1
0
Fork 0
alistair23-linux/arch/powerpc/kernel/setup-common.c

993 lines
24 KiB
C
Raw Normal View History

/*
* Common boot and setup code for both 32-bit and 64-bit.
* Extracted from arch/powerpc/kernel/setup_64.c.
*
* Copyright (C) 2001 PPC64 Team, IBM Corp
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#undef DEBUG
#include <linux/export.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/platform_device.h>
#include <linux/seq_file.h>
#include <linux/ioport.h>
#include <linux/console.h>
#include <linux/screen_info.h>
#include <linux/root_dev.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/unistd.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
#include <linux/percpu.h>
#include <linux/memblock.h>
#include <linux/of_platform.h>
#include <linux/hugetlb.h>
#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/paca.h>
#include <asm/prom.h>
#include <asm/processor.h>
#include <asm/vdso_datapage.h>
#include <asm/pgtable.h>
#include <asm/smp.h>
#include <asm/elf.h>
#include <asm/machdep.h>
#include <asm/time.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/firmware.h>
#include <asm/btext.h>
#include <asm/nvram.h>
#include <asm/setup.h>
#include <asm/rtas.h>
#include <asm/iommu.h>
#include <asm/serial.h>
#include <asm/cache.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/xmon.h>
#include <asm/cputhreads.h>
#include <mm/mmu_decl.h>
#include <asm/fadump.h>
#include <asm/udbg.h>
#include <asm/hugetlb.h>
#include <asm/livepatch.h>
#include <asm/mmu_context.h>
#include <asm/cpu_has_feature.h>
#include "setup.h"
#ifdef DEBUG
#include <asm/udbg.h>
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif
/* The main machine-dep calls structure
*/
struct machdep_calls ppc_md;
EXPORT_SYMBOL(ppc_md);
struct machdep_calls *machine_id;
EXPORT_SYMBOL(machine_id);
int boot_cpuid = -1;
EXPORT_SYMBOL_GPL(boot_cpuid);
/*
* These are used in binfmt_elf.c to put aux entries on the stack
* for each elf executable being started.
*/
int dcache_bsize;
int icache_bsize;
int ucache_bsize;
unsigned long klimit = (unsigned long) _end;
/*
* This still seems to be needed... -- paulus
*/
struct screen_info screen_info = {
.orig_x = 0,
.orig_y = 25,
.orig_video_cols = 80,
.orig_video_lines = 25,
.orig_video_isVGA = 1,
.orig_video_points = 16
};
#if defined(CONFIG_FB_VGA16_MODULE)
EXPORT_SYMBOL(screen_info);
#endif
/* Variables required to store legacy IO irq routing */
int of_i8042_kbd_irq;
EXPORT_SYMBOL_GPL(of_i8042_kbd_irq);
int of_i8042_aux_irq;
EXPORT_SYMBOL_GPL(of_i8042_aux_irq);
#ifdef __DO_IRQ_CANON
/* XXX should go elsewhere eventually */
int ppc_do_canonicalize_irqs;
EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
#endif
#ifdef CONFIG_CRASH_CORE
/* This keeps a track of which one is the crashing cpu. */
int crashing_cpu = -1;
#endif
/* also used by kexec */
void machine_shutdown(void)
{
#ifdef CONFIG_FA_DUMP
/*
* if fadump is active, cleanup the fadump registration before we
* shutdown.
