2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 20:23:57 +08:00
linux-next/arch/x86/include/asm/uv/uv_hub.h
Jack Steiner c4ed3f04ba x86, UV: Fix macros for multiple coherency domains
Fix bug in the SGI UV macros that support systems with multiple
coherency domains.  The macros used for referencing global MMR
(chipset registers) are failing to correctly "or" the NASID
(node identifier) bits that reside above M+N. These high bits
are supplied automatically by the chipset for memory accesses
coming from the processor socket.

However, the bits must be present for references to the special
global MMR space used to map chipset registers. (See uv_hub.h
for more details ...)

The bug results in references to invalid/incorrect nodes.

Signed-off-by: Jack Steiner <steiner@sgi.com>
Cc: <stable@kernel.org>
LKML-Reference: <20090608154405.GA16395@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-08 18:57:47 +02:00

425 lines
12 KiB
C

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* SGI UV architectural definitions
*
* Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
*/
#ifndef _ASM_X86_UV_UV_HUB_H
#define _ASM_X86_UV_UV_HUB_H
#ifdef CONFIG_X86_64
#include <linux/numa.h>
#include <linux/percpu.h>
#include <linux/timer.h>
#include <asm/types.h>
#include <asm/percpu.h>
#include <asm/uv/uv_mmrs.h>
/*
* Addressing Terminology
*
* M - The low M bits of a physical address represent the offset
* into the blade local memory. RAM memory on a blade is physically
* contiguous (although various IO spaces may punch holes in
* it)..
*
* N - Number of bits in the node portion of a socket physical
* address.
*
* NASID - network ID of a router, Mbrick or Cbrick. Nasid values of
* routers always have low bit of 1, C/MBricks have low bit
* equal to 0. Most addressing macros that target UV hub chips
* right shift the NASID by 1 to exclude the always-zero bit.
* NASIDs contain up to 15 bits.
*
* GNODE - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
* of nasids.
*
* PNODE - the low N bits of the GNODE. The PNODE is the most useful variant
* of the nasid for socket usage.
*
*
* NumaLink Global Physical Address Format:
* +--------------------------------+---------------------+
* |00..000| GNODE | NodeOffset |
* +--------------------------------+---------------------+
* |<-------53 - M bits --->|<--------M bits ----->
*
* M - number of node offset bits (35 .. 40)
*
*
* Memory/UV-HUB Processor Socket Address Format:
* +----------------+---------------+---------------------+
* |00..000000000000| PNODE | NodeOffset |
* +----------------+---------------+---------------------+
* <--- N bits --->|<--------M bits ----->
*
* M - number of node offset bits (35 .. 40)
* N - number of PNODE bits (0 .. 10)
*
* Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
* The actual values are configuration dependent and are set at
* boot time. M & N values are set by the hardware/BIOS at boot.
*
*
* APICID format
* NOTE!!!!!! This is the current format of the APICID. However, code
* should assume that this will change in the future. Use functions
* in this file for all APICID bit manipulations and conversion.
*
* 1111110000000000
* 5432109876543210
* pppppppppplc0cch
* sssssssssss
*
* p = pnode bits
* l = socket number on board
* c = core
* h = hyperthread
* s = bits that are in the SOCKET_ID CSR
*
* Note: Processor only supports 12 bits in the APICID register. The ACPI
* tables hold all 16 bits. Software needs to be aware of this.
*
* Unless otherwise specified, all references to APICID refer to
* the FULL value contained in ACPI tables, not the subset in the
* processor APICID register.
*/
/*
* Maximum number of bricks in all partitions and in all coherency domains.
* This is the total number of bricks accessible in the numalink fabric. It
* includes all C & M bricks. Routers are NOT included.
*
* This value is also the value of the maximum number of non-router NASIDs
* in the numalink fabric.
*
* NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
*/
#define UV_MAX_NUMALINK_BLADES 16384
/*
* Maximum number of C/Mbricks within a software SSI (hardware may support
* more).
*/
#define UV_MAX_SSI_BLADES 256
