From 3b885787ea4112eaa80945999ea0901bf742707f Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 12 Oct 2009 13:26:31 -0700 Subject: net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/powerpc/include/asm/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h index 3ab8b3e6feb0..866f7606da68 100644 --- a/arch/powerpc/include/asm/socket.h +++ b/arch/powerpc/include/asm/socket.h @@ -67,4 +67,6 @@ #define SO_PROTOCOL 38 #define SO_DOMAIN 39 +#define SO_RXQ_OVFL 40 + #endif /* _ASM_POWERPC_SOCKET_H */ -- cgit v1.2.2 From 9d24c888c779c877f1baf5a73e0cec78266ff7bb Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:44 -0600 Subject: of: Rework linux/of.h and asm/prom.h include ordering In preparation to prune things out of the Sparc, PowerPC and Microblaze asm/prom.h files, change the #include statements to ensure that even if asm/prom.h is included first, linux/of.h gets to determine the order in which files are processed. This patch adds a #include to each of the prom.h files *above* the multi-include protection macros to ensure that linux/of.h can define things before prom.h gets processed. At the end of the merge the cross dependencies between the files should be gone and a sane #include scheme can be restored. Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 6ff04185d2aa..b0a84ea5f8ed 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -1,3 +1,4 @@ +#include /* linux/of.h gets to determine #include ordering */ #ifndef _POWERPC_PROM_H #define _POWERPC_PROM_H #ifdef __KERNEL__ @@ -349,11 +350,5 @@ extern int of_irq_to_resource(struct device_node *dev, int index, */ extern void __iomem *of_iomap(struct device_node *device, int index); -/* - * NB: This is here while we transition from using asm/prom.h - * to linux/of.h - */ -#include - #endif /* __KERNEL__ */ #endif /* _POWERPC_PROM_H */ -- cgit v1.2.2 From 731581e6a653f6a68a4d7ba9df6b886a85c7d080 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:46 -0600 Subject: of: merge phandle, ihandle and struct property Merge of common code duplicated between Sparc, PowerPC and Microblaze Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index b0a84ea5f8ed..c236326177a8 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -71,18 +71,6 @@ struct boot_param_header u32 dt_struct_size; /* size of the DT structure block */ }; - - -typedef u32 phandle; -typedef u32 ihandle; - -struct property { - char *name; - int length; - void *value; - struct property *next; -}; - struct device_node { const char *name; const char *type; -- cgit v1.2.2 From 6f1924928377bd035a9f64466f91a487c69271d2 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:49 -0600 Subject: of: merge struct device_node Merge of common code duplicated between Sparc, PowerPC and Microblaze Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index c236326177a8..c918db535f08 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -71,26 +71,6 @@ struct boot_param_header u32 dt_struct_size; /* size of the DT structure block */ }; -struct device_node { - const char *name; - const char *type; - phandle node; - phandle linux_phandle; - char *full_name; - - struct property *properties; - struct property *deadprops; /* removed properties */ - struct device_node *parent; - struct device_node *child; - struct device_node *sibling; - struct device_node *next; /* next device of same type */ - struct device_node *allnext; /* next in list of all nodes */ - struct proc_dir_entry *pde; /* this node's proc directory */ - struct kref kref; - unsigned long _flags; - void *data; -}; - extern struct device_node *of_chosen; static inline int of_node_check_flag(struct device_node *n, unsigned long flag) -- cgit v1.2.2 From d8678b58708d7e6bf947ebd03eaf44baf2adfad8 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:53 -0600 Subject: of: add common header for flattened device tree representation Add a common header file for working with the flattened device tree data structure and merge the shared data tags used by Microblaze and PowerPC Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index c918db535f08..7181f8ac40f9 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -17,6 +17,7 @@ * 2 of the License, or (at your option) any later version. */ #include +#include #include #include #include @@ -29,17 +30,6 @@ #define of_prop_cmp(s1, s2) strcmp((s1), (s2)) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) -/* Definitions used by the flattened device tree */ -#define OF_DT_HEADER 0xd00dfeed /* marker */ -#define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ -#define OF_DT_END_NODE 0x2 /* End node */ -#define OF_DT_PROP 0x3 /* Property: name off, size, - * content */ -#define OF_DT_NOP 0x4 /* nop */ -#define OF_DT_END 0x9 - -#define OF_DT_VERSION 0x10 - /* * This is what gets passed to the kernel by prom_init or kexec * -- cgit v1.2.2 From d45d94f672e3c79b0db1e6d76e1638ee521d56c0 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:55 -0600 Subject: of: merge struct boot_param_header from Microblaze and PowerPC Merge common code for working with Flattened Device Tree data structure Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 7181f8ac40f9..ef20e6c23235 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -30,37 +30,6 @@ #define of_prop_cmp(s1, s2) strcmp((s1), (s2)) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) -/* - * This is what gets passed to the kernel by prom_init or kexec - * - * The dt struct contains the device tree structure, full pathes and - * property contents. The dt strings contain a separate block with just - * the strings for the property names, and is fully page aligned and - * self contained in a page, so that it can be kept around by the kernel, - * each property name appears only once in this page (cheap compression) - * - * the mem_rsvmap contains a map of reserved ranges of physical memory, - * passing it here instead of in the device-tree itself greatly simplifies - * the job of everybody. It's just a list of u64 pairs (base/size) that - * ends when size is 0 - */ -struct boot_param_header -{ - u32 magic; /* magic word OF_DT_HEADER */ - u32 totalsize; /* total size of DT block */ - u32 off_dt_struct; /* offset to structure */ - u32 off_dt_strings; /* offset to strings */ - u32 off_mem_rsvmap; /* offset to memory reserve map */ - u32 version; /* format version */ - u32 last_comp_version; /* last compatible version */ - /* version 2 fields below */ - u32 boot_cpuid_phys; /* Physical CPU id we're booting on */ - /* version 3 fields below */ - u32 dt_strings_size; /* size of the DT strings block */ - /* version 17 fields below */ - u32 dt_struct_size; /* size of the DT structure block */ -}; - extern struct device_node *of_chosen; static inline int of_node_check_flag(struct device_node *n, unsigned long flag) -- cgit v1.2.2 From 50436312f47f1fd2bf82c983638fe27ca7e03238 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:57:58 -0600 Subject: of: merge of_node_*_flag() and set_node_proc_entry() Merge common code between PowerPC and Microblaze Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index ef20e6c23235..2cfd43288a3e 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -32,25 +32,8 @@ extern struct device_node *of_chosen; -static inline int of_node_check_flag(struct device_node *n, unsigned long flag) -{ - return test_bit(flag, &n->_flags); -} - -static