OpenCloudOS-Kernel/arch/arm/kernel/setup.c

1337 lines
32 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/kernel/setup.c
*
* Copyright (C) 1995-2001 Russell King
*/
#include <linux/efi.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/utsname.h>
#include <linux/initrd.h>
#include <linux/console.h>
#include <linux/seq_file.h>
#include <linux/screen_info.h>
ARM: default machine descriptor for multiplatform Since we now have default implementations for init_time and init_irq, the init_machine callback is the only one that is not yet optional, but since simple DT based platforms all have the same of_platform_populate function call in there, we can consolidate them as well, and then actually boot with a completely empty machine_desc. Unofortunately we cannot just default to an empty init_machine: We cannot call of_platform_populate before init_machine because that does not work in case of auxdata, and we cannot call it after init_machine either because the machine might need to run code after adding the devices. To take the final step, this adds support for booting without defining any machine_desc whatsoever. For the case that CONFIG_MULTIPLATFORM is enabled, it adds a global machine descriptor that never matches any machine but is used as a fallback if nothing else matches. We assume that without CONFIG_MULTIPLATFORM, we only want to boot on the systems that the kernel is built for, so we still retain the build-time warning for missing machine descriptors and the run-time warning when the platform does not match in that case. In the case that we run on a multiplatform kernel and the machine provides a fully populated device tree, we attempt to keep booting, hoping that no machine specific callbacks are necessary. Finally, this also removes the misguided "select ARCH_VEXPRESS" that was only added to avoid a build error for allnoconfig kernels. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nicolas Pitre <nico@linaro.org> Acked-by: Olof Johansson <olof@lixom.net> Cc: "Russell King - ARM Linux" <linux@arm.linux.org.uk> Cc: Rob Herring <robherring2@gmail.com>
2013-02-01 01:51:18 +08:00
#include <linux/of_platform.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/libfdt.h>
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
#include <linux/of_fdt.h>
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/proc_fs.h>
#include <linux/memblock.h>
#include <linux/bug.h>
#include <linux/compiler.h>
#include <linux/sort.h>
#include <linux/psci.h>
#include <asm/unified.h>
#include <asm/cp15.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/efi.h>
#include <asm/elf.h>
#include <asm/early_ioremap.h>
#include <asm/fixmap.h>
#include <asm/procinfo.h>
#include <asm/psci.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
#include <asm/mach-types.h>
#include <asm/cacheflush.h>
#include <asm/cachetype.h>
#include <asm/tlbflush.h>
#include <asm/xen/hypervisor.h>
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
#include <asm/prom.h>
#include <asm/mach/arch.h>
#include <asm/mach/irq.h>
#include <asm/mach/time.h>
#include <asm/system_info.h>
#include <asm/system_misc.h>
#include <asm/traps.h>
#include <asm/unwind.h>
#include <asm/memblock.h>
#include <asm/virt.h>
#include "atags.h"
#if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
char fpe_type[8];
static int __init fpe_setup(char *line)
{
memcpy(fpe_type, line, 8);
return 1;
}
__setup("fpe=", fpe_setup);
#endif
extern void init_default_cache_policy(unsigned long);
extern void paging_init(const struct machine_desc *desc);
ARM: 8667/3: Fix memory attribute inconsistencies when using fixmap To cope with the variety in ARM architectures and configurations, the pagetable attributes for kernel memory are generated at runtime to match the system the kernel finds itself on. This calculated value is stored in pgprot_kernel. However, when early fixmap support was added for ARM (commit a5f4c561b3b1) the attributes used for mappings were hard coded because pgprot_kernel is not set up early enough. Unfortunately, when fixmap is used after early boot this means the memory being mapped can have different attributes to existing mappings, potentially leading to unpredictable behaviour. A specific problem also exists due to the hard coded values not include the 'shareable' attribute which means on systems where this matters (e.g. those with multiple CPU clusters) the cache contents for a memory location can become inconsistent between CPUs. To resolve these issues we change fixmap to use the same memory attributes (from pgprot_kernel) that the rest of the kernel uses. To enable this we need to refactor the initialisation code so build_mem_type_table() is called early enough. Note, that relies on early param parsing for memory type overrides passed via the kernel command line, so we need to make sure this call is still after parse_early_params(). [ardb: keep early_fixmap_init() before param parsing, for earlycon] Fixes: a5f4c561b3b1 ("ARM: 8415/1: early fixmap support for earlycon") Cc: <stable@vger.kernel.org> # v4.3+ Tested-by: afzal mohammed <afzal.mohd.ma@gmail.com> Signed-off-by: Jon Medhurst <tixy@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
2017-04-10 18:13:59 +08:00
extern void early_mm_init(const struct machine_desc *);
extern void adjust_lowmem_bounds(void);
extern enum reboot_mode reboot_mode;
extern void setup_dma_zone(const struct machine_desc *desc);
unsigned int processor_id;
EXPORT_SYMBOL(processor_id);
unsigned int __machine_arch_type __read_mostly;
EXPORT_SYMBOL(__machine_arch_type);
unsigned int cacheid __read_mostly;
EXPORT_SYMBOL(cacheid);
unsigned int __atags_pointer __initdata;
unsigned int system_rev;
EXPORT_SYMBOL(system_rev);
const char *system_serial;
EXPORT_SYMBOL(system_serial);
unsigned int system_serial_low;
EXPORT_SYMBOL(system_serial_low);
unsigned int system_serial_high;
EXPORT_SYMBOL(system_serial_high);
unsigned int elf_hwcap __read_mostly;
EXPORT_SYMBOL(elf_hwcap);
unsigned int elf_hwcap2 __read_mostly;
EXPORT_SYMBOL(elf_hwcap2);
#ifdef MULTI_CPU
struct processor processor __ro_after_init;
#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
struct processor *cpu_vtable[NR_CPUS] = {
[0] = &processor,
};
#endif
#endif
#ifdef MULTI_TLB
struct cpu_tlb_fns cpu_tlb __ro_after_init;
#endif
#ifdef MULTI_USER
struct cpu_user_fns cpu_user __ro_after_init;
#endif
#ifdef MULTI_CACHE
struct cpu_cache_fns cpu_cache __ro_after_init;
#endif
#ifdef CONFIG_OUTER_CACHE
struct outer_cache_fns outer_cache __ro_after_init;
EXPORT_SYMBOL(outer_cache);
#endif
/*
* Cached cpu_architecture() result for use by assembler code.
* C code should use the cpu_architecture() function instead of accessing this
* variable directly.
