) {
+ t->used = true;
+ *value = t->val.num;
+ return 0;
+ }
+ }
+ }
+
+ if (verbose)
+ printf("Required parameter '%s' not specified\n", term->config);
+
+ return -1;
+}
+
+/*
* Setup one of config[12] attr members based on the
* user input data - term parameter.
*/
static int pmu_config_term(struct list_head *formats,
struct perf_event_attr *attr,
struct parse_events_term *term,
+ struct list_head *head_terms,
bool zero)
{
struct perf_pmu_format *format;
__u64 *vp;
+ __u64 val;
+
+ /*
+ * If this is a parameter we've already used for parameterized-eval,
+ * skip it in normal eval.
+ */
+ if (term->used)
+ return 0;
/*
- * Support only for hardcoded and numnerial terms.
* Hardcoded terms should be already in, so nothing
* to be done for them.
*/
if (parse_events__is_hardcoded_term(term))
return 0;
- if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
- return -EINVAL;
-
format = pmu_find_format(formats, term->config);
- if (!format)
+ if (!format) {
+ if (verbose)
+ printf("Invalid event/parameter '%s'\n", term->config);
return -EINVAL;
+ }
switch (format->value) {
case PERF_PMU_FORMAT_VALUE_CONFIG:
@@ -552,11 +589,16 @@ static int pmu_config_term(struct list_head *formats,
}
/*
- * XXX If we ever decide to go with string values for
- * non-hardcoded terms, here's the place to translate
- * them into value.
+ * Either directly use a numeric term, or try to translate string terms
+ * using event parameters.
*/
- pmu_format_value(format->bits, term->val.num, vp, zero);
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+ val = term->val.num;
+ else
+ if (pmu_resolve_param_term(term, head_terms, &val))
+ return -EINVAL;
+
+ pmu_format_value(format->bits, val, vp, zero);
return 0;
}
@@ -567,9 +609,10 @@ int perf_pmu__config_terms(struct list_head *formats,
{
struct parse_events_term *term;
- list_for_each_entry(term, head_terms, list)
- if (pmu_config_term(formats, attr, term, zero))
+ list_for_each_entry(term, head_terms, list) {
+ if (pmu_config_term(formats, attr, term, head_terms, zero))
return -EINVAL;
+ }
return 0;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 00/10] Add support for parameterized events from sysfs
From: Sukadev Bhattiprolu @ 2014-09-24 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
What this patchset does:
- the first patch (override sysfs in tools/perf via SYSFS_PATH) was sent out
previously, but needed a resend anyhow. Having it is useful for testing the
later changes to tools/perf.
- the second patch is a bugfix to the powerpc hv-24x7 code which was
previously sent out, which is a good idea to have when testing these patches
on POWER8 hardware.
- document perf sysfs and the changes to add parameterized events
- semi-notably: removes the growing list of specific POWER cpu events and
begins documenting them generically, much like the docs for
/sys/modules/MODULENAME do for modules.
- tools/perf changes to support parameterized events
- export some parameterized events from the powerpc pmus hv_24x7 and hv_gpci
Description of "event parameters" from the documentation patch:
Event parameters are a basic way for partial events to be specified in
sysfs with per-event names given to the fields that need to be filled in
when using a particular event.
It is intended for supporting cases where the single 'cpu' parameter is
insufficient. For example, POWER 8 has events for physical
sockets/cores/cpus that are accessible from with virtual machines. To
keep using the single 'cpu' parameter we'd need to perform a mapping
between Linux's cpus and the physical machine's cpus (in this case
Linux is running under a hypervisor). This isn't possible because
bindings between our cpus and physical cpus may not be fixed, and we
probably won't have a "cpu" on each physical cpu.
Description of the sysfs contents when events are parameterized (copied from an
included patch):
Examples:
domain=0x1,offset=0x8,starting_index=phys_cpu
In the case of the last example, a value replacing "phys_cpu"
would need to be provided by the user selecting the particular
event. This is refered to as "event parameterization". All
non-numerical values indicate an event parameter.
Notes on how perf-list displays parameterized events (and how to use them,
again culled from an included patch):
PARAMETERIZED EVENTS
--------------------
Some pmu events listed by 'perf-list' will be displayed with '?' in
them. For example:
hv_gpci/dtbp_ptitc,phys_processor_idx=?/
This means that when provided as an event, a value for
phys_processor_idx must also be supplied. For example:
perf stat -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
Changelog[v4]
- [Jiri Olsa] Rebase to perf/core tree (fix small merge conflict)
Changelog[v3]
- [Jiri Olsa] Changed the event parameters are specified. If
event file specifes 'param=val' make the usage 'param=123'
rather than 'val=123'. (patch 1,2/10)
- Shortened event names using "PHYS" and "VCPU" (patch 4/10)
- Print help message if invalid parameter is specified or required
parameter is missing.
- Moved 3 patches that are unrelated to parametrized events into
a separate patchset.
- Reordered patches so code changes come first.
Changelog[v2]
- [Joe Perches, David Laight] Use beNN_to_cpu() instead of guessing
the size from type.
- Use kmem_cache_free() to free page allocated with kmem_cache_alloc().
- Rebase to recent kernel
Cody P Schafer (10):
tools/perf: support parsing parameterized events
tools/perf: extend format_alias() to include event parameters
perf: provide sysfs_show for struct perf_pmu_events_attr
powerpc/perf/hv-24x7: parse catalog and populate sysfs with events
perf: add PMU_EVENT_ATTR_STRING() helper
powerpc/perf/{hv-gpci,hv-common}: generate requests with counters
annotated
powerpc/perf/hv-gpci: add the remaining gpci requests
perf Documentation: add event parameters
tools/perf: Document parameterized and symbolic events
powerpc/perf/hv-24x7: Document sysfs event description entries
.../testing/sysfs-bus-event_source-devices-events | 6 +
.../testing/sysfs-bus-event_source-devices-hv_24x7 | 22 +
arch/powerpc/perf/hv-24x7-catalog.h | 25 +
arch/powerpc/perf/hv-24x7-domains.h | 28 +
arch/powerpc/perf/hv-24x7.c | 787 ++++++++++++++++++++-
arch/powerpc/perf/hv-24x7.h | 12 +-
arch/powerpc/perf/hv-common.c | 10 +-
arch/powerpc/perf/hv-gpci-requests.h | 262 +++++++
arch/powerpc/perf/hv-gpci.c | 8 +
arch/powerpc/perf/hv-gpci.h | 37 +-
arch/powerpc/perf/req-gen/_begin.h | 13 +
arch/powerpc/perf/req-gen/_clear.h | 5 +
arch/powerpc/perf/req-gen/_end.h | 4 +
arch/powerpc/perf/req-gen/_request-begin.h | 15 +
arch/powerpc/perf/req-gen/_request-end.h | 8 +
arch/powerpc/perf/req-gen/perf.h | 155 ++++
include/linux/perf_event.h | 10 +
kernel/events/core.c | 8 +
tools/perf/Documentation/perf-list.txt | 13 +
tools/perf/Documentation/perf-record.txt | 12 +
tools/perf/Documentation/perf-stat.txt | 20 +-
tools/perf/util/parse-events.h | 1 +
tools/perf/util/pmu.c | 91 ++-
23 files changed, 1492 insertions(+), 60 deletions(-)
create mode 100644 arch/powerpc/perf/hv-24x7-domains.h
create mode 100644 arch/powerpc/perf/hv-gpci-requests.h
create mode 100644 arch/powerpc/perf/req-gen/_begin.h
create mode 100644 arch/powerpc/perf/req-gen/_clear.h
create mode 100644 arch/powerpc/perf/req-gen/_end.h
create mode 100644 arch/powerpc/perf/req-gen/_request-begin.h
create mode 100644 arch/powerpc/perf/req-gen/_request-end.h
create mode 100644 arch/powerpc/perf/req-gen/perf.h
--
1.8.3.1
^ permalink raw reply
* [PATCH v2 4/4] perf Documentation: remove duplicated docs for powerpc cpu specific events
From: Sukadev Bhattiprolu @ 2014-09-24 19:24 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586681-21262-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Listing specific events doesn't actually help us at all here because:
- these events actually vary between different ppc processors, they
aren't garunteed to be present.