inline void of_node_set_flag(struct device_node *n, unsigned long flag) -{ - set_bit(flag, &n->_flags); -} - - #define HAVE_ARCH_DEVTREE_FIXUPS -static inline void set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de) -{ - dn->pde = de; -} - - extern struct device_node *of_find_all_nodes(struct device_node *prev); extern struct device_node *of_node_get(struct device_node *node); extern void of_node_put(struct device_node *node); -- cgit v1.2.2 From b6caf2ad7ce30648b89c1cf40d8f7cf6f4b58033 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:58:00 -0600 Subject: of: merge of_read_number() an of_read_ulong() Merge common code between Microblaze and PowerPC Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 2cfd43288a3e..d8c0525c3139 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -89,26 +89,6 @@ extern int release_OF_resource(struct device_node* node, int index); * OF address retreival & translation */ - -/* Helper to read a big number; size is in cells (not bytes) */ -static inline u64 of_read_number(const u32 *cell, int size) -{ - u64 r = 0; - while (size--) - r = (r << 32) | *(cell++); - return r; -} - -/* Like of_read_number, but we want an unsigned long result */ -#ifdef CONFIG_PPC32 -static inline unsigned long of_read_ulong(const u32 *cell, int size) -{ - return cell[size-1]; -} -#else -#define of_read_ulong(cell, size) of_read_number(cell, size) -#endif - /* Translate an OF address block into a CPU physical address */ extern u64 of_translate_address(struct device_node *np, const u32 *addr); -- cgit v1.2.2 From 526b5b3ed97bac22ed0c9feed97adcdc3a25244c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:58:02 -0600 Subject: of: merge of_node_get(), of_node_put() and of_find_all_nodes() Merge common code between Sparc, PowerPC and Microblaze. Sparc differs in the implementation at this point, so this patch uses a #ifdef to handle sparc differently for now. The merging of implementations will occur in a later patch Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index d8c0525c3139..622769cd1d62 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -34,10 +34,6 @@ extern struct device_node *of_chosen; #define HAVE_ARCH_DEVTREE_FIXUPS -extern struct device_node *of_find_all_nodes(struct device_node *prev); -extern struct device_node *of_node_get(struct device_node *node); -extern void of_node_put(struct device_node *node); - /* For scanning the flat device-tree at boot time */ extern int __init of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, int depth, -- cgit v1.2.2 From 8482f56803b9498af84bc09e7bc769a5924f6443 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:58:04 -0600 Subject: of: merge of_*_flat_dt*() functions Merge common flattened device tree code between Microblaze and PowerPC Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 622769cd1d62..c8b59330b04a 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -34,16 +34,6 @@ extern struct device_node *of_chosen; #define HAVE_ARCH_DEVTREE_FIXUPS -/* For scanning the flat device-tree at boot time */ -extern int __init of_scan_flat_dt(int (*it)(unsigned long node, - const char *uname, int depth, - void *data), - void *data); -extern void* __init of_get_flat_dt_prop(unsigned long node, const char *name, - unsigned long *size); -extern int __init of_flat_dt_is_compatible(unsigned long node, const char *name); -extern unsigned long __init of_get_flat_dt_root(void); - /* For updating the device tree at runtime */ extern void of_attach_node(struct device_node *); extern void of_detach_node(struct device_node *); -- cgit v1.2.2 From 82b2928c95d824afd9af3bb41660f3c3fa1f234e Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:58:07 -0600 Subject: of: merge other miscellaneous prototypes Merge common prototypes used by Microblaze and PowerPC Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/include/asm/prom.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index c8b59330b04a..2ab9cbd98826 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -38,20 +38,6 @@ extern struct device_node *of_chosen; extern void of_attach_node(struct device_node *); extern void of_detach_node(struct device_node *); -/* Other Prototypes */ -extern void finish_device_tree(void); -extern void unflatten_device_tree(void); -extern void early_init_devtree(void *); -extern int machine_is_compatible(const char *compat); -extern void print_properties(struct device_node *node); -extern int prom_n_intr_cells(struct device_node* np); -extern void prom_get_irq_senses(unsigned char *senses, int off, int max); -extern int prom_add_property(struct device_node* np, struct property* prop); -extern int prom_remove_property(struct device_node *np, struct property *prop); -extern int prom_update_property(struct device_node *np, - struct property *newprop, - struct property *oldprop); - #ifdef CONFIG_PPC32 /* * PCI <-> OF matching functions -- cgit v1.2.2 From e91edcf5a2940bb7f1f316c871dfe9e2aaf9d6d9 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 Oct 2009 10:58:09 -0600 Subject: of: merge of_find_all_nodes() implementations Merge common code between Microblaze and PowerPC, and make it available to Sparc Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Wolfram Sang Acked-by: Michal Simek Acked-by: Stephen Neuendorffer Acked-by: Stephen Rothwell --- arch/powerpc/kernel/prom.c | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d4405b95bfaa..4ec300862466 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1316,29 +1316,6 @@ struct device_node *of_find_next_cache_node(struct device_node *np) return NULL; } -/** - * of_find_all_nodes - Get next node in global list - * @prev: Previous node or NULL to start iteration - * of_node_put() will be called on it - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_all_nodes(struct device_node *prev) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = prev ? prev->allnext : allnodes; - for (; np != 0; np = np->allnext) - if (of_node_get(np)) - break; - of_node_put(prev); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_all_nodes); - /** * of_node_get - Increment refcount of a node * @node: Node to inc refcount, NULL is supported to -- cgit v1.2.2 From bc284e5d9d6da48934a177db92bf8e09b96a9cb8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 21 Sep 2009 16:56:10 +0000 Subject: powerpc: perf_event: Log invalid data addresses as all 1s When we take an exception and the SDAR isn't synchronised we currently log 0 as the address. Unfortunately this is a pretty common value, so use ~0UL instead. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index bbcbae183e92..73c3b73bf009 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1162,7 +1162,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, */ if (record) { struct perf_sample_data data = { - .addr = 0, + .addr = ~0ULL, .period = event->hw.last_period, }; -- cgit v1.2.2 From 81cd5ae303e88a1e9d3a3e0f1fe8abd100edde16 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 27 Oct 2009 18:31:29 +0000 Subject: powerpc: perf_event: Enable SDAR in continous sample mode In continuous sampling mode we want the SDAR to update. While we can select between dcache misses and ERAT (L1-TLB) misses, a decent default is to enable both. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/kernel/power5+-pmu.c | 4 ---- arch/powerpc/kernel/power5-pmu.c | 6 +----- arch/powerpc/kernel/power6-pmu.c | 2 +- arch/powerpc/kernel/power7-pmu.c | 6 +----- arch/powerpc/kernel/ppc970-pmu.c | 4 ---- 6 files changed, 5 insertions(+), 19 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 6315edc205d8..bc8dd53f718a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -489,6 +489,8 @@ #define SPRN_MMCR1 798 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ +#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL +#define MMCRA_SDAR_ERAT_MISS 0x20000000UL #define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */ #define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index 0f4c1c73a6ad..199de527d411 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -72,10 +72,6 @@ #define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) #define MMCR1_PMCSEL_MSK 0x7f -/* - * Bits in MMCRA - */ - /* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index c351b3a57fbb..98b6a729a9dd 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -72,10 +72,6 @@ #define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) #define MMCR1_PMCSEL_MSK 0x7f -/* - * Bits in MMCRA - */ - /* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 @@ -390,7 +386,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; unsigned int pmc, unit, byte, psel; unsigned int ttm, grp; int i, isbus, bit, grsel; diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index ca399ba5034c..84a607bda8fb 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -178,7 +178,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; int i; unsigned int pmc, ev, b, u, s, psel; unsigned int ttmset = 0; diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 28a4daacdc02..852f7b7f6b40 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -50,10 +50,6 @@ #define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) #define MMCR1_PMCSEL_MSK 0xff -/* - * Bits in MMCRA - */ - /* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 @@ -230,7 +226,7 @@ static int power7_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; unsigned int pmc, unit, combine, l2sel, psel; unsigned int pmc_inuse = 0; int i; diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 479574413a93..8eff48e20dba 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -83,10 +83,6 @@ static short mmcr1_adder_bits[8] = { MMCR1_PMC8_ADDER_SEL_SH }; -/* - * Bits in MMCRA - */ - /* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 -- cgit v1.2.2 From eecff81d1fcda22cd0029d11fe2a71dceed11dad Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 27 Oct 2009 18:46:55 +0000 Subject: powerpc: Create PPC_WARN_ALIGNMENT to match PPC_WARN_EMULATED perf_event wants a separate event for alignment and emulation faults, so create another emulation event. This will make it easy to hook in perf_event at one spot. We pass in regs which will be required for these events. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/emulated_ops.h | 7 +++++-- arch/powerpc/kernel/align.c | 12 ++++++------ arch/powerpc/kernel/traps.c | 18 +++++++++--------- 3 files changed, 20 insertions(+), 17 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 9154e8526732..640c4e456aa5 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -57,7 +57,7 @@ extern u32 ppc_warn_emulated; extern void ppc_warn_emulated_print(const char *type); -#define PPC_WARN_EMULATED(type) \ +#define __PPC_WARN_EMULATED(type) \ do { \ atomic_inc(&ppc_emulated.type.val); \ if (ppc_warn_emulated) \ @@ -66,8 +66,11 @@ extern void ppc_warn_emulated_print(const char *type); #else /* !CONFIG_PPC_EMULATED_STATS */ -#define PPC_WARN_EMULATED(type) do { } while (0) +#define __PPC_WARN_EMULATED(type) do { } while (0) #endif /* !CONFIG_PPC_EMULATED_STATS */ +#define PPC_WARN_EMULATED(type, regs) __PPC_WARN_EMULATED(type) +#define PPC_WARN_ALIGNMENT(type, regs) __PPC_WARN_EMULATED(type) + #endif /* _ASM_POWERPC_EMULATED_OPS_H */ diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index a5b632e52fae..3839839f83c7 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -732,7 +732,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_SPE if ((instr >> 26) == 0x4) { - PPC_WARN_EMULATED(spe); + PPC_WARN_ALIGNMENT(spe, regs); return emulate_spe(regs, reg, instr); } #endif @@ -786,7 +786,7 @@ int fix_alignment(struct pt_regs *regs) flags |= SPLT; nb = 8; } - PPC_WARN_EMULATED(vsx); + PPC_WARN_ALIGNMENT(vsx, regs); return emulate_vsx(addr, reg, areg, regs, flags, nb); } #endif @@ -794,7 +794,7 @@ int fix_alignment(struct pt_regs *regs) * the exception of DCBZ which is handled as a special case here */ if (instr == DCBZ) { - PPC_WARN_EMULATED(dcbz); + PPC_WARN_ALIGNMENT(dcbz, regs); return emulate_dcbz(regs, addr); } if (unlikely(nb == 0)) @@ -804,7 +804,7 @@ int fix_alignment(struct pt_regs *regs) * function */ if (flags & M) { - PPC_WARN_EMULATED(multiple); + PPC_WARN_ALIGNMENT(multiple, regs); return emulate_multiple(regs, addr, reg, nb, flags, instr, swiz); } @@ -825,11 +825,11 @@ int fix_alignment(struct pt_regs *regs) /* Special case for 16-byte FP loads and stores */ if (nb == 16) { - PPC_WARN_EMULATED(fp_pair); + PPC_WARN_ALIGNMENT(fp_pair, regs); return emulate_fp_pair(addr, reg, flags); } - PPC_WARN_EMULATED(unaligned); + PPC_WARN_ALIGNMENT(unaligned, regs); /* If we are loading, get the data from user space, else * get it from register values diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6f0ae1a9bfae..9d1f9354d6ca 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -759,7 +759,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate the mfspr rD, PVR. */ if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) { - PPC_WARN_EMULATED(mfpvr); + PPC_WARN_EMULATED(mfpvr, regs); rd = (instword >> 21) & 0x1f; regs->gpr[rd] = mfspr(SPRN_PVR); return 0; @@ -767,7 +767,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulating the dcba insn is just a no-op. */ if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) { - PPC_WARN_EMULATED(dcba); + PPC_WARN_EMULATED(dcba, regs); return 0; } @@ -776,7 +776,7 @@ static int emulate_instruction(struct pt_regs *regs) int shift = (instword >> 21) & 0x1c; unsigned long msk = 0xf0000000UL >> shift; - PPC_WARN_EMULATED(mcrxr); + PPC_WARN_EMULATED(mcrxr, regs); regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk); regs->xer &= ~0xf0000000UL; return 0; @@ -784,19 +784,19 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate load/store string insn. */ if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) { - PPC_WARN_EMULATED(string); + PPC_WARN_EMULATED(string, regs); return emulate_string_inst(regs, instword); } /* Emulate the popcntb (Population Count Bytes) instruction. */ if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) { - PPC_WARN_EMULATED(popcntb); + PPC_WARN_EMULATED(popcntb, regs); return emulate_popcntb_inst(regs, instword); } /* Emulate isel (Integer Select) instruction */ if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) { - PPC_WARN_EMULATED(isel); + PPC_WARN_EMULATED(isel, regs); return emulate_isel(regs, instword); } @@ -995,7 +995,7 @@ void SoftwareEmulation(struct pt_regs *regs) #ifdef CONFIG_MATH_EMULATION errcode = do_mathemu(regs); if (errcode >= 0) - PPC_WARN_EMULATED(math); + PPC_WARN_EMULATED(math, regs); switch (errcode) { case 0: @@ -1018,7 +1018,7 @@ void SoftwareEmulation(struct pt_regs *regs) #elif defined(CONFIG_8XX_MINIMAL_FPEMU) errcode = Soft_emulate_8xx(regs); if (errcode >= 0) - PPC_WARN_EMULATED(8xx); + PPC_WARN_EMULATED(8xx, regs); switch (errcode) { case 0: @@ -1129,7 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs) flush_altivec_to_thread(current); - PPC_WARN_EMULATED(altivec); + PPC_WARN_EMULATED(altivec, regs); err = emulate_altivec(regs); if (err == 0) { regs->nip += 4; /* skip emulated instruction */ -- cgit v1.2.2 From 196f02bf900c5eb6f85d889c4f70e7cc11fda7e8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 01:13:00 +0000 Subject: powerpc: perf_event: Add alignment-faults and emulation-faults software events Hook up the alignment-faults and emulation-faults events for powerpc. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/emulated_ops.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 640c4e456aa5..f0fb4fc1f6e6 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -19,6 +19,7 @@ #define _ASM_POWERPC_EMULATED_OPS_H #include +#include #ifdef CONFIG_PPC_EMULATED_STATS @@ -70,7 +71,18 @@ extern void ppc_warn_emulated_print(const char *type); #endif /* !CONFIG_PPC_EMULATED_STATS */ -#define PPC_WARN_EMULATED(type, regs) __PPC_WARN_EMULATED(type) -#define PPC_WARN_ALIGNMENT(type, regs) __PPC_WARN_EMULATED(type) +#define PPC_WARN_EMULATED(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, \ + 1, 0, regs, 0); \ + __PPC_WARN_EMULATED(type); \ + } while (0) + +#define PPC_WARN_ALIGNMENT(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, \ + 1, 0, regs, regs->dar); \ + __PPC_WARN_EMULATED(type); \ + } while (0) #endif /* _ASM_POWERPC_EMULATED_OPS_H */ -- cgit v1.2.2 From 1bf4af165050d90ea6659ffb2536ec8ca783aab5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:47:42 +0000 Subject: powerpc: tracing: Add powerpc tracepoints for interrupt entry and exit This adds powerpc-specific tracepoints for interrupt entry and exit. While we already have generic irq_handler_entry and irq_handler_exit tracepoints there are cases on our virtualised powerpc machines where an interrupt is presented to the OS, but subsequently handled by the hypervisor. This means no OS interrupt handler is invoked. Here is an example on a POWER6 machine with the patch below applied: -0 [006] 3243.949840744: irq_entry: pt_regs=c0000000ce31fb10 -0 [006] 3243.949850520: irq_exit: pt_regs=c0000000ce31fb10 -0 [007] 3243.950218208: irq_entry: pt_regs=c0000000ce323b10 -0 [007] 3243.950224080: irq_exit: pt_regs=c0000000ce323b10 -0 [000] 3244.021879320: irq_entry: pt_regs=c000000000a63aa0 -0 [000] 3244.021883616: irq_handler_entry: irq=87 handler=eth0 -0 [000] 3244.021887328: irq_handler_exit: irq=87 return=handled -0 [000] 3244.021897408: irq_exit: pt_regs=c000000000a63aa0 Here we see two phantom interrupts (no handler was invoked), followed by a real interrupt for eth0. Without the tracepoints in this patch we would have missed the phantom interrupts. Signed-off-by: Anton Blanchard Acked-by: Steven Rostedt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 53 ++++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/irq.c | 6 +++++ 2 files changed, 59 insertions(+) create mode 100644 arch/powerpc/include/asm/trace.h (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h new file mode 100644 index 000000000000..187696da5ae7 --- /dev/null +++ b/arch/powerpc/include/asm/trace.h @@ -0,0 +1,53 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM powerpc + +#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_POWERPC_H + +#include + +struct pt_regs; + +TRACE_EVENT(irq_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(irq_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +#endif /* _TRACE_POWERPC_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH asm +#define TRACE_INCLUDE_FILE trace + +#include diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index e5d121177984..02a334662cc0 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -70,6 +70,8 @@ #include #include #endif +#define CREATE_TRACE_POINTS +#include int __irq_offset_value; static int ppc_spurious_interrupts; @@ -325,6 +327,8 @@ void do_IRQ(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); unsigned int irq; + trace_irq_entry(regs); + irq_enter(); check_stack_overflow(); @@ -348,6 +352,8 @@ void do_IRQ(struct pt_regs *regs) timer_interrupt(regs); } #endif + + trace_irq_exit(regs); } void __init init_IRQ(void) -- cgit v1.2.2 From 6795b85c6a4f690e61e7be31aa150d945c723fb5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:49:14 +0000 Subject: powerpc: tracing: Add powerpc tracepoints for timer entry and exit We can monitor the effectiveness of our power management of both the kernel and hypervisor by probing the timer interrupt. For example, on this box we see 10.37s timer interrupts on an idle core: -0 [010] 3900.671297: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3900.671302: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 -0 [010] 3911.042963: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3911.042968: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 -0 [010] 3921.414630: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3921.414635: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 Since we have a 207MHz decrementer it will go negative and fire every 10.37s even if Linux is completely idle. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 34 ++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/time.c | 6 ++++++ 2 files changed, 40 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 187696da5ae7..b558c31d409e 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -42,6 +42,40 @@ TRACE_EVENT(irq_exit, TP_printk("pt_regs=%p", __entry->regs) ); +TRACE_EVENT(timer_interrupt_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(timer_interrupt_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + #endif /* _TRACE_POWERPC_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 92dc844299b6..d6e88df4630c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs) struct clock_event_device *evt = &decrementer->event; u64 now; + trace_timer_interrupt_entry(regs); + /* Ensure a positive value is written to the decrementer, or else * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); @@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs) now = decrementer->next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + trace_timer_interrupt_exit(regs); return; } old_regs = set_irq_regs(regs); @@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs) irq_exit(); set_irq_regs(old_regs); + + trace_timer_interrupt_exit(regs); } void wakeup_decrementer(void) -- cgit v1.2.2 From c8cd093a6e9f96ea6b871576fd4e46d7c818bb89 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:50:29 +0000 Subject: powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig.debug | 2 +- arch/powerpc/include/asm/hvcall.h | 2 + arch/powerpc/include/asm/trace.h | 45 ++++++++++++ arch/powerpc/platforms/pseries/hvCall.S | 101 +++++++++++++++------------ arch/powerpc/platforms/pseries/hvCall_inst.c | 37 ++++++++++ arch/powerpc/platforms/pseries/lpar.c | 32 +++++++++ 6 files changed, 175 insertions(+), 44 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 3b1005185390..bf3382f1904d 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE config HCALL_STATS bool "Hypervisor call instrumentation" - depends