*/
int __cpu_architecture __read_mostly = CPU_ARCH_UNKNOWN;
struct stack {
u32 irq[3];
u32 abt[3];
u32 und[3];
u32 fiq[3];
} ____cacheline_aligned;
#ifndef CONFIG_CPU_V7M
static struct stack stacks[NR_CPUS];
#endif
char elf_platform[ELF_PLATFORM_SIZE];
EXPORT_SYMBOL(elf_platform);
static const char *cpu_name;
static const char *machine_name;
static char __initdata cmd_line[COMMAND_LINE_SIZE];
const struct machine_desc *machine_desc __initdata;
static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
#define ENDIANNESS ((char)endian_test.l)
DEFINE_PER_CPU(struct cpuinfo_arm, cpu_data);
/*
* Standard memory resources
*/
static struct resource mem_res[] = {
{
.name = "Video RAM",
.start = 0,
.end = 0,
.flags = IORESOURCE_MEM
},
{
.name = "Kernel code",
.start = 0,
.end = 0,
.flags = IORESOURCE_SYSTEM_RAM
},
{
.name = "Kernel data",
.start = 0,
.end = 0,
.flags = IORESOURCE_SYSTEM_RAM
}
};
#define video_ram mem_res[0]
#define kernel_code mem_res[1]
#define kernel_data mem_res[2]
static struct resource io_res[] = {
{
.name = "reserved",
.start = 0x3bc,
.end = 0x3be,
.flags = IORESOURCE_IO | IORESOURCE_BUSY
},
{
.name = "reserved",
.start = 0x378,
.end = 0x37f,
.flags = IORESOURCE_IO | IORESOURCE_BUSY
},
{
.name = "reserved",
.start = 0x278,
.end = 0x27f,
.flags = IORESOURCE_IO | IORESOURCE_BUSY
}
};
#define lp0 io_res[0]
#define lp1 io_res[1]
#define lp2 io_res[2]
static const char *proc_arch[] = {
"undefined/unknown",
"3",
"4",
"4T",
"5",
"5T",
"5TE",
"5TEJ",
"6TEJ",
"7",
"7M",
"?(12)",
"?(13)",
"?(14)",
"?(15)",
"?(16)",
"?(17)",
};
#ifdef CONFIG_CPU_V7M
static int __get_cpu_architecture(void)
{
return CPU_ARCH_ARMv7M;
}
#else
static int __get_cpu_architecture(void)
{
int cpu_arch;
if ((read_cpuid_id() & 0x0008f000) == 0) {
cpu_arch = CPU_ARCH_UNKNOWN;
} else if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
cpu_arch = (read_cpuid_id() & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3;
} else if ((read_cpuid_id() & 0x00080000) == 0x00000000) {
cpu_arch = (read_cpuid_id() >> 16) & 7;
if (cpu_arch)
cpu_arch += CPU_ARCH_ARMv3;
} else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) {
/* Revised CPUID format. Read the Memory Model Feature
* Register 0 and check for VMSAv7 or PMSAv7 */
unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0);
if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
(mmfr0 & 0x000000f0) >= 0x00000030)
cpu_arch = CPU_ARCH_ARMv7;
else if ((mmfr0 & 0x0000000f) == 0x00000002 ||
(mmfr0 & 0x000000f0) == 0x00000020)
cpu_arch = CPU_ARCH_ARMv6;
else
cpu_arch = CPU_ARCH_UNKNOWN;
} else
cpu_arch = CPU_ARCH_UNKNOWN;
return cpu_arch;
}
#endif
int __pure cpu_architecture(void)
{
BUG_ON(__cpu_architecture == CPU_ARCH_UNKNOWN);
return __cpu_architecture;
}
static int cpu_has_aliasing_icache(unsigned int arch)
{
int aliasing_icache;
unsigned int id_reg, num_sets, line_size;
/* PIPT caches never alias. */
if (icache_is_pipt())
return 0;
/* arch specifies the register format */
switch (arch) {
case CPU_ARCH_ARMv7:
set_csselr(CSSELR_ICACHE | CSSELR_L1);
isb();
id_reg = read_ccsidr();
line_size = 4 << ((id_reg & 0x7) + 2);
num_sets = ((id_reg >> 13) & 0x7fff) + 1;
aliasing_icache = (line_size * num_sets) > PAGE_SIZE;
break;
case CPU_ARCH_ARMv6:
aliasing_icache = read_cpuid_cachetype() & (1 << 11);
break;
default:
/* I-cache aliases will be handled by D-cache aliasing code */
aliasing_icache = 0;
}
return aliasing_icache;
}
static void __init cacheid_init(void)
{
unsigned int arch = cpu_architecture();
if (arch >= CPU_ARCH_ARMv6) {
unsigned int cachetype = read_cpuid_cachetype();
if ((arch == CPU_ARCH_ARMv7M) && !(cachetype & 0xf000f)) {
cacheid = 0;
} else if ((cachetype & (7 << 29)) == 4 << 29) {
/* ARMv7 register format */
arch = CPU_ARCH_ARMv7;
cacheid = CACHEID_VIPT_NONALIASING;
switch (cachetype & (3 << 14)) {
case (1 << 14):
cacheid |= CACHEID_ASID_TAGGED;
break;
case (3 << 14):
cacheid |= CACHEID_PIPT;
break;
}
} else {
arch = CPU_ARCH_ARMv6;
if (cachetype & (1 << 23))
cacheid = CACHEID_VIPT_ALIASING;
else
cacheid = CACHEID_VIPT_NONALIASING;
}
if (cpu_has_aliasing_icache(arch))
cacheid |= CACHEID_VIPT_I_ALIASING;
} else {
cacheid = CACHEID_VIVT;
}
pr_info("CPU: %s data cache, %s instruction cache\n",
cache_is_vivt() ? "VIVT" :
cache_is_vipt_aliasing() ? "VIPT aliasing" :
cache_is_vipt_nonaliasing() ? "PIPT / VIPT nonaliasing" : "unknown",
cache_is_vivt() ? "VIVT" :
icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" :
icache_is_vipt_aliasing() ? "VIPT aliasing" :
icache_is_pipt() ? "PIPT" :
cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown");
}
/*
* These functions re-use the assembly code in head.S, which
* already provide the required functionality.
*/
extern struct proc_info_list *lookup_processor_type(unsigned int);
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
void __init early_print(const char *str, ...)