*/
fadump_cleanup();
#endif
if (ppc_md.machine_shutdown)
ppc_md.machine_shutdown();
}
static void machine_hang(void)
{
pr_emerg("System Halted, OK to turn off power\n");
local_irq_disable();
while (1)
;
}
void machine_restart(char *cmd)
{
machine_shutdown();
if (ppc_md.restart)
ppc_md.restart(cmd);
smp_send_stop();
do_kernel_restart(cmd);
mdelay(1000);
machine_hang();
}
void machine_power_off(void)
{
machine_shutdown();
if (pm_power_off)
pm_power_off();
smp_send_stop();
machine_hang();
}
/* Used by the G5 thermal driver */
EXPORT_SYMBOL_GPL(machine_power_off);
void (*pm_power_off)(void);
EXPORT_SYMBOL_GPL(pm_power_off);
void machine_halt(void)
{
machine_shutdown();
if (ppc_md.halt)
ppc_md.halt();
smp_send_stop();
machine_hang();
}
#ifdef CONFIG_SMP
DEFINE_PER_CPU(unsigned int, cpu_pvr);
#endif
static void show_cpuinfo_summary(struct seq_file *m)
{
struct device_node *root;
const char *model = NULL;
#if defined(CONFIG_SMP) && defined(CONFIG_PPC32)
unsigned long bogosum = 0;
int i;
for_each_online_cpu(i)
bogosum += loops_per_jiffy;
seq_printf(m, "total bogomips\t: %lu.%02lu\n",
bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
#endif /* CONFIG_SMP && CONFIG_PPC32 */
seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
if (ppc_md.name)
seq_printf(m, "platform\t: %s\n", ppc_md.name);
root = of_find_node_by_path("/");
if (root)
model = of_get_property(root, "model", NULL);
if (model)
seq_printf(m, "model\t\t: %s\n", model);
of_node_put(root);
if (ppc_md.show_cpuinfo != NULL)
ppc_md.show_cpuinfo(m);
#ifdef CONFIG_PPC32
/* Display the amount of memory */
seq_printf(m, "Memory\t\t: %d MB\n",
(unsigned int)(total_memory / (1024 * 1024)));
#endif
}
static int show_cpuinfo(struct seq_file *m, void *v)
{
unsigned long cpu_id = (unsigned long)v - 1;
unsigned int pvr;
unsigned long proc_freq;
unsigned short maj;
unsigned short min;
#ifdef CONFIG_SMP
pvr = per_cpu(cpu_pvr, cpu_id);
#else
pvr = mfspr(SPRN_PVR);
#endif
maj = (pvr >> 8) & 0xFF;
min = pvr & 0xFF;
seq_printf(m, "processor\t: %lu\n", cpu_id);
seq_printf(m, "cpu\t\t: ");
if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name)
seq_printf(m, "%s", cur_cpu_spec->cpu_name);
else
seq_printf(m, "unknown (%08x)", pvr);
#ifdef CONFIG_ALTIVEC
if (cpu_has_feature(CPU_FTR_ALTIVEC))
seq_printf(m, ", altivec supported");
#endif /* CONFIG_ALTIVEC */
seq_printf(m, "\n");
#ifdef CONFIG_TAU
if (cur_cpu_spec->cpu_features & CPU_FTR_TAU) {
#ifdef CONFIG_TAU_AVERAGE
/* more straightforward, but potentially misleading */
seq_printf(m, "temperature \t: %u C (uncalibrated)\n",
cpu_temp(cpu_id));
#else
/* show the actual temp sensor range */
u32 temp;
temp = cpu_temp_both(cpu_id);
seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n",
temp & 0xff, temp >> 16);
#endif
}
#endif /* CONFIG_TAU */
/*
* Platforms that have variable clock rates, should implement
* the method ppc_md.get_proc_freq() that reports the clock
* rate of a given cpu. The rest can use ppc_proc_freq to
* report the clock rate that is same across all cpus.