on PPC_PSERIES && DEBUG_FS + depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS help Adds code to keep track of the number of hypervisor calls made and the amount of time spent in hypervisor calls. Wall time spent in diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 6251a4b10be7..c27caac47ad1 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -274,6 +274,8 @@ struct hcall_stats { unsigned long num_calls; /* number of calls (on this CPU) */ unsigned long tb_total; /* total wall time (mftb) of calls. */ unsigned long purr_total; /* total cpu time (PURR) of calls. */ + unsigned long tb_start; + unsigned long purr_start; }; #define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1) diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index b558c31d409e..9b01c0e43b55 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -76,6 +76,51 @@ TRACE_EVENT(timer_interrupt_exit, TP_printk("pt_regs=%p", __entry->regs) ); +#ifdef CONFIG_PPC_PSERIES +extern void hcall_tracepoint_regfunc(void); +extern void hcall_tracepoint_unregfunc(void); + +TRACE_EVENT_FN(hcall_entry, + + TP_PROTO(unsigned long opcode), + + TP_ARGS(opcode), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + ), + + TP_fast_assign( + __entry->opcode = opcode; + ), + + TP_printk("opcode=%lu", __entry->opcode), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); + +TRACE_EVENT_FN(hcall_exit, + + TP_PROTO(unsigned long opcode, unsigned long retval), + + TP_ARGS(opcode, retval), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + __field(unsigned long, retval) + ), + + TP_fast_assign( + __entry->opcode = opcode; + __entry->retval = retval; + ), + + TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); +#endif + #endif /* _TRACE_POWERPC_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index c1427b3634ec..01e95ab18d35 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -14,20 +14,54 @@ #define STK_PARM(i) (48 + ((i)-3)*8) -#ifdef CONFIG_HCALL_STATS +#ifdef CONFIG_TRACEPOINTS + + .section ".toc","aw" + + .globl hcall_tracepoint_refcount +hcall_tracepoint_refcount: + .llong 0 + + .section ".text" + /* * precall must preserve all registers. use unused STK_PARM() - * areas to save snapshots and opcode. + * areas to save snapshots and opcode. We branch around this + * in early init (eg when populating the MMU hashtable) by using an + * unconditional cpu feature. */ #define HCALL_INST_PRECALL \ - std r3,STK_PARM(r3)(r1); /* save opcode */ \ - mftb r0; /* get timebase and */ \ - std r0,STK_PARM(r5)(r1); /* save for later */ \ BEGIN_FTR_SECTION; \ - mfspr r0,SPRN_PURR; /* get PURR and */ \ - std r0,STK_PARM(r6)(r1); /* save for later */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); - + b 1f; \ +END_FTR_SECTION(0, 1); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + std r3,STK_PARM(r3)(r1); \ + std r4,STK_PARM(r4)(r1); \ + std r5,STK_PARM(r5)(r1); \ + std r6,STK_PARM(r6)(r1); \ + std r7,STK_PARM(r7)(r1); \ + std r8,STK_PARM(r8)(r1); \ + std r9,STK_PARM(r9)(r1); \ + std r10,STK_PARM(r10)(r1); \ + std r0,16(r1); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_entry; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + ld r4,STK_PARM(r4)(r1); \ + ld r5,STK_PARM(r5)(r1); \ + ld r6,STK_PARM(r6)(r1); \ + ld r7,STK_PARM(r7)(r1); \ + ld r8,STK_PARM(r8)(r1); \ + ld r9,STK_PARM(r9)(r1); \ + ld r10,STK_PARM(r10)(r1); \ + mtlr r0; \ +1: + /* * postcall is performed immediately before function return which * allows liberal use of volatile registers. We branch around this @@ -38,40 +72,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_PURR); BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ - ld r4,STK_PARM(r3)(r1); /* validate opcode */ \ - cmpldi cr7,r4,MAX_HCALL_OPCODE; \ - bgt- cr7,1f; \ - \ - /* get time and PURR snapshots after hcall */ \ - mftb r7; /* timebase after */ \ -BEGIN_FTR_SECTION; \ - mfspr r8,SPRN_PURR; /* PURR after */ \ - ld r6,STK_PARM(r6)(r1); /* PURR before */ \ - subf r6,r6,r8; /* delta */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ - ld r5,STK_PARM(r5)(r1); /* timebase before */ \ - subf r5,r5,r7; /* time delta */ \ - \ - /* calculate address of stat structure r4 = opcode */ \ - srdi r4,r4,2; /* index into array */ \ - mulli r4,r4,HCALL_STAT_SIZE; \ - LOAD_REG_ADDR(r7, per_cpu__hcall_stats); \ - add r4,r4,r7; \ - ld r7,PACA_DATA_OFFSET(r13); /* per cpu offset */ \ - add r4,r4,r7; \ - \ - /* update stats */ \ - ld r7,HCALL_STAT_CALLS(r4); /* count */ \ - addi r7,r7,1; \ - std r7,HCALL_STAT_CALLS(r4); \ - ld r7,HCALL_STAT_TB(r4); /* timebase */ \ - add r7,r7,r5; \ - std r7,HCALL_STAT_TB(r4); \ -BEGIN_FTR_SECTION; \ - ld r7,HCALL_STAT_PURR(r4); /* PURR */ \ - add r7,r7,r6; \ - std r7,HCALL_STAT_PURR(r4); \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + ld r6,STK_PARM(r3)(r1); \ + std r3,STK_PARM(r3)(r1); \ + mr r4,r3; \ + mr r3,r6; \ + std r0,16(r1); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_exit; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + mtlr r0; \ 1: #else #define HCALL_INST_PRECALL diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 3631a4f277eb..e44e1035f133 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -26,6 +26,7 @@ #include #include #include +#include DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats); @@ -100,6 +101,34 @@ static const struct file_operations hcall_inst_seq_fops = { #define HCALL_ROOT_DIR "hcall_inst" #define CPU_NAME_BUF_SIZE 32 + +static void probe_hcall_entry(unsigned long opcode) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &get_cpu_var(hcall_stats)[opcode / 4]; + h->tb_start = mftb(); + h->purr_start = mfspr(SPRN_PURR); +} + +static void probe_hcall_exit(unsigned long opcode, unsigned long retval) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &__get_cpu_var(hcall_stats)[opcode / 4]; + h->num_calls++; + h->tb_total = mftb() - h->tb_start; + h->purr_total = mfspr(SPRN_PURR) - h->purr_start; + + put_cpu_var(hcall_stats); +} + static int __init hcall_inst_init(void) { struct dentry *hcall_root; @@ -110,6 +139,14 @@ static int __init hcall_inst_init(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) return 0; + if (register_trace_hcall_entry(probe_hcall_entry)) + return -EINVAL; + + if (register_trace_hcall_exit(probe_hcall_exit)) { + unregister_trace_hcall_entry(probe_hcall_entry); + return -EINVAL; + } + hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL); if (!hcall_root) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 903eb9eec687..4b7b6e8e32de 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "plpar_wrappers.h" #include "pseries.h" @@ -661,3 +662,34 @@ void arch_free_page(struct page *page, int order) EXPORT_SYMBOL(arch_free_page); #endif + +#ifdef CONFIG_TRACEPOINTS +/* + * We optimise our hcall path by placing hcall_tracepoint_refcount + * directly in the TOC so we can check if the hcall tracepoints are + * enabled via a single load. + */ + +/* NB: reg/unreg are called while guarded with the tracepoints_mutex */ +extern long hcall_tracepoint_refcount; + +void hcall_tracepoint_regfunc(void) +{ + hcall_tracepoint_refcount++; +} + +void hcall_tracepoint_unregfunc(void) +{ + hcall_tracepoint_refcount--; +} + +void __trace_hcall_entry(unsigned long opcode) +{ + trace_hcall_entry(opcode); +} + +void __trace_hcall_exit(long opcode, unsigned long retval) +{ + trace_hcall_exit(opcode, retval); +} +#endif -- cgit v1.2.2 From 6f26353ca29e96475208bce673efb6a2c58b73f2 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:51:09 +0000 Subject: powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 9 ++++---- arch/powerpc/platforms/pseries/hvCall.S | 31 +++++++++++++++++++--------- arch/powerpc/platforms/pseries/hvCall_inst.c | 5 +++-- arch/powerpc/platforms/pseries/lpar.c | 9 ++++---- 4 files changed, 34 insertions(+), 20 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 9b01c0e43b55..cbe2297d68b6 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -82,9 +82,9 @@ extern void hcall_tracepoint_unregfunc(void); TRACE_EVENT_FN(hcall_entry, - TP_PROTO(unsigned long opcode), + TP_PROTO(unsigned long opcode, unsigned long *args), - TP_ARGS(opcode), + TP_ARGS(opcode, args), TP_STRUCT__entry( __field(unsigned long, opcode) @@ -101,9 +101,10 @@ TRACE_EVENT_FN(hcall_entry, TRACE_EVENT_FN(hcall_exit, - TP_PROTO(unsigned long opcode, unsigned long retval), + TP_PROTO(unsigned long opcode, unsigned long retval, + unsigned long *retbuf), - TP_ARGS(opcode, retval), + TP_ARGS(opcode, retval, retbuf), TP_STRUCT__entry( __field(unsigned long, opcode) diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 01e95ab18d35..383a5d0e9818 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -30,7 +30,7 @@ hcall_tracepoint_refcount: * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. */ -#define HCALL_INST_PRECALL \ +#define HCALL_INST_PRECALL(FIRST_REG) \ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ @@ -47,6 +47,7 @@ END_FTR_SECTION(0, 1); \ std r9,STK_PARM(r9)(r1); \ std r10,STK_PARM(r10)(r1); \ std r0,16(r1); \ + addi r4,r1,STK_PARM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ bl .__trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ @@ -68,7 +69,7 @@ END_FTR_SECTION(0, 1); \ * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. */ -#define HCALL_INST_POSTCALL \ +#define __HCALL_INST_POSTCALL \ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ @@ -88,9 +89,19 @@ END_FTR_SECTION(0, 1); \ ld r3,STK_PARM(r3)(r1); \ mtlr r0; \ 1: + +#define HCALL_INST_POSTCALL_NORETS \ + li r5,0; \ + __HCALL_INST_POSTCALL + +#define HCALL_INST_POSTCALL(BUFREG) \ + mr r5,BUFREG; \ + __HCALL_INST_POSTCALL + #else -#define HCALL_INST_PRECALL -#define HCALL_INST_POSTCALL +#define HCALL_INST_PRECALL(FIRST_ARG) +#define HCALL_INST_POSTCALL_NORETS +#define HCALL_INST_POSTCALL(BUFREG) #endif .text @@ -101,11 +112,11 @@ _GLOBAL(plpar_hcall_norets) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r4) HVSC /* invoke the hypervisor */ - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL_NORETS lwz r0,8(r1) mtcrf 0xff,r0 @@ -117,7 +128,7 @@ _GLOBAL(plpar_hcall) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -136,7 +147,7 @@ _GLOBAL(plpar_hcall) std r6, 16(r12) std r7, 24(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 @@ -183,7 +194,7 @@ _GLOBAL(plpar_hcall9) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -211,7 +222,7 @@ _GLOBAL(plpar_hcall9) std r11,56(r12) std r0, 64(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index e44e1035f133..2f58c71b7259 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -102,7 +102,7 @@ static const struct file_operations hcall_inst_seq_fops = { #define CPU_NAME_BUF_SIZE 32 -static void probe_hcall_entry(unsigned long opcode) +static void probe_hcall_entry(unsigned long opcode, unsigned long *args) { struct hcall_stats *h; @@ -114,7 +114,8 @@ static void probe_hcall_entry(unsigned long opcode) h->purr_start = mfspr(SPRN_PURR); } -static void probe_hcall_exit(unsigned long opcode, unsigned long retval) +static void probe_hcall_exit(unsigned long opcode, unsigned long retval, + unsigned long *retbuf) { struct hcall_stats *h; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4b7b6e8e32de..0707653612ba 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -683,13 +683,14 @@ void hcall_tracepoint_unregfunc(void) hcall_tracepoint_refcount--; } -void __trace_hcall_entry(unsigned long opcode) +void __trace_hcall_entry(unsigned long opcode, unsigned long *args) { - trace_hcall_entry(opcode); + trace_hcall_entry(opcode, args); } -void __trace_hcall_exit(long opcode, unsigned long retval) +void __trace_hcall_exit(long opcode, unsigned long retval, + unsigned long *retbuf) { - trace_hcall_exit(opcode, retval); + trace_hcall_exit(opcode, retval, retbuf); } #endif -- cgit v1.2.2 From b3c86ee6d128dea7c671380090488887e73fa774 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:51:57 +0000 Subject: powerpc: Disable HCALL_STATS by default The overhead of HCALL_STATS is quite high and the functionality is very rarely used. Key statistics are also missing (eg min/max). With the new hcall tracepoints much more powerful tracing can be done in a kernel module. Lets disable this by default. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/configs/pseries_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index f1889abb89b1..c568329723b8 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -1683,7 +1683,7 @@ CONFIG_HAVE_ARCH_KGDB=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_STACK_USAGE is not set # CONFIG_DEBUG_PAGEALLOC is not set -CONFIG_HCALL_STATS=y +# CONFIG_HCALL_STATS is not set # CONFIG_CODE_PATCHING_SELFTEST is not set # CONFIG_FTR_FIXUP_SELFTEST is not set # CONFIG_MSI_BITMAP_SELFTEST is not set -- cgit v1.2.2 From 907b1f45d901c956e4bcd3f27c4f1f25d6fb36b2 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:52:24 +0000 Subject: powerpc: Export powerpc_debugfs_root Kernel modules should be able to place their debug output inside our powerpc debugfs directory. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup-common.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 4271f7a655a3..845c72ab7357 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -660,6 +660,7 @@ late_initcall(check_cache_coherency); #ifdef CONFIG_DEBUG_FS struct dentry *powerpc_debugfs_root; +EXPORT_SYMBOL(powerpc_debugfs_root); static int powerpc_debugfs_init(void) { -- cgit v1.2.2 From 3cd980dbc1050889acca7306cbcedf79a4ba2f81 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 01:23:28 +0000 Subject: powerpc: perf_event: Cleanup copy_page output by hiding setup symbol A lot of hits in "setup" doesn't make much sense, so hide this symbol and allow all the hits to end up in copy_4k_page. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/lib/copypage_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 75f3267fdc30..e68beac0a171 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -26,11 +26,11 @@ BEGIN_FTR_SECTION srd r8,r5,r11 mtctr r8 -setup: +.Lsetup: dcbt r9,r4 dcbz r9,r3 add r9,r9,r12 - bdnz setup + bdnz .Lsetup END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ) addi r3,r3,-8 srdi r8,r5,7 /* page is copied in 128 byte strides */ -- cgit v1.2.2 From 917e407c762ba6d91d1a4bc1c804d518585082a3 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 01:24:29 +0000 Subject: powerpc: perf_event: Hide iseries_check_pending_irqs If CONFIG_PPC_ISERIES isn't defined we end up with iseries_check_pending_irqs and do_work at the same address. perf ends up picking iseries_check_pending_irqs which creates confusing backtraces. Hide it. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/entry_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 900e0eea0099..e722226cabc4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -551,7 +551,7 @@ restore: BEGIN_FW_FTR_SECTION ld r5,SOFTE(r1) FW_FTR_SECTION_ELSE - b iseries_check_pending_irqs + b .Liseries_check_pending_irqs ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) 2: TRACE_AND_RESTORE_IRQ(r5); @@ -623,7 +623,7 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) #endif /* CONFIG_PPC_BOOK3E */ -iseries_check_pending_irqs: +.Liseries_check_pending_irqs: #ifdef CONFIG_PPC_ISERIES ld r5,SOFTE(r1) cmpdi 0,r5,0 -- cgit v1.2.2 From c86e2eaded39843e1bf4f07d1adfab4494f20894 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 01:24:06 +0000 Subject: powerpc: perf_event: Cleanup output by adding symbols Add some dummy symbols for the branches at 0xf00, 0xf20 and 0xf40, otherwise hits end up in trap_0e which is confusing to the user. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/exceptions-64s.S | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1808876edcc9..c7eb4e0eb86c 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -185,12 +185,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) * prolog code of the PerformanceMonitor one. A little * trickery is thus necessary */ +performance_monitor_pSeries_1: . = 0xf00 b performance_monitor_pSeries +altivec_unavailable_pSeries_1: . = 0xf20 b altivec_unavailable_pSeries +vsx_unavailable_pSeries_1: . = 0xf40 b vsx_unavailable_pSeries -- cgit v1.2.2 From da3f6f9b3e0d1e73975ca81ae124406bf1587d40 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 3 Apr 2009 00:36:27 -0700 Subject: sysctl: Introduce a generic compat sysctl sysctl This uses compat_alloc_userspace to remove the various hacks to allow do_sysctl to write to throuh oldlenp. The rest of our mature compat syscall helper facitilies are used as well to ensure we have a nice clean maintainable compat syscall that can be used on all architectures. The motiviation for a generic compat sysctl (besides the obvious hack removal) is to reduce the number of compat sysctl defintions out there so I can refactor the binary sysctl implementation. ppc already used the name compat_sys_sysctl so I remove the ppcs version here. Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Acked-by: Arnd Bergmann Signed-off-by: Eric W. Biederman --- arch/powerpc/kernel/sys_ppc32.c | 52 ----------------------------------------- 1 file changed, 52 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index b97c2d67f4ac..c5a4732bcc48 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -520,58 +520,6 @@ asmlinkage long compat_sys_umask(u32 mask) return sys_umask((int)mask); } -#ifdef CONFIG_SYSCTL_SYSCALL -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long compat_sys_sysctl(struct __sysctl_args32 __user *args) -{ - struct __sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - oldlenp = (size_t __user *)addr; - if (get_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp)) || - put_user(oldlen, oldlenp)) - return -EFAULT; - } - - lock_kernel(); - error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, - compat_ptr(tmp.oldval), oldlenp, - compat_ptr(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, oldlenp) || - put_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp))) - error = -EFAULT; - } - copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused)); - } - return error; -} -#endif - unsigned long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) -- cgit v1.2.2 From ad32e8cb86e7894aac51c8963eaa9f36bb8a4e14 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 10 Nov 2009 19:46:19 +0900 Subject: swiotlb: Defer swiotlb init printing, export swiotlb_print_info() This enables us to avoid printing swiotlb memory info when we initialize swiotlb. After swiotlb initialization, we could find that we don't need swiotlb. This patch removes the code to print swiotlb memory info in swiotlb_init() and exports the function to do that. Signed-off-by: FUJITA Tomonori Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com Cc: tony.luck@intel.com Cc: benh@kernel.crashing.org LKML-Reference: <1257849980-22640-9-git-send-email-fujita.tomonori@lab.ntt.co.jp> [ -v2: merge up conflict ] Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/setup_32.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 53bcf3d792db..b152de3e64d4 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -345,7 +345,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_SWIOTLB if (ppc_swiotlb_enable) - swiotlb_init(); + swiotlb_init(1); #endif paging_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 04f638d82fb3..df2c9e932b37 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -550,7 +550,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_SWIOTLB if (ppc_swiotlb_enable) - swiotlb_init(); + swiotlb_init(1); #endif paging_init(); -- cgit v1.2.2 From 26ea51355847b5cd70b46fe9ec9c68ad067118a4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 3 Apr 2009 05:29:59 -0700 Subject: sysctl powerpc: Remove dead binary sysctl support Now that sys_sysctl is a generic wrapper around /proc/sys .ctl_name and .strategy members of sysctl tables are dead code. Remove them. Cc: Paul Mackerras Acked-by: Benjamin Herrenschmidt Signed-off-by: Eric W. Biederman --- arch/powerpc/kernel/idle.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 88d9c1d5e5fb..cece9e2cc5e4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -110,7 +110,6 @@ int powersave_nap; */ static ctl_table powersave_nap_ctl_table[]={ { - .ctl_name = KERN_PPC_POWERSAVE_NAP, .procname = "powersave-nap", .data = &powersave_nap, .maxlen = sizeof(int), @@ -121,7 +120,6 @@ static ctl_table powersave_nap_ctl_table[]={ }; static ctl_table powersave_nap_sysctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = powersave_nap_ctl_table, -- cgit v1.2.2 From 6d4561110a3e9fa742aeec6717248a491dfb1878 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 16 Nov 2009 03:11:48 -0800 Subject: sysctl: Drop & in front of every proc_handler. For consistency drop & in front of every proc_handler. Explicity taking the address is unnecessary and it prevents optimizations like stubbing the proc_handlers to NULL. Cc: Alexey Dobriyan Cc: Ingo Molnar Cc: Joe Perches Signed-off-by: Eric W. Biederman --- arch/powerpc/kernel/idle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index cece9e2cc5e4..049dda60e475 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -114,7 +114,7 @@ static ctl_table powersave_nap_ctl_table[]={ .data = &powersave_nap, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, {} }; -- cgit v1.2.2 From 2d4dc890b5c8fabd818a8586607e6843c4375e62 Mon Sep 17 00:00:00 2001 From: Ilya Loginov Date: Thu, 26 Nov 2009 09:16:19 +0100 Subject: block: add helpers to run flush_dcache_page() against a bio and a request's pages Mtdblock driver doesn't call flush_dcache_page for pages in request. So, this causes problems on architectures where the icache doesn't fill from the dcache or with dcache aliases. The patch fixes this. The ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE symbol was introduced to avoid pointless empty cache-thrashing loops on architectures for which flush_dcache_page() is a no-op. Every architecture was provided with this flush pages on architectires where ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE is equal 1 or do nothing otherwise. See "fix mtd_blkdevs problem with caches on some architectures" discussion on LKML for more information. Signed-off-by: Ilya Loginov Cc: Ingo Molnar Cc: David Woodhouse Cc: Peter Horton Cc: "Ed L. Cashin" Signed-off-by: Jens Axboe --- arch/powerpc/include/asm/cacheflush.