{
extern void printascii(const char *);
char buf[256];
va_list ap;
va_start(ap, str);
vsnprintf(buf, sizeof(buf), str, ap);
va_end(ap);
#ifdef CONFIG_DEBUG_LL
printascii(buf);
#endif
printk("%s", buf);
}
#ifdef CONFIG_ARM_PATCH_IDIV
static inline u32 __attribute_const__ sdiv_instruction(void)
{
if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
/* "sdiv r0, r0, r1" */
u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1);
return __opcode_to_mem_thumb32(insn);
}
/* "sdiv r0, r0, r1" */
return __opcode_to_mem_arm(0xe710f110);
}
static inline u32 __attribute_const__ udiv_instruction(void)
{
if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
/* "udiv r0, r0, r1" */
u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1);
return __opcode_to_mem_thumb32(insn);
}
/* "udiv r0, r0, r1" */
return __opcode_to_mem_arm(0xe730f110);
}
static inline u32 __attribute_const__ bx_lr_instruction(void)
{
if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
/* "bx lr; nop" */
u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0);
return __opcode_to_mem_thumb32(insn);
}
/* "bx lr" */
return __opcode_to_mem_arm(0xe12fff1e);
}
static void __init patch_aeabi_idiv(void)
{
extern void __aeabi_uidiv(void);
extern void __aeabi_idiv(void);
uintptr_t fn_addr;
unsigned int mask;
mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA;
if (!(elf_hwcap & mask))
return;
pr_info("CPU: div instructions available: patching division code\n");
fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1;
asm ("" : "+g" (fn_addr));
((u32 *)fn_addr)[0] = udiv_instruction();
((u32 *)fn_addr)[1] = bx_lr_instruction();
flush_icache_range(fn_addr, fn_addr + 8);
fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1;
asm ("" : "+g" (fn_addr));
((u32 *)fn_addr)[0] = sdiv_instruction();
((u32 *)fn_addr)[1] = bx_lr_instruction();
flush_icache_range(fn_addr, fn_addr + 8);
}
#else
static inline void patch_aeabi_idiv(void) { }
#endif
static void __init cpuid_init_hwcaps(void)
{
int block;
u32 isar5;
if (cpu_architecture() < CPU_ARCH_ARMv7)
return;
block = cpuid_feature_extract(CPUID_EXT_ISAR0, 24);
if (block >= 2)
elf_hwcap |= HWCAP_IDIVA;
if (block >= 1)
elf_hwcap |= HWCAP_IDIVT;
/* LPAE implies atomic ldrd/strd instructions */
block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
if (block >= 5)
elf_hwcap |= HWCAP_LPAE;
/* check for supported v8 Crypto instructions */
isar5 = read_cpuid_ext(CPUID_EXT_ISAR5);
block = cpuid_feature_extract_field(isar5, 4);
if (block >= 2)
elf_hwcap2 |= HWCAP2_PMULL;
if (block >= 1)
elf_hwcap2 |= HWCAP2_AES;
block = cpuid_feature_extract_field(isar5, 8);
if (block >= 1)
elf_hwcap2 |= HWCAP2_SHA1;
block = cpuid_feature_extract_field(isar5, 12);
if (block >= 1)
elf_hwcap2 |= HWCAP2_SHA2;
block = cpuid_feature_extract_field(isar5, 16);
if (block >= 1)
elf_hwcap2 |= HWCAP2_CRC32;
}
static void __init elf_hwcap_fixup(void)
{
unsigned id = read_cpuid_id();
/*
* HWCAP_TLS is available only on 1136 r1p0 and later,
* see also kuser_get_tls_init.
*/
if (read_cpuid_part() == ARM_CPU_PART_ARM1136 &&
((id >> 20) & 3) == 0) {
elf_hwcap &= ~HWCAP_TLS;
return;
}
/* Verify if CPUID scheme is implemented */
if ((id & 0x000f0000) != 0x000f0000)
return;
/*
* If the CPU supports LDREX/STREX and LDREXB/STREXB,
* avoid advertising SWP; it may not be atomic with
* multiprocessing cores.
*/
if (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) > 1 ||
(cpuid_feature_extract(CPUID_EXT_ISAR3, 12) == 1 &&
cpuid_feature_extract(CPUID_EXT_ISAR4, 20) >= 3))
elf_hwcap &= ~HWCAP_SWP;
}
/*
* cpu_init - initialise one CPU.
*
* cpu_init sets up the per-CPU stacks.
*/
void notrace cpu_init(void)
{
#ifndef CONFIG_CPU_V7M
unsigned int cpu = smp_processor_id();
struct stack *stk = &stacks[cpu];
if (cpu >= NR_CPUS) {
pr_crit("CPU%u: bad primary CPU number\n", cpu);
BUG();
}
/*
* This only works on resume and secondary cores. For booting on the
* boot cpu, smp_prepare_boot_cpu is called after percpu area setup.
*/
set_my_cpu_offset(per_cpu_offset(cpu));
cpu_proc_init();
/*
* Define the placement constraint for the inline asm directive below.
* In Thumb-2, msr with an immediate value is not allowed.
*/
#ifdef CONFIG_THUMB2_KERNEL
#define PLC_l "l"
#define PLC_r "r"
#else
#define PLC_l "I"
#define PLC_r "I"
#endif
/*
* setup stacks for re-entrant exception handlers
*/
__asm__ (
"msr cpsr_c, %1\n\t"
"add r14, %0, %2\n\t"
"mov sp, r14\n\t"
"msr cpsr_c, %3\n\t"
"add r14, %0, %4\n\t"
"mov sp, r14\n\t"
"msr cpsr_c, %5\n\t"
"add r14, %0, %6\n\t"
"mov sp, r14\n\t"
"msr cpsr_c, %7\n\t"
"add r14, %0, %8\n\t"
"mov sp, r14\n\t"
"msr cpsr_c, %9"
:
: "r" (stk),
PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
"I" (offsetof(struct stack, irq[0])),
PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
"I" (offsetof(struct stack, abt[0])),
PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE),
"I" (offsetof(struct stack, und[0])),
PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE),
"I" (offsetof(struct stack, fiq[0])),
PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
: "r14");
#endif
}
u32 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID };
void __init smp_setup_processor_id(void)
{
int i;
u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
u32 cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
cpu_logical_map(0) = cpu;
for (i = 1; i < nr_cpu_ids; ++i)
cpu_logical_map(i) = i == cpu ? 0 : i;
/*
* clear __my_cpu_offset on boot CPU to avoid hang caused by
* using percpu variable early, for example, lockdep will
* access percpu variable inside lock_release
*/
set_my_cpu_offset(0);
pr_info("Booting Linux on physical CPU 0x%x\n", mpidr);
}
ARM: kernel: build MPIDR hash function data structure On ARM SMP systems, cores are identified by their MPIDR register. The MPIDR guidelines in the ARM ARM do not provide strict enforcement of MPIDR layout, only recommendations that, if followed, split the MPIDR on ARM 32 bit platforms in three affinity levels. In multi-cluster systems like big.LITTLE, if the affinity guidelines are followed, the MPIDR can not be considered an index anymore. This means that the association between logical CPU in the kernel and the HW CPU identifier becomes somewhat more complicated requiring methods like hashing to associate a given MPIDR to a CPU logical index, in order for the look-up to be carried out in an efficient and scalable way. This patch provides a function in the kernel that starting from the cpu_logical_map, implement collision-free hashing of MPIDR values by checking all significative bits of MPIDR affinity level bitfields. The hashing can then be carried out through bits shifting and ORing; the resulting hash algorithm is a collision-free though not minimal hash that can be executed with few assembly instructions. The mpidr is filtered through a mpidr mask that is built by checking all bits that toggle in the set of MPIDRs corresponding to possible CPUs. Bits that do not toggle do not carry information so they do not contribute to the resulting hash. Pseudo code: /* check all bits that toggle, so they are required */ for (i = 1, mpidr_mask = 0; i < num_possible_cpus(); i++) mpidr_mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); /* * Build shifts to be applied to aff0, aff1, aff2 values to hash the mpidr * fls() returns the last bit set in a word, 0 if