linux-stable/arch/powerpc/kernel/prom.c

1029 lines
27 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Procedures for creating, accessing and interpreting the device tree.
*
* Paul Mackerras August 1996.
* Copyright (C) 1996-2005 Paul Mackerras.
*
* Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
* {engebret|bergner}@us.ibm.com
*/
#undef DEBUG
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/threads.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/kexec.h>
2006-07-03 11:36:01 +00:00
#include <linux/irq.h>
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/cpu.h>
mm: reorder includes after introduction of linux/pgtable.h The replacement of <asm/pgrable.h> with <linux/pgtable.h> made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s <file> <header>" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include <linux/%s>" % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include <linux/"): in_hdrs = True elif not moved and in_hdrs: moved = True print hdr_to_move print line Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:32:42 +00:00
#include <linux/pgtable.h>
#include <linux/seq_buf.h>
#include <asm/rtas.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <asm/irq.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/smp.h>
#include <asm/mmu.h>
#include <asm/paca.h>
#include <asm/powernv.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/pci-bridge.h>
#include <asm/kexec.h>
#include <asm/opal.h>
#include <asm/fadump.h>
#include <asm/epapr_hcalls.h>
#include <asm/firmware.h>
#include <asm/dt_cpu_ftrs.h>
#include <asm/drmem.h>
#include <asm/ultravisor.h>
#include <asm/prom.h>
#include <asm/plpks.h>
[POWERPC] 85xx: Add support for relocatable kernel (and booting at non-zero) Added support to allow an 85xx kernel to be run from a non-zero physical address (useful for cooperative asymmetric multiprocessing situations and kdump). The support can be configured at compile time by setting CONFIG_PAGE_OFFSET, CONFIG_KERNEL_START, and CONFIG_PHYSICAL_START as desired. Alternatively, the kernel build can set CONFIG_RELOCATABLE. Setting this config option causes the kernel to determine at runtime the physical addresses of CONFIG_PAGE_OFFSET and CONFIG_KERNEL_START. If CONFIG_RELOCATABLE is set, then CONFIG_PHYSICAL_START has no meaning. However, CONFIG_PHYSICAL_START will always be used to set the LOAD program header physical address field in the resulting ELF image. Currently we are limited to running at a physical address that is a multiple of 256M. This is due to how we map TLBs to cover lowmem. This should be fixed to allow 64M or maybe even 16M alignment in the future. It is considered an error to try and run a kernel at a non-aligned physical address. All the magic for this support is accomplished by proper initialization of the kernel memory subsystem and use of ARCH_PFN_OFFSET. The use of ARCH_PFN_OFFSET only affects normal memory and not IO mappings. ioremap uses map_page and isn't affected by ARCH_PFN_OFFSET. /dev/mem continues to allow access to any physical address in the system regardless of how CONFIG_PHYSICAL_START is set. Signed-off-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-04-21 18:22:34 +00:00
#include <mm/mmu_decl.h>
#ifdef DEBUG
#define DBG(fmt...) printk(KERN_ERR fmt)
#else
#define DBG(fmt...)
#endif
int *chip_id_lookup_table;
#ifdef CONFIG_PPC64
int __initdata iommu_is_off;
int __initdata iommu_force_on;
unsigned long tce_alloc_start, tce_alloc_end;
u64 ppc64_rma_size;
unsigned int boot_cpu_node_count __ro_after_init;
#endif
static phys_addr_t first_memblock_size;
static int __initdata boot_cpu_count;
static int __init early_parse_mem(char *p)
{
if (!p)
return 1;
memory_limit = PAGE_ALIGN(memparse(p, &p));
DBG("memory limit = 0x%llx\n", memory_limit);
return 0;
}
early_param("mem", early_parse_mem);
/*
* overlaps_initrd - check for overlap with page aligned extension of
* initrd.
*/
static inline int overlaps_initrd(unsigned long start, unsigned long size)
{
#ifdef CONFIG_BLK_DEV_INITRD
if (!initrd_start)
return 0;
return (start + size) > ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
start <= ALIGN(initrd_end, PAGE_SIZE);
#else
return 0;
#endif
}
/**
* move_device_tree - move tree to an unused area, if needed.
*
* The device tree may be allocated beyond our memory limit, or inside the
* crash kernel region for kdump, or within the page aligned range of initrd.
* If so, move it out of the way.
*/
static void __init move_device_tree(void)
{
unsigned long start, size;
void *p;
DBG("-> move_device_tree\n");
start = __pa(initial_boot_params);
size = fdt_totalsize(initial_boot_params);
if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
!memblock_is_memory(start + size - 1) ||
overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) {
powerpc: use memblock functions returning virtual address Since only the virtual address of allocated blocks is used, lets use functions returning directly virtual address. Those functions have the advantage of also zeroing the block. [rppt@linux.ibm.com: powerpc: remove duplicated alloc_stack() function] Link: http://lkml.kernel.org/r/20190226064032.GA5873@rapoport-lnx [rppt@linux.ibm.com: updated error message in alloc_stack() to be more verbose] [rppt@linux.ibm.com: convereted several additional call sites ] Link: http://lkml.kernel.org/r/1548057848-15136-3-git-send-email-rppt@linux.ibm.com Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.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: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> 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 06:29:00 +00:00
p = memblock_alloc_raw(size, PAGE_SIZE);
if (!p)
panic("Failed to allocate %lu bytes to move device tree\n",
size);
memcpy(p, initial_boot_params, size);
initial_boot_params = p;
DBG("Moved device tree to 0x%px\n", p);
}
DBG("<- move_device_tree\n");
}
/*
* ibm,pa/pi-features is a per-cpu property that contains a string of
* attribute descriptors, each of which has a 2 byte header plus up
* to 254 bytes worth of processor attribute bits. First header
* byte specifies the number of bytes following the header.
* Second header byte is an "attribute-specifier" type, of which
* zero is the only currently-defined value.
* Implementation: Pass in the byte and bit offset for the feature
* that we are interested in. The function will return -1 if the
* pa-features property is missing, or a 1/0 to indicate if the feature
* is supported/not supported. Note that the bit numbers are
* big-endian to match the definition in PAPR.
* Note: the 'clear' flag clears the feature if the bit is set in the
* ibm,pa/pi-features property, it does not set the feature if the
* bit is clear.