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index ba667a383b8c..ab9e402518e8 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -25,6 +25,7 @@ #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) -- cgit v1.2.2 From e8105903d78c81119754a42926951d9d17e191ba Mon Sep 17 00:00:00 2001 From: Becky Bruce Date: Mon, 23 Nov 2009 12:28:53 +0000 Subject: powerpc: Fix DEBUG_HIGHMEM build break from d4515646699 Code was added to mm/higmem.c that depends on several kmap types that powerpc does not support. We add dummy invalid definitions for KM_NMI, KM_NM_PTE, and KM_IRQ_PTE. According to list discussion, this fix should not be needed anymore starting with 2.6.33. The code is commented to this effect so hopefully we will remember to remove this. Signed-off-by: Becky Bruce Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/kmap_types.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index b6bac6f61c16..916369575c97 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -29,5 +29,16 @@ enum km_type { KM_TYPE_NR }; +/* + * This is a temporary build fix that (so they say on lkml....) should no longer + * be required after 2.6.33, because of changes planned to the kmap code. + * Let's try to remove this cruft then. + */ +#ifdef CONFIG_DEBUG_HIGHMEM +#define KM_NMI (-1) +#define KM_NMI_PTE (-1) +#define KM_IRQ_PTE (-1) +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KMAP_TYPES_H */ -- cgit v1.2.2 From 367e1319b229110a27c53221c2fa32a6aa86d4a9 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 26 Aug 2009 14:57:07 +0300 Subject: KVM: Return -ENOTTY on unrecognized ioctls Not the incorrect -EINVAL. Signed-off-by: Avi Kivity --- arch/powerpc/kvm/powerpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 2a4551f78f60..95af62217b6b 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -421,7 +421,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { default: - r = -EINVAL; + r = -ENOTTY; } return r; -- cgit v1.2.2 From 10474ae8945ce08622fd1f3464e55bd817bf2376 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 15 Sep 2009 11:37:46 +0200 Subject: KVM: Activate Virtualization On Demand X86 CPUs need to have some magic happening to enable the virtualization extensions on them. This magic can result in unpleasant results for users, like blocking other VMMs from working (vmx) or using invalid TLB entries (svm). Currently KVM activates virtualization when the respective kernel module is loaded. This blocks us from autoloading KVM modules without breaking other VMMs. To circumvent this problem at least a bit, this patch introduces on demand activation of virtualization. This means, that instead virtualization is enabled on creation of the first virtual machine and disabled on destruction of the last one. So using this, KVM can be easily autoloaded, while keeping other hypervisors usable. Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/powerpc/kvm/powerpc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 95af62217b6b..5902bbc2411e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -78,8 +78,9 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { + return 0; } void kvm_arch_hardware_disable(void *garbage) -- cgit v1.2.2 From c0a187e12d48235cb8af4cdeff283117ab42bbb2 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 23 Oct 2009 00:35:30 +0000 Subject: KVM: powerpc: Fix BUILD_BUG_ON condition The old BUILD_BUG_ON implementation didn't work with __builtin_constant_p(). Fixing that revealed this test had been inverted for a long time without anybody noticing... Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/kvm/timing.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index 806ef67868bd..8167d42a776f 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -51,7 +51,7 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type) /* The BUILD_BUG_ON below breaks in funny ways, commented out * for now ... -BenH - BUILD_BUG_ON(__builtin_constant_p(type)); + BUILD_BUG_ON(!__builtin_constant_p(type)); */ switch (type) { case EXT_INTR_EXITS: -- cgit v1.2.2 From 6dfa5ca3c9a35cb395ab1f51e0e500106c85dff4 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 6 Dec 2009 17:06:19 +0100 Subject: i2c-powermac: Include the i2c_adapter in struct pmac_i2c_bus Include the i2c_adapter in struct pmac_i2c_bus. This avoids memory fragmentation and allows for several code cleanups. Signed-off-by: Jean Delvare Tested-by: Michel Daenzer Cc: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pmac_low_i2c.h | 6 +----- arch/powerpc/platforms/powermac/low_i2c.c | 25 +++++-------------------- 2 files changed, 6 insertions(+), 25 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/pmac_low_i2c.h b/arch/powerpc/include/asm/pmac_low_i2c.h index 131011bd7e76..01d71826d92f 100644 --- a/arch/powerpc/include/asm/pmac_low_i2c.h +++ b/arch/powerpc/include/asm/pmac_low_i2c.h @@ -72,11 +72,7 @@ extern int pmac_i2c_get_type(struct pmac_i2c_bus *bus); extern int pmac_i2c_get_flags(struct pmac_i2c_bus *bus); extern int pmac_i2c_get_channel(struct pmac_i2c_bus *bus); -/* i2c layer adapter attach/detach */ -extern void pmac_i2c_attach_adapter(struct pmac_i2c_bus *bus, - struct i2c_adapter *adapter); -extern void pmac_i2c_detach_adapter(struct pmac_i2c_bus *bus, - struct i2c_adapter *adapter); +/* i2c layer adapter helpers */ extern struct i2c_adapter *pmac_i2c_get_adapter(struct pmac_i2c_bus *bus); extern struct pmac_i2c_bus *pmac_i2c_adapter_to_bus(struct i2c_adapter *adapter); diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index 414ca9849f23..345e2da56767 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -80,7 +81,7 @@ struct pmac_i2c_bus struct device_node *busnode; int type; int flags; - struct i2c_adapter *adapter; + struct i2c_adapter adapter; void *hostdata; int channel; /* some hosts have multiple */ int mode; /* current mode */ @@ -1014,25 +1015,9 @@ int pmac_i2c_get_channel(struct pmac_i2c_bus *bus) EXPORT_SYMBOL_GPL(pmac_i2c_get_channel); -void pmac_i2c_attach_adapter(struct pmac_i2c_bus *bus, - struct i2c_adapter *adapter) -{ - WARN_ON(bus->adapter != NULL); - bus->adapter = adapter; -} -EXPORT_SYMBOL_GPL(pmac_i2c_attach_adapter); - -void pmac_i2c_detach_adapter(struct pmac_i2c_bus *bus, - struct i2c_adapter *adapter) -{ - WARN_ON(bus->adapter != adapter); - bus->adapter = NULL; -} -EXPORT_SYMBOL_GPL(pmac_i2c_detach_adapter); - struct i2c_adapter *pmac_i2c_get_adapter(struct pmac_i2c_bus *bus) { - return bus->adapter; + return &bus->adapter; } EXPORT_SYMBOL_GPL(pmac_i2c_get_adapter); @@ -1041,7 +1026,7 @@ struct pmac_i2c_bus *pmac_i2c_adapter_to_bus(struct i2c_adapter *adapter) struct pmac_i2c_bus *bus; list_for_each_entry(bus, &pmac_i2c_busses, link) - if (bus->adapter == adapter) + if (&bus->adapter == adapter) return bus; return NULL; } @@ -1053,7 +1038,7 @@ int pmac_i2c_match_adapter(struct device_node *dev, struct i2c_adapter *adapter) if (bus == NULL) return 0; - return (bus->adapter == adapter); + return (&bus->adapter == adapter); } EXPORT_SYMBOL_GPL(pmac_i2c_match_adapter); -- cgit v1.2.2