none * ffs() returns the first bit set in a word, 0 if none */ fs0 = mpidr_mask[7:0] ? ffs(mpidr_mask[7:0]) - 1 : 0; fs1 = mpidr_mask[15:8] ? ffs(mpidr_mask[15:8]) - 1 : 0; fs2 = mpidr_mask[23:16] ? ffs(mpidr_mask[23:16]) - 1 : 0; ls0 = fls(mpidr_mask[7:0]); ls1 = fls(mpidr_mask[15:8]); ls2 = fls(mpidr_mask[23:16]); bits0 = ls0 - fs0; bits1 = ls1 - fs1; bits2 = ls2 - fs2; aff0_shift = fs0; aff1_shift = 8 + fs1 - bits0; aff2_shift = 16 + fs2 - (bits0 + bits1); u32 hash(u32 mpidr) { u32 l0, l1, l2; u32 mpidr_masked = mpidr & mpidr_mask; l0 = mpidr_masked & 0xff; l1 = mpidr_masked & 0xff00; l2 = mpidr_masked & 0xff0000; return (l0 >> aff0_shift | l1 >> aff1_shift | l2 >> aff2_shift); } The hashing algorithm relies on the inherent properties set in the ARM ARM recommendations for the MPIDR. Exotic configurations, where for instance the MPIDR values at a given affinity level have large holes, can end up requiring big hash tables since the compression of values that can be achieved through shifting is somewhat crippled when holes are present. Kernel warns if the number of buckets of the resulting hash table exceeds the number of possible CPUs by a factor of 4, which is a symptom of a very sparse HW MPIDR configuration. The hash algorithm is quite simple and can easily be implemented in assembly code, to be used in code paths where the kernel virtual address space is not set-up (ie cpu_resume) and instruction and data fetches are strongly ordered so code must be compact and must carry out few data accesses. Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Colin Cross <ccross@android.com> Cc: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@linaro.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Dave Martin <Dave.Martin@arm.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Tested-by: Shawn Guo <shawn.guo@linaro.org> Tested-by: Kevin Hilman <khilman@linaro.org> Tested-by: Stephen Warren <swarren@wwwdotorg.org>
2013-05-16 17:32:09 +08:00
struct mpidr_hash mpidr_hash;
#ifdef CONFIG_SMP
/**
* smp_build_mpidr_hash - Pre-compute shifts required at each affinity
* level in order to build a linear index from an
* MPIDR value. Resulting algorithm is a collision
* free hash carried out through shifting and ORing
*/
static void __init smp_build_mpidr_hash(void)
{
u32 i, affinity;
u32 fs[3], bits[3], ls, mask = 0;
/*
* Pre-scan the list of MPIDRS and filter out bits that do
* not contribute to affinity levels, ie they never toggle.
*/
for_each_possible_cpu(i)
mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
pr_debug("mask of set bits 0x%x\n", mask);
/*
* Find and stash the last and first bit set at all affinity levels to
* check how many bits are required to represent them.
*/
for (i = 0; i < 3; i++) {
affinity = MPIDR_AFFINITY_LEVEL(mask, i);
/*
* Find the MSB bit and LSB bits position
* to determine how many bits are required
* to express the affinity level.
*/
ls = fls(affinity);
fs[i] = affinity ? ffs(affinity) - 1 : 0;
bits[i] = ls - fs[i];
}
/*
* An index can be created from the MPIDR by isolating the
* significant bits at each affinity level and by shifting
* them in order to compress the 24 bits values space to a
* compressed set of values. This is equivalent to hashing
* the MPIDR through shifting and ORing. It is a collision free
* hash though not minimal since some levels might contain a number
* of CPUs that is not an exact power of 2 and their bit
* representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}.
*/
mpidr_hash.shift_aff[0] = fs[0];
mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0];
mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] -
(bits[1] + bits[0]);
mpidr_hash.mask = mask;
mpidr_hash.bits = bits[2] + bits[1] + bits[0];
pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n",
mpidr_hash.shift_aff[0],
mpidr_hash.shift_aff[1],
mpidr_hash.shift_aff[2],
mpidr_hash.mask,
mpidr_hash.bits);
/*
* 4x is an arbitrary value used to warn on a hash table much bigger
* than expected on most systems.
*/
if (mpidr_hash_size() > 4 * num_possible_cpus())
pr_warn("Large number of MPIDR hash buckets detected\n");
sync_cache_w(&mpidr_hash);
}
#endif
/*
* locate processor in the list of supported processor types. The linker
* builds this table for us from the entries in arch/arm/mm/proc-*.S
*/
struct proc_info_list *lookup_processor(u32 midr)
{
struct proc_info_list *list = lookup_processor_type(midr);
if (!list) {
pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n",
smp_processor_id(), midr);
while (1)
/* can't use cpu_relax() here as it may require MMU setup */;
}
return list;
}
static void __init setup_processor(void)
{
unsigned int midr = read_cpuid_id();
struct proc_info_list *list = lookup_processor(midr);
cpu_name = list->cpu_name;
__cpu_architecture = __get_cpu_architecture();
init_proc_vtable(list->proc);
#ifdef MULTI_TLB
cpu_tlb = *list->tlb;
#endif
#ifdef MULTI_USER
cpu_user = *list->user;
#endif
#ifdef MULTI_CACHE
cpu_cache = *list->cache;
#endif
pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
list->cpu_name, midr, midr & 15,
proc_arch[cpu_architecture()], get_cr());
snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
list->arch_name, ENDIANNESS);
snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
list->elf_name, ENDIANNESS);
elf_hwcap = list->elf_hwcap;
cpuid_init_hwcaps();
patch_aeabi_idiv();
#ifndef CONFIG_ARM_THUMB
elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
#endif
#ifdef CONFIG_MMU
init_default_cache_policy(list->__cpu_mm_mmu_flags);
#endif
erratum_a15_798181_init();
elf_hwcap_fixup();
cacheid_init();
cpu_init();
}
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
void __init dump_machine_table(void)
{
const struct machine_desc *p;
early_print("Available machine support:\n\nID (hex)\tNAME\n");
for_each_machine_desc(p)
early_print("%08x\t%s\n", p->nr, p->name);
early_print("\nPlease check your kernel config and/or bootloader.\n");
while (true)
/* can't use cpu_relax() here as it may require MMU setup */;
}
int __init arm_add_memory(u64 start, u64 size)
{
u64 aligned_start;
/*
* Ensure that start/size are aligned to a page boundary.
* Size is rounded down, start is rounded up.
*/
aligned_start = PAGE_ALIGN(start);
if (aligned_start > start + size)
size = 0;
else
size -= aligned_start - start;
#ifndef CONFIG_PHYS_ADDR_T_64BIT
if (aligned_start > ULONG_MAX) {
pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n",
(long long)start);
return -EINVAL;
}
if (aligned_start + size > ULONG_MAX) {
pr_crit("Truncating memory at 0x%08llx to fit in 32-bit physical address space\n",
(long long)start);
/*
* To ensure bank->start + bank->size is representable in
* 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
* This means we lose a page after masking.
*/
size = ULONG_MAX - aligned_start;
}
#endif
if (aligned_start < PHYS_OFFSET) {
if (aligned_start + size <= PHYS_OFFSET) {
pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
aligned_start, aligned_start + size);
return -EINVAL;
}
pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
aligned_start, (u64)PHYS_OFFSET);
size -= PHYS_OFFSET - aligned_start;
aligned_start = PHYS_OFFSET;
}
start = aligned_start;
size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
/*
* Check whether this memory region has non-zero size or
* invalid node number.