- the documentation of the (generic) file contents is now superceded by the
docs for arbitrary event file contents.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
.../testing/sysfs-bus-event_source-devices-events | 573 ---------------------
1 file changed, 573 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index a5226f0..20979f8 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -27,579 +27,6 @@ Description: Generic performance monitoring events
"basename".
-What: /sys/devices/cpu/events/PM_1PLUS_PPC_CMPL
- /sys/devices/cpu/events/PM_BRU_FIN
- /sys/devices/cpu/events/PM_BR_MPRED
- /sys/devices/cpu/events/PM_CMPLU_STALL
- /sys/devices/cpu/events/PM_CMPLU_STALL_BRU
- /sys/devices/cpu/events/PM_CMPLU_STALL_DCACHE_MISS
- /sys/devices/cpu/events/PM_CMPLU_STALL_DFU
- /sys/devices/cpu/events/PM_CMPLU_STALL_DIV
- /sys/devices/cpu/events/PM_CMPLU_STALL_ERAT_MISS
- /sys/devices/cpu/events/PM_CMPLU_STALL_FXU
- /sys/devices/cpu/events/PM_CMPLU_STALL_IFU
- /sys/devices/cpu/events/PM_CMPLU_STALL_LSU
- /sys/devices/cpu/events/PM_CMPLU_STALL_REJECT
- /sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR
- /sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR_LONG
- /sys/devices/cpu/events/PM_CMPLU_STALL_STORE
- /sys/devices/cpu/events/PM_CMPLU_STALL_THRD
- /sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR
- /sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR_LONG
- /sys/devices/cpu/events/PM_CYC
- /sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED
- /sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED_IC_MISS
- /sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
- /sys/devices/cpu/events/PM_GCT_NOSLOT_IC_MISS
- /sys/devices/cpu/events/PM_GRP_CMPL
- /sys/devices/cpu/events/PM_INST_CMPL
- /sys/devices/cpu/events/PM_LD_MISS_L1
- /sys/devices/cpu/events/PM_LD_REF_L1
- /sys/devices/cpu/events/PM_RUN_CYC
- /sys/devices/cpu/events/PM_RUN_INST_CMPL
- /sys/devices/cpu/events/PM_IC_DEMAND_L2_BR_ALL
- /sys/devices/cpu/events/PM_GCT_UTIL_7_TO_10_SLOTS
- /sys/devices/cpu/events/PM_PMC2_SAVED
- /sys/devices/cpu/events/PM_VSU0_16FLOP
- /sys/devices/cpu/events/PM_MRK_LSU_DERAT_MISS
- /sys/devices/cpu/events/PM_MRK_ST_CMPL
- /sys/devices/cpu/events/PM_NEST_PAIR3_ADD
- /sys/devices/cpu/events/PM_L2_ST_DISP
- /sys/devices/cpu/events/PM_L2_CASTOUT_MOD
- /sys/devices/cpu/events/PM_ISEG
- /sys/devices/cpu/events/PM_MRK_INST_TIMEO
- /sys/devices/cpu/events/PM_L2_RCST_DISP_FAIL_ADDR
- /sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_CONFIRM
- /sys/devices/cpu/events/PM_IERAT_WR_64K
- /sys/devices/cpu/events/PM_MRK_DTLB_MISS_16M
- /sys/devices/cpu/events/PM_IERAT_MISS
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_LMEM
- /sys/devices/cpu/events/PM_FLOP
- /sys/devices/cpu/events/PM_THRD_PRIO_4_5_CYC
- /sys/devices/cpu/events/PM_BR_PRED_TA
- /sys/devices/cpu/events/PM_EXT_INT
- /sys/devices/cpu/events/PM_VSU_FSQRT_FDIV
- /sys/devices/cpu/events/PM_MRK_LD_MISS_EXPOSED_CYC
- /sys/devices/cpu/events/PM_LSU1_LDF
- /sys/devices/cpu/events/PM_IC_WRITE_ALL
- /sys/devices/cpu/events/PM_LSU0_SRQ_STFWD
- /sys/devices/cpu/events/PM_PTEG_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_SHR
- /sys/devices/cpu/events/PM_DATA_FROM_L21_MOD
- /sys/devices/cpu/events/PM_VSU1_SCAL_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_VSU0_8FLOP
- /sys/devices/cpu/events/PM_POWER_EVENT1
- /sys/devices/cpu/events/PM_DISP_CLB_HELD_BAL
- /sys/devices/cpu/events/PM_VSU1_2FLOP
- /sys/devices/cpu/events/PM_LWSYNC_HELD
- /sys/devices/cpu/events/PM_PTEG_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_INST_FROM_L21_MOD
- /sys/devices/cpu/events/PM_IERAT_XLATE_WR_16MPLUS
- /sys/devices/cpu/events/PM_IC_REQ_ALL
- /sys/devices/cpu/events/PM_DSLB_MISS
- /sys/devices/cpu/events/PM_L3_MISS
- /sys/devices/cpu/events/PM_LSU0_L1_PREF
- /sys/devices/cpu/events/PM_VSU_SCALAR_SINGLE_ISSUED
- /sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE
- /sys/devices/cpu/events/PM_L2_INST
- /sys/devices/cpu/events/PM_VSU0_FRSP
- /sys/devices/cpu/events/PM_FLUSH_DISP
- /sys/devices/cpu/events/PM_PTEG_FROM_L2MISS
- /sys/devices/cpu/events/PM_VSU1_DQ_ISSUED
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DMEM
- /sys/devices/cpu/events/PM_LSU_FLUSH_ULD
- /sys/devices/cpu/events/PM_PTEG_FROM_LMEM
- /sys/devices/cpu/events/PM_MRK_DERAT_MISS_16M
- /sys/devices/cpu/events/PM_THRD_ALL_RUN_CYC
- /sys/devices/cpu/events/PM_MEM0_PREFETCH_DISP
- /sys/devices/cpu/events/PM_MRK_STALL_CMPLU_CYC_COUNT
- /sys/devices/cpu/events/PM_DATA_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_VSU_FRSP
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_MOD
- /sys/devices/cpu/events/PM_PMC1_OVERFLOW
- /sys/devices/cpu/events/PM_VSU0_SINGLE
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L3MISS
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L31_SHR
- /sys/devices/cpu/events/PM_VSU0_VECTOR_SP_ISSUED
- /sys/devices/cpu/events/PM_VSU1_FEST