*/
struct ibm_feature {
unsigned long cpu_features; /* CPU_FTR_xxx bit */
unsigned long mmu_features; /* MMU_FTR_xxx bit */
unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */
unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */
unsigned char pabyte; /* byte number in ibm,pa/pi-features */
unsigned char pabit; /* bit number (big-endian) */
unsigned char clear; /* if 1, pa bit set => clear feature */
};
static struct ibm_feature ibm_pa_features[] __initdata = {
{ .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU },
{ .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU },
{ .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
{ .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
{ .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
#ifdef CONFIG_PPC_RADIX_MMU
{ .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE },
#endif
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
/*
* If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
* we don't want to turn on TM here, so we use the *_COMP versions
* which are 0 if the kernel doesn't support TM.
*/
{ .pabyte = 22, .pabit = 0, .cpu_features = CPU_FTR_TM_COMP,
.cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP },
{ .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 },
{ .pabyte = 68, .pabit = 5, .cpu_features = CPU_FTR_DEXCR_NPHIE },
};
/*
* ibm,pi-features property provides the support of processor specific
* options not described in ibm,pa-features. Right now use byte 0, bit 3
* which indicates the occurrence of DSI interrupt when the paste operation
* on the suspended NX window.
*/
static struct ibm_feature ibm_pi_features[] __initdata = {
{ .pabyte = 0, .pabit = 3, .mmu_features = MMU_FTR_NX_DSI },
{ .pabyte = 0, .pabit = 4, .cpu_features = CPU_FTR_DBELL, .clear = 1 },
};
static void __init scan_features(unsigned long node, const unsigned char *ftrs,
unsigned long tablelen,
struct ibm_feature *fp,
unsigned long ft_size)
{
unsigned long i, len, bit;
/* find descriptor with type == 0 */
for (;;) {
if (tablelen < 3)
return;
len = 2 + ftrs[0];
if (tablelen < len)
return; /* descriptor 0 not found */
if (ftrs[1] == 0)
break;
tablelen -= len;
ftrs += len;
}
/* loop over bits we know about */
for (i = 0; i < ft_size; ++i, ++fp) {
if (fp->pabyte >= ftrs[0])
continue;
bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
if (bit && !fp->clear) {
cur_cpu_spec->cpu_features |= fp->cpu_features;
cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
cur_cpu_spec->mmu_features |= fp->mmu_features;
} else if (bit == fp->clear) {
cur_cpu_spec->cpu_features &= ~fp->cpu_features;
cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
cur_cpu_spec->mmu_features &= ~fp->mmu_features;
}
}
}
static void __init check_cpu_features(unsigned long node, char *name,
struct ibm_feature *fp,
unsigned long size)
{
const unsigned char *pa_ftrs;
int tablelen;
pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen);
if (pa_ftrs == NULL)
return;
scan_features(node, pa_ftrs, tablelen, fp, size);
}
#ifdef CONFIG_PPC_64S_HASH_MMU
static void __init init_mmu_slb_size(unsigned long node)
{
const __be32 *slb_size_ptr;
slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL) ? :
of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
if (slb_size_ptr)
mmu_slb_size = be32_to_cpup(slb_size_ptr);
}
#else
#define init_mmu_slb_size(node) do { } while(0)
#endif
static struct feature_property {
const char *name;
u32 min_value;
unsigned long cpu_feature;
unsigned long cpu_user_ftr;
} feature_properties[] __initdata = {
#ifdef CONFIG_ALTIVEC
{"altivec", 0, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
{"ibm,vmx", 1, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
/* Yes, this _really_ is ibm,vmx == 2 to enable VSX */
{"ibm,vmx", 2, CPU_FTR_VSX, PPC_FEATURE_HAS_VSX},
#endif /* CONFIG_VSX */
#ifdef CONFIG_PPC64
{"ibm,dfp", 1, 0, PPC_FEATURE_HAS_DFP},
{"ibm,purr", 1, CPU_FTR_PURR, 0},
{"ibm,spurr", 1, CPU_FTR_SPURR, 0},
#endif /* CONFIG_PPC64 */
};
#if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU)
powerpc/prom: Mark identical_pvr_fixup as __init If identical_pvr_fixup() is not inlined, there are two modpost warnings: WARNING: modpost: vmlinux.o(.text+0x54e8): Section mismatch in reference from the function identical_pvr_fixup() to the function .init.text:of_get_flat_dt_prop() The function identical_pvr_fixup() references the function __init of_get_flat_dt_prop(). This is often because identical_pvr_fixup lacks a __init annotation or the annotation of of_get_flat_dt_prop is wrong. WARNING: modpost: vmlinux.o(.text+0x551c): Section mismatch in reference from the function identical_pvr_fixup() to the function .init.text:identify_cpu() The function identical_pvr_fixup() references the function __init identify_cpu(). This is often because identical_pvr_fixup lacks a __init annotation or the annotation of identify_cpu is wrong. identical_pvr_fixup() calls two functions marked as __init and is only called by a function marked as __init so it should be marked as __init as well. At the same time, remove the inline keywork as it is not necessary to inline this function. The compiler is still free to do so if it feels it is worthwhile since commit 889b3c1245de ("compiler: remove CONFIG_OPTIMIZE_INLINING entirely"). Fixes: 14b3d926a22b ("[POWERPC] 4xx: update 440EP(x)/440GR(x) identical PVR issue workaround") Signed-off-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://github.com/ClangBuiltLinux/linux/issues/1316 Link: https://lore.kernel.org/r/20210302200829.2680663-1-nathan@kernel.org
2021-03-02 20:08:29 +00:00
static __init void identical_pvr_fixup(unsigned long node)
{
unsigned int pvr;
const char *model = of_get_flat_dt_prop(node, "model", NULL);
/*
* Since 440GR(x)/440EP(x) processors have the same pvr,
* we check the node path and set bit 28 in the cur_cpu_spec
* pvr for EP(x) processor version. This bit is always 0 in
* the "real" pvr. Then we call identify_cpu again with
* the new logical pvr to enable FPU support.