*/
if (ppc_md.get_proc_freq)
proc_freq = ppc_md.get_proc_freq(cpu_id);
else
proc_freq = ppc_proc_freq;
if (proc_freq)
seq_printf(m, "clock\t\t: %lu.%06luMHz\n",
proc_freq / 1000000, proc_freq % 1000000);
if (ppc_md.show_percpuinfo != NULL)
ppc_md.show_percpuinfo(m, cpu_id);
/* If we are a Freescale core do a simple check so
* we dont have to keep adding cases in the future */
if (PVR_VER(pvr) & 0x8000) {
switch (PVR_VER(pvr)) {
case 0x8000: /* 7441/7450/7451, Voyager */
case 0x8001: /* 7445/7455, Apollo 6 */
case 0x8002: /* 7447/7457, Apollo 7 */
case 0x8003: /* 7447A, Apollo 7 PM */
case 0x8004: /* 7448, Apollo 8 */
case 0x800c: /* 7410, Nitro */
maj = ((pvr >> 8) & 0xF);
min = PVR_MIN(pvr);
break;
default: /* e500/book-e */
maj = PVR_MAJ(pvr);
min = PVR_MIN(pvr);
break;
}
} else {
switch (PVR_VER(pvr)) {
case 0x0020: /* 403 family */
maj = PVR_MAJ(pvr) + 1;
min = PVR_MIN(pvr);
break;
case 0x1008: /* 740P/750P ?? */
maj = ((pvr >> 8) & 0xFF) - 1;
min = pvr & 0xFF;
break;
case 0x004e: /* POWER9 bits 12-15 give chip type */
maj = (pvr >> 8) & 0x0F;
min = pvr & 0xFF;
break;
default:
maj = (pvr >> 8) & 0xFF;
min = pvr & 0xFF;
break;
}
}
seq_printf(m, "revision\t: %hd.%hd (pvr %04x %04x)\n",
maj, min, PVR_VER(pvr), PVR_REV(pvr));
#ifdef CONFIG_PPC32
seq_printf(m, "bogomips\t: %lu.%02lu\n",
loops_per_jiffy / (500000/HZ),
(loops_per_jiffy / (5000/HZ)) % 100);
#endif
seq_printf(m, "\n");
/* If this is the last cpu, print the summary */
if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
show_cpuinfo_summary(m);
return 0;
}
static void *c_start(struct seq_file *m, loff_t *pos)
{
if (*pos == 0) /* just in case, cpu 0 is not the first */
*pos = cpumask_first(cpu_online_mask);
else
*pos = cpumask_next(*pos - 1, cpu_online_mask);
if ((*pos) < nr_cpu_ids)
return (void *)(unsigned long)(*pos + 1);
return NULL;
}
static void *c_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return c_start(m, pos);
}
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 = show_cpuinfo,
};
void __init check_for_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
DBG(" -> check_for_initrd() initrd_start=0x%lx initrd_end=0x%lx\n",
initrd_start, initrd_end);
/* If we were passed an initrd, set the ROOT_DEV properly if the values
* look sensible. If not, clear initrd reference.
*/
if (is_kernel_addr(initrd_start) && is_kernel_addr(initrd_end) &&
initrd_end > initrd_start)
ROOT_DEV = Root_RAM0;
else
initrd_start = initrd_end = 0;
if (initrd_start)
pr_info("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
DBG(" <- check_for_initrd()\n");
#endif /* CONFIG_BLK_DEV_INITRD */
}
#ifdef CONFIG_SMP
int threads_per_core, threads_per_subcore, threads_shift;
cpumask_t threads_core_mask;
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-28 18:21:34 -06:00
EXPORT_SYMBOL_GPL(threads_per_core);
EXPORT_SYMBOL_GPL(threads_per_subcore);
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-28 18:21:34 -06:00
EXPORT_SYMBOL_GPL(threads_shift);
EXPORT_SYMBOL_GPL(threads_core_mask);
static void __init cpu_init_thread_core_maps(int tpc)
{
int i;
threads_per_core = tpc;
threads_per_subcore = tpc;
cpumask_clear(&threads_core_mask);
/* This implementation only supports power of 2 number of threads
* for simplicity and performance
*/
threads_shift = ilog2(tpc);
BUG_ON(tpc != (1 << threads_shift));
for (i = 0; i < tpc; i++)
cpumask_set_cpu(i, &threads_core_mask);
printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n",
tpc, tpc > 1 ? "s" : "");
printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift);
}
u32 *cpu_to_phys_id = NULL;
/**
* setup_cpu_maps - initialize the following cpu maps:
* cpu_possible_mask
* cpu_present_mask
*
* Having the possible map set up early allows us to restrict allocations
* of things like irqstacks to nr_cpu_ids rather than NR_CPUS.