- /sys/devices/cpu/events/PM_MRK_INST_DISP
- /sys/devices/cpu/events/PM_VSU0_COMPLEX_ISSUED
- /sys/devices/cpu/events/PM_LSU1_FLUSH_UST
- /sys/devices/cpu/events/PM_FXU_IDLE
- /sys/devices/cpu/events/PM_LSU0_FLUSH_ULD
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC
- /sys/devices/cpu/events/PM_LSU1_REJECT_LMQ_FULL
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L21_MOD
- /sys/devices/cpu/events/PM_INST_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_SHL_CREATED
- /sys/devices/cpu/events/PM_L2_ST_HIT
- /sys/devices/cpu/events/PM_DATA_FROM_DMEM
- /sys/devices/cpu/events/PM_L3_LD_MISS
- /sys/devices/cpu/events/PM_FXU1_BUSY_FXU0_IDLE
- /sys/devices/cpu/events/PM_DISP_CLB_HELD_RES
- /sys/devices/cpu/events/PM_L2_SN_SX_I_DONE
- /sys/devices/cpu/events/PM_STCX_CMPL
- /sys/devices/cpu/events/PM_VSU0_2FLOP
- /sys/devices/cpu/events/PM_L3_PREF_MISS
- /sys/devices/cpu/events/PM_LSU_SRQ_SYNC_CYC
- /sys/devices/cpu/events/PM_LSU_REJECT_ERAT_MISS
- /sys/devices/cpu/events/PM_L1_ICACHE_MISS
- /sys/devices/cpu/events/PM_LSU1_FLUSH_SRQ
- /sys/devices/cpu/events/PM_LD_REF_L1_LSU0
- /sys/devices/cpu/events/PM_VSU0_FEST
- /sys/devices/cpu/events/PM_VSU_VECTOR_SINGLE_ISSUED
- /sys/devices/cpu/events/PM_FREQ_UP
- /sys/devices/cpu/events/PM_DATA_FROM_LMEM
- /sys/devices/cpu/events/PM_LSU1_LDX
- /sys/devices/cpu/events/PM_PMC3_OVERFLOW
- /sys/devices/cpu/events/PM_MRK_BR_MPRED
- /sys/devices/cpu/events/PM_SHL_MATCH
- /sys/devices/cpu/events/PM_MRK_BR_TAKEN
- /sys/devices/cpu/events/PM_ISLB_MISS
- /sys/devices/cpu/events/PM_DISP_HELD_THERMAL
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_LSU1_SRQ_STFWD
- /sys/devices/cpu/events/PM_PTEG_FROM_DMEM
- /sys/devices/cpu/events/PM_VSU_2FLOP
- /sys/devices/cpu/events/PM_GCT_FULL_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L3_CYC
- /sys/devices/cpu/events/PM_LSU_SRQ_S0_ALLOC
- /sys/devices/cpu/events/PM_MRK_DERAT_MISS_4K
- /sys/devices/cpu/events/PM_BR_MPRED_TA
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L2MISS
- /sys/devices/cpu/events/PM_DPU_HELD_POWER
- /sys/devices/cpu/events/PM_MRK_VSU_FIN
- /sys/devices/cpu/events/PM_LSU_SRQ_S0_VALID
- /sys/devices/cpu/events/PM_GCT_EMPTY_CYC
- /sys/devices/cpu/events/PM_IOPS_DISP
- /sys/devices/cpu/events/PM_RUN_SPURR
- /sys/devices/cpu/events/PM_PTEG_FROM_L21_MOD
- /sys/devices/cpu/events/PM_VSU0_1FLOP
- /sys/devices/cpu/events/PM_SNOOP_TLBIE
- /sys/devices/cpu/events/PM_DATA_FROM_L3MISS
- /sys/devices/cpu/events/PM_VSU_SINGLE
- /sys/devices/cpu/events/PM_DTLB_MISS_16G
- /sys/devices/cpu/events/PM_FLUSH
- /sys/devices/cpu/events/PM_L2_LD_HIT
- /sys/devices/cpu/events/PM_NEST_PAIR2_AND
- /sys/devices/cpu/events/PM_VSU1_1FLOP
- /sys/devices/cpu/events/PM_IC_PREF_REQ
- /sys/devices/cpu/events/PM_L3_LD_HIT
- /sys/devices/cpu/events/PM_DISP_HELD
- /sys/devices/cpu/events/PM_L2_LD
- /sys/devices/cpu/events/PM_LSU_FLUSH_SRQ
- /sys/devices/cpu/events/PM_BC_PLUS_8_CONV
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_MOD_CYC
- /sys/devices/cpu/events/PM_L2_RCST_BUSY_RC_FULL
- /sys/devices/cpu/events/PM_TB_BIT_TRANS
- /sys/devices/cpu/events/PM_THERMAL_MAX
- /sys/devices/cpu/events/PM_LSU1_FLUSH_ULD
- /sys/devices/cpu/events/PM_LSU1_REJECT_LHS
- /sys/devices/cpu/events/PM_LSU_LRQ_S0_ALLOC
- /sys/devices/cpu/events/PM_L3_CO_L31
- /sys/devices/cpu/events/PM_POWER_EVENT4
- /sys/devices/cpu/events/PM_DATA_FROM_L31_SHR
- /sys/devices/cpu/events/PM_BR_UNCOND
- /sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_ALLOC
- /sys/devices/cpu/events/PM_PMC4_REWIND
- /sys/devices/cpu/events/PM_L2_RCLD_DISP
- /sys/devices/cpu/events/PM_THRD_PRIO_2_3_CYC
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L2MISS
- /sys/devices/cpu/events/PM_IC_DEMAND_L2_BHT_REDIRECT
- /sys/devices/cpu/events/PM_DATA_FROM_L31_SHR
- /sys/devices/cpu/events/PM_IC_PREF_CANCEL_L2
- /sys/devices/cpu/events/PM_MRK_FIN_STALL_CYC_COUNT
- /sys/devices/cpu/events/PM_BR_PRED_CCACHE
- /sys/devices/cpu/events/PM_GCT_UTIL_1_TO_2_SLOTS
- /sys/devices/cpu/events/PM_MRK_ST_CMPL_INT
- /sys/devices/cpu/events/PM_LSU_TWO_TABLEWALK_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L3MISS
- /sys/devices/cpu/events/PM_LSU_SET_MPRED
- /sys/devices/cpu/events/PM_FLUSH_DISP_TLBIE
- /sys/devices/cpu/events/PM_VSU1_FCONV
- /sys/devices/cpu/events/PM_DERAT_MISS_16G
- /sys/devices/cpu/events/PM_INST_FROM_LMEM
- /sys/devices/cpu/events/PM_IC_DEMAND_L2_BR_REDIRECT
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L2
- /sys/devices/cpu/events/PM_PTEG_FROM_L2
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_SHR_CYC
- /sys/devices/cpu/events/PM_MRK_DTLB_MISS_4K
- /sys/devices/cpu/events/PM_VSU0_FPSCR
- /sys/devices/cpu/events/PM_VSU1_VECT_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_MEM0_RQ_DISP
- /sys/devices/cpu/events/PM_L2_LD_MISS
- /sys/devices/cpu/events/PM_VMX_RESULT_SAT_1
- /sys/devices/cpu/events/PM_L1_PREF
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_LMEM_CYC
