aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/dma-mapping.h8
-rw-r--r--arch/x86/include/asm/page.h7
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h151
-rw-r--r--arch/x86/include/asm/xen/page.h8
-rw-r--r--arch/x86/include/asm/xen/swiotlb-xen.h14
5 files changed, 125 insertions, 63 deletions
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ac91eed2106..d4c419f883a 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -54,7 +54,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h) (1)
extern int dma_supported(struct device *hwdev, u64 mask);
extern int dma_set_mask(struct device *dev, u64 mask);
@@ -87,13 +86,6 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size,
flush_write_buffers();
}
-static inline int dma_get_cache_alignment(void)
-{
- /* no easy way to get cache size on all x86, so return the
- * maximum possible, to be safe */
- return boot_cpu_data.x86_clflush_size;
-}
-
static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
gfp_t gfp)
{
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 625c3f0e741..8ca82839288 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -37,6 +37,13 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x))
/* __pa_symbol should be used for C visible symbols.
This seems to be the official gcc blessed way to do such arithmetic. */
+/*
+ * We need __phys_reloc_hide() here because gcc may assume that there is no
+ * overflow during __pa() calculation and can optimize it unexpectedly.
+ * Newer versions of gcc provide -fno-strict-overflow switch to handle this
+ * case properly. Once all supported versions of gcc understand it, we can
+ * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
+ */
#define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x)))
#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index aa558ac0306..42d412fd8b0 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -34,6 +34,7 @@
*/
#define UV_ITEMS_PER_DESCRIPTOR 8
+/* the 'throttle' to prevent the hardware stay-busy bug */
#define MAX_BAU_CONCURRENT 3
#define UV_CPUS_PER_ACT_STATUS 32
#define UV_ACT_STATUS_MASK 0x3
@@ -45,10 +46,26 @@
#define UV_DESC_BASE_PNODE_SHIFT 49
#define UV_PAYLOADQ_PNODE_SHIFT 49
#define UV_PTC_BASENAME "sgi_uv/ptc_statistics"
+#define UV_BAU_BASENAME "sgi_uv/bau_tunables"
+#define UV_BAU_TUNABLES_DIR "sgi_uv"
+#define UV_BAU_TUNABLES_FILE "bau_tunables"
+#define WHITESPACE " \t\n"
#define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask))
#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL
+/* [19:16] SOFT_ACK timeout period 19: 1 is urgency 7 17:16 1 is multiplier */
+#define BAU_MISC_CONTROL_MULT_MASK 3
+
+#define UVH_AGING_PRESCALE_SEL 0x000000b000UL
+/* [30:28] URGENCY_7 an index into a table of times */
+#define BAU_URGENCY_7_SHIFT 28
+#define BAU_URGENCY_7_MASK 7
+
+#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL
+/* [45:40] BAU - BAU transaction timeout select - a multiplier */
+#define BAU_TRANS_SHIFT 40
+#define BAU_TRANS_MASK 0x3f
/*
* bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
@@ -59,24 +76,21 @@
#define DESC_STATUS_SOURCE_TIMEOUT 3
/*
- * source side threshholds at which message retries print a warning
- */
-#define SOURCE_TIMEOUT_LIMIT 20
-#define DESTINATION_TIMEOUT_LIMIT 20
-
-/*
- * misc. delays, in microseconds
+ * delay for 'plugged' timeout retries, in microseconds
*/
-#define THROTTLE_DELAY 10
-#define TIMEOUT_DELAY 10
-#define BIOS_TO 1000
-/* BIOS is assumed to set the destination timeout to 1003520 nanoseconds */
+#define PLUGGED_DELAY 10
/*
* threshholds at which to use IPI to free resources
*/
+/* after this # consecutive 'plugged' timeouts, use IPI to release resources */
#define PLUGSB4RESET 100
-#define TIMEOUTSB4RESET 100
+/* after this many consecutive timeouts, use IPI to release resources */
+#define TIMEOUTSB4RESET 1
+/* at this number uses of IPI to release resources, giveup the request */
+#define IPI_RESET_LIMIT 1
+/* after this # consecutive successes, bump up the throttle if it was lowered */
+#define COMPLETE_THRESHOLD 5
/*
* number of entries in the destination side payload queue
@@ -96,6 +110,13 @@
#define FLUSH_COMPLETE 4
/*
+ * tuning the action when the numalink network is extremely delayed
+ */
+#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */
+#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */
+#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */
+
+/*
* Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
* If the 'multilevel' flag in the header portion of the descriptor
* has been set to 0, then endpoint multi-unicast mode is selected.