*/
if (model && strstr(model, "440EP")) {
pvr = cur_cpu_spec->pvr_value | 0x8;
identify_cpu(0, pvr);
DBG("Using logical pvr %x for %s\n", pvr, model);
}
}
#else
#define identical_pvr_fixup(node) do { } while(0)
#endif
static void __init check_cpu_feature_properties(unsigned long node)
{
int i;
struct feature_property *fp = feature_properties;
const __be32 *prop;
for (i = 0; i < (int)ARRAY_SIZE(feature_properties); ++i, ++fp) {
prop = of_get_flat_dt_prop(node, fp->name, NULL);
if (prop && be32_to_cpup(prop) >= fp->min_value) {
cur_cpu_spec->cpu_features |= fp->cpu_feature;
cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
}
}
}
static int __init early_init_dt_scan_cpus(unsigned long node,
const char *uname, int depth,
void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
const __be32 *prop;
const __be32 *intserv;
int i, nthreads;
int len;
int found = -1;
int found_thread = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
return 0;
if (IS_ENABLED(CONFIG_PPC64))
boot_cpu_node_count++;
/* Get physical cpuid */
intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len);
if (!intserv)
intserv = of_get_flat_dt_prop(node, "reg", &len);
nthreads = len / sizeof(int);
/*
* Now see if any of these threads match our boot cpu.
* NOTE: This must match the parsing done in smp_setup_cpu_maps.
*/
for (i = 0; i < nthreads; i++) {
if (be32_to_cpu(intserv[i]) ==
fdt_boot_cpuid_phys(initial_boot_params)) {
found = boot_cpu_count;
found_thread = i;
}
#ifdef CONFIG_SMP
/* logical cpu id is always 0 on UP kernels */
boot_cpu_count++;
#endif
}
/* Not the boot CPU */
if (found < 0)
return 0;
boot_cpuid = found;
powerpc/64: Move paca allocation to early_setup() The early paca and boot cpuid dance is complicated and currently does not quite work as expected for boot cpuid != 0 cases. early_init_devtree() currently allocates the paca_ptrs and boot cpuid paca, but until that returns and early_setup() calls setup_paca(), this thread is currently still executing with smp_processor_id() == 0. One problem this causes is the paca_ptrs[smp_processor_id()] pointer is poisoned, so valid_emergency_stack() (any backtrace) and any similar users will crash. Another is that the hardware id which is set here will not be returned by get_hard_smp_processor_id(smp_processor_id()), but it would work correctly for boot_cpuid == 0, which could lead to difficult to reproduce or find bugs. The hard id does not seem to be used by the rest of early_init_devtree(), it just looks like all this code might have been put here to allocate somewhere to store boot CPU hardware id while scanning the devtree. Rearrange things so the hwid is put in a global variable like boot_cpuid, and do all the paca allocation and boot paca setup in the 64-bit early_setup() after we have everything ready to go. The paca_ptrs[0] re-poisoning code in early_setup does not seem to have ever worked, because paca_ptrs[0] was never not-poisoned when boot_cpuid is not 0. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> [mpe: Fix build error on 32-bit] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20221216115930.2667772-4-npiggin@gmail.com
2022-12-16 11:59:29 +00:00
if (IS_ENABLED(CONFIG_PPC64))
boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
powerpc/64: Move paca allocation later in boot Mahesh & Sourabh identified two problems[1][2] with ppc64_bolted_size() and paca allocation. The first is that on a Radix capable machine but with "disable_radix" on the command line, there is a window during early boot where early_radix_enabled() is true, even though it will later become false. early_init_devtree: <- early_radix_enabled() = false early_init_dt_scan_cpus: <- early_radix_enabled() = false ... check_cpu_pa_features: <- early_radix_enabled() = false ... ^ <- early_radix_enabled() = TRUE allocate_paca: | <- early_radix_enabled() = TRUE ... | ppc64_bolted_size: | <- early_radix_enabled() = TRUE if (early_radix_enabled())| <- early_radix_enabled() = TRUE return ULONG_MAX; | ... | ... | <- early_radix_enabled() = TRUE ... | <- early_radix_enabled() = TRUE mmu_early_init_devtree() V ... <- early_radix_enabled() = false This causes ppc64_bolted_size() to return ULONG_MAX for the boot CPU's paca allocation, even though later it will return a different value. This is not currently a bug because the paca allocation is also limited by the RMA size, but that is very fragile. The second issue is that when using the Hash MMU, when we call ppc64_bolted_size() for the boot CPU's paca allocation, we have not yet detected whether 1T segments are available. That causes ppc64_bolted_size() to return 256MB, even if the machine can actually support up to 1T. This is usually OK, we generally have space below 256MB for one paca, but for a kdump kernel placed above 256MB it causes the boot to fail. At boot we cannot discover all the features of the machine instantaneously, so there will always be some periods where we have incomplete knowledge of the system. However both the above problems stem from the fact that we allocate the boot CPU's paca (and paca pointers array) before we decide which MMU we are using, or discover its exact features. Moving the paca allocation slightly later still can solve both the issues described above, and means for a normal boot we don't do any permanent allocations until after we've discovered the MMU. Note that although we move the boot CPU's paca allocation later, we still have a temporary paca (boot_paca) accessible via r13, so code that does read only access to paca fields is safe. The only risk is that some code writes to the boot_paca, and that write will then be lost when we switch away from the boot_paca later in early_setup(). The additional code that runs before the paca allocation is primarily mmu_early_init_devtree(), which is scanning the device tree and populating globals and cur_cpu_spec with MMU related flags. I do not see any additional code that writes to paca fields. [1]: https://lore.kernel.org/r/20211018084434.217772-2-sourabhjain@linux.ibm.com [2]: https://lore.kernel.org/r/20211018084434.217772-3-sourabhjain@linux.ibm.com Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20220124130544.408675-1-mpe@ellerman.id.au
2022-01-20 01:33:20 +00:00
if (nr_cpu_ids % nthreads != 0) {
set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads));
pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n",
nr_cpu_ids);
}
if (boot_cpuid >= nr_cpu_ids) {
// Remember boot core for smp_setup_cpu_maps()
boot_core_hwid = be32_to_cpu(intserv[0]);
pr_warn("Boot CPU %d (core hwid %d) >= nr_cpu_ids, adjusted boot CPU to %d\n",
boot_cpuid, boot_core_hwid, found_thread);
// Adjust boot CPU to appear on logical core 0
boot_cpuid = found_thread;
}
DBG("boot cpu: logical %d physical %d\n", boot_cpuid,
be32_to_cpu(intserv[found_thread]));
/*
* PAPR defines "logical" PVR values for cpus that
* meet various levels of the architecture:
* 0x0f000001 Architecture version 2.04
* 0x0f000002 Architecture version 2.05
* If the cpu-version property in the cpu node contains
* such a value, we call identify_cpu again with the
* logical PVR value in order to use the cpu feature
* bits appropriate for the architecture level.
*
* A POWER6 partition in "POWER6 architected" mode
* uses the 0x0f000002 PVR value; in POWER5+ mode
* it uses 0x0f000001.