- /sys/devices/cpu/events/PM_GRP_IC_MISS_NONSPEC
- /sys/devices/cpu/events/PM_PB_NODE_PUMP
- /sys/devices/cpu/events/PM_SHL_MERGED
- /sys/devices/cpu/events/PM_NEST_PAIR1_ADD
- /sys/devices/cpu/events/PM_DATA_FROM_L3
- /sys/devices/cpu/events/PM_LSU_FLUSH
- /sys/devices/cpu/events/PM_LSU_SRQ_SYNC_COUNT
- /sys/devices/cpu/events/PM_PMC2_OVERFLOW
- /sys/devices/cpu/events/PM_LSU_LDF
- /sys/devices/cpu/events/PM_POWER_EVENT3
- /sys/devices/cpu/events/PM_DISP_WT
- /sys/devices/cpu/events/PM_IC_BANK_CONFLICT
- /sys/devices/cpu/events/PM_BR_MPRED_CR_TA
- /sys/devices/cpu/events/PM_L2_INST_MISS
- /sys/devices/cpu/events/PM_NEST_PAIR2_ADD
- /sys/devices/cpu/events/PM_MRK_LSU_FLUSH
- /sys/devices/cpu/events/PM_L2_LDST
- /sys/devices/cpu/events/PM_INST_FROM_L31_SHR
- /sys/devices/cpu/events/PM_VSU0_FIN
- /sys/devices/cpu/events/PM_VSU1_FCONV
- /sys/devices/cpu/events/PM_INST_FROM_RMEM
- /sys/devices/cpu/events/PM_DISP_CLB_HELD_TLBIE
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DMEM_CYC
- /sys/devices/cpu/events/PM_BR_PRED_CR
- /sys/devices/cpu/events/PM_LSU_REJECT
- /sys/devices/cpu/events/PM_GCT_UTIL_3_TO_6_SLOTS
- /sys/devices/cpu/events/PM_CMPLU_STALL_END_GCT_NOSLOT
- /sys/devices/cpu/events/PM_LSU0_REJECT_LMQ_FULL
- /sys/devices/cpu/events/PM_VSU_FEST
- /sys/devices/cpu/events/PM_NEST_PAIR0_AND
- /sys/devices/cpu/events/PM_PTEG_FROM_L3
- /sys/devices/cpu/events/PM_POWER_EVENT2
- /sys/devices/cpu/events/PM_IC_PREF_CANCEL_PAGE
- /sys/devices/cpu/events/PM_VSU0_FSQRT_FDIV
- /sys/devices/cpu/events/PM_MRK_GRP_CMPL
- /sys/devices/cpu/events/PM_VSU0_SCAL_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_GRP_DISP
- /sys/devices/cpu/events/PM_LSU0_LDX
- /sys/devices/cpu/events/PM_DATA_FROM_L2
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_VSU0_VECT_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_VSU1_2FLOP_DOUBLE
- /sys/devices/cpu/events/PM_THRD_PRIO_6_7_CYC
- /sys/devices/cpu/events/PM_BC_PLUS_8_RSLV_TAKEN
- /sys/devices/cpu/events/PM_BR_MPRED_CR
- /sys/devices/cpu/events/PM_L3_CO_MEM
- /sys/devices/cpu/events/PM_DATA_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_LSU_SRQ_FULL_CYC
- /sys/devices/cpu/events/PM_TABLEWALK_CYC
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_RMEM
- /sys/devices/cpu/events/PM_LSU_SRQ_STFWD
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_RMEM
- /sys/devices/cpu/events/PM_FXU0_FIN
- /sys/devices/cpu/events/PM_LSU1_L1_SW_PREF
- /sys/devices/cpu/events/PM_PTEG_FROM_L31_MOD
- /sys/devices/cpu/events/PM_PMC5_OVERFLOW
- /sys/devices/cpu/events/PM_LD_REF_L1_LSU1
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L21_SHR
- /sys/devices/cpu/events/PM_DATA_FROM_RMEM
- /sys/devices/cpu/events/PM_VSU0_SCAL_SINGLE_ISSUED
- /sys/devices/cpu/events/PM_BR_MPRED_LSTACK
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_MOD_CYC
- /sys/devices/cpu/events/PM_LSU0_FLUSH_UST
- /sys/devices/cpu/events/PM_LSU_NCST
- /sys/devices/cpu/events/PM_BR_TAKEN
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_LMEM
- /sys/devices/cpu/events/PM_DTLB_MISS_4K
- /sys/devices/cpu/events/PM_PMC4_SAVED
- /sys/devices/cpu/events/PM_VSU1_PERMUTE_ISSUED
- /sys/devices/cpu/events/PM_SLB_MISS
- /sys/devices/cpu/events/PM_LSU1_FLUSH_LRQ
- /sys/devices/cpu/events/PM_DTLB_MISS
- /sys/devices/cpu/events/PM_VSU1_FRSP
- /sys/devices/cpu/events/PM_VSU_VECTOR_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_L2_CASTOUT_SHR
- /sys/devices/cpu/events/PM_DATA_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_VSU1_STF
- /sys/devices/cpu/events/PM_ST_FIN
- /sys/devices/cpu/events/PM_PTEG_FROM_L21_SHR
- /sys/devices/cpu/events/PM_L2_LOC_GUESS_WRONG
- /sys/devices/cpu/events/PM_MRK_STCX_FAIL
- /sys/devices/cpu/events/PM_LSU0_REJECT_LHS
- /sys/devices/cpu/events/PM_IC_PREF_CANCEL_HIT
- /sys/devices/cpu/events/PM_L3_PREF_BUSY
- /sys/devices/cpu/events/PM_MRK_BRU_FIN
- /sys/devices/cpu/events/PM_LSU1_NCLD
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L31_MOD
- /sys/devices/cpu/events/PM_LSU_NCLD
- /sys/devices/cpu/events/PM_LSU_LDX
- /sys/devices/cpu/events/PM_L2_LOC_GUESS_CORRECT
- /sys/devices/cpu/events/PM_THRESH_TIMEO
- /sys/devices/cpu/events/PM_L3_PREF_ST
- /sys/devices/cpu/events/PM_DISP_CLB_HELD_SYNC
- /sys/devices/cpu/events/PM_VSU_SIMPLE_ISSUED
- /sys/devices/cpu/events/PM_VSU1_SINGLE
- /sys/devices/cpu/events/PM_DATA_TABLEWALK_CYC
- /sys/devices/cpu/events/PM_L2_RC_ST_DONE
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L21_MOD
- /sys/devices/cpu/events/PM_LARX_LSU1
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RMEM
- /sys/devices/cpu/events/PM_DISP_CLB_HELD
- /sys/devices/cpu/events/PM_DERAT_MISS_4K
- /sys/devices/cpu/events/PM_L2_RCLD_DISP_FAIL_ADDR
- /sys/devices/cpu/events/PM_SEG_EXCEPTION
- /sys/devices/cpu/events/PM_FLUSH_DISP_SB
- /sys/devices/cpu/events/PM_L2_DC_INV
- /sys/devices/cpu/events/PM_PTEG_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_DSEG
- /sys/devices/cpu/events/PM_BR_PRED_LSTACK