*/
if (size == 0)
return -EINVAL;
memblock_add(start, size);
return 0;
}
/*
* Pick out the memory size. We look for mem=size@start,
* where start and size are "size[KkMm]"
*/
static int __init early_mem(char *p)
{
static int usermem __initdata = 0;
u64 size;
u64 start;
char *endp;
/*
* If the user specifies memory size, we
* blow away any automatically generated
* size.
*/
if (usermem == 0) {
usermem = 1;
memblock_remove(memblock_start_of_DRAM(),
memblock_end_of_DRAM() - memblock_start_of_DRAM());
}
start = PHYS_OFFSET;
size = memparse(p, &endp);
if (*endp == '@')
start = memparse(endp + 1, NULL);
arm_add_memory(start, size);
return 0;
}
early_param("mem", early_mem);
static void __init request_standard_resources(const struct machine_desc *mdesc)
{
struct memblock_region *region;
struct resource *res;
kernel_code.start = virt_to_phys(_text);
kernel_code.end = virt_to_phys(__init_begin - 1);
kernel_data.start = virt_to_phys(_sdata);
kernel_data.end = virt_to_phys(_end - 1);
for_each_memblock(memory, region) {
phys_addr_t start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
phys_addr_t end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
unsigned long boot_alias_start;
/*
* Some systems have a special memory alias which is only
* used for booting. We need to advertise this region to
* kexec-tools so they know where bootable RAM is located.
*/
boot_alias_start = phys_to_idmap(start);
if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) {
memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Suggested-by: Michal Hocko <mhocko@suse.com> Acked-by: Paul Burton <paul.burton@mips.com> [MIPS] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:57 +08:00
res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
treewide: add checks for the return value of memblock_alloc*() Add check for the return value of memblock_alloc*() functions and call panic() in case of error. The panic message repeats the one used by panicing memblock allocators with adjustment of parameters to include only relevant ones. The replacement was mostly automated with semantic patches like the one below with manual massaging of format strings. @@ expression ptr, size, align; @@ ptr = memblock_alloc(size, align); + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, size, align); [anders.roxell@linaro.org: use '%pa' with 'phys_addr_t' type] Link: http://lkml.kernel.org/r/20190131161046.21886-1-anders.roxell@linaro.org [rppt@linux.ibm.com: fix format strings for panics after memblock_alloc] Link: http://lkml.kernel.org/r/1548950940-15145-1-git-send-email-rppt@linux.ibm.com [rppt@linux.ibm.com: don't panic if the allocation in sparse_buffer_init fails] Link: http://lkml.kernel.org/r/20190131074018.GD28876@rapoport-lnx [akpm@linux-foundation.org: fix xtensa printk warning] Link: http://lkml.kernel.org/r/1548057848-15136-20-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Anders Roxell <anders.roxell@linaro.org> Reviewed-by: Guo Ren <ren_guo@c-sky.com> [c-sky] Acked-by: Paul Burton <paul.burton@mips.com> [MIPS] Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> [s390] Reviewed-by: Juergen Gross <jgross@suse.com> [Xen] Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org> [m68k] Acked-by: Max Filippov <jcmvbkbc@gmail.com> [xtensa] Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:31 +08:00
if (!res)
panic("%s: Failed to allocate %zu bytes\n",
__func__, sizeof(*res));
res->name = "System RAM (boot alias)";
res->start = boot_alias_start;
res->end = phys_to_idmap(end);
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
request_resource(&iomem_resource, res);
}
memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Suggested-by: Michal Hocko <mhocko@suse.com> Acked-by: Paul Burton <paul.burton@mips.com> [MIPS] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:57 +08:00
res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
treewide: add checks for the return value of memblock_alloc*() Add check for the return value of memblock_alloc*() functions and call panic() in case of error. The panic message repeats the one used by panicing memblock allocators with adjustment of parameters to include only relevant ones. The replacement was mostly automated with semantic patches like the one below with manual massaging of format strings. @@ expression ptr, size, align; @@ ptr = memblock_alloc(size, align); + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, size, align); [anders.roxell@linaro.org: use '%pa' with 'phys_addr_t' type] Link: http://lkml.kernel.org/r/20190131161046.21886-1-anders.roxell@linaro.org [rppt@linux.ibm.com: fix format strings for panics after memblock_alloc] Link: http://lkml.kernel.org/r/1548950940-15145-1-git-send-email-rppt@linux.ibm.com [rppt@linux.ibm.com: don't panic if the allocation in sparse_buffer_init fails] Link: http://lkml.kernel.org/r/20190131074018.GD28876@rapoport-lnx [akpm@linux-foundation.org: fix xtensa printk warning] Link: http://lkml.kernel.org/r/1548057848-15136-20-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Anders Roxell <anders.roxell@linaro.org> Reviewed-by: Guo Ren <ren_guo@c-sky.com> [c-sky] Acked-by: Paul Burton <paul.burton@mips.com> [MIPS] Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> [s390] Reviewed-by: Juergen Gross <jgross@suse.com> [Xen] Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org> [m68k] Acked-by: Max Filippov <jcmvbkbc@gmail.com> [xtensa] Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:31 +08:00
if (!res)
panic("%s: Failed to allocate %zu bytes\n", __func__,
sizeof(*res));
res->name = "System RAM";
res->start = start;
res->end = end;
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
request_resource(&iomem_resource, res);
if (kernel_code.start >= res->start &&
kernel_code.end <= res->end)
request_resource(res, &kernel_code);
if (kernel_data.start >= res->start &&
kernel_data.end <= res->end)
request_resource(res, &kernel_data);
}
if (mdesc->video_start) {
video_ram.start = mdesc->video_start;
video_ram.end = mdesc->video_end;
request_resource(&iomem_resource, &video_ram);
}
/*
* Some machines don't have the possibility of ever
* possessing lp0, lp1 or lp2
*/
if (mdesc->reserve_lp0)
request_resource(&ioport_resource, &lp0);
if (mdesc->reserve_lp1)
request_resource(&ioport_resource, &lp1);
if (mdesc->reserve_lp2)
request_resource(&ioport_resource, &lp2);
}
#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) || \
defined(CONFIG_EFI)
struct screen_info screen_info = {
.orig_video_lines = 30,
.orig_video_cols = 80,
.orig_video_mode = 0,
.orig_video_ega_bx = 0,
.orig_video_isVGA = 1,
.orig_video_points = 8
};
#endif
static int __init customize_machine(void)
{
ARM: default machine descriptor for multiplatform Since we now have default implementations for init_time and init_irq, the init_machine callback is the only one that is not yet optional, but since simple DT based platforms all have the same of_platform_populate function call in there, we can consolidate them as well, and then actually boot with a completely empty machine_desc. Unofortunately we cannot just default to an empty init_machine: We cannot call of_platform_populate before init_machine because that does not work in case of auxdata, and we cannot call it after init_machine either because the machine might need to run code after adding the devices. To take the final step, this adds support for booting without defining any machine_desc whatsoever. For the case that CONFIG_MULTIPLATFORM is enabled, it adds a global machine descriptor that never matches any machine but is used as a fallback if nothing else matches. We assume that without CONFIG_MULTIPLATFORM, we only want to boot on the systems that the kernel is built for, so we still retain the build-time warning for missing machine descriptors and the run-time warning when the platform does not match in that case. In the case that we run on a multiplatform kernel and the machine provides a fully populated device tree, we attempt to keep booting, hoping that no machine specific callbacks are necessary. Finally, this also removes the misguided "select ARCH_VEXPRESS" that was only added to avoid a build error for allnoconfig kernels. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nicolas Pitre <nico@linaro.org> Acked-by: Olof Johansson <olof@lixom.net> Cc: "Russell King - ARM Linux" <linux@arm.linux.org.uk> Cc: Rob Herring <robherring2@gmail.com>
2013-02-01 01:51:18 +08:00
/*
* customizes platform devices, or adds new ones
* On DT based machines, we fall back to populating the
* machine from the device tree, if no callback is provided,
* otherwise we would always need an init_machine callback.