*
* If we're using device tree CPU feature discovery then we don't
* support the cpu-version property, and it's the responsibility of the
* firmware/hypervisor to provide the correct feature set for the
* architecture level via the ibm,powerpc-cpu-features binding.
*/
if (!dt_cpu_ftrs_in_use()) {
prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
identify_cpu(0, be32_to_cpup(prop));
seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop));
}
check_cpu_feature_properties(node);
check_cpu_features(node, "ibm,pa-features", ibm_pa_features,
ARRAY_SIZE(ibm_pa_features));
check_cpu_features(node, "ibm,pi-features", ibm_pi_features,
ARRAY_SIZE(ibm_pi_features));
}
identical_pvr_fixup(node);
init_mmu_slb_size(node);
#ifdef CONFIG_PPC64
if (nthreads == 1)
cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
else if (!dt_cpu_ftrs_in_use())
cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
#endif
return 0;
}
static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
const char *uname,
int depth, void *data)
{
const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
/* Use common scan routine to determine if this is the chosen node */
if (early_init_dt_scan_chosen(data) < 0)
return 0;
#ifdef CONFIG_PPC64
/* check if iommu is forced on or off */
if (of_get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL)
iommu_is_off = 1;
if (of_get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL)
iommu_force_on = 1;
#endif
/* mem=x on the command line is the preferred mechanism */
lprop = of_get_flat_dt_prop(node, "linux,memory-limit", NULL);
if (lprop)
memory_limit = *lprop;
#ifdef CONFIG_PPC64
lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-start", NULL);
if (lprop)
tce_alloc_start = *lprop;
lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-end", NULL);
if (lprop)
tce_alloc_end = *lprop;
#endif
#ifdef CONFIG_CRASH_RESERVE
lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
if (lprop)
crashk_res.start = *lprop;
lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
if (lprop)
crashk_res.end = crashk_res.start + *lprop - 1;
#endif
/* break now */
return 1;
}
powerpc/mm: Check memblock_add against MAX_PHYSMEM_BITS range With SPARSEMEM config enabled, we make sure that we don't add sections beyond MAX_PHYSMEM_BITS range. This results in not building vmemmap mapping for range beyond max range. But our memblock layer looks the device tree and create mapping for the full memory range. Prevent this by checking against MAX_PHSYSMEM_BITS when doing memblock_add. We don't do similar check for memeblock_reserve_range. If reserve range is beyond MAX_PHYSMEM_BITS we expect that to be configured with 'nomap'. Any other reserved range should come from existing memblock ranges which we already filtered while adding. This avoids crash as below when running on a system with system ram config above MAX_PHSYSMEM_BITS Unable to handle kernel paging request for data at address 0xc00a001000000440 Faulting instruction address: 0xc000000001034118 cpu 0x0: Vector: 300 (Data Access) at [c00000000124fb30] pc: c000000001034118: __free_pages_bootmem+0xc0/0x1c0 lr: c00000000103b258: free_all_bootmem+0x19c/0x22c sp: c00000000124fdb0 msr: 9000000002001033 dar: c00a001000000440 dsisr: 40000000 current = 0xc00000000120dd00 paca = 0xc000000001f60000^I irqmask: 0x03^I irq_happened: 0x01 pid = 0, comm = swapper [c00000000124fe20] c00000000103b258 free_all_bootmem+0x19c/0x22c [c00000000124fee0] c000000001010a68 mem_init+0x3c/0x5c [c00000000124ff00] c00000000100401c start_kernel+0x298/0x5e4 [c00000000124ff90] c00000000000b57c start_here_common+0x1c/0x520 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-21 08:31:57 +00:00
/*
* Compare the range against max mem limit and update
* size if it cross the limit.
*/
#ifdef CONFIG_SPARSEMEM
static bool __init validate_mem_limit(u64 base, u64 *size)
powerpc/mm: Check memblock_add against MAX_PHYSMEM_BITS range With SPARSEMEM config enabled, we make sure that we don't add sections beyond MAX_PHYSMEM_BITS range. This results in not building vmemmap mapping for range beyond max range. But our memblock layer looks the device tree and create mapping for the full memory range. Prevent this by checking against MAX_PHSYSMEM_BITS when doing memblock_add. We don't do similar check for memeblock_reserve_range. If reserve range is beyond MAX_PHYSMEM_BITS we expect that to be configured with 'nomap'. Any other reserved range should come from existing memblock ranges which we already filtered while adding. This avoids crash as below when running on a system with system ram config above MAX_PHSYSMEM_BITS Unable to handle kernel paging request for data at address 0xc00a001000000440 Faulting instruction address: 0xc000000001034118 cpu 0x0: Vector: 300 (Data Access) at [c00000000124fb30] pc: c000000001034118: __free_pages_bootmem+0xc0/0x1c0 lr: c00000000103b258: free_all_bootmem+0x19c/0x22c sp: c00000000124fdb0 msr: 9000000002001033 dar: c00a001000000440 dsisr: 40000000 current = 0xc00000000120dd00 paca = 0xc000000001f60000^I irqmask: 0x03^I irq_happened: 0x01 pid = 0, comm = swapper [c00000000124fe20] c00000000103b258 free_all_bootmem+0x19c/0x22c [c00000000124fee0] c000000001010a68 mem_init+0x3c/0x5c [c00000000124ff00] c00000000100401c start_kernel+0x298/0x5e4 [c00000000124ff90] c00000000000b57c start_here_common+0x1c/0x520 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-21 08:31:57 +00:00
{
u64 max_mem = 1UL << (MAX_PHYSMEM_BITS);
if (base >= max_mem)
return false;
if ((base + *size) > max_mem)
*size = max_mem - base;
return true;
}
#else
static bool __init validate_mem_limit(u64 base, u64 *size)
powerpc/mm: Check memblock_add against MAX_PHYSMEM_BITS range With SPARSEMEM config enabled, we make sure that we don't add sections beyond MAX_PHYSMEM_BITS range. This results in not building vmemmap mapping for range beyond max range. But our memblock layer looks the device tree and create mapping for the full memory range. Prevent this by checking against MAX_PHSYSMEM_BITS when doing memblock_add. We don't do similar check for memeblock_reserve_range. If reserve range is beyond MAX_PHYSMEM_BITS we expect that to be configured with 'nomap'. Any other reserved range should come from existing memblock ranges which we already filtered while adding. This avoids crash as below when running on a system with system ram config above MAX_PHSYSMEM_BITS Unable to handle kernel paging request for data at address 0xc00a001000000440 Faulting instruction address: 0xc000000001034118 cpu 0x0: Vector: 300 (Data Access) at [c00000000124fb30] pc: c000000001034118: __free_pages_bootmem+0xc0/0x1c0 lr: c00000000103b258: free_all_bootmem+0x19c/0x22c sp: c00000000124fdb0 msr: 9000000002001033 dar: c00a001000000440 dsisr: 40000000 current = 0xc00000000120dd00 paca = 0xc000000001f60000^I irqmask: 0x03^I irq_happened: 0x01 pid = 0, comm = swapper [c00000000124fe20] c00000000103b258 free_all_bootmem+0x19c/0x22c [c00000000124fee0] c000000001010a68 mem_init+0x3c/0x5c [c00000000124ff00] c00000000100401c start_kernel+0x298/0x5e4 [c00000000124ff90] c00000000000b57c start_here_common+0x1c/0x520 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-21 08:31:57 +00:00
{
return true;
}
#endif
#ifdef CONFIG_PPC_PSERIES
/*
* Interpret the ibm dynamic reconfiguration memory LMBs.