*
* We do not initialize the online map here; cpus set their own bits in
* cpu_online_mask as they come up.
*
* This function is valid only for Open Firmware systems. finish_device_tree
* must be called before using this.
*
* While we're here, we may as well set the "physical" cpu ids in the paca.
*
* NOTE: This must match the parsing done in early_init_dt_scan_cpus.
*/
void __init smp_setup_cpu_maps(void)
{
struct device_node *dn;
int cpu = 0;
int nthreads = 1;
DBG("smp_setup_cpu_maps()\n");
arch: simplify several early memory allocations There are several early memory allocations in arch/ code that use memblock_phys_alloc() to allocate memory, convert the returned physical address to the virtual address and then set the allocated memory to zero. Exactly the same behaviour can be achieved simply by calling memblock_alloc(): it allocates the memory in the same way as memblock_phys_alloc(), then it performs the phys_to_virt() conversion and clears the allocated memory. Replace the longer sequence with a simpler call to memblock_alloc(). Link: http://lkml.kernel.org/r/1546248566-14910-6-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Michal Simek <michal.simek@xilinx.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mackerras <paulus@samba.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Vincent Chen <deanbo422@gmail.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>
2019-03-07 17:31:06 -07:00
cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32),
__alignof__(u32));
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 00:30:31 -06:00
if (!cpu_to_phys_id)
panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
__func__, nr_cpu_ids * sizeof(u32), __alignof__(u32));
for_each_node_by_type(dn, "cpu") {
const __be32 *intserv;
__be32 cpu_be;
int j, len;
DBG(" * %pOF...\n", dn);
intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s",
&len);
if (intserv) {
DBG(" ibm,ppc-interrupt-server#s -> %d threads\n",
nthreads);
} else {
DBG(" no ibm,ppc-interrupt-server#s -> 1 thread\n");
intserv = of_get_property(dn, "reg", &len);
if (!intserv) {
cpu_be = cpu_to_be32(cpu);
/* XXX: what is this? uninitialized?? */
intserv = &cpu_be; /* assume logical == phys */
len = 4;
}
}
nthreads = len / sizeof(int);
for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
bool avail;
DBG(" thread %d -> cpu %d (hard id %d)\n",
j, cpu, be32_to_cpu(intserv[j]));
avail = of_device_is_available(dn);
if (!avail)
avail = !of_property_match_string(dn,
"enable-method", "spin-table");
set_cpu_present(cpu, avail);
set_cpu_possible(cpu, true);
cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
cpu++;
}
if (cpu >= nr_cpu_ids) {
of_node_put(dn);
break;
}
}
/* If no SMT supported, nthreads is forced to 1 */
if (!cpu_has_feature(CPU_FTR_SMT)) {
DBG(" SMT disabled ! nthreads forced to 1\n");
nthreads = 1;
}
#ifdef CONFIG_PPC64
/*
* On pSeries LPAR, we need to know how many cpus
* could possibly be added to this partition.