- /sys/devices/cpu/events/PM_VSU0_STF
- /sys/devices/cpu/events/PM_LSU_FX_FIN
- /sys/devices/cpu/events/PM_DERAT_MISS_16M
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_GCT_UTIL_11_PLUS_SLOTS
- /sys/devices/cpu/events/PM_INST_FROM_L3
- /sys/devices/cpu/events/PM_MRK_IFU_FIN
- /sys/devices/cpu/events/PM_ITLB_MISS
- /sys/devices/cpu/events/PM_VSU_STF
- /sys/devices/cpu/events/PM_LSU_FLUSH_UST
- /sys/devices/cpu/events/PM_L2_LDST_MISS
- /sys/devices/cpu/events/PM_FXU1_FIN
- /sys/devices/cpu/events/PM_SHL_DEALLOCATED
- /sys/devices/cpu/events/PM_L2_SN_M_WR_DONE
- /sys/devices/cpu/events/PM_LSU_REJECT_SET_MPRED
- /sys/devices/cpu/events/PM_L3_PREF_LD
- /sys/devices/cpu/events/PM_L2_SN_M_RD_DONE
- /sys/devices/cpu/events/PM_MRK_DERAT_MISS_16G
- /sys/devices/cpu/events/PM_VSU_FCONV
- /sys/devices/cpu/events/PM_ANY_THRD_RUN_CYC
- /sys/devices/cpu/events/PM_LSU_LMQ_FULL_CYC
- /sys/devices/cpu/events/PM_MRK_LSU_REJECT_LHS
- /sys/devices/cpu/events/PM_MRK_LD_MISS_L1_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L2_CYC
- /sys/devices/cpu/events/PM_INST_IMC_MATCH_DISP
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RMEM_CYC
- /sys/devices/cpu/events/PM_VSU0_SIMPLE_ISSUED
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_VSU_FMA_DOUBLE
- /sys/devices/cpu/events/PM_VSU_4FLOP
- /sys/devices/cpu/events/PM_VSU1_FIN
- /sys/devices/cpu/events/PM_NEST_PAIR1_AND
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_RL2L3_MOD
- /sys/devices/cpu/events/PM_PTEG_FROM_RMEM
- /sys/devices/cpu/events/PM_LSU_LRQ_S0_VALID
- /sys/devices/cpu/events/PM_LSU0_LDF
- /sys/devices/cpu/events/PM_FLUSH_COMPLETION
- /sys/devices/cpu/events/PM_ST_MISS_L1
- /sys/devices/cpu/events/PM_L2_NODE_PUMP
- /sys/devices/cpu/events/PM_INST_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_MRK_STALL_CMPLU_CYC
- /sys/devices/cpu/events/PM_VSU1_DENORM
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_SHR_CYC
- /sys/devices/cpu/events/PM_NEST_PAIR0_ADD
- /sys/devices/cpu/events/PM_INST_FROM_L3MISS
- /sys/devices/cpu/events/PM_EE_OFF_EXT_INT
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_DMEM
- /sys/devices/cpu/events/PM_INST_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_PMC6_OVERFLOW
- /sys/devices/cpu/events/PM_VSU_2FLOP_DOUBLE
- /sys/devices/cpu/events/PM_TLB_MISS
- /sys/devices/cpu/events/PM_FXU_BUSY
- /sys/devices/cpu/events/PM_L2_RCLD_DISP_FAIL_OTHER
- /sys/devices/cpu/events/PM_LSU_REJECT_LMQ_FULL
- /sys/devices/cpu/events/PM_IC_RELOAD_SHR
- /sys/devices/cpu/events/PM_GRP_MRK
- /sys/devices/cpu/events/PM_MRK_ST_NEST
- /sys/devices/cpu/events/PM_VSU1_FSQRT_FDIV
- /sys/devices/cpu/events/PM_LSU0_FLUSH_LRQ
- /sys/devices/cpu/events/PM_LARX_LSU0
- /sys/devices/cpu/events/PM_IBUF_FULL_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_SHR_CYC
- /sys/devices/cpu/events/PM_LSU_DC_PREF_STREAM_ALLOC
- /sys/devices/cpu/events/PM_GRP_MRK_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_SHR_CYC
- /sys/devices/cpu/events/PM_L2_GLOB_GUESS_CORRECT
- /sys/devices/cpu/events/PM_LSU_REJECT_LHS
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_LMEM
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L3
- /sys/devices/cpu/events/PM_FREQ_DOWN
- /sys/devices/cpu/events/PM_PB_RETRY_NODE_PUMP
- /sys/devices/cpu/events/PM_INST_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_MRK_INST_ISSUED
- /sys/devices/cpu/events/PM_PTEG_FROM_L3MISS
- /sys/devices/cpu/events/PM_RUN_PURR
- /sys/devices/cpu/events/PM_MRK_GRP_IC_MISS
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L3
- /sys/devices/cpu/events/PM_PTEG_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_LSU_FLUSH_LRQ
- /sys/devices/cpu/events/PM_MRK_DERAT_MISS_64K
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_DL2L3_MOD
- /sys/devices/cpu/events/PM_L2_ST_MISS
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L21_SHR
- /sys/devices/cpu/events/PM_LWSYNC
- /sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE
- /sys/devices/cpu/events/PM_MRK_LSU_FLUSH_LRQ
- /sys/devices/cpu/events/PM_INST_IMC_MATCH_CMPL
- /sys/devices/cpu/events/PM_NEST_PAIR3_AND
- /sys/devices/cpu/events/PM_PB_RETRY_SYS_PUMP
- /sys/devices/cpu/events/PM_MRK_INST_FIN
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_INST_FROM_L31_MOD
- /sys/devices/cpu/events/PM_MRK_DTLB_MISS_64K
- /sys/devices/cpu/events/PM_LSU_FIN
- /sys/devices/cpu/events/PM_MRK_LSU_REJECT
- /sys/devices/cpu/events/PM_L2_CO_FAIL_BUSY
- /sys/devices/cpu/events/PM_MEM0_WQ_DISP
- /sys/devices/cpu/events/PM_DATA_FROM_L31_MOD
- /sys/devices/cpu/events/PM_THERMAL_WARN
- /sys/devices/cpu/events/PM_VSU0_4FLOP
- /sys/devices/cpu/events/PM_BR_MPRED_CCACHE
- /sys/devices/cpu/events/PM_L1_DEMAND_WRITE
- /sys/devices/cpu/events/PM_FLUSH_BR_MPRED
- /sys/devices/cpu/events/PM_MRK_DTLB_MISS_16G
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_DMEM
- /sys/devices/cpu/events/PM_L2_RCST_DISP
- /sys/devices/cpu/events/PM_LSU_PARTIAL_CDF