* This contains a list of memory blocks along with NUMA affinity
* information.
*/
static int __init early_init_drmem_lmb(struct drmem_lmb *lmb,
const __be32 **usm,
void *data)
{
u64 base, size;
int is_kexec_kdump = 0, rngs;
base = lmb->base_addr;
size = drmem_lmb_size();
rngs = 1;
/*
* Skip this block if the reserved bit is set in flags
* or if the block is not assigned to this partition.
*/
if ((lmb->flags & DRCONF_MEM_RESERVED) ||
!(lmb->flags & DRCONF_MEM_ASSIGNED))
return 0;
if (*usm)
is_kexec_kdump = 1;
if (is_kexec_kdump) {
/*
* For each memblock in ibm,dynamic-memory, a
* corresponding entry in linux,drconf-usable-memory
* property contains a counter 'p' followed by 'p'
* (base, size) duple. Now read the counter from
* linux,drconf-usable-memory property
*/
rngs = dt_mem_next_cell(dt_root_size_cells, usm);
if (!rngs) /* there are no (base, size) duple */
return 0;
}
do {
if (is_kexec_kdump) {
base = dt_mem_next_cell(dt_root_addr_cells, usm);
size = dt_mem_next_cell(dt_root_size_cells, usm);
}
if (iommu_is_off) {
if (base >= 0x80000000ul)
continue;
if ((base + size) > 0x80000000ul)
size = 0x80000000ul - base;
}
powerpc/kernel: Enables memory hot-remove after reboot on pseries guests While providing guests, it's desirable to resize it's memory on demand. By now, it's possible to do so by creating a guest with a small base memory, hot-plugging all the rest, and using 'movable_node' kernel command-line parameter, which puts all hot-plugged memory in ZONE_MOVABLE, allowing it to be removed whenever needed. But there is an issue regarding guest reboot: If memory is hot-plugged, and then the guest is rebooted, all hot-plugged memory goes to ZONE_NORMAL, which offers no guaranteed hot-removal. It usually prevents this memory to be hot-removed from the guest. It's possible to use device-tree information to fix that behavior, as it stores flags for LMB ranges on ibm,dynamic-memory-vN. It involves marking each memblock with the correct flags as hotpluggable memory, which mm/memblock.c puts in ZONE_MOVABLE during boot if 'movable_node' is passed. For carrying such information, the new flag DRCONF_MEM_HOTREMOVABLE was proposed and accepted into Power Architecture documentation. This flag should be: - true (b=1) if the hypervisor may want to hot-remove it later, and - false (b=0) if it does not care. During boot, guest kernel reads the device-tree, early_init_drmem_lmb() is called for every added LMBs. Here, checking for this new flag and marking memblocks as hotplugable memory is enough to get the desirable behavior. This should cause no change if 'movable_node' parameter is not passed in kernel command-line. Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com> Reviewed-by: Bharata B Rao <bharata@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200402195156.626430-1-leonardo@linux.ibm.com
2020-04-02 19:51:57 +00:00
if (!validate_mem_limit(base, &size))
continue;
DBG("Adding: %llx -> %llx\n", base, size);
powerpc/kernel: Enables memory hot-remove after reboot on pseries guests While providing guests, it's desirable to resize it's memory on demand. By now, it's possible to do so by creating a guest with a small base memory, hot-plugging all the rest, and using 'movable_node' kernel command-line parameter, which puts all hot-plugged memory in ZONE_MOVABLE, allowing it to be removed whenever needed. But there is an issue regarding guest reboot: If memory is hot-plugged, and then the guest is rebooted, all hot-plugged memory goes to ZONE_NORMAL, which offers no guaranteed hot-removal. It usually prevents this memory to be hot-removed from the guest. It's possible to use device-tree information to fix that behavior, as it stores flags for LMB ranges on ibm,dynamic-memory-vN. It involves marking each memblock with the correct flags as hotpluggable memory, which mm/memblock.c puts in ZONE_MOVABLE during boot if 'movable_node' is passed. For carrying such information, the new flag DRCONF_MEM_HOTREMOVABLE was proposed and accepted into Power Architecture documentation. This flag should be: - true (b=1) if the hypervisor may want to hot-remove it later, and - false (b=0) if it does not care. During boot, guest kernel reads the device-tree, early_init_drmem_lmb() is called for every added LMBs. Here, checking for this new flag and marking memblocks as hotplugable memory is enough to get the desirable behavior. This should cause no change if 'movable_node' parameter is not passed in kernel command-line. Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com> Reviewed-by: Bharata B Rao <bharata@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200402195156.626430-1-leonardo@linux.ibm.com
2020-04-02 19:51:57 +00:00
memblock_add(base, size);
if (lmb->flags & DRCONF_MEM_HOTREMOVABLE)
memblock_mark_hotplug(base, size);
} while (--rngs);
return 0;
}
#endif /* CONFIG_PPC_PSERIES */
static int __init early_init_dt_scan_memory_ppc(void)
{
#ifdef CONFIG_PPC_PSERIES
const void *fdt = initial_boot_params;
int node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory");
if (node > 0)
walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb);
#endif
return early_init_dt_scan_memory();
}
/*
* For a relocatable kernel, we need to get the memstart_addr first,
* then use it to calculate the virtual kernel start address. This has
* to happen at a very early stage (before machine_init). In this case,
* we just want to get the memstart_address and would not like to mess the
* memblock at this stage. So introduce a variable to skip the memblock_add()
* for this reason.