*/
if (firmware_has_feature(FW_FEATURE_LPAR) &&
(dn = of_find_node_by_path("/rtas"))) {
int num_addr_cell, num_size_cell, maxcpus;
const __be32 *ireg;
num_addr_cell = of_n_addr_cells(dn);
num_size_cell = of_n_size_cells(dn);
ireg = of_get_property(dn, "ibm,lrdr-capacity", NULL);
if (!ireg)
goto out;
maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
/* Double maxcpus for processors which have SMT capability */
if (cpu_has_feature(CPU_FTR_SMT))
maxcpus *= nthreads;
if (maxcpus > nr_cpu_ids) {
printk(KERN_WARNING
"Partition configured for %d cpus, "
"operating system maximum is %u.\n",
maxcpus, nr_cpu_ids);
maxcpus = nr_cpu_ids;
} else
printk(KERN_INFO "Partition configured for %d cpus.\n",
maxcpus);
for (cpu = 0; cpu < maxcpus; cpu++)
set_cpu_possible(cpu, true);
out:
of_node_put(dn);
}
vdso_data->processorCount = num_present_cpus();
#endif /* CONFIG_PPC64 */
/* Initialize CPU <=> thread mapping/
*
* WARNING: We assume that the number of threads is the same for
* every CPU in the system. If that is not the case, then some code
* here will have to be reworked
*/
cpu_init_thread_core_maps(nthreads);
/* Now that possible cpus are set, set nr_cpu_ids for later use */
setup_nr_cpu_ids();
free_unused_pacas();
}
#endif /* CONFIG_SMP */
#ifdef CONFIG_PCSPKR_PLATFORM
static __init int add_pcspkr(void)
{
struct device_node *np;
struct platform_device *pd;
int ret;
np = of_find_compatible_node(NULL, NULL, "pnpPNP,100");
of_node_put(np);
if (!np)
return -ENODEV;
pd = platform_device_alloc("pcspkr", -1);
if (!pd)
return -ENOMEM;
ret = platform_device_add(pd);
if (ret)
platform_device_put(pd);
return ret;
}
device_initcall(add_pcspkr);
#endif /* CONFIG_PCSPKR_PLATFORM */
void probe_machine(void)
{
extern struct machdep_calls __machine_desc_start;
extern struct machdep_calls __machine_desc_end;
unsigned int i;
/*
* Iterate all ppc_md structures until we find the proper
* one for the current machine type
*/
DBG("Probing machine type ...\n");
/*
* Check ppc_md is empty, if not we have a bug, ie, we setup an
* entry before probe_machine() which will be overwritten
*/
for (i = 0; i < (sizeof(ppc_md) / sizeof(void *)); i++) {
if (((void **)&ppc_md)[i]) {
printk(KERN_ERR "Entry %d in ppc_md non empty before"
" machine probe !\n", i);
}
}
for (machine_id = &__machine_desc_start;
machine_id < &__machine_desc_end;
machine_id++) {
DBG(" %s ...", machine_id->name);
memcpy(&ppc_md, machine_id, sizeof(struct machdep_calls));
if (ppc_md.probe()) {
DBG(" match !\n");
break;
}
DBG("\n");
}
/* What can we do if we didn't find ? */
if (machine_id >= &__machine_desc_end) {
pr_err("No suitable machine description found !\n");
for (;;);
}
printk(KERN_INFO "Using %s machine description\n", ppc_md.name);
}
/* Match a class of boards, not a specific device configuration. */
int check_legacy_ioport(unsigned long base_port)
{
struct device_node *parent, *np = NULL;
int ret = -ENODEV;
switch(base_port) {
case I8042_DATA_REG:
if (!(np = of_find_compatible_node(NULL, NULL, "pnpPNP,303")))
np = of_find_compatible_node(NULL, NULL, "pnpPNP,f03");
if (np) {
parent = of_get_parent(np);
of_i8042_kbd_irq = irq_of_parse_and_map(parent, 0);
if (!of_i8042_kbd_irq)
of_i8042_kbd_irq = 1;
of_i8042_aux_irq = irq_of_parse_and_map(parent, 1);
if (!of_i8042_aux_irq)
of_i8042_aux_irq = 12;
of_node_put(np);
np = parent;
break;
}
np = of_find_node_by_type(NULL, "8042");
/* Pegasos has no device_type on its 8042 node, look for the
* name instead */
if (!np)
np = of_find_node_by_name(NULL, "8042");
if (np) {
of_i8042_kbd_irq = 1;
of_i8042_aux_irq = 12;
}
break;
case FDC_BASE: /* FDC1 */
np = of_find_node_by_type(NULL, "fdc");
break;
default:
/* ipmi is supposed to fail here */
break;
}
if (!np)
return ret;
parent = of_get_parent(np);
if (parent) {
if (of_node_is_type(parent, "isa"))
ret = 0;
of_node_put(parent);
}
of_node_put(np);
return ret;
}
EXPORT_SYMBOL(check_legacy_ioport);
static int ppc_panic_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
/*
* panic does a local_irq_disable, but we really
* want interrupts to be hard disabled.