- /sys/devices/cpu/events/PM_DISP_CLB_HELD_SB
- /sys/devices/cpu/events/PM_VSU0_FMA_DOUBLE
- /sys/devices/cpu/events/PM_FXU0_BUSY_FXU1_IDLE
- /sys/devices/cpu/events/PM_IC_DEMAND_CYC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_SHR
- /sys/devices/cpu/events/PM_MRK_LSU_FLUSH_UST
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L3MISS
- /sys/devices/cpu/events/PM_VSU_DENORM
- /sys/devices/cpu/events/PM_MRK_LSU_PARTIAL_CDF
- /sys/devices/cpu/events/PM_INST_FROM_L21_SHR
- /sys/devices/cpu/events/PM_IC_PREF_WRITE
- /sys/devices/cpu/events/PM_BR_PRED
- /sys/devices/cpu/events/PM_INST_FROM_DMEM
- /sys/devices/cpu/events/PM_IC_PREF_CANCEL_ALL
- /sys/devices/cpu/events/PM_LSU_DC_PREF_STREAM_CONFIRM
- /sys/devices/cpu/events/PM_MRK_LSU_FLUSH_SRQ
- /sys/devices/cpu/events/PM_MRK_FIN_STALL_CYC
- /sys/devices/cpu/events/PM_L2_RCST_DISP_FAIL_OTHER
- /sys/devices/cpu/events/PM_VSU1_DD_ISSUED
- /sys/devices/cpu/events/PM_PTEG_FROM_L31_SHR
- /sys/devices/cpu/events/PM_DATA_FROM_L21_SHR
- /sys/devices/cpu/events/PM_LSU0_NCLD
- /sys/devices/cpu/events/PM_VSU1_4FLOP
- /sys/devices/cpu/events/PM_VSU1_8FLOP
- /sys/devices/cpu/events/PM_VSU_8FLOP
- /sys/devices/cpu/events/PM_LSU_LMQ_SRQ_EMPTY_CYC
- /sys/devices/cpu/events/PM_DTLB_MISS_64K
- /sys/devices/cpu/events/PM_THRD_CONC_RUN_INST
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L2
- /sys/devices/cpu/events/PM_PB_SYS_PUMP
- /sys/devices/cpu/events/PM_VSU_FIN
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_MOD
- /sys/devices/cpu/events/PM_THRD_PRIO_0_1_CYC
- /sys/devices/cpu/events/PM_DERAT_MISS_64K
- /sys/devices/cpu/events/PM_PMC2_REWIND
- /sys/devices/cpu/events/PM_INST_FROM_L2
- /sys/devices/cpu/events/PM_GRP_BR_MPRED_NONSPEC
- /sys/devices/cpu/events/PM_INST_DISP
- /sys/devices/cpu/events/PM_MEM0_RD_CANCEL_TOTAL
- /sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_CONFIRM
- /sys/devices/cpu/events/PM_L1_DCACHE_RELOAD_VALID
- /sys/devices/cpu/events/PM_VSU_SCALAR_DOUBLE_ISSUED
- /sys/devices/cpu/events/PM_L3_PREF_HIT
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L31_MOD
- /sys/devices/cpu/events/PM_MRK_FXU_FIN
- /sys/devices/cpu/events/PM_PMC4_OVERFLOW
- /sys/devices/cpu/events/PM_MRK_PTEG_FROM_L3
- /sys/devices/cpu/events/PM_LSU0_LMQ_LHR_MERGE
- /sys/devices/cpu/events/PM_BTAC_HIT
- /sys/devices/cpu/events/PM_L3_RD_BUSY
- /sys/devices/cpu/events/PM_LSU0_L1_SW_PREF
- /sys/devices/cpu/events/PM_INST_FROM_L2MISS
- /sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_ALLOC
- /sys/devices/cpu/events/PM_L2_ST
- /sys/devices/cpu/events/PM_VSU0_DENORM
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_BR_PRED_CR_TA
- /sys/devices/cpu/events/PM_VSU0_FCONV
- /sys/devices/cpu/events/PM_MRK_LSU_FLUSH_ULD
- /sys/devices/cpu/events/PM_BTAC_MISS
- /sys/devices/cpu/events/PM_MRK_LD_MISS_EXPOSED_CYC_COUNT
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L2
- /sys/devices/cpu/events/PM_LSU_DCACHE_RELOAD_VALID
- /sys/devices/cpu/events/PM_VSU_FMA
- /sys/devices/cpu/events/PM_LSU0_FLUSH_SRQ
- /sys/devices/cpu/events/PM_LSU1_L1_PREF
- /sys/devices/cpu/events/PM_IOPS_CMPL
- /sys/devices/cpu/events/PM_L2_SYS_PUMP
- /sys/devices/cpu/events/PM_L2_RCLD_BUSY_RC_FULL
- /sys/devices/cpu/events/PM_LSU_LMQ_S0_ALLOC
- /sys/devices/cpu/events/PM_FLUSH_DISP_SYNC
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_MOD_CYC
- /sys/devices/cpu/events/PM_L2_IC_INV
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_MOD_CYC
- /sys/devices/cpu/events/PM_L3_PREF_LDST
- /sys/devices/cpu/events/PM_LSU_SRQ_EMPTY_CYC
- /sys/devices/cpu/events/PM_LSU_LMQ_S0_VALID
- /sys/devices/cpu/events/PM_FLUSH_PARTIAL
- /sys/devices/cpu/events/PM_VSU1_FMA_DOUBLE
- /sys/devices/cpu/events/PM_1PLUS_PPC_DISP
- /sys/devices/cpu/events/PM_DATA_FROM_L2MISS
- /sys/devices/cpu/events/PM_SUSPENDED
- /sys/devices/cpu/events/PM_VSU0_FMA
- /sys/devices/cpu/events/PM_STCX_FAIL
- /sys/devices/cpu/events/PM_VSU0_FSQRT_FDIV_DOUBLE
- /sys/devices/cpu/events/PM_DC_PREF_DST
- /sys/devices/cpu/events/PM_VSU1_SCAL_SINGLE_ISSUED
- /sys/devices/cpu/events/PM_L3_HIT
- /sys/devices/cpu/events/PM_L2_GLOB_GUESS_WRONG
- /sys/devices/cpu/events/PM_MRK_DFU_FIN
- /sys/devices/cpu/events/PM_INST_FROM_L1
- /sys/devices/cpu/events/PM_IC_DEMAND_REQ
- /sys/devices/cpu/events/PM_VSU1_FSQRT_FDIV_DOUBLE
- /sys/devices/cpu/events/PM_VSU1_FMA
- /sys/devices/cpu/events/PM_MRK_LD_MISS_L1
- /sys/devices/cpu/events/PM_VSU0_2FLOP_DOUBLE
- /sys/devices/cpu/events/PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_L31_SHR
- /sys/devices/cpu/events/PM_MRK_LSU_REJECT_ERAT_MISS
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_L2MISS
- /sys/devices/cpu/events/PM_DATA_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_INST_FROM_PREF
- /sys/devices/cpu/events/PM_VSU1_SQ
- /sys/devices/cpu/events/PM_L2_LD_DISP
- /sys/devices/cpu/events/PM_L2_DISP_ALL
- /sys/devices/cpu/events/PM_THRD_GRP_CMPL_BOTH_CYC
- /sys/devices/cpu/events/PM_VSU_FSQRT_FDIV_DOUBLE