*/
#ifdef CONFIG_RELOCATABLE
static int add_mem_to_memblock = 1;
#else
#define add_mem_to_memblock 1
#endif
void __init early_init_dt_add_memory_arch(u64 base, u64 size)
{
#ifdef CONFIG_PPC64
if (iommu_is_off) {
if (base >= 0x80000000ul)
return;
if ((base + size) > 0x80000000ul)
size = 0x80000000ul - base;
}
#endif
/* Keep track of the beginning of memory -and- the size of
* the very first block in the device-tree as it represents
* the RMA on ppc64 server
*/
if (base < memstart_addr) {
memstart_addr = base;
first_memblock_size = size;
}
/* Add the chunk to the MEMBLOCK list */
powerpc/mm: Check memblock_add against MAX_PHYSMEM_BITS range With SPARSEMEM config enabled, we make sure that we don't add sections beyond MAX_PHYSMEM_BITS range. This results in not building vmemmap mapping for range beyond max range. But our memblock layer looks the device tree and create mapping for the full memory range. Prevent this by checking against MAX_PHSYSMEM_BITS when doing memblock_add. We don't do similar check for memeblock_reserve_range. If reserve range is beyond MAX_PHYSMEM_BITS we expect that to be configured with 'nomap'. Any other reserved range should come from existing memblock ranges which we already filtered while adding. This avoids crash as below when running on a system with system ram config above MAX_PHSYSMEM_BITS Unable to handle kernel paging request for data at address 0xc00a001000000440 Faulting instruction address: 0xc000000001034118 cpu 0x0: Vector: 300 (Data Access) at [c00000000124fb30] pc: c000000001034118: __free_pages_bootmem+0xc0/0x1c0 lr: c00000000103b258: free_all_bootmem+0x19c/0x22c sp: c00000000124fdb0 msr: 9000000002001033 dar: c00a001000000440 dsisr: 40000000 current = 0xc00000000120dd00 paca = 0xc000000001f60000^I irqmask: 0x03^I irq_happened: 0x01 pid = 0, comm = swapper [c00000000124fe20] c00000000103b258 free_all_bootmem+0x19c/0x22c [c00000000124fee0] c000000001010a68 mem_init+0x3c/0x5c [c00000000124ff00] c00000000100401c start_kernel+0x298/0x5e4 [c00000000124ff90] c00000000000b57c start_here_common+0x1c/0x520 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-21 08:31:57 +00:00
if (add_mem_to_memblock) {
if (validate_mem_limit(base, &size))
memblock_add(base, size);
}
}
static void __init early_reserve_mem_dt(void)
{
unsigned long i, dt_root;
int len;
const __be32 *prop;
early_init_fdt_reserve_self();
early_init_fdt_scan_reserved_mem();
dt_root = of_get_flat_dt_root();
prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len);
if (!prop)
return;
DBG("Found new-style reserved-ranges\n");
/* Each reserved range is an (address,size) pair, 2 cells each,
* totalling 4 cells per range. */
for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
u64 base, size;
base = of_read_number(prop + (i * 4) + 0, 2);
size = of_read_number(prop + (i * 4) + 2, 2);
if (size) {
DBG("reserving: %llx -> %llx\n", base, size);
memblock_reserve(base, size);
}
}
}
static void __init early_reserve_mem(void)
{
__be64 *reserve_map;
reserve_map = (__be64 *)(((unsigned long)initial_boot_params) +
fdt_off_mem_rsvmap(initial_boot_params));
/* Look for the new "reserved-regions" property in the DT */
early_reserve_mem_dt();
#ifdef CONFIG_BLK_DEV_INITRD
/* Then reserve the initrd, if any */
if (initrd_start && (initrd_end > initrd_start)) {
memblock_reserve(ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
ALIGN(initrd_end, PAGE_SIZE) -
ALIGN_DOWN(initrd_start, PAGE_SIZE));
}
#endif /* CONFIG_BLK_DEV_INITRD */
if (!IS_ENABLED(CONFIG_PPC32))
return;
/*
* Handle the case where we might be booting from an old kexec
* image that setup the mem_rsvmap as pairs of 32-bit values
*/
if (be64_to_cpup(reserve_map) > 0xffffffffull) {
u32 base_32, size_32;
__be32 *reserve_map_32 = (__be32 *)reserve_map;
DBG("Found old 32-bit reserve map\n");
while (1) {
base_32 = be32_to_cpup(reserve_map_32++);
size_32 = be32_to_cpup(reserve_map_32++);
if (size_32 == 0)
break;
DBG("reserving: %x -> %x\n", base_32, size_32);
memblock_reserve(base_32, size_32);
}
return;
}
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static bool tm_disabled __initdata;
static int __init parse_ppc_tm(char *str)
{
bool res;
if (kstrtobool(str, &res))
return -EINVAL;
tm_disabled = !res;
return 0;
}
early_param("ppc_tm", parse_ppc_tm);
static void __init tm_init(void)
{
if (tm_disabled) {
pr_info("Disabling hardware transactional memory (HTM)\n");
cur_cpu_spec->cpu_user_features2 &=
~(PPC_FEATURE2_HTM_NOSC | PPC_FEATURE2_HTM);
cur_cpu_spec->cpu_features &= ~CPU_FTR_TM;
return;
}
pnv_tm_init();
}
#else
static void tm_init(void) { }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
static int __init
early_init_dt_scan_model(unsigned long node, const char *uname,
int depth, void *data)
{
const char *prop;
if (depth != 0)
return 0;
prop = of_get_flat_dt_prop(node, "model", NULL);
if (prop)
seq_buf_printf(&ppc_hw_desc, "%s ", prop);
/* break now */
return 1;
}
powerpc/64s: Save FSCR to init_task.thread.fscr after feature init At boot the FSCR is initialised via one of two paths. On most systems it's set to a hard coded value in __init_FSCR(). On newer skiboot systems we use the device tree CPU features binding, where firmware can tell Linux what bits to set in FSCR (and HFSCR). In both cases the value that's configured at boot is not propagated into the init_task.thread.fscr value prior to the initial fork of init (pid 1), which means the value is not used by any processes other than swapper (the idle task). For the __init_FSCR() case this is OK, because the value in init_task.thread.fscr is initialised to something sensible. However it does mean that the value set in __init_FSCR() is not used other than for swapper, which is odd and confusing. The bigger problem is for the device tree CPU features case it prevents firmware from setting (or clearing) FSCR bits for use by user space. This means all existing kernels can not have features enabled/disabled by firmware if those features require setting/clearing FSCR bits. We can handle both cases by saving the FSCR value into init_task.thread.fscr after we have initialised it at boot. This fixes the bug for device tree CPU features, and will allow us to simplify the initialisation for the __init_FSCR() case in a future patch. Fixes: 5a61ef74f269 ("powerpc/64s: Support new device tree binding for discovering CPU features") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200527145843.2761782-3-mpe@ellerman.id.au
2020-05-27 14:58:42 +00:00
#ifdef CONFIG_PPC64
static void __init save_fscr_to_task(void)
{
/*
* Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we
* have configured via the device tree features or via __init_FSCR().