*/
hard_irq_disable();
/*
* If firmware-assisted dump has been registered then trigger
* firmware-assisted dump and let firmware handle everything else.
*/
crash_fadump(NULL, ptr);
if (ppc_md.panic)
ppc_md.panic(ptr); /* May not return */
return NOTIFY_DONE;
}
static struct notifier_block ppc_panic_block = {
.notifier_call = ppc_panic_event,
.priority = INT_MIN /* may not return; must be done last */
};
void __init setup_panic(void)
{
/* PPC64 always does a hard irq disable in its panic handler */
if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
return;
atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
}
#ifdef CONFIG_CHECK_CACHE_COHERENCY
/*
* For platforms that have configurable cache-coherency. This function
* checks that the cache coherency setting of the kernel matches the setting
* left by the firmware, as indicated in the device tree. Since a mismatch
* will eventually result in DMA failures, we print * and error and call
* BUG() in that case.
*/
#ifdef CONFIG_NOT_COHERENT_CACHE
#define KERNEL_COHERENCY 0
#else
#define KERNEL_COHERENCY 1
#endif
static int __init check_cache_coherency(void)
{
struct device_node *np;
const void *prop;
int devtree_coherency;
np = of_find_node_by_path("/");
prop = of_get_property(np, "coherency-off", NULL);
of_node_put(np);
devtree_coherency = prop ? 0 : 1;
if (devtree_coherency != KERNEL_COHERENCY) {
printk(KERN_ERR
"kernel coherency:%s != device tree_coherency:%s\n",
KERNEL_COHERENCY ? "on" : "off",
devtree_coherency ? "on" : "off");
BUG();
}
return 0;
}
late_initcall(check_cache_coherency);
#endif /* CONFIG_CHECK_CACHE_COHERENCY */
#ifdef CONFIG_DEBUG_FS
struct dentry *powerpc_debugfs_root;
EXPORT_SYMBOL(powerpc_debugfs_root);
static int powerpc_debugfs_init(void)
{
powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL);
return powerpc_debugfs_root == NULL;
}
arch_initcall(powerpc_debugfs_init);
#endif
void ppc_printk_progress(char *s, unsigned short hex)
{
pr_info("%s\n", s);
}
void arch_setup_pdev_archdata(struct platform_device *pdev)
{
pdev->archdata.dma_mask = DMA_BIT_MASK(32);
pdev->dev.dma_mask = &pdev->archdata.dma_mask;
}
static __init void print_system_info(void)
{
pr_info("-----------------------------------------------------\n");
#ifdef CONFIG_PPC_BOOK3S_64
pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size);
#endif
#ifdef CONFIG_PPC_BOOK3S_32
pr_info("Hash_size = 0x%lx\n", Hash_size);
#endif
pr_info("phys_mem_size = 0x%llx\n",
(unsigned long long)memblock_phys_mem_size());
pr_info("dcache_bsize = 0x%x\n", dcache_bsize);
pr_info("icache_bsize = 0x%x\n", icache_bsize);
if (ucache_bsize != 0)
pr_info("ucache_bsize = 0x%x\n", ucache_bsize);
pr_info("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features);
pr_info(" possible = 0x%016lx\n",
(unsigned long)CPU_FTRS_POSSIBLE);
pr_info(" always = 0x%016lx\n",
(unsigned long)CPU_FTRS_ALWAYS);
pr_info("cpu_user_features = 0x%08x 0x%08x\n",
cur_cpu_spec->cpu_user_features,
cur_cpu_spec->cpu_user_features2);
pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features);
#ifdef CONFIG_PPC64
pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
#endif
#ifdef CONFIG_PPC_BOOK3S_64
if (htab_address)
pr_info("htab_address = 0x%p\n", htab_address);
if (htab_hash_mask)
pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask);
#endif
#ifdef CONFIG_PPC_BOOK3S_32
if (Hash)
pr_info("Hash = 0x%p\n", Hash);
if (Hash_mask)
pr_info("Hash_mask = 0x%lx\n", Hash_mask);
#endif
if (PHYSICAL_START > 0)
pr_info("physical_start = 0x%llx\n",
(unsigned long long)PHYSICAL_START);
pr_info("-----------------------------------------------------\n");
}
#ifdef CONFIG_SMP
static void smp_setup_pacas(void)
{
int cpu;
for_each_possible_cpu(cpu) {
if (cpu == smp_processor_id())
continue;
allocate_paca(cpu);
set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
}
memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32));
cpu_to_phys_id = NULL;
}
#endif
/*
* Called into from start_kernel this initializes memblock, which is used
* to manage page allocation until mem_init is called.