- /sys/devices/cpu/events/PM_INST_PTEG_FROM_DL2L3_SHR
- /sys/devices/cpu/events/PM_VSU_1FLOP
- /sys/devices/cpu/events/PM_HV_CYC
- /sys/devices/cpu/events/PM_MRK_LSU_FIN
- /sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_SHR
- /sys/devices/cpu/events/PM_DTLB_MISS_16M
- /sys/devices/cpu/events/PM_LSU1_LMQ_LHR_MERGE
- /sys/devices/cpu/events/PM_IFU_FIN
- /sys/devices/cpu/events/PM_1THRD_CON_RUN_INSTR
- /sys/devices/cpu/events/PM_CMPLU_STALL_COUNT
- /sys/devices/cpu/events/PM_MEM0_PB_RD_CL
- /sys/devices/cpu/events/PM_THRD_1_RUN_CYC
- /sys/devices/cpu/events/PM_THRD_2_CONC_RUN_INSTR
- /sys/devices/cpu/events/PM_THRD_2_RUN_CYC
- /sys/devices/cpu/events/PM_THRD_3_CONC_RUN_INST
- /sys/devices/cpu/events/PM_THRD_3_RUN_CYC
- /sys/devices/cpu/events/PM_THRD_4_CONC_RUN_INST
- /sys/devices/cpu/events/PM_THRD_4_RUN_CYC
-
-Date: 2013/01/08
-
-Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
- Linux Powerpc mailing list <linuxppc-dev@ozlabs.org>
-
-Description: POWER-systems specific performance monitoring events
-
- A collection of performance monitoring events that may be
- supported by the POWER CPU. These events can be monitored
- using the 'perf(1)' tool.
-
- These events may not be supported by other CPUs.
-
- The contents of each file would look like:
-
- event=0xNNNN
-
- where 'N' is a hex digit and the number '0xNNNN' shows the
- "raw code" for the perf event identified by the file's
- "basename".
-
- Further, multiple terms like 'event=0xNNNN' can be specified
- and separated with comma. All available terms are defined in
- the /sys/bus/event_source/devices/<dev>/format file.
-
What: /sys/bus/event_source/devices/<pmu>/events/<event>
Date: 2014/02/24
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 3/4] perf Documentation: sysfs events/ interfaces
From: Sukadev Bhattiprolu @ 2014-09-24 19:24 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586681-21262-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Add documentation for the <event>, <event>.scale, and <event>.unit
files in sysfs.
<event>.scale and <event>.unit were undocumented.
<event> was previously documented only for specific powerpc pmu events.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
.../testing/sysfs-bus-event_source-devices-events | 60 ++++++++++++++++++++++
1 file changed, 60 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 7b40a3c..a5226f0 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -599,3 +599,63 @@ Description: POWER-systems specific performance monitoring events
Further, multiple terms like 'event=0xNNNN' can be specified
and separated with comma. All available terms are defined in
the /sys/bus/event_source/devices/<dev>/format file.
+
+What: /sys/bus/event_source/devices/<pmu>/events/<event>
+Date: 2014/02/24
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description: Per-pmu performance monitoring events specific to the running system
+
+ Each file (except for some of those with a '.' in them, '.unit'
+ and '.scale') in the 'events' directory describes a single
+ performance monitoring event supported by the <pmu>. The name
+ of the file is the name of the event.
+
+ File contents:
+
+ <term>[=<value>][,<term>[=<value>]]...
+
+ Where <term> is one of the terms listed under
+ /sys/bus/event_source/devices/<pmu>/format/ and <value> is
+ a number is base-16 format with a '0x' prefix (lowercase only).
+ If a <term> is specified alone (without an assigned value), it
+ is implied that 0x1 is assigned to that <term>.
+
+ Examples (each of these lines would be in a seperate file):
+
+ event=0x2abc
+ event=0x423,inv,cmask=0x3
+ domain=0x1,offset=0x8,starting_index=0xffff
+
+ Each of the assignments indicates a value to be assigned to a
+ particular set of bits (as defined by the format file
+ corresponding to the <term>) in the perf_event structure passed
+ to the perf_open syscall.
+
+What: /sys/bus/event_source/devices/<pmu>/events/<event>.unit
+Date: 2014/02/24
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description: Perf event units
+
+ A string specifying the English plural numerical unit that <event>
+ (once multiplied by <event>.scale) represents.
+
+ Example:
+
+ Joules
+
+What: /sys/bus/event_source/devices/<pmu>/events/<event>.scale
+Date: 2014/02/24
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description: Perf event scaling factors
+
+ A string representing a floating point value expressed in
+ scientific notation to be multiplied by the event count
+ recieved from the kernel to match the unit specified in the
+ <event>.unit file.
+
+ Example:
+
+ 2.3283064365386962890625e-10
+
+ This is provided to avoid performing floating point arithmetic
+ in the kernel.
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 0/4] powerpc/perf: Miscellaneous fixes
From: Sukadev Bhattiprolu @ 2014-09-24 19:24 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
Miscellaenous fixes for perf and 24x7 counters in powerpc.