/*
* The largest possible NASID of a C or M brick (+ 2)
*/
#define UV_MAX_NASID_VALUE (UV_MAX_NUMALINK_NODES * 2)
struct uv_scir_s {
struct timer_list timer;
unsigned long offset;
unsigned long last;
unsigned long idle_on;
unsigned long idle_off;
unsigned char state;
unsigned char enabled;
};
/*
* The following defines attributes of the HUB chip. These attributes are
* frequently referenced and are kept in the per-cpu data areas of each cpu.
* They are kept together in a struct to minimize cache misses.
*/
struct uv_hub_info_s {
unsigned long global_mmr_base;
unsigned long gpa_mask;
unsigned int gnode_extra;
unsigned long gnode_upper;
unsigned long lowmem_remap_top;
unsigned long lowmem_remap_base;
unsigned short pnode;
unsigned short pnode_mask;
unsigned short coherency_domain_number;
unsigned short numa_blade_id;
unsigned char blade_processor_id;
unsigned char m_val;
unsigned char n_val;
struct uv_scir_s scir;
};
DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
#define uv_hub_info (&__get_cpu_var(__uv_hub_info))
#define uv_cpu_hub_info(cpu) (&per_cpu(__uv_hub_info, cpu))
/*
* Local & Global MMR space macros.
* Note: macros are intended to be used ONLY by inline functions
* in this file - not by other kernel code.
* n - NASID (full 15-bit global nasid)
* g - GNODE (full 15-bit global nasid, right shifted 1)
* p - PNODE (local part of nsids, right shifted 1)
*/
#define UV_NASID_TO_PNODE(n) (((n) >> 1) & uv_hub_info->pnode_mask)
#define UV_PNODE_TO_GNODE(p) ((p) |uv_hub_info->gnode_extra)
#define UV_PNODE_TO_NASID(p) (UV_PNODE_TO_GNODE(p) << 1)
#define UV_LOCAL_MMR_BASE 0xf4000000UL
#define UV_GLOBAL_MMR32_BASE 0xf8000000UL
#define UV_GLOBAL_MMR64_BASE (uv_hub_info->global_mmr_base)
#define UV_LOCAL_MMR_SIZE (64UL * 1024 * 1024)
#define UV_GLOBAL_MMR32_SIZE (64UL * 1024 * 1024)
#define UV_GLOBAL_MMR32_PNODE_SHIFT 15
#define UV_GLOBAL_MMR64_PNODE_SHIFT 26
#define UV_GLOBAL_MMR32_PNODE_BITS(p) ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
#define UV_GLOBAL_MMR64_PNODE_BITS(p) \
((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
#define UV_APIC_PNODE_SHIFT 6
/* Local Bus from cpu's perspective */
#define LOCAL_BUS_BASE 0x1c00000
#define LOCAL_BUS_SIZE (4 * 1024 * 1024)
/*
* System Controller Interface Reg
*
* Note there are NO leds on a UV system. This register is only
* used by the system controller to monitor system-wide operation.
* There are 64 regs per node. With Nahelem cpus (2 cores per node,
* 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
* a node.
*
* The window is located at top of ACPI MMR space
*/
#define SCIR_WINDOW_COUNT 64
#define SCIR_LOCAL_MMR_BASE (LOCAL_BUS_BASE + \
LOCAL_BUS_SIZE - \
SCIR_WINDOW_COUNT)
#define SCIR_CPU_HEARTBEAT 0x01 /* timer interrupt */
#define SCIR_CPU_ACTIVITY 0x02 /* not idle */
#define SCIR_CPU_HB_INTERVAL (HZ) /* once per second */
/* Loop through all installed blades */
#define for_each_possible_blade(bid) \
for ((bid) = 0; (bid) < uv_num_possible_blades(); (bid)++)
/*
* Macros for converting between kernel virtual addresses, socket local physical
* addresses, and UV global physical addresses.
* Note: use the standard __pa() & __va() macros for converting
* between socket virtual and socket physical addresses.
*/
/* socket phys RAM --> UV global physical address */
static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
{
if (paddr < uv_hub_info->lowmem_remap_top)
paddr |= uv_hub_info->lowmem_remap_base;
return paddr | uv_hub_info->gnode_upper;
}
/* socket virtual --> UV global physical address */
static inline unsigned long uv_gpa(void *v)
{
return uv_soc_phys_ram_to_gpa(__pa(v));
}
/* pnode, offset --> socket virtual */
static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
{
return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
}
/*
* Extract a PNODE from an APICID (full apicid, not processor subset)
*/
static inline int uv_apicid_to_pnode(int apicid)
{
return (apicid >> UV_APIC_PNODE_SHIFT);
}
/*
* Access global MMRs using the low memory MMR32 space. This region supports
* faster MMR access but not all MMRs are accessible in this space.
*/
static inline unsigned long *uv_global_mmr32_address(int pnode,