@@ -300,37 +321,16 @@ struct bau_payload_queue_entry {
/* bytes 24-31 */
};
-/*
- * one per-cpu; to locate the software tables
- */
-struct bau_control {
- struct bau_desc *descriptor_base;
+struct msg_desc {
+ struct bau_payload_queue_entry *msg;
+ int msg_slot;
+ int sw_ack_slot;
struct bau_payload_queue_entry *va_queue_first;
struct bau_payload_queue_entry *va_queue_last;
- struct bau_payload_queue_entry *bau_msg_head;
- struct bau_control *uvhub_master;
- struct bau_control *socket_master;
- unsigned long timeout_interval;
- atomic_t active_descriptor_count;
- int max_concurrent;
- int max_concurrent_constant;
- int retry_message_scans;
- int plugged_tries;
- int timeout_tries;
- int ipi_attempts;
- int conseccompletes;
- short cpu;
- short uvhub_cpu;
- short uvhub;
- short cpus_in_socket;
- short cpus_in_uvhub;
- unsigned short message_number;
- unsigned short uvhub_quiesce;
- short socket_acknowledge_count[DEST_Q_SIZE];
- cycles_t send_message;
- spinlock_t masks_lock;
- spinlock_t uvhub_lock;
- spinlock_t queue_lock;
+};
+
+struct reset_args {
+ int sender;
};
/*
@@ -344,18 +344,25 @@ struct ptc_stats {
unsigned long s_dtimeout; /* destination side timeouts */
unsigned long s_time; /* time spent in sending side */
unsigned long s_retriesok; /* successful retries */
- unsigned long s_ntargcpu; /* number of cpus targeted */
- unsigned long s_ntarguvhub; /* number of uvhubs targeted */
- unsigned long s_ntarguvhub16; /* number of times >= 16 target hubs */
- unsigned long s_ntarguvhub8; /* number of times >= 8 target hubs */
- unsigned long s_ntarguvhub4; /* number of times >= 4 target hubs */
- unsigned long s_ntarguvhub2; /* number of times >= 2 target hubs */
- unsigned long s_ntarguvhub1; /* number of times == 1 target hub */
+ unsigned long s_ntargcpu; /* total number of cpu's targeted */
+ unsigned long s_ntargself; /* times the sending cpu was targeted */
+ unsigned long s_ntarglocals; /* targets of cpus on the local blade */
+ unsigned long s_ntargremotes; /* targets of cpus on remote blades */
+ unsigned long s_ntarglocaluvhub; /* targets of the local hub */
+ unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */
+ unsigned long s_ntarguvhub; /* total number of uvhubs targeted */
+ unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/
+ unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */
+ unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */
+ unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */
+ unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */
unsigned long s_resets_plug; /* ipi-style resets from plug state */
unsigned long s_resets_timeout; /* ipi-style resets from timeouts */
unsigned long s_busy; /* status stayed busy past s/w timer */
unsigned long s_throttles; /* waits in throttle */
unsigned long s_retry_messages; /* retry broadcasts */
+ unsigned long s_bau_reenabled; /* for bau enable/disable */
+ unsigned long s_bau_disabled; /* for bau enable/disable */
/* destination statistics */
unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */
unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */
@@ -370,6 +377,52 @@ struct ptc_stats {
unsigned long d_rcanceled; /* number of messages canceled by resets */
};
+/*
+ * one per-cpu; to locate the software tables
+ */
+struct bau_control {
+ struct bau_desc *descriptor_base;
+ struct bau_payload_queue_entry *va_queue_first;
+ struct bau_payload_queue_entry *va_queue_last;
+ struct bau_payload_queue_entry *bau_msg_head;
+ struct bau_control *uvhub_master;
+ struct bau_control *socket_master;
+ struct ptc_stats *statp;
+ unsigned long timeout_interval;
+ unsigned long set_bau_on_time;
+ atomic_t active_descriptor_count;
+ int plugged_tries;
+ int timeout_tries;
+ int ipi_attempts;
+ int conseccompletes;
+ int baudisabled;
+ int set_bau_off;
+ short cpu;
+ short uvhub_cpu;
+ short uvhub;
+ short cpus_in_socket;
+ short cpus_in_uvhub;
+ unsigned short message_number;
+ unsigned short uvhub_quiesce;
+ short socket_acknowledge_count[DEST_Q_SIZE];
+ cycles_t send_message;
+ spinlock_t uvhub_lock;
+ spinlock_t queue_lock;
+ /* tunables */
+ int max_bau_concurrent;
+ int max_bau_concurrent_constant;
+ int plugged_delay;
+ int plugsb4reset;
+ int timeoutsb4reset;
+ int ipi_reset_limit;
+ int complete_threshold;
+ int congested_response_us;
+ int congested_reps;
+ int congested_period;
+ cycles_t period_time;
+ long period_requests;
+};
+
static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
{
return constant_test_bit(uvhub, &dstp->bits[0]);
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 018a0a40079..bf5f7d32bd0 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -112,13 +112,9 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine)
*/
static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
{
- extern unsigned long max_mapnr;
unsigned long pfn = mfn_to_pfn(mfn);
- if ((pfn < max_mapnr)
- && !xen_feature(XENFEAT_auto_translated_physmap)
- && (get_phys_to_machine(pfn) != mfn))
- return max_mapnr; /* force !pfn_valid() */
- /* XXX fixme; not true with sparsemem */
+ if (get_phys_to_machine(pfn) != mfn)
+ return -1; /* force !pfn_valid() */
return pfn;
}
diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
new file mode 100644
index 00000000000..1be1ab7d6a4
--- /dev/null
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_X86_SWIOTLB_XEN_H
+#define _ASM_X86_SWIOTLB_XEN_H
+
+#ifdef CONFIG_SWIOTLB_XEN
+extern int xen_swiotlb;
+extern int __init pci_xen_swiotlb_detect(void);
+extern void __init pci_xen_swiotlb_init(void);
+#else
+#define xen_swiotlb (0)
+static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
+static inline void __init pci_xen_swiotlb_init(void) { }
+#endif
+
+#endif /* _ASM_X86_SWIOTLB_XEN_H */