*/
if (machine_desc->init_machine)
machine_desc->init_machine();
return 0;
}
arch_initcall(customize_machine);
static int __init init_machine_late(void)
{
struct device_node *root;
int ret;
if (machine_desc->init_late)
machine_desc->init_late();
root = of_find_node_by_path("/");
if (root) {
ret = of_property_read_string(root, "serial-number",
&system_serial);
if (ret)
system_serial = NULL;
}
if (!system_serial)
system_serial = kasprintf(GFP_KERNEL, "%08x%08x",
system_serial_high,
system_serial_low);
return 0;
}
late_initcall(init_machine_late);
#ifdef CONFIG_KEXEC
/*
* The crash region must be aligned to 128MB to avoid
* zImage relocating below the reserved region.
*/
#define CRASH_ALIGN (128 << 20)
static inline unsigned long long get_total_mem(void)
{
unsigned long total;
total = max_low_pfn - min_low_pfn;
return total << PAGE_SHIFT;
}
/**
* reserve_crashkernel() - reserves memory are for crash kernel
*
* This function reserves memory area given in "crashkernel=" kernel command
* line parameter. The memory reserved is used by a dump capture kernel when
* primary kernel is crashing.
*/
static void __init reserve_crashkernel(void)
{
unsigned long long crash_size, crash_base;
unsigned long long total_mem;
int ret;
total_mem = get_total_mem();
ret = parse_crashkernel(boot_command_line, total_mem,
&crash_size, &crash_base);
if (ret)
return;
if (crash_base <= 0) {
unsigned long long crash_max = idmap_to_phys((u32)~0);
ARM: kexec: avoid allocating crashkernel region outside lowmem Allocating the crashkernel region outside lowmem causes the kernel to oops while trying to kexec into the new kernel: Loading crashdump kernel... Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = edd70000 [00000000] *pgd=de19e835 Internal error: Oops: 817 [#2] SMP ARM Modules linked in: ... CPU: 0 PID: 689 Comm: sh Not tainted 4.12.0-rc3-next-20170601-04015-gc3a5a20 Hardware name: Generic DRA74X (Flattened Device Tree) task: edb32f00 task.stack: edf18000 PC is at memcpy+0x50/0x330 LR is at 0xe3c34001 pc : [<c04baf30>] lr : [<e3c34001>] psr: 800c0193 sp : edf19c2c ip : 0a000001 fp : c0553170 r10: c055316e r9 : 00000001 r8 : e3130001 r7 : e4903004 r6 : 0a000014 r5 : e3500000 r4 : e59f106c r3 : e59f0074 r2 : ffffffe8 r1 : c010fb88 r0 : 00000000 Flags: Nzcv IRQs off FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: add7006a DAC: 00000051 Process sh (pid: 689, stack limit = 0xedf18218) Stack: (0xedf19c2c to 0xedf1a000) ... [<c04baf30>] (memcpy) from [<c010fae0>] (machine_kexec+0xa8/0x12c) [<c010fae0>] (machine_kexec) from [<c01e4104>] (__crash_kexec+0x5c/0x98) [<c01e4104>] (__crash_kexec) from [<c01e419c>] (crash_kexec+0x5c/0x68) [<c01e419c>] (crash_kexec) from [<c010c5c0>] (die+0x228/0x490) [<c010c5c0>] (die) from [<c011e520>] (__do_kernel_fault.part.0+0x54/0x1e4) [<c011e520>] (__do_kernel_fault.part.0) from [<c082412c>] (do_page_fault+0x1e8/0x400) [<c082412c>] (do_page_fault) from [<c010135c>] (do_DataAbort+0x38/0xb8) [<c010135c>] (do_DataAbort) from [<c0823584>] (__dabt_svc+0x64/0xa0) This is caused by image->control_code_page being a highmem page, so page_address(image->control_code_page) returns NULL. In any case, we don't want the control page to be a highmem page. We already limit the crash kernel region to the top of 32-bit physical memory space. Also limit it to the top of lowmem in physical space. Reported-by: Keerthy <j-keerthy@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
2017-07-20 06:01:38 +08:00
unsigned long long lowmem_max = __pa(high_memory - 1) + 1;
if (crash_max > lowmem_max)
crash_max = lowmem_max;
crash_base = memblock_find_in_range(CRASH_ALIGN, crash_max,
crash_size, CRASH_ALIGN);
if (!crash_base) {
pr_err("crashkernel reservation failed - No suitable area found.\n");
return;
}
} else {
unsigned long long start;
start = memblock_find_in_range(crash_base,
crash_base + crash_size,
crash_size, SECTION_SIZE);
if (start != crash_base) {
pr_err("crashkernel reservation failed - memory is in use.\n");
return;
}
}
ret = memblock_reserve(crash_base, crash_size);
if (ret < 0) {
pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n",
(unsigned long)crash_base);
return;
}
pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
(unsigned long)(crash_size >> 20),
(unsigned long)(crash_base >> 20),
(unsigned long)(total_mem >> 20));
/* The crashk resource must always be located in normal mem */
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
insert_resource(&iomem_resource, &crashk_res);
if (arm_has_idmap_alias()) {
/*
* If we have a special RAM alias for use at boot, we
* need to advertise to kexec tools where the alias is.