* That value will then be propagated to pid 1 (init) and all future
* processes.
*/
if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
init_task.thread.fscr = mfspr(SPRN_FSCR);
}
#else
static inline void save_fscr_to_task(void) {}
powerpc/64s: Save FSCR to init_task.thread.fscr after feature init At boot the FSCR is initialised via one of two paths. On most systems it's set to a hard coded value in __init_FSCR(). On newer skiboot systems we use the device tree CPU features binding, where firmware can tell Linux what bits to set in FSCR (and HFSCR). In both cases the value that's configured at boot is not propagated into the init_task.thread.fscr value prior to the initial fork of init (pid 1), which means the value is not used by any processes other than swapper (the idle task). For the __init_FSCR() case this is OK, because the value in init_task.thread.fscr is initialised to something sensible. However it does mean that the value set in __init_FSCR() is not used other than for swapper, which is odd and confusing. The bigger problem is for the device tree CPU features case it prevents firmware from setting (or clearing) FSCR bits for use by user space. This means all existing kernels can not have features enabled/disabled by firmware if those features require setting/clearing FSCR bits. We can handle both cases by saving the FSCR value into init_task.thread.fscr after we have initialised it at boot. This fixes the bug for device tree CPU features, and will allow us to simplify the initialisation for the __init_FSCR() case in a future patch. Fixes: 5a61ef74f269 ("powerpc/64s: Support new device tree binding for discovering CPU features") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200527145843.2761782-3-mpe@ellerman.id.au
2020-05-27 14:58:42 +00:00
#endif
void __init early_init_devtree(void *params)
{
phys_addr_t limit;
DBG(" -> early_init_devtree(%px)\n", params);
/* Too early to BUG_ON(), do it by hand */
if (!early_init_dt_verify(params))
panic("BUG: Failed verifying flat device tree, bad version?");
of_scan_flat_dt(early_init_dt_scan_model, NULL);
#ifdef CONFIG_PPC_RTAS
/* Some machines might need RTAS info for debugging, grab it now. */
of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
#endif
#ifdef CONFIG_PPC_POWERNV
/* Some machines might need OPAL info for debugging, grab it now. */
of_scan_flat_dt(early_init_dt_scan_opal, NULL);
/* Scan tree for ultravisor feature */
of_scan_flat_dt(early_init_dt_scan_ultravisor, NULL);
#endif
#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
/* scan tree to see if dump is active during last boot */
of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
#endif
/* Retrieve various informations from the /chosen node of the
* device-tree, including the platform type, initrd location and
* size, TCE reserve, and more ...
*/
of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
/* Scan memory nodes and rebuild MEMBLOCKs */
early_init_dt_scan_root();
early_init_dt_scan_memory_ppc();
/*
* As generic code authors expect to be able to use static keys
* in early_param() handlers, we initialize the static keys just
* before parsing early params (it's fine to call jump_label_init()
* more than once).
*/
jump_label_init();
parse_early_param();
/* make sure we've parsed cmdline for mem= before this */
if (memory_limit)
first_memblock_size = min_t(u64, first_memblock_size, memory_limit);
setup_initial_memory_limit(memstart_addr, first_memblock_size);
/* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START);
2008-08-30 01:43:47 +00:00
/* If relocatable, reserve first 32k for interrupt vectors etc. */
if (PHYSICAL_START > MEMORY_START)
memblock_reserve(MEMORY_START, 0x8000);
reserve_kdump_trampoline();
#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
/*
* If we fail to reserve memory for firmware-assisted dump then
* fallback to kexec based kdump.
*/
if (fadump_reserve_mem() == 0)
#endif
reserve_crashkernel();
early_reserve_mem();
/* Ensure that total memory size is page-aligned. */
limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
memblock_enforce_memory_limit(limit);
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES)
if (!early_radix_enabled())
memblock_cap_memory_range(0, 1UL << (H_MAX_PHYSMEM_BITS));
#endif
memblock: s/memblock_analyze()/memblock_allow_resize()/ and update users The only function of memblock_analyze() is now allowing resize of memblock region arrays. Rename it to memblock_allow_resize() and update its users. * The following users remain the same other than renaming. arm/mm/init.c::arm_memblock_init() microblaze/kernel/prom.c::early_init_devtree() powerpc/kernel/prom.c::early_init_devtree() openrisc/kernel/prom.c::early_init_devtree() sh/mm/init.c::paging_init() sparc/mm/init_64.c::paging_init() unicore32/mm/init.c::uc32_memblock_init() * In the following users, analyze was used to update total size which is no longer necessary. powerpc/kernel/machine_kexec.c::reserve_crashkernel() powerpc/kernel/prom.c::early_init_devtree() powerpc/mm/init_32.c::MMU_init() powerpc/mm/tlb_nohash.c::__early_init_mmu() powerpc/platforms/ps3/mm.c::ps3_mm_add_memory() powerpc/platforms/embedded6xx/wii.c::wii_memory_fixups() sh/kernel/machine_kexec.c::reserve_crashkernel() * x86/kernel/e820.c::memblock_x86_fill() was directly setting memblock_can_resize before populating memblock and calling analyze afterwards. Call memblock_allow_resize() before start populating. memblock_can_resize is now static inside memblock.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "H. Peter Anvin" <hpa@zytor.com>
2011-12-08 18:22:08 +00:00
memblock_allow_resize();
memblock_dump_all();
DBG("Phys. mem: %llx\n", (unsigned long long)memblock_phys_mem_size());
/* We may need to relocate the flat tree, do it now.
* FIXME .. and the initrd too? */
move_device_tree();
DBG("Scanning CPUs ...\n");
dt_cpu_ftrs_scan();
// We can now add the CPU name & PVR to the hardware description
seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
/* Retrieve CPU related informations from the flat tree
* (altivec support, boot CPU ID, ...)