Patches 1,3,4 were submitted earlier as a part of the parametrized
events for 24x7 counters. But they are not directly related to the
parametrized events.
Patch 2 simplifies and fixes a bug in catalog_read() which causes the
catalog file to not read first page.
Changelog[v2]
Rebase to perf/core tree.
Cody P Schafer (3):
powerpc/perf/hv-24x7: use kmem_cache instead of aligned stack
allocations
perf Documentation: sysfs events/ interfaces
perf Documentation: remove duplicated docs for powerpc cpu specific
events
Sukadev Bhattiprolu (1):
Simplify catalog_read()
.../testing/sysfs-bus-event_source-devices-events | 611 ++-------------------
arch/powerpc/perf/hv-24x7.c | 144 ++---
2 files changed, 96 insertions(+), 659 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH v2 1/4] powerpc/perf/hv-24x7: use kmem_cache instead of aligned stack allocations
From: Sukadev Bhattiprolu @ 2014-09-24 19:24 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586681-21262-1-git-send-email-sukadev@linux.vnet.ibm.com>
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Ian pointed out the use of __aligned(4096) caused rather large stack
consumption in single_24x7_request(), so use the kmem_cache
hv_page_cache (which we've already got set up for other allocations)
insead of allocating locally.
CC: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
CC: Haren Myneni <hbabu@us.ibm.com>
CC: Cody P Schafer <dev@codyps.com>
Reported-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-24x7.c | 52 ++++++++++++++++++++++++++++++++-------------
1 file changed, 37 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 70d4f74..2f2215c 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -294,7 +294,7 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
u16 lpar, u64 *res,
bool success_expected)
{
- unsigned long ret;
+ unsigned long ret = -ENOMEM;
/*
* request_buffer and result_buffer are not required to be 4k aligned,
@@ -304,7 +304,27 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
struct reqb {
struct hv_24x7_request_buffer buf;
struct hv_24x7_request req;
- } __packed __aligned(4096) request_buffer = {
+ } __packed * request_buffer;
+ struct resb {
+ struct hv_24x7_data_result_buffer buf;
+ struct hv_24x7_result res;
+ struct hv_24x7_result_element elem;
+ __be64 result;
+ } __packed * result_buffer;
+
+ BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
+ BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
+
+ request_buffer = kmem_cache_alloc(hv_page_cache, GFP_USER);
+
+ if (!request_buffer)
+ goto out_reqb;
+
+ result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
+ if (!result_buffer)
+ goto out_resb;
+
+ *request_buffer = (struct reqb) {
.buf = {
.interface_version = HV_24X7_IF_VERSION_CURRENT,
.num_requests = 1,
@@ -320,28 +340,30 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
}
};
- 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));
+ 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;
+ result_buffer->buf.detailed_rc,
+ result_buffer->buf.failing_request_ix);
+ goto out_hcall;
}
- *res = be64_to_cpu(result_buffer.result);
+ *res = be64_to_cpu(result_buffer->result);
+ kfree(result_buffer);
+ kfree(request_buffer);
+ return ret;
+
+out_hcall:
+ kfree(result_buffer);
+out_resb:
+ kfree(request_buffer);
+out_reqb:
return ret;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 2/4] Simplify catalog_read()
From: Sukadev Bhattiprolu @ 2014-09-24 19:24 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, ak, Jiri Olsa, peterz, eranian,
Paul Mackerras
Cc: Michael Ellerman, linux-kernel, dev, linuxppc-dev,
Anshuman Khandual
In-Reply-To: <1411586681-21262-1-git-send-email-sukadev@linux.vnet.ibm.com>
catalog_read() implements the read interface for the sysfs file
/sys/bus/event_source/devices/hv_24x7/interface/catalog
It essentially takes a buffer, an offset and count as parameters
to the read() call. It makes a hypervisor call to read a specific
page from the catalog and copy the required bytes into the given
buffer. Each call to catalog_read() returns at most one 4K page.
Given these requirements, we should be able to simplify the
catalog_read().
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
arch/powerpc/perf/hv-24x7.c | 92 +++++----------------------------------------
1 file changed, 10 insertions(+), 82 deletions(-)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 2f2215c..9427ef7 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -75,86 +75,6 @@ static struct attribute_group format_group = {
static struct kmem_cache *hv_page_cache;
-/*
- * 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_(unsigned long phys_4096,
unsigned long version,
unsigned long index)
@@ -185,6 +105,8 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
ssize_t ret = 0;
size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
loff_t page_offset = 0;
+ loff_t offset_in_page;
+ size_t copy_len;
uint64_t catalog_version_num = 0;
void *page = kmem_cache_alloc(hv_page_cache, GFP_USER);
struct hv_24x7_catalog_page_0 *page_0 = page;
@@ -203,6 +125,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
page_offset = offset / 4096;
page_count = count / 4096;
+ offset_in_page = count % 4096;
if (page_offset >= catalog_page_len)
goto e_free;
@@ -216,8 +139,13 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
}
}
- ret = read_offset_data(buf, count, offset,
- page, 4096, page_offset * 4096);
+ copy_len = 4096 - offset_in_page;
+ if (copy_len > count)
+ copy_len = count;
+
+ memcpy(buf, page+offset_in_page, copy_len);
+ ret = copy_len;
+
e_free:
if (hret)
pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:"
--
1.8.3.1
^ permalink raw reply related
* [PATCHv8 3/6] ppc/cell: trivial: replace get_unused_fd() by get_unused_fd_flags(0)
From: Yann Droneaud @ 2014-09-24 13:11 UTC (permalink / raw)
To: Jeremy Kerr, Arnd Bergmann, Benjamin Herrenschmidt,
Paul Mackerras, Michael Ellerman, Al Viro, Andrew Morton,
Jiri Kosina
Cc: Yann Droneaud, cbe-oss-dev, linux-fsdevel, linuxppc-dev,
linux-kernel
In-Reply-To: <cover.1411562410.git.ydroneaud@opteya.com>
This patch replaces calls to get_unused_fd() with equivalent call to
get_unused_fd_flags(0) to preserve current behavor for existing code.
In a further patch, get_unused_fd() will be removed so that new code
start using get_unused_fd_flags(), with the hope O_CLOEXEC could be
used, either by default or choosen by userspace.
Link: http://lkml.kernel.org/r/cover.1411562410.git.ydroneaud@opteya.com
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: trivial@kernel.org
Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
---
arch/powerpc/platforms/cell/spufs/inode.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 87ba7cf99cd7..51effcec30d8 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -301,7 +301,7 @@ static int spufs_context_open(struct path *path)
int ret;
struct file *filp;
- ret = get_unused_fd();
+ ret = get_unused_fd_flags(0);
if (ret < 0)
return ret;
@@ -518,7 +518,7 @@ static int spufs_gang_open(struct path *path)
int ret;
struct file *filp;
- ret = get_unused_fd();
+ ret = get_unused_fd_flags(0);
if (ret < 0)
return ret;
--
1.9.3
^ 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