unsigned long offset)
{
return __va(UV_GLOBAL_MMR32_BASE |
UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
}
static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
unsigned long val)
{
*uv_global_mmr32_address(pnode, offset) = val;
}
static inline unsigned long uv_read_global_mmr32(int pnode,
unsigned long offset)
{
return *uv_global_mmr32_address(pnode, offset);
}
/*
* Access Global MMR space using the MMR space located at the top of physical
* memory.
*/
static inline unsigned long *uv_global_mmr64_address(int pnode,
unsigned long offset)
{
return __va(UV_GLOBAL_MMR64_BASE |
UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
}
static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
unsigned long val)
{
*uv_global_mmr64_address(pnode, offset) = val;
}
static inline unsigned long uv_read_global_mmr64(int pnode,
unsigned long offset)
{
return *uv_global_mmr64_address(pnode, offset);
}
/*
* Access hub local MMRs. Faster than using global space but only local MMRs
* are accessible.
*/
static inline unsigned long *uv_local_mmr_address(unsigned long offset)
{
return __va(UV_LOCAL_MMR_BASE | offset);
}
static inline unsigned long uv_read_local_mmr(unsigned long offset)
{
return *uv_local_mmr_address(offset);
}
static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
{
*uv_local_mmr_address(offset) = val;
}
static inline unsigned char uv_read_local_mmr8(unsigned long offset)
{
return *((unsigned char *)uv_local_mmr_address(offset));
}
static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
{
*((unsigned char *)uv_local_mmr_address(offset)) = val;
}
/*
* Structures and definitions for converting between cpu, node, pnode, and blade
* numbers.
*/
struct uv_blade_info {
unsigned short nr_possible_cpus;
unsigned short nr_online_cpus;
unsigned short pnode;
};
extern struct uv_blade_info *uv_blade_info;
extern short *uv_node_to_blade;
extern short *uv_cpu_to_blade;
extern short uv_possible_blades;
/* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */
static inline int uv_blade_processor_id(void)
{
return uv_hub_info->blade_processor_id;
}
/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
static inline int uv_numa_blade_id(void)
{
return uv_hub_info->numa_blade_id;
}
/* Convert a cpu number to the the UV blade number */
static inline int uv_cpu_to_blade_id(int cpu)
{
return uv_cpu_to_blade[cpu];
}
/* Convert linux node number to the UV blade number */
static inline int uv_node_to_blade_id(int nid)
{
return uv_node_to_blade[nid];
}
/* Convert a blade id to the PNODE of the blade */
static inline int uv_blade_to_pnode(int bid)
{
return uv_blade_info[bid].pnode;
}
/* Determine the number of possible cpus on a blade */
static inline int uv_blade_nr_possible_cpus(int bid)
{
return uv_blade_info[bid].nr_possible_cpus;
}
/* Determine the number of online cpus on a blade */
static inline int uv_blade_nr_online_cpus(int bid)
{
return uv_blade_info[bid].nr_online_cpus;
}
/* Convert a cpu id to the PNODE of the blade containing the cpu */
static inline int uv_cpu_to_pnode(int cpu)
{
return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
}
/* Convert a linux node number to the PNODE of the blade */
static inline int uv_node_to_pnode(int nid)
{
return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
}
/* Maximum possible number of blades */
static inline int uv_num_possible_blades(void)
{
return uv_possible_blades;
}
/* Update SCIR state */
static inline void uv_set_scir_bits(unsigned char value)
{
if (uv_hub_info->scir.state != value) {
uv_hub_info->scir.state = value;
uv_write_local_mmr8(uv_hub_info->scir.offset, value);
}
}
static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
{
if (uv_cpu_hub_info(cpu)->scir.state != value) {
uv_cpu_hub_info(cpu)->scir.state = value;
uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
}
}
static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
{
unsigned long val;
val = (1UL << UVH_IPI_INT_SEND_SHFT) |
((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) |
(vector << UVH_IPI_INT_VECTOR_SHFT);
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
}
#endif /* CONFIG_X86_64 */
#endif /* _ASM_X86_UV_UV_HUB_H */