*/
powerpc/64: Move paca allocation to early_setup() The early paca and boot cpuid dance is complicated and currently does not quite work as expected for boot cpuid != 0 cases. early_init_devtree() currently allocates the paca_ptrs and boot cpuid paca, but until that returns and early_setup() calls setup_paca(), this thread is currently still executing with smp_processor_id() == 0. One problem this causes is the paca_ptrs[smp_processor_id()] pointer is poisoned, so valid_emergency_stack() (any backtrace) and any similar users will crash. Another is that the hardware id which is set here will not be returned by get_hard_smp_processor_id(smp_processor_id()), but it would work correctly for boot_cpuid == 0, which could lead to difficult to reproduce or find bugs. The hard id does not seem to be used by the rest of early_init_devtree(), it just looks like all this code might have been put here to allocate somewhere to store boot CPU hardware id while scanning the devtree. Rearrange things so the hwid is put in a global variable like boot_cpuid, and do all the paca allocation and boot paca setup in the 64-bit early_setup() after we have everything ready to go. The paca_ptrs[0] re-poisoning code in early_setup does not seem to have ever worked, because paca_ptrs[0] was never not-poisoned when boot_cpuid is not 0. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> [mpe: Fix build error on 32-bit] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20221216115930.2667772-4-npiggin@gmail.com
2022-12-16 11:59:29 +00:00
of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
if (boot_cpuid < 0) {
printk("Failed to identify boot CPU !\n");
BUG();
}
powerpc/64s: Save FSCR to init_task.thread.fscr after feature init At boot the FSCR is initialised via one of two paths. On most systems it's set to a hard coded value in __init_FSCR(). On newer skiboot systems we use the device tree CPU features binding, where firmware can tell Linux what bits to set in FSCR (and HFSCR). In both cases the value that's configured at boot is not propagated into the init_task.thread.fscr value prior to the initial fork of init (pid 1), which means the value is not used by any processes other than swapper (the idle task). For the __init_FSCR() case this is OK, because the value in init_task.thread.fscr is initialised to something sensible. However it does mean that the value set in __init_FSCR() is not used other than for swapper, which is odd and confusing. The bigger problem is for the device tree CPU features case it prevents firmware from setting (or clearing) FSCR bits for use by user space. This means all existing kernels can not have features enabled/disabled by firmware if those features require setting/clearing FSCR bits. We can handle both cases by saving the FSCR value into init_task.thread.fscr after we have initialised it at boot. This fixes the bug for device tree CPU features, and will allow us to simplify the initialisation for the __init_FSCR() case in a future patch. Fixes: 5a61ef74f269 ("powerpc/64s: Support new device tree binding for discovering CPU features") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200527145843.2761782-3-mpe@ellerman.id.au
2020-05-27 14:58:42 +00:00
save_fscr_to_task();
#if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
/* We'll later wait for secondaries to check in; there are
* NCPUS-1 non-boot CPUs :-)
*/
spinning_secondaries = boot_cpu_count - 1;
#endif
mmu_early_init_devtree();
#ifdef CONFIG_PPC_POWERNV
/* Scan and build the list of machine check recoverable ranges */
of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
#endif
epapr_paravirt_early_init();
/* Now try to figure out if we are running on LPAR and so on */
pseries_probe_fw_features();
/*
* Initialize pkey features and default AMR/IAMR values
*/
pkey_early_init_devtree();
#ifdef CONFIG_PPC_PS3
/* Identify PS3 firmware */
if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3"))
powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
#endif
/* If kexec left a PLPKS password in the DT, get it and clear it */
plpks_early_init_devtree();
tm_init();
DBG(" <- early_init_devtree()\n");
}
#ifdef CONFIG_RELOCATABLE
/*
* This function run before early_init_devtree, so we have to init
* initial_boot_params.
*/
void __init early_get_first_memblock_info(void *params, phys_addr_t *size)
{
/* Setup flat device-tree pointer */
initial_boot_params = params;
/*
* Scan the memory nodes and set add_mem_to_memblock to 0 to avoid
* mess the memblock.
*/
add_mem_to_memblock = 0;
early_init_dt_scan_root();
early_init_dt_scan_memory_ppc();
add_mem_to_memblock = 1;
if (size)
*size = first_memblock_size;
}
#endif
/*******
*
* New implementation of the OF "find" APIs, return a refcounted
* object, call of_node_put() when done. The device tree and list
* are protected by a rw_lock.
*
* Note that property management will need some locking as well,
* this isn't dealt with yet.
*
*******/
/**
* of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
* @np: device node of the device
*
* This looks for a property "ibm,chip-id" in the node or any
* of its parents and returns its content, or -1 if it cannot
* be found.
*/
int of_get_ibm_chip_id(struct device_node *np)
{
of_node_get(np);
while (np) {
u32 chip_id;
/*
* Skiboot may produce memory nodes that contain more than one
* cell in chip-id, we only read the first one here.
*/
if (!of_property_read_u32(np, "ibm,chip-id", &chip_id)) {
of_node_put(np);
return chip_id;
}
np = of_get_next_parent(np);
}
return -1;
}
EXPORT_SYMBOL(of_get_ibm_chip_id);
/**
* cpu_to_chip_id - Return the cpus chip-id
* @cpu: The logical cpu number.
*
* Return the value of the ibm,chip-id property corresponding to the given
* logical cpu number. If the chip-id can not be found, returns -1.
*/
int cpu_to_chip_id(int cpu)
{
struct device_node *np;
int ret = -1, idx;
idx = cpu / threads_per_core;
if (chip_id_lookup_table && chip_id_lookup_table[idx] != -1)
return chip_id_lookup_table[idx];
np = of_get_cpu_node(cpu, NULL);
if (np) {
ret = of_get_ibm_chip_id(np);
of_node_put(np);
if (chip_id_lookup_table)
chip_id_lookup_table[idx] = ret;
}
return ret;
}
EXPORT_SYMBOL(cpu_to_chip_id);
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
#ifdef CONFIG_SMP
/*
* Early firmware scanning must use this rather than
* get_hard_smp_processor_id because we don't have pacas allocated
* until memory topology is discovered.
*/
if (cpu_to_phys_id != NULL)
return (int)phys_id == cpu_to_phys_id[cpu];
#endif
return (int)phys_id == get_hard_smp_processor_id(cpu);
}