*/
void __init setup_arch(char **cmdline_p)
{
*cmdline_p = boot_command_line;
/* Set a half-reasonable default so udelay does something sensible */
loops_per_jiffy = 500000000 / HZ;
/* Unflatten the device-tree passed by prom_init or kexec */
unflatten_device_tree();
/*
* Initialize cache line/block info from device-tree (on ppc64) or
* just cputable (on ppc32).
*/
initialize_cache_info();
/* Initialize RTAS if available. */
rtas_initialize();
/* Check if we have an initrd provided via the device-tree. */
check_for_initrd();
/* Probe the machine type, establish ppc_md. */
probe_machine();
/* Setup panic notifier if requested by the platform. */
setup_panic();
/*
* Configure ppc_md.power_save (ppc32 only, 64-bit machines do
* it from their respective probe() function.
*/
setup_power_save();
/* Discover standard serial ports. */
find_legacy_serial_ports();
/* Register early console with the printk subsystem. */
register_early_udbg_console();
/* Setup the various CPU maps based on the device-tree. */
smp_setup_cpu_maps();
/* Initialize xmon. */
xmon_setup();
/* Check the SMT related command line arguments (ppc64). */
check_smt_enabled();
/* Parse memory topology */
mem_topology_setup();
/*
* Release secondary cpus out of their spinloops at 0x60 now that
* we can map physical -> logical CPU ids.
*
* Freescale Book3e parts spin in a loop provided by firmware,
* so smp_release_cpus() does nothing for them.
*/
#ifdef CONFIG_SMP
smp_setup_pacas();
/* On BookE, setup per-core TLB data structures. */
setup_tlb_core_data();
smp_release_cpus();
#endif
/* Print various info about the machine that has been gathered so far. */
print_system_info();
/* Reserve large chunks of memory for use by CMA for KVM. */
kvm_cma_reserve();
klp_init_thread_info(&init_task);
init_mm.start_code = (unsigned long)_stext;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = klimit;
#ifdef CONFIG_PPC_MM_SLICES
#ifdef CONFIG_PPC64
if (!radix_enabled())
init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
powerpc/mm/slice: Fix hugepage allocation at hint address on 8xx On the 8xx, the page size is set in the PMD entry and applies to all pages of the page table pointed by the said PMD entry. When an app has some regular pages allocated (e.g. see below) and tries to mmap() a huge page at a hint address covered by the same PMD entry, the kernel accepts the hint allthough the 8xx cannot handle different page sizes in the same PMD entry. 10000000-10001000 r-xp 00000000 00:0f 2597 /root/malloc 10010000-10011000 rwxp 00000000 00:0f 2597 /root/malloc mmap(0x10080000, 524288, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|0x40000, -1, 0) = 0x10080000 This results the app remaining forever in do_page_fault()/hugetlb_fault() and when interrupting that app, we get the following warning: [162980.035629] WARNING: CPU: 0 PID: 2777 at arch/powerpc/mm/hugetlbpage.c:354 hugetlb_free_pgd_range+0xc8/0x1e4 [162980.035699] CPU: 0 PID: 2777 Comm: malloc Tainted: G W 4.14.6 #85 [162980.035744] task: c67e2c00 task.stack: c668e000 [162980.035783] NIP: c000fe18 LR: c00e1eec CTR: c00f90c0 [162980.035830] REGS: c668fc20 TRAP: 0700 Tainted: G W (4.14.6) [162980.035854] MSR: 00029032 <EE,ME,IR,DR,RI> CR: 24044224 XER: 20000000 [162980.036003] [162980.036003] GPR00: c00e1eec c668fcd0 c67e2c00 00000010 c6869410 10080000 00000000 77fb4000 [162980.036003] GPR08: ffff0001 0683c001 00000000 ffffff80 44028228 10018a34 00004008 418004fc [162980.036003] GPR16: c668e000 00040100 c668e000 c06c0000 c668fe78 c668e000 c6835ba0 c668fd48 [162980.036003] GPR24: 00000000 73ffffff 74000000 00000001 77fb4000 100fffff 10100000 10100000 [162980.036743] NIP [c000fe18] hugetlb_free_pgd_range+0xc8/0x1e4 [162980.036839] LR [c00e1eec] free_pgtables+0x12c/0x150 [162980.036861] Call Trace: [162980.036939] [c668fcd0] [c00f0774] unlink_anon_vmas+0x1c4/0x214 (unreliable) [162980.037040] [c668fd10] [c00e1eec] free_pgtables+0x12c/0x150 [162980.037118] [c668fd40] [c00eabac] exit_mmap+0xe8/0x1b4 [162980.037210] [c668fda0] [c0019710] mmput.part.9+0x20/0xd8 [162980.037301] [c668fdb0] [c001ecb0] do_exit+0x1f0/0x93c [162980.037386] [c668fe00] [c001f478] do_group_exit+0x40/0xcc [162980.037479] [c668fe10] [c002a76c] get_signal+0x47c/0x614 [162980.037570] [c668fe70] [c0007840] do_signal+0x54/0x244 [162980.037654] [c668ff30] [c0007ae8] do_notify_resume+0x34/0x88 [162980.037744] [c668ff40] [c000dae8] do_user_signal+0x74/0xc4 [162980.037781] Instruction dump: [162980.037821] 7fdff378 81370000 54a3463a 80890020 7d24182e 7c841a14 712a0004 4082ff94 [162980.038014] 2f890000 419e0010 712a0ff0 408200e0 <0fe00000> 54a9000a 7f984840 419d0094 [162980.038216] ---[ end trace c0ceeca8e7a5800a ]--- [162980.038754] BUG: non-zero nr_ptes on freeing mm: 1 [162985.363322] BUG: non-zero nr_ptes on freeing mm: -1 In order to fix this, this patch uses the address space "slices" implemented for BOOK3S/64 and enhanced to support PPC32 by the preceding patch. This patch modifies the context.id on the 8xx to be in the range [1:16] instead of [0:15] in order to identify context.id == 0 as not initialised contexts as done on BOOK3S This patch activates CONFIG_PPC_MM_SLICES when CONFIG_HUGETLB_PAGE is selected for the 8xx Alltough we could in theory have as many slices as PMD entries, the current slices implementation limits the number of low slices to 16. This limitation is not preventing us to fix the initial issue allthough it is suboptimal. It will be cured in a subsequent patch. Fixes: 4b91428699477 ("powerpc/8xx: Implement support of hugepages") Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-02-22 07:27:26 -07:00
#elif defined(CONFIG_PPC_8xx)
init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW;
#else
#error "context.addr_limit not initialized."
#endif
#endif
#ifdef CONFIG_SPAPR_TCE_IOMMU
mm_iommu_init(&init_mm);
#endif
irqstack_early_init();
exc_lvl_early_init();
emergency_stack_init();
initmem_init();
early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
#ifdef CONFIG_DUMMY_CONSOLE
conswitchp = &dummy_con;
#endif
if (ppc_md.setup_arch)
ppc_md.setup_arch();
setup_barrier_nospec();
setup_spectre_v2();
paging_init();
/* Initialize the MMU context management stuff. */
mmu_context_init();
#ifdef CONFIG_PPC64
/* Interrupt code needs to be 64K-aligned. */
if ((unsigned long)_stext & 0xffff)
panic("Kernelbase not 64K-aligned (0x%lx)!\n",
(unsigned long)_stext);
#endif
}