*/
static struct resource crashk_boot_res = {
.name = "Crash kernel (boot alias)",
.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
};
crashk_boot_res.start = phys_to_idmap(crash_base);
crashk_boot_res.end = crashk_boot_res.start + crash_size - 1;
insert_resource(&iomem_resource, &crashk_boot_res);
}
}
#else
static inline void reserve_crashkernel(void) {}
#endif /* CONFIG_KEXEC */
void __init hyp_mode_check(void)
{
#ifdef CONFIG_ARM_VIRT_EXT
sync_boot_mode();
if (is_hyp_mode_available()) {
pr_info("CPU: All CPU(s) started in HYP mode.\n");
pr_info("CPU: Virtualization extensions available.\n");
} else if (is_hyp_mode_mismatched()) {
pr_warn("CPU: WARNING: CPU(s) started in wrong/inconsistent modes (primary CPU mode 0x%x)\n",
__boot_cpu_mode & MODE_MASK);
pr_warn("CPU: This may indicate a broken bootloader or firmware.\n");
} else
pr_info("CPU: All CPU(s) started in SVC mode.\n");
#endif
}
void __init setup_arch(char **cmdline_p)
{
const struct machine_desc *mdesc = NULL;
void *atags_vaddr = NULL;
if (__atags_pointer)
atags_vaddr = FDT_VIRT_BASE(__atags_pointer);
setup_processor();
if (atags_vaddr) {
mdesc = setup_machine_fdt(atags_vaddr);
if (mdesc)
memblock_reserve(__atags_pointer,
fdt_totalsize(atags_vaddr));
}
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
if (!mdesc)
mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type);
if (!mdesc) {
early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n");
early_print(" r1=0x%08x, r2=0x%08x\n", __machine_arch_type,
__atags_pointer);
if (__atags_pointer)
early_print(" r2[]=%*ph\n", 16, atags_vaddr);
dump_machine_table();
}
machine_desc = mdesc;
machine_name = mdesc->name;
dump_stack_set_arch_desc("%s", mdesc->name);
if (mdesc->reboot_mode != REBOOT_HARD)
reboot_mode = mdesc->reboot_mode;
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = (unsigned long) _end;
/* populate cmd_line too for later use, preserving boot_command_line */
strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = cmd_line;
early_fixmap_init();
early_ioremap_init();
parse_early_param();
#ifdef CONFIG_MMU
ARM: 8667/3: Fix memory attribute inconsistencies when using fixmap To cope with the variety in ARM architectures and configurations, the pagetable attributes for kernel memory are generated at runtime to match the system the kernel finds itself on. This calculated value is stored in pgprot_kernel. However, when early fixmap support was added for ARM (commit a5f4c561b3b1) the attributes used for mappings were hard coded because pgprot_kernel is not set up early enough. Unfortunately, when fixmap is used after early boot this means the memory being mapped can have different attributes to existing mappings, potentially leading to unpredictable behaviour. A specific problem also exists due to the hard coded values not include the 'shareable' attribute which means on systems where this matters (e.g. those with multiple CPU clusters) the cache contents for a memory location can become inconsistent between CPUs. To resolve these issues we change fixmap to use the same memory attributes (from pgprot_kernel) that the rest of the kernel uses. To enable this we need to refactor the initialisation code so build_mem_type_table() is called early enough. Note, that relies on early param parsing for memory type overrides passed via the kernel command line, so we need to make sure this call is still after parse_early_params(). [ardb: keep early_fixmap_init() before param parsing, for earlycon] Fixes: a5f4c561b3b1 ("ARM: 8415/1: early fixmap support for earlycon") Cc: <stable@vger.kernel.org> # v4.3+ Tested-by: afzal mohammed <afzal.mohd.ma@gmail.com> Signed-off-by: Jon Medhurst <tixy@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
2017-04-10 18:13:59 +08:00
early_mm_init(mdesc);
#endif
setup_dma_zone(mdesc);
xen_early_init();
efi_init();
/*
* Make sure the calculation for lowmem/highmem is set appropriately
* before reserving/allocating any mmeory
*/
adjust_lowmem_bounds();
arm_memblock_init(mdesc);
/* Memory may have been removed so recalculate the bounds. */
adjust_lowmem_bounds();
early_ioremap_reset();
paging_init(mdesc);
request_standard_resources(mdesc);
if (mdesc->restart)
arm_pm_restart = mdesc->restart;
arm/dt: probe for platforms via the device tree If a dtb is passed to the kernel then the kernel needs to iterate through compiled-in mdescs looking for one that matches and move the dtb data to a safe location before it gets accidentally overwritten by the kernel. This patch creates a new function, setup_machine_fdt() which is analogous to the setup_machine_atags() created in the previous patch. It does all the early setup needed to use a device tree machine description. v5: - Print warning with neither dtb nor atags are passed to the kernel - Fix bug in setting of __machine_arch_type to the selected machine, not just the last machine in the list. Reported-by: Tixy <tixy@yxit.co.uk> - Copy command line directly into boot_command_line instead of cmd_line v4: - Dump some output when a matching machine_desc cannot be found v3: - Added processing of reserved list. - Backed out the v2 change that copied instead of reserved the dtb. dtb is reserved again and the real problem was fixed by using alloc_bootmem_align() for early allocation of RAM for unflattening the tree. - Moved cmd_line and initrd changes to earlier patch to make series bisectable. v2: Changed to save the dtb by copying into an allocated buffer. - Since the dtb will very likely be passed in the first 16k of ram where the interrupt vectors live, memblock_reserve() is insufficient to protect the dtb data. [based on work originally written by Jeremy Kerr <jeremy.kerr@canonical.com>] Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-04-29 04:27:21 +08:00
unflatten_device_tree();
arm_dt_init_cpu_maps();
psci_dt_init();
#ifdef CONFIG_SMP
if (is_smp()) {
if (!mdesc->smp_init || !mdesc->smp_init()) {
if (psci_smp_available())
smp_set_ops(&psci_smp_ops);
else if (mdesc->smp)
smp_set_ops(mdesc->smp);
}
smp_init_cpus();
ARM: kernel: build MPIDR hash function data structure On ARM SMP systems, cores are identified by their MPIDR register. The MPIDR guidelines in the ARM ARM do not provide strict enforcement of MPIDR layout, only recommendations that, if followed, split the MPIDR on ARM 32 bit platforms in three affinity levels. In multi-cluster systems like big.LITTLE, if the affinity guidelines are followed, the MPIDR can not be considered an index anymore. This means that the association between logical CPU in the kernel and the HW CPU identifier becomes somewhat more complicated requiring methods like hashing to associate a given MPIDR to a CPU logical index, in order for the look-up to be carried out in an efficient and scalable way. This patch provides a function in the kernel that starting from the cpu_logical_map, implement collision-free hashing of MPIDR values by checking all significative bits of MPIDR affinity level bitfields. The hashing can then be carried out through bits shifting and ORing; the resulting hash algorithm is a collision-free though not minimal hash that can be executed with few assembly instructions. The mpidr is filtered through a mpidr mask that is built by checking all bits that toggle in the set of MPIDRs corresponding to possible CPUs. Bits that do not toggle do not carry information so they do not contribute to the resulting hash. Pseudo code: /* check all bits that toggle, so they are required */ for (i = 1, mpidr_mask = 0; i < num_possible_cpus(); i++) mpidr_mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); /* * Build shifts to be applied to aff0, aff1, aff2 values to hash the mpidr * fls() returns the last bit set in a word, 0 if none * ffs() returns the first bit set in a word, 0 if none */ fs0 = mpidr_mask[7:0] ? ffs(mpidr_mask[7:0]) - 1 : 0; fs1 = mpidr_mask[15:8] ? ffs(mpidr_mask[15:8]) - 1 : 0; fs2 = mpidr_mask[23:16] ? ffs(mpidr_mask[23:16]) - 1 : 0; ls0 = fls(mpidr_mask[7:0]); ls1 = fls(mpidr_mask[15:8]); ls2 = fls(mpidr_mask[23:16]); bits0 = ls0 - fs0; bits1 = ls1 - fs1; bits2 = ls2 - fs2; aff0_shift = fs0; aff1_shift = 8 + fs1 - bits0; aff2_shift = 16 + fs2 - (bits0 + bits1); u32 hash(u32 mpidr) { u32 l0, l1, l2; u32 mpidr_masked = mpidr & mpidr_mask; l0 = mpidr_masked & 0xff; l1 = mpidr_masked & 0xff00; l2 = mpidr_masked & 0xff0000; return (l0 >> aff0_shift | l1 >> aff1_shift | l2 >> aff2_shift); } The hashing algorithm relies on the inherent properties set in the ARM ARM recommendations for the MPIDR. Exotic configurations, where for instance the MPIDR values at a given affinity level have large holes, can end up requiring big hash tables since the compression of values that can be achieved through shifting is somewhat crippled when holes are present. Kernel warns if the number of buckets of the resulting hash table exceeds the number of possible CPUs by a factor of 4, which is a symptom of a very sparse HW MPIDR configuration. The hash algorithm is quite simple and can easily be implemented in assembly code, to be used in code paths where the kernel virtual address space is not set-up (ie cpu_resume) and instruction and data fetches are strongly ordered so code must be compact and must carry out few data accesses. Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Colin Cross <ccross@android.com> Cc: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@linaro.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Dave Martin <Dave.Martin@arm.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Tested-by: Shawn Guo <shawn.guo@linaro.org> Tested-by: Kevin Hilman <khilman@linaro.org> Tested-by: Stephen Warren <swarren@wwwdotorg.org>
2013-05-16 17:32:09 +08:00
smp_build_mpidr_hash();
}
#endif
if (!is_smp())
hyp_mode_check();
reserve_crashkernel();
#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
handle_arch_irq = mdesc->handle_irq;
#endif
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
#endif
if (mdesc->init_early)
mdesc->init_early();
}
static int __init topology_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu);
ARM: 8392/3: smp: Only expose /sys/.../cpuX/online if hotpluggable Writes to /sys/.../cpuX/online fail if we determine the platform doesn't support hotplug for that CPU. Furthermore, if the cpu_die op isn't specified the system hangs when we try to offline a CPU and it comes right back online unexpectedly. Let's figure this stuff out before we make the sysfs nodes so that the online file doesn't even exist if it isn't (at least sometimes) possible to hotplug the CPU. Add a new 'cpu_can_disable' op and repoint all 'cpu_disable' implementations at it because all implementers use the op to indicate if a CPU can be hotplugged or not in a static fashion. With PSCI we may need to add a 'cpu_disable' op so that the secure OS can be migrated off the CPU we're trying to hotplug. In this case, the 'cpu_can_disable' op will indicate that all CPUs are hotpluggable by returning true, but the 'cpu_disable' op will make a PSCI migration call and occasionally fail, denying the hotplug of a CPU. This shouldn't be any worse than x86 where we may indicate that all CPUs are hotpluggable but occasionally we can't offline a CPU due to check_irq_vectors_for_cpu_disable() failing to find a CPU to move vectors to. Cc: Mark Rutland <mark.rutland@arm.com> Cc: Nicolas Pitre <nico@linaro.org> Cc: Dave Martin <Dave.Martin@arm.com> Acked-by: Simon Horman <horms@verge.net.au> [shmobile portion] Tested-by: Simon Horman <horms@verge.net.au> Cc: Magnus Damm <magnus.damm@gmail.com> Cc: <linux-sh@vger.kernel.org> Tested-by: Tyler Baker <tyler.baker@linaro.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-07-29 07:34:48 +08:00
cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu);
register_cpu(&cpuinfo->cpu, cpu);
}
return 0;
}
subsys_initcall(topology_init);
#ifdef CONFIG_HAVE_PROC_CPU
static int __init proc_cpu_init(void)
{
struct proc_dir_entry *res;
res = proc_mkdir("cpu", NULL);
if (!res)
return -ENOMEM;
return 0;
}
fs_initcall(proc_cpu_init);
#endif
static const char *hwcap_str[] = {
"swp",
"half",
"thumb",
"26bit",
"fastmult",
"fpa",
"vfp",
"edsp",
"java",
"iwmmxt",
"crunch",
"thumbee",
"neon",
"vfpv3",
"vfpv3d16",
"tls",
"vfpv4",
"idiva",
"idivt",
"vfpd32",
"lpae",
"evtstrm",
NULL
};
static const char *hwcap2_str[] = {
"aes",
"pmull",
"sha1",
"sha2",
"crc32",
NULL
};
static int c_show(struct seq_file *m, void *v)
{
int i, j;
u32 cpuid;
for_each_online_cpu(i) {
/*
* glibc reads /proc/cpuinfo to determine the number of
* online processors, looking for lines beginning with
* "processor". Give glibc what it expects.
*/
seq_printf(m, "processor\t: %d\n", i);
cpuid = is_smp() ? per_cpu(cpu_data, i).cpuid : read_cpuid_id();
seq_printf(m, "model name\t: %s rev %d (%s)\n",
cpu_name, cpuid & 15, elf_platform);
#if defined(CONFIG_SMP)
seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
(per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
#else
seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
loops_per_jiffy / (500000/HZ),
(loops_per_jiffy / (5000/HZ)) % 100);
#endif
/* dump out the processor features */
seq_puts(m, "Features\t: ");
for (j = 0; hwcap_str[j]; j++)
if (elf_hwcap & (1 << j))
seq_printf(m, "%s ", hwcap_str[j]);
for (j = 0; hwcap2_str[j]; j++)
if (elf_hwcap2 & (1 << j))
seq_printf(m, "%s ", hwcap2_str[j]);
seq_printf(m, "\nCPU implementer\t: 0x%02x\n", cpuid >> 24);
seq_printf(m, "CPU architecture: %s\n",
proc_arch[cpu_architecture()]);
if ((cpuid & 0x0008f000) == 0x00000000) {
/* pre-ARM7 */
seq_printf(m, "CPU part\t: %07x\n", cpuid >> 4);
} else {
if ((cpuid & 0x0008f000) == 0x00007000) {
/* ARM7 */
seq_printf(m, "CPU variant\t: 0x%02x\n",
(cpuid >> 16) & 127);
} else {
/* post-ARM7 */
seq_printf(m, "CPU variant\t: 0x%x\n",
(cpuid >> 20) & 15);
}
seq_printf(m, "CPU part\t: 0x%03x\n",
(cpuid >> 4) & 0xfff);
}
seq_printf(m, "CPU revision\t: %d\n\n", cpuid & 15);
}
seq_printf(m, "Hardware\t: %s\n", machine_name);
seq_printf(m, "Revision\t: %04x\n", system_rev);
seq_printf(m, "Serial\t\t: %s\n", system_serial);
return 0;
}
static void *c_start(struct seq_file *m, loff_t *pos)
{
return *pos < 1 ? (void *)1 : NULL;
}
static void *c_next(struct seq_file *m, void *v, loff_t *pos)
{
++*pos;
return NULL;
}
static void c_stop(struct seq_file *m, void *v)
{
}
const struct seq_operations cpuinfo_op = {
.start = c_start,
.next = c_next,
.stop = c_stop,
.show = c_show
};